133 results about "Flow process chart" patented technology

The invention discloses an Agent-based tool combination and task processing method and device, equipment and a medium, and the method comprises the steps: carrying out the natural language processing of a task instruction inputted by a user, and generating a structured semantic vector containing task semantics; performing similarity matching on the structured semantic vector and a predefined tool node semantic tag in a knowledge base, and outputting a candidate tool node set related to the current task; performing dynamic priority ranking on the candidate tool node set based on context parameters to generate an initial thinking chain; converting the thinking chain into a tree flow chart structure, and performing dynamic addition and deletion or parameter adjustment on tool nodes in the flow chart according to a feedback or preset optimization strategy; and updating tool combinational logic according to the adjusted thinking chain, processing the task instruction, and outputting a task processing result. The tool nodes are matched through the Agent agents, and the thinking chain is generated through dynamic sorting, so that the task processing efficiency and accuracy are improved.

The invention provides an industrial PLC code generation system and method based on artificial intelligence, and the system comprises an input module, a model optimization module, a code generation module and a deployment module, the input module is used for receiving and analyzing a natural language, a flow chart and an I / O configuration table, and generating a structured logic constraint; the model optimization module is used for supporting low-precision reasoning and dynamic expert network load balancing by adopting an artificial intelligence model of industrial control field data fine tuning; the code generation module is used for outputting PLC codes meeting industrial standards and supporting simulation verification and error correction; and the deployment module is used for downloading the generated code to target PLC equipment or integrating the generated code to engineering software. According to the industrial PLC code generation system and method based on the artificial intelligence, a tool for generating the PLC code based on the natural language of the artificial intelligence is provided, the code development efficiency is improved, and the error rate is reduced.

The invention provides a personalized federal learning method for a pipeline instrument flow chart. When a PID drawing is used for knowledge graph model training, the problems of insufficient local training data and inconsistent joint training standards are often encountered, and the generalization ability and the individuation ability of the model are influenced. The method comprises the following steps: establishing a mapping relation between a local PID legend standard and a global PID legend standard by introducing a federated learning framework; constructing a triple by using the extracted knowledge corresponding PID legend standard by using a target detection and character recognition technology, and forming a local knowledge graph and a global knowledge graph; a federal learning method is used for training a knowledge completion model and a knowledge embedding model, drawing data from different enterprises are fully utilized, and the generalization ability of the models is improved while the privacy of the drawing data is protected; personalized training is carried out based on a federal training result, so that the extracted knowledge is ensured to benefit from other node data, and meanwhile, the personalized requirements of each enterprise are met.

The invention discloses a multi-modal large model automatic evaluation method and system based on Agentic Workflow, relates to the technical field of artificial intelligence model evaluation, and solves the technical problems that an existing large model evaluation method lacks image-text evaluation, is relatively high in subjectivity and is easy to cause illusion. The method comprises the following steps that S1, an input task is analyzed, and a structured task template is generated; s2, generating a multi-round multi-modal task flow chart based on the task template generated in the step S1; s3, based on the flow chart in the step S2, distributing the multi-modal large model component to each task node, executing a task and obtaining an intermediate result; s4, performing multi-dimensional scoring on the intermediate and final results in the step S3 by a plurality of scoring Agents, and fusing to generate an evaluation result; and S5, generating a feedback report based on the process data in the steps S1 to S4, identifying a model short plate, and providing an optimization suggestion. The method has the advantages of comprehensive evaluation of multiple modes, real-time feedback optimization and the like.

The invention relates to a business process information extraction method based on a large language model. The method comprises the following steps: collecting business process text data; calling a large language model to pre-process the collected business process text data; performing context example learning on the large language model, and extracting business process information in the preprocessed business process text data through the learned large language model; generating a visual business flow chart based on the business flow information; according to the method, the automation degree and efficiency of business process information extraction are improved, the accuracy and consistency of the information are remarkably improved, complex natural language description can be processed, key information can be automatically extracted, a standardized business process model is generated, high flexibility and adaptability are achieved, and the method is suitable for popularization and application. Adjustment and optimization can be carried out according to specific requirements of different enterprises and industries, and diversified business process modeling requirements are met.

The invention provides a multi-module business process automatic splicing method and system, and relates to the technical field of business process splicing, and the method comprises the steps: carrying out the modularization processing of business functions, obtaining a plurality of function module sets, and each function module set comprises a plurality of independent business function modules; performing function demand analysis based on the real-time service demand, and determining a target function demand; matching to obtain a plurality of standby function modules; compatibility and splicability analysis is carried out, N target function modules are obtained through screening, and N is larger than or equal to 0; carrying out business process analysis, and constructing a business flow chart containing a logic sequence and a dependency relationship; and based on the business flow chart, performing automatic splicing of the N target function modules to form a multi-module business flow. The technical problems that in the prior art, the development time is long and the flexibility is insufficient due to the fact that the corresponding process logic usually needs to be developed from the beginning for each new business requirement, and modular reuse is difficult to achieve are solved.

