37 results about "Process description" patented technology

The invention discloses a biochemical experiment automation script training generation method based on RAG and DPO. The method comprises the steps that biochemical experiment technical documents are collected to serve as an external knowledge base; the BM25 and the Fiss are fused to construct a hybrid retriever; generating experimental process description by using a large language model, determining equipment, protocols and materials, and retrieving related documents from a knowledge base on the basis of the experimental process description, the protocols and the materials; generating an experiment script based on a retrieval result, and performing platform simulation verification, and performing iterative optimization on the script which fails in verification; marking successful and failed scripts as preference data pairs, and constructing a training set; carrying out LoRA fine tuning on a local large language model by adopting direct preference optimization; and according to a target and appliance prompt input by a user, generating a verified experiment script by using the large language model after direct preference optimization training. According to the method, the script generation automation level and the passing rate are remarkably improved, the manual intervention cost is reduced, and an efficient solution is provided for automation of biochemical experiments.

Automatic annotations and technical specification generation for robotic process automation (RPA) workflows using artificial intelligence (AI) is disclosed. AI / ML models may enable smart searching of workflows and automatically generate documentation for the workflows, including descriptions of each activity, input / output parameters, and overall process explanations. Annotations and documentation may be provided for an entire complex business automation that is the sum of multiple workflows and applications. A Process Definition Document (PDD) for the business process may be generated from the RPA workflow code itself when it does not exist. Other documents, such as audit documents, compliance documents required by laws or regulations, etc. may be produced. The process may be iterative, where a generative AI model automatically converts text to RPA workflow code, a runtime automation is produced from this RPA workflow, and the other documentation is generated as well.

The invention discloses a manufacturing industry process parameter optimization method based on a knowledge graph, and belongs to the field of manufacturing industry intellectualization. The technical problems that in the prior art, parameter optimization depends on artificial experience, systematic management is lacked, intelligent reasoning is difficult to conduct, and knowledge retrieval precision is low are solved. The method comprises the steps of firstly collecting and preprocessing manufacturing industry process data; then, constructing a semantic vector embedding model, and converting the process description into vector representation by adopting a pre-trained bidirectional encoder; defining a process knowledge ontology model, and establishing a parameter association relationship through semantic coding to form a knowledge graph; storing the coded knowledge vector into a distributed database and establishing a retrieval index; user requirements are received, and parameter matching is carried out through cosine similarity calculation; optimizing the matching parameters based on the knowledge graph association relationship; and finally collecting feedback to continuously update the knowledge graph. Through continuous optimization of the feedback learning mechanism, the precision and efficiency of technological parameter optimization in the manufacturing industry are improved.

The invention discloses an SRAF graph generation method and system based on a large language model, and the method comprises the steps: carrying out the preprocessing of multi-modal sample data collected in advance, converting the sample data into word vectors which can be recognized by the large language model, the sample data comprises an SRAF graph, a target layout pattern for generating the SRAF graph and a process description in a text form; inputting the preprocessed training data into a large language model for training to obtain an SRAF generation model capable of automatically generating an SRAF graph according to the target layout pattern and the process description; and inputting the preprocessed pattern and process description of the target layout into the SRAF generation model, and automatically generating an SRAF graph of the target layout. By adopting the technical method provided by the invention, the generation efficiency of the SRAF graph can be improved.

The invention relates to the field of information management systems, and discloses an approval process intelligent information management method and device based on LLM, and the method comprises the steps: constructing an approval process description vector library; the user inputs an approval demand, and meanwhile, the approval demand is vectorized to obtain a user approval demand vector; inputting the user approval demand vector into an approval process description vector library for matching to obtain an approval process entry with the highest matching degree; and the user enters the approval process entrance with the highest matching degree, and performs approval process circulation according to a preset template. According to the invention, the intensity of the manual approval process is obviously reduced, and the approval efficiency is improved.

Automatic annotations and technical specification generation for robotic process automation (RPA) workflows using artificial intelligence (AI) is disclosed. AI / ML models may enable smart searching of workflows and automatically generate documentation for the workflows, including descriptions of each activity, input / output parameters, and overall process explanations. Annotations and documentation may be provided for an entire complex business automation that is the sum of multiple workflows and applications. A Process Definition Document (PDD) for the business process may be generated from the RPA workflow code itself when it does not exist. Other documents, such as audit documents, compliance documents required by laws or regulations, etc. may be produced. The process may be iterative, where a generative AI model automatically converts text to RPA workflow code, a runtime automation is produced from this RPA workflow, and the other documentation is generated as well.

