48 results about "Database graph" patented technology

The invention relates to the field of data processing, in particular to a scientific and technological achievement data batch arrangement method based on OCR and semantic processing. Comprising the following steps: scanning paper scientific and technological achievements to obtain an archive image; preprocessing and segmenting the archive image, and converting the archive image into a digital document; extracting corresponding metadata from the digital document; storing the digital document and the corresponding metadata into a database as a paper scientific and technological achievement in a structured data form; generating a knowledge graph according to the digital document and the corresponding metadata, and storing the knowledge graph in a graph database in a knowledge graph form; storing the original scanning copy of the paper scientific and technological achievement into the storage object; correlating the contents of the same paper scientific and technological achievements in the database, the graph database and the object storage. Through the multi-mode OCR recognition, dynamic semantic annotation, intelligent data analysis and knowledge fusion technology, full-process automation of scientific and technological achievement data from collection, processing to storage is achieved.

The invention discloses a structured query statement generation method and device, equipment and a storage medium, belongs to the field of data processing, and can accurately generate SQL statements according to natural statements. The method comprises the steps of obtaining a to-be-generated statement, and determining intention information in the to-be-generated statement; based on a preset sub-graph determination rule, determining a first sub-graph structure corresponding to the intention information in a preset database graph structure, the database graph structure being formed based on a plurality of first graph nodes and an association relationship between the first graph nodes, and the first graph nodes being determined based on structure information of a plurality of associated databases; a plurality of preset second graph structures are obtained, the second graph structures with the structural similarity with the first sub-graph structures larger than a first threshold value are determined as third graph structures, and different second graph structures are generated based on different types of preset SQL statements; and determining statement generation parameters in the first sub-graph structure based on the third graph structure, so as to generate a target SQL statement based on the statement generation parameters.

The invention relates to the technical field of computer vision and geographic information, and particularly discloses a cross-view geographic positioning acceleration method based on semantic description, which comprises the following steps of: performing instruction fine tuning on an input query image and a database image by adopting a visual language model to generate natural language description; coding the natural language description into a low-dimensional semantic vector by utilizing a word embedding model; constructing a semantic keyword association graph based on a graph embedding technology, and fusing a general semantic knowledge base and a geographic domain ontology to construct a surface feature special semantic tree; screening candidate subsets according to a preset ground feature priority and a saliency detection result of the query image; extracting global features and local key point descriptors of the images in the candidate subsets by adopting a lightweight model; constructing a visual similarity calculation model based on the state space model, and modeling a feature sequence dependency relationship; and fusing the semantic matching score and the visual similarity, outputting a final matching result by adopting a weighted sorting strategy, and cooperatively accelerating according to the matching result in combination with a lightweight model.

The invention discloses a Text2SQL (Structured Query Language) training and reasoning method based on structured database atlas enhancement, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: receiving a natural language query request input by a user; splicing a natural language query request input by a user and the map enhancement representation corresponding to the target database into an input sequence, and inputting the input sequence into the trained large language model to generate a group of candidate SQL query statements; performing semantic consistency verification and grammar legality verification on the candidate SQL query statements to obtain final SQL query statements passing verification; and submitting the final SQL query statement to the target database for execution to obtain an execution result.

The invention provides a full-link management method and device for business data, and the method comprises the steps: collecting first metadata covering the whole process of a target business, the first metadata comprising at least one type of metadata; storing the first metadata into a relational database; a matched target analysis logic is determined according to the type of the first metadata, the target analysis logic is called to analyze the first metadata, the blood relationship among the metadata is obtained, and the target analysis logic comprises at least one of SQL statement analysis logic, ETL script analysis logic, API interface analysis logic and exchange operation analysis logic; constructing a corresponding blood relationship map in a map database in a layering manner based on the blood relationship among the metadata, and storing the blood relationship map; and in response to the change of the structure of the second metadata, searching a blood relationship link related to the change in the relational database and the graph database so as to trace and obtain all nodes influenced by the change.

