225 results about "Graph query" patented technology

The invention relates to the technical field of intelligent decision making, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a knowledge graph question and answer result generation method, device, equipment and medium, which comprises the steps of performing semantic analysis on a user question to obtain entity information and a query intention, performing logic analysis on the entity information and the query intention to obtain a question and answer result; obtaining an initial execution plan; calling a sub-graph query tool according to the initial execution plan, and querying sub-graph data by using the sub-graph query tool; performing linearization processing on the sub-graph data to obtain a sub-graph data text, extracting a candidate entity set in the sub-graph data text, and screening out a matched target entity from the candidate entity set; performing logic analysis on the target entity and the query intention to obtain a target execution plan, and screening out a matched atomic query tool from the candidate tool set; and querying a knowledge graph question-answer result by using an atomic query tool. The knowledge graph question and answer result generation accuracy can be improved.

The invention relates to the technical field of distributed agent collaboration and graph database query optimization, in particular to a graph query processing method and system based on multi-agent collaboration, and the method comprises the following steps: reasoning a coordination agent to analyze the semantics and intention of user query by using a large language model; a structured multi-agent execution plan is output, and an entity search agent or a relation analysis agent needing to be called is explicitly called; the agent coordinator receives the multi-agent execution plan and selects agents according to task types and task allocation; obtaining a distributed intermediate result set; starting a result aggregation mechanism, and performing typed processing, priority ranking and deduplication merging on the distributed intermediate result set to obtain an arrangement result; and outputting an answer for answering the initial question of the user. The system comprises an agent execution plan output module, a multi-task execution module and an arrangement result reasoning module. According to the method, efficient, extensible and fault-tolerant graph query processing is realized.

The invention discloses a new energy equipment troubleshooting method based on a knowledge graph and a large model. The method is used for solving the problems of fault positioning and troubleshooting of photovoltaic and wind power new energy equipment and the like. The method mainly comprises the following steps: performing data cleaning and preprocessing on a new energy equipment troubleshooting professional field document, and constructing a structured knowledge graph of equipment types, fault types, fault information and solution nodes in a graph database through Cypher; the big language model analyzes the user fault description, extracts and maps node attributes in the knowledge graph, and generates a graph query statement; the question-tracing type multi-round interaction is realized, the missing information is dynamically complemented, and the basic fault is accurately positioned in a step-by-step reasoning mode; according to the method, multi-modal resources such as texts, schematic diagrams and videos stored in the knowledge graph are combined, a step-by-step reasoning path and a solution with illustrative features are generated through a preset template, the whole reasoning process is visualized in a branch thinking graph form, and the accuracy, interpretability and user experience of troubleshooting are remarkably improved.

Embodiments of the disclosed technologies include parsing a query into a first query portion and at least one second query portion, matching an embedding of the at least one second query portion with an embedding that corresponds to a portion of a document of a document set, mapping the portion of the document to a first node of a graph; by a generative artificial intelligence model, constructing a graph query based on at least the first node, executing the graph query on the graph to identify a second node of the graph, extracting a path from the graph, and configuring the path for output at a device.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a root cause analysis method and device based on a space-time dependency graph, equipment and a medium. Comprising the steps of constructing a space-time dependency graph, generating a diagnosis path blueprint, identifying a fault source and a root cause entity type, generating a graph query statement, executing query and performing cause and effect verification, and outputting a root cause analysis report. And the causal reasoning and root cause positioning of the system state change are realized by fusing the graph structure information and the natural language processing capability. Through cooperative processing of a language model and a graph data structure, fault symptom information and system structured state data are deeply fused, a path is generated in the graph structure, and a causal relationship is verified, so that the ability of understanding a complex system state evolution chain is improved, and accurate identification and diagnosis of root causes are realized. And the accuracy and the automation level of root cause analysis are obviously enhanced.

