分类归档 dhrtf

1. Sit in the water and watch the frying rustle. Hand side a bowl of tea without any reason, just this feeling to love the people who love tea. -Tang Bai Juyi’s "Mountain Spring Fried Tea is pregnant"

2. Only the water is heard in the piano, and the old tea is Mengshan. -Tang Bai Juyi’s "Qin Tea"

3. who, prizing money first, careless how he left her, had gone, a month before, to Fuliang to buy tea. -Tang Bai Juyi’s Pipa Trip

4. One or two scoops of tea at night, and three counts of autumn songs. -Bai Juyi’s "beginning of autumn has a dream in the evening"

5. leave the porridge and cold porridge, and cook new tea on the fire. -Bai Juyi’s "Send Wei Shi to the Imperial Court on Qingming Day"

6. Ye Zhaoren is a summer hairpin, and Songhua is full of bowls to try new tea. -Tang Liu Yuxi’s "Send Li Langzhong to his post"

7. Poetry tea helps cool, and medicinal wine can be declared. -Tang Liu Yuxi’s "Rewarding Lotte for Leisure"

8. Where the world is like a fairyland, when Chunshan picks tea with prostitutes. -Tang Liu Yuxi’s "Five Slogans of Xing Wu to Send Han Qi Zhong Cheng from Luozhong"

9. I want to go home for five days, and I am invited by the public in three spring. Tea stove depends on green bamboo shoots, and the chess game is a heart. -Tang Liu Yuxi’s "Forty Rhymes of Dr. Li’s Dream in West Zhejiang and the Fair Pay and Brilliant Sound in East Zhejiang"

10. Mo Chen bakes tea with dark smoke, but he likes to bask in the sunny valley. -Tang Zhangji’s "Mountain Home"

11. Tea cakes are fragrant when chewed, and smoke condenses at the place where water sinks. -Tang Li Tao "Spring Day Palindrome"

12. The deer is firmly guarded against hunters, and the tea pot is filled with monks. -Tang Du Xunhe’s "Kasugayama has something to do with snow"

13. Sun medicine keeps the bamboo house warm, and pounding tea makes the courtyard deep. -Tang Huangfu Ran’s "Looking for Chu Shi"

14.tea Fragrant leaves, tender buds. Poets love monks. -Tang Yuan-zhen’s "17 Orders, Tea"

15. Shenggong said that Taiwan is empty, and Lu Yu’s tea well does not exist. -Gu Feng’s Title Tiger Hill

16. Under the bamboo, I forgot to talk about the purple tea, and I won the victory. -Tang Qian Qi "Tea Banquet with Zhao Ju"

17. Yunnuan picks tea to Lingbei, and Yueming sells wine to Xinan. -Tang Du Mu’s "Shihan Village in Huaimao Mountain in Autumn Night"

18. Take a trip with tea in the twelfth lunar month, and there are articles about illness in Maoling. -Tang Du Mu’s "Visit the Golden Cave of Linquan Temple in Chizhou"

19. In the afternoon, there was no sound, and Shan Tong knocked on the tea mortar across the bamboo. -Tang Liu Zongyuan’s "Summer Day Occasionally"

20. Reading is not as good as classics, and drinking is not as good as tea. -Tang Gaoshi’s "Stay in Kaizenji with the same group and give Chen Sixteen’s residence"

21. The road is long with wine, but it is sleepy, and the Japanese people are thirsty for tea. -Song Sushi’s "Huanxisha Rustling Clothes and Towels Falling Jujube Flowers"

22. Strive for new pets, each with his own intention. This year, we will fight for official tea. -Su Shi’s Litchi Tan

23. Don’t miss your old country and try new tea with new fire. Poetry and wine take advantage of time. -Song Sushi’s "Looking at Jiangnan, Transcendent Taiwan"

24. It has been changed to frying tea fire, and it is still transferred to porridge. -Song Sushi’s "Nan Gezi Late Spring"

25. It’s spring soon, so I’d like to knock on Chai Men for a cup of tea. -Song Xie Fangde’s "Looking for Tea"

26. The wine cellar is more fond of the bitter tea, and the dream is broken. -Song Qingzhao, "Partridge Days, Cold Days, Rustling on the Window"

27. In those days, I won the prize, smoked my sleeves, and divided my tea with a lively fire. -Song Qingzhao’s "Turning Man Tingfang Fangcao Pond"

28. Laughter and sophistry, live fire to cook new tea. -Li Qingzhao’s Xiao Meng

29. Cardamom is fried with water, so don’t divide tea. -Song Qingzhao’s "Breaking the Huanxisha, Sick and Rustling"

30. bring a bottle of water from the heart of the river, and try to make tea first. -Song Yang Wanli’s Two Songs of Crossing the Yangtze River

31. It is better to divide tea than to fry tea, and frying tea is not as clever as dividing tea. -Yang Wanli’s "Sitting on the Temple in the Temple and Sharing Tea"

32. brew tea, a new test of water, is clear in the world and travels outside things. -Song Zhao Changqing’s "Man Tingfang, Late Color Shen Shen"

33. Stay young and have a drink, then go to brew tea and Yangzhou Crane. -Song Xin Qiji’s "Man Jiang Hong and Fan Xian’s Snow"

34. Sigh and forget the past, and whoever sleeps will have tea in the afternoon. -Lu You’s "Living in the Early Summer"

35. The short paper is idle for grass, and the window is fine and the milk is divided into tea. -Song Luyou’s "Lin ‘an Spring Rain"

36. Grain Rain is known by the tea from the mountain temple, and it’s clear to others that the willow is planted. -Lu You’s "Spring Day, Spring Come Day, Sleepy Spring Village"

37. Camellia is fragrant and tender, and wild fruit is sweet and cold. -Lu You’s Reading Su Shu Party’s Poems in the Northern Mountain of Ruzhou, with its rhyme and form in a hundred years.