The application belongs to the technical field of computers and discloses a general metadata operation method and system based on a graph database, which comprises the following steps: S1, using a configuration file yml of SpringBoot to configure to create a connection pool SessionPool of a NebulaGraph Database graph database based on a NebulaPool custom implementation, containing definitions of maxCountSession, minCountSession, hostAndPort, userName and passWord parameters; S2, defining parameter models for accepting different interfaces, including a model for creating a graph space, a model for creating a point, a model for creating an edge, a model for creating an index and a general query model; S3, using an independently developed NebulaUtil tool to automatically arrange nGQL statements for the accepted parameter models according to the input models; S4, defining different Controller layers to provide an open and unified Api interface externally; S5, using an execution service of a GraphCommonService graph database to obtain an effective connection of the NebulaGraph Database graph database from the SessionPool; and S6, executing the nGQL statements automatically arranged by the NebulaUtil tool and analyzing and returning a result model, and uniformly returning the result.

The application discloses a kind of multi-modal information comprehensive retrieval street view image positioning method and system, by establishing multi-modal information database, using visual feature extraction model and scene text recognition model establish multi-modal information database;By fusion feature retrieval, global feature and local feature are fused and preliminary recall search is carried out;By geometric verification rearrangement, the geometric verification algorithm based on local feature is used to rearrange preliminary recall search result, and obtain refined retrieval result;By scene text retrieval, the scene text set overlap degree of query picture and database picture is calculated, and the final retrieval result is obtained based on this score ranking. The application considers the comprehensive retrieval scheme of multi-modal information, can greatly improve the image positioning accuracy in practical application, and to a certain extent, solves the complete positioning failure problem of single modal information in some scenes.

The application provides a multi-source spatial data topology consistency automatic processing method for quick update of a vector database, and belongs to the field of topology relation checking. The method comprises the following steps: pre-processing a fusion data layer graph spot, processing the topology consistency of the fusion data layer graph spot and a basic database graph spot, and post-processing the fusion data layer graph spot; setting a topology consistency processing threshold value of the fusion data layer graph spot and the basic database graph spot, and obtaining a processing result according to the processing. The application uses an R-tree spatial index method to search for geometric graph spots with common points, common edges or overlaps, so that the accuracy is not sacrificed while meeting the quick search. The application processes and aligns the boundaries of points, lines and surfaces of the geometric graph spots in all directions, and has high correction accuracy and high speed.

The invention discloses a cross-platform data fusion method in the field of cross-border trade, and the method specifically comprises the following steps: A1, constructing three types of data storage modes of a modular trusted data middle table, a support relational database, a graph database and a block chain, and relates to the technical field of data processing. According to the cross-platform data fusion method in the cross-border trade field, by constructing a modular data platform and integrating a relational database, a graph database and block chain storage, the problem of unified storage and management of multi-source heterogeneous data in cross-border trade is effectively solved. Based on a micro-service architecture and a unified data access layer, flexible deployment of an algorithm module and efficient access of multiple data sources are realized, and the automation level of data fusion processing and the system flexibility are remarkably improved. Through the introduction of the block chain credible mutual recognition system, the authenticity, traceability and non-tampering performance in the cross-border data sharing process are ensured, a credible foundation is laid for multi-party cooperation, and the credibility of the platform is greatly enhanced.

The invention discloses a semiconductor equipment part shipment report generation method and system based on a serial number, and relates to the technical field of intelligent manufacturing, image information, helium detection information, granularity information, size detection information and order information are collected in real time through a data acquisition module which runs through a whole production process, and the information is packaged into a reference data set after integrity verification; a unique serial number is generated by fusing the customer identifier, the material number and the completion timestamp with the UUID, the unique serial number is bound with the reference data set and stored in a shipment database as a key value record, and an image link points to an independent file server; according to a client identifier, a template library is intelligently matched, a corresponding field is dynamically extracted, an image and a detection result are automatically embedded, a multi-language visual shipment report is generated according to needs, a storage path is returned, single-piece-level data tracing, quality inspection closed loop and personalized report second-level output are achieved, and delivery transparency and client satisfaction are improved.

