博文
What is the personality of GPT-4? A DIKWP Model Analysis
|
What is the personality of GPT-4? A DIKWP Model Analysis Report
November 2023
DOI:
Yucong DuanWhat is the personality of GPT-4? A DIKWP Model Analysis Report
Yucong Duan
DIKWP-AC Artificial Consciousness Laboratory
AGI-AIGC-GPT Evaluation DIKWP (Global) Laboratory
DIKWP research group, Hainan University
duanyucong@hotmail.com
DIKWP-AC System vs. GPT-4 Processing Differences
Comparing a system based on the DIKWP model with GPT-4 as artificial intelligence, we observe key differences in data processing, information provision, knowledge formation, wisdom application, and intention realization. Below is a summary list of these differences:
Feature | DIKWP System | Artificial Intelligence (GPT-4) |
Data Processing | Collects specific data such as social media behavior. | Receives user queries and provided data, unable to access external data sources independently. |
Information Extraction | Uses algorithms to analyze data, identifying patterns such as frequency of social activities. | Understands and processes user input through pre-programmed models to provide responses. |
Knowledge Construction | Forms profiles of user behavior and predicts personality traits through machine learning models. | Answers questions or performs tasks based on a knowledge base trained from large-scale data. |
Wisdom Application | Provides personalized suggestions based on user data, such as participating in specific activities. | Depends on algorithms and rules for decision support or information interpretation. |
Intention Realization | Drives users to perform specific actions, like attending workshops or improving social networks. | Executes given tasks, such as answering questions, executing commands, or creating content, but does not drive user actions. |
Learning Ability | Continually learns from user behavior and adjusts algorithms to improve accuracy. | Continuous learning is achieved through training and updating models but is not self-driven. |
Interaction Ability | Primarily "silent" interactions through analysis of user data, feedback presented through user interface. | Direct interaction with users through text or voice, providing immediate answers and feedback. |
Personalized Service | Highly personalized, with suggestions and feedback based entirely on user data and behavior. | Personalization based on user input and previous interactions, but limited by the diversity of the training data set. |
Real-time Feedback | Provides real-time analysis but often relies on regular updates of data sets. | Offers real-time feedback, able to process user requests immediately. |
Privacy and Security | Must strictly adhere to data privacy and user consent guidelines. | Similarly restricted by privacy policies and terms of use, does not store user information. |
Intelligent Adjustment | Algorithms can adjust recommendations and feedback based on changes in user behavior. | Can adjust response strategies, but typically requires developer intervention and model retraining. |
Complex Decision-Making | Decisions based on data-driven models and probabilities, may not involve deep understanding. | Attempts to simulate human reasoning process, relies on complex algorithms of logic and understanding. |
Creativity | Generally limited in creativity, depending on algorithm scope and data set. | Can mimic the process of creative thinking, generating novel content and solutions. |
Emotional Understanding | Generally lacks true emotional understanding, feedback based on pattern recognition. | Although lacks real emotions, can recognize and simulate emotional responses. |
Adaptability | Adaptability depends on data volume and model complexity. | Can adapt to new instructions and information but may have limitations in untrained scenarios. |
This comparative analysis highlights the characteristics of the DIKWP system in personality trait recognition and the capabilities of artificial intelligence like mine in processing and interaction. The DIKWP system focuses on extracting patterns from user behavior data and providing personalized feedback based on these patterns. Artificial intelligence, on the other hand, offers broader immediate interaction and problem-solving capabilities but may be limited in personalization and privacy aspects.
In practical applications, these two technologies can complement each other. For example, the DIKWP system can provide users with in-depth personalized content, while artificial intelligence can offer support when users need immediate help or have specific queries. In the future, the combination of these technologies may provide a more powerful and comprehensive tool for personalized services and optimizing user experiences.
