Human-machine cooperation intelligent control method and system based on AIGC and storage medium
Through AIGC's human-computer collaborative intelligent control method, multimodal data and holographic perception feature encoding, the instruction conversion and execution of large language models in human-computer interaction is optimized, solving the problem of uncertainty in the generated content and achieving more accurate results and efficient operation reduce the iteration cost of collective intelligence.
Patent Information
- Application Number
- CN202310598259.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-24
- Publication Date
- 2024-11-26
AI Technical Summary
There is uncertainty in the content generated by large language models in human-computer interaction, especially in precise devices such as autonomous vehicles and industrial robots, which affect the precise execution of instructions.
Using AIGC-based human-machine collaborative intelligent control method, through the interaction between biological intelligence, collective intelligence and artificial intelligence, the holographic perception feature encoding of multimodal data and the Transformer attention mechanism are used to construct a context training set from cause to effect. and knowledge graphs, form goals and constraints to limit generation methods, and optimize instruction conversion and execution processes.
It reduces the iteration and training costs of collective intelligence, improves the perception, reasoning and decision-making capabilities of human-computer collaborative intelligent control systems, achieves more accurate operations and more efficient information transmission, and supports the coding capabilities of silicon-based artificial life.
Smart Images

Figure CN119024723A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a human-machine collaborative intelligent control method, system and storage medium based on AIGC. Background Art
[0002] The emergence of large language models with transformer technology as the core algorithm has made content generation faster and more accurate.
[0003] In 2017, Google released a paper on transformers, which described a language model that has strong language generation after inputting expected data and training; in 2022, the number of parameters of GPT3.5 reached 175 billion, which is higher than the number of neurons in the human brain, which is about 14 billion. Language models with tens of billions of parameters or more are usually called large language models, and are referred to as large models when there is no ambiguity. With the emergence of large language models (LLMs), content generation includes dozens of common human languages and hundreds of common programming languages, and multi-modal content generation is achieved through the mechanism of converting language into media forms such as pictures, where multi-modality includes voice, pictures, videos, etc.
[0004] However, the large language model is still a statistical probability model, which means that the generated content may be biased. If the content is only used for communication and exchange, the uncertainty of information can be reduced through continuous communication. However, in human-computer interaction, especially in the process of giving instructions to precise equipment such as self-driving cars, industrial robots, and industrial machine tools, the uncertainty in the generated content will become a problem in the human-computer collaboration process.
[0005] On the other hand, due to the objective existence of the complexity of the human brain and the imprecision of language, simply relying on understanding human instructions and executing them is not enough to perform precise operations. Summary of the invention
[0006] In order to solve the technical problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a human-machine collaborative intelligent control method, system and storage medium based on AIGC, which is conducive to the balanced development of artificial intelligence AI, biological intelligence BI and collective intelligence CI, reduces the iteration and training costs of collective intelligence CI, realizes autonomous development and evolution, and gradually optimizes the perception, reasoning, decision-making and action execution functions of the human-machine collaborative intelligent control system based on AIGC.
[0007] To achieve the above-mentioned object of the invention, the present invention provides a human-machine collaborative intelligent control method based on AIGC, comprising the following steps:
[0008] Step S10, the biological intelligence BI sends a command message to the collective intelligence CI;
[0009] Step S20, the collective intelligence CI converts the instruction information into a control instruction;
[0010] Step S30: After receiving and executing the control instruction, the artificial intelligence AI displays it to the user;
[0011] Step S40: The user feeds back correction instructions to the collective intelligence CI based on the displayed content of the artificial intelligence AI.
[0012] According to one aspect of the present invention, it also includes:
[0013] Step S50, repeatedly execute step S10 to step S40 until the result output by the artificial intelligence AI meets the constraint conditions and the target reaches the acceptable threshold range of the biological intelligence BI.
[0014] According to one aspect of the present invention, the instruction information of step S10 is multimodal data, and the collective intelligence CI is equipped with feature encoding of the multimodal data. A feature vector is generated by encoding and compressing the input multimodal data, and the original information can be decoded from the feature vector.
[0015] According to one aspect of the present invention, the feature coding of the multimodal data adopts a feature coding method of holographic perception, and the feature coding of holographic perception has the property of locally reflecting the overall characteristics, and the collective intelligence CI has the analytical ability to map the local holographic feature coding to the global feature information with a certain probability and confidence interval.
