51 results about "Thinking processes" patented technology

Systems and methods for guiding or steering thought processes on a persistent cognitive machine (PCM) that uses a continuous, differentiable, thought manifold in geometric space to allow a computer to engage in human-like thought processes. The PCM with thought manifold represents a fundamental advancement in artificial intelligence beyond current probabilistic AI system such as large language models (LLMs) and similar reasoning models. A PCM with cognitive manifold performs cognition on a thought manifold in a continuous, differentiable, thought manifold in geometric space as opposed to probabilistic prediction in a discontinuous, anisotropic, and topologically fractured vector space. Methods for guiding or steering thought processes on the thought manifold are disclosed that involve mathematical manipulations of the geometric space of the thought manifold inspired by gravitational lensing.

A system and method for a digital thought architecture, otherwise called a persistent cognitive machine (PCM), that uses a continuous, differentiable, thought manifold in geometric space to allow a computer to engage in human-like thought processes. The PCM with thought manifold represents a fundamental advancement in artificial intelligence beyond current probabilistic AI system such as large language models (LLMs) and similar reasoning models. Not only does the PCM with thought manifold maintain persistent cognitive processes regardless of external interaction, overcoming limitations of existing AI systems that operate within a prompt-response paradigm where they await input, generate output, and return to a waiting state, it also performs cognition on a thought manifold in a continuous, differentiable, thought manifold in geometric space as opposed to probabilistic prediction in a discontinuous, anisotropic, and topologically fractured vector space. In some embodiments, the thought manifold may be implemented as a neuromorphic platform.

The invention belongs to the technical field of electric power artificial intelligence, and discloses an electric power knowledge question-answering method based on a knowledge reasoning thinking chain embedded large model and a related device. The method comprises the steps of obtaining a power problem text; and inputting the power question text into a pre-trained knowledge reasoning thinking chain embedding large model, and outputting a text answer of the power question. According to the method, a supervised learning and preference optimization mechanism is fused, and collaborative optimization of large-model professional knowledge learning and thinking path modeling is realized by constructing an electric power knowledge question and answer and analyzing a thinking chain data set; the technical problems that an existing large model is weak in knowledge, inconsistent in thinking process and insufficient in generalization ability in power professional text questions and answers are solved.

The invention provides a corpus data generation method and device based on a large model and an intelligent agent, and relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, large models, intelligent questions and answers and the like. The corpus data generation method based on the large model comprises the steps that a content generation task is executed on the basis of a preset requirement condition through the large model, corpus content is obtained, the content generation task comprises multiple target tasks with a dependency relationship, and the multiple target tasks represent the thinking process of the large model for the corpus content to be generated; and based on the corpus content and the thinking process information related to the multiple target tasks, determining target corpus data.

Systems and methods for latent slice budgeting on a persistent cognitive machine (PCM) that uses a continuous, differentiable, cognitive manifold in geometric space to allow a computer to engage in human-like thought processes. The PCM with cognitive manifold represents a fundamental advancement in artificial intelligence beyond current probabilistic AI system such as large language models (LLMs) and similar reasoning models. A PCM with cognitive manifold performs cognition on a thought manifold in a continuous, differentiable, thought manifold in geometric space as opposed to probabilistic prediction in a discontinuous, anisotropic, and topologically fractured vector space. Methods for latent slice budgeting on the cognitive manifold are disclosed that foliation of the cognitive manifold into time slices and budgeting change between the time slices.

The embodiment of the invention provides a model parameter determination method and device, a storage medium and a program product, and the method comprises the steps: processing input data through employing a specified model, so as to generate at least one piece of thinking process information and corresponding answer information, and at least part of the thinking process information corresponds to a plurality of pieces of answer information; performing evaluation processing on the input data based on at least part of the answer information to determine corresponding optimization feedback information; updating at least one parameter of the specified model according to the optimization feedback information; wherein the specified model is a visual language model or a large language model, and the input data comprises at least one of text data, image data and point cloud data. Through multi-answer sampling, optimization feedback of more answer levels can be obtained under the condition that the generation number in the thinking process is reduced or is kept unchanged, so that the training time and the calculation overhead are remarkably reduced, the training efficiency is improved, and the thinking and summarization ability of the model can be improved under limited calculation resources through a training scheme after reinforcement learning.

