37 results about "Automaticity" patented technology

The invention discloses an engineering drawing compliance intelligent review method and system constructed based on a knowledge base and a large model. The method mainly comprises the following steps: intelligently analyzing a design specification in a natural language form by utilizing a large language model, and dynamically constructing a machine-readable rule base and a knowledge base; uniformly converting the multi-format engineering drawing into a structured intermediate format; functional areas and primitives in the drawing are recognized through a computer vision model, and natural language information describing attributes of the functional areas and the primitives is generated; and finally, in combination with the knowledge base and natural language description, performing compliance judgment by utilizing the reasoning ability of the large language model, and generating an interpretable review report. According to the method, computer vision and a large language model technology are fused, so that the defects that traditional manual review is low in efficiency and prone to making mistakes and a traditional automatic tool lacks semantic understanding ability are overcome, and efficient and accurate engineering drawing automatic compliance review with deep semantic understanding ability is achieved. Figure 1 of the abstract is a system architecture block diagram.

The invention relates to the technical field of learning education, in particular to an AR-based personalized learning education auxiliary method and system. By collecting and synchronously processing multi-modal behavior data such as eye movement, gestures and head orientation, time sequence characteristics capable of accurately reflecting the learning state of a user are constructed, and then a hidden cognitive state sequence is decoded by using a hidden Markov model and inflection points of the hidden cognitive state sequence are recognized; finally, dynamic and automatic adjustment of learning contents is realized by means of a reinforcement learning model, deep cognitive state changes can be captured from continuous and dynamic user behaviors, accurate teaching intervention is timely performed at'inflection points' of key transition of cognitive states, personalized adaptive learning path planning is realized, and the learning efficiency is improved. The pertinence and effectiveness of learning are obviously improved; the technical problem that an existing AR learning system is difficult to intervene in time at an inflection point where a user cognition state is changed during path planning, so that real personalized learning path planning is realized is solved.

The invention discloses a computer-aided old-age language erosion assessment method and assessment system, and relates to the technical field of old-age health assessment, and the method comprises the following steps: S1, collecting the voice data, text input data and interactive behavior data of an old-age user; s2, preprocessing the data, and extracting voice acoustic features, language structure features and cognitive behavior features; s3, inputting the extracted features into a pre-trained language erosion evaluation model, and outputting a language ability score and an erosion type classification result; and S4, generating a visual evaluation report, wherein the visual evaluation report comprises the language ability degradation degree, key obstacle points and intervention suggestions. According to the method, the score and classification result is automatically output through the multi-modal data acquisition and pre-trained deep learning model, so that the evaluation time is greatly shortened, the subjective deviation is eliminated, the result objectivity is ensured, the problems of low manual evaluation efficiency and high subjectivity are solved, and the effect of automatic evaluation is realized.

The invention relates to the technical field of artificial intelligence question answering systems, and discloses an interactive question answering system based on multi-model parallel reasoning. The system comprises an interactive interface module, a query cognition construction module, a hierarchical index module, a multi-model parallel reasoning module, an interactive answer synthesis module and a tool calling adaptation module. The system constructs query cognition mapping by deeply analyzing a time sequence query stream containing texts and media of a user, and drives dynamic evolution of hierarchical indexes according to the query cognition mapping. The multi-model parallel reasoning is based on evolution strategy coordination processing, and knowledge slices with state vectors are generated. And finally, synthesizing a natural language answer attached with the interaction intention unit, and adapting the natural language answer to an external tool calling instruction. According to the system, the cognition and retrieval precision under complex query is improved through intention-driven dynamic indexing, and automatic closed loop from information question answering to business operation is realized through executable answers.

The application relates to a general field thought chain corpus generation method and medium, which comprises the following steps: acquiring general field corpora of different task types, converting the corpora into a unified standard format through structuring, and obtaining standardized corpora, wherein the task types include subjective types and objective types; generating initial thought chain texts and conclusions according to general matching reasoning links based on the standardized corpora of different task types; and verifying the initial thought chain texts and conclusions through a multi-dimensional automatic quality inspection mechanism to obtain final thought chain texts and conclusions. Compared with the prior art, the application has the advantages of generalization, process standardization, controllable quality and the like.