The invention discloses an automatic inspection method suitable for a building heating and ventilation system before intelligent regulation and control input, and the method comprises the steps: carrying out the standardized definition of a connection relation and associated equipment related to the building heating and ventilation system, obtaining a standardized construction building heating and ventilation system process description language, and storing the language in a database; performing algorithm availability selection based on the building heating and ventilation system, and determining a corresponding regulation and control algorithm and input and output parameters; based on a parameter dependency relationship dynamic verification mechanism oriented to a physical link of the building heating and ventilation system, performing dependency relationship verification on the input and output parameters; and carrying out regulation and control adaptability data baseline evaluation on the input and output parameters of which the dependency relationship verification is successful, and carrying out control logic simulation and verification by calling an API (Application Program Interface). According to the method, an AI algorithm user or developer can be efficiently helped to perform full self-inspection before the algorithm is input, and the reliability before the algorithm is input is guaranteed; and meanwhile, related AI algorithm practitioners are helped to optimize algorithm engineering.

The application discloses a design method and device of a silicon optical circuit, a storage medium and an electronic device. The method comprises the following steps: obtaining an optical design file input by a user and a preset process description file, and analyzing the optical design file and the process description file to obtain design parameters of the silicon optical circuit; generating path parameters meeting a first target dimension constraint condition based on the design parameters through a pre-trained path generation network; wherein the first target dimension at least comprises a geometric dimension, an optical dimension and a process dimension; constructing a path geometric model based on the path parameters, converting the path geometric model into layout data under a target process, and generating an initial layout file of the silicon optical circuit based on the layout data; performing photoelectric consistency verification on the initial layout file, and determining a target layout file corresponding to the initial layout file based on a verification result. Through the technical scheme provided by the application, the layout and wiring of the silicon optical circuit can be optimized to meet the design requirements of the silicon optical circuit.

This application provides a method, apparatus, device, medium, and program product for developing business process software. It relates to the field of financial technology. The method includes: responding to receiving a visual orchestration topology diagram constructed by a user through a preset visual orchestration editor; generating an operation instruction set corresponding to the visual orchestration topology diagram using a preset semantic bridging compiler; constructing an intermediate description model based on the operation instruction set and generating a structured process description file; determining a target program design pattern based on the intermediate description model; and generating corresponding application code based on the target program design pattern and the structured process description file. This method allows business personnel to directly design processes through a visual interface and generate code in real time, significantly shortening development time. The code structure based on the program design pattern ensures high cohesion and low coupling, reduces human error, and is easy to extend and maintain.

This application provides a text processing method, apparatus, computer device, and readable storage medium. The method includes: acquiring business text provided by a business object for a business task, historical text associated with the business task, and a process description syntax corresponding to the business task; the process description syntax includes S process operations of a workflow; modifying the process description syntax according to the historical text to obtain a modified process description syntax corresponding to the business task; the modified process description syntax includes N process operations that can be executed after executing the process operations corresponding to the historical text; determining the modified process description syntax as prompt words; inputting the business text, historical text, and prompt words into a large language model; outputting candidate output text through the large language model; and determining the response text used to reply to the business text in the business task based on the candidate output text and associated process operations. This application can improve the reliability of text responses.

The invention provides a spacecraft fault handling flow chart construction method and device and an executable script generation method and device, and can be applied to the technical field of computers. According to the spacecraft fault disposal flow chart construction and executable script generation method and device provided by the embodiment of the invention, the fault disposal process is described by adopting the state nodes, the fault disposal process is bound in a graphical manner, the fault disposal process is visually displayed, the operation is easy, the binding correctness of the fault disposal process is conveniently checked, and the fault disposal efficiency is improved. According to the fault disposal process description method based on the structured text, a starting node serves as a starting point, an ending node serves as an ending point, a node relation network is traversed according to a connection relation, graphical nodes and the relation network are converted into a fault disposal process structured description text, and the fault disposal process description text is converted into a fault disposal program. And the spacecraft fault can be automatically handled.