The application provides a method for generating an answer to a question, an electronic device and a computer program product, and applies to the technical field of artificial intelligence. The method comprises the following steps: in response to an input question to be replied, a plurality of reply rules representing a thinking process in an auxiliary learning scenario are determined; the reply rules are rules that need to be followed when replying to the question; the plurality of reply rules are sorted differently, different thinking processes are simulated based on different sorting results, and the reply content generated under the optimal thinking process is selected as the answer to the question to be replied; wherein the reply content generated under the thinking process is generated based on the reply content corresponding to each reply rule included in the thinking process. The application designs a plurality of reply rules representing a thinking process in an auxiliary learning scenario, and combines different reply rule sequences, so that the reply process can reflect the human thinking process. Compared with directly generating an answer based on model parameters, the intelligent level is improved.

The present invention relates to the technical field of artificial intelligence, and provides a method and apparatus for constructing a human-like answering engine. The method comprises: acquiring a state transition graph of each answering algorithm; respectively merging and integrating input nodes, output nodes, identical key state nodes, and identical state transition paths in all state transition graphs to form an integrated state transition graph; and performing function configuration on the integrated state transition graph to construct a static graph of an answering technique as the human-like answering engine. The method and apparatus for constructing the human-like answering engine provided by the present invention simulate the thought processes of human, and progressively analyze and solve algebraic questions by means of a series of state transitions, so that the answering engine is more flexible and intelligent, and can handle complex and variable question types, thereby expanding the range of answerable questions.

The invention discloses a fine tuning method, system and equipment for an electric power intrinsic safety analysis model based on knowledge distillation, and a medium, and belongs to the technical field of electric power safety analysis. The method comprises the following steps: collecting professional knowledge data in the field of electric power intrinsic safety analysis, and performing professional knowledge supervision fine tuning to obtain a distillation model; and guiding an output thinking process and a root cause based on problem description through the distillation model, and introducing a super model and a causal knowledge graph for evaluation to obtain an evaluation result. Through combination of knowledge distillation and the causal knowledge graph, the accuracy and interpretability of an electric power intrinsic safety analysis inference model are remarkably improved, the thinking process and the root cause of problem description are generated through the distillation model, output is evaluated by using the super model and the causal knowledge graph, the causal inference ability is enhanced, and the accuracy and the interpretability of the electric power intrinsic safety analysis inference model are improved. The problem that the causal relationship of a traditional model is fuzzy in complex power accident analysis is effectively solved.

Systems and methods for persistence of memory on a persistent cognitive machine (PCM) that uses a continuous, differentiable, cognitive manifold in geometric space to allow a computer to engage in human-like thought processes. The PCM with cognitive manifold represents a fundamental advancement in artificial intelligence beyond current probabilistic AI system such as large language models (LLMs) and similar reasoning models. A PCM with cognitive manifold performs cognition on a thought manifold in a continuous, differentiable, thought manifold in geometric space as opposed to probabilistic prediction in a discontinuous, anisotropic, and topologically fractured vector space. Persistence of memory is reflected on the cognitive manifold through relative displacements between geodesics after a reasoning trajectory has been calculated in a manner analogous to gravitational wave echoes in general relativity physics.

The invention relates to a visual thinking chain, in particular to a bionic visual thinking chain cross-modal model based on eye movement tracking and a visualization system and method, and solves the technical problems that an existing visual thinking chain model lacks real visual thinking process simulation and is difficult to establish a visual thinking chain conforming to a real human visual thinking mode. According to the bionic visual thinking chain cross-modal model based on eye movement tracking, the to-be-detected image eye movement gazing area image blocks from eye movement tracking data and the gazing sequence and the gazing duration of the to-be-detected image eye movement gazing area image blocks are adopted, and the dynamic characteristics and the time sequence mode of human visual cognition can be truly reflected; the big language model is made to process visual information step by step according to the sequence of human eye movement tracks, a human real visual thinking mode is simulated, and therefore a real visual thinking chain is established; besides, an eye movement vector prediction matrix and an eye movement prediction text answer can be obtained, so that a bionic visual thinking chain and a text thinking chain are output at the same time, and the interpretability of the thinking process after the text and the image are fused is improved.