To provide an image retrieval system and method with high retrieval accuracy.SOLUTION: The database has a function of storing a plurality of pieces of database image data, and a database tag is associated with each of the plurality of pieces of database image data. The processing unit has a function of acquiring database image feature amount data representing a feature amount of database image data for each piece of database image data, a function of acquiring query image feature amount data representing a feature amount of query image data, a function of calculating a first degree of similarity that is a degree of similarity of the database image data to the query image data for each piece of database image data, and a function of acquiring a query tag that is a tag associated with the query image data using a part of the database tag.SELECTED DRAWING: Figure 11

The application discloses a kind of customer relationship audit analysis method and system based on graph database, and heterogeneous data is synchronized by distributed lock, customer, account is converted into graph node, and is converted into relationship edge such as fund transfer, legal person, mobile phone association, and dynamic construction customer relationship graph model;Adopt relational database+graph database hybrid storage, utilize KCore, shortest path, community discovery and other graph algorithms to complete depth audit analysis;With JSON / Schemaless dynamic structure storage result, without modifying database table structure, can extend audit dimension;With standardization interface and visual interaction realize with audit business platform depth integration.The application can significantly improve the efficiency of complex relationship query under large-scale customer data, guarantee data consistency, enhance system scalability, reduce audit operation threshold, and be suitable for bank customer relationship audit, anti-money laundering investigation, associated transaction identification, risk penetration verification scene.

Embodiments of the present application relate to systems and methods of inspecting reticles using machine learning. Near-field reticle images are generated via a deep learning process based on reticle database images generated from a design database, and far-field reticle images at an image plane of an inspection system are simulated via a physics-based process based on the near-field reticle images. The deep learning process includes training a deep learning model based on minimizing differences between the far-field reticle images and a plurality of corresponding training reticle images acquired by imaging training reticles fabricated from the design database. Test regions of test reticles fabricated from the design database are inspected for defects via a die-to-database process that includes comparing a plurality of reference images from reference far-field reticle images to a plurality of test images acquired by the inspection system from the test reticles. The reference far-field reticle images are simulated based on reference near-field reticle images generated by the trained deep learning model.

The invention discloses a personnel re-recognition system and method based on attitude guide generation and reasoning stage enhanced retrieval, and the method comprises the steps: carrying out the retrieval of a query image, selecting the first k results with the highest cosine similarity from a database image, and selecting m reference images based on the identity recognition accuracy; performing attitude extraction on the reference image; pixel features and attitude features are extracted and fused to obtain an attitude normalized generated image; identifying identity consistency of the generated image and the query image and attitude consistency of the generated image and the reference image; and in a reasoning stage, combining the query image with the generated image set, performing feature matching, and calculating weighted cosine similarity to obtain a retrieval-enhanced personnel re-identification task sorting result. According to the method, the target attitude is extracted by using the reference image in the reasoning stage, the generated image with the normalized attitude is guided to be obtained, and the query image and the generated image are combined for retrieval, so that the personnel re-recognition performance is improved.

The invention belongs to the field of fabric retrieval methods, and relates to a fabric retrieval method based on image masking and repairing characterization, which comprises the following steps: establishing a fabric image retrieval database; designing an image masking mode to pre-process the fabric image; constructing a fabric image masking and repairing model; training a fabric image masking and repairing model; carrying out image characterization by utilizing the fabric image masking and repairing model, and obtaining features of the to-be-retrieved image and the database image; and measuring the obtained features of the to-be-queried image and the features of the images in the database image by using a similarity measurement method, and outputting a retrieval result according to the similarity for guiding fabric design. According to the method, the overall structure and texture of the image can be automatically understood for representation, manual design of an image feature extractor is avoided, high retrieval precision and efficiency are achieved, the method can be widely applied to the fields of related weaving enterprises, e-commerce shopping and the like, and a user is helped to quickly query needed fabric products.