The application discloses a Bloom cognitive hierarchy constraint-based achievement-oriented education diagnosis method and system. The method takes course outline text and student evaluation data as input, and realizes the automatic diagnosis of course goal achievement through three structural modifications in the large language model Transformer architecture: the logarithmic value of the cognitive hierarchy transfer matrix is embedded as a learnable bias item in the attention score calculation path to realize feature coding of cognitive hierarchy perception; the continuous differentiable relaxation technique is used to establish an end-to-end differentiable inference path for the course goal achievement weight; and the Bloom partial order constraint is coded as a training loss, so that the diagnosis result meets the cognitive hierarchy progressive relationship. The three modifications are optimized by a joint loss function, which significantly improves the diagnosis accuracy and promotes the interpretability and scientificity of the large language model diagnosis in the achievement-oriented education scene.

The invention provides a multi-modal large model fine-tuning corpus production method for the field of planning and natural resources, and aims at solving the problems that existing corpus lacks professional semantics, manual annotation is low in efficiency, and no standardized process exists. According to the method, an exclusive VQA corpus is generated through four core modules including construction of an industry exclusive cognitive task and VQA template library, image-text pairing generation, template-driven VQA sample generation and automatic quality control optimization in combination with an industry planning standard and a cognitive hierarchy, namely perception-reasoning-association-application. The method comprises the following steps: firstly, automatically extracting visual elements and policy texts of a planning graph, and matching a professional template to generate candidate Qamp; the method comprises the following steps: A, finally outputting a standardized corpus package through semantic detection and expert re-check optimization; according to the method, professional semantic accurate alignment is realized, the labor cost is greatly reduced, the corpus quality is reliable, the method can be expanded to similar fields, and efficient support is provided for field multi-mode large model fine adjustment and capability evaluation.

The application relates to the technical field of automation operation and maintenance, and discloses an intention recognition method and system based on dynamic ontology evolution and multi-agent, which comprises the following steps: receiving a natural language instruction, performing entity extraction and probabilistic linking by using a dynamic ontology knowledge base, and generating an initial intention based on predicate analysis; automatically completing missing key slots by using a probabilistic graph model, and generating a standardized intention; decomposing the standardized intention into an atomic subtask sequence, dynamically matching an execution agent based on an agent capability-demand matrix, generating a collaborative workflow, controlling the execution agent to call an atomic tool to execute a task, performing causal correlation analysis on multi-source results according to logical relations between ontology instances, generating a structured reasoning chain, and feeding back; and extracting a new treatment script based on execution feedback by using an evolution engine, and updating an ontology knowledge base and an agent confidence degree. The application can realize accurate understanding, automatic execution and adaptive evolution of a knowledge base of a fuzzy operation and maintenance intention.

The invention relates to the technical field of artificial intelligence, in particular to an extensible large language model driven cognitive competence assessment system and method.One or more large language models are adjusted and optimized by using an example data set with a label, and questions in a project question bank are automatically classified by using the adjusted and optimized large language models, so that the accuracy of cognitive competence assessment is improved. Obtaining a classification result; constructing a cognitive competence test based on the classification result, generating a structured evaluation result, and storing the evaluation result in a historical record of the user; the method comprises the steps of obtaining an evaluation result of a user, based on historical records of the user and the evaluation result, activating a dialogue agent driven by a large language model, converting recommended items into a structured query request, integrating retrieval results and generating a customized course scheme exclusive to the user, and according to the method, the large language model (LLM) is deeply integrated into an education evaluation and course generation closed loop; and full-process automation of automatic question classification, dynamic cognitive competence diagnosis, continuous model optimization and personalized course delivery is realized.

