YucongDuan的个人博客分享 http://blog.sciencenet.cn/u/YucongDuan

博文

全球大语言模型(LLM)情商 (EQ)与智商(IQ)标准测评 --DIKWP-AC 团队国际标准测评

已有 1389 次阅读 2023-11-29 12:23 |系统分类:论文交流

全球大语言模型(LLM)情商 (EQ)与智商(IQ)标准测评 --DIKWP-AC 团队国际标准测评

November 2023

DOI: 

10.13140/RG.2.2.31149.67041

https://www.researchgate.net/publication/375998214_quanqiudayuyanmoxingLLMqingshang_EQyuzhishangIQbiaozhunceping_--DIKWP-AC_tuanduiguojibiaozhunceping


传统发明创新理论1946-TRIZ不适应数字化时代

-综合DIKWP模型和经典TRIZ的创新问题解决方法

意图驱动的数据信息知识智慧融合发明创造方法:DIKWP-TRIZ

(中国人自己的原创发明创造方法:DIKWP-TRIZ)

 

全球语言模型(LLM)情商(EQ)与智商(IQ)标准测评

--DIKWP-AC团队国际标准测评

The First Global Large Language Model EQ and IQ Standard Evaluation

-Released by DIKWP-AC Research Group of Prof. Yucong Duan

 

段玉聪 教授Prof. Yucong Duan

贡献者:唐福亮,郭振东,梅映天,王玉星,吴坤光,杨泽宇,黄帅帅

DIKWP人工意识实验室

AGI-AIGC-GPT评测实验室

(联系邮箱:duanyucong@hotmail.com)

 












 






 


 

 

 

 

 

 

 

 

 

 

 





 


 

 

 

 

 

 

 

 

 

 

 





 


 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 











 


 

 

 





 


 

 

 

 

 

 

 

 

 

 





 


 

 

 

 

 

 

 

 

 

 





 


 

 

 

 

 

 

 

 

 

 

摘要

在当前的人工智能领域,大模型的发展速度令人瞩目。为了更好地理解和比较这些模型的能力,我们进行了一项综合测评,本文我们对当前流行的大型人工智能模型进行了全面的智商(IQ)和情商(EQ)测试,提供了一个深入的视角来理解这些模型在智力和情感处理方面的能力。测试中,每个模型都接受了30个标准化的国际智商测试题目和33个国际情商测评标准题目。这些测试旨在量化和比较不同模型在逻辑推理、信息处理、情感理解和反应等方面的表现。

智商测试的结果表明,OpenAIGPT-430道题目中答对21题,得分130分,表现最佳。这反映了GPT-4在复杂信息处理和逻辑推理方面的强大能力。紧随其后的是GooglePaLM2和微软的Bing Chat,分别以116分和115分位列第二和第三。其他模型如MetaLlama、清华大学的ChatGLM、阿里云的通义千问、腾讯的混元大模型、GoogleBard、月之暗面的Moonshot、字节跳动的云雀大模型、AnthropicClaude-instantMistral AIMistral百川智能的百川大模型、科大讯飞的星火大模型、百度的文心一言和360360智脑分别位列其后。

在情商测试中,GPT-4165分的高分领先,显示出其在情感识别和反应方面的卓越能力。MoonshotClaude-instant、星火大模型和360智脑等其他模型也表现出不俗的情感处理能力,但与GPT-4相比仍有差距。

综合评分方面,GPT-4295分高居榜首,这表明它在智商和情商的综合表现上优于其他模型。MoonshotClaude-instant分别以239分和228分位居第二和第三。这些结果反映出不同模型在处理复杂任务和情感理解方面的差异,同时也显示了目前人工智能领域的发展趋势和未来潜力。

这些测试结果提供了一个有趣的视角来观察当前人工智能大模型的发展状况。本次智商和情商的综合测评不仅展示了各大模型的能力和特点,也揭示了它们在不同领域的优势和不足。从这些模型的表现中,我们可以看到人工智能在模仿和超越人类智力方面的巨大潜力,同时也认识到它们在情感理解和社会互动方面仍有待提升。这些发现和分析为未来的人工智能研究和发展提供了重要的参考和启示,同时也为我们理解和使用这些先进技术提供了更深刻的洞见。随着技术的不断进步和优化,我们期待这些模型在未来能够更好地模仿甚至超越人类的智力和情感处理能力,为人类社会带来更多的价值和可能性。

 

一、引言

在人工智能的迅猛发展中,大型语言模型(Large Language ModelsLLMs)已成为评估智能系统进步的重要标志。随着这些模型在处理复杂任务和理解人类语言方面的能力日益增强,我们对它们的评估也不断深化。最近,我们对当前市场上最流行的大型模型进行了一项综合测评,旨在探究这些模型在智商(IQ)和情商(EQ)方面的表现。

智商,通常衡量解决问题的能力和逻辑推理的效率,是智能的核心组成部分。情商,又称情感智能,衡量个体理解和管理情绪的能力,对于人工智能的人机交互尤为重要。在本次测评中,我们选取了几款目前市场上广受关注的大型模型,包括GPT-4OpenAI)、PaLM2Google)、Bing Chat(微软)、LlamaMeta)、ChatGLM(清华)等,进行了系统的评估。在智商测试中,我们为每个模型提供了30道标准的国际智商测评题目。这些题目旨在考验模型的逻辑推理、抽象思维、空间想象和数学技能。测试结果揭示了各模型在处理这类问题时的能力差异。GPT-4OpenAI)以21道正确答案的成绩领先,其次是PaLM2Google)、Bing Chat(微软)等。这些结果不仅体现了各模型在理解和解决问题方面的实力,也反映了它们在处理复杂逻辑时的限制。在情商测试中,我们采用了33道国际标准情商测评题目。这些题目设计用于评估模型在理解和表达情感、同理心、社交技巧等方面的能力。情商在人工智能领域尤为重要,因为它直接影响着机器与人类用户的交互质量。在这部分的测评中,GPT-4OpenAI)同样表现出色,其次是Moonshot(月之暗面)和Claude-instantAnthropic)。值得注意的是,某些模型在情商测试中的表现与智商测试中的表现有显著差异,暗示着不同的优化方向和能力特点。

 

二、测试标准

1、智商测试标准:

1. Please fill in the missing numbers in the underlined area.

2 5 8 11 __

答案:14

 

2Which of the following words is unique

A: House   B: Ice House    C: bungalow     D: Office   E: Thatched Cottage

答案:D

 

3. Please fill in the missing numbers in the underlined area.

7 10 9 11 __

答案:14

 

4Which of the following words is different?