[0016] According to one aspect of the present invention, the artificial intelligence AI, the biological intelligence BI and the collective intelligence CI use goals and constraints to limit the generation, forming the intention of the human-machine collaborative intelligent control method.
[0017] The goal is to maximize the probability that the CI-generated content instructs AI to perform operations that comply with the instructions issued by BI;
[0018] The constraints refer to the realistic conditions that constrain the AI's execution capabilities, including the machine's power, speed, acceleration, position range, control capabilities, etc.
[0019] According to one aspect of the present invention, the self-adjusting parameters generated in step S20 and step S30 are used for feedback adjustment of the human-machine collaborative intelligent control method.
[0020] According to one aspect of the present invention, the collective intelligence CI is obtained by constructing a contextual training set from cause to effect and training based on the attention mechanism of Transformer.
[0021] According to one aspect of the present invention, the collective intelligence CI is also configured with a knowledge graph preset by a user, the word vectors of the knowledge graph partially overlap with the word vectors of the context training set, and the weight parameter information of the overlapping part can be obtained by the user preset value.
[0022] According to one aspect of the present invention, in step S20, it includes:
[0023] Step S201, the collective intelligence CI calls the knowledge graph;
[0024] Step S202: Convert the instruction information into control instructions based on the knowledge graph.
[0025] According to one aspect of the present invention, there is provided a human-machine collaborative intelligent control system for implementing a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions, which consists of three parts: artificial intelligence AI, biological intelligence BI and collective intelligence CI.
[0026] According to one aspect of the present invention, a computer-readable storage medium is provided for storing computer instructions. When the computer instructions are executed by a processor, a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions is implemented.
[0027] According to one aspect of the present invention, a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions is proposed and applied to a robot.
[0028] According to one aspect of the present invention, a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions is proposed and applied to intelligent manufacturing.
[0029] According to one aspect of the present invention, a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions is proposed, which is applied to unmanned vehicle navigation.
[0030] Compared with the prior art, the present invention has the following beneficial effects:
[0031] The present invention proposes a human-machine collaborative intelligent control method, system and storage medium based on AIGC. Through the interaction between artificial intelligence AI, biological intelligence BI and collective intelligence CI, the interaction capability is iteratively improved during the interaction process, making artificial intelligence AI and collective intelligence CI more accurate, which is conducive to the balanced development of artificial intelligence AI, biological intelligence BI and collective intelligence CI, reduces the iteration and training cost of collective intelligence CI, realizes autonomous development and evolution, and gradually optimizes the perception, reasoning, decision-making and action execution functions of the human-machine collaborative intelligent control system based on AIGC, provides coding capability support for the emergence of silicon-based artificial life, and has the characteristics of complexity and diversity. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0033] Figure 1 A flowchart of a human-machine collaborative intelligent control method based on AIGC is schematically shown according to an embodiment of the present invention;
[0034] Figure 2 Schematically showing the interaction structure between artificial intelligence AI, biological intelligence BI and collective intelligence CI in an embodiment of the present invention;
[0035] Figure 3 The specific flow chart of step S20 in the embodiment of the present invention is schematically shown;
[0036] Figure 4 The flowchart of the human-machine collaborative intelligent control method based on AIGC provided in another embodiment of the present invention is schematically shown. DETAILED DESCRIPTION
[0037] The description of the embodiments of this specification should be combined with the corresponding drawings, which should be considered as part of the complete specification. In the drawings, the shape or thickness of the embodiments may be enlarged and indicated for simplification or convenience. Furthermore, the parts of each structure in the drawings will be described separately. It is worth noting that the elements not shown in the drawings or not described in words are in a form known to ordinary technicians in the relevant technical field.
[0038] The description of the embodiments herein and any reference to directions and orientations are only for the convenience of description and are not to be construed as any limitation on the scope of protection of the present invention. The following description of the preferred embodiments may involve combinations of features, which may exist independently or in combination, and the present invention is not particularly limited to the preferred embodiments. The scope of the present invention is defined by the claims.
