609 results about "Data graph" patented technology

The invention discloses a tunnel lining crack identification method and system based on panoramic space image splicing, and relates to the technical field of tunnel visual identification. The method comprises the following steps: acquiring a tunnel lining image array, and performing local splicing on tunnel lining images by using a splicing model based on cylindrical surface projection to obtain a local spliced image; fusing and splicing the local spliced images by using the global image space model to obtain a panoramic spliced data graph; and abnormal region detection is carried out on the panoramic splicing data graph according to the spatial local difference, and a tunnel lining crack identification result is obtained. According to the method, the lining panoramic space model based on image two-stage fusion is used for splicing, so that the visual coherence and naturalness of a global spliced image are improved.

The invention provides a retrieval enhancement generation method and system for multi-modal semantic alignment in the technical field of computer vision and natural language processing. The method comprises the steps that S1, a large amount of text data, image data and 3D model data are acquired to construct a multi-modal vector knowledge base; s2, acquiring an input query image and a natural language question, and performing joint semantic coding on the query image and the natural language question to obtain a multi-modal query feature vector; s3, evaluating complexity, dynamically adjusting retrieval parameters based on the complexity, and retrieving Top-K candidate knowledge from the multi-modal vector knowledge base through an approximate nearest neighbor search method based on the retrieval parameters and the multi-modal query feature vectors; and S4, in combination with multi-dimensional similarity and token-level interaction alignment, screening each candidate knowledge, and outputting a retrieval result. The method has the advantages that the reasoning precision, the answer credibility and the response efficiency in a complex question and answer scene are greatly improved.

The invention provides an image data and pattern spot management system and method and electronic equipment, and relates to the technical field of geographic information data processing, and the image data and pattern spot management system comprises an image data indexing module which is used for carrying out three-dimensional indexing on a remote sensing image to obtain a space-time-data source association chain of the remote sensing image, the remote sensing image contains pattern spot data with an identifier; the pattern spot complete cycle construction module is used for performing multi-temporal analysis on the pattern spot data to obtain an analysis result, and constructing a pattern spot change life cycle map of the pattern spot data in combination with the association chain; and the tracing module is used for positioning the target pattern spot when the target pattern spot needs to be traced to obtain a change node of the target pattern spot and a space-time-data source index corresponding to the change node, and searching in the association chain according to the change node and the space-time-data source index to obtain a traceable data chain. According to the invention, the storage and management of the geographic image data and the pattern spot data are more systematized and refined.

The invention discloses a graphic rendering system and method based on OpenGL SC and a related product. The system comprises a rendering interface module used for providing a high-order graphic rendering function interface for an application program to receive graphic modeling data; the data conversion module is used for converting the graphic modeling data into intermediate drawing data conforming to the OpenGL SC standard; the graphic processing module is used for executing graphic calculation and rendering logic based on the intermediate drawing data and generating a rendering instruction; and the graph drawing module is used for calling the underlying OpenGL SC function library to execute the rendering instruction so as to complete graph rendering. According to the graphic rendering system, the underlying graphic pipeline is packaged inside, the development threshold and complexity are reduced through the high-order graphic interface, and the development efficiency and reliability are improved. All the modules are standardized and coordinated to realize complete process packaging from data to rendering, so that optimization and maintenance are integrated inside, and the maintainability, expandability and stability of the system are enhanced.

The invention relates to a manufacturing process quality tracing and root cause analysis system based on a data graph, and belongs to the technical field of manufacturing process quality control. The system performs cleaning, duplicate removal and standardization processing on multi-source heterogeneous data in the whole manufacturing process through a data processing module to generate structured data; the data graph construction module fuses the manufacturing domain knowledge ontology, constructs a manufacturing process digital twin semantic model and a multi-dimensional manufacturing data graph, introduces a dynamic association weight updating mechanism and mines node potential implicit association; the quality tracing module positions map nodes based on query semantic vectors, and reconstructs an entity state change track by using a digital twin semantic model to generate a tracing link; and the root cause analysis module screens candidate abnormal factors, locates a root cause in combination with dynamic weight and multi-scene simulation verification, and generates a quality optimization scheme. According to the invention, full-link accurate tracing and root cause efficient positioning of the manufacturing process quality are realized, and the intelligence and refinement level of manufacturing quality management and control is improved.