38. Qingming Jiangmei Village sells, which is praised by Grain Rain Chaxiang Courtyard. -Lu You’s "Wandering around, Going to the Store through the Monks"

39. It’s really old to travel all over the world. Worry without sleep, a few wisps of tea smoke in the temples. -Lu You’s "Fisherman’s Pride, Sending High"

40. Half a tea bowl for morning porridge and a cloth for autumn clothes. -Song Luyou’s "Sickness Reduction and Recovery"

41. The children are full of poems and books, but the men read and cook spring tea. -Song Huang Tingjian’s "Send Wang Lang"

42. Unknown Dongguo Qingming wine is like Grain Rain tea in the west window. -Song Huang Tingjian’s "See Twenty Brothers Advocating Peace and Flower Words Manxing Five Poems, Falling Flocculation and Spring in March"

43. When you get old, it is like a sick wine in spring. Only a small curtain of tea is fragrant. -Song Xin Qiji’s "Dingfengbo, Hunchun Manxing"

44. Today, I occasionally come to the monk, but I’m here, cooking tea and eating Lushan Mountain. -Song Fangyue, "Summer is not mixed, only weeding vegetables and armor can also hinder leisure"

45. From the beauty of the tea valley, I know the true face of Lushan Mountain. -Song Fangyue’s "Old Sex Causes Lushan Tea"

46. Yesterday, Grain Rain, the former effect, put a tea flag, and the wine pool was turned three times. -Song Xiang Anshi’s "Uncle Born in Korea"

47. Sweep loose pre-made Qingming wine, and rent Grain Rain tea before entering the gorge. -Song Dai Fugu’s "Dream before Qingming Festival"

48. Tea and cigarettes quietly stroke the harp crane, while Grain Rain hoes the wheat in a light cage. -Song Wang Yucheng’s "Farewell with Chen Zhoutian Scheeren, New Iced Wicker in Huaiyang"

49. Grain Rain has beautiful bamboo shoots and tea, and all kinds of flowers and chrysanthemums compete with each other. -Song Liuguo "Spring is the thing, no one asks for a long time"

50. Poems are written about the beautiful moon, and tea is fried in the rain and spring. -Song Huang Geng’s "The Guest"

51. Tea seedlings seal Grain Rain, and books send apples to the wind. -Song Wangchen’s "Jian Zhang Bo He"

52. No ally, fry more Grain Rain tea. -Song Yeyin’s "Dojo Garden Ten Mu"

53. On a cold night, guests come to tea as wine, and the bamboo stove soup turns red at the beginning. -Song Du Lei "Cold Night"

54. It’s cold in Grain Rain, tea and cigarettes are blooming, and it’s peony time again. -Song Chen Yunping, "Passing Qin Lou Grain Rain to Receive Cold"

55. Grain Rain Chunjiang dusk, tea smoke Xiao Si sunny. -Song Chen Yunping’s "Reward Comrade"

56. The little maid cries the autumn rain before the lamp, but the bamboo house doesn’t see tea at night. -Song Lin Jingxi’s "Crying De and Bo’s Six Poems, Empty Legacy and Broken Inkstone, Lonely Heart and Bitterness"

57. It’s hard to stick to a pen, knock on the bed and make tea. -Qing Dashu’s "Twilight Snow"

58. The chicken flew over the fence and the dog barked, knowing that a merchant had come to buy tea. -Song Fan Chengda’s "Late Spring Pastoral Miscellaneous"

59. Mid-autumn moon is yellow again, and after the end of the year, tea will be served in the afternoon. -Song Fan Chengda’s "Posting the West Lake and Sending the Pure Kindness to Show the Old Three Unique Mid-Autumn Moon and Yellow Flowers"

60. The secluded people in the forest save trouble, and the tea stove on the pen bed will board the boat. -Song Ye Shaoweng’s "Your Tour"

61. Go to Chachuan, and it will be sunny in Grain Rain for the first time. -Song Liao Rong’s "Book Wubin House Wall"

62. After the peach blossoms want to release a breeze, the tea buds are newly supplied to Grain Rain. -Song Li Xu Ji "Seeing the Pure Land with Runan Scholar"

63. Flowers are clear and flowers are near, and tea is ahead of Grain Rain. -Song Huang Yanping’s "Two Poems of Tian Jia Chun Ri Chi Ri Fang Zhong Cao"

64. If Yuyao falls, it is especially praised by the Tea Classics. -Song Sunyin "More Questions, More Tea"

65. It’s sunny when the wind flies, and the tea affair exclaims to explore the new fire. -Song Cheng Gongxu’s "Four Poems of Visiting Haiyun Temple on Qingming Day, It’s Clear and Clear on a Windy Day"

66. Chun Qing Grain Rain Tea in March. -Song Wu Shan’s "Qinhuai Boat Collection with Mrs. Liu and Li"

67. Close the tea-scented floating snow house, and push the window and the mountain shadow to drop curling. -Song Chen wrote "Occasionally, did you ever ask if you have a livelihood?"

Source: Gaoxian Women’s Federation

Editor: Liu Li

Editor: Liu Qin

Approved by: Wang Xifeng

END

Welcome to scan the QR code below to pay attention to "Gaozhou Women" WeChat official account. We will continue to release information about women’s participation in economic construction and social development in Gaoxian County, and the representation and protection of women’s interests and the promotion of gender equality by Gaoxian Women’s Federation. Thank you for your attention! ! !

Keep sliding to see the next one.

67 ancient poems about tea, poetic and tea-loving, sent to Gaozhou women who love tea and touched the original text.

Gaozhou women like sharing, reading and writing messages, sliding up to see the next one.

Original title: "67 ancient poems about tea, poetic and tea-loving, sent to tea lovers"

Read the original text

CCTV News:On July 24th, News Network and other columns reported good news such as the increase of summer grain production in China, the improvement of the quality and efficiency of central enterprises’ operation, and the continuous warming of the "cultural and cultural fever" in summer. There are many bright spots of "thriving" in many fields, which shows the vigorous development of China.

Summer grain production increased by 7.25 billion Jin, the largest increase in recent 9 years.

On the morning of July 24th, the reporter learned from the press conference of the State Council Press Office that this year’s summer grain production increased by 7.25 billion Jin, the largest increase in summer grain production in recent nine years, which has obvious effects on stabilizing prices and stabilizing people’s expectations. According to reports, there are two main reasons for the bumper harvest of summer grain this year. First, the area has stabilized. Last year, all localities actively responded to the unfavorable conditions of autumn sowing and realized that all kinds should be planted. The area of wheat harvested in summer was 346 million mu, an increase of 475,000 mu on the historical high. Second, the yield per unit area has increased. Improving the yield per unit area requires a close combination of improved varieties, fertile fields, good opportunities and good laws, and at the same time, there must be good policies. The minimum purchase price of summer grain wheat has increased this year, which has stabilized farmers’ expectations.

In the first half of the year, the quality and efficiency of central enterprises improved.

The reporter learned from the State-owned Assets Supervision and Administration Commission of the State Council that in the first half of this year, the production and operation of central enterprises made steady progress, with good quality and efficiency, achieving a total profit of 1.4 trillion yuan, up 1.9% year-on-year, and the annualized labor productivity and R&D investment intensity of all employees increased steadily year-on-year. In the next step, the proportion of income and added value of strategic emerging industries of state-owned central enterprises will be further increased.

The "Guangdong-Yunnan-Lanzhou-Meizhou Line" international freight train officially started.

