26 results about "Link diagram" patented technology

The invention discloses a cognitive link diagram modeling and visual expression method, device and system, and belongs to the field of user behavior data modeling visualization, and the method comprises the steps: building a diagram expression and a traceable path of a causal structure based on a user behavior data modeling result; wherein the logic relevance and evolution directivity between entities in the graph are enhanced through a semantic annotation mechanism of nodes and edges of the graph, and the user cognition evolution process in the user behavior data is presented. According to the method, path-traceable graph structure visual expression is supported, and the cognitive evolution process of the user can be presented more finely.

The invention relates to an application test method and device, electronic equipment and a storage medium, and relates to the technical field of computers, and the method comprises the steps: obtaining an application service relation graph and test range indication information under the condition that an application test instruction is received; determining a plurality of to-be-tested services and service link diagrams based on the application service relation diagram; performing link weight analysis on each to-be-tested sub-link based on the edge weight information or the node weight information in each to-be-tested sub-link to obtain sub-link weight information; based on the sub-link weight information and the service link diagram, performing a flow distribution test on the plurality of to-be-tested sub-links to obtain a link calling test result; obtaining service test codes corresponding to a plurality of to-be-tested services; based on the service test code, performing a service execution test on each service to be tested in the plurality of services to be tested to obtain a service execution test result; and generating an application test result based on the link call test result and the service execution test result.

The invention provides an AI-driven industrial production line intelligent quality detection method, which comprises the steps of obtaining an initial parameter and a detection level identifier of a product quality detection request from an industrial production environment, judging whether the initial parameter accords with a preset quality threshold range or not, and obtaining an initial detection result and a corresponding timestamp mark; constructing a product quality tracing link diagram according to the position of the interruption point and the misjudgment and missing detection information, performing priority ranking on nodes of the link diagram by adopting a classification algorithm, and determining a defect source in a production link; and integrating a detection result record and a timestamp mark from the improved detection efficiency index, constructing a product quality detection link traceability system, judging the integrity of the traceability system, and obtaining final quality guarantee output.

A system can efficiently determine whether an identity is manipulated. The system can receive entity data and interaction data associated with a target entity. The system can determine, based on the entity data and the interaction data, one or more risk signals associated with the target entity using one or more artificial intelligence models. The system can generate a linked graph structure based on a first graph structure and a second graph structure each generated using the entity data and the interaction data. The system can apply the one or more risk signals to the linked graph structure to determine a risk indicator associated with the target entity. The system can provide a responsive message based on the risk indicator. The responsive message can be used to control access of the target entity to an interactive computing environment.

The application provides a masterbatch production process record method and system applied to quality tracing, relates to the computer technology field, and first acquires an initial process event record set of multiple production process nodes of a masterbatch production line, generates a production process event flow data set through production process event flow reconstruction processing; then calls a production material batch tracking model to analyze a material flow path, and constructs a material batch flow link diagram; then binds production equipment operation state records to the flow nodes, and generates equipment operation state parameter sequences; finally, generates a masterbatch production process tracing record set according to the material batch flow link diagram and the equipment operation state parameter sequences, and stores the masterbatch production process tracing record set to a tracing database, so that the masterbatch production process tracing record set can be called for subsequent quality tracing query, and efficient and accurate quality tracing is realized.

The invention discloses a property facility intelligent operation and maintenance management system and method based on deep learning, and belongs to the technical field of property facility operation and maintenance management.The method comprises the steps that firstly, through analysis of operation data of property facilities, the facilities with fault risks are recognized and defined as potential fault points; generating a fault influence link diagram based on the physical connection path and the function association between the facilities; according to the link diagram, positioning all affected associated facilities as troubleshooting points, and according to a conduction sequence, facility grades and influence ranges, performing priority grading and parameter matching; then, integrating the fault point and all troubleshooting points into a task group, matching maintenance and detection personnel according to a link diagram, and planning a continuous detection path; and finally, the fault features, the influence links, the grading strategy and the execution scheme in the processing process are packaged into operation and maintenance scene templates, and intelligent multiplexing and continuous improvement of the operation and maintenance strategy are realized by comparing the feature similarity of historical templates.