The invention relates to the field of fault detection, in particular to a radar system troubleshooting process generation method and system based on a large model. The method comprises the following steps: S1, picture extraction; s2, fault tree picture recognition and structured conversion; s3, troubleshooting guide picture recognition and structured conversion; s4, obtaining a mapping relation between the fault tree and the troubleshooting process; s5, constructing a fault knowledge database; and S6, performing fault retrieval and troubleshooting guidance. The system comprises a fault knowledge database, a picture extraction module, a fault tree picture extraction module, a troubleshooting guide picture extraction module, a mapping module and a fault retrieval and troubleshooting guide module. According to the method, the fault knowledge database of the radar system is constructed, so that the matched troubleshooting process can be quickly and accurately positioned; a natural language processing and semantic understanding technology is realized by means of a large model; and the next troubleshooting measure is automatically selected according to the detection result in the troubleshooting process, so that intelligent promotion and optimization of the troubleshooting process are realized.

The invention provides an agent-based medication question and answer management method, system and equipment, and the method comprises the steps: disassembling a demand according to demand basic information inputted by a user; based on a visual arrangement tool, creating a workflow which comprises an intention recognition node, a database interaction node and a large language model generation answer node; the method comprises the following steps of: standardizing a medicine specification and a user health file by utilizing a database tool, defining a workflow node data calling dynamic calling logic, preferentially calling database data, and triggering large model reasoning when the data is insufficient; large language model texts, voices and database pictures are utilized, and the intelligent agent API is connected with the interaction layer to output question and answer results. The answer is output in a question and answer mode, meanwhile, medicine consultation service, medicine reminding and medicine deadline management are provided for family users in combination with existing information of the database and large model reasoning, the situation that the medicine is still used after expiration is avoided, and the method has the advantages of being easy to operate, intelligent and convenient to use.

The invention provides a code generation method and device, equipment, a medium and a program product. Relates to the technical field of code generation. The method comprises the steps of performing code generation processing on an obtained page image based on a pre-constructed code generation system to obtain a page code output by the code generation system; the code generation system comprises an image segmentation model, an image retrieval model, a code generation model and a component code database; the image segmentation model is used for obtaining a plurality of component images contained in the page image and a hierarchical relationship among the component images; the image retrieval model is used for obtaining component code snippets of the component images based on the component code database; and the code generation model is used for generating a page code corresponding to the page image according to the component code snippets of the component images and the hierarchical relationship between the component images. According to the method, the technical problem of low development efficiency in an existing code generation scheme is solved.

This invention relates to the field of information retrieval, specifically to a database query method based on a graph structure. The method includes collecting all data tables in the database, multiple query statement-data table pairs, and establishing an enterprise knowledge base; modeling a database graph structure based on all data tables; enhancing the input natural language query using RAG to obtain an enhanced query statement; selecting initial nodes from the graph structure based on the enhanced query statement and completing graph initial node matching; generating a target node set based on each initial node; generating an SQL statement corresponding to the enhanced query statement based on the target node set to achieve SQL statement conversion; and executing the SQL statement to query the database and obtain the query results. Existing NL2SQL suffers from insufficient semantic understanding and poor interpretability. The database query method based on a graph structure provided by this invention has better semantic understanding and interpretability.

The present application provides a design assistance device, a design assistance system, a design assistance method, and a storage medium that can assist a design service. The design assistance device refers to a database in which a graph configuration is stored. The graph configuration includes a specification item indicating a specification of a product, a unit item indicating a unit included in the product, a first item associated with a system simulation model indicating a relationship between an input and an output in the unit, and a second item associated with a three-dimensional model indicating a three-dimensional shape of the unit. The design assistance device further sends a first notification to a first processing device associated with the first item when the three-dimensional model is updated. The design assistance device further sends a second notification to a second processing device associated with the second item when the system simulation model is updated.