On July 24th, the international freight train of "Guangdong-Yunnan-Lanzhou-Meizhou Line", an international freight corridor connecting Guangdong, Yunnan and Southeast Asian countries, was officially launched. Goods from Guangdong-Hong Kong-Macao Greater Bay Area are connected to China-Laos Railway Lanmei Express Line through domestic express trains, which can go directly to Bangkok, Thailand, and the transportation time of the whole line is shortened by two to three days.

The contracted exhibition area of the 7th China International Import Expo(CIIE) Enterprise Exhibition has exceeded 360,000 square meters.

On the occasion of the 100-day countdown to the 7th China International Import Expo, China International Import Expo Bureau held a news briefing on July 24th to introduce that the 7th China International Import Expo(CIIE) will be held in Shanghai from November 5th to 10th this year. Up to now, more than 50 countries and international organizations have confirmed their participation, and the contracted exhibition area has exceeded 360,000 square meters.

At the same time, the Seventh Hongqiao Forum will hold the main forum and several sub-forums with the theme of "persisting in high-level opening up and promoting inclusive economic globalization".

This year’s China International Import Expo(CIIE) Enterprise Exhibition continues the six exhibition areas of food and agricultural products, automobiles, technical equipment, consumer goods, medical devices, medical care and service trade, and strives to create an innovation incubation area. The work of organizing trade delegations and professional visitors has been accelerated, and the progress is faster than that of the same period last year. It is expected that more professional visitors will participate in the 7th China International Import Expo(CIIE).

"Wenbo fever" continues to heat up in summer.

With the opening of summer vacation, the ever-rising "Wenbo fever" has become a beautiful tourist landscape. Faced with the strong demand for cultural tourism, many museums in China have carried out a series of beneficial explorations in canceling real-name reservation and extending opening hours, and launched a number of special activities to bring visitors a different exhibition experience.

More than 90% of Sanxingdui’s cultural relics made their debut.

"Ingenuity — — The exhibition of newly unearthed cultural relics protection and restoration achievements at Sanxingdui site was held in Sanxingdui Museum in Guanghan, Sichuan on July 23rd. More than 50 pieces of bronze, gold and jade unearthed from Sanxingdui site are exhibited in the exhibition, all of which are the results of the protection and restoration of the newly unearthed cultural relics in Sanxingdui in the past year, and more than 90% of them are the first time to appear.

Since June, the search popularity of "museums" has increased by 61% from the previous month.

The data shows that the search popularity of "museums" on the platform has increased by 61% since June, among which Xi ‘an, Beijing, Shanghai, Chengdu and Wuhan have become the five cities with the highest search popularity, and the phenomenon of "one appointment is hard to find" in popular museums has reappeared. In order to better meet the needs of tourists in summer vacation, many cultural and art venues have entered "daylight saving time", and measures such as not closing on Mondays, delaying opening and adjusting reservation policies have been implemented.

The "upgrade" of the museum provides an immersive exhibition experience for the audience.

In order to cope with the peak of summer passenger flow, major museums "show their magical powers" and continue to enhance the audience’s exhibition experience. The Sanxingdui Museum introduces a digital display system, and visitors can experience the ancient and mysterious Sanxingdui civilization by means of the interaction between high technology and ancient Shu culture. The National Museum of Classics allows children to experience the colorful picture book world, sit on the grass of the tropical rain forest, watch animals play in front of their eyes, cross the Antarctic world day and night, and feel the changes of time; China national film museum has specially added a movie dubbing experience pavilion for the summer vacation to attract young people to increase their scientific wisdom and artistic accomplishment through interactive practice.

According to industry insiders, "understanding a city and entering a museum first" has become the consensus of many tourists. Behind the "cultural craze" is the "traditional culture craze", especially the young people’s strong interest in traditional culture, including overseas tourists’ curiosity and exploration of Chinese culture.

　　China Daily Online, September 30th According to a report on the website of the US Capitol Hill newspaper on the 29th, inflation is not the only reason for the rising prices of food and clothing in the United States. Shoplifting incidents that are out of control continue to occur, making the bills that people can’t bear even higher. The U.S. government’s failure to crack down on retail theft is unfair to hard-working American families who are trying to pay for daily necessities and save money for the future, which has caused many obstacles for them to realize their "American dream."

　　According to related reports, in 2021 alone, shoplifting in the United States caused nearly $100 billion in losses to retailers, and every American could feel the price. However, federal lawmakers and prosecutors chose to refuse to hold criminals accountable, which made the situation worse.

　　Screenshot of the US Capitol Hill website report

　　The report pointed out that many police departments in the United States are seriously short of funds and manpower, and the "Defund the police movement" aggravated this trend, which made the police team demoralized and frustrated the recruitment work. This year, due to the "serious" shortage of manpower, the Boston Police Department issued an urgent appeal for recruiting new police for the second time in its history. As expected, the number of police patrolling in a specific area is directly related to the violent crime rate, which makes communities with insufficient police force more vulnerable to theft, shooting and other crimes.

　　At the same time, prosecutors in crime-prone areas refused to put people’s safety first. In Washington, D.C., for example, federal prosecutors in the region openly refused to prosecute nearly 70% of people arrested in 2022. Most of the cases he ignored involved gun possession, drug possession and burglary charges. Similarly, the Manhattan district attorney’s office revealed in 2022 that it only accepted two cases against a serial thief, who was a serial pickpocket who committed 23 different thefts.

　　The article points out that there is no doubt that crimes in all parts of the United States are in a period of high incidence. In the past three years, property crimes, motor vehicle theft and robbery cases in cities including Washington, D.C. have increased sharply. This uncontrolled crime wave and the coexistence of retail theft at a record high are causing a devastating blow to American retailers.

　　Dick’s Sporting Goods lost 23% of its profits in the second quarter due to theft, so families who buy sports necessities for their children at the company may soon see prices soar. Target and Home Depot have suffered similar shoplifting consequences all over the United States.

　　Thieves ransacked Nord stron Department Store in the United States. Figure: Network screenshot

　　Simple and everyday shopping behavior is becoming a thing of the past in America. Due to rampant theft, a grocery store in Washington, D.C. is planning to empty all American national brands from its health and beauty shelves. Shoppers will no longer be able to buy Tide or Colgate, and they will have to show their receipts to employees before leaving the store. Giant’ S) President Ira Kress said: "We hope to continue to serve the community, but we can’t bring great losses or risks to our employees like today."

　　Gabriel Nadales, the author of the article and the national director of Our America, said that American politicians are abandoning the American people in this crisis-level store theft. He pointed out that it is high time for members of Congress to re-engage and actively and comprehensively solve this problem by re-examining the budget priorities, providing funds to the police and replacing prosecutors who are unwilling to perform their duties. Lawmakers need to persistently implement policies to encourage the American criminal justice system to protect American citizens dutifully so that they can continue to pursue the American dream.

