33 results about "Enterprise information system" patented technology

The invention provides an enterprise knowledge graph automatic construction and intelligent retrieval method, which comprises the following steps: collecting multi-source data from a heterogeneous enterprise information system, and carrying out data cleaning and standardization processing; on the basis of a comprehensive scoring mechanism of field similarity and behavior semantic vectors, entities from different systems are merged, and a standard entity set with a unique identifier is generated; based on the standard entity set, in combination with a scoring mechanism of a task-type relationship and a collaborative relationship, extracting a semantic relationship from a behavior record, and constructing an enterprise knowledge graph structure; extracting representative semantic paths from the knowledge graph structure, screening high-quality paths through a path scoring model, and organizing the high-quality paths into a structured path index set; and receiving a natural language query statement, encoding the natural language query statement into a semantic vector, matching the semantic vector with the path index set, executing query in the atlas in combination with an authority control mechanism, and returning a result.

The invention belongs to the field of artificial intelligence, and discloses a distributed data acquisition system based on multi-agent collaborative decision and a construction method, and the method comprises the steps: 1, collecting heterogeneous data of production equipment, an environment sensor, a man-machine interaction terminal and an enterprise information system in real time through the deployment of a distributed data acquisition network, cleaning, de-noising and standardizing the edge computing nodes to generate a structured data stream; 2, automatically extracting features and laws of structured data through a multi-dimensional engine analysis model, and completing semantic alignment and fusion of heterogeneous data; 3, multiple agents are adopted to form empirical data according to a deterministic strategy gradient model in combination with a multi-dimensional reward function optimization model; and step 4, performing incremental learning on the empirical data to optimize the anomaly detection model, realizing multi-dimensional information visualization display of first-line decision and center command, and deploying corresponding functional agents according to the multi-dimensional information. The problems that a multi-agent system is low in control precision and low in efficiency are solved.

The invention discloses an enterprise risk clue generation method and device, and the method comprises the steps: obtaining related feature data of an enterprise information system, inputting the related feature data into a trained risk clue prediction model, and outputting a risk clue prediction result of an enterprise; explaining the output risk clue prediction result through an SHAP method, and determining the contribution degree; and utilizing a causal forest model to predict the risk clues of the enterprise according to the related feature data and the corresponding contribution degrees, and obtaining an average value of output results of all the causal trees in the causal forest model as a final enterprise risk clue prediction result. Retrieving in an RAG knowledge database to obtain a corresponding text information retrieval result, and generating corresponding prompt word information; and inputting the prompt word information into the large language model to generate an answer to the enterprise risk clue. According to the invention, the accuracy and interpretability of risk clue prediction can be improved.

The invention provides a large model context protocol implementation system and method based on an enterprise bus, belongs to the technical field of enterprise information system integration, and aims to solve the problems of non-uniform protocols, lack of context management, insufficient service governance and the like in large model integration. The system comprises an MCP protocol adaptation layer used for converting internal and external protocols; the unified service management module is used for service discovery and intelligent routing; the context management module is used for recovering and persisting the context before and after calling the service to realize stateful interaction; and the enterprise resource access module is used for packaging the knowledge base and the data center into standard services. The method comprises the steps of protocol conversion, context recovery, service routing, target service calling, context persistence, response conversion and the like. Uniform integration and stateful management of large models are realized, and a channel between the models and enterprise private knowledge data is opened.

The invention discloses a multi-source heterogeneous data fusion method based on dynamic loading. The multi-source heterogeneous data fusion method is applied to the field of data fusion integration of different data sources and different structures. The method comprises the following steps: (1) constructing a reliable data acquisition layer comprising a main data platform, a unified data integration interface service realized based on message middleware, and an integrated log management module; (2) in a data loading and data processing stage, cleaning and integrating data by adopting dynamic fragmentation and streaming processing, and constructing a multi-level authority control function based on role and data attribute matching and a full-process data transmission and storage encryption and decryption function based on an annotation technology aiming at a data security problem; and (3) constructing a user-defined data display layer. The method mainly solves the problems that data transmission is unreliable, authority control is dispersed and granularity is inconsistent in data processing, and dynamic data cannot be displayed in a user-defined mode, and an effective method is provided for full-process data fusion of a discrete manufacturing enterprise information system.

