506 results about "Problem solve" patented technology

The invention discloses an aerospace intelligent manufacturing large model construction method, which comprises the steps of collecting original data, performing preprocessing and data association, and constructing an aerospace intelligent manufacturing database; establishing a knowledge acquisition and structured conversion assembly line, a multi-dimensional associated domain knowledge graph, a knowledge quality control system and a dynamic updating mechanism, and constructing a professional knowledge base; aligning the cross-modal manufacturing data to generate a corpus; combining base general large model pre-training, injecting terminology semantics and multi-modal association capability, and completing knowledge migration; based on the pre-trained aerospace intelligent manufacturing large model, constructing an aerospace manufacturing cognitive agent, and forming a complex engineering problem solving framework; professional ability is optimized through a two-stage progressive multi-task training strategy, and dynamic adaptation of a production environment is realized in combination with an online learning and incremental updating mechanism. The intelligent level of aerospace intelligent manufacturing is remarkably improved.

The invention discloses a multi-agent dynamic arrangement method based on multi-modal analysis and adaptive retrieval, and relates to the technical field of artificial intelligence and information retrieval. Comprising the steps of S1, converting a text, an image, structured data and voice content input by a user into a unified multi-mode semantic representation, S2, converting the unified multi-mode semantic representation into a specific execution process, and S3, automatically scheduling a reasoning agent, a knowledge obtaining agent and an execution agent according to DAG nodes, task elements and available resources, and obtaining the task elements and the execution agent according to the reasoning agent, the knowledge obtaining agent and the execution agent. S4, after task process construction and agent arrangement are completed, dynamic retrieval, evidence convergence and strategy optimization are carried out on information requirements related to a user task, so that a reasoning agent obtains complete knowledge support with consistent context, and S5, knowledge evidence is combined with a task process, so that the task process is completed. The method comprises the following steps: step S6, implementing problem solving, strategy generation and task closed-loop execution through a reasoning agent, step S6, performing actual operation on a target task by an execution agent according to an executable instruction sequence output by the reasoning agent, and outputting a result, and step S7, performing result verification according to an output result returned by the execution agent, and the correctness, integrity and consistency of an output result are examined through rule verification, model evaluation and evidence alignment.

The invention relates to the technical field of artificial intelligence, and discloses an AI intelligent auxiliary question answering system for student practice. According to the system, various interactive data such as texts, voices and handwritten formula images of students are collected through a multi-modal data acquisition module, semantic feature vectors of all modals are generated through a multi-dimensional feature analysis module, and then the semantic feature vectors are mapped to a unified semantic space through a cross-modal fusion module. The double-layer graph construction module constructs a domain knowledge graph and a learning behavior graph, and the dynamic reasoning and recommendation module generates a personalized problem solving path recommendation and knowledge point completion strategy based on fusion semantic representation and a graph library. In addition, the system also has the functions of interactive behavior log anomaly detection, path backtracking, knowledge forgetting curve prediction and the like. The system can comprehensively understand questions of students, provides personalized question answering service, and effectively improves the learning efficiency and knowledge mastering degree of the students.

A tree-of-thought (ToT) system is presented that improves problem-solving capabilities of machine learning models, such as auto-regressive large language models (LLMs). The TOT system can solve complex reasoning tasks through trial and error. In this process, the system explores the solution space through a tree-like thought process, allowing for backtracking when necessary. The system augments an LLM with additional modules including a prompter agent, a checker module, a memory module, and a ToT controller. These modules engage in a multi-round conversation with the LLM. The memory module records the conversation and state history of the problem-solving process, which allows the system to backtrack to the previous steps of the thought-process and explore other solution paths. This new system can be applied to a blockchain and / or a distributed computing system.

The invention provides an intelligent customer service dialogue generation optimization method and system based on a knowledge graph, and relates to the technical field of knowledge graphs, and the method comprises the steps: employing a bidirectional long-short-term memory network to recognize the entity and intention of a user question; performing multi-hop query in the knowledge graph based on the question entity to obtain an initial knowledge sub-graph; constructing a user feature vector containing a dialogue state, problem solving and service preference; performing hierarchical reconstruction on the initial knowledge sub-graph based on the user feature vector; calculating the structural similarity of the domain knowledge graph, and extracting a general knowledge organization mode; decomposing the reconstructed knowledge sub-graph into a structure template and a content filling item, and determining a knowledge mapping relation between fields to obtain a migration optimization knowledge graph; and generating candidate replies based on the optimized knowledge graph and the initial intention, evaluating the accuracy, suitability and correlation of the candidate replies, and selecting the optimal reply output.