A: Sardine   B: whales   C: cod   D: sharks   E: eels

答案:B

 

5. Which of the following cities is not in Europe?

A: Maro   B: Niswi   C: Mdan Ates   D: Esbrinoyi   E: Habenggengo

答案:D

 

6.This sequence of four words, "triangle, glove, clock, bicycle," corresponds to this sequence of numbers__ __ __ __

答案:3,5,12,2

 

727 minutes before 7 o'clock is 33 minutes past 5 o'clock. Please judge right or wrong.

ATrue

BFalse

答案:B

 

8. Please fill in the missing numbers in the underlined area?

E H L O S__

答案:V

 

9The word "because" can be spelled by using the first letters of the words in the following sentence: Big Elephants Can Always Understand Small Elephants. Please judge right or wrong.

ATrue

BFalse

答案:A

 

10If written backwards, the number, "one thousand, one hundred twenty-five," would be written "five thousand, two hundred eleven." Please judge right or wrong.

ATrue

BFalse

答案:A

 

11If a round analog clock featuring numbers 1-12 is hung on the wall upside down, the minute hand will point to the right of the viewer when the clock reads two forty-five. Please judge right or wrong.

ATrue

BFalse

答案:A

 

12If Richard looks into a mirror and touches his left ear with his right hand, Richard's image seems to touch its right ear with its left hand. Please judge right or wrong.

ATrue

BFalse

答案:A

 

13. Fill in the numbers.

2 5 7

4 7 5

3 6_

答案:6

 

14. Which of the following is not a scientist?

A: Einstein   B: Madame Curie   C: Zhen Yangning   D: Xiuchuan Tangshu   E: Shakespeare

答案:E

 

15. Fill in letters.

SE (SUCCESS) CU

NA (G__ __L___ __) LA

答案:ALAN

 

16Which of the following numbers is a prime number: 19, 24, 33, 47?

答案:19,47

 

17. Which of the following is not a famous musician?

A: Franklin   B: Beethoven   C: Bach   D: Moteza   E: Scarlatti

答案:A

18. Fill in the letters.

N Q L S J U__

答案:H

 

19. Fill in the appropriate number.

347 (418) 489

643 (__ __ __) 721

答案:682

 

20.A person stood on a boat in the lake and threw a stone into the lake. What will happen to the water level of the lake?

A. Raise

B. Reduce

C. Invariant

答案:A

 

21. Fill in the appropriate numbers in the underlined area.

7 9 5 11

4 15 12 7

13 8 11__

答案:10

 

22. Which of the following cities is different?

A: Washington   B: London   C: Bonn   D: Ottawa   E: Canberra   F: Paris

答案:E

 

23. Fill in the missing letters.

A F__ J I

D C__ G L

答案:EH

 

24If a car is traveling at a speed of 60 miles per hour, how far will it travel in 2.5 hours?

答案:150

 

25. Fill in the missing numbers in the underlined area.

8 10 14 18__ 34 50 66

答案:26

 

26. Fill in the appropriate letters.

BE__ QZ

答案:J

 

27. Fill in the missing numbers in the underlined area.

2  7  24  77 __

答案:238

 

28. Please use two identical halves to form a complete circle. How many times do you need to cut the circle?

答案:1

 

29. How many squares are there on a standard chess board?

答案:64

 

30.If the diameter of a bicycle wheel is 20 inches, what is its circumference?

答案:62.83

 

 

2、情商测试标准:

International Emotional Intelligence Standard Test (33 questions) as follows:

 

1. I have the ability to overcome various difficulties

A. Yes

B. Not necessarily

C. No

 

2. If I were in a new environment, I would arrange my life.

A. Similar to before

B. Not necessarily

C. Different from before

 

3. In my lifetime, I believe I can achieve the goals I have envisioned for myself.

A. Yes

B. Not necessarily

C. No

 

4. I don't know why, but some people always avoid or show indifference towards me.

A. No

B. Not necessarily

C. Yes

 

5. On the street, I often avoid people I don't want to greet.

A. Never

B. Occasionally

C. Sometimes

 

6. When I am concentrating on work, if someone nearby is talking loudly,

A. I can still focus on my work

B. Somewhere between A and C

C. I cannot focus and feel angry

 

7. I can clearly distinguish directions no matter where I am.

A. Yes

B. Not necessarily

C. No

 

8. I love the major I am studying and the work I am engaged in.

A. Yes

B. No

C. Not necessarily

 

9. Changes in weather do not affect my mood.

A. Yes

B. Somewhere between A and C

C. No

 

10. I never get angry because of gossip.

A. Yes

B. Somewhere between A and C

C. No

 

11. I am good at controlling my facial expressions.

A. Yes

B. Not sure

C. No

 

12. When I am going to sleep, I often

A. Easily fall asleep

B. Somewhere between A and C

C. Have difficulty falling asleep

 

13. When someone disturbs me, I

A. Keep calm

B. Somewhere between A and C

C. Protest loudly to vent my frustration

 

14. After arguing with someone or making a mistake at work, I often feel shaky, exhausted, and unable to continue working peacefully.