The embodiment of the invention provides an autism auxiliary diagnosis method. The autism auxiliary diagnosis method comprises the following steps: constructing an individual brain function connection diagram; based on a community detection algorithm of a graph theory, performing functional region division on the individual brain function link graph to generate an individual brain map; taking the surface area percentage of the functional network of the healthy control group in the cerebral cortex as a response variable, taking the individual age as a smooth nonlinear independent variable, introducing an average head movement parameter as a linear covariable, and constructing a normal population development reference model; and comparing the surface area percentage of the functional network of the individual brain map with the normal population development reference model of the same age, and quantifying the deviation degree to realize auxiliary diagnosis of the autism. According to the autism auxiliary diagnosis method provided by the embodiment of the invention, individualized autism auxiliary diagnosis considering individual differences can be realized. The embodiment of the invention further provides an autism auxiliary diagnosis device and electronic equipment.

The application discloses an operation and maintenance data processing method and device and electronic equipment. The method comprises the following steps: obtaining operation and maintenance data of a target data source, wherein the operation and maintenance data comprises object information, relationship information and running data of an operation and maintenance object; constructing an operation and maintenance object relationship network based on the object information and the relationship information of the operation and maintenance object, wherein the operation and maintenance object relationship network is used for displaying multiple operation and maintenance relationships of the operation and maintenance object; creating a visual view based on the operation and maintenance object relationship network to display the object information, the relationship information and the running data of the operation and maintenance object under different performance dimensions, wherein the visual view is used for displaying a physical deployment diagram and a key link diagram of the operation and maintenance object. The application solves the technical problem that the operation and maintenance object, the operation and maintenance relationship and the running data of the operation and maintenance object cannot be uniformly integrated, so that the running state of the operation and maintenance object cannot be clearly and conveniently displayed.

The present disclosure relates to a user interaction device and method for searching and organizing vast papers with a node-link diagram. The device is configured to display at least one first node respectively representing at least one first paper, display a second node representing a desired paper generated by a user and at least one link respectively representing a citation relationship between the at least one first paper and the desired paper between the at least one first node and the second node, search for at least one second paper corresponding to the citation relationship as the desired paper, and collect the at least one second paper in the second node.

The application discloses a machine reading comprehension event extraction method and device based on template bridging, and medium, the method steps comprise: step S01. Input text and trigger word question template are obtained and combined to form an input instance with a trigger word question prompt template; step S02. Syntax analysis is performed on the input instance to form an adjacency graph, the input text and the trigger word question prompt template are connected according to the adjacency graph to obtain a link graph, and global features are extracted according to the link graph; the global features and semantic features are fused to identify the trigger word and the trigger word type; step S03. A argument question prompt template is generated, the prompt template is combined with the input text to form an input instance with a question prompt template; step S04. Argument extraction is performed to obtain argument and argument type output. The application has the advantages of simple implementation method, high event extraction efficiency and precision, good portability and the like.

Embodiments of the present disclosure relate to a workflow creation method and apparatus, a device, and a storage medium. The method proposed herein comprises: in response to a received editing operation, adding a first node to a node-link diagram; acquiring configuration information associated with a first node, wherein the configuration information at least indicates a group of nodes corresponding to a cyclic process; and creating a target workflow on the basis of the node-link diagram, such that during running of the target workflow, in response to the first node being triggered, a processing process corresponding to said group of nodes is cyclically executed. In this way, the embodiments of the present disclosure can support definition of a cyclic process in a workflow, so as to support one or more nodes being triggered for cyclic execution.