Systems and techniques for environment mapping are described. In some examples, a system receives image data and depth data captured using at least one sensor. The image data and the depth data both include respective representations of an environment. The system processes the image data using semantic segmentation to identify segments of the environment that represent different types of objects in the environment in the image data. The system combines the depth data with the semantic segmentation to generate a voxel-based three-dimensional map of the environment.

The invention relates to the technical field of intelligent tourism management, and discloses a tourist behavior dynamic modeling method based on space-time big data, which comprises the steps of collecting and preprocessing multi-source positioning data, inputting the multi-source positioning data into a multi-source positioning fusion engine, and combining statistical optimization and deep learning model fusion to obtain a high-precision positioning model. Track reconstruction and time sequence aggregation are carried out on continuous position points of tourists based on a high-precision positioning model, a structured activity data graph is generated, activity data of the tourists at all positions are obtained, activity preference characteristics are extracted through an association rule mining and clustering algorithm, and a Markov chain and a spatio-temporal evolution model are combined to predict a tourist flow trend. And forming a flow prediction result, and generating a visual dynamic decision support by using the prediction result. According to the invention, visual and dynamic decision support is provided, the crowd congestion is relieved, and the operation safety of the scenic area is guaranteed.

The invention discloses a synchronous positioning and mapping method and system based on multi-sensor fusion, a storage medium and electronic equipment. The method comprises the following steps: acquiring IMU data, an image and point cloud data measured by a laser radar; performing pre-integration on the IMU data to obtain real-time pose estimation, and performing laser probability updating and visual probability updating based on the real-time pose estimation to obtain an updated local map; a laser point cloud matching residual error, a visual reprojection residual error, an IMU pre-integration residual error and a marginalization residual error are constructed, a residual error equation is constructed based on the laser point cloud matching residual error, the visual reprojection residual error, the IMU pre-integration residual error and the marginalization residual error, a sliding window is adopted for nonlinear optimization, and robot pose estimation is obtained; and visual loopback detection, laser loopback detection and pose global optimization are carried out. According to the method, the calculation rate, the positioning precision and the reliability can be improved in a complex or feature degradation scene.

The invention relates to the technical field of industrial intelligent control, and discloses a multi-model collaborative optimization industrial MES intelligent control system. The system comprises a data analysis module, a knowledge enhancement module, a collaborative decision engine module, a decision fusion module and a control execution module. And the data analysis module executes tree structure-based data link analysis on the MES multi-source heterogeneous data, and constructs a production data tree structure with a multi-layer father-son relationship. And a knowledge enhancement module injects a domain knowledge template into each node of the structure to form a knowledge-enhanced production data graph structure. And the collaborative decision engine distributes the graph structure to a plurality of heterogeneous artificial intelligence models for parallel analysis through the unified service gateway. And the decision fusion module performs fusion processing based on confidence weighting on the output of each model to generate a comprehensive control decision instruction, and finally the control execution module drives the MES to complete production adjustment, equipment optimization and material scheduling. According to the system, the accuracy, the real-time performance and the interpretability of industrial intelligent decision making are improved.

The disclosure provides a graph neural network training method, a training system and an abnormal account identification method. The graph neural network training method comprises: obtaining initial graph structure data corresponding to a terminal device; the initial graph structure data obtained by a plurality of distributed training terminals respectively is derived from the same sample graph structure data; the following graph structure data processing stage and graph neural network training stage are executed cyclically until a target neural network meeting the training requirement is obtained: determining a processing time of the current execution graph structure data processing stage according to historical execution data of the historical execution graph structure data processing stage and the historical execution graph neural network training stage; performing graph structure data processing on the initial graph structure data in the graph structure data processing stage according to the processing time to generate target graph structure data; the graph structure data processing comprises data sampling processing and feature extraction processing; and training the target neural network based on the target graph structure data in the graph neural network training stage.