This invention provides a software conversion generation system, data structure, program, and control method for the software conversion generation system that can accurately generate conversions of software systems that operate on a target platform. [Solution] The software conversion generation system 10 includes a scoring processing unit that scores by referring to a database which includes a graph database configured to store source code conversion generation rules between multiple programming languages ​​in a graph structure of nodes and edges and enable structural searching, and a vector database configured to store vector embedding representations of the source code conversion generation rules and enable semantic searching, and a conversion generation processing unit that performs conversion generation of a software system while referring to the scores scored by the scoring processing unit.

The application discloses an encrypted image search method based on a quantum homomorphism K-neighbor algorithm, which comprises the following steps: obtaining database images, extracting image feature vectors, encrypting the features, and sending the obtained encrypted database image feature vectors to a cloud server; the cloud server encodes the encrypted database image features into quantum states and constructs an index; a user extracts features of a to-be-queried image and encrypts the features, and sends an encrypted query request to the cloud server; the cloud server encodes the encrypted to-be-queried image features into quantum states, and calculates the similarity between the to-be-queried image and the database images by using an exchange test; based on a quantum phase estimation algorithm, the similarity is encoded onto a quantum state, and based on a Grover algorithm, K images with the highest similarity in the database images are queried and sent to the to-be-queried image user; the to-be-queried image user decrypts the K encrypted images to obtain image search results, and completes the encrypted image search. The method can ensure the security and availability of images in a cloud environment, maintain the retrieval precision, and improve the search efficiency.

The application relates to the technical field of robot autonomous navigation and visual recognition, and discloses a visual scene recognition method for spatial self-perception under self-attention, which is realized by adopting an S3VPR model composed of a ViTbackbone and a feature aggregation module Token Module and comprises the following steps: 1) for a given input image, extracting basic features by using the ViTbackbone to obtain a feature map, and then forming a new feature map; 2) performing a reshape operation on the new feature map to convert the two-dimensional feature map into a three-dimensional feature map; 3) using the feature aggregation module Token Module to first process the three-dimensional feature map along the spatial dimension to obtain a spatial interaction feature map, then processing the spatial interaction feature map along the channel dimension to obtain a channel interaction feature map, and further processing the channel interaction feature map to obtain a global descriptor; and 4) using a similarity algorithm to one-by-one compare the global descriptor of a query image with the global descriptors of all database images in a database to find all database images belonging to the same scene as the query image.

The invention relates to an image retrieval system and an image retrieval method. Provided is an image retrieval system with high retrieval accuracy. An image retrieval system includes a database and a processing unit. The database has a function of storing a plurality of database image data, each of the plurality of database image data being associated with a database tag. The processing unit has a function of acquiring database image feature amount data indicating a feature amount of the database image data for each database image data. In addition, the processing unit has a function of acquiring query image feature amount data indicating a feature amount of the query image data. Furthermore, the processing unit has a function of calculating a first degree of similarity of the database image data with respect to the degree of similarity of the query image data for each database image data. In addition, the processing unit has a function of acquiring a query tag of a tag associated with the query image data using a portion of the database tag.

This invention belongs to the field of artificial intelligence technology and discloses a digital acne identification and assessment method. It includes database establishment, image capture, RGB algorithm, acne assessment, and targeted beautification. This invention can dynamically (multi-angle transformation) identify acne, monitor changes in acne after a period of medication in real time, and recommend concealer shades based on changes in acne color in makeup applications.