1. The name of the present design product: display area of smart conversation or search graphical user interface of electronic device. 2. The use of the present design product: an electronic device. 3. The design points of the present design product: the partial graphical user interface in the electronic device. 4. The picture or photo that best shows the design points: design 1 front view. 5. The designated design 6 is the basic design. 6. The use of the graphical user interface: the graphical user interface is used for smart conversation or search. The partial graphical user interface that is claimed is used to display the question input by the user and the thinking process for the question. 7. The human-computer interaction mode of the graphical user interface: in design 1, design 2 and design 4, the graphical user interface can display the question input by the user and the thinking process for the question, and the user can stop the thinking of the question by touching or clicking the stop button at the bottom of the graphical user interface. In design 3, the user can continue the thinking process for the user's question by touching or clicking the "continue to generate" button in the graphical user interface. In response to the user touching or clicking the "supplement files or links" area in the design 5 front view and uploading files and links, the graphical user interface changes from the design 5 front view to the design 5 changed state view to display the supplemented files and links. In response to the completion of the reference information search for the user's question, the graphical user interface changes from the design 6 front view to the design 6 changed state view to display the outline generation process. In response to the completion of the reference information search for the user's question, the graphicaluser interface changes from the design 7 front view to the design 7 changed state view to display the outline generation process. In response to the user touching or clicking the "supplement files or links" area in design 8 front view and uploading files and links, the graphical user interface changes from design 8 front view to design 8 changed state view 1 to display the supplemented files and links; in response to the user touching or clicking the "continue to generate" button in design 8 changed state view 1, the graphical user interface changes from design 8 changed state view 1 to design 8 changed state view 2 to continue the thinking process for the user's question. 8. Other circumstances that need to be explained Other explanations: the part of the graphical user interface shown by the black dashed line in each view of design 1 to design 8 does not constitute the part claimed in the present design. The present design does not claim protection of color.

The invention relates to a method for realizing combined scheduling and arrangement for automobile SOA service. The method comprises the following steps: receiving JSON format data from a data source; analyzing the data of the data source, and analyzing a dependency relationship through node information; generating an execution link diagram according to the node information and the task dependency relationship; converting the execution link graph into a directed acyclic graph (DAG); performing task scheduling on the DAG; and executing the scheduled task through the vehicle end service orchestration engine. By the adoption of the method and device for achieving combined scheduling and arrangement for the automobile SOA service, the processor and the computer readable storage medium of the processor, a plurality of modules such as an automobile central control screen function module, an automatic driving module, an intelligent cabin module and a power system module can communicate through an SOA framework, and the system can be managed through a unified management strategy. The effects of cooperative work, dynamic scheduling, optimal configuration and the like of various functional modules are achieved, and the overall performance of the system and the user experience are improved.

The invention relates to a model-enabled supply chain risk early warning method and system, and the method comprises the following steps: detecting whether an abnormal order block exists in collected supply chain data or not, and carrying out the restoration of a supply chain path according to the abnormal order block if the abnormal order block exists, and obtaining a risk link diagram; inputting the risk link diagram into a preset time sequence diagram neural network model for risk conduction analysis to obtain risk probability distribution and a prediction influence range; and generating a risk early warning report based on the risk probability distribution and the prediction influence range, and pushing the risk early warning report to a related decision maker to support risk prevention and control and emergency response. And the risk early warning often lags behind the actual risk occurrence process.

The invention discloses a data consanguinity extraction and completion method and system of a development script, equipment and a medium, the method generates a data consanguinity link diagram of the development script based on a natural language model, and also generates natural language description of a consanguinity link, so that accurate identification and analysis of a service intention of the development script are realized, and the development script is more accurate in data consanguinity extraction and completion. And the field-level blood relationship is extracted in detail. Besides, implicit field-level dependencies which are not clearly written in codes but actually exist can be intelligently complemented by means of strong semantic thrust and association capability of the large language model, so that the recognition rate and complementation accuracy of the implicit dependency relationship are remarkably improved, and the continuity and credibility of full-link blood relationship are ensured. Moreover, low-consensus-degree blood relationship links are removed based on multiple rounds of verification, so that stable convergence and credible screening of the blood relationship links are realized, and the stability, robustness and audit traceability of the final data blood relationship are greatly improved.