The present invention discloses a method for generating processing description content based on a 3D CAD model, comprising: establishing a processing description content template database; establishing a 3D CAD model processing area vector database based on the processing description content template database; establishing 3D CAD model views according to the process and step granularity of the preset 3D CAD model; assigning the 3D CAD model views to be processed and achieved according to the process and step to form a process and step dimensioning view set; and generating a process and step process description content result by extracting model information and capturing images of the view dimensioning-associated area based on the process and step dimensioning view set, the processing description content template database, and the 3D CAD model processing area vector database. The present invention improves the efficiency of process specification compilation and enhances the standardization and consistency of process description content in process specifications.

A method, (e.g., a computer-implemented method), of generating a production plan is provided. The method includes obtaining one or more product and / or production characteristics, (e.g., a production content, a production time, and / or a production quantity, for example, in a E-BOM, M-BOM, and / or CAD file format), for a product to be manufactured. The method further includes determining, by a rule engine, based on the one or more product and / or production characteristics, one or more library elements from a plurality of library elements, wherein each library element includes one or more process descriptions relating to the characteristic. The method further includes arranging, by the rule engine, the one or more process descriptions into a production plan.

The application provides a railway system operation behavior modeling method and system based on behavior primitives and hierarchical state machines, and belongs to the technical field of railway system modeling and simulation operation. The application abstracts the railway system operation process into behavior primitive units, classifies and expresses them according to event perception, cognitive decision and intervention execution, realizes the structural decomposition and unified modeling of complex operation behaviors, upgrades the behavior expression from 'process description' to 'computable behavior unit', enhances the resolvability and modeling consistency of operation behaviors, constructs a hierarchical state machine system, realizes the cross-level state collaborative expression, establishes system-level, equipment-level and component-level hierarchical state machine models, introduces state mapping relationships, realizes the collaborative evolution expression of different granularity operation states, takes the behavior primitives as a unified triggering mechanism, realizes the cross-level state synchronous update and consistency mapping, and improves the multi-scale operation behavior modeling capability.

The present invention provides a method for automatically constructing a mathematical simulation software framework for an aircraft, belonging to the technical field of system simulation, and comprising the following steps: S1: encapsulate each discipline model and store the information in a model library; S2: read a graphical simulation process description file; S3: perform DTD constraint verification on the file; if the file is invalid, execute S13; if it is valid, execute S4; S4: parse the file; S5: connect to the model library, if the connection fails, execute S13; if the connection is successful, execute S6; S6: obtain the information parsed in S3 from the model library; S7: check whether the input and output match; S8: if the connection rules are not met, execute S13; if they are met, execute S9; S9: determine the execution order of each model; S10: generate a basic simulation program framework; S11: add call codes for model initialization functions; S12: add call codes for model running functions to obtain a mathematical simulation software, solving the problem of slow framework construction speed in the prior art.

The invention relates to the technical field of multi-party cooperative work, in particular to a multi-party cooperative process control and guidance method and device, and the method comprises the steps: compiling a script file for describing a target complex task according to a preset description model of the multi-party cooperative process; performing interpretation, task process visualization, state updating and task sequence control on the script file by utilizing a multi-party collaborative process control and guidance tool; based on a data transponder mechanism, task commands and variable settings are sent to multiple parties in related directions according to a multi-party collaborative process control and guidance tool and received collaborative requests of all parties, so that the state is updated, task progress is coordinated, and multiple parties are guided to collaboratively complete a target complex task. Therefore, the problems that an existing multi-party cooperative working method lacks real-time guidance and control on the cooperative process, has high requirements on program understanding, manual coordination and recording, is affected by programming quality and the like are solved.

The invention provides a business process self-construction and evolution method, and relates to the technical field of information technology application and business process management, and the method comprises the steps: automatically recognizing process characteristics according to a current business environment, generating process description, and constructing an executable process entity, and dynamically matching and executing required resources and a calling mode thereof in combination with a resource library and an access framework, and driving process operation and verification according to actual parameters to realize self-adaptive construction and efficient execution of a service process.

The invention provides a customer service statement generation method and device, and belongs to the technical field of natural language processing. The method comprises the steps of obtaining a preset flow description text corresponding to a target dialogue scene, wherein the preset flow description text is textualized representation of a preset flow chart; analyzing the preset flow description text, and adding mark text information corresponding to elements of a preset flow chart in the preset flow description text to obtain a structured description text; and according to the structured description text, constructing prompt information, and based on a preset question and answer model, according to the prompt information, generating a dialogue customer service statement corresponding to the target dialogue of the user. According to the embodiment of the invention, organic unification of intelligence and certainty of customer service statement generation can be realized.

