136 results about "Enterprise system" patented technology

The invention discloses an intelligent agent platform and information system integration compatible method and equipment, belongs to the technical field of digital transformation, and aims to overcome the defects of high cost, long development period, difficulty in maintenance and the like of an existing intelligent agent platform and information system integration scheme. And dynamic upgrading of an enterprise system and access of a new system are difficult to adapt. The method comprises the following steps: constructing dynamic protocol conversion middleware supporting multiple protocols, and converting heterogeneous protocol data through the dynamic protocol conversion middleware to obtain standardized data; performing format conversion on the standardized data through a hierarchical data converter to obtain readable data; respectively transmitting the high-frequency calling data and the low-frequency calling data to an intelligent agent platform through a hybrid communication bus; wherein enterprise sensitive data in the readable data is transmitted to the intelligent agent platform in a token form after being subjected to desensitization operation and / or encryption operation.

The invention relates to the technical field of information security, in particular to a cluster self-discovery method suitable for a cloud server cipher machine, which comprises the following steps: when physical equipment of the cloud server cipher machine leaves a factory, a certificate management module generates an equipment certificate and a root CA certificate in combination with an enterprise CA system, and stores the equipment certificate and the root CA certificate; after the virtual cipher machine is created and started, the key management service module combines with the certificate management module to generate a virtual machine certificate, and stores the virtual machine certificate, the storage device certificate and the root CA certificate together; the cluster management service module enables the master node of the virtual cipher machine to discover the slave node of the virtual cipher machine in the same network domain through UDP broadcast, and executes three-level verification on the slave node of the virtual cipher machine from three aspects of an equipment certificate, a virtual machine certificate and an authentication signature; and the virtual cipher machine master node synchronizes the cluster master key to the virtual cipher machine slave node passing verification. According to the invention, hierarchical identity isolation and verification of the cloud server cipher machine host and the virtual cipher machine can be realized, and the security of cluster self-discovery and authentication stages is ensured.

A system and method for generating a guidance path for automated navigation of large agricultural equipment. Vehicle path data from leading vehicles can be recorded, stored or inputted into the system for generation of guidance paths offset from the swaths traversed by the leading vehicle. Combines, planters sprayers and other vehicles utilizing guidance system can be used to record leading vehicle data for use by the following vehicle in real time or in subsequent cycles. Enterprise systems can manage multiple grain carts and / or combines or other vehicles to maximize efficiency.

At least one non-transitory computer readable media storing instructions that, when executed by one or more hardware processors, causes performance of operations. The operations include receiving a natural language query defining a policy for a workflow. The operations also include retrieving supplementary information relevant to at least one of the workflow and the natural language query, wherein the supplementary information includes at least one code fragment. The operations further include building an input prompt for a large language model. The input prompt includes the natural language query and the supplementary information, and the input prompt directs the large language model to generate, based at least in part on the at least one code fragment, code that is executable to implement the policy for the workflow.

The invention relates to the technical field of ERP financial risk assessment, and discloses an ERP financial data risk assessment method based on machine learning. The method comprises the steps of obtaining multi-dimensional historical financial data in a target enterprise ERP system, and performing preprocessing to generate a standardized financial data set associated with a timestamp and a financial index type label; constructing a dynamic feature extraction network, and extracting time sequence correlation features and cross-dimension coupling features from the dynamic feature extraction network according to tags; initializing a risk assessment model containing a parallel anomaly detection branch and a trend prediction branch, wherein the two branches respectively receive corresponding features; iteratively optimizing the model by adopting a hierarchical adversarial training strategy until two branch outputs meet an error convergence condition; and inputting real-time ERP financial data, and generating an evaluation report containing a risk level mark and a confidence score. The method adapts to ERP financial data characteristics through cooperation of multi-dimensional feature extraction and a double-branch model, and can be effectively used for enterprise financial risk management and control.

The invention discloses an intelligent accounting and analysis system for enterprise operation cost and expense, and relates to the technical field of intelligent accounting and analysis of enterprise operation, comprising a data preprocessing module used for obtaining original cost data from an enterprise ERP system, a financial system and a production management system, performing cleaning, field mapping and time sequence alignment operations on the original cost data, and outputting a structured unified data set; the deviation decomposition module is used for dividing a total cost deviation into four types of components, namely a usage difference, a price difference, an efficiency deviation and a structure migration deviation, based on a budget value and an actual value in the structured unified data set, performing attribution analysis according to a department, a product line or a project dimension, and outputting deviation detail data; and the weight calculation module is used for generating a dynamic weight vector according to the historical fluctuation characteristics of each cost item in the deviation detail data and the business association strength of the cost item in the enterprise operation in combination with an external market change signal.