The invention discloses a Chinese grammar error correction multi-task training method based on thinking process distillation, which comprises the following steps: in a data construction stage, guiding a DeepSeek model by utilizing a designed constraint condition and a prompt project, and taking the DeepSeek model as a teacher model, in a training stage, taking a small-volume large language model as a student model to learn knowledge of the teacher model, and taking a small-volume large language model as a student model to learn the knowledge of the teacher model. The semantic comprehension ability of a teacher model is migrated from multiple dimensions by combining structured supervision and a multi-task learning mechanism, so that tasks are mutually enhanced, the same wrong sentence can be trained at the same time in multiple dimensions, and the model is promoted to learn more universal and more robust feature representation; according to the method, an end-to-end interpretable error correction process is realized, a user is helped to understand a model decision basis, and an error correction analysis and display process is added; the features of different dimensions are aligned in the multi-task learning process, so that the model learns more universal and more robust feature representation, and the generalization ability of the model in complex grammar error, composite error and zero sample scenes is remarkably improved.

The application discloses a trial finding text generation method and related device, and relates to the technical field of artificial intelligence, which comprises the following steps: normalizing a plurality of evidence data of a target case into a structured evidence list, taking an evidence item in the evidence list as an evidence node, taking a fact element extracted from the evidence list as a fact node, constructing an evidence fact correlation graph, the edge relationship in the evidence fact correlation graph comprises a contradiction relationship, inputting the evidence fact correlation graph into a graph neural network model for feature transmission and aggregation between nodes, obtaining updated features of each fact node, and determining a dispute focus node and a non-dispute node from each fact node according to the fact credibility in the updated features and the contradiction relationship in the evidence fact correlation graph, and generating a trial finding text in a judgment according to the dispute focus node and the non-dispute node. The application simulates the reasoning thinking process of judges in determining facts by the graph node feature transmission process, and improves the accuracy and efficiency of fact determination.

The invention discloses an interpretable sleep staging method based on training after visual language model supervision fine tuning, which comprises the following steps: acquiring multi-channel sleep data and a corresponding sleep reasoning text to construct a data set; performing numbering based on interpretation rules related to sleep in clinical rule knowledge to construct a corresponding rule base; taking a pre-trained visual language model as a basic model, and performing supervision fine tuning training on the basic model through the data set to obtain a visual language model; multi-channel sleep data to be analyzed and preset cue words are input into the visual language model to generate a structured JSON result, and the JSON result comprises a sleep stage label, a judgment reason text and a rule number list of related interpretation rules. The invention further provides a device capable of explaining sleep staging. According to the method provided by the invention, the thinking process of experts can be simulated, so that comprehensive data support conforming to clinical rules is provided for each sleep staging result.

The invention discloses a medical history collection system supporting clinical thinking path recognition, and belongs to the technical field of medical information. The system comprises a hypothesis agent cluster management module used for initializing an agent cluster composed of a plurality of hypothesis agents based on a clinical knowledge graph, each hypothesis agent corresponding to a candidate disease and comprising static knowledge related to the candidate disease; the doctor-patient interaction interface module is used for receiving the initial clinical evidence and analyzing the initial clinical evidence into an initial clinical evidence state vector; the dynamic evidence processing and state evolution engine is used for iteratively driving the state evolution of the agent cluster; and the thinking path generation and visualization module is used for generating a clinical thinking path according to the state evolution process of the agent cluster. The technical problem that the dynamic and nonlinear diagnosis thinking process of clinicians cannot be effectively captured and restored in the prior art is solved.

The invention relates to the technical field of operation and maintenance of communication operators, in particular to a method and system for complementing a positioning rule based on large model reasoning ability, and the method comprises the following steps: fault feature and tool preparation, cue word framework construction, thinking process generation and expert auditing, rule generation and current network verification, and feedback optimization mechanism. The method has the beneficial effects that by virtue of the reasoning capability of the Deepseek large model, the rule data of fault diagnosis is generated by continuously adjusting the input conditions such as the fault feature library and the fault diagnosis tool. Supplementing or perfecting a current network fault positioning rule; the problems of high expert dependency, insufficient rule credibility, difficulty in verification and the like in a traditional rule are solved, the time investment of experts is reduced, and the existing rule is perfected; an efficient, credible and iterable fault positioning mechanism is realized, and the intelligent level of network operation and maintenance is improved.

