Enterprise knowledge and project management system and method based on AI intelligence

Abstract

The invention discloses an enterprise knowledge and project management system and method based on AI intellectualization. The system comprises an application layer, a service component layer and a data layer. The data layer is located between the application layer and the service component layer; the application layer is used for constructing an operation interface, directly interacting with a user by adopting the operation interface, and pushing enterprise knowledge through user behaviors in the interaction process; according to a project management conference request input by a user, generating a visual approval process map through an intelligent tool, and sending the visual approval process map to the data layer and the service component layer; the data layer is used for storing interaction information input by the operation interface and sending the interaction information to the service component layer, and storing, querying and analyzing the visual approval process map; and the service component layer is used for displaying the visual approval process map. According to the method, a visual approval process map can be provided, query and analysis are supported, and the approval efficiency and transparency are improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial modeling technology, and specifically to an enterprise knowledge and project management system and method based on AI intelligence. Background Art

[0002] In today's knowledge economy, enterprise knowledge management faces numerous challenges, including knowledge fragmentation, low retrieval efficiency, difficulties in collaborative work, and insufficient knowledge innovation. Traditional knowledge management systems typically have limited functionality and are unable to meet enterprises' needs for full-lifecycle knowledge management. Existing technologies rely heavily on keyword matching and lack semantic understanding. Intelligent office assistance tools are separated from knowledge management systems, resulting in inefficient information transfer. Scientific research project management lacks intelligent support, making it difficult to accumulate and transform knowledge. Therefore, a comprehensive solution is urgently needed that integrates knowledge base construction, intelligent retrieval, intelligent office assistance, knowledge innovation, and scientific research project management. Summary of the Invention

[0003] The present invention provides an AI-based intelligent enterprise knowledge and project management system to solve the problems raised by the background technology.

[0004] To achieve the above objectives, the present invention adopts the following technical solutions: In the first aspect, the present invention proposes an enterprise knowledge and project management system based on AI intelligence, comprising: an application layer, a service component layer, and a data layer; the data layer is located between the application layer and the service component layer;

[0005] The application layer is used to build an operation interface, directly interact with users through the operation interface, and push enterprise knowledge through user behavior during the interaction process; according to the project management meeting request input by the user, a visual approval process map is generated through intelligent tools and sent to the data layer and the service component layer;

[0006] The data layer is used to store the interactive information inputted from the operation interface and send it to the service component layer, and to store, query and analyze the visual approval process map;

[0007] The service component layer is used to display the visual approval process map.

[0008] Preferably, the application layer includes: a knowledge base construction module, an intelligent search and recommendation module, an intelligent office assistance module, a knowledge innovation tool module and a scientific research project management module that are interconnected;

[0009] The knowledge base construction module is used to generate a knowledge graph based on the documents, charts or videos obtained from the operation interface and send it to the intelligent retrieval recommendation module;

[0010] The intelligent search and recommendation module is used to build an operation interface; based on the knowledge graph, it uses the semantic understanding of the large model of the operation interface to directly interact with the user, and pushes enterprise knowledge through user behavior obtained through the operation interface;

[0011] The intelligent office assistance module is used to generate tasks according to the project management meeting request input by the user into the operation interface; based on the task, a visual approval process is generated according to a preset meeting template and sent to the knowledge innovation tool module and the scientific research project management module;

[0012] The knowledge innovation tool module is used to create slides, reports or charts based on the visual approval process using intelligent generation technology;

[0013] The scientific research project management module is used to generate a visual approval process map through intelligent tools based on the visual approval process.

[0014] Preferably, the knowledge base construction module is specifically used to identify the title, paragraph, and keywords of the document based on the document, chart or video obtained from the operation interface; extract metadata of the chart or video through voice recognition technology; classify based on the title, paragraph, keyword or metadata to obtain classification results; and construct a knowledge graph based on the classification results and send it to the intelligent retrieval recommendation module.