The invention relates to the technical field of artificial intelligence, in particular to a hierarchical tree and auto-reflection-based retrieval enhancement generation method, device and medium, the method comprises: constructing a multi-layer tree structure knowledge base, the knowledge base comprising a plurality of tree index structures constructed based on text similarity, enterprise organization architecture and level architecture; receiving user query and user identity information; generating a plurality of sub-queries corresponding to different retrieval intentions based on the user query and the user identity information; performing multi-path retrieval on each sub-query in the corresponding tree index structure to obtain a related knowledge fragment set; and based on an auto-reflection mechanism, a final answer is generated, and knowledge traceability is realized at the same time. According to the method, the problems of low knowledge base quality, poor retrieval result correlation and single retrieval path in the traditional RAG technology are solved, and the accuracy, correlation and interpretability of enterprise system questions and answers are remarkably improved.

The invention relates to the technical field of system compliance management, and discloses a system compliance early warning method and system, electronic equipment and a storage medium, and the method comprises the steps: collecting system file data, and carrying out the standardization processing and structural analysis; data preparation is carried out based on the system metadatabase and the supervision fine tuning corpus set, an initial model is constructed and trained, a trained system large model is formed, and version management is carried out; determining early warning types, establishing a system revision early warning model for different early warning types, and triggering early warning reminding according to an output result of the early warning model; performing difference comparative analysis on the same-theme systems based on the system large model, and generating a compliance inspection report; receiving a natural language question, generating an answer and providing system traceability information; a system outline is generated according to system revision requirements, a chapter summary and clause content are generated based on the system outline, and real-time compliance check and clause recommendation are supported. According to the invention, the intelligent demand of enterprise system full-life-cycle management can be met.

Disclosed are systems and methods for detecting a vulnerability across programs of an enterprise system and automatically mitigating the vulnerability. The systems and methods utilize artificial intelligence (“AI”) systems to process data received from a particular network, such as systems data, software data, and software configuration data. The AI systems processes the software data and software configuration data and compares the data to known vulnerabilities stored to a database. The system maps the vulnerabilities to attack signatures. When a vulnerability is identified within the network, the AI systems run classification analysis and categorization analysis to determine the probability a vulnerability is a known vulnerability and the category of software it relates to. The system self-executes a rule that enables the attack signatures to protect against the identified vulnerability by either removing or patching.

The invention relates to an agent generation method and system for enterprise process automation. The method comprises the following steps: S1, obtaining a standard specification document of an enterprise; s2, knowledge extraction and knowledge graph construction; s3, semantic analysis and intention discrimination; and S4, process reasoning and automatic execution. According to the method, full-link intellectualization from enterprise system document automatic analysis to business process closed-loop execution is realized, context sensing and dynamic adaptation capabilities are realized, multiple types of tasks are supported, the analysis fine granularity and cross-system cooperation efficiency of business process rules are effectively improved, and high universality and expandability are realized.

Disclosed are systems and methods for detecting a vulnerability across programs of an enterprise system and notifying remediation agent. The systems and methods utilize artificial intelligence (“AI”) systems to process data received from a particular network, such as systems, software, and software configuration data. The AI systems processes the software and software configuration data and compares the data to known vulnerabilities stored to a database. The system maps the vulnerabilities to attack signatures. When a vulnerability is identified within the network, the AI systems run classification analysis and categorization analysis to determine the probability a vulnerability is a known vulnerability and the category of software it relates to. The AI systems then runs a remediation agent analysis to determine the proper remediation agent to mitigate the vulnerability. Once a remediation agent is determined, a remediation agent is notified of the vulnerability and mitigates the vulnerability by removing or patching.

The invention discloses a dynamic self-verification method based on service flow-test flow homologous heterogeneous execution. The method comprises the following steps: uniformly describing service logic and a corresponding interface test contract through a strong type of domain specific language (DSL); the method comprises the following steps: simultaneously compiling homologous DSL descriptions into stateful business workflows executed by a process engine and stateless and combinable atomic test contract sets called by a test executor by utilizing a double-path compiling engine; during operation, loose coupling synchronous triggering and execution of a service flow and a test flow are realized based on a high-throughput event bus, and real-time and high-fidelity contract verification, performance monitoring and chaos probe testing are performed on cross-system interface calling in a production environment. According to the invention, the traditional post-event and off-line integration test is converted into the in-event, on-line and continuous system endogenous capability, and the industrial problems that the complex enterprise system group integration test is difficult and the operation and maintenance monitoring is passive are effectively solved.