[0039] like Figure 1 , Figure 2 and Figure 4 As shown, a human-machine collaborative intelligent control method based on AIGC of the present invention comprises the following steps:
[0040] Step S10, the biological intelligence BI sends a command message to the collective intelligence CI;
[0041] Step S20, the collective intelligence CI converts the instruction information into a control instruction;
[0042] Step S30: After receiving and executing the control instruction, the artificial intelligence AI displays it to the user;
[0043] Step S40: The user feeds back correction instructions to the collective intelligence CI based on the displayed content of the artificial intelligence AI.
[0044] In this embodiment, a new interaction mode between artificial intelligence AI, biological intelligence BI and collective intelligence CI is proposed. Through the interaction between artificial intelligence AI, biological intelligence BI and collective intelligence CI, the interaction capability is iteratively improved during the interaction process, which is conducive to the balanced development of artificial intelligence AI, biological intelligence BI and collective intelligence CI, reduces the iteration and training costs of collective intelligence CI, realizes autonomous development and evolution, and gradually optimizes the perception, reasoning, decision-making and action execution functions of the human-machine collaborative intelligent control system based on AIGC, providing coding capability support for the emergence of silicon-based artificial life, which is characterized by complexity and diversity.
[0045] Among them, AIGC, the full name of which is "AI generated content", is also called generative AI, which means artificial intelligence generates content. Artificial intelligence AI refers to the ability of machines to perform tasks that require human intelligence, and biological intelligence BI refers to the cognitive ability of organisms (including humans). It can be understood that biological intelligence BI refers to humans, which may be the user itself, or a proxy human who can express user needs. Collective intelligence CI here refers to the large language model represented by GPT, which is a summary of past knowledge trained based on massive human data.
[0046] Specifically, the core of the human-machine collaborative intelligent control method based on AIGC of the present invention is to change the goal of collective intelligence CI training from generating human-expected statements with the maximum probability to how to maximize the probability of consistency between the results of artificial intelligence AI executing the instructions generated by biological intelligence BI through collective intelligence CI and the expected results of biological intelligence BI.
[0047] Furthermore, the execution capability of artificial intelligence AI and biological intelligence BI according to the execution results of artificial intelligence AI are added to the "language intelligence" based on the original language model of biological intelligence BI->collective intelligence CI->biological intelligence BI, forming a "behavioral intelligence" cycle of "biological intelligence BI-language->collective intelligence CI-instructions->artificial intelligence AI-execution results->biological intelligence BI-->confirmation status, language feedback again-->collective intelligence CI".
[0048] like Figure 4 As shown, in one embodiment of the present invention, preferably, it also includes:
[0049] Step S50, repeatedly execute step S10 to step S40 until the result output by the artificial intelligence AI meets the constraint conditions and the target reaches the acceptable threshold range of the biological intelligence BI.
[0050] In this embodiment, the result of the artificial intelligence AI output is used as a constraint condition, and the acceptable threshold range of the biological intelligence BI is used as a target condition. The interaction capability is iteratively improved during the interaction process, making the artificial intelligence AI and collective intelligence CI more accurate.
[0051] In one embodiment of the present invention, preferably, the instruction information of step S10 is multimodal data, and the collective intelligence CI is equipped with feature encoding of the multimodal data. A feature vector is generated by encoding and compressing the input multimodal data, and the original information can be decoded from the feature vector.
[0052] In this embodiment, the human-machine collaborative intelligent control system uses multimodal data (vision, laser, sound, touch, etc.) as input and utilizes the holographic perception function to increase information density, which is beneficial to reducing the data volume requirement, increasing the coordination among artificial intelligence AI, the biological intelligence BI and the collective intelligence CI, and the efficiency of information transmission in the cycle process, making the information transmission between artificial intelligence AI, the biological intelligence BI and the collective intelligence CI more efficient, without the need to construct a full data set of the original sensor, and efficient storage can be achieved with the help of holographic perception coding.
[0053] In one embodiment of the present invention, preferably, the feature coding of the multimodal data adopts a feature coding method of holographic perception, and the feature coding of holographic perception has the property of locally reflecting the overall characteristics, and the collective intelligence CI has the analytical ability to map the local holographic feature coding to the global feature information with a certain probability and confidence interval.