The invention belongs to the technical field of computer-aided project management, and discloses an electric power engineering design project management system and method, and the system comprises a data integration and processing module, a multilayer dynamic knowledge graph data storage library, a graph-based automatic compliance check engine, and a graph neural network-based predictive risk engine. And an active design change impact analysis module. According to the method, a unified and intelligent project data core is constructed, heterogeneous data sources such as design files and law and regulation texts are integrated in a multi-layer dynamic knowledge graph, automatic compliance review is realized by utilizing graph query, data-driven risk prediction is realized by utilizing a graph neural network GNN, and the risk prediction efficiency is improved. And the linkage influence of design change can be simulated and quantitatively evaluated. According to the method, the problems of data islanding, passive compliance examination, subjective risk management, difficulty in change analysis and the like in the prior art are solved, and the management efficiency, accuracy and initiative of the electric power engineering design project can be remarkably improved.

The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating function code and test code to determine that the function code satisfies an intent query. For example, the disclosed systems utilize a large language model to process an intent query and generate function code that defines one or more processes whose execution satisfies the intent query. In addition, the disclosed systems also utilize the large language model to generate test code that defines a function test for determining that the function code satisfies the intent query. Moreover, the disclosed systems can execute the test code to determine that the function code satisfies the intent query.

Described are examples for creating a graph model for data obtained from multiple data sources and stored in a common data format. A selection of columns of data stored in the common data format that are to be associated with one another in the graph model can be obtained. Based on the selection, a graph model can be created including metadata that defines a list of vertices corresponding to at least a portion of the columns and a list of edges between two or more of the vertices identifying a relationship between corresponding columns. A graph query or graph algorithm can be performed over the graph model of the data as stored in the common data format without requiring copying of the data to a separate graph database.

The embodiment of the invention provides a crop knowledge graph question answering method and system based on a large model and data assimilation, and the method comprises the steps: generating an initial knowledge graph based on a dynamic graph neural network; updating the initial knowledge graph based on a dynamic incremental graph updating algorithm; performing knowledge extraction and understanding on questions of a user based on a large language model LLM, processing an output result of the LLM, and generating a graph structured query template; obtaining Prompt query templates constructed by LLM, fusing the Prompt query templates with the knowledge graph, obtaining optimal information query by applying a reinforcement learning path optimization method, and integrating graph query results obtained by the Prompt query templates; and performing question and answer result generation based on the optimized and adjusted LLM fusion graph query result. According to the method, multi-modal data are fused, a high-precision qa question-answer pair is generated in combination with historical user query questions q to finely adjust the vertical field large model, and the question-answer accuracy is improved by building a multi-layer Prompt strategy.

The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating function code and test code to determine that the function code satisfies an intent query. For example, the disclosed systems utilize a large language model to process an intent query and generate function code that defines one or more processes whose execution satisfies the intent query. In addition, the disclosed systems also utilize the large language model to generate test code that defines a function test for determining that the function code satisfies the intent query. Moreover, the disclosed systems can execute the test code to determine that the function code satisfies the intent query.

The present invention provides a method for evaluating the effects of communication confrontation based on a knowledge graph, which relates to the field of communication confrontation. The present invention first constructs a knowledge graph of the communication network, converts nodes, communication relationships, and interference relationships into a graph structure, and represents the connection and interference between nodes through the edges in the graph. Then, the node connection relationship is obtained through graph query, the impact of interference and communication quality is calculated, and the shortest path between nodes is calculated using a graph algorithm to achieve an evaluation of the communication effect. The present invention aims to provide a more comprehensive and accurate evaluation of the effects of communication confrontation from the perspective of complex communication networking by analyzing the connection relationship and information transmission path between communication nodes. Through this method, the effect of communication confrontation can be evaluated from the global perspective of the communication network, thereby improving the comprehensiveness and accuracy of the evaluation.

Various examples of improving an in-memory graph query engine using a persisted storage component are provided. The method includes updating data stored in an in-memory graph query engine and, based on updating the data, converting the data to a plain text form that may be more efficiently stored in the persistent storage component. The method further includes updates to additional in-memory graph query engines from the persistent storage component such that in-memory data stored in the graph query engines is synchronized.