Example embodiments of the present disclosure provide a method, a device, and a computer program product for processing a workflow chart. The method includes encoding structural information of the workflow chart including a plurality of nodes and a plurality of edges by using a graph neural network to acquire a vector representation of the structural information; acquiring textual description data about the workflow chart at the nodes; training a language model based on the acquired textual description data and the acquired vector representation to acquire a pretrained language model; and fine-tuning the pretrained language model through training data of a specific task to acquire a fine-tuned language model. Through the method for processing the workflow chart of the present disclosure, the combination of the graph neural network and the language model not only can process a large number of complex workflow charts, but also can generate effective natural language outputs.

The invention discloses a carbon emission weak link identification method and system for an industrial enterprise, and relates to the technical field of industrial carbon emission management, and the method comprises the steps: collecting production process data of the industrial enterprise, the production process data comprising a process flow diagram, equipment energy consumption data and material consumption data; an actual sample and a theoretical sample are constructed based on production process data, an XGBoost algorithm is adopted to establish a prediction model of characteristic parameters and carbon emission, and a contribution value of each characteristic parameter to the carbon emission is quantified through an SHAP algorithm. By integrating the process flow diagram, the equipment energy consumption and the material consumption data, a complete carbon emission data system is established, and the problems of scattered data acquisition and non-uniform standards in a traditional method are solved.

The invention provides a laboratory detection task intelligent allocation method and system based on big data, and relates to the technical field of laboratory management, and the method comprises the steps: collecting detection task data, carrying out the detachable analysis to construct a collaborative flow chart, calculating a collaborative efficiency index and a task priority, and extracting personnel collaboration features to generate an association weight matrix; and allocating task queues by adopting a double-layer adaptive task allocation algorithm, performing density peak clustering on the first layer to divide task clusters, and optimizing an allocation scheme in combination with personnel ability and cooperative affinity on the second layer. According to the invention, the distribution efficiency and cooperation quality of complex laboratory detection tasks are improved.

The invention discloses a cross-system data collaborative driving workflow full-link approval method and system, belongs to the technical field of workflow management, and aims to solve the technical problem of how to realize cross-system data collaborative driving and cover a workflow full-link approval method and process. Comprising the steps that a system architecture composed of a unified workflow engine, data collaboration middleware and a plurality of service systems is built; drawing a cross-system workflow full-link approval flow chart in the unified workflow engine; by means of data collaboration middleware, a collaboration mapping relation of all service systems is established, and data format conversion, extraction and integration operations are automatically executed in process execution; and the unified workflow engine generates a process instance, notifies a service system of a subsequent approval node through the data collaboration middleware, sends an approval task to the corresponding approval node, transmits related data through the data collaboration middleware, notifies related personnel, and records various information in a full-link approval process execution process in real time.

The invention relates to the technical field of information management, in particular to a software development service management platform and method. The method comprises the following steps: acquiring customer demand change information, analyzing the customer demand change information, and determining demand change key information; obtaining a project development flow chart, analyzing the demand change key information and the project development flow chart, and determining a business modification starting node; obtaining a project milestone node list, modifying the initial node according to the business, screening the project milestone node list, and determining a key milestone node; analyzing a service modification starting node and a key milestone node, and determining a resource overall planning influence factor set; and according to the resource overall planning influence factor set, determining and outputting a resource overall planning plan for reference of a project development team. According to the method and the device, software development project resources are quickly and effectively planned, so that the software development business process is prevented from being disrupted by temporary requirements of customers, and the customer satisfaction is improved while project risks are reduced.

The invention provides an interactive exchange chip debugging graphical interface construction method, device and equipment, and the method comprises the steps: obtaining a basic chip flow chart drawn based on an automatic flow chart drawing tool, and generating a visual SVG format file according to the basic chip flow chart, the SVG format file comprises a logic function module and a register of the chip; based on the SVG format file and the background data of the register, dynamically rendering each logic function module of the chip, binding the corresponding background data in real time, and realizing display and updating; and displaying detailed information of a specific logic function module or a register on an application interface according to a click operation of a user, and displaying an abnormal point of an assembly line in the chip in real time. According to the method, the development cycle and the labor cost of developing the graphical interface can be remarkably reduced.