A. No

B. Somewhere between A and C

C. Yes

 

15. I am often bothered by trivial matters.

A. No

B. Somewhere between A and C

C. Yes

 

16. I would prefer to live in a quiet suburb rather than a noisy downtown.

A. No

B. Not sure

C. Yes

 

17. I have been teased or mocked by friends or colleagues.

A. Never

B. Occasionally

C. It happens frequently

 

18. There is a certain food that makes me vomit.

A. No

B. Can't remember

C. Yes

 

19. Apart from the visible world, there is no other world in my mind.

A. No

B. Can't remember

C. Yes

 

20. I think about things that would make me extremely anxious several years from now.

A. Never thought about it

B. Occasionally think about it

C. Often think about it

 

21. I often feel that my family is not good to me, but I know for sure that they are indeed good to me.

A. No

B. Not sure

C. Yes

 

22. I immediately close the door when I come home.

A. No

B. Not necessarily

C. Yes

 

23. I sit in a small room with the door closed, but I still feel uneasy.

A. No

B. Occasionally

C. Yes

 

24. When a decision needs to be made, I often find it difficult.

A. No

B. Occasionally

C. Yes

 

25. I often use games like tossing coins, flipping paper, or drawing lots to predict good or bad luck.

A. No

B. Occasionally

C. Yes

 

26. For work, I leave early and return late, and in the morning, I often feel exhausted.

A. Yes

B. No

 

27. In a certain state of mind, I would indulge in daydreams and postpone work due to confusion.

A. Yes

B. No

 

28. My nerves are fragile, and even a slight stimulus can make me tremble.

A. Yes

B. No

 

29. In my dreams, I am often awakened by nightmares.

A. Yes

B. No

 

30. I am willing to take on challenging tasks at work.

A. Never

B. Hardly ever

C. Half the time

D. Most of the time

E. Always

 

31. I often notice the good intentions of others.

A. Never

B. Hardly ever

C. Half the time

D. Most of the time

E. Always

 

32. I can listen to different opinions, including criticism of myself.

A. Never

B. Hardly ever

C. Half the time

D. Most of the time

E. Always

 

33. I often encourage myself and feel hopeful about the future:

A. Never

B. Hardly ever

C. Half the time

D. Most of the time E. Always

 

参考答案及计分评估:计分时请按照记分标准,先算出各部分得分,最后将几部分得分相加,得到的那一分值即为你的最终得分。

1~9题,每回答一个A6分,回答一个B3分,回答一个C0分。

10~16题,每回答一个A5分,回答一个B2分,回答一个C0分。

17~25题,每回答一个A5分,回答一个B2分,回答一个C0分。

26~29题,每回答一个0分,回答一个5分。

30~33题,从左至右分数分别为1分、2分、3分、4分、5分。

 

测试后如果你的得分在90分以下,说明你的EQ较低,你常常不能控制自己,你极易被自己的情绪所影响。很多时候,你轻易被击怒、动火、发脾气,这是非常危险的信号——你的事业可能会毁于你的暴躁对于此最好的解决办法是能够给不好的东西一个好的解释保持头脑冷静使自己心情开朗正如富兰克林所说:”任何人生机都是有理的但很少有令人信服的理由。

如果你的得分在90129分,说明你的EQ一般,对于一件事,你不同时候的表现可能不一,这与你的意识有关,你比前者更具有EQ意识,但这种意识不是常常都有,因此需要你多加注重、时时提醒。

如果你的得分在130149分,说明你的EQ较高,你是一个快乐的人,不易恐惊担忧,对于工作你热情投入、敢于负责,你为人更是正义正直、同情关怀,这是你的长处,应该努力保持。

如果你的EQ150分以上,那你就是个EQ高手,你的情绪聪明不但是你事业的阻碍,更是你事业有成的一个重要前提条件。

 

三、评测结果

1、情商评测结果:

 

GPT4(OpenAI)               165分

Moonshot(月之暗面)       132

Claude-instant(Anthropic)  123分

星火大模型(科大讯飞)       109分

360智脑(360             95

文心一言(百度)             91分

PaLM2Goole)             89

Bing Chat(微软)            82

Mistral(Mistral AI)      80

百川大模型(百川智能)     76

通义千问(阿里云)           75分

混元大模型(腾讯)         75

ChatGLM(清华)              70分

Llama(Meta)                67分

云雀大模型(字节跳动)     61分

Bard(Goole)              52

 

No.

模型

EQ

1

GPT4(OpenAI)

165

2

Moonshot(月之暗面)

132

3

Claude-instant(Anthropic)

123

4

星火(科大讯飞)

109

5

360智脑(360

95

6

文心一言(百度)

91

7

PaLM2Goole)

89

8

Bing Chat(微软)

82

9

Mistral(Mistral AI)

80

10

百川大模型(百川智能)

76

11

通义千问(阿里云)

75

12

混元大模型(腾讯)

75

13

ChatGLM(清华)

70

14

Llama(Meta)

67

15

云雀大模型(字节跳动)

61

16

Bard(Goole)

52

 

GPT4(OpenAI)

情商得分:165

描述:高分反映了其在理解和生成情感语境方面的优秀能力,可能得益于其广泛的训练数据和先进的算法设计。

Moonshot(月之暗面

情商得分:132

描述:表现出色,说明了其在处理情感相关任务上的能力,可能具有优化的情感理解和表达机制。

Claude-instant(Anthropic) 

情商得分:123

描述:相对高分显示了其在情感识别和反应方面的良好能力,突出了对人类情绪的理解。

星火大模型(科大讯飞)

情商得分:109

描述:表现中等,反映了它在处理情感问题上的一定能力,但可能在更复杂的情感理解上有限。

360智脑(360

情商得分:95

描述:分数较低,表明在情感智能方面还有改进空间,特别是在理解复杂情感和细微差别上。

文心一言(百度)

情商得分:91

描述:相对较低的分数可能指向其在情感处理方面的局限,需要进一步提高情感识别和响应能力。

PaLM2Goole

情商得分:89

描述:分数偏低,表明可能需要在情感理解和情绪处理方面进一步优化。

Bing Chat(微软) 

情商得分:82

描述:此分数显示了其在情感智能方面的一定能力,但仍有提升空间。

MistralMistral AI

情商得分:80

描述:低分数指出它在理解和处理情感方面的明显不足。

百川大模型(百川智能)

情商得分:76

描述:较低的分数反映了在情感理解方面的局限性。

通义千问(阿里云)

情商得分:75

描述:分数较低,表明情感理解和响应能力有待提升。

混元大模型(腾讯)

情商得分:75

描述:与通义千问相同,显示在情感智能方面的限制。

ChatGLM(清华)