The invention provides a large model active tool calling method and system based on multi-step reasoning, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting tool information, generating a structured tool description set, automatically generating an executable code sample and corresponding natural language explanation based on the tool description set, and constructing a reverse training data set; the method comprises the following steps of: marking tool use necessity tags in a real problem, prompting a large model to generate a multi-step reasoning path combined with a natural language and codes, verifying and filtering the correctness of the reasoning path, and constructing a forward training data set; and performing three-stage training on the large model based on the reverse training data set and the forward training data set. According to the method, the problem that the active tool calling capability of a large model is insufficient is solved, and the code execution rate and problem solving efficiency of a complex reasoning task are improved.

The invention relates to a stipulation processing method and system for mathematical subjective question answering steps. The method comprises the steps of performing deep semantic understanding on problem solving information of mathematical subjective problems based on a pre-training language model of a Transform architecture, generating semantic representation information, and segmenting the problem solving information into semantically coherent atomic steps based on the information; matching the atomic steps with a knowledge graph to obtain a first matching result, and determining a connection relationship between the atomic steps based on the knowledge graph; based on the connection relation of the atomic steps and the atomic steps, constructing an answer step graph, and performing reasoning through a graph neural network to obtain a reasoning result; a reference answer is generated according to the reasoning result, semantic matching is conducted on the atomic step and the reference answer, a second matching result is obtained, and the result is used for indicating generation of correction feedback. According to the method, through semantic understanding, the knowledge graph and the graph neural network, automatic and accurate answer step analysis can be realized, and the question solving efficiency and the feedback quality are improved.

Certain aspects provide techniques and apparatus for executing queries in a computing system using machine learning models. An example method generally includes receiving a plan to satisfy a request in the computing system and event log data associated with execution of the plan. The plan generally specifies a first plurality of function calls at a first level of granularity. Using a plan refinement machine learning model, a refined plan is generated when the event log data indicates that execution of the generated plan results in one or more execution errors and the one or more execution errors are solvable. Generally, the refined plan specifies a second plurality of function calls at a second level of granularity, the second level of granularity being finer than the first level of granularity.

The invention relates to the technical field of teaching systems, in particular to a teaching information processing method and system based on artificial intelligence, and the method comprises the following steps: S1, carrying out the collection and fusion of multi-modal data, and carrying out the fusion of the data through a time warping dynamic alignment algorithm; s2, cognitive state modeling: introducing a dynamic forgetting gate mechanism on the basis of a traditional LSTM, quantifying the half-life effect of knowledge points, and obtaining a deviation degree delta gt between a problem solving path of a student and an expected optimal path; 0.4, an alarm is triggered; and S3, a dynamic knowledge topological component dynamically updates a relation weight between knowledge points based on a graph neural network, and an improved Sweller cognitive load index is used. The method solves the problem that when students have unexposed understanding deviation in an algebraic'factorization 'link (such as a'square difference formula' and a'complete square formula '), a system still mechanically advances to a'polynomial operation' module to cause chain accumulation of knowledge vulnerabilities and finally cause systematic learning collapse.

A computer implemented method determines a solution to a Master Problem, MP, the MP derived from a Mixed-Integer Program, MIP, problem and associated with a Sub-Problem, SP. The method comprises determining, using a quantum computer, a solution to a first version of the MP. The first version of the MP comprises a first initial constraint. The solution to the first version of the MP comprising: a first value for the group of one or more respective integer variables. The SP is run, using the one or more first values, to determine either: a third value, corresponding to the dual problem, for a solution for the SP; a fourth value corresponding to an extreme ray. Using the third value or fourth value, a further constraint for a second version of the MP is generated. The second version of the MP is generated by replacing the first initial constraint with the further constraint. A further solution to the second version of the MP is determined, using the quantum computer.