This invention relates to a task allocation method, apparatus, device, medium, and program product. In this method, the historical similarity allocation gain and matching value corresponding to each task are determined based on the task execution environment description text, multiple historical task execution process description vectors, the capability parameters of each mobile device to be allocated, and the requirement parameters of each task. The task execution cost corresponding to each task is calculated based on the location and speed of each mobile device to be allocated, as well as the task location and preset basic cost of each task. A single-objective optimization model is then constructed and solved to obtain the allocation result for each mobile device to be allocated and each task. This solution, by constructing a single-objective optimization model and solving it using matching value, historical allocation gain, and task execution cost, can improve the matching degree between mobile devices and tasks.

The present invention relates to the technical field of software system modeling design, and discloses a process description and operation control method and control system in a distributed environment. The process description and operation control method comprises the following steps: S1, defining a process model: describing the process in a text format independent of the programming language, and supporting extended programming of active block models in the form of extension packages; S2, loading and running the process model: the process operation control service runs the loaded process model and monitors and controls the operation of the process through a process information list. The present invention solves the problems existing in the prior art, such as the difficulty in quickly defining processes, the low reuse of exception handling solutions, the poor scalability of process models, and the poor operational stability in a distributed environment.

A device for generating a process description for a process comprises a learning unit and a parameterization unit. The learning unit is configured to determine a process topology with a plurality of process units for implementing the process based on a process specification and based on reinforcement learning. The parameterization unit is configured to determine parameters of the process topology based on a learning-free optimization algorithm in order to obtain a parameterized process topology. The device is configured to output the process description comprising the parameterized process topology.

The invention provides a method and a system for directly running a process without installing an RPA client, and relates to the technical field of robot process automation, and the method comprises the following specific steps: S1, carrying out process analysis and preparation; s2, a process generation engine; s3, environment compatibility judgment; and S4, monitoring and managing process operation. The system comprises a process description language analysis module; a flow generation module; a dependency library management module; a code optimization and localization module; a version control and verification module; a performance monitoring and optimizing module; an exception handling and recovering module; an adaptive environment adaptation module; according to the method, technologies such as dynamic code generation, environment adaptation, performance monitoring and exception handling are combined, so that the automation efficiency and stability of the process are improved; through a recursive descent analysis method and an analysis technology based on a syntax tree, the logic judgment nodes and the dependency relationship between the nodes can be comprehensively evaluated, and a solid technical basis is provided for optimization and automation of the process.

A video of a manufacturing process, along with accompanying narration and other descriptive materials, can be used to automatically generate an application for control of the manufacturing process, or assist in a semi-automated generation of the application. As a significant advantage, a generative artificial intelligence system can support the application creation process by providing domain-specific process knowledge and no-code / low-code programming tools to convert general process descriptions into an application that is executable in the manufacturing environment for the process.

The invention discloses an automatic plan flow chart generation method based on a semi-normalized description system. According to the plan flow chart automatic generation method, through ontology constraint, automatic flow construction and a reverse generation mechanism, an automatic conversion and standardized correction process from a natural language plan to a standardized flow chart is realized. The method comprises three steps: plan flow description specification based on ontology constraint, automatic generation of a plan flow chart based on semi-standardized description, and strict plan standardization correction based on a reverse generation mechanism. According to the method, accurate description of events, conditions and skips is ensured through ontology constraints, a semi-normalized description system is utilized to automatically construct a logical relationship between the events and the conditions and generate a flow chart meeting the plan requirements, and finally, a reverse generation mechanism is adopted to convert the flow chart back to natural language expression. And a correction suggestion which does not conform to the specification description is given, so that the standardization and the consistency of the plan are ensured. According to the method, through process automatic conversion and standardized correction, the compiling efficiency of the complex system maintenance plan is improved, the readability and the executability of the emergency plan are enhanced, and the method is suitable for modern complex emergency management scenes.