The invention discloses a knowledge link diagram construction method and device, a terminal and a medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining fusion confidence scores corresponding to any two types of entities in various types of entities of original data; and based on the various entities and the fusion confidence score, constructing a target knowledge link diagram, nodes in the target knowledge link diagram being in one-to-one correspondence with the various entities, and weights of edges in the target knowledge link diagram being determined according to the fusion confidence score. According to the method, the knowledge link diagram is constructed, the method can adapt to the dynamically-changing data relation, many-to-many transitive complex association between entities can be efficiently stored and inquired, the bottleneck of a traditional relational database is overcome, and then entity information of different sources and different modes is more accurately recognized and associated.

This invention relates to the field of substation technology and discloses a substation defense optimization method and system. This method constructs a circuit breaker action link diagram and an action link replay model, enabling candidate risk scenarios to be input into the model and the circuit breaker action results to be derived. By comparing the tripping results output by the model with the permissible circuit breaker action results, it can distinguish between normal tripping under actual faults and false tripping under scenarios where tripping should not occur. By performing counterfactual substitution replay on candidate disturbance variables in false tripping risk scenarios, the set of counterfactual substitutions that can change a circuit breaker from false tripping to non-tripping is shrunk, determining the minimum set of causes for false tripping from multiple concurrent anomalies. Based on the controllable attributes of the minimum set of causes for false tripping, candidate preventive calibration actions are generated, and the target preventive calibration action that minimizes the risk of false tripping is selected and executed, thereby reducing unnecessary circuit breaker tripping and improving the continuity of substation operation.

The embodiment of the invention relates to an information display method and device, equipment and a medium, and the method comprises the steps: obtaining input information, and determining a planning task according to the input information; in the process of analyzing the input information by using the alarm analysis model, an analysis link diagram corresponding to analysis process information is aggregated and displayed according to the planning task, and the key nodes are highlighted by the analysis link diagram; displaying a target confirmation card corresponding to a target interaction node in response to display of the target interaction node in the analysis link diagram; and in response to a selection operation of a user on a target option in the target confirmation card, continuing the analysis process based on the target option until an end node of the analysis link diagram is displayed according to output information of the alarm analysis model. According to the method, the analysis process information planning task of the model is subjected to aggregation visual display, and the reasoning logic can be quickly understood when the analysis process is relatively long, so that a user can quickly know key nodes, and the reasoning efficiency and the reasoning effect are effectively improved.

The invention discloses a firewall opening method and device and electronic equipment, and relates to the technical field of distribution.The method comprises the steps that calling link data are determined based on a target request identifier carried by an external service request, a calling link diagram is generated according to the calling link data, a service label of a target distributed system is determined, and the service label of the target distributed system is sent to the external service request; determining initial firewall data information according to the service label and the calling link diagram, and determining an initial production address identifier of a server where an initiating service node is located and a target production address identifier of a server where a receiving service node is located in a production environment according to a server name; and replacing the initial address identifier with the initial production address identifier, replacing the target address identifier with the target production address identifier to obtain target firewall data information, and opening the firewall in the production environment according to the target firewall data information. According to the invention, the technical problem of low accuracy of determining the firewall needing to be opened in the prior art is solved.

The application discloses a data blood relationship extraction and completion method and system for developing scripts, equipment and a medium. The method generates a data blood relationship link diagram of a development script based on a natural language model, and also generates a natural language description of the blood relationship link. The method not only realizes accurate identification and analysis of the business intent of the development script, but also extracts field-level blood relationship in detail. In addition, with the help of the powerful semantic thrust and correlation ability of the large language model, implicit field-level dependencies that are not explicitly written in the code but actually exist can be intelligently completed. The identification rate and completion accuracy of the implicit dependency relationship are significantly improved, ensuring the coherence and reliability of the full-link blood relationship. Furthermore, based on multi-round verification, low-consensus blood relationship links are removed, realizing stable convergence and reliable screening of the blood relationship link, and greatly improving the stability, robustness and audit traceability of the final data blood relationship.