A method for controlling an artificial intelligence (AI) device can include receiving a user query, retrieving safe and unsafe trajectories from a trajectory history database, providing the user query, the at least one safe trajectory, and the at least one unsafe trajectory to an actor agent configured as a first large language model, generating, by the actor agent, a proposed action and a thought process for performing a step related to the task based on the at least one safe trajectory and the at least one unsafe trajectory. Also, the method can further include providing the proposed action and the thought process to a critic agent configured as a second large language model, generating, by the critic agent, a feedback critique of the proposed action, and executing, by the actor agent, a final action in an environment based on the feedback critique from the second large language model.

The invention discloses a visual shared whiteboard system and method for solving a group collaboration mathematical problem, and belongs to the technical field of computer science and human-computer interaction crossing. The system comprises a multi-modal fusion input module used for converting input such as handwriting and voice into a structured mathematical object; the real-time semantic understanding and knowledge graph engine is used for constructing a collaborative cognitive model; the collaborative process management module based on the directed hypergraph is used for carrying out formalized modeling and navigation on a nonlinear problem solving process; the context-aware intelligent auxiliary module is used for providing verification, recommendation and guiding consensus achievement; and a multi-user cooperation engine ensures stable cooperation experience. According to the method, the problems of professional expression, real-time cooperation splitting, group thinking process management difficulty and the like are solved, and a unified, intelligent and efficient integrated cooperation environment is provided for group solving of complex mathematical problems.

The invention discloses a micro-course extraction method, a related method and a related device, and relates to the technical field of resource fragmentization, and the micro-course extraction method comprises the steps: obtaining a target course video of a target subject; analyzing the content of the target course video, and generating target text data with a timestamp; performing knowledge point slicing on the target text data based on a large slicing model to obtain a segmentation result at least comprising starting and ending time of a knowledge point fragment, and adopting training text data marked with a real knowledge point segmentation result by the large slicing model, and meanwhile, obtaining thinking process data of the real knowledge point segmentation result in an assisted manner to obtain a knowledge point segmentation result; training the general large model base to obtain training text data, wherein the training text data is text data corresponding to course video samples of the target subject; and extracting the knowledge point video clip from the target course video according to the starting and ending time of the knowledge point clip to obtain a knowledge point video micro-course. The micro-course extraction method disclosed by the invention can automatically extract the accurate knowledge point video micro-course from the course video.

This invention relates to the field of financial technology and discloses a business processing method, electronic device, storage medium, and program product. The method includes: acquiring a user's business requirement description information and parsing the information to obtain the user's business processing requirements under a target business type; supplementing the business processing requirements with requirement description data based on prompts and / or thought processes corresponding to the target business type to obtain business processing association parameters; orchestrating the business processing flow using a trained orchestration model based on the business processing requirements and association parameters to generate a dynamic service plugin invocation scheme; and invoking the corresponding service plugin to perform business processing under the target business type based on the dynamic service plugin invocation scheme and association parameters. By supplementing the business processing requirements with data, accurate matching of requirements can be achieved; and by orchestrating the business processing flow, multiple types of businesses can be processed using a large model.

The invention provides an information determination method, equipment and a computer program product. The method comprises the following steps: determining a text representation of a target hypertext markup language corresponding to a multi-mode user interface of screen information of virtualized mobile equipment; wherein the screen information is generated based on input of a user on the virtualized mobile device; based on the text representation and a large language model, generating a thinking chain prompt and a to-be-executed task corresponding to the text representation; wherein the thinking chain prompt is used for leading out a logical reasoning process in the large language model, so that the thinking process of the large language model is clarified before the large language model obtains a final answer; and executing the to-be-executed task based on the thinking chain prompt through an executor to obtain an operation result corresponding to the to-be-executed task.

The invention discloses an HITL method and system for unloading a large model reasoning task in a heterogeneous GPU computing power cloud. The method comprises the following steps: constructing a system model of the heterogeneous GPU computing power cloud; an HITL system architecture based on multiple agents is designed; human expert feedback is introduced through an HITL method, and recognition of a large model on a user intention is corrected; human expert feedback is introduced through an HITL method, and recognition of a large model on a user intention is corrected; the multi-agent cooperation module maps the intention of a user to a utility function through interaction among a plurality of agents; an optimized cue word method is used, the thinking process of a large model is decomposed, and the intention recognition accuracy is improved in a chain reasoning mode. According to the method, dynamic scheduling of computing power resource management and large model reasoning tasks can be optimized, and the service quality and the user experience in the heterogeneous GPU computing power cloud environment are improved.