The application discloses a kind of organization storage method and system of discrete industrial time series data based on production process, the method first uses production process description language to express the production process of single product, forms product production process description file.Secondly, product data template is generated according to production process description file.Then, according to product data template, each sensor data is associated with production process, and single product data block is generated.Finally, multiple product data blocks are integrated to form a data page composed of multiple product data blocks and the data page is organized and managed.In digital twin, production process decision analysis, time series prediction and anomaly detection, etc.Application scenarios, the convenience and efficiency of data processing are greatly improved.

The invention provides a costume design data processing system and method, and the method comprises the steps: firstly obtaining an original data set containing priori design data (composed of a plurality of basic style diagrams, derivative design variant diagrams and corresponding process description documents) and real-time demand corpora (composed of a plurality of user expression statements and market trend reports); performing feature extraction on the original data set to obtain a design element feature set and a demand intention feature set, inputting the design element feature set and the demand intention feature set into a pre-trained AI matching model to generate a candidate design scheme set, and performing adaptability verification processing on the candidate design scheme set based on sample case features in prior design data to obtain a scheme evaluation result; and finally, performing iterative optimization processing according to the scheme evaluation result, and generating target costume design data meeting the demand intention, thereby improving the costume design efficiency and quality, and meeting the market diversification demand.

The application relates to an intelligent agent code-free task arrangement method, system, device and medium, which comprises the following steps: receiving a natural language instruction input by a user, acquiring dynamic knowledge related to the semantic of the natural language instruction, performing a timeliness verification operation on the dynamic knowledge, and generating an instruction-knowledge association set; performing semantic analysis on the instruction-knowledge association set, extracting a core intention and a key entity, performing a task disassembly operation based on the core intention and the key entity, and generating a subtask set; based on the subtask set, matching a target intelligent agent from a pre-constructed intelligent agent capability library to obtain an intelligent agent matching result; based on the intelligent agent matching result, generating an intelligent agent collaboration process; performing a file conversion operation on the intelligent agent collaboration process to obtain a standardized process description file; and outputting the standardized process description file to a visual interface for user confirmation. The application has the effect of improving the collaborative execution efficiency of intelligent agent arrangement.

The invention discloses a cross-platform memory non-inductive instrumentation and exception isolation method, system and device suitable for a power grid industrial control system and a medium, and belongs to the technical field of network protection. The method comprises the steps that a process description structure is constructed through dynamic analysis, safety control logic is generated in a self-adaptive mode, and credibility verification is completed; establishing an access control mechanism to detect abnormal behaviors in real time; isolating illegal threads and verifying network traffic; and on the basis of transaction log execution instruction rollback and state self-healing, a security protection closed loop without service interruption is realized. The method has the beneficial effects that through a horizontal closed-loop architecture, a detection-blocking-self-healing whole process is compressed to a sub-microsecond level, and the strict real-time requirement of a relay protection 4ms period is met; second-level security updating with zero interruption of business is realized based on an instruction-level hot rollback and differential patch technology of a transaction log; through hardware-level linkage of memory security and protocol verification, an abnormal influence range is accurately controlled in a single-thread single-transaction.

The invention provides a part graph process identification processing method, which comprises the following steps: acquiring a drawing data set which comprises a plurality of graph objects and text marks; splitting the drawing data set into a first processing subset and a second processing subset; performing grouping processing on the graphic objects and the text marks in the first processing subset to obtain a plurality of grouping sets; performing attribute extraction on the grouping set to obtain a plurality of attribute feature sets; performing grouping processing on the graphic objects and the text marks in the second processing subset to obtain a plurality of different pieces of grouping information; inputting the grouping information into the attribute feature set to obtain an extraction result; performing process judgment according to the extraction result, and generating process description content; and classifying the graphic object and the text mark according to the process description content to generate a final process text.

The invention relates to the field of garment production, and discloses an intelligent process management system and method and electronic device.The system comprises a process demand conversion module, a code matching module, a data storage module, a production resource scheduling module, a risk feedback module and a man-hour quotation module. The standard and the consistency of the process description are ensured, and the manufacturing time of the process table is shortened to a certain extent. Through centralized management of information such as technical files and man-hour data, the information query efficiency is effectively improved. In addition, the equipment demand information is generated by analyzing the vehicle type field, so that the preparation in advance of the workshop is facilitated, and the rapid conversion is realized. Meanwhile, potential risks can be marked in time, new risks can be associated, response measures can be formulated in advance, and the production risk is reduced.