计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230900104-8.doi: 10.11896/jsjkx.230900104

• 交叉&应用 • 上一篇    下一篇

机器思维的数学原理

朱平1,2, 邹卫明3, 吕珀华1, 史进3, 蒋学涛1, 马益荣3   

  1. 1 北京博大网信股份有限公司 北京 101111
    2 泰豪智慧城市研究院 北京 100176
    3 北京泰豪智能工程有限公司 北京 100176
  • 发布日期:2024-06-06
  • 通讯作者: 邹卫明(zowm@tellhow.com.cn)
  • 作者简介:(1401626437@qq.com)

Mathematical Principles of Machine Thinking

ZHU Ping1,2, ZOU Weiming3, LYU Pohua1, SHI Jin3, JIANG Xuetao1, MA Yirong3   

  1. 1 Beijing Broad Network & Information Company Limited,Beijing 101111,China
    2 Tellhow Institute of Smart City,Beijing 100176,China
    3 Beijing Tellhow Intelligent Engineering Company Limited,Beijing 100176,China
  • Published:2024-06-06
  • About author:ZHU Ping,born in 1970,Ph.D,professor.His main research interests include thinking machine,semantic understan-ding and complex algorithm.
    ZOU Weiming,born in 1972,master,senior engineer.His main research interests include big data and intelligent engineering.

摘要: 本研究以构建以人类可以理解的方式寻找解决实际问题的方法与步骤的机器思维机制为目的。数学是人类描述客观世界状态和运行规律的重要思维工具。数学也是机器类人自动求解问题答案、解释运行方法和生成中间步骤的重要工具。客观世界的描述语言表述形式多样、规模巨大且特征稀疏,其语义表示、语义积聚、语义分析、以及机器思维机制的实现方法都是基于用例积累渐进式明晰和完善的。在数学应用题类人自动求解领域,机器思维主要依靠的基本数学概念及其蕴含的计算理论包括集合、比例(分数)、不等关系、枚举和数据归纳与推导(趋势判别)等。从机器思维系统实现的角度,以集合对象及其比例计算的语义渐进积聚和识别为例,讨论了数学原理在机器思维系统中的应用技术路线。最后,用示例介绍了机器自动类人求解一道具体的初等数学应用题的完整过程和中间步骤,展望了机器思维应用不等关系、枚举、数轴、坐标系和数学归纳与推导等数学工具的方法和前景。

关键词: 机器思维, 集合, 比例, 数学对象, 数学概念

Abstract: Constructing machine thinking mechanisms that are understandable to humans is the ultimate goal of this paper.Ma-thematic is an important thinking tool for humans to describe the state and running laws of the objective world,and is also a tool for machines to automatic resolving,interpretable running,and intermediate steps generating.The description language of the objective world has diverse forms,huge scale,and sparse features.Its semantic representation,semantic accumulation,semantic analyzing,and the implementation of machine thinking mechanisms are all based on progressive clarity and perfection by use cases.In the field of automatic humanoid solving elementary mathematic application problem,machine thinking mainly relies on basic mathematical concepts and their underlying computation theories,including set,proportion(fraction),unequal relationship,enumeration,and data induction and derivation(trend discrimination).Taking the semantic gradual accumulation and recognition of set elements and their proportions as the example,this paper discusses the application technology of mathematical principles in machine thinking systems from the perspective of machine thinking system implementation.Finally,an example is presented to illustrate the complete process and intermediate steps of machine automated humanoid resolving a specific elementary mathematic application problem.The methods and prospects of using mathematical tools such as inequality,enumeration,number axis,coordinate system,and mathematical induction and deduction in machine thinking are discussed.

Key words: Machine thinking, Set, Proportion, Mathematical object, Mathematical concept

中图分类号: 

  • TP391
[1]ALEKSANDAR P,CRAIG C,PAUL B.Knowledge based engineering(KBE) past,present and future[EB/OL].https://www.researchgate.net/publication/266586531.
[2]HU S.Preliminary exploration of Turing’s machine thinkingthought[D].Wuhan:Central China Normal University,2017.
[3]CHEN Z C,WANG C.A new knowledge acquisition method for continuous information Systems[J].Journal of Chongqing University of Technology(Natural Science),2008,22(6):54-59.
[4]PAN L,FENG S.Sentence analysis and knowledge extraction of elementary school application questions based on conceptual hierarchical networks[J]Computer System Applications,2009(12):179-183.
[5]CHEN L J.A case driven application system analysis and design method[J].Computer Applications and Software,2002,(4):42-45.
[6]HAO J S.Design and research of intelligent systems based onbig data analysis[J].Information Systems Engineering,2022,35(2):37-40.
[7]GUO S R.Research on machine reading understanding method based on frame semantic representation[D].Taiyuan:Shanxi University,2021.
[8]JIN Z L,ZHU H Y,SU Y L,et al.Research on answer selection methods based on multi granularity interactive reasoning[J].Chinese Journal of Information Technology,2023,37(1):104-111,120.
[9]WEI X C.Research on multi perspective feature fusion answerselection method based on relation reasoning and text understanding[D].Beijing:Beijing University of Technology,2018.
[10]CHENG S Y,GUO Z Y,LIU W,et al.Research on natural language reasoning with fusion attention multi granularity sentence interaction[J].Small Micro Computer System,2019,40(6):1215-1220.
[11]WANG X,SUN J P,JU S G,et al.Reasoning over intra-document and jointly matching question and candidate answer to the passage based multiple-choice Reading Comprehension[J].Journal of Sichuan University:Natural Science Edition,2019,56(3):423-430.
[12]ZHANG H,WANG Y J,LI R,et al.A machine reading comprehension multi hop inference model and method for enhancing syntactic relationships:CN202011410644.X[P].2021-2-26.
[13]YUBO X,PEARL P.How Commonsense Knowledge Helpswith Natural Language Tasks:A Survey of Recent Resources and Methodologies[J].arXiv:2108.04674,2021.
[14]BOS J H.A survey of computational semantics:representation,inference and knowledge in wide-coverage text understanding[J].Language and Linguistics Compass,2011(6):336-366.
[15]CHEN P,DING W,DING C.SenseNet:A knowledge representation model for computational semantics[C]// IEEE 2006 5th IEEE International Conference on Cognitive Informatics.Beijing,China,2006:434-439.
[16]ZHANG J H,ZHANG S W,LIN H F,et al.Humor level recognition based on multi granularity semantic interactive understanding network[J].Chinese Journal of Information Technology,2022,36(3):10-18.
[17]DING Z X.Research on machine reading comprehension method based on BERT[D].Beijing:Beijing Institute of Printing,2022.
[18]WANG Y,WANG W,CHEN Q,et al.Fusing external know-ledge resources for natural language understanding techniques:A survey[J].Information Fusion,2023,92:190-204.
[19]CHAN S W K,FRANKLIN J.Dynamic context generation for natural language understanding:a multifaceted knowledge approach[J].IEEE transactions on systems,man,and cybernetics.Part A,Systems and humans,2003,33(1):23-41.
[20]ZHU S X.A cognitive linguistic study of XYZ construction metaphor[D].Nanjing:Nanjing Normal University,2012.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!