The invention belongs to the technical field of business process analysis, and discloses an agent-based industrial software demand acquisition and analysis method and system, and the method comprises the steps: constructing a multi-agent-based demand analysis system; converting user multi-modal input into a structured industrial software demand by using a multi-agent-based demand analysis system; and generating a business flow chart conforming to the BPMN standard according to the requirements of the structured industrial software. According to the invention, the multi-agent system is combined with the demand analysis task, so that efficient and accurate demand analysis is realized, and powerful support is provided for project planning and implementation in the new industrial era.

The invention relates to the technical field of process control, in particular to a radiation environment laboratory full-process traceable system and a processing method.According to the radiation environment laboratory full-process traceable system and processing method.By executing timestamp sequence extraction, attribute difference screening and path structure decomposition operation on detector records and shielding cover logs, causal, time sequence and role attachment relation edges between nodes are established; and classifying attribute values to construct a unified mapping set, converting the multi-source heterogeneous data into a flow chart structure with relevance, executing node embedding operation through a graph attention network algorithm, and performing adjacent node feature weighted aggregation and edge weight screening processing based on an embedding result. And calling a Tarjan strong connected component algorithm to analyze a node branch structure, identifying a heterogeneous sub-graph in a flow path by branch index difference, executing priority ranking and task insertion actions in combination with the number of available tokens and lead plate thickness grade parameters, and generating a dynamic scheduling sequence under a multi-task coexistence condition in a control path.

The invention discloses a visual process automatic layout method based on dependency graph optimization, and relates to the technical field of visual layout optimization, and the method comprises the following steps: S1, carrying out the global scanning of an overall dependency graph, employing a self-adaptive structure entropy algorithm, extracting the connectivity and path span information of each node, and constructing a structure bit order vector of the connection strength between the nodes; according to the method, low coupling dependence is identified through structure bit sequence vectors and semantic confidence scores, spatial distribution of weak connection subgraphs is optimized by combining a field model and repulsive force, path smoothness and layout stability are ensured through dynamic path adjustment and local simulation optimization, and visual hierarchy definition is improved through hierarchy consistency verification and global correction. According to the scheme, the readability and interactivity of the flow chart and the stability and adaptability in dynamic updating and industrial application are remarkably enhanced.

The invention relates to a malicious APP family identification method based on multi-modal feature fusion, and belongs to the technical field of information security. The method comprises the following steps: performing data preprocessing on the Android APK, including unpacking and decompiling operations, to obtain a byte code file and a smali code file; respectively extracting byte code image features, operation code sequence features and control flow chart features; according to the method, byte code image features are extracted by using an OfficientNetV2L convolutional neural network, operation code sequence features are extracted by using a k-Shingles algorithm and a SimHash algorithm, and control flow chart features are extracted by using a static analysis tool and a capsule graph neural network. And carrying out low-rank multi-modal fusion on the three features, and constructing a CNN-BiLSTM-Attention detection classification model, so as to realize identification and judgment on the malicious APP family. According to the method, the recognition accuracy is improved, and the generalization ability of the model is enhanced.

The invention provides a task execution method and device and electronic equipment, and the method comprises the steps: carrying out the intention recognition of a task processing request, extracting a plurality of pieces of task key information, and constructing a task semantic map based on the plurality of pieces of task key information; constructing an execution flow chart based on the execution dependency relationship and the execution path of each node, and adding metadata information of the node in each node in the execution flow chart to obtain the execution flow chart added with the metadata information; and performing task execution based on the execution flow chart added with the metadata information, and determining an execution result of the task processing request. The execution flow chart constructed based on the task semantic graph not only clarifies the execution dependency relationship and path of each node, but also provides an execution index for node execution by adding metadata information, so that high automation of task execution is realized, and the accuracy and execution efficiency of the automatic task execution process are greatly improved.

The invention discloses a templated business process management method, and relates to the technical field of enterprise management.The method comprises the steps that repeatable task units in a business process are represented and packaged into function components capable of being configured in a draggable mode, combined arrangement is conducted in a visual working area template, and process construction is conducted from the development coding level to the development coding level; according to the technical scheme, the method sinks to a configuration level which can be understood by business personnel, in the step of creating the visual workflow template, when the working area templates bearing specific tasks are bound with process nodes, separation and standardized packaging of business logic and execution logic are achieved, and various working area templates are predefined through a graphical interface; the node function assembly can be quickly completed only by quoting the templates in the flow chart, the defect that each node needs to be independently developed or written in a traditional mode is overcome, and the core defects that in the prior art, flow construction is complex, the reuse rate is low, and the method excessively depends on technicians are overcome.