The invention discloses an MCP data acquisition system and method for autonomously arranging and self-correcting calling of a target system interface API based on a large language model, and belongs to the technical field of enterprise information system integration and intelligent data processing. The method comprises the following steps of: firstly, automatically acquiring an API (Application Program Interface) document, interface parameters and authentication requirements of a target system, performing semantic analysis on structured and unstructured contents in the document, and extracting interface fields, parameter types, response structures and error code information; then, based on a document analysis result and actual interface calling feedback, API semantic inversion and dependency relation recognition are executed, and the field purpose, the parameter input and output relation, a paging mechanism and an interface calling link are automatically deduced. According to the method, the heterogeneous API interface document can be automatically analyzed, the calling chain can be automatically generated, self-error correction and self-adaptive optimization can be realized in the calling process, the API docking cost can be greatly reduced, and the stability and the automation degree of interface calling are improved. Meanwhile, multi-source data from an energy system, a logistics system and a supply chain system can be subjected to semantic recognition and automatic mapping, the requirements for data collection and standardization in the first range, the second range and the third range of carbon emission are met, and end-to-end automatic integration and processing of carbon emission data are achieved. The method has high universality, strong robustness and continuous evolution capability, and is suitable for various business scenes such as enterprise carbon accounting, cross-system intelligent data integration, system API management and automatic operation and maintenance.

The invention provides an abnormal risk dynamic identification method for park enterprise multi-source heterogeneous operation data, and relates to the technical field of enterprise risk management and equipment state monitoring, and the method comprises the steps: collecting battery pack multi-mode sensing data and heterogeneous operation data in real time through an optical fiber sensor network and an enterprise information system; carrying out cleaning, fusion and normalization preprocessing on the data; calculating a battery health index based on the sensing data, and calculating a dynamic operation risk score in combination with the operation data; identifying an abnormal risk by monitoring score change in real time; and finally, triggering an alarm, adjusting operation parameters or starting active protection measures such as an emergency process. According to the method, deep fusion analysis of the physical equipment state and the enterprise operation data is realized, the defects of lagging and isolation of traditional risk identification are overcome, and the real-time performance, accuracy and initiative of risk management of enterprises in the park are remarkably improved.

This application relates to the technical field of network and information security, and discloses an account security inspection system based on the RDP protocol. It uses the WinRM protocol as the core remote execution protocol, while also supporting the RDP protocol as an alternative connection method, enabling agentless remote management of Windows hosts. The system employs a multi-dimensional security inspection module covering more than 20 security checks, including password policies, account locking, user permissions, and login auditing. It supports all versions of Windows Server 2008 to 2022 through a cross-distribution compatibility mechanism. It utilizes a dynamic load-aware concurrent inspection engine to process log analysis and embedded account scanning tasks in parallel, and automatically identifies abnormal changes to account information through baseline comparison with integrity protection and a permission change awareness module. This invention requires no software deployment on the target host, is non-intrusive to the production environment, and can efficiently complete account security checks on large-scale Windows assets, significantly improving the account security protection capabilities of enterprise information systems.

Apparatus and methods for providing a co-browsing session between an artificial intelligence (“AI”)-equipped customer assistance digital robot (“bot”) and a user of an enterprise information system portal. The methods may include receiving, by the bot, on a first channel that is accessible by the user from the portal, from the user, performing an operation on a working web page. The working web page may be accessible by the user via the portal from a second channel. The second channel may be accessible by the user from the portal. The second channel may be different from the first channel. The second channel may be in communication with a user-activity monitor. The user-activity monitor may be configured to collect and serve user-activity data. The bot may be a bot that does not have permission to access the user-activity monitor.