This invention provides a method for generating visual content based on a big model, which improves the accuracy of target result information and enables the target result information to meet user requirements, as well as a method for training a target big model. [Solution] A method for generating visual content based on a big model includes the steps of: acquiring target instruction information; inputting the target instruction information into a target big model; and obtaining and outputting corresponding target result information, which includes target visual content, and is generated based on target thinking information, which is thought process information generated by the target big model in relation to the target instruction information.

1. Name of the product in this design: Dialogue area of ​​an intelligent dialogue graphical user interface for electronic devices. 2. Purpose of this design: An electronic device. 3. The key design features of this product are the graphical user interface in the electronic device for which protection is sought. 4. The picture or photo that best illustrates the key design points: Design 1 Change State Diagram 1. 5. Design 1 is designated as the basic design. 6. Purpose of Graphical User Interface: Graphical user interfaces are used for intelligent dialogue. The graphical user interface requests protection for the portion used for displaying and inputting dialog content. 7. Human-computer interaction method of graphical user interface: The main view of Design 1 is the initial state of the user's thinking process for the problem. As the thinking process progresses, the graphical user interface changes from the main view of Design 1 to the change state diagram of Design 1 to output the thinking process in the preset area. In response to the completion of thinking and the completion of the generation of response content, the graphical user interface changes from the change state diagram of Design 1 to the change state diagram of Design 1 to display the generated response content. Design 2's main view represents the initial state of the user's thought process regarding the problem. As the thought process progresses, the graphical user interface changes from Design 2's main view to Design 2's transition state diagram 1, displaying the thought process within a preset area. In response to the user touching or clicking the expand button next to "Thinking," the graphical user interface changes from Design 2's transition state diagram 1 to Design 2's transition state diagram 2, showcasing more of the thought process. In response to the completion of the thought process and the generation of the response content, the graphical user interface changes from Design 2's transition state diagram 2 to Design 2's transition state diagram 3, displaying the generated response content and the complete thought process. Design 3's main view represents the initial state of the user's thought process regarding the problem. As the thought process progresses, the graphical user interface changes from Design 3's main view to Design 3's transition state diagram 1 to output the thought process within a preset area. In response to the completion of the thought process and the generation of the response content, the graphical user interface changes from Design 3's transition state diagram 1 to Design 3's transition state diagram 2 to display the generated response content. In response to the user touching or clicking the expand button next to "Deep Thinking Completed," the graphical user interface changes from Design 3's transition state diagram 2 to Design 3's transition state diagram 3 to display the complete thought process. Design 4's main view represents the initial state of the user's thought process regarding the problem. As the thought process progresses, the graphical user interface changes from Design 4's main view to Design 4's change state diagram 1 to output the thought process within a preset area. In response to the completion of the thought process and the generation of the response content, the graphical user interface changes from Design 4's change state diagram 1 to Design 4's change state diagram 2 to display the generated response content. Design 5's main view represents the initial state of the user's thought process regarding the problem. As the thought process progresses, the graphical user interface changes from Design 5's main view to Design 5's change state diagram 1, displaying the thought process within a preset area. In response to the user touching or clicking the expand button next to "Thinking," the graphical user interface changes from Design 5's change state diagram 1 to Design 5's change state diagram 2, showcasing more of the thought process. In response to the completion of the thought process and the generation of the response content, the graphical user interface changes from Design 5's change state diagram 2 to Design 5's change state diagram 3, displaying the generated response content and the complete thought process. Design 6's main view represents the initial state of the user's thought process regarding the problem. As the thought process progresses, the graphical user interface changes from Design 6's main view to Design 6's change state diagram 1 to output the thought process within a preset area. In response to the completion of the thought process and the generation of the response content, the graphical user interface changes from Design 6's change state diagram 1 to Design 6's change state diagram 2 to display the generated response content. In response to the user touching or clicking the expand button next to "Deep Thinking Completed," the graphical user interface changes from Design 6's change state diagram 2 to Design 6's change state diagram 3 to display the complete thought process. 8. Other situations requiring explanation: The portions of the graphical user interface shown by the dashed lines in the views of Design 1 to Design 6 do not constitute the parts protected by this design.