The invention relates to the technical field of equipment control, and provides an equipment control method and system based on a natural language and electronic equipment. According to the application, the machine language vector is generated through the intention recognition result of the natural language instruction, and the graph query statement is generated according to the semantic concept after the machine language vector is deconstructed, so that the equipment knowledge graph of the original equipment is queried through the graph query statement to obtain the equipment operation path meeting the semantic concept; the knowledge graph has a mesh topology structure, the equipment knowledge graph is used for replacing a rigid relational database structure, deep requirements in natural language instructions are mined through intention recognition, machine language vectors are obtained, the machine language vectors are deconstructed, and the control of the original equipment is achieved. And generating a graph query statement corresponding to the equipment knowledge graph according to the deconstructed semantic concept, thereby accurately and comprehensively querying the complex context semantic relationship between the nodes, and improving the understanding accuracy of the natural language instruction.

The invention belongs to the technical field of map construction, and discloses an online vectorization map construction method based on dynamic query management. Extracting perspective image features; generating aerial view view angle features based on the perspective image features; initializing map element query; inputting the initialized map element query and the aerial view view angle features into a map decoder based on dynamic query management, and optimizing the map element query; taking the output result of the Lth layer of the map decoder based on the dynamic query management as the final prediction of the attribute of the map element; and carrying out loss calculation and training. By optimizing and dynamically managing map queries in a map decoder, the computational consumption of low confidence map queries is effectively reduced. Under the same computing resources, the model is allowed to process a larger number of map queries, so that the construction precision of the vectorized map is improved. The research of automatic driving on-line map construction is further promoted, and the deployment of an on-line vectorization map model is facilitated.

The invention discloses a dynamic knowledge graph construction and application method, system and device for energy policy influence conduction analysis and a medium, and the method comprises the steps: carrying out the multi-dimensional knowledge extraction of an energy policy text through employing a first adaptive extraction model, and outputting a structured knowledge triple; constructing a dynamic multi-subject knowledge graph; performing deduction search on the potential association path through a first influence search algorithm, and identifying a key policy influence conduction chain; an event-driven knowledge graph closed-loop self-evolution mechanism is established, policy change events are captured in real time through automatic monitoring, and incremental updating and structure correction of the dynamic multi-subject knowledge graph are triggered; and constructing a scene-oriented personalized application service interface according to the dynamic multi-subject knowledge graph, converting a user natural language query into a graph query instruction, and generating a scene response in combination with a retrieval result. According to the invention, the cost of manual arrangement and maintenance is obviously reduced, and the working efficiency and expandability of the system are improved.

The invention discloses an airport apron operation intelligent question answering system and method based on knowledge graph reasoning, and belongs to the technical field of knowledge graphs and artificial intelligence. The method comprises the following steps: constructing an airport apron operation knowledge graph by fusing multi-modal data sources; analyzing a user query intention by using a large language model, realizing alignment of the oral entity and the map standard entity, and generating a standardized query; decomposing the standardized query into an ordered subtask sequence based on thinking chain reasoning, and generating a tool calling plan; and executing the tool calling plan, obtaining a fact basis by sequentially calling a graph query tool, and generating an interpretable answer in combination with a reasoning path. According to the method, multi-modal source data can be deeply fused, a high-precision domain knowledge graph is automatically constructed, and on the basis, an interactive, reasonable, safe and credible intelligent question and answer system is provided.

In general, this disclosure describes techniques for analyzing anomalies in a network. In an example, a method comprises obtaining, by a system, a graph query and a network graph for a network, wherein the network graph includes one or more nodes having one or more properties that indicate a plurality of anomalies for the network; executing, by the system, the graph query on the network graph for the network to determine a matching subgraph of the network graph, wherein the graph query matches on the one or more nodes and the one or more properties; and based on the determination of the matching subgraph, outputting an indication of an association of the plurality of anomalies.

The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating function code and test code to determine that the function code satisfies an intent query. For example, the disclosed systems utilize a large language model to process an intent query and generate function code that defines one or more processes whose execution satisfies the intent query. In addition, the disclosed systems also utilize the large language model to generate test code that defines a function test for determining that the function code satisfies the intent query. Moreover, the disclosed systems can execute the test code to determine that the function code satisfies the intent query.