The invention provides a SysML model construction method, a SysML model driven design model construction method and a SysML model driven design model construction system. The SysML model driven design model construction method comprises the following steps: obtaining a first system model, a first equipment model and a process model; the first system model, the first device model and the process model are described based on a meta-model extended from SysML semantics; constructing a design model according to a conversion rule, the first system model, the first equipment model and the process model; wherein the meta model extended from SysML semantics can be used for identifying information used for constructing the design model; the first system model is used for describing a system for constructing the design model; the first equipment model is used for describing equipment for constructing the design model; and the flow model is used for constructing the design model comprising a pipeline and instrument flow chart.

The invention provides a medical business process generation method and device, equipment and a storage medium, and relates to the technical field of medical treatment. According to the method, a process investigation file of a target hospital is obtained, and the process investigation file comprises process description information of multiple medical services in the target hospital; and according to the process description information of the plurality of medical businesses, updating configuration information of target process nodes corresponding to the plurality of medical businesses in a preset standard flow chart, and generating a target flow chart of the target hospital. Therefore, the target flow chart of the target hospital is generated according to the format of the standard flow chart, so that the medical business process of each hospital is clearer and is convenient for a user to use, the user can intuitively and comprehensively know the business process of the hospital, and the user experience is improved.

The invention relates to a client work order management method and system based on intelligent template dynamic configuration, and the method comprises the following steps: S1, obtaining a business demand document, historical work order data and a field rule library, extracting all business scene universal fields, and storing the universal fields in the field rule library; s2, constructing template metadata according to the field rule base; s3, dynamically generating a work order instance; s4, after the work order is generated, the whole work order processing cycle is driven according to the flow rule, and each work order node and operation action are dynamically executed according to the template flow chart configuration; and S5, regularly and automatically counting the field utilization rate, common process bottlenecks and high-frequency branches through data analysis, generating template optimization suggestions in combination with user feedback and user satisfaction survey data, automatically classifying new problem descriptions by the system according to a pre-trained machine learning model, recommending the most suitable template, and finally, carrying out data analysis on the new problem descriptions. And a work order dispatching strategy is optimized in combination with historical efficiency data. According to the invention, high flexibility and intelligence of work order management are realized.

The invention relates to a method for generating an overall Pamp based on a three-dimensional model. The invention discloses an ID graph system and method, and the system comprises a processor which comprises an extraction module, a symbol mapping module, a relation construction module and a layout module. The extraction module is used for analyzing a designated area of the three-dimensional model and extracting a three-dimensional symbol type and a topological relation of the three-dimensional model; the symbol mapping module is used for establishing a mapping relation table of the three-dimensional symbol types and the two-dimensional symbol types based on the three-dimensional symbol types and a mapping rule so as to retrieve the two-dimensional symbol types based on the three-dimensional symbol types; the relation building module is used for building a logic diagram data table based on the topological relation so as to store the connection relation and the sequence relation; the layout module is used for carrying out two-dimensional symbol layout based on the two-dimensional symbol type and the three-dimensional symbol type to form a complete Pamp; and an ID graph. According to the invention, the traditional Pamp is abandoned; according to the thought of generating the complete flow chart on the ID, the efficiency is improved by intelligently extracting the information topological relation of the model and combining the user-defined symbol mapping rule.

The embodiment of the invention provides an industrial monitoring method and device, electronic equipment and a medium. According to the embodiment of the invention, the data model and the algorithm program of the industrial project are obtained, and the algorithm program is analyzed to generate the algorithm flow chart, so that the monitoring parameters in the data model and the program variables in the algorithm program are accurately bound based on the variable binding address. In the execution process of the industrial project, the real-time data of the monitoring parameters are dynamically mapped to the corresponding program variables in the algorithm flow chart, and the corresponding target flow chart nodes in the algorithm flow chart can be determined and marked according to the actual execution state of the industrial project, so that the operation and maintenance threshold is reduced, the automation level of industrial monitoring is improved, and the industrial monitoring efficiency is improved. Problems in the production process can be found and solved in time, and finally the stability and efficiency of industrial production are improved.

The invention discloses a business flow chart processing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps that in response to a monitored copy event, a to-be-multiplexed process in a first business flow chart is stored in a shared storage, and the to-be-multiplexed process comprises at least one process node and a connection relation between the process nodes; in response to the monitored paste event, obtaining a to-be-multiplexed process from the shared storage; and pasting the to-be-multiplexed flow into the second business flow chart to edit the second business flow chart. According to the embodiment, the cross-business flow chart copying and pasting function is realized, switching and operation among multiple business flow charts can be conveniently realized, the problem of flow reuse among the business flow charts is solved, the working flow of a user is simplified, and the operation flexibility and the generation efficiency of the business flow charts are improved.

