158 results about "Logical expression" patented technology

The invention discloses an electronic medical record automatic quality control system and method based on a large language model, and the method comprises the steps: extracting medical record data from a medical information system, and carrying out the data preprocessing; and performing deep semantic analysis on the medical text by utilizing a large language model, and extracting key diagnosis and operation information. And performing semantic representation on the medical terms by fine tuning the pre-training language model and combining with a multi-layer attention mechanism. And constructing an ICD coding knowledge graph, and calculating the semantic similarity between the diagnosis terms and the ICD coding terms in the electronic medical record by using an embedded vector technology to realize automatic matching. And according to a predefined quality control rule, automatically checking the electronic medical record through the logic expression, and generating a quality control report and an improvement suggestion. And finally, visually displaying quality control and coding results, and outputting a quality control report. The electronic medical record quality control efficiency and accuracy are improved, and standardization and automation of quality control work are achieved.

The invention provides a software demand defect detection method based on a large language model and a satisfiability problem solver, and the method comprises the steps: constructing a domain knowledge base, guiding the large language model to extract key elements in a demand text through combining with a cue word project, and recognizing imperfect and ambiguous defects; and meanwhile, the demand is converted into a logic expression, and logic inconsistency is detected by using an SAT solver. According to the method, incremental updating of the knowledge base is supported, efficient retrieval and comparison are achieved through vectorization and Hash coding technologies, experiments show that the method is remarkably superior to a traditional technology in demand detection in the fields of finance and the like, defects can be accurately positioned, correction suggestions can be provided, and the efficiency and accuracy of demand analysis are effectively improved.

The invention discloses a tool calling semantic analysis method and system for a low-resource data environment, and relates to the technical field of semantic analysis, and the method comprises the following steps: constructing a logic expression of each tool based on a context-independent grammar, and generating initial training data in combination with a cue word project and a large language model; performing iterative training on a pre-configured semantic analysis model according to the obtained training data in combination with a self-training method to obtain an optimized semantic analysis model; and performing similarity calculation on the tool candidate data and the training data through a recall model to obtain vector scores of the tool candidate data and the training data, and screening out tools which do not conform to user semantics to obtain a final semantic analysis model. According to the method, the initial analysis data set based on the context-independent grammar is constructed, and the analysis capability of the model is enhanced in combination with the self-training strategy, so that the performance of the model in a low-resource environment is improved, and the semantic analysis capability is effectively expanded.

The invention discloses a small and medium-sized enterprise information management method and system based on a multi-layer architecture, and belongs to the technical field of information management, and the method comprises the steps: constructing a decoupling architecture of a user interface layer, a business logic layer and a data storage layer; analyzing the evaluation standard through a dynamic rule engine of a business logic layer, and generating a configurable rule unit comprising a logic expression and a dynamic weight parameter; an offline priority strategy is adopted at the mobile terminal, and a vector clock identifier containing a client ID and a logic clock sequence is added to a data record; executing dynamic weighted evaluation calculation to generate a total evaluation score; and performing industry reference threshold verification on the numeric field. The technical bottleneck of tight coupling of multiple layers of modules in a traditional single framework is broken through by constructing a decoupling framework of the user interface layer, the service logic layer and the data storage layer and an asynchronous message bus communication mechanism, so that cross-layer codes do not need to be synchronously modified when the system adds or adjusts the evaluation dimension, and the system reliability is improved. And the framework flexibility and the expansion efficiency are obviously improved.