　　In a recent report, USA-Today website quoted John Gerzema, CEO of Harris Polling Company, as saying: "Their organization conducted an online survey of more than 2,000 American adults at the end of August, and the American public who were asked said that they could not realize the American dream like their parents and grandparents, because this dream could not be realized. At the same time, young Americans are facing unprecedented challenges, such as the climate crisis and unprecedented political differences.

Family, today’s test drive of Aouita 12, this steering wheel is almost "bright blind"! When I saw the octagon, my heart tightened. Can this be reliable? However, after going on the road, I was amazed at the comfortable grip, and the automatic heating function instantly warmed my hands and heart. The steering is ridiculously accurate, as if the car follows the heart. The big screen is almost unobstructed, and the field of vision is so wide that I think I am flying a plane. Cool!

The second half of the big model welcomes the CAMBRIAN Agent explosion.

540 million to 360 million years ago, marine life broke, and higher-level intelligence such as trilobites, sponges and chordates was born compared with previous single-celled or simple multicellular organisms. Similar to the CAMBRIAN explosion of life, experimental products such as BabyGPT, AutoGPT and Generative Agents have come out one after another.

From the perspective of evolution, the development of life is mainly realized by unit enhancement and organization enhancement. These two ways of enhancement complement each other, making life have more diverse and complex expressions.

Just like agent-we hope it is an agent that can think independently and interact with the environment in any system.

Now that it has a "brain" with enough IQ, how to make Agent think and execute like a human being-as long as any goal is given, it can automatically solve various problems. It is a "self" unit to further improve IQ and enhance agents; Or strengthen the "organizational" ability with the help of external modules?

Although today’s Agent can’t complete the general task, it is also difficult to form a dynamic stable body like the socialized division of labor among multiple cells. However, the local modules of individual Agents, such as HuggingGPT, have demonstrated their ability to use tools, including the fact that Plug-in has become an important milestone in the actual landing. In the second half of the large model, it will be the moment when the agent landed in Cambrian.

Where is the landing bottleneck of Agent at this moment? Can it reach GM from dedicated? What will multimodal bring to Agent? How will the future pattern evolve?

Just like the first cell born on the earth, even though the current Agent can’t replace our role in practical work, everything comes from this first cell, which is the starting point of agent evolution.

Even if you are confused about the landing of Agent, you should continue to "emerge".

Because the success or failure of Agent will be the key to decide whether this GPT revolution is a new generation of industrial revolution.

The following will think in a structured way, and where will Agent go?

1. What exactly is AI Agent?

A few days ago, the AI Town with 25 agents was officially open source, and the "westworld" AI Town was built with it. The interaction between AI Agents will deduce the evolution process of the whole civilization.

Andrej Karpathy, co-founder of OpenAI, also shouted: "AI Agent represents a crazy future."

What is an Agent? The word Agent originated from the Latin word Agere, which means "to do".In the context of LLM, Agent can be understood as an agent that can independently understand, plan and make decisions and perform complex tasks.

Agent is not an upgraded version of ChatGPT. It not only tells you how to do it, but also helps you to do it. If CoPilot is the co-pilot, then the Agent is the main driver.

A simplified Agent decision-making process, using function expression:

Agent: p (perception)-—> P (planning)-> a (action)

Similar to the process of human "doing things", the core function of Agent can be summarized as a cycle of three steps:perception（Perception）, planning（Planning）And action（Action）.

perception（Perception）Refers to the ability of Agent to collect information from the environment and extract relevant knowledge from it, planning（Planning）Refers to the decision-making process and action made by Agent for a certain goal.（Action）Refers to actions based on environment and planning.

Among them, Policy is the core decision of Agent to make Action, and action is observed.（Observation）It becomes the premise and foundation of further Perception and forms an independent closed-loop learning process.

This process is like Marxism’s "theory of practice": "Understanding begins with practice, through which theoretical understanding is obtained, and then returns to practice." Agent also evolved in the integration of knowledge and practice.

A more complete Agent must fully interact with the environment, which includes two parts-one is the Agent part, and the other is the environment part.At this moment, Agent is like "human" in the physical world, and the physical world is the "external environment" of human beings.

As you can imagine, the process of human interaction with the external environment: based on our full perception of the world, we deduce its hidden state, and combine our own memory and knowledge understanding of the world to make Planning, decision-making and action; And actions will react to the environment, giving us new feedback, and human beings will combine the observation of feedback and then make decisions, so as to go back and forth.

The most intuitive formula:

Agent = LLM+Planning+Feedback+Tool use

Among them, in the process of Planning, in addition to the current state, there are also memories, experiences, some reflections and summaries of the past, as well as world knowledge.

Compared with today’s ChatGPT, it is actually not an Agent, but a universal world knowledge, that is, a knowledge source for Planning. It is not based on specific environmental conditions, nor is it based on Memory, Experience and Reflection.

Of course, ChatGPT can do logical reasoning and certain planning based on its own knowledge, and it can also add vector database to solve reasoning problems, and add Reflection to enrich the process. In this way, ChatGPT, an end-to-end black box, can be made more explicit-in fact, symbols are a very explicit system, and based on this, it can be directionally corrected and promoted.

For Feedback, Agent gets positive or trial-and-error feedback, phased results or rewards based on Action. There are many forms of Feedback. If ChatGPT chatting with us is regarded as an Agent, the reply we typed in the text box is a kind of Feedback, just a kind of Feedback in text form. At this time, we are an environment for ChatGPT. RLHF is also an environment, an extremely simple environment.

"Man is human because he can use tools."

As an Agent, agent can also extend its functions with the help of external tools, so that it can handle more complex tasks. For example, LLM uses weather API to obtain weather forecast information. If you don’t call external tools, Action and Feedback can also deal with the environment directly by learning Policy.

It can be seen that Agent is the key to truly release LLM’s potential actively. As the core of LLM, Agent provides subjective initiative for LLM.

How to land the LLM today? LLM is an IQ engine, and other peripheral tools can be used as Prompt. Will LLM be an end-to-end system in the future? If there are not enough tools around, will there be a more general adaptation framework?

Second, the bottleneck of Agent landing is because "IQ" is not enough?

Agent itself uses two parts of abilities, one is LLM as its "intelligence quotient" or "brain" part, the other is based on LLM, and it needs a controller outside to complete various Prompt, such as enhancing Memory through retrieval, getting Feedback from the environment, and how to do Reflection.

Agent needs both brain and external support.

Is LLM’s own "intelligence quotient" not enough or its external systematization not enough?