The invention provides a feature subset-based prediction model visual comparison and iterative optimization method and system, and belongs to the technical field of machine learning and data visualization. The method comprises the following steps: acquiring multivariable time sequence data and constructing a feature subset; constructing a multivariable time series prediction model by using the selected feature subset and adopting an integrated learning method; repeating and constructing different models; performing model correlation calculation from multiple dimensions of feature subset types, feature importance, algorithm weights and model evaluation indexes; recording an exploration process of a user by utilizing a hierarchical node link graph, performing model comparison visual analysis and performing layout optimization; the optimal feature subset is derived after iteratively optimizing the feature subsets. A visual analysis method is applied to the selection of the optimal feature subset, and a user is assisted to iteratively select the feature subset to construct a model in combination with domain knowledge, so that different feature subsets and models are better understood, diagnosed and compared, and the accuracy and credibility of a prediction result are enhanced.

The application discloses a sequence recommendation method based on an edge-enhanced global decoupling graph neural network, comprising: an input layer: all items in the training data are taken as nodes, and the interaction order between the user and the item is taken as an edge to construct a global link graph and input into the graph neural network; a decoupling learning layer: the influence probability of a preset number of factors from all neighbor items of the item and the influence probability of a preset number of factors from the target user's items in the front according to the interaction time sequence; a prediction layer: the decoupled item representation of the global level and the local level is accumulated, multiplied by the initial embedding representation of the candidate item, and the probability that the target user appears as the next interaction item v i The application has the beneficial effects of perceiving the transfer of the user's intention and more accurately recommending the product to the user.

The invention provides a cargo congestion event processing method and device, electronic equipment, a storage medium and a computer program product, and relates to the field of logistics and the field of artificial intelligence, in particular to the field of logistics congestion processing and data analysis. According to the specific implementation scheme, the method comprises the steps of obtaining equipment state data in a logistics system, wherein the equipment state data comprises at least one of cargo length, cargo volume and cargo space distribution; and detecting a cargo congestion event based on the device state data, the link graph and the mode threshold. According to the scheme, the cargo congestion event is actively detected based on the comprehensive equipment state data, the congestion event can be recognized more timely and more accurately, and the efficiency of a logistics system is improved.

This invention relates to the field of big data analytics, and more particularly to a method and system for analyzing and guiding tourism public opinion based on big data. By performing semantic analysis and sentiment recognition on tourism public opinion data, a semantic propagation link diagram and a sequence of sentiment change trajectories are constructed, and then a public opinion crisis state vector is calculated. By analyzing the dominant offset direction, node attributes, and evolution trend of this vector, guidance targets are mapped, guidance channel priorities are determined, and the decay cycle of guidance effects is predicted, ultimately generating a public opinion guidance plan. This invention achieves accurate quantitative analysis of tourism public opinion and automatic generation of dynamic guidance strategies.

The invention relates to the field of engineering safety, in particular to a BIM-based construction engineering safety management method and system. The method comprises the following steps: dividing a construction process into step-level procedures according to obtained building engineering construction data, obtaining engineering characteristic data and construction tool data, analyzing the building engineering construction data, and constructing a component space range and multi-dimensional mapping relation; on the basis of the component space range and the engineering feature data, representing each step-level process as a space occupation entity, and analyzing the space occupation entity on the basis of the step-level processes to generate a process space occupation entity set; generating a conflict coupling link diagram based on the multi-dimensional mapping relation and the process space occupation entity set; constructing a multi-segment conflict sequence based on the conflict coupling link diagram; constructing a time sequence evolution structure diagram according to the multi-segment conflict sequence; and analyzing the time sequence evolution structure diagram to generate a security collaboration strategy. The predictability and the collaboration of construction safety management can be improved.

The invention provides an information generation method and device, electronic equipment and a storage medium, relates to the field of cloud storage, and can be applied to a cloud platform. The method comprises the following steps: in response to received demand information, determining target identification information of target data according to the demand information; determining a target data packet corresponding to the target identification information from a pre-constructed data set; generating a use link diagram of the target data according to the target data packet; and generating a data analysis result corresponding to the target data according to the use link diagram. According to the invention, the readability of the information is improved, and the use experience of the user is improved.