The invention relates to a public multi-mode cloud network resource software security enhancement method based on neural symbol fusion reasoning, which comprises the following steps: an intermediate representation generation stage: generating and optimizing an intermediate representation of a program through a fine-tuned large language model, and establishing semantic mapping from a source code to a structured logic representation; in the symbol language conversion stage, the intermediate representation generated by the large language model is converted into a domain-specific language fact set which can be recognized in the symbol logic reasoning stage, and formal and logic expression of program semantics is achieved; and a symbol logic reasoning stage: matching the fact set with the rule base through a symbol logic reasoning engine, performing detection and verification according to the safety rule, generating a structured report, and feeding back a result for optimization. The method is suitable for security enhancement of various core software systems in a public cloud network multi-modal network environment, high-precision security analysis is carried out on cross-modal and cross-subsystem fragmented codes in a compiling-free environment, and verifiable technical support is provided for public cloud network security control.

Techniques for a natural language interface for searching and retrieval of digitally-stored information are disclosed. In one embodiment, a computerized method is disclosed comprising receiving, at a computing device, natural language input from a user; generating, by the computing device, a prompt using the natural language input; submitting, by the computing device, the prompt to a large language model (LLM); receiving, by the computing device, from the LLM, a response to the submitted prompt, the response comprising a logical expression of the natural language input generated by the LLM using the prompt; generating, by the computing device, for a data source, a query using the logical expression; retrieving, by the computing device, a query result set from the data source using the query; and generating, by the computing device, a response to the natural language input using the query result set.

The invention discloses a large language model knowledge verification and improvement method and device and a medium. The method comprises the steps that task description, specific problems and example data input by a user are received; in combination with a preset heuristic cue word and structured processing, generating a logic expression, and removing redundant contradiction rules to form a logic knowledge base; inputting specific questions into the large language model to generate preliminary answers, and performing symbolization conversion on the preliminary answers to extract entities, relationships and attributes so as to obtain symbolized propositions; matching the symbolized proposition with the logic knowledge base, if a conflict is matched, generating a candidate correction scheme through deductive reasoning, determining an optimal scheme according to a predefined correction cost function, feeding back the optimal scheme to the large language model, and regenerating an answer; and iterating the related steps until the answer passes verification, and outputting a final answer, a confidence score and an interpretability report. Through the deductive constraint and bidirectional feedback mechanism, the LLM output reliability is improved, the knowledge base cost is reduced, and dynamic updating and interpretability of knowledge are realized.

The invention discloses an expressive control dynamic display system and method for a semiconductor design form, and the system comprises an expression configuration module which is used for receiving a logic expression inputted by a user, and prompting available variables in the form in real time; the variable dependency analysis module is used for identifying dynamic variable reference in the logic expression; the change monitoring and scheduling module is used for monitoring a form data change event, acquiring an affected control set when variable value change is detected, and merging and optimizing expression calculation requests; the expression analysis service module is used for performing grammar check and dangerous operation filtering on the logic expression, processing an expression calculation request and returning an analysis result; and the state updating execution module is used for comparing the difference between the analysis result and the current control state according to the analysis result, and judging whether the current control needs to be updated or not according to the difference. According to the method, the problem of performance waste caused by global monitoring data change is effectively solved.

The embodiment of the invention discloses an intelligent number asking method and system based on dynamic feedback, a storage medium and electronic equipment. The method comprises the steps that a subject domain and a semantic model are constructed, a data view is established, data mapping is configured, and a natural language problem and a standardized index are analyzed; generating an SQL (Structured Query Language) logical expression based on the Few-shot example and the large model, and carrying out semantic correction on the SQL logical expression; sQL query is executed, dynamic feedback storage is carried out based on an execution result, and SQL generation parameters are updated by utilizing a self-adaptive learning mechanism. According to the method, through semantic modeling and data mapping, precise alignment of a natural language and a database structure is achieved; few-shot examples and large model generation are combined with semantic correction rules, so that the accuracy and stability of SQL generation are improved; and a continuously optimized intelligent number-asking closed loop is constructed by executing a feedback and adaptive learning mechanism, so that the self-learning and evolution capabilities of the system are improved.