The invention provides a mathematical question and answer process teaching system, which comprises a user interaction module, a question analysis and standardization module, a cognitive diagnosis engine, a generative teaching module, a mathematical knowledge graph database and a user portrait database, teaching content and guiding questions are presented to the user in a multi-mode form; the question analysis and standardization module is used for performing semantic understanding and structured analysis on mathematical questions and generating standardized question description and at least one standard question solving path; according to the method, the structured reasoning of the knowledge graph is combined with the natural language generation ability of the generative AI, so that a closed loop from'problem solving 'to'diagnosis' to'heuristic teaching 'is realized, thinking blockage points of students can be accurately positioned and personalized tutoring can be provided like human teachers, and the learning efficiency and the autonomous thinking ability are remarkably improved.

The invention discloses a data processing method and device, a storage medium and electronic equipment, and relates to the technical field of artificial intelligence, first type memory information is obtained according to the current session context with a user, a model can be ensured to understand the background of a current problem, the problem background is supplemented by using second type memory information, namely the historical session record of the user, and the user experience is improved. According to the method, the service knowledge information related to the question is retrieved, namely the target knowledge information, the target model generates the comprehensive reply according to the information, the context of the instant session is considered, and the personalized preference of the historical session and the current service rule are combined, so that the generated reply information is more comprehensive, and the reply efficiency is improved. Therefore, incoherence or inaccuracy caused by forgetting important details is avoided, and the technical effects of improving the accuracy of problem solving and enhancing individuation and satisfaction of user experience are achieved.

The invention provides an intelligent assistant method and system based on a large model, relates to the field of large model application, is used for providing a question and answer result for a user question, and comprises the following steps: constructing an entity recognition cue word, and recognizing an entity in the user question through the large model; constructing intention recognition and tool selection prompt words, recognizing user intentions in the user questions through a large model, and determining tools to be used; based on the assembled user questions and entities, related information is retrieved from a pre-constructed vector knowledge base, and a large model is combined with the retrieved related information to enhance and generate an answer text; processing the answer text according to the user intention and the tool, and outputting a final question and answer result; according to the method, the limitation that a traditional intelligent assistant cannot deeply understand user semantics and only can mechanically carry out rule matching is solved, and the requirements of the user can be more accurately grasped to provide a more accurate problem solving strategy.

The invention discloses a student comprehensive ability evaluation system based on artificial intelligence, and belongs to the technical field of artificial intelligence student learning evaluation. Aiming at the problems of single dimension and poor evaluation effect in the existing student evaluation system, the system not only can provide personalized feedback and improvement suggestions for students and help the students to improve team cooperation, communication and problem solving capabilities, but also can provide accurate teaching evaluation and decision support for teachers and education managers, so that the students can have a better teaching effect. And intelligent upgrading of a teaching mode is promoted. By promoting digital transformation of education evaluation, the system provides an innovative solution for constructing a more scientific, fair and efficient learning evaluation system, and assists high-quality development of education.

The invention discloses an intelligent agent system and a control method thereof, and relates to the technical field of natural language processing. The system comprises an execution layer, a planning layer and an auditing layer, the planning layer identifies and extracts innovation task meta-information, constructs a task tree to complete operations such as hierarchical clustering, and determines a task execution path; the execution layer calculates the semantic similarity between the content of the knowledge graph and the user innovation question, determines the optimal question and answer, extracts heuristic information, and decomposes the heuristic information into sub-questions to construct a dependency graph; generating an answer set based on the graph solving sub-problems, and integrating answers by using a genetic algorithm to obtain an overall solution; and the auditing layer performs multi-dimensional scoring on the scheme, and determines a structured scheme report and optimization suggestions for users to use according to a scoring result. The method has the capabilities of structured reasoning, problem recursive decomposition and scheme closed-loop optimization, can generate a multi-dimensional evaluation result, and efficiently realizes systematic modeling of a clear path for analogy heuristic information support problem solution.