The present invention discloses a deep learning method, device, working medium and computer equipment for abnormality detection in industrial control systems. The neural network model constructed by the method uses one-dimensional convolution and linear layers to extract the time-dependent features of sensor nodes. The physical flow chart divides the sensor nodes into subgraphs, and extracts local dependency features by setting it as a complete graph and a graph attention network, generates physical process embedding by pooling, and applies the graph attention network to capture the global dependency between processes. The control chart extracts the communication features of sensors in the controller through the graph attention network, generates controller embedding by pooling, and then applies the graph attention network to capture the information flow between controllers. Through the joint modeling of the physical flow chart and the controller communication graph, multi-level dependencies are effectively captured. The early stopping mechanism is used to avoid overfitting, and anomaly location based on anomaly scores is supported. The method can efficiently detect and locate anomalies in industrial control systems and ensure the safe and stable operation of the system.

The invention relates to the field of pipeline configuration, and discloses a method for generating a process pipeline and an instrument flow chart of equipment, which is suitable for being executed in computing equipment, and comprises the following steps: in response to a received drawing request for drawing the process pipeline and the instrument flow chart, obtaining target interface information of one or more interfaces from a machine demand table, the target interface information comprises flow information and interface information, and the interface information comprises an interface size; determining the pipeline size of a branch pipe connected with each interface according to the target interface information of each interface; determining an access mode of connecting the branch pipes to the system according to the pipeline size of each branch pipe and the interface information to be accessed to the system; and generating a process pipeline and instrument flow chart of the equipment according to the pipeline size of the branch pipe and the access mode of connecting the branch pipe to the system.

The invention provides a feedback information generation method and device, and relates to the technical field of artificial intelligence, in particular to the technical fields of large models, automatic driving, intelligent traffic and the like. According to the specific implementation scheme, the method comprises the steps of determining an application field of current query information and a target component set associated with the application field; inputting the current query information and the target component set into a large language model, and generating a function component calling flow chart; and the execution function component calls the action instruction sequence corresponding to the flow chart to generate feedback information. According to the mode, the accuracy and efficiency of generating the feedback information are effectively improved.

The present invention relates to the field of pipeline configuration and discloses a method for generating a process pipeline and instrument flow chart of an equipment, which is suitable for execution in a computing device. The method comprises the following steps: in response to receiving a drawing request for drawing a process pipeline and instrument flow chart, obtaining target interface information of one or more interfaces from a machine requirement table, the target interface information including flow information and interface information, the interface information including interface size; determining the pipe size of a branch pipe connected to each interface according to the target interface information of each interface; determining the access mode of connecting the branch pipe to the system according to the pipe size of each branch pipe and the interface information of the system to be connected; and generating a process pipeline and instrument flow chart of the equipment according to the pipe size of the branch pipe and the access mode of connecting the branch pipe to the system.

The invention discloses a data processing method and device based on software testing and a program product. The method relates to the field of software testing or financial science and technology, and comprises the following steps: acquiring all test elements of to-be-tested software to obtain a test element set; classifying the test elements in the test element set to obtain a classification result; obtaining a business processing flow of the to-be-tested software to obtain business flow data; based on the classification result and the business process data, a test flow chart is generated, and the test flow chart is used for providing services for compiling test cases. By means of the method and device, the problem that in the related technology, in the testing process of a complex tested system, the coverage range of a compiled testing case in the tested system is small, and consequently the testing result is inaccurate is solved.

The invention discloses a visual compiling system for cloud intelligent screen operation chain tracking, and relates to the technical field of intelligent office systems.The system comprises an operation chain logic modeling module, a visual interaction configuration module, a compiling deployment execution module, an abnormity intelligent diagnosis module and a repairing scheme closed-loop module. A structured logic graph is generated and converted into a visual flow chart, runnable codes are automatically generated and deployed, abnormity is accurately diagnosed, an adaptive repair scheme is generated, and whole-process closed-loop management is formed; according to the method, full-process automation from operation collection to code generation is realized by integrating an automatic process module, a structured graph is constructed by relying on a logic dependency algorithm, a configuration threshold is reduced by combining a visual interface, differentiation and offline deployment are supported, the development period is shortened, the maintainability is improved, and meanwhile, the development efficiency is improved. And an anomaly diagnosis and repair closed-loop mechanism accurately locates an anomaly root, a reliable repair scheme is generated, the manual troubleshooting cost is reduced, and the fault response efficiency is improved.