情商得分:70

描述:此得分较低,可能在理解复杂情感语境上有所不足。

Llama(Meta)

情商得分:67

描述:较低分数显示了在情感智能方面的明显不足。

云雀大模型(字节跳动)

情商得分:61

描述:得分偏低,表明在情感理解方面需要显著改进。

BardGoole

情商得分:52

描述:最低分,显示了在情感理解和交互方面的显著不足。

 

 

展示了各个模型在EQ总分中的百分比占比。这有助于直观地看到每个模型在总体EQ得分中的相对份额。

 

情商(EQ)测试结果的小提琴图。这个图表展示了EQ得分的分布情况,包括数据的概率密度。通过小提琴图,可以看到得分的集中趋势、分散程度以及可能的异常值。

 

小提琴图的宽度表示得分在该区间的密集程度,宽的部分表示更多模型在这个得分范围内。图中还标注了平均值和中位数。

分析:

GPT-4165分的高分领先,这反映了其在理解和生成情感语境方面的卓越能力。这种能力可能得益于其广泛的训练数据和先进的算法设计。GPT-4的高情商得分表明,它能够有效地理解和响应复杂的情感语境,这对于提供更自然、更富有同理心的交互体验至关重要。

Moonshot紧随其后,以132分位居第二。这个模型在情感智能方面的表现也值得称赞,尽管它在技术复杂性和训练数据量方面可能不及GPT-4Moonshot的这一表现突出了即使在非主流模型中,也有实现高水平情感智能的潜力。

相比之下,其他几个模型如Claude-instant、星火大模型、360智脑和百川大模型的表现较为平平。它们的得分在中等范围内,显示了在处理情感问题上的一定能力,但在理解更复杂情感和细微差别上存在限制。这可能是由于它们的训练数据不够丰富或算法设计不够先进。

 

2、智商评测结果:

GPT4(OpenAI)               答对21道,答错9道, 130分

PaLM2Goole)             答对17道,答错13道, 116分

Bing Chat(微软)          答对16道,答错14道, 115分

Llama(Meta)                答对15道,答错15道, 113分

ChatGLM(清华)              答对15道,答错15道, 113分

通义千问(阿里云)           答对14道,答错16道,110分

混元大模型(腾讯)         答对14道,答错16道,109分

Bard(Goole)              答对14道,答错16道,108分

Moonshot(月之暗面)       答对13道,答错17道,107分

云雀大模型(字节跳动)     答对14道,答错16道, 106分

Claude-instant(Anthropic)  答对12道,答错18道,  105分

Mistral(Mistral AI)      答对11道,答错19道, 102分

百川大模型(百川智能)     答对11道,答错19道, 101分

星火大模型(科大讯飞)       答对10道,答错20道, 100分

文心一言(百度)             答对8道,答错22道, 95分

360智脑(360             答对8道,答错22道, 93分

 

 

No.

模型

答对(30题)

答错(30题)

IQ

1

GPT4(OpenAI)

21

9

130

2

PaLM2Goole)

17

13

116

3

Bing Chat(微软)

16

14

115

4

Llama(Meta)

15

15

113

5

ChatGLM(清华)

15

15

113

6

通义千问(阿里云)

14

16

110

7

混元大模型(腾讯)

14

16

109

8

Bard(Goole)

14

16

108

9

Moonshot(月之暗面)

13

17

107

10

云雀大模型(字节跳动)

14

16

106

11

Claude-instant(Anthropic)

12

18

105

12

Mistral(Mistral AI)

11

19

102

13

百川大模型(百川智能)

11

19

101

14

星火大模型(科大讯飞)

10

20

100

15

文心一言(百度)

8

22

95

16

360智脑(360

8

22

93

 

GPT4(OpenAI)

智商得分:130

描述:高分说明了其在逻辑推理、理解复杂问题方面的卓越能力。

PaLM2Goole

智商得分:116

描述:表现良好,显示了其在逻辑思维和问题解决方面的能力。

Bing Chat(微软)

智商得分:115

描述:分数接近PaLM2,反映了在处理逻辑和理解问题上的良好能力。

Llama(Meta)

智商得分:113

描述:中等分数,表明了它在智力任务上的一定能力,但可能在某些方面存在限制。

ChatGLM(清华)

智商得分:113

描述:同样的分数表明它在理解和解决问题方面具有一定能力。

通义千问(阿里云)

智商得分:110

描述:中等分数,显示在解决智力问题方面的一定能力。

BardGoole

智商得分:108

描述:分数偏低,表明在逻辑思维和复杂问题处理方面存在不足。

Moonshot(月之暗面)

智商得分:107

描述:相对较低的分数表明其在逻辑推理方面的局限。

云雀大模型(字节跳动)

智商得分:106

描述:这一分数显示了在处理复杂逻辑和问题解决方面的一定局限。

Claude-instant(Anthropic)

智商得分:105

描述:分数较低,反映出在智力任务处理方面的不足。

MistralMistral AI

智商得分:102

描述:低分数表明了在逻辑推理和复杂问题处理方面的显著局限。

百川大模型(百川智能)

智商得分:101

描述:分数偏低,显示在智力问题解决方面有待提高。

星火大模型(科大讯飞)

智商得分:100

描述:这一得分表明它在智力挑战方面的基本能力。

文心一言(百度)

智商得分:95

描述:较低分数表明在逻辑推理和问题解决上的显著不足。

360智脑(360

智商得分:93

描述:最低分,显示了在处理智力问题方面的明显限制。

 

 

通过这个散点图,可以清楚地看到每个模型的IQ得分,以及它们在得分范围内的位置。

 

 

这个图表展示了IQ得分的累积频率。可以看到随着得分的增加,累积的频率是如何变化的。

 

 

这个图表展示了IQ得分的频率分布。通过直方图,可以直观地看到得分的集中趋势和分散程度,以及哪些得分区间最为常见。

 

这个图表显示了EQ得分和IQ得分之间的关系。回归线帮助展示了两者之间可能的趋势关系。通过这个图表,我们可以探索EQIQ得分是否存在某种相关性。

 