[0054] In one embodiment of the present invention, preferably, the artificial intelligence AI, the biological intelligence BI and the collective intelligence CI adopt a method of limiting generation by using goals and constraints to form the intention of the human-machine collaborative intelligent control method, and the goal refers to maximizing the probability that the CI-generated content guides the AI to perform operations in accordance with the instructions issued by the BI;
[0055] The constraints refer to the realistic conditions that constrain the AI's execution capabilities, including the machine's power, speed, acceleration, position range, control capabilities, etc.
[0056] In one embodiment of the present invention, preferably, the self-adjusting parameters generated in step S20 and step S30 are used for feedback adjustment of the human-machine collaborative intelligent control method.
[0057] In one embodiment of the present invention, preferably, the collective intelligence CI is obtained by constructing a context training set from cause to effect and training based on the attention mechanism of Transformer.
[0058] In one embodiment of the present invention, preferably, the collective intelligence CI is also configured with a knowledge graph preset by a user, the word vectors of the knowledge graph partially overlap with the word vectors of the context training set, and the weight parameter information of the overlapping part can be obtained by the user preset value.
[0059] like Figure 2 and Figure 3 As shown, in one embodiment of the present invention, preferably, in the step S20, it includes:
[0060] Step S201, the collective intelligence CI calls the knowledge graph;
[0061] Step S202: Convert the instruction information into control instructions based on the knowledge graph.
[0062] According to one aspect of the present invention, there is provided a human-machine collaborative intelligent control system for implementing a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions, which consists of three parts: artificial intelligence AI, biological intelligence BI and collective intelligence CI.
[0063] According to one aspect of the present invention, a computer-readable storage medium is provided for storing computer instructions. When the computer instructions are executed by a processor, a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions is implemented.
[0064] Computer readable storage media may include any medium capable of storing or transmitting information. Examples of computer readable storage media include electronic circuits, semiconductor memory systems, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. Code segments may be downloaded via computer networks such as the Internet, intranets, etc.
[0065] According to one aspect of the present invention, a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions is proposed and applied to a robot.
[0066] According to one aspect of the present invention, a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions is proposed and applied to intelligent manufacturing.
[0067] According to one aspect of the present invention, a human-machine collaborative intelligent control method based on AIGC as described in any one of the above technical solutions is proposed, which is applied to unmanned vehicle navigation.
[0068] The present invention discloses a human-machine collaborative intelligent control method, system and storage medium based on AIGC. The human-machine collaborative intelligent control method based on AIGC includes: step S10, biological intelligence BI sends instruction information to collective intelligence CI; step S20, the collective intelligence CI converts the instruction information into control instructions; step S30, artificial intelligence AI receives and executes the control instructions and displays them to the user; step S40, the user feeds back the correction instructions to the collective intelligence CI based on the display content of the artificial intelligence AI; through the interaction between artificial intelligence AI, biological intelligence BI and collective intelligence CI, the interaction capability is iteratively improved during the interaction process, so that artificial intelligence AI and collective intelligence CI are more accurate, which is conducive to the balanced development of artificial intelligence AI, biological intelligence BI and collective intelligence CI, reduces the iteration and training cost of collective intelligence CI, realizes autonomous development and evolution, and gradually optimizes the perception, reasoning, decision-making and action execution functions of the human-machine collaborative intelligent control system based on AIGC, provides coding capability support for the emergence of silicon-based artificial life, and has the characteristics of complexity and diversity.
[0069] In addition, it should be noted that the present invention can be provided as a method, an apparatus or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.
[0070] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal systems (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal system to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal system generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0071] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal system to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded into a computer or other programmable data processing terminal system, so that a series of operation steps are executed on the computer or other programmable terminal system to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal system provide the functions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0072] It should also be noted that, in this article, the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal system. In the absence of more restrictions, an element defined by the sentence "comprising a ..." does not exclude the existence of other identical elements in the process, method, article or terminal system including the element.
[0073] Finally, it should be noted that the above is a preferred embodiment of the present invention. It should be pointed out that although the preferred embodiment of the present invention has been described, for those skilled in the art, once the basic creative concept of the present invention is known, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.
Claims
1. A human-machine collaborative intelligent control method based on AIGC, It is characterized in that The following steps are involved: Step S10, the biological intelligence BI sends a command message to the collective intelligence CI; Step S20, the collective intelligence CI converts the instruction information into a control instruction; Step S30: After receiving and executing the control instruction, the artificial intelligence AI displays it to the user; Step S40: The user feeds back correction instructions to the collective intelligence CI based on the displayed content of the artificial intelligence AI.