The invention discloses a big model driven information intelligent recommendation system based on RAG, and relates to the technical field of artificial intelligence and information recommendation. The system comprises a state judgment module, a portrait heat preservation module, a recommendation curve generation module, a sensitive curve generation module, an RAG recommendation module and a portrait updating module. Firstly, user multi-dimensional behavior data is collected in a preset monitoring period, a silence judgment index is calculated to identify different types of silent users, a heat preservation portrait is generated according to the silence type and the silence level, and a recommendation curve is constructed in a reactivation time period; generating and dynamically adjusting a sensitive curve by combining external influence parameters and real-time interaction data; and the RAG recommendation module generates an information weight vector according to the sensitive curve to realize retrieval and content generation of semantic related information. According to the method, the personalized recommendation and question and answer ability can be quickly recovered when the silent user is reactivated, and the recommendation timeliness and the intelligent level of a government and enterprise information system are improved.

The invention belongs to the technical field of informatization and intelligent manufacturing of ferrous metallurgy enterprises, and discloses a dynamic value optimization and self-adaptive disposal system and method for steel and iron material excess materials, and the method comprises the steps: obtaining steel and iron material excess material data and steel and iron material related data from an enterprise information system database, and carrying out the data integration processing; according to a data integration processing result, carrying out size changing scheme matching on the steel and iron material remainder, and obtaining a size changing benefit value of a size changing scheme based on an economic benefit measurement and calculation model; setting a target benefit value and a target library age of the steel and iron material remainder, acquiring the current library age of the steel and iron material remainder, performing dual threshold decision logic judgment in combination with the scale change benefit value, generating system recommendation, performing final selection of a scale change scheme in combination with manual reexamination, acquiring a scale change execution instruction, and issuing the scale change execution instruction to an execution system; according to the method, dual threshold decision logic judgment is carried out on the residual materials, the dynamic value of the residual materials can be optimized, and the residual materials can be subjected to rapid and accurate size changing treatment.

The invention belongs to the technical field of industrial policy information processing, and discloses an industrial policy information consultation method and system based on big data, and the method comprises the steps: collecting data of a government information platform, an industry database and an enterprise information system, and adding a version number, a timestamp, an industrial label and an effectiveness state to policy data; analyzing the policy text, extracting application conditions, support measures and limiting terms, establishing a mutual exclusion relationship, an aging relationship and an application domain relationship, and constructing policy, industry and enterprise evolution models; calculating risk indexes such as coverage, duration and conflict degree in combination with industrial data and enterprise declaration information; and docking the enterprise portrait with the evolution model, calculating a matching result based on applicability, availability and compliance factors, and outputting a rectification item or generating a consultation report. The system is composed of a data processing device, an analysis and modeling engine and a consultation delivery unit, and policy data dynamic management and traceable consultation can be achieved.

This invention provides a food inspection method, equipment, and medium based on industrial big data. By deploying sensors on the production line and the enterprise information system, it collects and stores multi-source industrial big data in real time. The collected multi-source industrial big data is preprocessed, and a deep autoencoder model is trained using historical normal batch datasets to determine the dynamic reconstruction error threshold for food quality characteristics. During online detection, the real-time data stream is input into the deep autoencoder model to calculate the reconstruction error. If the error exceeds the threshold, an early warning is triggered, and the feature variable with the highest contribution rate is located. Using the located feature variable with the highest contribution rate, combined with association rule mining, suspicious risk sources are output. This invention achieves reduced false alarm rates and improved detection sensitivity by generating a dedicated dynamic threshold, locating abnormal contribution rates, and then combining association rule mining to trace risk sources, thus achieving closed-loop real-time quality control from early warning triggering to risk source output.

The present application provides an enterprise knowledge graph automatic construction and intelligent retrieval method, the method comprises the following steps: collecting multi-source data from heterogeneous enterprise information systems, performing data cleaning and standardization processing; and based on the comprehensive scoring mechanism of field similarity and behavior semantic vector, merging the entities from different systems to generate a standard entity set with unique identification; based on the standard entity set, combining the scoring mechanism of task-type relationship and collaborative relationship, extracting semantic relationship from behavior records to construct enterprise knowledge graph structure; extracting representative semantic paths from the knowledge graph structure, screening high-quality paths through a path scoring model, and organizing them into a structured path index set; receiving a natural language query sentence, encoding the natural language query sentence into a semantic vector, matching it with the path index set, and executing a query in the graph and returning the result in combination with the permission control mechanism.