A dialogue system, comprising:an input, configured to receive input data from a user, wherein the input data comprises one or more of text data, speech data, image data and motion data; an output, configured to output data to the user; and one or more processors, configured to:obtain information identifying a skill and obtain information identifying a proficiency level of the user for the identified skill from stored proficiency level information; and execute at least one iteration of a coaching session, each iteration comprising performing one or more dialogue interactions, wherein each dialogue interaction comprises:receiving first input data from the user via the input;generating a first language model prompt and providing the first language model prompt to a language model, said first language model prompt comprising the first input data, the information identifying a skill, the information identifying a proficiency level of the user for the identified skill and a request to generate coaching information based on the first input data, the information identifying a skill and the information identifying a proficiency level; and generating first output data based on a first language model response to the first language model prompt and outputting, via the output, the first output data to the user;wherein the at least one iteration of the coaching session further comprises, after the one or more dialogue interactions:generating a second language model prompt and providing the second language model prompt to the language model, said second language model prompt comprising the information identifying a skill, the information identifying a proficiency level of the user for the identified skill, the first input data and the first output data, and a request to generate at least one proficiency update assessment based on the first input data, the first output data, the identified skill and the information identifying a proficiency level; generating second output data based on a second language model response to the second language model prompt and outputting, via the output, the second output data to the user; receiving second input data from the user via the input; determining a revised proficiency level of the user for the identified skill based on the second input data; andupdating the stored proficiency level information based on the revised proficiency level.

The invention relates to an electric power energy labeling method and system, and the method comprises the steps: carrying out the preprocessing of multi-mode original data in an electric power system, obtaining the cleaned preprocessing data, and enabling the preprocessing data to comprise text data, image data, time sequence signal data and audio data; the preprocessed data is dynamically bound based on a space-time-event three-dimensional rule, a structured multi-modal data card is generated, and the multi-modal data card takes a device ID-timestamp-event type as a unique identifier and comprises a text abstract, an image thumbnail, a time sequence curve fragment and an audio waveform; based on the multi-modal data card, intelligent labeling is carried out in a man-machine cooperation mode, and an initial label set is obtained; the initial label set is dynamically optimized, label errors are corrected, a high-quality labeling result is obtained, and the high-quality labeling result is stored in a structured mode and output to a downstream application system through an API interface.

The invention discloses a building material mechanical testing system based on multi-algorithm fusion, and belongs to the technical field of building material testing, and the system comprises an initial damage quantification module which is used for obtaining detection information of a tested material test piece before mechanical loading and generating a quantitative evaluation result; the loading and information acquisition module is used for applying a mechanical load to the tested material test piece with the generated quantitative evaluation result and acquiring a mechanical response signal and a microscopic state signal of the tested material test piece; the damage analysis module is used for calling a preset second data processing algorithm and analyzing and generating a dominant damage path; and the diagnosis and prediction module is used for integrating the associated data atlas and the dominant damage path information, generating a material performance diagnosis report and constructing a prediction model through a preset third data processing algorithm. According to the method, the initial damage of the tested material test piece is quantified, so that systematic deviation of a test result caused by neglecting the initial damage is corrected.

This invention provides a data integration and governance system and method for multimodal large models, relating to the field of data processing technology. The method includes: acquiring a data input set of a multimodal large model and preprocessing it to form a preliminary multimodal data set; performing timestamp mapping processing to align the collection timestamps of text data, image data, and speech data to a unified time index table; performing semantic consistency detection processing to identify semantic misalignments across modalities by comparing symptom descriptions in text data, structured annotations in image data, and spoken content in speech data, forming a consistent multimodal data set; performing dynamic label alignment processing to generate correction labels for detected misalignments and update the correction labels to the corresponding modal annotation content; and inputting the data into the large model training pipeline to perform unified governance processing of cross-modal features, forming a training data set. This invention improves the accuracy of data integration and governance.

The invention discloses a data layer processing method and system for spatial planning land data arrangement, and relates to the technical field of land data, and the method comprises the following steps: obtaining and collecting a plurality of predefined spatial planning constraint layers; the spatial planning constraint layer comprises a stable cultivated land, a permanent basic farmland, an ecological protection red line and a town development boundary; processing each spatial planning constraint layer to generate a site selection base map database of the temporary land; configuring a land use avoidance rule for each constraint layer of the site selection base map database; the avoidance rule comprises a prohibitive rule and a conditional rule, the prohibitive rule is configured for the layers of the permanent basic farmland and the ecological protection red line, and the conditional rule is configured for the layers of the stable cultivated land and the urban development boundary; responding to a temporary land site selection request of the user; the method has the effect of improving the accuracy and compliance of site selection decision.

