11 results about "Formal representation" patented technology

A system and method are disclosed for interfacing with one or more databases using natural-language queries. The system translates a natural-language input into an intermediate formal representation, such as a Concept Query Language (CQL), which references domain concepts rather than database-specific structures. A data access subsystem maps these domain concepts to database-specific queries using a domain dictionary, enabling seamless translation across heterogeneous databases and database management systems (DBMSs). The system supports distributed data retrieval, error recovery, and dynamic query planning. A presentation subsystem formats the results into user-friendly outputs such as charts or tables. The architecture allows for modular grammar and dictionary configuration, enabling rapid adaptation to new domains, schemas, or user roles without procedural code changes. This approach improves accessibility, maintainability, and scalability of database interactions by abstracting technical complexity from end users.

The invention relates to a trade rule reasoning method and system based on bidirectional mapping and a storage medium, and relates to the technical field of trade management.The trade rule reasoning method comprises the steps that a trade rule text is collected and split, and a plurality of rule terms are obtained; analyzing the rule terms according to preset key entity elements to obtain rule condition segments, and combining the rule feature weight values to obtain trade rule feature vectors; identifying and converting trade rule feature vectors according to the rule attributes and the dependency relationship between the rules, and constructing a rule dependency graph; converting the trade rule text into formalized rule elements according to the semantic framework and the logic structure in combination with the rule dependency graph; generating an optimal rule reasoning path according to the rule query request in combination with the formalized rule elements; aggregating all the optimal rule reasoning paths to form a trade rule corresponding to the rule query request; and establishing a mapping relationship between the semantic structure and the formalized representation of the rule text through a bidirectional mapping mechanism.

The application relates to the field of space-time data processing, and provides a space-time narrative map generation method and system and a storage medium, wherein deep semantic understanding ability of a large language model (LLM) is innovatively integrated, space-time knowledge is formally represented, a reliable reasoning and checking mechanism is introduced, a verified structured space-time knowledge graph is generated, and finally a complete reasoning chain is visually presented by using an interactive map. Compared with a traditional method, the core advantage of the application lies in that reliable and real-time updating of the space-time knowledge graph is realized, the reasoning process is transparent and intelligent, the reliability of space-time decision support is greatly improved, and the depth and efficiency of information transmission are improved.

This invention relates to the field of contract management technology in the construction and real estate industry, and particularly to an intelligent element extraction method and system for contracts in the construction and real estate sector. The invention includes: standardizing the format and extracting the content of contract documents to obtain extracted files; defining semantic feature rules for the extracted files to obtain a graph structure; performing divide-and-conquer parallel processing on the graph structure to obtain processed subtasks; and performing deep validation on the processed subtasks to obtain structured data. This invention, through the formal representation of graph theory structures, enables rules to handle nested, branching, and looping logic, thereby significantly improving the accuracy and coverage of extraction and reducing missed and false extractions.

This application discloses a code generation method, apparatus, device, medium, and product, relating to the field of application development. The method includes converting front-end application design data into a structured dataset containing page element information, initial interaction topology, and visual design specifications, addressing the problem of insufficient interaction logic description capabilities. It then converts this data into an attributed state transition diagram, describing the complete interaction attributes of the front-end application's page-to-page interaction from pre-interaction preparation to the completion of the interaction's effect, replacing vague natural language descriptions and achieving machine-analyzable interaction logic, bridging the information gap between design and implementation. Finally, it combines a pre-trained language model to directly generate front-end development code, achieving automated and standardized output from design to code, addressing the lack of machine-analyzable formal representation of front-end interaction logic, thereby improving front-end development efficiency and code quality, and reducing communication and maintenance 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.

This invention utilizes methods from the field of network security to realize a training and application method, storage medium, chip, and system for molecular multimodal models. First, the Encoder structure in a Transformer facilitates interaction between candidate document sets and between subtopics or queries. After obtaining formal representations of documents and subtopics, weights are combined using selected documents, all candidate documents, and subtopics. Explicit and implicit scores are obtained through interaction, and finally, the updated weights combine the explicit and implicit scores into a final diversified score range. The method provided in this invention designs an explicit-implicit feature combination model that dynamically adjusts weights at different steps in different queries to improve the diversification of search results. The model is trained using a listpairwise LambdaRank loss function, and experimental results demonstrate the model's effectiveness and interpretability.

The invention relates to the field of spatio-temporal data processing, and provides a spatio-temporal narrative map generation method and system and a storage medium, spatio-temporal knowledge is subjected to formalized representation by innovatively fusing the deep semantic understanding ability of a large language model (LLM), then a trusted reasoning and verification mechanism is introduced, and a verified structured spatio-temporal knowledge map is generated. And finally, visually presenting a complete reasoning chain by using an interactive map. Compared with a traditional method, the method has the core advantages that credibility and real-time updating of the space-time knowledge graph are achieved, transparency and intelligence of the reasoning process are achieved, the reliability of space-time decision support is greatly improved, and the depth and efficiency of information transmission are improved.

The invention relates to an automobile software demand intelligent clarification system and clarification method, and the system comprises a sensing module which is used for obtaining the multi-mode demand information of a user; the clarification module is used for fusing and understanding the adjustment request of the demand information or the formalized representation based on a large language model, and outputting the formalized representation after consistency verification; the dynamic interaction module is used for rendering a visual graph to the user in real time based on the formalized representation; receiving a visual graph modification request of a user, sending a formally represented adjustment request to the clarification module, and displaying the adjusted formally represented visual image to the user; the storage module is used for storing clarified demand information and formalized representation and visual graphs corresponding to the demand information; and finely adjusting the clarification module based on the correction information of the user on the clarification module. Through the big language model and formalization conversion, clear interaction experience and precision are improved, and ambiguity is reduced.

A system and method are disclosed for interfacing with one or more databases using natural-language queries. The system translates a natural-language input into an intermediate formal representation, such as a Concept Query Language (CQL), which references domain concepts rather than database-specific structures. A data access subsystem maps these domain concepts to database-specific queries using a domain dictionary, enabling seamless translation across heterogeneous databases and database management systems (DBMSs). The system supports distributed data retrieval, error recovery, and dynamic query planning. A presentation subsystem formats the results into user-friendly outputs such as charts or tables. The architecture allows for modular grammar and dictionary configuration, enabling rapid adaptation to new domains, schemas, or user roles without procedural code changes. This approach improves accessibility, maintainability, and scalability of database interactions by abstracting technical complexity from end users.

The application relates to a multi-party human-computer interaction reply personification method based on a knowledge graph, and belongs to the field of human-computer interaction. The method comprises the following steps: S1: multi-party human-computer interaction emotional state evaluation; and S2: knowledge graph water ripple propagation. The method adopts a knowledge graph representation mode to mine similar experiences of multiple parties to find potential interesting dialogue content, similar experience promotes users to share emotional experience and group feelings, additional emotional information is introduced into a model by using a VAD emotional dictionary to be formally represented, a robot can feel emotions of multiple parties, and the emotions are fed back to the multiple parties, so that more suitable emotional and more content-rich replies are generated. Experiments are carried out on multi-party dialogue data sets, and experimental results show that the multi-party human-computer interaction system with emotional temperature and knowledge depth can attract the attention of the rest of the parties and become the focus of the multiple parties.