The invention relates to the technical field of artificial intelligence education, and discloses an AI intelligent education tutoring system based on a thinking chain and a retrieval enhancement generation technology. Transparent generation and dynamic verification of a problem solving logic chain are realized through a CoT-RAG fusion architecture, and the interdisciplinary confusion rate is reduced in combination with a knowledge graph technology of subject boundary isolation; the non-question-bank-dependent generation engine creates questions in real time based on semantic association, and the coverage rate is increased; federated learning and differential privacy technologies are integrated, and the safety of user data is ensured while the generalization ability of the model is improved; the learning behavior analysis unit dynamically optimizes a knowledge recommendation path through time sequence modeling, and cooperates with the interactive logic correction module to form a self-evolution closed loop. Finally, an intelligent education system which is high in interpretability, high in professional precision and compliant in privacy is constructed, and the learning efficiency and the interdisciplinary problem solving capability are remarkably improved.

The invention discloses an electric power field credible question-answering system based on a knowledge graph and multiple agents, and belongs to the technical field of intelligent power grids. The electric power field credible question-answering system comprises the steps that an existing knowledge base is stored through a vector knowledge base, the knowledge graph and a relational database, and then a multi-agent system is constructed based on a large language model; a complex problem is decomposed into a plurality of sub-problems by adopting a logic form language in real-time dialogue, solving is carried out based on operators such as planning, reasoning and retrieval, symbolization and structuring of a problem solving process are realized, knowledge is aligned and integrated by using a semantic reasoning technology, a semantic relationship between the knowledge is identified and established, and a real-time dialogue result is obtained. And realizing credible questions and answers in a manner of recalling related knowledge. According to the method, the deep fusion of the unstructured text, the structured data and the semantic relationship is realized by constructing the multi-modal knowledge storage system, the knowledge coverage rate and the semantic consistency are remarkably improved, and the understanding and response capabilities of the system to compound problems are improved.

The invention provides a mathematical application question solving method and system based on a few-sample thinking chain prompt, and the method comprises the steps: coding a question sample and an inference chain thereof into feature vectors based on a pre-training encoder; classifying the feature vectors, selecting the first N feature vectors of each class, constructing cue words, and guiding a large language model to construct examples for each class of problems; an example most similar to the to-be-solved problem is extracted from the example set, and an initial prompt word is constructed based on the example and the to-be-solved problem; adjusting and optimizing the initial cue word based on a programmable declarative cue word optimization framework; and using the optimized cue word to guide the large language model to solve the problem to be solved. An optimal example similar to a to-be-solved problem is constructed by processing the problem in training data and a reasoning chain, so that the illusion risk of a large language model due to inconsistent example types is reduced; by utilizing a programmable cue word template optimization method, the generalization ability of the cue word template is improved, the large language model is effectively guided to solve, and the problem solving accuracy is improved.

The invention discloses an AI recruitment candidate comprehensive ability evaluation method based on a multi-modal large model, and relates to the technical field of artificial intelligence recruitment and multi-modal data processing. The method comprises the following steps: S1, constructing a post digital twinborn environment; S2, collecting candidate multi-modal interaction data; S3, training and optimizing a multi-modal large model; and S4, evaluating the comprehensive ability of the candidate and outputting a result. According to the method, a high-simulation post digital twinborn environment is constructed, multi-modal interaction data acquisition is combined, and deep analysis and evaluation are performed by using a multi-modal large model, so that the method not only considers the traditional resume and interview performance of candidates, but also improves the evaluation efficiency by simulating a real working scene. The method comprehensively evaluates the actual operation capability, the communication cooperation capability, the problem solving capability and other multi-dimensional capabilities of the candidates, and compared with a traditional recruitment mode, the method can more accurately predict the scene adaptation speed and the comprehensive capability performance of the candidates after the candidates enter the job.

The invention relates to the field of power transmission and communication, and discloses an intelligent cable monitoring system for monitoring the state of a cable in real time, and the system comprises a data collection module, a physical modeling module, an inverse problem solving module, an optimization algorithm module, a fault positioning module and a precision evaluation module. The method comprises the following steps of: arranging various sensors at key positions of a cable, acquiring temperature, stress, vibration and electromagnetic field data in real time, accurately positioning a cable fault position by combining physical modeling and an optimization algorithm, and optimizing a fault positioning result through precision evaluation and regularization adjustment. According to the method, the cable fault positioning precision is improved through multi-physics field joint modeling, inverse problem solving and optimization algorithms, and the problems of insufficient information dimension and poor flexibility are solved. Precision evaluation and regularization dynamic adjustment are introduced, the adaptive capacity of the system is enhanced, visual fault output and automatic report generation are designed, and the information interaction efficiency and the operation and maintenance response speed are improved.