The invention discloses a full-process logistics management system which is characterized by comprising a control system, an intelligent warehouse, an RGV trolley, an AGV trolley and a trolley control module, the trolley control module is used for controlling operation of the RGV trolley and the AGV trolley, and the control system is used for calculating and processing material distribution in the intelligent warehouse and sending an operation command to the trolley control module. The control system is integrated with an enterprise information system to realize sharing of production information, the RGV is used for carrying materials in the intelligent warehouse, and the AGV is used for carrying materials between the intelligent warehouse and an enterprise production line; the logistics management system has the advantages that the time of materials in the storage and transportation process is greatly shortened, and the efficiency and accuracy of logistics management are improved; and the control system and the enterprise information system are integrated, so that links such as production planning and material purchasing can be more closely coordinated, the collaboration and planning of production and logistics are improved, and the production efficiency is further improved.

The invention relates to the field of enterprise transformation decision-making auxiliary systems, in particular to an enterprise digital transformation decision-making auxiliary system based on an AI (artificial intelligence) agent, which is characterized in that a multi-source data acquisition module is used for acquiring data from an enterprise internal information system and an external environment data source and performing characterization processing; the industry knowledge graph construction module is used for constructing an enterprise digital knowledge graph based on the collected data and an industry model, and realizing association retrieval among enterprises, policies, technologies and indexes; the AI agent decision engine module comprises a plurality of AI agents which operate cooperatively, and performs calculation reasoning through a reinforcement learning algorithm and large language model reasoning. According to the invention, the problems of enterprise data splitting and insufficient decision basis are solved through multi-source data integration and AI agent collaborative reasoning, the system can generate personalized transformation schemes and policy matching suggestions to improve the feasibility of decision, and the system can optimize the effect according to the implementation effect, so that the decision-making efficiency is improved. And the reliability of the system scheme effect is continuously enhanced.

The invention belongs to the technical field of log analysis and intelligent operation and maintenance, and discloses a rare earth industry-oriented mass log data intelligent association analysis method and system. Aiming at the problems that traditional log analysis depends on manpower, the efficiency is low and cross-system association is difficult to discover, heterogeneous log data generated by multiple systems are converged, and a mode self-learning algorithm is adopted to automatically identify a log format and extract structured information; performing association mining on the log events based on time sequence co-occurrence analysis and semantic similarity analysis; and constructing a log event association graph, and automatically locking a fault source from massive association events by adopting a causal reasoning algorithm. According to the method, the fault positioning time is shortened from the hour level to the minute level, the root cause locking accuracy is 95% or above, and the method is suitable for operation and maintenance monitoring and fault diagnosis scenes of a rare earth enterprise informatization system.

This invention belongs to the field of information security technology and provides a security risk assessment platform for enterprise information systems based on big data analysis. The platform includes collecting visitor access behavior characteristic data of asset nodes in the enterprise information system; then, quantifying the probability of security damage based on the degree of abnormality of the access behavior, and integrating multi-dimensional behavioral characteristics to generate a comprehensive probability of damage to the asset node by the visitor; based on this, aggregating the probability of damage to the same asset node by all visitors to generate a comprehensive probability of damage and a comprehensive risk score for that asset node; finally, weighted fusion of the risk scores of each asset node to obtain the overall security risk score of the enterprise information system, completing the risk assessment. This invention achieves quantitative assessment of security risks of enterprise information systems, improves the objectivity and accuracy of risk assessment, quantifies visitor behavior risks and establishes a probability model, reduces subjective reliance, and thus more effectively identifies and responds to security threats.

The invention discloses a multi-system fused wooden door manufacturing enterprise information system integration architecture and method, which adopts a layered loose coupling design, and comprises an enterprise operation layer which comprises an enterprise resource planning system for order and financial management and a product life cycle management system for product model and process management; the planning and scheduling layer comprises an advanced planning and scheduling system which serves as a planning decision center and carries out limited productivity simulation and optimized scheduling based on multi-source real-time data, and the manufacturing operation layer comprises a manufacturing execution system used for production execution and monitoring and a warehouse management system used for fine management of materials. By constructing a unified data model, adopting an event-driven loose coupling collaboration mechanism and establishing a middle platform for converging real-time manufacturing data, full-process digital communication and intelligent linkage from customer orders, product design, material supply, intelligent scheduling, manufacturing execution to warehouse logistics are realized.