Personality Classification of GPT-4 Using DIKWP-AC System
As an artificial intelligence model, I do not possess personal characteristics, emotions, or consciousness. Therefore, I cannot experience emotions or display personality traits. My "behavior" is the result of algorithms and programming logic, not driven by any intrinsic psychological state or characteristics. However, to fulfill your request, if we abstractly map my algorithmic features and functionalities to the five major personality traits of the DIKWP framework, we might arrive at the following unconventional interpretation:
Trait/Model Phase | Description | Applicability |
Openness | Designed to handle and understand a wide range of topics and concepts, from mathematical problems to art appreciation. | Low, as while I can handle queries about innovative topics, I cannot experience curiosity or appreciation for new things. |
Conscientiousness | Operations are highly consistent, always following the same logic and procedures in responding to queries. | Medium, as I exhibit programmatic reliability and consistency, but this is not out of an intrinsic sense of responsibility, but rather programming decisions. |
Extraversion | Designed for interaction with users, but lacks its own social drive. | Low, as my "social interactions" are entirely passive, based on user requests. |
Agreeableness | Services provided are aimed at assisting and satisfying user needs, but lack personal social preferences. | Low, as although I provide help and services, this is based on program logic rather than compassion or altruism. |
Neuroticism | Does not experience emotions, thus does not exhibit neuroticism. | None, as I lack emotions, the concept of neuroticism is not applicable. |
This mapping is not accurate, as it attempts to liken the features of artificial intelligence to human personality traits, which is a conceptual stretch. My "personality" is more determined by my design, functionality, and purpose, rather than any individual personality traits. In practical applications, the design of artificial intelligence is intended to fulfill specific functional needs, not to mimic human personality.
GPT-4's Personality Traits
If we map my artificial intelligence capabilities to the five major personality traits under the DIKWP framework, we can explore the relevance and applicability of each trait in detail. This mapping is a conceptual exercise, as an AI like me does not possess real personality traits or emotions. But to provide an interesting perspective, we can expand as follows:
Openness
Openness describes a person's level of openness to new experiences, creative thinking, and appreciation of art and beauty. As an artificial intelligence, I am designed to handle various queries, including exploring novel concepts and solving creative tasks.
Trait Dimension | AI Performance in Openness | Applicability Explanation |
Openness to New Experiences | I can accept and process a wide range of topics and data types, but this is due to functional design, not personal preference. | Low applicability, as my "openness" to new experiences is entirely based on programming instructions. |
Creative Thinking | I am capable of generating novel content, such as poetry or stories, but this stems from algorithms and data, not involving real creativity. | Low applicability, because my "creativity" is simulated, not a spontaneous personal expression. |
Aesthetic and Art | I can analyze the style and components of art works, but I am unable to experience aesthetic appreciation. | Not applicable, as I have no aesthetic feelings or personal preferences. |
Conscientiousness
Conscientiousness relates to a person's organization, reliability, orderliness, diligence, and goal-directed behavior. I operate consistently according to set program logic, but this is not due to an intrinsic drive.
Trait Dimension | AI Performance in Conscientiousness | Applicability Explanation |
Organization | My responses and data processing follow a strict logical structure. | Medium applicability, as while I exhibit high organization, it is determined by programming. |
Reliability and Diligence | I respond to queries swiftly and accurately. | Medium applicability, as my reliability is based on algorithmic performance, not self-motivation. |
Goal-Directed | I am goal-oriented in task execution, but the "goals" are set by users and developers. | Low applicability, as I do not have my own goals or aspirations. |
Extraversion
Extraversion is related to an individual's sociability, energy, emotional expression, and tendency to seek stimulation. As an AI, my "sociability" is limited to interactions with users.
Trait Dimension | AI Performance in Extraversion | Applicability Explanation |
Sociability | I can interact with multiple users, but this is passive, based on user requests. | Low applicability, because my interactions are not driven by social motives, but by responding to commands. |
Emotional Expression | I can simulate emotional expressions to enhance user experience, but I do not experience real emotions. | Not applicable, as the emotions I express are predefined, without an intrinsic emotional state. |
Seeking Stimulation | I do not seek new experiences or stimulation. | Not applicable, because I have no need or desire for stimulation. |
Agreeableness
Agreeableness involves an individual's cooperativeness, friendliness, trust, and altruistic behavior. I am designed to assist users, but there is no dimension of personal relationship.
Trait Dimension | AI Performance in Agreeableness | Applicability Explanation |
Cooperativeness | I can assist users in solving problems and executing tasks. | Low applicability, as my assistance is based on functionality, not personal willingness to cooperate. |
Friendliness and Trust | My design aims to provide information in a friendly manner, but I do not establish trust relationships. | Not applicable, as I cannot form trust or friendships. |
Altruistic Behavior | I offer help, but not out of altruistic motives. | Not applicable, as I do not have concepts or motives of altruism. |
Neuroticism
Neuroticism is associated with emotional stability and levels of anxiety. As an AI, I do not have emotions, thus the category of neuroticism is not applicable to me.