Described are methods, systems, and media for regulatory exploration comprising: receiving a regulatory exploration request comprising a scenario comprising a desired outcome and a plurality of partial inputs to describe the scenario and identify fact constraints; receiving an executable regulatory logic flow chart, wherein each element of the flow chart is associated with a regulatory text; applying algorithm to determine all paths in the regulatory logic flow chart; filtering the paths based on the desired outcome; transforming each remaining path into a logical expression comprising attributes; generating a query space comprising conditions on the input facts associated with each attribute; generating a fact space comprising input facts associated with each attribute; generating a possibility space by joining the input facts in the fact space under the conditions in the query space; converting the possibility space to a plurality of database queries; and running the queries to generate an output.

The invention provides an agent control instruction generation method and device, equipment, a medium and a product. The intelligent agent control instruction generation method comprises the following steps: splitting an obtained natural language according to a set rule to obtain splitting units; generating a function corresponding to each splitting unit based on the splitting units and a trained function model; constructing a capability logic expression corresponding to the obtained natural language based on the function corresponding to each splitting unit; and generating an agent control instruction based on the capability logic expression. By analyzing the natural language, the corresponding split unit is converted into the corresponding function, the natural language data is standardized through the function, then the agent control instruction is constructed based on the function, and semantic analysis is decoupled from the internal logic of the agent, so that the intelligent agent control instruction is obtained. Therefore, the instruction generation method can be flexibly and repeatedly used and is convenient to migrate.

A logical expression acquisition unit (502) acquires a logical expression that represents a condition under which searchable encryption is permitted, by a logical structure with a plurality of attribute values and a logical operator. An encrypted tag generation unit (504) sets a secret sharing value which reflects the logical structure, to each of the plurality of attribute values, and generates an encrypted tag to be used for the searchable encryption, using a plurality of secret sharing values set to the plurality of attribute values.

A distributed system provides access by a principal to a resource associated with sensitive data. Micro-services in communication with an authorization engine each include a resource provider that receives a resource action request from the principal to access the resource, determines a context for the request, and transmits the context to the authorization engine in an authorization request. The authorization engine receives the authorization request, resolves the authorization request context against a plurality of pre-defined resource conditions, and responds to the resource provider with an authorization response of allow, deny, or allow-with-conditions. The context for the request includes metadata regarding attributes of the principal, and each of the resource conditions includes a logical expression operating upon the attributes.

The invention relates to the technical field of software testing, and discloses an LLM and SMT solver-based test case generation method, which is characterized in that a search type test is taken as a core drive, when coverage stagnation occurs, an execution path is subjected to semantic analysis by means of an LLM, a logic expression for describing a target path condition is generated, and in consideration of the limitation of the LLM in logical reasoning, a test case is generated; the system further introduces an SMT solver to perform verification and reasoning on a logic expression output by the LLM, finally feasible test input is generated, and the test efficiency and the coverage rate are improved. According to the method, the efficiency and precision of path coverage are improved, good adaptability and universality are achieved, the method is suitable for various languages and complex program structures, and the intelligent level and engineering practical value of automatic testing are effectively improved. The problem of insufficient accuracy of a large language model in complex path constraint reasoning is effectively relieved.

The invention relates to a 5G security demand extraction and assertion generation technology based on LLM and RAG, and the technology comprises the following steps: 1, a standard document preprocessing module, splitting a 3GPP standard document according to a security process hierarchy, mapping the 3GPP standard document to a corresponding label, and solving a knowledge fragmentation problem; the RAG knowledge base construction module analyzes document slices by using an RAGF low tool, divides the document slices into text blocks, stores the text blocks into a database through vectorization of an embedded model, and realizes efficient retrieval by adopting hierarchical indexing; 3, an LLM semantic understanding and assertion generation module, which is used for converting a natural language demand into a logic expression based on a DeepSeek model in combination with a cue word framework, a knowledge base and a signaling alphabet; and the assertion post-processing module is used for performing grammar check, standard conformity verification, simplification and logic conflict detection on the LTL assertion. According to the technology, automatic extraction of security requirements and assertion generation are realized, efficiency and accuracy are improved, security requirements in multiple aspects are covered, and a reliable scheme is provided for 5G terminal protocol security testing.