If the degree of external systematization is not enough, it will be a long-awaited problem. If it’s just a problem of insufficient IQ, when GPT-4 becomes GPT-5 and has a higher IQ, it can make up for the previous problems.

So what is the main bottleneck of Agent?

To truly understand the crux of this problem, we can make wrong attribution first.That is to say, in the actual mistakes, it is clearly attributed to LLM itself or Prompt in the wrong way.

For example, ask the voice assistant "What’s the weather like?" The question itself is ambiguous-where is the weather? What day’s the weather? What information do you want to know about the weather? None of these problems can be solved by LLM itself, and it needs to call an external tool system.

If it is only attributed to "IQ", LLM only needs to understand "what’s the weather like". If there is a specific context, such as "what’s the weather like in Shanghai next month", whether LLM can infer accurate information based on this is a question of "IQ"; But what tools to call and whether the parameters to execute are accurate are not attributed to "IQ".

3. Can a more general external framework of Agent be realized in the future?

Many people regard LLM as the implementation of Agent, which is too simple and rude. For example, after setting a goal for Agent and defining some basic constraints, we expect it to complete the whole process of self-planning, task decomposition, self-prompting, and even calling external tools and giving answers. However, LLM itself is not trained in this way, and it certainly does not have this ability, but this is not due to the "IQ" problem.

From the perspective of Agent landing, external logical framework is still needed.

Although there are many kinds of Agent at present, most of them are superficial and not universal enough. Even the simplest Agent application, voice assistant or intelligent outgoing call system, its complexity and how to introduce environmental Feedback have not been effectively solved.

Therefore, in addition to a more detailed analysis of the errors, one question we should study is: Besides LLM itself being universal enough, will a universal external logic framework be realized to solve the problem of Agent’s real landing?

If we can’t find a common external logical framework, then the so-called AGI revolution may be just a bubble, a huge bubble, which may not be essentially different from the previous generation NLP.

At present, the landing of Agent is not only a question of "intelligence quotient", but also a question of how to get from special to general by external tools-and this is a more important question.

4. How can Agent have a universal adaptive environment? Do you need a learnable environment model?

What will happen if LLM is put into a virtual world?

In the game My World, NVIDIA developed the latest method, Voyager, to light up the technology tree at a speed of 15.3 times, and at the same time, he obtained 3.3 times of unique items and 2.3 times of exploration scope. The reason is attributed to GPT-4′ s in-depth understanding of the rules of the game and rich knowledge reserve, which comes from the pre-training process rather than the subsequent reinforcement learning.

From this perspective, in the process of optimizing Agent, we should not only pay attention to Feedback, but also consider how the model perceives the environment. So what is the relationship between the general brain and the environmental model, and how to cooperate? How does Agent arrive at General from Private?

At present, there are few good and universal landing effects of Agent, and most of them solve specific problems in specific scenes-LLM is used as a general brain and designed into different roles through Prompt to complete special tasks, rather than universal applications.

One of the key problems, namely, Feedback, will become a major constraint factor in the implementation of Agent, which is particularly evident in Tool use. For some simple problems such as weather query, it is only necessary to design an appropriate Prompt, but for complex Tools applications, its success probability will be greatly reduced.

It is impossible to make an Agent with LLM simply and rudely.

On the one hand, this approach ignores the importance of Feedback, on the other hand, even if LLM gets Feedback, it may not fully understand all the environments or Feedback by virtue of its "IQ", and it is even more difficult to adjust its behavior based on this.

In order to successfully land the Agent, it is necessary to give the Agent a more general adaptive environment. One possible solution is to create a small model dedicated to understanding and adapting the environment, so as to interact with LLM.

Because of super brain’s "IQ" part-LLM(such as GPT-4)Because the scale is too large, it is difficult to retrain specific Agent, and the small model can adapt to environmental changes and train many times. In this scene, we can regard LLM as the brain, and the small model is like the cerebellum, which acts as the middle layer to deal with the environment Feedback and interact with GPT-4.

So, what will be the implementation path of Agent from private to general?

Assuming that Agent will eventually land in 100 different environments, can a framework model be abstracted to solve all external universality problems under the premise that even the simplest external application is difficult to realize at present?

It may be one of the ways to realize the universal Agent by making the Agent in a certain scene to the extreme-stable and robust enough, and then gradually turning it into a universal framework.

5. How important is multimodal in the development of Agent?

Now GPT-4 is to convert all the contents into text language, and then human beings will Prompt it. First of all, the transformation process may lose information or produce errors, which may lead to the deviation of the results.

The next version of GPT, if it can realize the super ability of multimodal understanding, will it alleviate the unreliability and information loss and deviation of today’s Agent to some extent? What will be the relationship between multimodal and Agent?

If LLM does not need to interact in the real world, but only performs a specific task in the virtual world, then multimodal may not be very helpful for completing the task. But if LLM needs to interact with the real world, then multimodal is undoubtedly very important.

Multimodal can only solve the problem of Agent’s perception, but not the problem of cognition.

In many cases, such as intelligent customer service scenarios, users may provide information in a variety of ways. Multimodal has good perceptual value, but it is still far from solving some core problems such as logic and reasoning.

Multimodal is an inevitable trend, the future big model must be a multimodal big model, and the future Agent must also be an Agent in a multimodal world.

When developing text-based agents, when the multi-modal watershed moment comes, do these agents continue to develop on the basis of the original text and further integrate multi-modal characteristics? Or do you need to completely change the original concept and architecture of developing Agent to adapt to the future multimodal world?

The development of Agent does not need to be completely reinvented, but once Agent has multi-modal ability, it will be completely different from the existing model. For example, the next generation version of GPT may contain some more powerful multimodal understanding functions such as images. We don’t have to rush to build such a model immediately, but we can also choose to call such a module first, that is, it is best to build the multimodal understanding function into the model.

After half a year, we will see the arrival of multi-modal large models. The arrival of multimodal Agent may be faster than we thought.

First of all, many large companies are developing multimodal in general by stockpiling arms. The accumulation of this quantitative change is very likely to lead to qualitative change, and actual products may be launched soon. Secondly, the Agent people expect is an assistant like human beings. He can not only talk, but also see, hear and feel. Theoretically, an excellent Agent should be able to realize multi-sensory and multi-modal interaction, and both Perception and Policy need multi-modal.

With the release of RT-2, a new visual language action model, VLA, has realized the ChatGPT of the entity robot by stuffing the multi-modal large model into the manipulator. ?

From the trend point of view, the future Agent must be multimodal. Multi-modality must be necessary for Agent to succeed.