The invention discloses a mathematical problem solving method and device based on a large language model, a computer program and a storage medium. Relates to the technical field of artificial intelligence and natural language processing, and also relates to the technical field of mathematical solution and solution process demonstration based on artificial intelligence. The method comprises the following steps: S1, acquiring mathematical problems; s2, text features of the mathematical problem are extracted and classified, and a classification result is obtained; s3, constructing a cue word knowledge base, and matching corresponding cue words according to a classification result to obtain a question and answer sequence; s4, decomposing the question and answer sequence into four subtasks of question condition analysis, key formula application, calculation verification and result induction to obtain a preliminary answer; and S5, verifying the preliminary answer. The problems that an existing mathematical problem solving system is incomplete in reasoning process, a logic chain is prone to breakage, contextual information utilization is insufficient, and an effective verification mechanism is lacked are solved. The method is suitable for the fields of education teaching assistance and scientific research calculation support.

The invention discloses an energy storage power station capacity measuring and calculating method considering the power grid bearing capacity and multiple application scenes. The method comprises the following steps: firstly, performing fitting correction on a scene by adopting a scene aggregation correction technology based on least square fitting; and constructing an energy storage power station capacity optimal measurement and calculation model considering the power grid bearing capacity and multiple application scenes, finally carrying out linear transformation on the energy storage power station capacity optimal measurement and calculation model, and solving by adopting commercial optimization software. According to the calculation model, multiple application scenes are introduced, and peak regulation, frequency modulation and standby multiple dimensions are considered, so that the operation and income calculation of the energy storage power station are more comprehensive, the behavior of investing the energy storage power station on the user side can be better simulated, and the influence of energy storage access on the power grid can be better evaluated. According to the scene aggregation correction technology, fitting correction is carried out on the scene by introducing the least square method, more efficient and accurate scene expression is achieved, and the problem solving scale and solving difficulty are reduced.

There is provided a system and methods to determine an improved solution to a Mixed Integer Problem (MIP) using a quantum-assisted MIP solver. The methods are performed by a digital processor in communication with a quantum processor. Methods include: selecting at least one feasible solution determined by an MIP solver, determining a first sub-problem of the MIP based on the at least one feasible solution; casting the first sub-problem as Binary Quadratic Models (BQMs); solving the BQMs using the quantum processor to generate sample solutions; determining a second sub-problem based on at least the sample solutions, and obtaining a current solution to the MIP by evaluating the second sub-problem; and updating an incumbent solution if the current solution improves over the current incumbent solution. The quantum-assisted MIP solver uses hybrid crossover and mutation heuristics to improve the convergence time and accuracy of solutions obtained using Branch-and-Cut solvers.

The invention relates to the technical field of quality supervision and early warning management, in particular to an AI-based subway engineering construction quality supervision and early warning management system and method, and the system comprises a process data fusion module which obtains the sensor monitoring data deviation degree, the material detection qualified rate and the personnel operation specification conformity of a shield tunneling process. According to the method, a quality vulnerability index for expressing process state fluctuation is established by fusing a sensor monitoring data deviation degree, a material detection qualification rate and a personnel operation specification conformity, and an accumulated risk assessment mode based on a process chain conduction relation is formed by combining dynamic quantification of an upstream process defect on a downstream influence probability. And the capability of identifying the coupling influence between the working procedures is enhanced. And synchronously analyzing information request metadata, scheduling personnel hour data, access control behavior records and rectification cycle time, and constructing a multi-dimensional collaborative efficiency index sequence covering information circulation efficiency, personnel operation load and problem solving efficiency.