The invention relates to the technical field of ISO authentication, and provides an ISO system service authentication process method. Comprising the following steps: constructing an enterprise system association analysis model based on a graph neural network, establishing an authentication strategy optimization mechanism based on reinforcement learning, designing a cross-modal fusion intelligent auditing system, constructing an industry authentication knowledge sharing platform based on federated learning, and implementing a continuous compliance monitoring system based on digital twinning. The method is supported by various frontier artificial intelligence technologies, systematically solves the core problems of low efficiency, inaccurate risk identification, insufficient privacy protection, limited knowledge sharing and the like in the traditional ISO system authentication, and greatly improves the intelligent level and management effect of the authentication process.

Described herein are methods and systems for optimizing the retrieval of data from multiple different destination software applications or systems comprising a planner module, a navigator module, an executor module, and a response generator module, which together divide natural language queries of users into manageable sub-tasks using a large language learning model (LLM), convert sub-tasks into computer executable sub-tasks involving LLM-generated code, extract relevant data from destination software systems, and return a natural language result to the user utilizing an LLM. The methods and systems also include internal verifications and user feedback-implemented output modifications.

Techniques for operating a chatbot system for enterprise-level conversational agents are disclosed. These techniques are performed by an application or cloud service executing on one or more computing devices. An enterprise system can deploy conversational agents onto user devices to run as chat interfaces for logging analytics question-answering. One example application or cloud service may be a multi-model chat mechanism configured to support these chat interfaces with backend functionality. In response to an incoming question, the chat mechanism first consolidates the question with any conversation history and then, classifies the user's question as either a question regarding unstructured document data, a question regarding structured log data, or a hybrid question. Based on the classification, the chat mechanism can generate a proper large language model (LLM) response.

The invention discloses an AI virtual employee system based on multi-modal deep learning and an implementation method. The system comprises a multi-modal fusion processing module, which is used for carrying out cross-modal fusion processing on multi-modal input data input by a user by adopting a multi-head attention mechanism of a Transform architecture; the role customization engine constructs AI employee roles according to specific post requirements of the user; the knowledge graph construction module is used for constructing structured knowledge representation of professional knowledge of the construction industry; the task understanding and planning module is used for analyzing user requirements and making an execution plan for an AI employee role according to the fused multi-modal data and the structured knowledge representation of the professional knowledge of the construction industry; the main execution controller is used for the AI employee role to coordinate each function module to complete a specific task according to the execution plan; the enterprise system integration interface is used for carrying out data interaction and function calling with an enterprise core system; and the result output module is used for outputting an execution result of the execution plan.

A business management system with integrated business intelligence and IT-supported optimization, consisting of: a computer device comprising at least one processor and a memory arrangement for storing executable instructions; a data acquisition and integration unit that is operationally connected to the at least one processor and is configured to receive heterogeneous enterprise data from a variety of source systems, including financial transaction systems, operational control systems, human resource information systems, supply chain systems, customer interaction systems, and IT infrastructure monitoring systems, wherein the data acquisition and integration unit is further configured to normalize syntactic formats, resolve temporal inconsistencies, and map source-specific attributes into a unified enterprise data representation stored in the storage system; a business intelligence processing unit that is operationally coupled with the data acquisition and integration unit and is configured to calculate business performance indicators through multidimensional aggregation, correlation analysis, and trend extraction over the unified business data representation, with the calculated business performance indicators being time-stamped and permanently stored; an optimization unit that is operationally coupled with the business intelligence processing unit and is configured to compare the calculated business performance indicators with stored business objectives and constraints and to determine optimized business control parameters that correspond to resource allocation, operational planning, cost efficiency or performance improvement; a control and orchestration unit that is operationally linked to the data acquisition and integration unit, the business intelligence processing unit, and the optimization unit, wherein the control and orchestration unit is configured to coordinate the execution sequence, forward the results of the business intelligence analysis to the optimization unit, and manage feedback by incorporating the effects of applied optimized business control parameters into subsequent data acquisition cycles; and a communication interface that is connected to at least one processor and configured to exchange data and control signals with external enterprise systems and user terminals.

The present application relates to a system and method whereby an enterprise system can identify items within an image and recommend similar enterprise products to a consumer. In some examples, such a system may include an object detection component trained on a known dataset, which may be used to identify objects / items in an image. Cropped items of interest may be extracted from the image. The system may include an image embedding and category prediction component, which may generate embedding vectors and predict category information for the cropped images. A visual similarity search component, which may reference embeddings for product images to identify products which are visually similar to the items identified from the image. An attribute-based ranking process may be applied to rank the top recommended items obtained from the visual similarity search component. A final ordering of recommended items may then be provided to a consumer.