A business linkage processing method and apparatus for an enterprise information system, a computer program product, and a readable storage medium, the business linkage processing method comprising: receiving configuration information, the configuration information being used for establishing a custom association field associated with a second business object for a first business object; in response to a preset first linkage triggering condition, packaging a first event message containing the state data of the first business object, and sending the first event message to the asynchronous communication medium; in response to the situation that a first event message in the asynchronous communication medium is monitored and grabbed, triggering and executing a second business object based on the user-defined associated field; wherein the packaging and sending of the first event message and the monitoring and capturing of the first event message are executed asynchronously. By adopting the scheme, the association relationship between the business objects is configurable, the linkage rule between different business modules can be defined without modifying a program code, and the flexibility and maintainability of the system are improved.

The application discloses a processing method and device of a system element, a program product and an electronic device, relates to the technical field of artificial intelligence, and the method comprises the following steps: performing semantic coding on standard words in a standard dictionary to obtain standard vectors, and constructing a standard vector knowledge base based on the standard vectors and standard word information corresponding to each standard word; performing semantic coding on original elements in an information system; inputting the original vectors obtained through coding into the standard vector knowledge base for semantic matching; performing compliance verification on the original elements based on M similar standard words obtained through matching, wherein the compliance verification comprises at least one of name semantic sub-verification, description text semantic sub-verification, enumerated value semantic sub-verification and enumerated value sequence sub-verification; in the case that the original elements are not compliant, generating a rectification scheme of the original elements based on the compliance verification result, and processing the original elements based on the rectification scheme. The application solves the technical problem of non-standard element setting in an enterprise information system.

The invention provides a label generation method and device and a medium, and relates to the field of data processing. The method comprises the following steps: acquiring unstructured text data in an enterprise information system, wherein the unstructured text data is a natural language text which is not formatted; performing context analysis on the unstructured text data by utilizing a large language model to generate an initial label set; and processing the initial label set based on a preset rule to form a cross-hierarchy label structure, the cross-hierarchy label structure comprising at least two label layers with different semantic dimensions, and establishing an association relationship network between the label layers. According to the invention, the hysteresis of label updating is reduced.

The invention discloses an intelligent data retrieval method based on a large language model. The method comprises the steps that the model receives an input data retrieval instruction described by a user in a natural language mode through an input side; the statement component is recognized, data content needing to be retrieved by the user is obtained according to the data retrieval statement component, and report type data needing to be generated is obtained according to the data content needing to be retrieved by the user; identifying the statement according to the data retrieval instruction to perform word segmentation, classifying each vocabulary, and obtaining report content data needing to be generated according to the classified vocabulary; constructing a grammatical structure of an SQL retrieval statement according to the report type data and the report content data; generating an SQL code according to the constructed grammatical structure of the SQL retrieval statement; calling operation data and business basic data required by a report in an enterprise information system database according to the SQL code; and calling operation data and business basic data required by the report according to the SQL code to generate a data report, and displaying the data report on an output side.

The application provides a heterogeneous financial system data conversion and interfacing method and device, relates to the technical field of enterprise information system integration, and comprises the following steps: generating a push context according to a voucher push request of a business system, wherein the push context at least contains a target financial system identifier, a voucher category and business data; matching a target adapter from an adapter set according to the push context, wherein the adapters all provide a unified interface contract, and are defined with data conversion, data push and result recording operations; executing a data conversion operation of the target adapter, converting the business data into an interface data object, and mapping a business code into a system code according to a hierarchical matching rule; executing a data push operation, and sending the interface data object to a target financial system interface; and receiving a response result and executing a result recording operation. The application solves the problems of high code coupling degree, poor expansibility and low code reuse rate caused by directly calling different financial system interfaces in the prior art.