The invention discloses a primary school mind map auxiliary teaching system, which belongs to the technical field of education informatization and comprises a mind map data acquisition module, a topological structure mapping module, a thinking path analysis module, a multi-dimensional capability evaluation module, a personalized cultivation scheme generation module and a visual presentation module. The system maps a mind map into a structural representation in a topological space by collecting operation data of students in a mind map construction process in real time, analyzes a thinking path and a turning point, constructs a multi-dimensional evaluation system including thinking integrity, fluency, flexibility and creativity, generates a personalized cultivation scheme based on an evaluation result, and provides a personalized cultivation scheme for students. According to the method, the limitation that a traditional mind mapping teaching system only pays attention to knowledge content and neglects thinking ability cultivation is broken through, dynamic capture and analysis of the thinking process are achieved, a scientific thinking ability evaluation and personalized cultivation scheme is provided, and the method is suitable for different users. And comprehensive development of the thinking ability of pupils is promoted.

The application discloses a micro-lesson extraction method, related method and related device, and relates to the technical field of resource fragmentation, wherein the micro-lesson extraction method comprises the following steps: obtaining a target course video of a target subject; analyzing the content of the target course video to generate target text data with timestamps; performing knowledge point slicing on the target text data based on a slicing large model to obtain a segmentation result comprising at least the start and end times of a knowledge point segment, wherein the slicing large model is obtained by training a general large model base by using training text data annotated with real knowledge point segmentation results and supplemented with thinking process data for obtaining the real knowledge point segmentation results, and the training text data is text data corresponding to a course video sample of the target subject; and extracting a knowledge point video segment from the target course video according to the start and end times of the knowledge point segment to obtain a knowledge point video micro-lesson. The micro-lesson extraction method disclosed by the application can automatically extract an accurate knowledge point video micro-lesson from a course video.

Large model-based visual content generation and target large model training methods, relating to artificial intelligence fields such as deep learning, a large model, computer vision and natural language processing, are provided. A large model-based visual content generation method may include: obtaining target instruction information; inputting the target instruction information into a target large model to obtain and output corresponding target result information, where the target result information includes target visual content, the target result information is generated by the target large model according to target thinking information, and the target thinking information is thinking process information generated by the target large model for the target instruction information.

The invention discloses a learner computational thinking path planning method based on multi-modal data reasoning. The method comprises the steps of obtaining context information, visual behavior data, thinking process data and action execution data of a learner target task; determining cognitive state information based on the visual behavior data, the thinking process data, and the action execution data; extracting a first knowledge entity of the target task; matching the first knowledge entity with a second knowledge entity in a preset computational thinking hypergraph to determine a target knowledge entity, and based on the cognitive state information and the target knowledge entity, performing reasoning in the preset computational thinking hypergraph to generate a knowledge node path sequence; and fusing the knowledge node path sequence, the context information and the cognitive state information to generate a teaching action sequence. According to the method, the optimal learning path accurately matched with the real-time cognitive demand and the ability state of the learner can be planned, personalized cultivation of dynamic adaptation is realized, and the method can be widely applied to the technical field of computers.

The invention relates to the technical field of artificial intelligence, and provides a multi-agent communication method and device, equipment and a medium, which are applied to financial and medical health care service scenes, and can configure a target Transform layer of a first agent and a target Transform layer of a second agent to avoid information redundancy or inference interference caused by improper layer selection. A target Transform layer of a first agent is utilized to record an intermediate layer hidden state corresponding to each token output by the first agent when executing a target task, and a state difference track is generated according to the intermediate layer hidden state corresponding to each token, so that reasoning dynamics are reserved, and information loss caused by single-path pruning is avoided; and packaging the token sequence and the state difference track into the to-be-sent data, and inputting the to-be-sent data into the second agent, thereby supplementing invisible information in the reasoning process on the premise of not breaking the universality of the natural language, and solving the problem that the thinking process in the traditional natural language communication cannot be transmitted.

This invention discloses a method and system for generating key scenarios for autonomous driving based on a large language model, belonging to the field of autonomous driving. The method includes: selecting a background vehicle as the controlled vehicle for the autonomous vehicle in the current scenario and extracting the current scenario description information; obtaining the optional actions of the controlled vehicle and calculating the reward score for each optional action; obtaining several historical scenario descriptions and their corresponding large language model thinking processes and decision results; and transmitting the current scenario description information, optional actions and their reward scores, and historical scenario descriptions to the large language model to obtain the autonomous vehicle's action decisions. This invention can efficiently generate key scenarios while improving the rationality of the generated scenarios.