The application provides an automobile IBC product offline appearance identification detection system and method, and relates to the technical field of automobile part detection. The system comprises: a feeding vision module for identifying the placement posture of the IBC product to be detected on the conveying line and outputting posture data; a mechanical hand module for grabbing the product according to the posture data and transferring it to a detection station; a rotary table module arranged at the detection station for fixing and rotating the product; a vision detection module for scanning the surface of the product during rotation, acquiring three-dimensional image data, and performing defect detection and classification based on the three-dimensional image data; a data tracing module in communication with a central control system and an enterprise MES system for binding the unique identification of the product and the detection data; and the central control system for coordinating the operation of each module and controlling the mechanical hand module to perform a sorting and stacking operation corresponding to the result according to the result of defect detection and classification. Full automation and full coverage of the detection process are realized.

The invention provides a multi-agent business method for purchase contract comprehensive review based on a large language model. The method comprises the following steps: acquiring a contract to be reviewed; performing general review on the to-be-reviewed contract, calling the large language model to generate a contract summary according to the key business information of the to-be-reviewed contract, calling the text compliance requirement library to perform standard recognition on the contract text of the to-be-reviewed contract, and generating a first review conclusion; performing special review on the contract to be reviewed, calling the large language model, reviewing whether terms of the contract to be reviewed conform to legal compliance review and / or enterprise system based on a legal library and / or a system library, and generating a second review conclusion; performing risk assessment on suppliers involved in the contract to be audited, and generating a third review conclusion; and combining the first review conclusion, the second review conclusion and the third review conclusion to generate a final contract review report, wherein the contract review report comprises review suggestions and modification suggestions for each contract term.

This invention provides secure remote access for digital engineering. Industrial Information Centers (IIHs) and Industrial Development Centers (IDHs) serve as industrial ecosystem platforms where multiple participants can deliver repeatable and standardized services relevant to their core competencies. At the heart of the IIH system is a development ecosystem that creates and delivers value for users (including industrial enterprises, OEMs, system integrators, suppliers, etc.) by aggregating digital content and domain expertise. The IIH system acts as a trusted information broker between the ecosystem and the OT environment of the plant facility, providing a platform for connecting assets, contextualizing asset data, and providing secure access to the ecosystem. As part of this ecosystem, the IIH system uses a secure remote access architecture to allow users to remotely access data about their plant floor assets via a VPN connection.

An enterprise system may include one or more devices that perform respective operations of an enterprise and a sustainability platform system. The sustainability platform system may obtain search parameters associated with one or more sustainability parameters of the enterprise, obtain input data from one or more input data sources, and determine confidence parameters for the input data based on the input data sources. The sustainability platform system may also store the input data and the confidence parameters in a database of the sustainability platform system, generate one or more sustainability action plans for improving the sustainability parameters of the enterprise based on the input data stored in the database, and send one or more commands to the devices to adjust their respective operations according to the one or more sustainability action plans.

An enterprise system may include one or more devices that perform respective operations of an enterprise and a sustainability platform system. The sustainability platform system may obtain a sustainability model representative of a state of operations of the enterprise and sustainability target data of target constraints on one or more sustainability parameters of the enterprise. Additionally, the sustainability platform system may identify one or more abatement technologies from a database of multiple abatement technologies based on the sustainability model and the sustainability target data and generate a sustainability action plan for implementing at least one abatement technology of the identified abatement technologies such that the at least one abatement technology, when implemented via the sustainability action plan, is estimated to satisfy the sustainability target data. The sustainability platform system may also send commands to the devices to adjust their respective operations according to the sustainability action plan.

A machine-learning based (ML-based) system and method for automatically extracting one or more data fields from one or more documents, are disclosed. The ML-based system includes a document obtaining subsystem to obtain documents, a document pre-processing subsystem to generate pre-processed data, a field identifying subsystem to identify data fields using a trained ML model, and a field extracting subsystem to extract financial information. The ML-based system also comprises an output subsystem to deliver the extracted data to end users via user interfaces. The ML model is trained using historical documents, labelled data fields, and features such as distance-based features, direction-based features, dimension-based features, positional features, and value-based features. The M-based system employs hyperparameter optimization, noise removal, and accuracy assessment mechanisms to enhance performance. This ML-based system provides a scalable, accurate, and automated solution for financial information extraction, ensuring efficiency, adaptability, and seamless integration with enterprise systems.