The invention provides a multi-agent self-adaptive test question generation method and system based on cognitive constraints, and relates to the technical field of large language models, and the method comprises the steps: receiving a question setting request of a user; based on the question setting request, performing retrieval on a pre-constructed double-layer cognitive education knowledge graph to obtain an initial teaching method sub-graph; retrieving from a pre-constructed external vectorization test question bank to obtain candidate test questions; judging whether the context of the initial teaching method sub-graph is sufficient or not; if the context is insufficient, executing a self-adaptive context evolution loop, expanding the initial teaching method sub-graph, performing judgment again, and continuously expanding the loop until the context is sufficient; if the context is sufficient, a final context sub-graph is obtained, a graph constraint decoding algorithm is executed, the final context sub-graph serves as cognitive constraint, the candidate test questions are reconstructed, and a target test question is generated and output. The invention provides an automatic test question generation capability with high teaching law alignment and high knowledge loyalty.

The invention discloses a code review opinion generation method based on retrieval enhancement. The code review opinion generation method comprises the steps of 1, constructing a comparative learning training data set fusing code change structure features and review intention semantic features; 2, driving a universal pre-training code encoder to carry out transfer learning to a code review field by utilizing the comparative learning data set to obtain a review intention perception retriever; step 3, recalling a historical reference case as a reference context based on the retriever after fine tuning, and constructing a structured prompt template containing an anti-noise mechanism; and step 4, combining the prompt template, and performing instruction fine tuning on the large language model by using a low-rank adaptive technology (LoRA). Through cooperation of retrieval vector space remodeling and efficient parameter fine tuning, the problem that in the prior art, review opinions are seriously generalized is effectively solved, the pertinence and reference value of automatically generated opinions are remarkably improved, and the expert-level automatic code review opinion generation technology in the low-computing-resource environment is achieved.

The application discloses a fusion large model intelligent teaching quality evaluation improvement system and relates to the technical field of wisdom education.The application realizes automatic identification of skill response behavior by means of a disturbance group modeling module and a behavior characteristic difference set of students between original questions and candidate comparison questions.System no longer depends on subjective judgment of teachers, but analyzes answer stability of students when facing semantically equivalent and structurally stable questions through quantitative index.When it is detected that the behavior path of students deviates by a high amplitude, the system can immediately determine that there are skill dependence and concept misplacement problems.For example, after answering the disturbance question, the correct rate of the answer decreases, which indicates that there is a strategic answer instead of concept reasoning, and the objectivity and traceability of the teaching quality evaluation are further improved through the knowledge graph of the original question stem.

The application discloses an automatic penetration testing method and system based on a cognitive decision model, relates to the technical field of information security and data processing, and realizes deep cognitive modeling of a penetration environment by constructing a multilayer state space composed of an explicit state layer, a structural state layer and a potential cognitive state layer, directly records observable attributes through the explicit state layer, infers network topology and component correlation through graph analysis through the structural state layer, and speculates unknown factors based on a probability model through the potential cognitive state layer to form conditional probability representation, so that the modeling mode enables the system to construct complete environmental cognition from fragmented information, maintains decision stability through probabilistic reasoning when the information is incomplete, meanwhile, penetration experience trajectories are parsed into unified state-action sequences through a semantic mapping function from natural language penetration records, so that the trajectories ensure that expert reasoning logic is reflected, and a test system with environmental cognition and experience internalization is formed.

The application discloses a kind of big language model causal inference method and system based on knowledge guidance, comprising: the standard knowledge base of target field is constructed, the original observation corpus of target field is acquired, based on the standard knowledge base of target field, J similar variables and its variable types are matched in original observation corpus, according to J similar variables and its variable types, the causal inference graph of target field is constructed, the set of variables to be reasoned is acquired, the set of variables to be reasoned is taken as the input of causal inference graph, the corresponding causal inference path is output, and the causal inference path is returned to user end;The application realizes the automatic determination of reasoning direction by introducing the position of variable in knowledge fact tuple, and can use the part of variable as anchor point, combine the causal pairing relationship in standard knowledge base, complete the missing node and edge on demand, so as to restore the complete candidate knowledge fact, improve the adaptability in data missing or incomplete information scene.

