Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1199results about How to "Improve query efficiency" patented technology

Method, system and equipment for generating SQL (Structured Query Language) statement based on large model

The invention relates to the field of natural language processing, and discloses an SQL statement generation method, system and device based on a large model. Respectively carrying out vectorization processing and document processing on the metadata and the metadata description text information from the database, and storing the metadata and the metadata description text information into a vector database and a full-text retrieval library; in response to the query instruction, respectively performing query matching on the vector database and the full-text retrieval library, screening matching results which are ranked in the front and are preset ranks according to the similarity from high to low, and determining an optimal SQL statement list and optimal metadata; on the basis of the current language of the query instruction, generating a cue word of the current language in combination with the optimal SQL statement list and the optimal metadata; the large model of the preset type is determined according to the language type of the cue word, the preset large model is called to conduct reasoning on the cue word, and the SQL statement is generated. Based on the large model and the generative AI technology, the accuracy of the generated SQL statement is improved, the use threshold of non-technical personnel is lowered, and the query efficiency of the SQL statement is also improved.
Owner:广域铭岛数字科技有限公司 +1

Power data security policy large model question-answering system and method based on relation pooling

The invention belongs to the technical field of electric power data security management and intelligent question answering, and particularly relates to an electric power data security policy large model question answering system and method based on relation pooling. The system comprises a power data security policy knowledge base, a language model, a question processing module, an answer generation module and a user output module. Data of the electric power data security policy knowledge base comes from an electric power data security policy file; the language model converts a natural language problem into a structured query for knowledge base retrieval; the question processing module retrieves policy terms related to the natural language question to serve as retrieval results; the answer generation module generates a final answer according to the natural language question and a retrieval result of the knowledge base; by introducing the intelligent question-answering system combining the large language model and the knowledge base, the problems of low efficiency, inaccurate interpretation, incapability of dynamically updating and the like in the existing power data security policy query and management are solved.
Owner:ECONOMIC TECH RES INST OF STATE GRID HENAN ELECTRIC POWER +1

Natural language SQL (Structured Query Language) conversion method based on data platform and large language model

The invention provides a natural language SQL (Structured Query Language) conversion method based on a data platform and a large language model, which relates to the technical field of data processing and comprises the following steps of: performing vectorization storage on metadata, blood relationship, indexes and historical query information, performing intention judgment and vector matching on a user query request, and determining a query condition based on a matching result. An association path is constructed according to data consanguinity, and an optimal SQL statement is generated by utilizing a historical query optimization table connection sequence and combining index matching. According to the method, intelligent conversion from the natural language to the efficient SQL can be realized, the query efficiency is improved, and the use threshold of a user is reduced.
Owner:ZHEJIANG SHUXIN NETWORK CO LTD

Unstructured database federated learning collaboration method and system based on swarm intelligence

The invention provides an unstructured database federated learning collaboration method and system based on swarm intelligence, and relates to the technical field of structured data, and the method comprises the steps: training a query pattern recognition sub-model, a path planning sub-model and a resource allocation sub-model through federated learning, and constructing a swarm intelligence collaboration network. After a user query request is analyzed by the query mode recognition sub-model, candidate query paths are generated and optimized by fusing an ant colony algorithm and a particle swarm algorithm, and a query execution scheme is generated. And the resource allocation sub-model performs resource scheduling accordingly. And generating a performance optimization target for updating local model parameters of each node, and fusing the updated parameters through a security aggregation algorithm to guide the next query optimization. According to the method, the query efficiency of the unstructured database is improved, and the resource consumption is reduced.
Owner:北京科杰科技有限公司

Method and system for constructing space-time dynamic graph of engineering construction project