The application relates to the technical field of operation and maintenance management, in particular to a big data-based information system comprehensive operation and maintenance management platform method and system, which comprises the following steps: collecting system operation data of a specified enterprise information system in real time, storing and preprocessing the system operation data, and outputting a system operation data set; performing time axis calibration and fusion processing on the system operation data set, and outputting a multidimensional correlation data set; establishing a dynamic correlation model based on the multidimensional correlation data set, monitoring abnormal conditions in real time, and outputting an early warning level; matching a candidate treatment scheme set based on the early warning level; selecting an optimal treatment scheme from the candidate treatment scheme set based on a preset screening rule and executing the optimal treatment scheme; and outputting an execution effect evaluation result of the optimal treatment scheme and feeding back the execution effect evaluation result to a preset big data platform. The application has the advantages of real-time discovery of equipment hidden dangers and automatic selection of optimal solution effects.

This invention belongs to the field of enterprise information technology and discloses a method and system for rapid deployment of enterprise information systems based on a no-code platform. The method includes the following steps: constructing a business data analysis model and a rapid deployment scheme generation model, and connecting them to the no-code platform; performing business data analysis using the business data analysis model based on real-time business data; generating a rapid deployment scheme using the rapid deployment scheme generation model based on the real-time business data analysis results and real-time business management needs; deploying the enterprise's business management system by calling pre-built templates and components of the no-code platform according to the real-time rapid deployment scheme, and visualizing the deployment; and connecting the enterprise server to the no-code platform, downloading metadata, and building the system. This invention solves the problems of long deployment cycles, high costs, poor flexibility, low customization, and insufficient data utilization in existing technologies.

This invention relates to the field of data transmission technology, specifically a data transmission analysis and processing method for an information system in a construction enterprise. The method includes: recording the total number of transmissions, the number of transmission failures, and the lock period for transmission failures during the current transmission task execution; determining the task execution status of the transmission task during data anomalies; applying multi-objective constraints to the current transmission task, calculating the data increment of the transmission task under these constraints, sorting the transmission tasks according to the data increment, and generating a task queue corresponding to each transmission task; performing correlation analysis between the transmission tasks and the receiving system based on the task queues, calculating the adjustment ratio of each transmission task during queuing transmission; optimizing batch division based on the adjustment ratio of transmission tasks in each batch, setting hierarchical response actions corresponding to the distribution of each batch, and adjusting the queue data volume of transmission tasks in each batch; thus achieving both efficiency and stability in data uploading.

The invention discloses a multi-dimensional information interaction method, and relates to the technical field of enterprise information system integration and data processing, and relates to an enterprise information system including sales management, purchase management, warehouse management, production management and financial management, and the method is characterized in that the method comprises the following steps: responding to a business operation in any business module; and generating a structured service event, wherein the structured service event is packaged with service data, an event type and a related service entity identifier. According to the multi-dimensional information interaction method, by constructing a unified event flow platform and an intelligent routing collaboration mechanism, information integration and flow communication across multiple service modules such as sales, purchase, warehouses, production and finance are realized. According to the method, discrete business operation is converted into a standardized structured event, and intelligent routing decision is performed based on a dynamic rule and a real-time state, so that an information island in an enterprise information system is effectively broken, and the efficiency of cross-department business collaboration and the continuity of overall operation are improved.

The invention relates to the technical field of management platform systems, and particularly discloses a new energy project multi-party cooperation digital management platform system, which comprises an intelligent coding data center module, a quantization calculation engine module, a block chain cooperation bus module and a meta universe decision support module. An informatization system is regarded as a single system formed by a plurality of interactively communicated subsystems, so that the enterprise informatization system forms an organic whole which is closely connected from top to bottom; the project department can complete project-related work in the platform, the management layer completes an approval process, and the leader layer can quickly query information of a plurality of projects and carry out comparative analysis, so that powerful data support is provided for decision making, standardization, refinement, intelligence and collaboration of project management are realized, and the project management efficiency is improved. And the efficiency, quality and risk control capability of new energy project management are comprehensively improved.

AI-Powered User Interface for Intelligent Data Access Control and Breach Detection in Enterprise Information Systems