In the aspect of multimodal interaction, Digital Man also provides a good example, which shows the advantages of calling external tools. When the big model calls digital people, because the images have been set in advance, we don’t have to worry that it will suddenly generate the image or voice of a political figure, even his illusion.

Although it is euphemistically called "generative AI", it is better to call external tools in its "generative" part to ensure its certainty and avoid the illusion of the big model.

For example, in multimodal interaction, if you want LLM to play Trump and directly generate a congratulatory video, it is likely to be risky. It is safer and more controllable if LLM only generates scripts and then calls the established digital human and sound interface to synthesize video.

6. Will multi-agent really succeed?

Now the Agent is still a caveman, but the interaction of more AI Agents will change everything.

In the Generative Agents experiment inspired by the simulated life game, each role is controlled by an AI Agent, and they live and interact in a sandbox environment, which fully embodies the process of turning feedback and environmental information into action and realizing the "socialization" of AI Agents.

In the process of planning and response, AI Agents will fully consider the relationship between each other and the observation and feedback of one Agent to another Agent to take the next step.

This interesting simulation has led to some dramatic social phenomena, such as the spread of "rumors" and relational memory. In the experiment, two AI Agents often continue their previous topics, hold Party, call friends and other social activities.

Obviously, the real landing of Agent must be based on the perception of environment, dynamic learning and continuous updating.

7. In what scene did Agent first land?

As early as February this year, some online education companies began to be active in the discussion of big models. "Our industry, if we don’t act again, will be the first to be subverted." When most companies haven’t felt the impact of the big model, people from a head online education company first make predictions and worries.

And which industries will be subverted by Agent first, and which industries will not be so fast?

The ability of large model is well known, but "IQ" is only a part of the landing of Agent. Even if OpenAI claims that AGI has come, it is difficult to make practical applications if you know nothing about the industry.

Just like a doctor at Stanford, if you don’t understand the industry and product attributes of a company, then the initial work will be very difficult. Therefore, we need to discuss more deeply which industries are more suitable for Agent landing.

For example, the online education industry that can be completely online and digital, especially during the past three years, many offline industries have been hit, while the online industry has developed rapidly because of the advantages of digitalization, and it will be subverted by Agent first. In contrast, robots or traditional industries are more difficult to be subverted in a short time.

At present, whether in China or the United States, a new consensus is gradually forming: firstly, Agent needs to call external tools, and secondly, the way to call tools is to output codes-LLM brain outputs an executable code, such as a semantic analyzer, which understands the meaning of each sentence, then converts it into a machine instruction, and then calls external tools to execute or generate answers.

Although the present form of Function Call needs to be improved, this way of calling tools is very necessary and the most thorough means to solve the illusion problem.

8. Will the future development pattern of Agent be a hundred flowers blossom or Winners take all?

In the future, the competition pattern of big models is becoming increasingly clear, and it is inevitable that several companies will dominate or be based on open source.

And in the next year or two, what will be the market structure of Agent, and will it form the same situation?

Because Agent can’t be universal, Agent is not a monopoly, but will form a very long tail supplier pattern. There will be many Agent in the market, each of which is operated by a different company.

Like the previous generation NLP, many AI companies provide intelligent customer service or automatic outbound service, but each company can only serve a few customers and cannot form scale effect. Based on the technical judgment of Agent today, it is not much different from the previous generation.

Although the semantic understanding of LLM is universal, the combination of Agent environment and domain we discussed before is not universal, which will lead to a very scattered market, and no stronger company will appear.

Of course, Agent is also divided into depth.(major)And shallowness(universal)Two types.

We want to be a general Agent. In the market environment of China, if an Agent is deeply integrated with the enterprise, it will eventually become "outsourcing" because it needs to be privatized and integrated into the enterprise workflow. Many companies will compete for big customers in insurance companies, banks and automobiles. This will be very similar to the outcome of the previous generation AI company, and the marginal cost is difficult to reduce, and it is not universal.

The future is the world of Agent. Under the Agent process today, the story of AI yesterday is still repeated, and the privatization deployment will face challenges.

This article comes from WeChat WeChat official account:Brother Fei said AI (AI(ID：FeigeandAI), author: Gao Jia

　　[Looking back at the "Thirteenth Five-Year Plan" and enjoying new achievements]

　　"Our days are getting better and better, the community is clean and tidy, and the management is standardized and orderly. It is very comfortable to live in such an environment." In winter, although the weather is getting cold, Wang Min, who lives in Kangxingyuan Community, Cuntan Street, Jiangbei District, Chongqing, looks at the changes in the community and feels warm in her heart.

　　In recent years, the process of urbanization has accelerated, and the contradiction of residential property has gradually become prominent, which has increasingly become a shortcoming of urban grassroots governance. In some places, property conflicts once accounted for 70% of the total number of letters and visits.

　　How to solve this problem? "Jiangbei District adheres to the guidance of party building as the main line, integrates the party’s leadership into all aspects of property community governance, and explores ‘ Strengthen the guidance of party building, persist in resolving according to law, guide residents’ autonomy, and strengthen effective supervision ’ Working methods, get through to serve the masses ‘ The last 100 meters ’ 。” The main person in charge of the organization department of Jiangbei District Committee said that most of the difficulties encountered by the masses can be solved without leaving the community, and the continuous resolution of property conflicts has effectively improved the sense of acquisition and happiness of the masses.

　　It is more direct to serve the masses from "breakpoint" to "contact"

　　"Everyone trusts you. If you can be elected as the branch secretary and elected to the industry Committee, the masses will be more at ease." At the beginning, Ling Chiang, secretary of Dongjiaxi Community, found the owner Zhou Rong many times and wanted to invite her to participate in the community management.

　　"I have done management work before, but I have been retired for many years and it is difficult to participate in community governance." Zhou Rong always refuses. "Don’t be too busy to refuse me. We are fully combining the party branch setting with the residential building, building the party branch into the residential area and building the party group into the building. Now it is more convenient and direct to serve the residents." After several exchanges, Zhou Rong promised to transfer the organizational relationship from the original unit to the community and run for the post of Party branch secretary of the community to serve the residents of the community.

　　"In the past, there was no single party branch or party group in Jinxiu Beibin Community, and community party organizations went to the property community to become ‘ Breakpoint ’ 。” Ling Chiang said, the first thing to carry out party building to lead and resolve the contradiction of residential property is to build the party branch in the residential area and the party group in the building, and at the same time establish the party branch in the industry Committee and the property management company to build a "community party Committee — Community Party Branch — Building Party Group+Property Party Branch "mode, so that the building and the community party member can contact and coordinate to solve the building and community affairs. After the establishment of the Party branch of Jinxiu Beibin Community, four party groups were established with the building as the unit, and party member, a member of the industry committee, served as the leader of the party group.