The invention provides a time-space dynamic graph construction method and system for an engineering construction project, and relates to the field of railway tunnel engineering management.The method comprises the steps that construction data entities are extracted, and an entity set is generated; taking entities in the entity set as nodes to be added into the graph, and configuring attributes for each node; adding a relation edge for each node according to a logic structure between the construction data; adding a time label and a space label to each node so as to form a data graph; associating each entity in the data atlas with a time chain and a space chain to form a data atlas attached to the time-space chain; combining a node merging strategy and a graph neural network to optimize a graph structure; and dynamically modeling dimensional changes of entities and relationships in time by means of a time sequence diagram neural network. According to the method, the dynamic change graph of the relationship between the construction data entities is constructed, so that the spatial-temporal information and the entity relationship of each process are accurately expressed and efficiently associated, and the retrieval efficiency and the management level are favorably improved.
Owner:CHINA RAILWAY CONSTR BRIDGE ENG BUREAU GRP CO LTD +1

Method and system for managing visualization tables of databases of different types

The invention provides a different types of database visualization table management method and system, and relates to the technical field of computers.The method comprises the steps that a database general operation system comprising a general operation interface and a dialect abstract base class is constructed, and a query performance evaluation system is established based on performance data; and predicting an optimal database connection mode through deep reinforcement learning and generating a multi-stage execution plan. Meanwhile, an anomaly feature knowledge base based on a graph neural network is constructed, and anomaly prediction and preventive processing are carried out based on the anomaly feature knowledge base. A multi-stage execution plan is executed after a database operation request is subjected to grammar adaptation, and a distributed transaction processor dynamically adjusts a transaction isolation level and a concurrency control parameter. And finally, according to the terminal and the data volume, selecting a proper data display mode to carry out visual presentation.
Owner:北京科杰科技有限公司

Data analysis method and system and storage medium

ActiveCN119557424AImprove the effectiveness of analytical processingimprove organizationSemantic analysisBiological modelsTheoretical computer scienceData profiling
The invention discloses a data analysis method and system and a storage medium, and is applied to the field of natural language processing. The method comprises the steps of obtaining a natural language input by a user; constructing a semantic data model for converting the natural language into a semantic query statement; combining the semantic data model with a user-defined rule to construct a semantic parser; inputting the natural language into the semantic parser for parsing to obtain a semantic query statement; inputting the semantic query statement into a semantic corrector for correction to obtain a target semantic query statement; converting the target semantic query statement into a structured query statement through a semantic translator; and inputting the structured query statement into the database for query to obtain a query result.
Owner:CETC BIGDATA RES INST CO LTD

Intelligent bid evaluation expert extraction and management system

The invention discloses an intelligent bid evaluation expert extraction and management system, and relates to the technical field of expert extraction systems. Comprising a data cleaning and compression module, a database logic and table relation design module, an expert information collection standard and automation module, an information real-time updating and principal management module, an extraction algorithm design module, a safety and authority management module and a real-time monitoring and auditing function module. Through a self-adaptive sparse auto-encoder and a dynamic clustering technology in the data cleaning and compression module, abnormal values in a bid evaluation expert database can be detected and cleaned, data compression is performed by adopting a self-adaptive dictionary coding algorithm, and the storage efficiency and query performance of the database are improved; based on a multi-modal information fusion and reinforcement learning method, accurate collection, dynamic updating and intelligent management of expert information are realized. The randomness and fairness of the bid evaluation expert extraction process are ensured by using a mode of combining deep reinforcement learning and a quantum random number generator in an extraction algorithm design module.
Owner:FUJIAN YILI ELECTRIC POWER TECH CO LTD

Smart power grid monitoring data storage system

The invention belongs to the technical field of intelligent power grids, and particularly relates to an intelligent power grid monitoring data storage system which comprises a data acquisition module, a data preprocessing module, a hierarchical data storage module, an intelligent data retrieval and management module and a data analysis and visualization module. Power grid operation data are collected in real time through various sensors; the data preprocessing module is used for cleaning, denoising and formatting the collected data and identifying data abnormal values by adopting a dynamic threshold detection method; the hierarchical data storage module adopts a hierarchical storage strategy of hot data, temperature data and cold data, stores the data in different media respectively, and introduces a time sequence database; the intelligent data retrieval and management module retrieves the stored data by using a multi-condition complex query algorithm, and improves the query efficiency through an intelligent data indexing and retrieval mechanism; and the data analysis and visualization module generates a report and a visualization chart through an advanced data analysis algorithm.
Owner:WUXI XINFENG IOT INTELLIGENT TECH CO LTD