The invention provides an intelligent printer remote monitoring and data collaboration system based on the Internet of Things, and relates to the technical field of the Internet of Things, and the system comprises a sensing layer, an edge layer, a cloud layer and an application layer which are adaptive to printing equipment, and the sensing layer and the edge layer are in data transmission connection through a dual-mode communication module. The edge layer and the cloud layer realize bidirectional interaction through a 5G / WiFi network, and the cloud layer completes cross-platform data collaboration with an enterprise OA system and an ERP system; a four-level architecture of a sensing layer, an edge layer, a cloud layer and an application layer is adopted, all levels are clear in division of labor and smooth in data interaction, the sensing layer directly collects equipment core operation data and configures a security encryption sub-module, the AES-256 algorithm is adopted to encrypt the equipment operation data and printing task data in real time, identity authentication is completed through an equipment unique identifier (UUID), and the equipment core operation data and the printing task data are encrypted in real time. Information leakage and tampering risks are avoided from a data source, and the security and privacy of enterprise printing data are guaranteed.

Information technology service management (ITSM) is provided by at least one computing device, including by accessing plurality of ITSM requests. For each one, a determination is made whether the respective ITSM request is valid. Where the request is not valid, a status identifier is assigned. Where the request is valid, the computing device(s) identifies, in the respective ITSM request, request information representing at least a request for action associated with a back-end service, a target service name, and a target system. Further, the computing device(s) distinguishes in the respective ITSM request, as a function of at least the request information, a technical infrastructure detail associated with the back-end service. Moreover, the computing device(s) generates, as a function of the technical infrastructure detail, a notification for implementing the action and transmits to at least one computing device associated with the back-end service the notification for implementing the action.

The invention provides an online marketing customer obtaining method and device based on enterprise WeChat, and is applied to a marketing customer obtaining system, the front end of the marketing customer obtaining system is integrated with enterprise WeChat so as to enable the enterprise WeChat to serve as a front-end interaction entrance, and the rear end of the marketing customer obtaining system is integrated with different enterprise systems and / or function systems so as to enable the enterprise WeChat to serve as a front-end interaction entrance. The method comprises the following steps: obtaining customer data through a target system; configuring a feature tag for the customer data; generating corresponding candidate marketing clues according to the feature tags and the customer data; calling a pre-constructed scoring card model to score the candidate marketing clues based on a rule weighting mechanism, and screening out marketing clues based on a scoring result; according to the matching degree between the marketing clues and feature information of different customer managers, the marketing clues are distributed to workbenches of corresponding target customer managers; and pushing a marketing strategy to the workbench in combination with the marketing clues and the feature information of the target customer manager.

An integrated security analysis data structure and a method for multi-container software projects. A data repository storing containers and a software bill of materials (SBOM) is queried. The SBOM includes first data describing the containers and second data describing software images in the containers. The software images include corresponding components. The SBOM further includes metadata about the containers, the software images, and the one or more corresponding components. A dependency graph, showing dependencies among the software images, of the software images is built automatically. Usage data describing usage of the containers as deployed in an enterprise system is retrieved automatically. The SBOM, the dependency graph, and the usage data are transformed into a SBOM data structure. The SBOM data structure includes a searchable data object that is searchable by: the containers, the software images, the one or more corresponding components of the software images, the metadata, and the usage data.

A label architecture building system and a label architecture building method are provided. The label architecture building system includes a storage device and a processor. The processor executes a plurality of modules in the storage device. A task profile label building module performs data mining according to task and user information in an enterprise system to generate task label data and builds a task profile label architecture according to the task label data. A user profile label building module performs data mining according to user information in the enterprise system to generate user label data and builds a user profile label architecture according to the user label data, so that a recommendation system provides recommendation information according to input information, the task profile label architecture, and the user profile label architecture. The efficiency of building the label architecture and the accuracy of the profile are accordingly improved.

Aspects of the disclosure include a machine learning architecture for leveraging graph-enhanced semantic retrieval augmented generation (RAG) for cross domain data in enterprise systems. A method includes processing a natural language query using a large language model to generate a query intent and a query schema, generating text embeddings representing the query intent, and generating node embeddings representing the query schema. A semantic similarity search and a structural similarity search are performed to identify two sets of nodes and edges, which are aggregated. A connected subgraph is built from the aggregated set of nodes and edges and an optimal path through the connected subgraph is identified based on a learned cost function. A retrieval augmented generation executable is generated based on the at least one optimal path and executed against a database to retrieve contextual data. The contextual data is leveraged to respond to the query.