This invention relates to the field of artificial intelligence technology, specifically to an automatic construction method and system for large-scale language model intelligent agents. The system includes: S1 Modular representation and knowledge construction, decomposing the intelligent agent into standardized functional modules and establishing a module knowledge base and a historical experience base; S2 Initial intelligent agent automatic assembly, generating an initial configuration from the language model based on task description and dual-base retrieval results; S3 Execution and hybrid evaluation, collecting execution data and generating performance feedback through holistic evaluation of the language model and game theory module contribution evaluation; S4 Dynamic module reorganization and optimization, performing module replacement or optimization based on feedback to achieve knowledge accumulation; S5 Iterative optimization, cyclically executing evaluation and optimization to output the optimal configuration. The system comprises four main units: module management, assembly, execution and evaluation, and optimization, used to implement the above method. This invention achieves automated construction and dynamic optimization of intelligent agents, improving interpretability, cross-task adaptability, and continuous optimization capabilities, while reducing development costs.

The present application relates to artificial intelligence. More specifically, the present application provides an automated method and an automated system integrating large language models and formal reasoning. The method comprises: transforming / converting / encoding, by a trained first large language model, an input natural language description for describing a problem into a structured formal representation for representing the problem; and performing automated formal reasoning on the formal representation to provide a solution to the problem. In the method, by combining the capability of the large language model in language processing with automated formal reasoning, the first large language model is allowed to convert the natural language describing the problem into a structured formal representation that can accurately represent the problem, and rigorous logical reasoning is applied to the formal representation to provide a correct solution to the problem, thereby enhancing the analytical reasoning capability of the second large language model. The inherent limitations of large language models in analytical reasoning are solved, thereby ensuring the correctness, consistency and coherence of the output of the second large language model.

Systems and methods for automated adaptive learning framework for large language models are provided. A method includes receiving one or more input parameters, including at least one of a user query, an automated response, or a validated response. The automated response is based on a prompt. The method further includes providing the one or more input parameters and an input analysis prompt to a first large language model, and receiving an analysis report from the first large language model. Furthermore, the method includes providing the one or more input parameters and the analysis report to one of the first large language model or a second large language model, and receiving a learned memory from one of the first large language model or the second large language model. The method also includes generating an updated prompt through memory injection of the learned memory into the prompt.

The application provides a self-adaptive procedure generation method based on case-based reasoning and transfer learning, and the application constructs an excellent case knowledge base, structures and makes implicit knowledge, i.e., successful experience of experts verified in history, explicit, and innovatively combines the case-based reasoning and the transfer learning thought, so that the system can not only find the most similar historical case, but also intelligently and self-adaptively correct the scheme in a "transfer" mode according to the difference between the new task and the historical case, thereby automatically generating the engineering procedure which is highly customized, close to the actual situation and has the "design thought" annotation. The application solves the technical problems of low efficiency and poor consistency of the traditional method, and the technical problems of rigidity and lack of learning evolution ability of the existing software system.

The invention provides a GPU operation and maintenance intelligent system integrating anomaly perception, semantic-level reasoning, causal chain reconstruction, intelligent repair decision and self-feedback learning. According to the system, interpretable root cause tracking is achieved through a retrieval-enhanced generation (RAG)-map hybrid reasoning mechanism, automatic repair action planning is achieved through a strategic generation model, and knowledge edge weight self-updating and reasoning ability self-evolution are achieved through verification feedback. According to the method, the normal form transition of GPU fault handling from post analysis to real-time deduction and self-healing regulation is realized, and a full-process intelligent closed loop of sustainable evolution is formed.