Data fusion method and system based on logistics distribution knowledge graph

The invention relates to the technical field of logistics distribution data fusion, in particular to a data fusion method and system based on a logistics distribution knowledge graph. The method comprises the following steps: extracting original data and carrying out independent representation learning and unified representation processing; extracting uniformly expressed context information and carrying out dynamic perception embedding to obtain semantic enhancement features; fusing time-space and dependency features and physical characteristic features based on semantic enhancement features, performing message passing and relation inference by using a graph neural network, and finally determining a multi-mode relation set; global entity clustering and local feature fine matching are carried out based on semantic enhancement features, hierarchical entity alignment is carried out in combination with the multi-mode relation set, and an aligned entity set is obtained; and constructing an entity filling graph according to the aligned entity set, supplementing multi-dimensional relation attributes, and finally generating a logistics distribution knowledge graph. According to the invention, through a logistics distribution data fusion technology, a more comprehensive and more intelligent logistics distribution knowledge graph is realized.
Owner:BEIJING WANLIAN YIDA TECHNOLOGY GROUP CO LTD

Abnormality detection method and system based on dynamic traceability graph

The invention discloses an anomaly detection method and system based on a dynamic traceability graph, and belongs to the field of network anomaly detection.The anomaly detection method comprises the steps that the traceability graph is constructed, and node features of all nodes and features of edges connected with the nodes are spliced to serve as state feature vectors of the corresponding nodes; continuously monitoring system traceability information and dynamically updating the traceability graph; when a new edge et is generated, executing the following steps: inputting the et, a state vector st-of a graph structure surrounding the et at a t-moment and a generation moment t of the et into the graph attention network to obtain an embedded vector z of the et, and updating a source node and a destination node of the et; inputting z into a decoder, and predicting the type of et to obtain a prediction vector P (et); the decoder comprises a long short-term memory network and a plurality of full connection layers which are connected in sequence; calculating a reconstruction error RE between the actual edge type vector of the P (et) and the actual edge type vector of the et; if Th is greater than Th, judging that abnormity exists, otherwise, judging that no abnormity exists. According to the invention, the detection precision and real-time performance of anomaly detection can be improved.
Owner:HUAZHONG UNIV OF SCI & TECH +1

Software query information management method and system

The invention discloses a software query information management method and system, and belongs to the technical field of software information security, and the method specifically comprises the following steps: after a query request of a user is received, creating a dynamic topology network architecture according to semantic features of query contents; creating a virtual query container corresponding to the dynamic topological network in the isolated memory space, wherein the virtual query container generates a dynamic encryption channel bound with the current topological structure; dynamically embedding user permission labels into topological network nodes through an attribute-based encryption algorithm, and establishing a mapping relation between permission characteristics and network paths; when distributed query is executed in the virtual query container, the topological node connection weight is dynamically adjusted according to the real-time network load; before a query result is fed back to a user, data elements are recombined based on a reverse entropy value of an original topology network architecture; and when an abnormal access feature is detected, triggering a topological network structure dynamic failure mechanism.
Owner:SHAANXI JIAZHIYI NETWORK TECH CO LTD

Knowledge service system construction method

The invention relates to the technical field of knowledge base construction, in particular to a knowledge service system construction method, which comprises a knowledge acquisition step for collecting knowledge data from knowledge sources of multiple fields; the preprocessing step is used for preprocessing the knowledge data; the classification step is used for classifying the obtained knowledge data; the similarity calculation step is used for calculating the similarity between different categories of knowledge bases; the first judgment step is used for judging whether the similarity is greater than a first threshold value or not; the association step is used for establishing association between the knowledge according to the similarity; the second judgment step is used for judging whether the similarity is greater than a second threshold value or not; the labeling step is used for constructing a new upper label; a label directory generation step for establishing a label directory; a query demand acquisition step for acquiring a knowledge retrieval demand of a user and generating a query request; the knowledge retrieval step is used for conducting knowledge recommendation according to the query request. The method has the effect of improving the searching efficiency.
Owner:STATE GRID SHANDONG ELECTRIC POWER CO MARKETING SERVICE CENT (MEASURING CENT) +1