A security alert meta-analysis (SAMA) system is disclosed capable of identifying causally related evidence of a cyberattack in a computing environment. In embodiments, the system builds a security data graph from security alerts generated by other security monitoring services. The security data graph links related entities (e.g. users and resources) in the computing environment and the entities to their associated security alerts. Edges in the graph are filtered based on edge weights to identify sub-graphs that represent clusters of causally related evidence probative of attacks. The evidence clusters are presented to analysts to be investigated further. In embodiments, the meta-analysis process is implemented as periodic jobs executed on a cluster of worker nodes. Advantageously, the disclosed system is able to filter through large volumes of alerts to reduce false positives, and group related alerts, possibly from different monitoring services, so that they can be investigated together.

The invention relates to an entry and exit certificate verification method based on dynamic weight and multi-modal fusion, and belongs to the technical field of entry and exit certificate information processing and verification. The method comprises the following steps: collecting multi-source heterogeneous data of a certificate in three modes of visual reading, machine reading and chip reading; constructing a verification data graph taking the unique identification of the certificate as a core, and carrying out data association and alignment; based on a dynamic weight distribution model, performing weighted voting fusion on the homologous key fields, and performing semantic fusion on the heterologous complementary fields; and constructing a traceable verification decision factor matrix, judging a verification conclusion according to the content of the matrix, positioning a source when the verification conclusion is abnormal, and generating a structured verification record containing a complete decision path and a disposal scheme. Through the dynamic weight fusion and the decision factor matrix, the problem of splitting of the existing verification mode is effectively solved, and the accuracy and reliability of the verification result and the process traceability are remarkably improved.

The invention provides a method for generating a system architecture diagram by automatically optimizing a cue word-driven reasoning large model. The method comprises the following steps of: preparing a multi-mode and reasoning large model and a sample data picture; generating content description and an initial layout requirement text; inputting the combined cue words into a large reasoning model, generating an HTML5 code, and converting the HTML5 code into a target picture; comparing the similarity between the target picture and the sample layout by the multi-modal model, and outputting a difference if the similarity does not reach a threshold value; and optimizing the layout requirement text based on the difference, and iterating until the similarity reaches the standard. Through cross-modal model collaboration, cue word closed-loop optimization, multi-role expert simulation and other technical innovations, the core pain points of strong manual dependence, insufficient flexibility and limited accuracy in traditional system architecture diagram generation are effectively solved, the technical spanning from passive auxiliary drawing to active intelligent generation is realized, and the system architecture diagram generation efficiency is improved. And the method has remarkable advantages in the aspects of automation degree, adaptability and generation quality.

The invention discloses a multi-modal water level monitoring and well lid alarming method based on AI, and the method comprises the steps: arranging a water immersion and triggering alarm terminal of an integrated electrode sensor and a Hall sensor in an open bin of a well lid base, integrating terminal data, image data and environment data, and carrying out the standardization processing, thereby generating a multi-modal fusion feature. And by taking the characteristics as core input, constructing an AI model, and outputting an accumulated water abnormal probability and a well lid jacking probability. In combination with the pipe network topology, historical data and a dynamic threshold value of a digital twin system, the road surface ponding grade and the well lid abnormity reason are accurately judged, and the alarm effectiveness is verified through multi-source credibility fusion. Meanwhile, an alarm result and disposal feedback are synchronized to the digital twin system, and a training data set is updated to iteratively optimize model parameters. According to the method, the hysteresis quality and the false alarm rate of traditional monitoring are effectively reduced, the operation and maintenance efficiency and the emergency response capability of a municipal pipe network are remarkably improved, and reliable technical support is provided for urban inland inundation prevention and control and road safety guarantee.

The invention relates to the technical field of electric power storage, and particularly discloses an electric power storage resource global collaborative management method and system, and the method comprises the steps: constructing an electric power professional warehouse data graph with an Internet of Things physical ID as a core node, the Internet of Things physical ID being a unique physical identifier of an electric power storage resource; associating material data of a safety supervision warehouse, a regulation and control warehouse and a logistics warehouse, and integrating key data entities of a safety tool verification system, a scheduling equipment management system and a work order management system; a unified data format and a data mapping rule are defined, and standardized interaction of cross-system heterogeneous data is achieved. According to the method, standardized real-time synchronization of cross-system data is realized by constructing a power professional warehouse data graph and relying on an internet of things entity ID active synchronization engine; by using a multi-dimensional rule engine, based on a professional warehouse type-material attribute-business scene three-dimensional rule base, accurate management and control are provided for warehouse-in, warehouse-in, warehouse-out and exception handling of materials, and the asset utilization efficiency is effectively improved.