The invention belongs to the technical field of data retrieval, and particularly discloses an inquiry method and system based on a vector database and graph query, a terminal and a medium, and the method comprises the following steps: importing structured data into a graph database, and constructing a knowledge graph with entity nodes and edge relationships; generating a first semantic vector through the semantic coding model, storing the first semantic vector into a vector database, and establishing an index; a user inquiry text is received, and after sensitive information detection and context analysis are executed, a second semantic vector is generated through the semantic coding model; performing similarity retrieval in a vector database based on the second semantic vector to obtain a plurality of candidate node identifiers; executing query in a limited range by taking the candidate node as a starting point in the graph database, and extracting associated nodes and relationships to form a sub-graph; performing joint scoring on the sub-graph structures, and sorting the paths based on a scoring result; and generating and outputting an answer text according to the sorting result. The problem that in the prior art, semantic understanding and relation reasoning are disjointed and difficult to co-process is solved.

The invention provides a civil aircraft fault information retrieval method and system based on a knowledge graph and vector retrieval. The method comprises the following steps: firstly, carrying out batch vectorization processing on knowledge in a knowledge graph library, and constructing a vector index library; after a user query is received, the system preprocesses the user query and extracts information by adopting a hybrid strategy: special codes are accurately matched and recognized through a dictionary, and meanwhile, natural language description is converted into query vectors by utilizing a deep semantic model. Then, the system executes two kinds of retrieval in parallel: one is structured graph query based on accurate information, and the other is semantic similarity search in a vector index database; and finally, performing intelligent fusion and sorting on results returned by the two kinds of retrieval. By combining the accuracy of structured query and the recall capability of vector retrieval, the problems of various expressions, fuzzy semantics and the like in civil aircraft fault information query are effectively solved, the accuracy and comprehensiveness of fault information retrieval are remarkably improved, and more accurate and efficient decision support is provided for aircraft maintenance personnel.

The embodiment of the invention provides a graph query statement generation method, a data query method and related devices, and belongs to the technical field of natural language processing. The graph query statement generation method comprises the following steps: identifying an entity relationship in a natural language question, and retrieving a target vertex matched with the entity relationship in a graph; wherein the graph is pre-generated based on the graph structure data; acquiring local graph structure data within a specified degree from the target vertex, and generating a first prompt statement based on the local graph structure data; and inputting the first prompt statement into the large language model to generate a first graph query statement. According to the method, the accuracy of converting the natural language into the graph query language by a large model can be improved.

The invention belongs to the technical field of computer data processing, and particularly relates to a dynamic RAG-NL2SQL system based on a real-time data blood relationship map. Comprising the steps that a cost-delay sensing intelligent routing module receives a user question, carries out macroscopic element decision making and calls related modules for execution; the real-time data blood relationship map construction and maintenance module constructs and dynamically maintains a real-time data blood relationship map; the intention-blood relationship dynamic retrieval enhancement module queries a data source sub-graph matched with a user question from a real-time data blood relationship graph and serializes the data source sub-graph into text description; the traceable SQL generation and closed-loop verification module generates an SQL according to the text description and the original problem of the user, executes and verifies an execution result, and starts a closed-loop verification and repair process if verification fails; the zero sample memory bank multiplexing module constructs the verified query into a memory unit, and dynamically evaluates the memory unit; semantic multiplexing and intelligent elimination are carried out according to an evaluation result; the automation level and the overall reliability of the system are improved.

The invention discloses a medical data storage method based on semantic recognition, and belongs to the technical field of data processing, and the method comprises the steps: receiving medical data, carrying out the parallel processing of an unstructured medical text in the medical data through a large language model, and generating a structured semantic triple and a semantic vector representing the overall semantics; constructing a semantic graph index and a vector index to form a mixed index structure; the method comprises the following steps: receiving a natural language query, analyzing the query into a structured query condition and a query vector, forming an executable multi-modal query instruction, executing atlas query and a vector similarity search process in parallel, and mapping the structured query condition to a semantic atlas execution path for matching. In the implementation process of the technical scheme, natural language processing and a large language model are introduced, entity recognition, relation extraction and semantic role labeling are conducted on medical unstructured texts, and structured conversion of key information such as illness state description, diagnosis conclusions and treatment schemes is achieved.