The application discloses a deep variable-length hash retrieval method with adaptive bit selection, and relates to the technical field of image retrieval. The image is input into a trained retrieval model to generate a query image binary code, the Hamming distance between the query image binary code and the image binary code in an image database is calculated, and the database images are returned in order of distance from small to large as retrieval results. The training process of the retrieval model comprises the following steps: step one, each image in the constructed image training set is sequentially input into a deep hash network to output the binary code corresponding to each image, the deep hash network is trained by optimizing the metric, and a bit pool is generated; step two, the bit pool is input into a bit selection agent for bit selection, and the same optimization metric as that in step one is used as an environmental reward; and step three, steps one and two are alternately iterated until the retrieval model converges. The retrieval method realizes compact feature expression with variable length and improves retrieval precision.

The invention discloses a parameterized drawing system and method for a roadway cross-section diagram in the technical field of coal mine intelligence. The parameterized drawing system comprises a system management module used for calling and managing a roadway cross-section diagram template in a database; the parameter input module is used for inputting roadway section parameters; the database primitive module is used for providing a roadway section diagram template and a primitive module after roadway section parameters are input; the parameterization amount calculation module is used for redefining key parameters, constraint conditions and geometrical relationships of all components in the roadway cross-section diagram template and the primitive module by utilizing a parameterization amount calculation formula, and then inserting the key parameters, the constraint conditions and the geometrical relationships into a built-in diagram frame in the database according to a position relationship; the cross-section diagram output module is used for outputting a roadway cross-section diagram meeting the drawing standard; and the cross-section diagram modification module is used for modifying the outputted cross-section diagram of the roadway. The labor intensity of designers can be reduced, the working efficiency of the designers is improved, and the drawing standardization degree and the coal mine design intelligent level are improved.

The invention relates to the technical field of plant knowledge retrieval, in particular to a plant knowledge retrieval enhancement system and method based on data fusion. Comprising a plant text processing module, a user input module, an input preprocessing module, a model input processing module, a model output processing module, a parallel retrieval module, a data fusion module and an output result module. Constructing the relational database, the graph database and the vectorization knowledge base; receiving a natural language query input by a user, and generating a structured query statement and question classification information through a large language model; retrieving a relational database, a graph database and a vectorization knowledge base in parallel based on the structured query statement to obtain an intermediate retrieval result; and carrying out data fusion processing on the intermediate retrieval result, sorting according to the occurrence frequency of the record identifier, and retrieving from the original database and outputting a final result.

The application discloses a kind of roadway section drawing parameterization drawing system and method in the technical field of coal mine intellectualization, comprising: system management module: for calling and managing roadway section drawing template in database;Parameter input module: for inputting roadway section parameter;Database graph element module: for providing roadway section drawing template and graph element module after roadway section parameter input;Parameterized calculation module: for using parameterized calculation formula, the key parameters of each component in roadway section drawing template and graph element module, constraint condition and geometric relation are redefined, and then according to position relation inserts the picture frame built-in in database;Section drawing output module: for outputting roadway section drawing satisfying drawing standard;Section drawing modification module: for modifying the roadway section drawing that has been output.The application can reduce the labor intensity of designer, improve the work efficiency of designer, improve the standardization degree of drawing and the intelligent level of coal mine design.

The invention relates to the field of database management and natural language processing, and particularly discloses a database sub-mode division-based txt-to-sql generation method, which comprises the following steps of: S1, constructing a database graph; s2, the weighted undirected graph G is subjected to sub-mode division based on graph segmentation, a plurality of sub-graphs are obtained, and each sub-graph corresponds to a database sub-mode; s3, generating a sub-mode abstract; s4, a two-stage matching mechanism is adopted, and an optimal sub-mode most relevant to natural language query input by the user is selected from the sub-mode set; and S5, on the basis of the optimal sub-mode, the corresponding abstract and a user natural language query construction cue word, inputting the large model to generate an SQL query statement. According to the technical scheme provided by the invention, the static structure and the dynamic query behavior of the database are fused, the high-correlation sub-modes are automatically divided, the correlation sub-modes are accurately positioned through two-stage matching, the input complexity of a large model is greatly reduced, the accuracy and efficiency of SQL generation are improved, and the method is adaptive to a large-scale database scene.