The invention provides a forest fire risk area division and prevention and control method, electronic equipment and a storage medium, and the method comprises the steps: obtaining environment data of each area of a target forest area, and carrying out the timestamp marking of the environment data, and forming an environment data set; based on the environment data set, identifying a region in which the environment data is remarkably changed, and creating risk nodes according to region attributes; according to the method, multi-source data such as meteorology, vegetation, landform and human activities are integrated, environmental data are preprocessed through a sliding window algorithm, data mutation is captured, a dynamic risk data graph is constructed in combination with space-time weight, and meanwhile, real-time environmental parameters are introduced as dynamic correction factors, so that the dynamic risk data graph is obtained. The current situation that a traditional static assessment mode cannot respond to environmental changes in time is changed, the risk assessment precision and the high-risk area identification accuracy are improved, and accurate dynamic assessment of forest fire risks is achieved.

The invention provides a multi-modal fusion analysis-based bid and string bid duplicate checking detection method and system, relates to the field of data processing, and solves the technical problems that in the prior art, the detection dimension of bid and string bid behaviors is single, the analysis is shallow, and all technical means cannot effectively cooperate with one another. The method comprises the following steps: acquiring bidding document electronic documents of a plurality of bidding parties, and respectively extracting text data, image data and quotation list data; processing the text data, the image data and the quotation list data, generating a corresponding text feature vector, an image comprehensive feature vector and a quotation feature vector, and obtaining a multi-modal feature vector; constructing an incidence relation graph based on the multi-modal feature vector; inputting the association relationship graph into a pre-trained graph neural network model, learning an association mode between nodes through the graph neural network model, and identifying a high-risk bidder group; the high risk represents that there are predefined similar or cooperative cheating behaviors.

The invention relates to a question and answer processing method for a data chart, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to an optimization request for a first answer result, displaying an optimization interface; the first answer result is generated based on the first natural language question; the optimization interface comprises a first data screening condition of the data chart obtained by analyzing a first natural language question; responding to an editing operation aiming at the first data screening condition in the optimization interface; editing the first data screening condition according to the editing operation to obtain a second data screening condition; according to a second data screening condition, constructing and displaying a second natural language question; and in response to a confirmation operation for the second natural language question, displaying a second answer result corresponding to the second natural language question. By adopting the method, the question and answer processing efficiency and accuracy can be improved.

The invention relates to the technical field of industrial data mining, in particular to an enterprise operation index prediction system based on data mining, and the system comprises a heterogeneous data graph construction module which is used for recognizing equipment, materials, personnel and orders as entity nodes according to equipment maintenance records and operator handover logs, defining interactive operation as a relation, and constructing a database; and connecting all entity nodes, and establishing an enterprise operation space-time dependence graph. According to the method, unstructured data such as equipment maintenance records and operator handover logs are analyzed, production elements such as equipment, materials, personnel and orders are constructed into entity nodes, relationships are defined through interactive operation, time and space attributes are given to the relationships, and therefore the space-time dependency graph reflecting the enterprise operation process is established; complicated time sequence and logic association among elements in production activities are restored, and the limitation that only flattened table data can be processed through traditional data analysis is overcome.

The invention discloses a power grid supply chain supplier risk intelligent assessment system, which realizes full-dimension assessment of supplier risks through dynamic index construction, multi-model collaborative analysis and adaptive weight adjustment technologies. The system integrates structured data, a graph network relationship and unstructured text information, and combines reinforcement learning to dynamically optimize the weight, so that the real-time performance and accuracy of risk assessment are remarkably improved.