The invention relates to an employment matching method and system based on intelligent data analysis. According to the method, multi-modal recessive skill data of candidates in an occupational cooperation platform, professional field contribution and occupational evaluation are collected, recessive ability vectors of communication cooperation, problem solving and the like are extracted through structured processing and an emotion analysis algorithm, and cooperation compactness and skill complementarity among members are modeled in combination with a team skill relation graph. And based on a game theory multi-objective optimization algorithm, enterprise employment cost, team efficiency and individual development demands are dynamically balanced, employment matching of accurate quantification of recessive skills, team structure suitability optimization and multi-party benefit balance is finally realized, and the precision of employment matching and the sustainability of long-term occupational development are significantly improved.

The invention discloses a rich text multi-dimensional difference analysis and accurate revision method and system based on AI, and relates to the technical field of artificial intelligence and data analys.The rich text multi-dimensional difference analysis and accurate revision method comprises the steps that firstly, a rich text file is analyzed, a document structure is reconstructed, vectorization and key information labeling are conducted on semantic blocks, and structuralization and semantic enhancement of a text are achieved; the method comprises the following steps of: firstly, carrying out text surface layer, semantic deep layer and structure association dimension difference analysis in parallel, then carrying out system knowledge graph-based revision influence degree evaluation on the basis of difference analysis, tracing associated terms through penetrating analysis, calculating an influence degree score and early warning potential conflicts, and automatically generating accurate revision suggestions; visual difference preview and one-key generation of a revised draft are provided, a closed loop from problem discovery to problem solving is realized, and the efficiency and accuracy of system revision are greatly improved.

The invention relates to the technical field of cross-modal geometric problem solving methods, in particular to a knowledge-driven multi-thinking-chain cross-modal geometric problem solving method and system. According to the technical scheme, the knowledge-driven multi-thinking-chain cross-modal geometric problem solving method and system are provided. The method comprises the following steps: firstly, inputting a geometric knowledge point candidate set, and generating a function set by utilizing a multi-modal large language model query theorem; inputting questions, pictures and answers, screening knowledge point subsets, and extracting corresponding theorems and function subsets; a language and program thinking chain prompt template is constructed, and a thinking chain is generated and verified; then taking the successfully verified thinking chain as training data, and carrying out instruction optimization on the small-scale multi-modal model; and finally, generating a thinking chain through the model, performing comprehensive verification, and outputting a final answer.

One example method includes providing a problem, and associated inputs and constraints, to an annealer, when the annealer runs an annealing process on the problem and does not find a solution to the problem that meets the constraints, loosening one of the constraints, re-running the annealing process using the constraint that was loosened, performing the loosening, and the re-running, until a new and feasible solution is found that meets the constraints, and performing an optimization process that comprises re-running the annealing process, with noise, to determine whether a solution exists that is better than the new and feasible solution.

The embodiment of the invention provides a multi-mode problem solving method, a multi-mode problem solving system, computing equipment and a medium, and the multi-mode problem solving method comprises the steps that an input image is acquired, and the input image comprises a problem text and an initial problem graph; based on the initial topic graph, analyzing the topic text to obtain a topic analysis result and a target graph element; reasoning the question analysis result based on the target graphic element to obtain an answer text; based on the answer text, performing vector graphic marking on the target graphic element to obtain a vector graphic marking result; and based on a vector graph marking result, rendering the target graph element on the initial topic graph to obtain a rendered topic graph. Students can visually see the answering process and the final result, and the learning effect and the question solving experience are improved.

The invention discloses a knowledge space control method and system for assisting learning, and relates to the technical field of knowledge space generation methods, and the method comprises the steps: determining a corresponding problem solving path according to the previous problem solving content of a user; and determining error contents of each problem solving node in the problem solving path based on matching of the problem solving path and the knowledge application space, and marking knowledge nodes associated with the error contents. Determining corresponding correct content according to the error content and knowledge content presented by the knowledge node, determining difference content between the correct content and the error content, determining a correct answering thought according to the difference content and the answering thought of the user relative to the error content, and marking knowledge difficult points of the user; the error factors of the user are determined according to the knowledge difficult points of the user, the corresponding mastering level and the answering accuracy of the user, the corresponding auxiliary learning measures are determined based on the error factors of the user and the current learning process of the user, and the accuracy of the auxiliary learning measures is improved.