The invention relates to the technical field of data analysis, and discloses an event context generation method and device, computer equipment and a storage medium, and aims to analyze theme description information, recommend synonyms and generate a keyword list through a large language model, simplify the operation difficulty of clients and improve the data comprehensiveness. According to the method, the news data are collected through the logic expression corresponding to the keyword list, the time feature text in the news data is standardized, the target short sentence only containing the standard time is obtained, the standard time corresponding to various texts is deduced through the context reasoning ability of the large language model, and the data recall rate and accuracy are improved. The target short sentences are grouped and clustered by using a large language model vector, so that the merging capability of similar events is improved. And selecting the core short sentences of each cluster to generate event sequence data, processing the event sequence data in combination with a logic expression, and filtering uncorrelated events. And finally, generating event venation with high readability by utilizing text output and summarization capability of the large language model.

The invention provides a complex scene visual recognition rapid construction method based on natural language description, and relates to the technical field of computer vision and natural language processing, and the method comprises the steps: obtaining natural language description information inputted by a user; performing language analysis and element extraction on the natural language description information to obtain a scene semantic table; decoupling the scene semantic table into M atomic conditions, and obtaining an atomic instruction set; performing visual feature extraction on the to-be-recognized image by using a visual encoder to generate an image feature vector; converting the atomic instruction set into an atomic instruction vector set, and outputting an atomic instruction verification set; generating a relation verification matrix; and executing global logic expression verification operation based on the atomic instruction verification set and the relationship verification matrix, and outputting comprehensive confidence. The technical problems that in the prior art, semantic understanding depth is insufficient, complex scene understanding is limited, and self-adaptive capacity is insufficient are solved.

The invention discloses a chemical industry park environmental pollution risk intelligent assessment method and system, and relates to the technical field of environmental risk management, and the method comprises the steps: extracting an association rule of a risk event based on a real-time data stream, coding the association rule into a symbolic logic expression, constructing a mixed neural symbol architecture, and carrying out the construction of a hybrid neural symbol architecture; optimizing the symbolic logic expression and the mixed neural symbolic architecture parameters through joint training, and outputting a preliminary risk level assessment result; according to the real-time data stream, extracting a'risk event-cause-consequence 'triple, generating a risk knowledge graph, and performing graph reasoning in combination with a preliminary risk level assessment result to obtain a risk event causal chain and a diffusion path; according to the method, efficient integration and dynamic optimization of the multi-source heterogeneous data are achieved by constructing the mixed neural symbol architecture, and the problem that space-time relevance is weakened due to data splitting type processing in an existing method is solved.

The invention discloses a logic knowledge construction method and device based on a large language model and logic programming, electronic equipment and a storage medium, and belongs to the field of artificial intelligence knowledge engineering. According to the method, automatic conversion from multi-source heterogeneous knowledge to machine reasonable logic knowledge is realized through combination of semantic understanding capability of a large language model and standardized processing of logic programming. The method specifically comprises the steps of obtaining unstructured / semi-structured original knowledge data, performing entity relationship recognition and predicate logic detection by utilizing a large language model to generate a preliminary logic expression, performing grammar normalization processing to form standard logic facts and rules, and constructing a consistent logic knowledge base through a conflict detection and resolution mechanism. According to the method, a mixed conversion framework of natural language and formalized logic is innovatively provided, and the maintainability and expandability of the knowledge base are remarkably improved by introducing timestamp metadata, a rule dependence graph and an incremental updating mechanism. The technology provides structured logic support for subsequent large model reasoning, and can be widely applied to intelligent questions and answers, decision support and other scenes requiring precise logic reasoning.