Data acquisition method and device of industrial Internet of Things, and storage medium

The invention relates to the field of technical data acquisition, and particularly discloses a data acquisition method and device for an industrial Internet of Things and a storage medium, and the method comprises the following steps: S1, constructing a dynamic sensor network, and collecting the operation data of industrial equipment in real time through a multi-modal sensor; s2, dynamically adjusting a data acquisition frequency # imgabs2 # based on an environment noise coefficient # imgabs0 # and an equipment health index # imgabs1 #; s3, performing hierarchical compression and encryption on the acquired data, and allocating a compression rate # imgabs4 # and encryption strength # imgabs5 # according to data type importance # imgabs3 #; s4, executing load balancing through an edge computing node, and distributing a computing task to an optimal node; and S5, storing the processed data into a distributed database according to spatial-temporal correlation, and generating a multi-copy disaster recovery index. Through dynamic acquisition, intelligent processing, optimized storage and adaptive strategy adjustment, accurate and efficient data acquisition is realized, data security and processing performance are flexibly guaranteed, storage query efficiency and disaster tolerance capability are improved, and storage resources are utilized to the maximum extent.
Owner:CHENYANG CHENGSHUO ELECTRONIC TECHNOLOGY CO LTD

Data query method and device, electronic equipment, medium and program product

The embodiment of the invention discloses a data query method and device, electronic equipment, a medium and a program product. The method comprises the following steps: receiving a target data query request sent by a user side; the target data query request carries a target natural language query statement input by a user of the user side; performing intention recognition on the target natural language query statement to obtain a target intention recognition result; the target natural language query statement and the target intention recognition result are input into a target large model, a target database query statement is output, and the target large model is obtained through training on the basis of multiple known database query statements and natural language query statements of the intention recognition result; verifying whether the target database query statement meets a preset database query condition or not; and if yes, in response to the target data query request, executing the target database query statement to obtain a target data query result.
Owner:CHONGQING ANT CONSUMER FINANCE CO LTD

Data processing method and device, storage medium and electronic equipment

The invention discloses a data processing method and device, a storage medium and electronic equipment. The method comprises the steps that a dependency collection plug-in is created under a construction node in a project object model file of a target application, the project object model file is analyzed through the dependency collection plug-in, initial dependency data of the target application is determined, and the target application is set to be deployed on at least two platforms with different platform identifiers; monitoring different stages in the construction process of the target application, and determining change dependency data of the target application; processing the initial dependency data and the change dependency data into target dependency data, and uploading the target dependency data to a target database; and in response to the target query message, querying and displaying the target dependency data from the target database. The technical problem of low query efficiency depending on data is solved.
Owner:CHINA CONSTR BANK CORP

Block chain storage method and system based on social network

The invention provides a social network-based block chain storage method and system, and the method comprises the steps: constructing a network transaction graph according to node transaction data, and mining a social relation between nodes from the graph, which represents the probability of possible transaction in the future; according to the social relation, the nodes are divided into different communities, the nodes store related transactions of the nodes of the same community, and the burden of storing the whole block chain account book is avoided; according to the storage and query cost of a single node, modeling the total storage and query cost in the whole network into a multi-objective optimization model, and minimizing the storage cost and the query cost in the network; a multi-population ant colony algorithm is adopted for solving, and the storage position of the transaction is allocated by adjusting the storage saving rate and the query cost tolerance rate, so that the balance of the storage cost and the query cost in the network is achieved. The technical problems that the node storage burden is large, the storage and query efficiency is low, and the storage cost balance degree is not high are solved.
Owner:THE ACAD OF TIANJIN UNIV HEFEI