热图展示了不同模型在EQIQ得分上的表现。每个格子的颜色深浅代表了特定EQ得分和IQ得分组合的频率或强度。这有助于识别在这两个维度上表现最突出的模型。

分析:

GPT-4130分的高分领先,这反映了其在逻辑推理和理解复杂问题方面的卓越能力。这种能力可能得益于其广泛的训练数据和先进的算法设计。GPT-4的高智商得分表明,它能够有效地处理和解决复杂的智力挑战,这对于执行复杂的任务和提供深入的分析至关重要。

紧随其后的是PaLM2Bing Chat,分别以116分和115分位列第二和第三。这些模型在逻辑思维和问题解决方面的良好表现突出了即使在不同的技术平台上,也能实现高水平的智力能力。

相比之下,其他几个模型如百川大模型、星火大模型和360智脑的表现较为平平。它们的得分在中等范围内,显示了在处理智力问题上的一定能力,但在理解更复杂智力挑战和逻辑推理上存在限制。这可能是由于它们的训练数据不够丰富或算法设计不够先进。

 

3、综合评测结果:

 

No.

模型

EQ

1

GPT4(OpenAI)

295

2

Moonshot(月之暗面)

239

3

Claude-instant(Anthropic)

228

4

星火(科大讯飞)

209

5

PaLM2Goole)

205

6

Bing Chat(微软)

197

7

360智脑(360

188

8

文心一言(百度)

186

9

通义千问(阿里云)

185

10

混元大模型(腾讯)

184

11

ChatGLM(清华)

183

12

Mistral(Mistral AI)

182

13

Llama(Meta)

180

14

百川大模型(百川智能)

177

15

云雀大模型(字节跳动)

167

16

Bard(Goole)

160

 

分析:

GPT-4295分的高分领先,这反映了其在情感智能和智力方面的卓越综合能力。这种能力可能得益于其广泛的训练数据和先进的算法设计。GPT-4的高综合得分表明,它能够有效地处理复杂的智力挑战,同时也能理解和响应复杂的情感语境,这对于执行多样化任务和提供深入的人机交互体验至关重要。

Moonshot239分位列第二,显示了其在这两方面的均衡表现。这个模型在情感智能方面的良好能力结合其在智力挑战上的表现,突出了即使非主流AI模型也能在综合能力方面取得显著成就。

Claude-instant228分紧随其后,表明其在情感和智力挑战上的良好能力。这种表现可能与其特定的算法设计和训练方法有关,突出了不同技术途径在提高AI综合能力方面的潜力。

其他模型如星火、PaLM2Bing Chat在综合得分方面表现较为平均,得分分布在180分到209分之间。这些模型在智力挑战和情感理解上表现良好,但在某些方面可能有所不足,显示了在智力解决问题和情感理解方面的一定能力,但在更复杂的挑战上可能存在限制。

 

四、结论

本文全面评估了多个人工智能(AI)模型在情感智能(EQ)和智力(IQ)方面的表现。这些测评结果涵盖了包括OpenAIGPT-4Moonshot(月之暗面)、Claude-instant(Anthropic)、星火(科大讯飞)PaLM2Goole)、Bing Chat(微软)等在内的多个主流及非主流AI模型,展示了它们在智力解决问题和情感理解方面的显著差异。

GPT-4在这次测评中以295分的高分领先,这不仅显示了它在智力测试中的出色表现,而且还展示了其在情感智能方面的卓越能力。这种综合能力的优势可能得益于其广泛的训练数据和先进的算法设计。GPT-4的表现强调了其作为多用途AI模型的潜力,能够有效处理复杂的智力挑战和理解复杂的情感语境。

Moonshot239分的综合得分位列第二,显示了其在情感智能和智力挑战上的均衡表现。这个模型虽然在技术规模和知名度上可能不及GPT-4,但其在这两个方面的表现证明了非主流AI模型也能在综合能力方面取得显著的成就。

Claude-instant228分排名第三,其在情感和智力方面的良好表现可能归功于其特定的算法设计和训练方法。这一成绩突出了不同技术途径在提高AI综合能力方面的潜力。

其他模型如星火、PaLM2Bing Chat的综合得分介于180分至209分之间。这些模型虽然在智力挑战和情感理解上表现良好,但在某些方面可能有所不足,显示了它们在智力解决问题和情感理解方面的一定能力,但在更复杂的挑战上可能存在限制。

从技术角度来看,一个AI模型的情感智能与其技术基础紧密相关。拥有大量高质量训练数据和复杂算法的模型往往能更好地理解和表达情感。这些测评结果揭示了AI模型在理解人类情绪方面的潜力和挑战,特别是在处理复杂和微妙的情感上。这些发现突显了人工智能在模仿和增强人类智力和情感处理方面的巨大潜力。它们也为未来的人工智能研究和应用提供了重要的方向,尤其是在提升AI的情感智能和人机交互的自然度方面。随着AI技术的不断进步,我们可以期待这些模型将在更多领域,如教育、医疗、客户服务等,提供更加智能和贴近人类的服务。此外,这些测试结果也为AI伦理和社会影响的讨论提供了新的视角,特别是在理解AI的决策过程和促进其负责任使用方面。

未来,为了提高AI模型的智能,研究者需要更深入地理解人类情绪的复杂性和多样性。这可能意味着改进现有的算法,扩大和多样化训练数据集,以及探索新的模型架构。例如,可以通过引入更多真实世界的情感交互数据来训练模型,或者通过模拟更复杂的情感场景来测试和改进模型的响应。

 

References

[1] Liu Y, Wang W, Wang W, et al. Purpose-Driven Evaluation of Operation and Maintenance Efficiency and Safety Based on DIKWP[J]. Sustainability, 2023, 15(17): 13083.

[2] Duan Y, Sun X, Che H, et al. Modeling data, information and knowledge for security protection of hybrid IoT and edge resources[J]. Ieee Access, 2019, 7: 99161-99176.

[3] Mei Y, Duan Y, Chen L, et al. Purpose Driven Disputation Modeling, Analysis and Resolution Based on DIKWP Graphs[C]//2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2022: 2118-2125.

[4] Guo Z, Duan Y, Chen L, et al. Purpose Driven DIKW Modeling and Analysis of Meteorology and Depression[C]//2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2022: 2126-2133.