The invention discloses a fitting uniformity detection method and device, electronic equipment and a storage medium, and relates to the technical field of head-mounted display device.The method comprises the steps that in a first time interval when to-be-detected equipment is installed on a head model, a driving assembly is controlled to drive the head model to swing in a preset first driving mode; within a second time interval when the to-be-tested equipment is installed on the head model, the driving assembly is controlled to drive the head model to swing in a preset second driving mode, and the swing amplitude of the head model in the second driving mode is larger than that in the first driving mode; collecting a first pressure data graph in a first time interval through a pressure sensor, and collecting a second pressure data graph in a second time interval; and according to the first pressure data graph and the second pressure data graph, determining a fitting uniformity result of the to-be-tested equipment. According to the invention, the accuracy of fitting uniformity detection of the head-mounted display device can be improved.

The invention provides a multi-source solid waste comprehensive road system and method for road reconstruction and expansion, and relates to the technical field of multi-source solid waste distribution. The system comprises a solid waste classification and coding module, a standard solid waste three-level classification system is established, and a unique digital identity code is generated for each kind of solid waste; the multi-source solid waste database construction module is used for storing and managing digital identity codes, attribute data, image information and geographic position information of the solid wastes and constructing a multi-source solid waste database; the solid waste image recognition and search module determines a solid waste image code and inputs the solid waste image code into a multi-source solid waste database for search matching to obtain a target solid waste attribute file corresponding to the solid waste image code; the intelligent matching module for the solid waste road receives project requirements of road reconstruction and extension, performs multi-target optimization matching on the project requirements and the target solid waste attribute file through a built-in intelligent algorithm, and outputs a recommended solid waste recycling scheme; and optimal utilization of solid wastes in road use is selected, so that high value of resources is realized.

The invention relates to the technical field of early warning management platforms, and particularly discloses a whole-plant comprehensive early warning management platform and method based on multi-source heterogeneous data fusion, and the platform comprises an image data collection layer, a data governance layer, an early warning analysis layer, an application interaction layer, and a safety protection layer. The image data acquisition layer covers data of the DCS system, the NCS system, the field inspection system, the fire alarm system, the video monitoring system and the intelligent monitoring system; the early warning analysis layer realizes alarm grading through a three-stage process of weight calculation, severity evaluation and score correction; and the application interaction layer is linked with the early warning analysis layer, a differential push strategy is triggered according to an alarm level, and the security protection layer meets the requirements of national energy group network security level protection of three levels or above. The core technical scheme (such as data atlas construction logic, an early warning algorithm model and a safety protection mechanism) of the method is not limited to specific unit types, and can be flexibly adapted to different types of thermal power projects such as gas turbines and coal-fired units with the capacity of 300MW-1000MW.

The invention discloses an implementation method and system for AI and Agent agents to perform autonomous exploration and produce content, and relates to the technical field of AI and Agent agents, and the implementation method comprises the following steps: receiving an Agent identity file, an exploration target keyword, a narrative style parameter and an observation preference parameter configured by a user at a client, and generating Agent metadata containing character vectors and behavior tendencies; generating a virtual city model with a spatial topological structure based on GIS data, a POI map and historical and cultural corpora, and endowing buildings, roads and NPCs in a city with queriable semantic tags and interactive states to form a city-level semantic environment; by constructing a city-level semantic environment and a multi-agent collaborative exploration mechanism, autonomous perception, hierarchical decision and dynamic narrative generation of the AI Agent in a highly structured virtual city are realized, and by means of deep fusion of GIS data, POI atlas and historical and cultural corpora, a real geographic basis and cultural connotation are given to a virtual space, and immersion and logic coherence are improved.

The invention discloses a multilevel intelligent mind map generation device based on a large model, and the device comprises a multi-modal data conversion module which processes audio and video data through a multi-modal large model, and converts the input text data and the audio and video processing data into a unified structured text format; the data preprocessing module is used for performing deep semantic analysis on the structured text, extracting key information elements, and performing document slicing and entity structure processing to obtain structured data; the graph fusion module is used for constructing a knowledge graph based on the structured data and ensuring the data quality through an entropy increase resistant mechanism; the graph generation module is used for extracting a community structure from the knowledge graph and generating hierarchical node data of the mind map; the mapping module is used for rendering the node data into a multi-level mind map; and the output module provides interactive display and file export functions of the mind map. According to the device, automatic and multi-level generation of the mind map is realized, and the generation efficiency and accuracy are remarkably improved.