Database table field index establishment method and device, electronic equipment and storage medium

The embodiment of the invention provides a database table field index establishment method and device, electronic equipment and a storage medium, and belongs to the technical field of financial science and technology. The method comprises the steps of obtaining a target query statement and statement execution plan information; splitting the target query statement to obtain statement key data; determining the total row number of the candidate database table based on the historical index database; extracting index use data from the candidate database table based on the statement execution plan information; determining a new field index from the candidate column indexes based on the candidate distinction degree of the candidate column indexes; verifying the new field index based on the statement execution plan information, the historical index database, the new region division degree of the new field index and the candidate region division degree to obtain an index verification result; and if the index verification result is that the index establishment verification is passed, performing field index establishment based on the new field index. According to the embodiment of the invention, the database table field index more suitable for the current query request can be automatically established, so that the data query efficiency is improved.
Owner:PING AN BANK CO LTD

High-frequency vehicle track map matching method

The invention discloses a high-frequency vehicle track map matching method, which comprises the following steps of: (1) dividing a track T to be matched into a plurality of sub-tracks based on a reference line distance, and extracting key track points in the sub-tracks; (2) extracting a road where the key track point is located and a road type of the road, filtering the extracted road based on the road type, and storing filtered road data by adopting an R-Tree structure; and (3) matching an optimal matching path of the track T to be matched from the road data stored in the R-Tree structure through a hidden Markov probability matching model. From the perspective of reducing the scale of original data, trajectory and road network data are simplified. Then, space and direction analysis is carried out on the simplified trajectory, a micro-region splicing strategy is adopted to accelerate shortest path search, and a path deviation function is designed to improve the topology of a matching result; in addition, the extraction process of track motion key points is refined by fusing more road semantic information, so that a better matching result is obtained.
Owner:ANHUI NORMAL UNIV

Data desensitization method and device, equipment and medium

The invention discloses a data desensitization method and device, equipment and a medium, and relates to the technical field of data security, and the method comprises the following steps: constructing an associated syntax tree based on a target query statement; the associated syntax tree is used for recording a mapping association relationship between an original field in an original data table and a return field in a return table; and determining a target sensitive data type of the return field based on the associated syntax tree, and performing desensitization processing on the return field according to a pre-configured desensitization rule corresponding to the target sensitive data type to obtain a desensitization result. According to the method, the inevitable grammar diversity problem of a traditional abstract syntax tree can be solved, the grammar analysis difficulty is reduced, meanwhile, the query efficiency is improved, the leakage problem of sensitive information is effectively solved, and the safety and availability of user data are improved.
Owner:CETC CYBERSPACE SECURITY TECH CO LTD

Big data real-time processing system and method

The invention discloses a big data real-time processing system and method, and relates to the technical field of big data processing, and the big data real-time processing system comprises a data partitioning module, a data storage module, a data reading module and a data backup module; the data partitioning module is used for partitioning big data entering a block chain in real time by using a partitioning strategy, extracting keywords, and distinguishing the frequency of data blocks according to historical query records; the data storage module stores data blocks through a storage contract, encrypts identifiers of the data blocks and establishes a mapping relation; the data reading module screens data blocks based on the private key set when a user queries, and determines a sending sequence through keyword matching; the data backup module generates a backup after storage, performs different updating strategies for data blocks with different frequencies, and performs adaptive modification on original data by using a hash value; in combination with the block chain technology, multiple advantages of real-time processing, efficient storage, safe reading, flexible backup and the like are integrated, and a comprehensive and efficient solution is provided for big data processing.
Owner:XIAN JIAOTONG UNIV CITY COLLEGE