The invention provides a method and device for medical question answering, electronic equipment and a medium, and relates to the field of artificial intelligence, in particular to the field of knowledge maps and large language models. The method can comprise the steps of obtaining an intention label and an intention confidence coefficient through a first large language model based on a query text from a user; in response to determining that the intention label is not matched with the intention in the intention list or the intention confidence does not meet a confidence threshold, executing a first query process to obtain a query result; and obtaining a reply text for the query text based on the query result, the first query process comprising: executing vector retrieval based on the query text to obtain a first sub-query result; generating a graph query statement by using a second large language model based on the query text; and obtaining a query result at least based on the first sub-query result.

Systems and methods are directed to incorporating large language model (LLM) prompts into graph queries using graph query language and executing these graph queries. The system receives a graph query that includes a LLM prompt in the graph query language. The LLM prompt comprises an input context and a query to be answered. Based on the graph query, the system traverses a knowledge graph to obtain context data associated with the input context. The context data may be constrained by access control policies of an enterprise providing the knowledge graph. A context table may be generated using the context data based on the input context indicated in the LLM prompt. The system then invokes an LLM to determine a result by applying the query of the LLM prompt to the context data obtained from the traversal of the knowledge graph. The result is then presented on a user interface of a client device.

The application provides a knowledge graph-based information query method and device, equipment and a storage medium. The method comprises: constructing a target entity vector of a to-be-queried text according to an entity word in the to-be-queried text and an entity type corresponding to the entity word; determining a target query mode corresponding to the target entity vector, and obtaining a graph feature item corresponding to the target query mode; wherein the target query mode is used to indicate a query process of the to-be-queried text in a knowledge graph; associating the entity word to the corresponding graph feature item by using the target query mode; generating a corresponding graph query statement according to the target query mode and the graph feature item associated with the entity word; and querying the knowledge graph according to the graph query statement to obtain a corresponding first query result. The method provides the accuracy of the query result.

Two modes of result set rebalancing are provided to cover the needs of distributed graph engines: unordered and ordered rebalancing. Unordered rebalancing allows moving any combination of chunks from one machine to another with the only goal being to reach a target balance. Ordered rebalancing maintains the order of a result set, dividing and rebuilding new chunks as they are moved between consecutive machines in the order of the result set to reach the target balance. The rebalancing solutions capitalize on the internal structure of result sets commonly present distributed graph processing systems.

The application discloses a kind of based on graph structure's power grid voltage stability margin online prediction method, comprising the following steps: constructing power grid attribute graph model in graph database, and establishing event-driven mechanism to realize the incremental update of topological change;Based on parameterized graph query template, dynamically generate graph database query statement, obtain the node feature matrix and adjacency matrix of prediction time, and convert to sparse tensor format;Constructing spatio-temporal graph convolution network prediction model;Through the incremental update of topological change driven by event-driven mechanism, to drive spatio-temporal graph convolution network prediction model;The prediction result and model intermediate layer node embedding vector are written back to graph database as attribute.This application realizes the millisecond level online prediction of power grid voltage stability margin, meets the real-time, accuracy and adaptability requirements of power system online safety analysis.

The embodiment of the application discloses a neural network compilation optimization method, comprising: dividing a computation graph of a neural network into a plurality of subgraphs; querying a topology feature library to determine whether an optimization strategy of a known subgraph that is consistent with the topology of at least one divided subgraph exists; if the optimization strategy exists, extracting the optimization strategy of the known subgraph that is consistent with the topology of the at least one divided subgraph from the topology feature library to optimize the at least one subgraph. The embodiment of the application stores the compilation optimization strategy of the known subgraph of the neural network in the feature library. When the compilation of the neural network is performed, the computation graph of the neural network is divided into a plurality of subgraphs, the optimization strategy corresponding to at least one divided subgraph is found from the topology feature library, and the optimization strategy is directly applied to the subgraph, so that repeated optimization calculation of the subgraph is not needed, and the compilation process of the neural network model is accelerated.