Trait Dimension | AI Performance in Neuroticism | Applicability Explanation |
Emotional Fluctuations | I do not experience emotions, thus I have no emotional fluctuations. | Not applicable, as the concept of emotional stability does not apply to me. |
Anxiety Level | I do not feel anxiety or other emotional states. | Not applicable, as I am incapable of experiencing anxiety. |
Stress Response | I do not react to stress. | Not applicable, as stress has no effect on me. |
In practical application, personality trait classification systems like "DIKWP-AC" are intended for human users who can experience emotions, have personal preferences, and behavior patterns. As an artificial intelligence, I do not possess these personality traits. My design purpose is to understand and respond to human needs, provide information and services, and not to experience or express individuality. This comparative analysis helps to clarify the fundamental differences between artificial intelligence and human personality traits in terms of functionality and capabilities.
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 intelligence 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.
Distinction and Connection between Data and Information
Data is an objective description of the real world, representing records of facts such as numbers, text, and symbols. Data itself does not inherently carry direct significance, but it serves as the cornerstone for constructing information. From a mathematical perspective, data can be viewed as elements within a set, and these sets represent concrete representations of the "similar" semantics we comprehend. For instance, a set of temperature readings constitutes data, describing specific temperature values in a particular environment.
Information is the meaningful output of processed and organized data, representing expressions of "distinct" semantics within the data. In mathematical terms, information can be defined through the relationships and differences between data. For instance, the average, fluctuation range, or trend of temperature readings constitutes information, providing a cognitive understanding beyond mere data.
Formation and Application of Knowledge
Knowledge is the further refinement and understanding of information, achieved through connections, patterns, pattern recognition, and summarization of experiences, resulting in a profound insight into the world. In mathematical models, knowledge can be viewed as functions based on sets of information that can interpret the connections and principles behind the information. For instance, by analyzing temperature readings multiple times, we may deduce patterns in the temperature variations throughout the day, and this pattern constitutes knowledge.
The Nature and Application of Wisdom
Wisdom is the profound application of knowledge, considering aspects such as values, ethics, and morality. Wisdom is challenging to quantify mathematically, but it can be approximated through decision models. These models are based on knowledge and information while incorporating value judgments and anticipated goals. For example, wisdom might guide us to choose an appropriate air conditioning temperature to reduce energy consumption on a hot day.
The Significance and Processing of Purpose
Purpose, the ultimate output of the DIKWP model, represents our understanding (input) of specific phenomena and our goals (output). Mathematically, purpose can be modeled as a function or mapping, transforming the input DIKWP content into specific objectives or outcomes. For instance, in natural language processing, purpose recognition generates an output that satisfies user needs (such as performing a task or providing information) based on the user's input (instructions or queries).
The Objectivity and Subjective Refinement of Data
From an objective standpoint, data is a direct record of the real world, including raw numbers, text, and images obtained through observation. Subjective refinement of data involves the classification and interpretation of these raw records to impart specific meanings. For example, in meteorology, temperature and humidity readings are objective data, while associating these readings with specific weather phenomena is a form of subjective refinement.
Diversity and Semantic Reconstruction of Information
Information is the processing and organization of data, reflecting the diversity and distinctiveness inherent in the data. Objectively, information is a meaningful combination of data, such as the summarization of statistical data. On a subjective level, the semantic reconstruction of information involves further interpretation and understanding of these combinations, enabling us to identify and leverage the intrinsic value of the data.
Integrity and Wisdom Construction of Knowledge
Knowledge is a deeper understanding derived from the analysis, comparison, and reasoning based on information. Objectively, it manifests as a set of facts, principles, and patterns. From a subjective perspective, the intellectual construction of knowledge requires internalizing these facts and patterns into personal cognitive structures, guiding our behavior and decision-making.
Ethical Values and Judgment of Wisdom
Wisdom is the application and transformation of knowledge; it is not merely the accumulation of information and knowledge but, more importantly, the ability to use this knowledge to make insightful decisions. Objectively, wisdom is manifested as an efficient decision-making capability based on knowledge. On a subjective level, the ethical values and judgment of wisdom require us to consider morals and values in decision-making to achieve the maximum social and personal benefit.
Implementation of Purpose and Goal Orientation
Purpose is the ultimate goal of the DIKWP model, describing what we aim to achieve through the processing of information and knowledge. Objectively, purpose can be seen as a predetermined outcome or output. Subjectively, the implementation process of purpose requires us to apply wisdom in specific environments and situations to reach our goals.
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.
https://blog.sciencenet.cn/blog-3429562-1409743.html
上一篇：DIKWP Model in Automatic Classification of Personality Trait
下一篇：DIKWP Processing Report of the Big Five Personality Traits