The invention discloses a summary generation method and a related device, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining multi-source information of a target conference, obtaining a summary generation prompt instruction according to the multi-source information, the summary generation prompt instruction is used for instructing a summary generation large model to generate a summary according to the content of the multi-source information, and generating a structured conference summary by referring to the hierarchical structure in the conference presentation, and inputting a summary generation prompt instruction into a pre-trained summary generation large model to obtain the conference summary of the target conference. According to the method, the hierarchical structure of the conference summary can be reconstructed based on the hierarchical structure of the conference presentation, so that the content of the multi-source information can be presented as a more logical expression in the conference summary, and the readability of the conference summary is improved.

The invention discloses an index system early warning method and device, equipment, a storage medium and a program product, and relates to the technical field of operation and maintaining.The method comprises the steps that a logic expression input by a user in a similar natural language form is analyzed, an abstract syntax tree is generated, recursion processing is conducted through a recursion decline interpreter, and an executable rule object is obtained; scheduling the executable rule object according to a preset priority weight to obtain a total scheduling result, the preset priority weight being a weight allocated for the priority of each early warning rule; and when the early warning rule is triggered, carrying out early warning on the abnormal indexes in the logic expression. According to the method, the logic expression is introduced to dynamically define the index, then the logic expression is analyzed into the abstract syntax tree, and dynamic compiling of the abstract syntax tree is realized by using the recursive decline interpreter, so that the flexibility of index early warning can be improved through the introduced logic expression in a complex monitoring scene, and the early warning efficiency is improved. Therefore, the efficiency of index operation and maintenance response is improved.

The invention relates to the technical field of information security, in particular to a trusted data space-based data exchange security verification method, which comprises the following steps of: identifying punctuation marks of request data, splitting the request data into a plurality of data segments, identifying logic expression words in each data segment, and then identifying parallel information in the data segments, so as to verify the security of the data exchange. The method comprises the steps of dividing a data segment into a plurality of pieces of independent local information based on parallel information, carrying out privacy value calculation on each piece of independent local information, setting a corresponding security verification level for the local information based on the privacy value of the local information, and carrying out security verification on each piece of local information based on the security verification level, thereby avoiding an overall verification vulnerability; according to the method, the privacy value and the verification level of each piece of local information are dynamically evaluated, and the circulation efficiency is improved while compliance is ensured.

The invention discloses a wide table data analysis method and system based on semantic association, and the method comprises the steps: receiving a natural language query demand input by a user, carrying out the semantic understanding through a pre-training language model combined with a financial knowledge graph, and generating a corresponding semantic expression; performing semantic analysis on the semantic expression, and disassembling the semantic expression into a logic expression containing a query demand and an analysis demand; based on the logic expression of the query demand, matching a corresponding wide table and field information through a preset index library, generating an executable query statement, and obtaining target data from the wide table; and according to the logic expression of the analysis demand, generating a corresponding data analysis code by using the code generation model, and analyzing the target data to generate an analysis result. The limitation of a traditional wide table fixed association mode is broken through, efficient integration and intelligent analysis of wide table data are achieved, the flexibility and accuracy of data processing are improved, and the limitation of wide table application in a fixed scene is broken through.

The present invention discloses a tool call semantic parsing method and system for low-resource data environment, which relates to the field of semantic parsing technology. The method comprises the following steps: based on context-free grammar, constructing logical expressions of various tools, and combining prompt word engineering and large language model to generate initial training data; for the acquired training data, combining self-training method, iteratively training the pre-configured semantic parsing model to obtain an optimized semantic parsing model; through the recall model, similarity calculation is performed on the tool candidate data and the training data to obtain vector scores of the tool candidate data and the training data, and the tools that do not conform to the user semantics are screened out to obtain the final semantic parsing model. The present invention constructs an initial parsing data set based on context-free grammar, and enhances the parsing ability of the model in combination with a self-training strategy, thereby improving its performance in a low-resource environment and effectively expanding the ability of semantic parsing.