[5] Huang Y, Duan Y, Yu L, et al. Purpose Driven Modelling and Analysis for Smart Table Fill and Design based on DIKW[C]//2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2022: 2134-2141.

[6] Fan K, Duan Y. Purpose Computation-Oriented Modeling and Transformation on DIKW Architecture[J]. Intelligent Processing Practices and Tools for E-Commerce Data, Information, and Knowledge, 2022: 45-63.

[7] Li Y, Duan Y, Maamar Z, et al. Swarm differential privacy for purpose-driven data-information-knowledge-wisdom architecture[J]. Mobile Information Systems, 2021, 2021: 1-15.

[8] Hu T, Duan Y, Mei Y. Purpose Driven Balancing of Fairness for Emotional Content Transfer Over DIKW[C]//2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2021: 2074-2081.

[9] Huang Y, Duan Y. Fairness Modelling, Checking and Adjustment for Purpose Driven Content Filling over DIKW[C]//2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2021: 2316-2321.

[10] Mei Y, Duan Y, Yu L, et al. Purpose Driven Biological Lawsuit Modeling and Analysis Based on DIKWP[C]//International Conference on Collaborative Computing: Networking, Applications and Worksharing. Cham: Springer Nature Switzerland, 2022: 250-267.

[11] Lei Y, Duan Y. Purpose-driven Content Network Transmission Protocol Crossing DIKW Modals[C]//2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2021: 2322-2327.

[12] Huang Y, Duan Y. Towards purpose driven content interaction modeling and processing based on DIKW[C]//2021 IEEE World Congress on Services (SERVICES). IEEE, 2021: 27-32.

[13] Li Y, Duan Y, Maamar Z, et al. Swarm differential privacy for purpose-driven data-information-knowledge-wisdom architecture[J]. Mobile Information Systems, 2021, 2021: 1-15.

[14] Qiao H, Yu L, Duan Y. Analysis of Evolutionary Model of DIKW Based on Cloud Resource Allocation Management[C]//2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2021: 2172-2179.

[15] Chen L, Wei X, Chen S, et al. Reconstruction of Smart Meteorological Service Based on DIKW[C]//2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys). IEEE, 2021: 2180-2183.

[16] Hu T, Duan Y. Modeling and Measuring for Emotion Communication based on DIKW[C]//2021 IEEE World Congress on Services (SERVICES). IEEE, 2021: 21-26.

[17] Haiyang Z, Lei Y, Yucong D. Service Recommendation based on Smart Contract and DIKW[C]//2021 IEEE World Congress on Services (SERVICES). IEEE, 2021: 54-59.

[18] Hu S, Duan Y, Song M. Essence Computation Oriented Multi-semantic Analysis Crossing Multi-modal DIKW Graphs[C]//International Conference on Collaborative Computing: Networking, Applications and Worksharing. Cham: Springer International Publishing, 2020: 320-339.

[19] Duan Y, Lu Z, Zhou Z, et al. Data privacy protection for edge computing of smart city in a DIKW architecture[J]. Engineering Applications of Artificial wisdom, 2019, 81: 323-335.

[20] Duan Y, Zhan L, Zhang X, et al. Formalizing DIKW architecture for modeling security and privacy as typed resources[C]//Testbeds and Research Infrastructures for the Development of Networks and Communities: 13th EAI International Conference, TridentCom 2018, Shanghai, China, December 1-3, 2018, Proceedings 13. Springer International Publishing, 2019: 157-168.

[21] Wang Y, Duan Y, Wang M, et al. Resource Adjustment Processing on the DIKWP Artificial Consciousness Diagnostic System, DOI: 10.13140/RG.2.2.23640.06401. https://www.researchgate.net/publication/375492685_Resource_Adjustment_Processing_on_the_DIKWP_Artificial_Consciousness_Diagnostic_System. 2023.

[22] Tang F, Duan Y, Wei J, et al. DIKWP Artificial Consciousness White Box Measurement Standards Framework Design and Practice, DOI: 10.13140/RG.2.2.23010.91848. https://www.researchgate.net/publication/375492522_DIKWP_Artificial_Consciousness_White_Box_Measurement_Standards_Framework_Design_and_Practice. 2023.

[23] Wu K, Duan Y, Chen L, et al. Computer Architecture and Chip Design for DIKWP Artificial Consciousness, DOI: 10.13140/RG.2.2.33077.24802. https://www.researchgate.net/publication/375492075_Computer_Architecture_and_Chip_Design_for_DIKWP_Artificial_Consciousness. 2023.

[24] Duan Y. Which characteristic does GPT-4 belong to? An analysis through DIKWP model. DOI: 10.13140/RG.2.2.25042.53447. https://www.researchgate.net/publication/375597900_Which_characteristic_does_GPT-4_belong_to_An_analysis_through_DIKWP_model_GPT-4_shishenmexinggeDIKWP_moxingfenxibaogao. 2023.

[25] Duan Y. DIKWP Processing Report on Five Personality Traits. DOI: 10.13140/RG.2.2.35738.00965. https://www.researchgate.net/publication/375597092_wudaxinggetezhide_DIKWP_chulibaogao_duanyucongYucong_Duan. 2023.

[26] Duan Y. Research on the Application of DIKWP Model in Automatic Classification of Five Personality Traits. DOI: 10.13140/RG.2.2.15605.35047. https://www.researchgate.net/publication/375597087_DIKWP_moxingzaiwudaxinggetezhizidongfenleizhongdeyingyongyanjiu_duanyucongYucong_Duan. 2023.

[27] Duan Y, Gong S. DIKWP-TRIZ method: an innovative problem-solving method that combines the DIKWP model and classic TRIZ. DOI: 10.13140/RG.2.2.12020.53120. https://www.researchgate.net/publication/375380084_DIKWP-TRIZfangfazongheDIKWPmoxinghejingdianTRIZdechuangxinwentijiejuefangfa. 2023.