　　At present, there are 19 Party branches in Jinxiu Beibin Community in party member, and the establishment of Party-Mass Post Stations in each building not only ensures a place for party member’s study and activities, but also gives the owners a place for discussion and leisure.

　　Change from "disorder" to "order" and do practical things according to the law and regulations

　　"oriental home Community has more than 8,000 permanent residents and is also an old community with concentrated houses." Yang Mingying, a resident of the community, told the reporter that with the aging of the community, property conflicts arose and accumulated, especially when the term of office of the fourth industry Committee expired, the original industry Committee could not perform its duties normally, resulting in some contradictions being resolved in time.

　　"The urgent task is to elect a new industry committee. We have learned the lessons from the unsuccessful last change. This change was promoted in accordance with the property regulations from the beginning. " Li Shengquan, secretary of the Party Working Committee of Huaxin Street, said. Street community party organizations intervened in advance, and guided and supervised the election of industry committees in accordance with the "six-step work method" of organizing publicity, selecting representatives, collecting applications, setting up special classes, preparing for the conference, and electing according to law.

　　"The regulations are well-known and the community is shared harmoniously. We went home to publicize the newly revised property management regulations, which were distributed by one household to help residents learn the law in their lives, find the law when they encounter problems, and solve problems by law. " Gou Yingrong, secretary of the Party Committee of oriental home Community, said that during the election process, the opinions and suggestions put forward by the owners were sorted out and investigated, and they were solved one by one through door-to-door visits and joint meeting research, thus winning the trust. Finally, a new industry committee was successfully elected according to law. Among the five members of the industry committee, there were 3 party member and 2 people, and the newly elected director of the industry committee was the secretary of the community party branch, achieving "one shoulder and one shoulder".

　　"The selection of the industry committee is the starting point, not the end point. Next, we will lead the community industry committee and the property company to accomplish the practical things they promised to do and build a harmonious and beautiful livable home." Yan Yingrong said.

　　Change from "incurable" to "autonomous". The masses participate in mass affairs.

　　"Parking in the community is too messy. It has been many years ‘ An incurable disease ’ 。” Shengli Garden Community is a typical rural-to-non-resettlement community, and the phenomenon of disorderly parking of vehicles is prominent, which brings hidden dangers to the safety of residents in the community.

　　"Only by letting residents manage their own affairs and play the role of masters can we truly build a beautiful and happy home that residents are satisfied with." In order to solve the parking problem, Zou Saixia, a member of Tieshanping Street Committee, was appointed as the first secretary of the community, and a working group for resolving property conflicts headed by the first secretary was set up. The industry committee and the property management company were combined to "receive issues" through various channels, and many parties earnestly talked about "ideas", discussed and organized "plans", posted a list to make public the way, specially reviewed "conventions", and residents voted "final decisions". In the end, the community formed a "two stops and three stops" parking convention (unilateral parking, parking spaces, non-stop fire exits, non-stop sidewalks, non-stop corners), and the property management company added 350 parking spaces on the road in the community, which not only solved the parking difficulties, but also allowed the fire exits to be used normally.

　　"After the establishment of the industry Committee, we not only solved the difficulty of parking, but also established rules and regulations in time to let autonomy run on the institutional track. At present, we have solved seven problems, such as throwing objects at high altitude and not lighting street lamps." Zhang Qizheng, director of the Industry Committee of Shengli Garden Community, said that the community has initially formed an autonomous network of "community-led autonomy, community autonomy and residents’ participation in autonomy", and has embarked on a road of community mass autonomy led by party organizations.

　　 (Reporter Zhang Guosheng Li Hong)

CCTV News:On September 7th, the Propaganda Department of the CPC Central Committee held a series of press conferences on the theme of "Ten Years in China", introducing the development achievements of health care since the 18th CPC National Congress and answering questions from reporters.

Li Bin, deputy director of the National Health and Wellness Committee, said that National Health Commission has conscientiously implemented the decision-making arrangements made by the CPC Central Committee and the State Council, taken measures together with relevant departments, and paid close attention to implementation. The main goal of the Healthy China Action in 2022 was achieved ahead of schedule, and the construction of a healthy China started well and progressed smoothly.

First, the policy system of promoting health has been basically established. The Health China Action Promotion Committee was established, and an expert advisory committee was set up to explore the establishment of a health impact assessment system, forming a working pattern of departmental collaboration and linkage among provinces, cities and counties.

Second, knowledge has entered thousands of families, and the "two libraries and one mechanism" for health science popularization has been gradually built. Establish a national health science expert database and resource database, and an all-media health science knowledge release and dissemination mechanism to fully popularize health knowledge.

The third is to pay attention to the whole cycle, and the health maintenance ability has been significantly improved. The per capita subsidy standard for basic public health services has been raised to 84 yuan. For patients with hypertension, diabetes, tuberculosis and other key diseases and 0-mdash; 6-year-old children, pregnant women and elderly people over 65 provide health management services. Comprehensive prevention and control of myopia in children and adolescents has been solidly promoted, and the physical health of students has gradually improved. Major diseases have been effectively curbed, and the premature mortality rate of major chronic diseases is lower than the global average.

Fourth, life is healthier and the production and living environment continues to improve. Healthy lifestyle has become a new fashion, and the health literacy level of residents has increased to 25.4%; The area of sports venues is constantly increasing, and the proportion of people who regularly participate in physical exercise reaches 37.2%. The urban living environment has improved significantly, and the ratio of days with excellent air quality has continued to increase; Rural sanitation has taken on a new look, and the penetration rate of tap water and sanitary toilets has steadily increased.

Fifth, with the participation of the whole people, the atmosphere of "Healthy China Action" is getting stronger and stronger. "Co-construction and sharing, health for all" is the strategic theme of building a healthy China. Vigorously advocate "everyone is the first responsible person for their own health", forming a good social atmosphere for everyone to pursue and maintain health.

CCTV News:Shenzhou 16 manned mission is China’s 11th manned space flight. Since China’s first astronaut, Yang Liwei, became the first China visitor in the vast space in 2003, Chinese has made nine trips to space, and 16 China astronauts have visited space. Next, let’s review the 20-year manned space dream-chasing process from Shenzhou 5 to Shenzhou XV.

one.China astronauts entered space for the first time.

On October 15th, 2003, Yang Liwei flew into the sky on the Shenzhou 5, and the Chinese nation’s dream of flying for a thousand years came true. China has become the third country in the world to master manned space technology independently, and since then, there has been a touch of China red in space.

2.China began to realize "multi-person and multi-day" space flight.