2. According to the AIGC-based human-machine collaborative intelligent control method of claim 1, It is characterized in that Also includes: Step S50, repeatedly execute step S10 to step S40 until the result output by the artificial intelligence AI meets the constraint conditions and the target reaches the acceptable threshold range of the biological intelligence BI.
3. According to the AIGC-based human-machine collaborative intelligent control method of claim 1, It is characterized in that The instruction information of step S10 is multimodal data, and the collective intelligence CI is equipped with feature coding of the multimodal data. A feature vector is generated by encoding and compressing the input multimodal data, and the original information can be decoded from the feature vector.
4. According to the AIGC-based human-machine collaborative intelligent control method of claim 3, It is characterized in that The feature coding of the multimodal data adopts the feature coding method of holographic perception. The feature coding of holographic perception has the property of locally reflecting the overall characteristics. The collective intelligence CI has the analytical ability to map the local holographic feature coding to the global feature information with a certain probability and confidence interval.
5. According to the AIGC-based human-machine collaborative intelligent control method of claim 4, It is characterized in that The artificial intelligence AI, the biological intelligence BI and the collective intelligence CI use goals and constraints to limit the generation method, forming the intention of the human-machine collaborative intelligent control method. The goal is to maximize the probability that the CI-generated content instructs AI to perform operations that comply with the instructions issued by BI; The constraints refer to the realistic conditions that constrain the AI's execution capabilities, including the machine's power, speed, acceleration, position range, control capabilities, etc.
6. According to the AIGC-based human-machine collaborative intelligent control method of claim 1, It is characterized in that The self-adjusting parameters generated in step S20 and step S30 are used for feedback adjustment of the human-machine collaborative intelligent control method.
7. According to the AIGC-based human-machine collaborative intelligent control method of claim 1, It is characterized in that The collective intelligence CI is obtained by constructing a contextual training set from cause to effect and training based on the Transformer's attention mechanism.
8. According to the AIGC-based human-machine collaborative intelligent control method of claim 7, It is characterized in that The collective intelligence CI is also configured with a knowledge graph preset by a user. The word vectors of the knowledge graph partially overlap with the word vectors of the context training set, and the weight parameter information of the overlapping part can be obtained by the user preset value.
9. The human-machine collaborative intelligent control method based on AIGC according to claim 1, It is characterized in that In the step S20, it includes: Step S201, the collective intelligence CI calls the knowledge graph; Step S202: Convert the instruction information into control instructions based on the knowledge graph.
10. A human-machine collaborative intelligent control system for implementing the AIGC-based human-machine collaborative intelligent control method according to any one of claims 1 to 9, It is characterized in that It consists of three parts: artificial intelligence AI, biological intelligence BI and collective intelligence CI.
11. A computer-readable storage medium, It is characterized in that Used to store computer instructions, which, when executed by a processor, implement the AIGC-based human-machine collaborative intelligent control method as described in any one of claims 1 to 9.
12. A human-machine collaborative intelligent control method based on AIGC as claimed in any one of claims 1 to 9, It is characterized in that Applied to robots.
13. A human-machine collaborative intelligent control method based on AIGC as claimed in any one of claims 1 to 9, It is characterized in that Applied to smart manufacturing.
14. A human-machine collaborative intelligent control method based on AIGC as claimed in any one of claims 1 to 9, It is characterized in that Applied to unmanned vehicle navigation.
Citation Information
Patent Citations
Collective intelligence evaluation machine suitable for multiple heterogeneous intelligent agents and implementation method thereof
CN110874312A
Intelligent equipment control method and device, readable storage medium and computer equipment
CN112415908A
Swarm intelligence emergence calculation service platform based on artificial intelligence
CN113850388A
Behavior decision-making method and device of man-machine interaction equipment, equipment and storage medium
CN115186829A
AI application deployment method and related platform, cluster, medium and program product
CN115237428A
Cited By
Man-machine cooperation intelligent control system based on AIGC
CN119940425A
A human-machine collaborative intelligent control system based on AIGC
CN119940425B
Intelligent agent service system based on domestic operating system
CN120029517A