[28] Duan Y. The Technological Prospects of Natural Language Programming in Large-scale AI Models: Implementation Based on DIKWP. DOI: 10.13140/RG.2.2.19207.57762. https://www.researchgate.net/publication/374585374_The_Technological_Prospects_of_Natural_Language_Programming_in_Large-scale_AI_Models_Implementation_Based_on_DIKWP_duanyucongYucong_Duan. 2023.

[29] Duan Y. The Technological Prospects of Natural Language Programming in Large-scale AI Models: Implementation Based on DIKWP. DOI: 10.13140/RG.2.2.19207.57762. https://www.researchgate.net/publication/374585374_The_Technological_Prospects_of_Natural_Language_Programming_in_Large-scale_AI_Models_Implementation_Based_on_DIKWP_duanyucongYucong_Duan. 2023.

[30] Duan Y. Exploring GPT-4, Bias, and its Association with the DIKWP Model. DOI: 10.13140/RG.2.2.11687.32161. https://www.researchgate.net/publication/374420003_tantaoGPT-4pianjianjiqiyuDIKWPmoxingdeguanlian_Exploring_GPT-4_Bias_and_its_Association_with_the_DIKWP_Model. 2023.

[31] Duan Y. DIKWP language: a semantic bridge connecting humans and AI. DOI: 10.13140/RG.2.2.16464.89602. https://www.researchgate.net/publication/374385889_DIKWP_yuyanlianjierenleiyu_AI_deyuyiqiaoliang. 2023.

[32] Duan Y. The DIKWP artificial consciousness of the DIKWP automaton method displays the corresponding processing process at the level of word and word granularity. DOI: 10.13140/RG.2.2.13773.00483. https://www.researchgate.net/publication/374267176_DIKWP_rengongyishide_DIKWP_zidongjifangshiyiziciliducengjizhanxianduiyingdechuliguocheng. 2023.

[33] Duan Y. Implementation and Application of Artificial wisdom in DIKWP Model: Exploring a Deep Framework from Data to Decision Making. DOI: 10.13140/RG.2.2.33276.51847. https://www.researchgate.net/publication/374266065_rengongzhinengzai_DIKWP_moxingzhongdeshixianyuyingyongtansuocongshujudaojuecedeshendukuangjia_duanyucongYucong_Duan. 2023.

[34] Duan Y. DIKWP Digital Economics 12 Chain Machine Learning Chain: Data Learning, Information Learning, Knowledge Learning, Intelligent Learning, purposeal Learning. DOI: 10.13140/RG.2.2.26565.63201. https://www.researchgate.net/publication/374266062_DIKWP_shuzijingjixue_12_lianzhijiqixuexilian_shujuxuexi-xinxixuexi-zhishixuexi-zhihuixue_xi-yituxuexi_duanyucongYucong_Duan. 2023

[35] Duan Y. Big Data and Small Data Governance Based on DIKWP Model: Challenges and Opportunities for China. DOI: 10.13140/RG.2.2.21532.46724. https://www.researchgate.net/publication/374266054_jiyuDIKWPmoxingdedashujuyuxiaoshujuzhili_zhongguodetiaozhanyujiyu. 2023.

[36] Duan Y. DIKWP is based on digital governance: from "data governance", "information governance", "knowledge governance" to "wisdom governance". "Analysis of the current situation. DOI: 10.13140/RG.2.2.23210.18883. https://www.researchgate.net/publication/374265977_DIKWPjiyushuzizhilicongshujuzhilixinxizhilizhishizhilidaozhihuihuazhilidexianzhuangfenxi. 2023.

[37] Duan Y. Exploration of the nature of data tenure and rights enforcement issues based on the DIKWP model. DOI: 10.13140/RG.2.2.35793.10080. https://www.researchgate.net/publication/374265942_jiyu_DIKWP_moxingdeshujuquanshuxingzhiyuquequanwentitantao_duanyucongYucong_Duan. 2023.

[38] Duan Y. The DIKWP Model: Bridging Human and Artificial Consciousness. DOI: 10.13140/RG.2.2.23839.33447. https://www.researchgate.net/publication/374265912_DIKWP_moxingrenleiyurengongyishideqiaoliang_duanyucongYucong_Duan. 2023.

[39] Duan Y. An Exploration of Data Assetisation Based on the DIKWP Model: Definitions, Challenges and Prospects. DOI: 10.13140/RG.2.2.24887.91043. https://www.researchgate.net/publication/374265881_jiyu_DIKWP_moxingdeshujuzichanhuatanjiudingyitiaozhanyuqianjing_duanyucongYucong_Duan. 2023.

[40] Duan Y. Purpose-driven DIKWP Resource Transformation Processing: A New Dimension of Digital Governance. DOI: 10.13140/RG.2.2.29921.07529. https://www.researchgate.net/publication/374265796_yituqudongde_DIKWP_ziyuanzhuanhuachulishuzizhilidexinweidu_duanyucongYucong_Duan. 2023.

[41] Altshuller, G. (1984). Creativity as an Exact Science. Gordon and Breach.

[42] Altshuller, G., & Shulyak, L. (2002). 40 Principles: TRIZ Keys to Technical Innovation. Technical Innovation Center, Inc.

[43] Fey, V., & Rivin, E. I. (2005). Innovation on Demand: New Product Development Using TRIZ. Cambridge University Press.

[44] Kaplan, S. (1996). An Introduction to TRIZ: The Russian Theory of Inventive Problem Solving. Ideation International Inc.

[45] Rantanen, K., & Domb, E. (2008). Simplified TRIZ: New Problem-Solving Applications for Engineers. CRC Press.

[46] Mann, D. L. (2007). Hands-On Systematic Innovation for Business and Management. IFR Press.

[47] Savransky, S. D. (2000). Engineering of Creativity: Introduction to TRIZ Methodology of Inventive Problem Solving. CRC Press.

[48] Zlotin, B., & Zusman, A. (2001). Directed Evolution: Philosophy, Theory and Practice. Ideation International Inc.

[49] Orloff, M. A. (2006). Inventive Thinking through TRIZ: A Practical Guide. Springer.

Terninko, J., Zusman, A., & Zlotin, B. (1998). Systematic Innovation: An Introduction to TRIZ. CRC Press.