On October 12th, 2005, astronauts Fei Junlong and Nie Haisheng successfully completed the five-day mission aboard Shenzhou VI, which indicated that China had the key technology of multi-person and multi-day on-orbit flight.

three.China astronauts carried out space extravehicular activities for the first time.

On September 25th, 2008, astronauts Zhai Zhigang, Liu Boming and Jing Haipeng flew into space on Shenzhou VII. Zhai Zhigang successfully carried out China’s first extravehicular activity and took the first step of Chinese’s extravehicular walk. This mission broke through and mastered the technology of space extravehicular activity.

four.The first hand-controlled rendezvous and docking, the first female astronaut into space

On June 16th, 2012, Shenzhou IX sent astronauts Jing Haipeng, Liu Wang and Liu Yang into space, and Liu Yang became the first female astronaut in China. During the mission, the first manned space rendezvous and docking and hand-controlled rendezvous and docking were successfully implemented, which was a key step towards building a space station.

five.China held the first space lecture.

On June 11th, 2013, Shenzhou 10 embarked on a journey, which was the first applied flight of manned space flight in China. Astronauts Nie Haisheng, Zhang Xiaoguang and Wang Yaping completed the first space lecture in Tiangong-1 during their 15-day mission, and Wang Yaping became the first space teacher in China.

six.China astronauts completed their mid-term stay mission.

On October 17th, 2016, astronauts Jing Haipeng and Chen Dong were launched on Shenzhou XI and stationed in Tiangong-2, successfully completing their 33-day mission, achieving their mid-term in-orbit stay for the first time, laying a foundation for the construction and operation of China’s space station.

seven.Chinese entered his own space station for the first time.

On June 17th, 2021, the Shenzhou XII manned spacecraft was launched and docked with the Tianhe core module to form an assembly. Astronauts Nie Haisheng, Liu Boming and Tang Hongbo successively entered the core module, which was the first time that Chinese entered his own space station. During the three-month in-orbit flight, he successfully completed two extravehicular activities and appeared in the sky for the first time in a new generation of "Feitian" extravehicular spacesuit independently developed by China.

eight.First verification of long-term in-orbit residency capability

On October 16th, 2021, the Shenzhou XIII manned spacecraft was launched, and the astronauts Zhai Zhigang, Wang Yaping and Ye Guangfu flew in orbit for 183 days, which was the first time to verify the long-term in-orbit staying ability of the astronauts on the space station mission. In the meantime, they conducted two "Tiangong Classroom" space lectures and two extravehicular activities, and Wang Yaping took the first step of China women’s cabin walking in outer space. The successful manned mission of Shenzhou XIII marks the perfect conclusion of the key technology verification phase of China Space Station.

nine.Complete the basic configuration of the space station "T"

On June 5, 2022, the space station welcomed three astronauts, Chen Dong, Liu Yang and Cai Xuzhe, from Shenzhou 14. With the arrival of the experiment module of candlestick and the experiment module of dream, they ushered in the historic moment when the basic configuration of "T" of China Space Station was assembled, and opened the "three-bedroom" era of Chinese space.

10.The first space rendezvous was completed in China’s space station.

On November 30th, 2022, three astronauts of Shenzhou XV, Fei Junlong, Deng Qingming and Zhang Lu, entered the China Space Station, and the two astronauts joined the team for the first time.

During the mission, China Space Station was officially completed and entered a new stage of application and development. In addition, the Shenzhou 15 crew completed four outbound missions, making it the most frequent flight crew.

With the coming of Shenzhou 16, China Space Station will once again usher in the historical moment of six astronauts’ on-orbit handover. This is the first manned mission in the application and development stage of the space station, and we look forward to a new record of manned space flight in China.

Sogou input method and Microsoft input method are better to evaluate and compare;

Both sogou and Microsoft have their own computer input methods, and the market share of these two input methods is also very high, so which one is more useful for users who have installed input methods for the first time on computers? Let’s introduce it to you through this article and read it together!

Sogou pinyin input method is an old-fashioned intelligent pinyin input method, which was launched by Sohu in June 2006. Mainly used for Chinese pinyin input under Windows platform. Beautiful and rich personalized skin is a highlight of sogou, and tens of thousands of cell dictionaries provide the most possible candidate words.

1. After entering the names of festivals and solar terms, a prompt will appear in the upper right corner of the input box, such as telling you when the Spring Festival is this year;

2. Long sentence association function, which can supplement commonly used or classic sentences immediately after you enter a few Chinese characters.

3. Support traditional input function. Press "ctrl+shift+F" or directly switch between traditional and simplified characters on the status bar to input traditional Chinese characters.

4. The Chinese-English mixed input function is more pleasing, and English words can be directly input when inputting Chinese without switching between Chinese and English.

5. You can quickly insert a date, and you can insert today’s date only by entering "Date" or "rq".

6. The mispronounced prompt function can correct you when you enter the wrong pinyin, and it will also display the correct vocabulary, as follows

7. Enter the emoji, click Properties-Advanced-Custom Phrase-Add New Definition, and then you can set it.

8. The split input function is very practical, and you can easily input words you don’t know, as follows.

9, convenient weather, constellation query, as long as you enter "weather" or "tq", you can see the local weather on the day in the input box.

10. The common symbol input function will display "& radical;" when "Pair" is input. Symbol, if you enter "triangle", the "△" symbol will appear, and if you enter "lying gun", the funny "_ (:з"∠ )_”

11. The basic method of sogou input method is to right-click the input method status bar and select "Change Skin".

Microsoft Pinyin Input Method adopts Pinyin as the input method of Chinese characters, and adopts the sentence-based whole sentence conversion method, so that users can continuously input the pinyin of whole sentences. Microsoft Pinyin input method has a richer lexicon, supports automatic dictionary updating and shared extended dictionary platform, and provides customized online search. At the same time, it provides two mainstream input styles: new experience and simplicity, without manual word segmentation and selection of candidate words.

1. Quick-quick and sensitive response

Microsoft pinyin input method is quick to start, quick to respond, and available at any time.

2, accurate-accurate and smooth typing

Microsoft pinyin input method is based on intelligent pinyin conversion of massive knowledge base, which allows you to type words smoothly, accurately and carefree.

3, wonderful-typing at will

Microsoft Pinyin Input Method provides two input styles of "new experience" and "simplicity" to meet different input habits.

4. There are too many words.

Microsoft pinyin input method supports rich professional dictionaries, and you can make it a convenient tool for inputting professional documents.

5, Qiao-Qiao hit and search.

Microsoft Pinyin Input Method supports customizable online search queries and searches for keywords at any time.

Well, that’s all that Xiaobian brings to you about the question "Which is better, Microsoft Pinyin or sogou Input Method". I believe that through this article introduction, you should have a brand-new understanding and hope to help you.