Cache consistency maintenance method and device and multi-core system

The invention provides a cache consistency maintenance method and device and a multi-core system.The method comprises the steps that a write-in pointer and an eviction pointer of a directory are obtained, and the directory comprises cache line sharing information; configuring an emergency threshold and a conventional threshold, wherein the emergency threshold is smaller than the conventional threshold; if the sum of the write-in pointer and the emergency threshold value is greater than the eviction pointer, setting a high priority, and preferentially performing directory eviction; if the sum of the write-in pointer and the emergency threshold value is less than or equal to the eviction pointer and the sum of the write-in pointer and the conventional threshold value is greater than the eviction pointer, setting a low priority, and evicting the directory; wherein the directory comprises the shared information of the cache lines, and the directory eviction means that the shared information of the cache lines which are not used for the longest time in the directory is evicted; and repeating the steps until the sum of the write-in pointer and the conventional threshold value is smaller than the eviction pointer. According to the method, available space in the catalog is guaranteed to the maximum extent to store new data, the method is suitable for a small system, catalog coverage can be guaranteed, query efficiency is improved, and query power consumption is reduced.
Owner:EHIWAY MICROELECTRONIC SCI & TECH (SUZHOU) CO LTD

Database query plan optimization method and system

The invention discloses a database query plan optimization method and system, and belongs to the technical field of databases and artificial intelligence. AI model training: training the model by using the preprocessed historical query data according to a specific model architecture, a training mode and resource and time arrangement, and dynamically adjusting the model according to the change of the database; query analysis: evaluating the complexity of the query and the possibly involved data volume, and allocating a complexity level and a data access volume range for the query; query plan generation: generating and evaluating a plurality of candidate query plans based on prediction and query analysis results of the AI model, and selecting an optimal query plan as a final execution scheme; and performing query execution and monitoring. According to the method, the query execution time can be greatly shortened, and the database response speed is increased; system resources are utilized more effectively; dynamic changes of the database can be adapted, and the query plan is automatically updated according to structure and data distribution adjustment.
Owner:上海沄熹科技有限公司

Data processing method and device and electronic equipment

The invention provides a data processing method and apparatus, and an electronic device. The method comprises the steps of obtaining a linked list array of a specified size and a to-be-updated P2L reverse mapping table; determining the number of an L2P forward mapping table to which each logic offset address belongs; for each L2P forward mapping table, calculating relative offset between each logic offset address belonging to the table and a specified logic offset address, and calculating a remainder value obtained by dividing the number by a specified size; adding each relative offset corresponding to the L2P forward mapping table to a linked list corresponding to the remainder value; and updating the physical offset address corresponding to the logic offset address indicated by each relative offset in each linked list. According to the mode, the linked list array with the specified size is used, each relative offset corresponding to the L2P forward mapping table is uniformly recorded in each linked list by adopting the mode that the specified size is remainder by adopting the serial number of the L2P forward mapping table to which the logic offset address belongs, so that the query efficiency can be improved, and the consumption of a memory is reduced.
Owner:SHENZHEN CITY TECHWIN SEMICONDUCTOR COMPANY LIMITED

Intelligent query system and method based on semantic analysis

The invention relates to the technical field of information retrieval, in particular to an intelligent query system and method based on semantic analysis, and the system comprises an entity relation mapping module which collects user query data, carries out part-of-speech tagging and syntactic analysis operation on user query, constructs connection mapping according to syntactic relations among key elements, and sends the connection mapping to an entity query module; and calculating the correlation degree between each pair of keywords in the mapping, quantifying the attribute interaction strength, and generating a keyword relation mapping table. According to the method and the device, the precision and the efficiency of information retrieval are improved by deeply analyzing the query data of the user and combining the technical innovation of natural language processing. When part-of-speech tagging and syntactic analysis are carried out on a user query statement, key elements are accurately identified, connection mapping is constructed, and accurate capture of core information is ensured. And the information retrieval precision is enhanced by quantifying the association degree between the keywords and the attribute interaction strength. And a coherence score is calculated, so that the system can screen out the most relevant information.
Owner:SHENZHEN HESHENG NETWORK TECHNOLOGY CO LTD

Intestinal microorganism intelligent question-answering system based on knowledge graph and large model