The invention discloses an automatic cue word generation model training method and system based on a multi-modal large model. The method mainly comprises the steps of generating to-be-evaluated cue words through an automatic cue word generation model, and respectively inputting the to-be-evaluated cue words into a first multi-modal model and a second multi-modal model to obtain an output result containing answers and an analysis process; calculating a composite loss value based on the output result and preset annotation data, and updating parameters of the cue word automatic generation model; the method is characterized in that new guidance information used for next training iteration is generated based on comparative analysis of the analysis process in the first output result and the second output result, and therefore a feedback closed loop is formed. According to the method, by constructing the self-evolution closed loop in the reasoning process of the supervision model, automatic and efficient generation of the high-quality multi-mode cue word is achieved, and the cue word guiding capacity and the model reliability are remarkably improved.

The invention discloses an automatic penetration testing method and system based on a cognitive decision model, and relates to the technical field of information security and data processing. Deep cognitive modeling of a penetration environment is realized by constructing a multi-layer state space composed of an explicit state layer, a structural state layer and a potential cognitive state layer; the explicit state layer directly records observable attributes, the structure state layer deduces network topology and component association through graph analysis, the potential cognitive state layer deduces unknown factors based on a probability model and forms conditional probability representation, and the modeling mode enables the system to construct complete environment cognition from fragmented information and to obtain a complete environment cognition result when the information is incomplete. Decision stability is kept through probabilistic reasoning, meanwhile, natural language permeation records are analyzed into a unified state-action sequence through a semantic mapping function according to the permeation experience track, it is ensured that the track reflects expert reasoning logic, and a test system of environmental cognition and experience internalization is formed.

The invention discloses an open reading understanding problem difficulty estimation method and system based on an LLMs large language model, and the method mainly comprises the steps: taking a multi-capability heterogeneous LLM as a pretest subject, enabling a teacher agent to carry out the scoring according to an automatic index, carrying out the monotone probability calibration, and enabling a score to be mapped into an approximate correct probability; under the IRT framework, an expert agent jointly estimates the subject ability theta and the question difficulty beta through EM, EM maximum likelihood solution is supported, and weighted aggregation and K-level discretization labeling of continuous difficulty are carried out on the question difficulty according to the model confidence coefficient; furthermore, the monotonous relationship of'difficulty sequence-score sequence 'is verified and checked through self-playing verification of sequence consistency and weighting consistency, so that the non-manual quality acceptance and backtracking are realized. On the premise of unifying the theoretical scale and interpretability, the method has the engineering characteristics of parallelism, friendliness and near-linear expansion, and the robustness and generalization ability are improved; and the obtained difficulty labels are approximately in normal distribution, so that paper composition and hierarchical teaching are facilitated.

The invention provides a weak spot diagnosis and path planning method for an English knowledge graph, relates to the technical field of natural language processing, and aims to provide a weak spot diagnosis and path planning method for an English knowledge graph by constructing a dynamic assessment model of cognitive uncertainty, a cause and attribution diagnosis mechanism of cognitive friction and a diagnosis and repair integrated closed-loop path planning method. And efficient and accurate diagnosis and self-adaptive repair of the weak points of the learner in the English knowledge graph are realized. The robustness and accuracy of weak spot diagnosis are improved, and misjudgment caused by instantaneous behavior disturbance is effectively avoided; through an accurate probe strategy of cause formation and attribution, interference to a learner is reduced, and meanwhile, the efficiency and depth of active diagnosis are improved; according to the method, automatic closed loop from problem discovery to problem solving is realized, and a structured cognitive repair path can be dynamically generated and executed according to a diagnosis result, so that the overall efficiency of personalized learning is improved.

The invention provides a control method and device based on semantic perception and related equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: receiving a natural language trigger condition, and obtaining environment perception data; determining a control instruction associated with the natural language trigger condition in response to matching of the environment perception data and the natural language trigger condition; and executing the control instruction. According to the method, the environmental perception data can be matched with the received natural language triggering condition, and the control instruction is triggered and executed when the environmental perception data and the received natural language triggering condition are matched, so that automatic control based on semantic perception is realized, equipment can more intelligently respond to a target described by a natural language, the operation convenience and the intelligent degree are improved, and the user experience is improved. And the naturalness and efficiency of man-machine interaction are improved, and the requirement of a user for controlling equipment in a natural language is met.