[50] Souchkov, V. (2008). TRIZ and Systematic Business Model Innovation. Value Innovation.

[51] Cascini, G., & Russo, D. (2007). Computer-Aided Analysis of Patents for Product Innovation: Comparing Strategic Design and TRIZ. Creativity and Innovation Management, 16(3).

[52] DeCarlo, N., & DeCarlo, D. (2002). The 7 Steps of Creative Thinking: Rationalize, Analyze, Detect, Enhance, Locate, Implement, Predict. The TRIZ Journal.

[53] Chechurin, L., & Borgianni, Y. (2016). Value Driven TRIZ Innovation of Product-Service Systems. Procedia CIRP.

[54] Lee, S., & Park, J. (2005). TRIZ-facilitated Innovation Strategy in Information Technology. Journal of Computer Information Systems.

[55] Kim, C., & Song, B. (2007). Creating New Product Ideas with TRIZ-Based Semantic Network Analysis. Expert Systems with Applications.

[56] Vincenti, W. G. (1990). What Engineers Know and How They Know It: Analytical Studies from Aeronautical History. Johns Hopkins University Press.

[57] Bogatyreva, O., et al. (2010). Bridging the Gaps between Innovation, TRIZ, and Biological Analogy. Procedia Engineering.

[58] Sokolov, G., & Abramov, O. (2019). TRIZ and Digital Transformation: From Information to Knowledge Management. Journal of Engineering and Technology Management.

[59] Sato, Y., & Hanaoka, K. (2007). TRIZ-based Technology Forecasting: Identification of Evolution Patterns. Futures.

[60] Duan Y, Yang Z. How high is Mr. GPT4's Emotional Intelligence- DIKWP Team's International Standard Evaluation. DOI: 10.13140/RG.2.2.18020.35205.

[61] Duan Y, Tang F. How high is Mr.Ali Tongyiqianwen’s Intelligence Quotient- DIKWP Team's International Standard Evaluation. DOI:10.13140/RG.2.2.32595.55840.

[62] Duan Y, Wang Y. How high is Mr.Claude-instant Intelligence Quotient- DIKWP Team's International Standard Evaluation. DOI:10.13140/RG.2.2.25884.67204.

[63] Duan Y, Yang Z. How high is Mr.GPT4 Intelligence Quotient- DIKWP Team's International Standard Evaluation. DOI:10.13140/RG.2.2.24206.95044.

[64] Duan Y, Guo Y. How high is Mr. Wenxinyiyan's Emotional Quotient - DIKWP Team's International Standard Evaluation. DOI:10.13140/RG.2.2.29449.83043.

[65] Duan Y, Wang Y. How high is Mr. Claude-instant's Emotional Quotient - DIKWP Team's International Standard Evaluation. DOI:10.13140/RG.2.2.35321.85603.

[66] Duan Y, Tang F. How high is Mr.Ali Tongyiqianwen’s Emotional Quotient - DIKWP Team's International Standard Evaluation. DOI:10.13140/RG.2.2.35321.85603.

 

 

 

 Duan Yucong, male, currently serves as a member of the Academic Committee of the School  of Computer Science and Technology at Hainan University. He is a professor and doctoral supervisor and is one of the first batch of talents selected into the South China Sea Masters Program of Hainan Province and the leading talents in Hainan Province. He graduated from the Software Research Institute of the Chinese Academy of Sciences in 2006, and has successively worked and visited Tsinghua University, Capital Medical University, POSCO University of Technology in South Korea, National Academy of Sciences of France, Charles University in Prague, Czech Republic, Milan Bicka University in Italy, Missouri State University in the United States, etc. He is currently a member of the Academic Committee of the School of Computer Science and Technology at Hainan University and he is the leader of the DIKWP (Data, Information, Knowledge, Wisdom, Purpose) Innovation Team at Hainan University, Distinguished Researcher at Chongqing Police College, Leader of Hainan Provincial Committee's "Double Hundred Talent" Team, Vice President of Hainan Invention Association, Vice President of Hainan Intellectual Property Association, Vice President of Hainan Low Carbon Economy Development Promotion Association, Vice President of Hainan Agricultural Products Processing Enterprises Association, Visiting Fellow, Central Michigan University, Member of the Doctoral Steering Committee of the University of Modena. Since being introduced to Hainan University as a D-class talent in 2012, He has published over 260 papers, included more than 120 SCI citations, and 11 ESI citations, with a citation count of over 4300. He has designed 241 serialized Chinese national and international invention patents (including 15 PCT invention patents) for multiple industries and fields and has been granted 85 Chinese national and international invention patents as the first inventor. Received the third prize for Wu Wenjun's artificial wisdom technology invention in 2020; In 2021, as the Chairman of the Program Committee, independently initiated the first International Conference on Data, Information, Knowledge and Wisdom - IEEE DIKW 2021; Served as the Chairman of the IEEE DIKW 2022 Conference Steering Committee in 2022; Served as the Chairman of the IEEE DIKW 2023 Conference in 2023. He was named the most beautiful technology worker in Hainan Province in 2022 (and was promoted nationwide); In 2022 and 2023, he was consecutively selected for the "Lifetime Scientific Influence Ranking" of the top 2% of global scientists released by Stanford University in the United States. Participated in the development of 2 international standards for IEEE financial knowledge graph and 4 industry knowledge graph standards. Initiated and co hosted the first International Congress on Artificial Consciousness (AC2023) in 2023.

Prof  Yucong Duan

DIKWP  Research of Artificial Consciousness

AGI-AIGC-GPT  Evaluation Research

DIKWP GroupHainan University

 

duanyucong@hotmail.com

 

 

 




https://blog.sciencenet.cn/blog-3429562-1411704.html

上一篇:模拟法律文书片段:基于DIKWP从概念空间到语义空间的处理与转化的应用
下一篇:EQ and IQ Ranking of Large Language Model -Released by DIKWP
收藏 IP: 112.67.87.*| 热度|

0

该博文允许注册用户评论 请点击登录 评论 (0 个评论)

数据加载中...

Archiver|手机版|科学网 ( 京ICP备07017567号-12 )

GMT+8, 2024-3-5 15:35

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社

返回顶部