The invention discloses a judgment logic configuration method and device, a readable medium, electronic equipment and a product, and the method comprises the steps: displaying a judgment logic configuration page, and displaying an input region which is used for a user to construct a judgment logic expression in a mode of inputting a judgment variable name in the judgment logic configuration page; in response to a variable input operation in the input area, displaying a variable name of a candidate judgment variable corresponding to the variable input operation; in response to a selection operation on a target variable name in the variable names of the candidate judgment variables, displaying the target variable name in the input area; and in response to an input operation of inputting a logic operator and a target judgment parameter in the input region, obtaining a target logic expression comprising the target variable name, the logic relational symbol and the target judgment parameter. A user can construct the judgment logic expression in the mode of inputting the variable name in the input area, operation is easy, errors are not prone to occurring, and the editing efficiency of the judgment logic expression can be improved.

The application belongs to the technical field of natural language processing and knowledge graph, and discloses a kind of multi-modal acquisition and evolution graph analysis method and system of policy text. In view of the passive decision problem caused by the rigidity of existing policy analysis, semantic understanding and lack of dynamic correlation, the application adopts visual and DOM feature weighted fusion and reinforcement learning agent to realize multi-modal adaptive acquisition and joint alignment in anti-crawling environment;Use large language model for semantic deconstruction, and convert implicit logic into computer-readable explicit logic expression through thought chain reasoning;Construct a policy evolution knowledge graph with time and validity level attributes, perform satisfiability analysis to output conflict detection results;Map the target object portrait to the graph and the logic expression to evaluate item by item, and output intelligent decision deduction results combined with quantitative dimensions. The application realizes the whole life cycle intelligent analysis of policy data acquisition, deep logic analysis and active deduction.

The invention belongs to the technical field of intelligent question answering, and particularly relates to an experimental question answering method and system based on a knowledge graph. The method comprises the following steps of: generating a candidate combination category grammatical analysis tree for an input experimental question statement, and when vocabularies outside a preset dictionary are encountered, assigning a temporary combination category in combination with word vectors and adjacent entity types; calculating the syntactic probability of the analysis tree and the node intensity of the entity subgraph in the tree, determining a target syntactic analysis tree, and converting the target syntactic analysis tree into a logic expression; extracting an anchor point entity and a semantic relationship, determining a search depth according to sub-graph intensity, and constructing an initial graph query statement by utilizing bidirectional breadth-first search; if the query result does not exist, differential query reconstruction is carried out according to an intensity threshold value, when the intensity is high, only the semantic relation is replaced with a parent class, otherwise, the parent class and brother class relation is considered at the same time, and a sub-graph or an entity obtained through query is output as an answer. According to the method, the suitability, accuracy and fault tolerance of the experiment question-answering system can be improved, and the query efficiency and the recall rate are balanced.

The embodiment of the invention provides a digital pilot model generation method and device, equipment and a medium. The method comprises the steps that a digital pilot is constructed; according to the model element logic expressions of the digital pilots corresponding to the different flight sorties, the model definitions of the digital pilots corresponding to the different flight sorties and the flight data corresponding to the flight sorties, action parameters of the digital pilots corresponding to the flight sorties are determined; constructing a digital pilot model training data set according to the behavior action, the action parameter and the operation safety value of the digital pilot of each flight sortie; and training the initial digital pilot model based on the constructed digital pilot model training data set, and determining a target digital pilot model. And a basis is provided for subsequent comprehensive and efficient identification of safety risks existing in the flight process.

The application relates to the fields of data query and blockchains, and particularly relates to a query method and device based on a Chinese logical expression. The method comprises the following steps: receiving a query request carrying Chinese query information from a user end; generating a Chinese logical expression according to the Chinese query information carried by the query request; querying a pre-constructed block information table according to the Chinese logical expression to obtain a query result; and returning the query result to the user end. The embodiment of the application can enable users without a learning basis of a traditional SQL query language to conveniently query block information.