The invention discloses a student cognitive input intelligent evaluation method and system based on multi-agent cooperation. According to the method, on the basis of a directed acyclic graph structure, automatic evaluation is achieved through ordered cooperation of a cognitive input concept agent, a data rule mapping agent, a classroom situation analysis agent, a multi-modal data analysis agent and a comprehensive report generation agent. The method comprises the following steps: firstly, calling a large language model by a cognitive input concept agent to construct a theoretical dimension of cognitive input; the data rule mapping agent generates a specific mapping rule from the data to the index; the classroom situation analysis agent reversely reasones a specific classroom interaction situation based on rules and data; the multi-modal data analysis agent performs feature extraction and classification on the multi-modal data according to rules and situations to generate a structured evidence chain; and finally, the comprehensive report generation agent fuses the evidence and generates an evaluation report, so that comprehensive evaluation of the cognitive investment of the students is realized.

The application provides a cognitive diagnosis method, medium, equipment and product for automatic construction of a Q matrix, relates to the technical field of cognitive diagnosis, and the method comprises the following steps: calculating the correlation score of an exercise and a pre-defined knowledge point, and screening an initial knowledge point set of the exercise by using a large language model; generating a reasoning path for the exercise solution by using the large language model, screening necessary knowledge points on the reasoning path, generating an implicit knowledge point set of the exercise, and constructing a Q matrix by using the initial knowledge point set and the implicit knowledge point set of the exercise; and using the Q matrix for cognitive diagnosis by using a diagnosis model. The application realizes full-automatic construction of the Q matrix in a non-labeled scene, and reduces the dependence of a CDM on data in actual application.

The invention relates to the technical field of automatic typesetting, in particular to a teaching PPT automatic typesetting method and system with cognitive load balance, which comprises the following steps of: based on a teaching PPT page scene, analyzing information unit spatial layout and adjacent interval change, extracting spatial distribution characteristics, combining cognitive load balance, analyzing knowledge point paragraphs and character spans, and obtaining a teaching PPT page scene; dividing knowledge levels, screening visual level conflicts, and outputting page arrangement configuration parameters. According to the method, by analyzing page information unit distribution and knowledge point span characteristics, hierarchical aggregation and primary and secondary partition of knowledge content are achieved, page layout parameters are actively adjusted according to different changes of teaching content, priority judgment and configuration matching are automatically completed when parameter conflicts are processed, and the method is high in practicability. Page display with clear knowledge structure logic and clear primary and secondary contents is displayed, intelligent typesetting with balanced cognitive load is helped to be realized, key knowledge is guaranteed to be efficiently conveyed, and the orderliness and scene adaptability of PPT contents are improved.

The invention discloses a rule determination method, computing equipment and a machine readable storage medium. Relates to the technical field of knowledge engineering and artificial intelligence. The method comprises the steps that a cognitive behavior sequence is determined based on input user operation flow, automatic rule generation is achieved, rule creation and maintenance cost is reduced, and complex behavior logic is adapted; under the condition that an input labeling event is received, determining a target behavior sequence in the cognitive behavior sequence based on the labeling event; under the condition that the target behavior sequence meets the preset sequence specification, the target rule is generated based on the target behavior sequence and the annotation event, it is ensured that the rule can reflect deep association of behaviors and events, and the judgment for complex situations is improved; an internal logic chain of expert decision making is restored through a cognitive behavior sequence, a complete cognitive model of an expert is effectively captured and digitalized, the problem of'cognitive fault 'in knowledge management and inheritance is solved, and efficient conversion from expert implicit experience to reusable dominant rules is achieved.