The invention provides an intelligent question-answering system for enteric microorganisms based on a knowledge graph and a large model, and intelligent question-answering in the field of enteric microorganisms is realized based on a Graph RAG technology by calling an available LLM through a constructed Keying enteric microorganism knowledge base. In the intelligent question-answering system for intestinal microorganisms, the knowledge richness of question-answering is remarkably improved. By combining the knowledge graph and the large language model (LLM), the system not only can provide direct knowledge points, but also can supplement context and background information and multi-level scientific interpretation, so that the answer content is richer and more comprehensive.
Owner:SHANGHAI LISHAN BIOPHARMACEUTICAL CO LTD

Medical information data query method and system based on artificial intelligence

The invention provides a medical information data query method and system based on artificial intelligence, and relates to the field of data processing.The system comprises a data acquisition module used for acquiring medical data; the data processing module is used for preprocessing the medical data; the data encryption module is used for encrypting the preprocessed medical data; the data storage module is used for storing the encrypted medical data; the data query module is used for receiving a data query request of the patient end or the medical care end, performing permission verification on the patient end or the medical care end based on the data query request, determining target medical data corresponding to the data query request through artificial intelligence after the permission verification, and feeding back the target medical data to the patient end or the medical care end; the method has the advantage of improving the intelligence of medical data query.
Owner:CHENGDU YANCHONGWEI TECHNOLOGY CO LTD

A graph database load balancing method and device based on request type

The present application discloses a graph database load balancing method and device based on request type, which relates to the field of graph database query technology, and solves the problem in the prior art that several complex queries with long time consumption and heavy load may all fall on the same query service, causing the query service to be under great pressure and slow response, because only focusing on the resource utilization of the server and ignoring the characteristics of the query request itself. The method includes: constructing a mapping table, and according to the complexity of the query request, independently polling and routing the requests for complex queries according to the type, and independently polling and routing the requests for non-complex queries. Since the complex queries are routed to different query services, the effective dispersion of complex query requests of the same type is achieved, and the pressure on each query service to process data is balanced and small, thereby effectively improving the overall query efficiency and reducing the query time.
Owner:杭州悦数科技有限公司

Character string data read optimization method based on B + tree and learning index

The invention discloses a character string data read optimization method based on a B + tree and a learning index. A learning index generated based on a machine learning (ML) model focuses on integer data of a fixed size, but is lack of consideration for character strings of variable lengths and is poor in performance in character string data. In order to solve the problem, the invention provides a character string slicing method which can convert a character string with a variable length into an integer with a fixed size for prediction and extract a common prefix from a character string key to reduce a model fitting error. According to the method, the characteristics of character string data are fully considered, complex multi-dimensional linear regression is simplified into one-dimensional linear regression, and the model calculation overhead is reduced. Besides, the invention provides a self-adaptive strategy to select a proper index to manage the calculation cost, the method for dynamically selecting the index nodes can utilize the advantages of the two index types to the maximum extent, and the calculation overhead is effectively reduced while the index efficiency is ensured.
Owner:HOHAI UNIV

Urban rail transit emergency field question and answer method and system based on optimized RAG

The invention discloses an optimized RAG-based urban rail transit emergency field question and answer method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: firstly rewriting a user question into a new question conforming to an urban rail transit style, and then analyzing different types of documents in a knowledge base; then, the document is segmented, vector embedding is carried out, and meanwhile, a new problem is converted into a vector; then, by calculating the similarity between a problem vector and a document block vector, the most relevant document block is selected to form a recall set; then, a cross encoder is used for reordering the recalled documents, and the most relevant documents are selected to form a rearranged document set; and finally, inputting the new question and the rearranged document set into the fine-tuned large language model to generate a final answer. According to the method, through a large language model of question rewriting, accurate document segmentation and vectorization, multi-level retrieval and rearrangement and field fine adjustment, the accuracy and correlation of question answering in the urban rail transit emergency field are remarkably improved, and more professional and reliable intelligent question answering service is achieved.
Owner:TONGJI UNIV