[0015] Preferably, the data layer includes: a database module, a data processing module and a data source module that are communicatively connected to each other;

[0016] The database module is used to store the interactive information input through the operation interface and the visual approval process map;

[0017] The data processing module is used to parse the contents of technical documents and operation manuals in the interactive information using preset rules; and extract image data features in the interactive information using a convolutional neural network for storage;

[0018] The data source module is used to store the visual approval process map; based on the visual approval process map, query and analyze the interactive information input into the operation interface.

[0019] Preferably, the data source module is specifically used to identify the user's query intention based on the interactive information input into the operation interface based on the visual approval process map; and perform query and analysis based on the query intention.

[0020] Preferably, the data layer is further used to convert the unstructured document input by the user into a multi-dimensional vector through an embedding model; and perform semantic retrieval on the unstructured document based on the multi-dimensional vector.

[0021] Preferably, the application layer is also used to obtain the user's interaction information, and based on the interaction information, record the search history in the interaction information, the click behavior in the interaction information, and the dwell time in the interaction information; build a user interest model based on the search history, the click behavior, and the dwell time; based on the user interest model, recommend information to the user according to the obtained user's current input.

[0022] Preferably, the meeting template includes a meeting agenda, meeting participants, meeting minutes, and a simplified meeting organization process.

[0023] Preferably, the scientific research project management module is also used to automatically trigger the approval task according to a preset process based on the visual approval process map, and monitor the progress of the approval task in real time through the visual approval process map.

[0024] Secondly, the present invention also proposes an enterprise knowledge and project management method based on AI intelligence, including:

[0025] Utilize the application layer to build an operation interface, which is used to directly interact with users and push enterprise knowledge based on user behavior during the interaction process; generate a visual approval process map through intelligent tools based on project management meeting requests input by users;

[0026] Utilize the data layer to store the interactive information inputted into the operation interface and to store, query and analyze the visual approval process map;

[0027] The service component layer is used to display the visual approval process map.

[0028] In a third aspect, the present invention also proposes an electronic device, comprising: at least one processor and a memory; the memory and the processor are connected via a bus;

[0029] The memory is used to store one or more programs;

[0030] When the one or more programs are executed by the at least one processor, the enterprise knowledge and project management method based on AI intelligence is implemented.

[0031] Fourthly, the present invention application also proposes a readable storage medium on which an execution program is stored. When the execution program is executed, the enterprise knowledge and project management method based on AI intelligence is implemented.

[0032] Beneficial effects of the present invention: An enterprise knowledge and project management system and method based on AI intelligence, comprising: an application layer, a service component layer, and a data layer; the data layer is located between the application layer and the service component layer; the application layer is used to build an operation interface, use the operation interface to directly interact with the user, and push enterprise knowledge through the user behavior in the interaction process; according to the project management meeting request input by the user, a visual approval process map is generated through an intelligent tool and sent to the data layer and the service component layer; the data layer is used to store the interactive information input in the operation interface and send it to the service component layer, and store, query and analyze the visual approval process map; the service component layer is used to display the visual approval process map. The present invention can provide a visual approval process map, support query and analysis, improve approval efficiency and transparency, and meet the needs of enterprises for knowledge life cycle management. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a schematic diagram of the enterprise knowledge and project management system structure of the AI ​​intelligent technology of the present invention;

[0034] Figure 2 Building and managing a technical roadmap for the knowledge base of this invention;

[0035] Figure 3 This is the intelligent retrieval and recommendation technology roadmap of the present invention;

[0036] Figure 4 This is the technical roadmap for intelligent assisted office work of the present invention;

[0037] Figure 5 It is the technical roadmap of the knowledge innovation tool of the present invention;

[0038] Figure 6 This is the technical roadmap for scientific research project management of the present invention. DETAILED DESCRIPTION

[0039] Specific embodiments of the present invention will now be fully described with reference to the accompanying drawings. For clarity, many physical details will be included in the following description. However, it should be understood that these physical details are not intended to limit the present invention. In other words, in some embodiments of the present invention, these physical details are not essential. Furthermore, to simplify the illustrations, some commonly used structures and components are depicted in a simplified schematic manner.

[0040] Example 1:

[0041] like Figure 1As shown, an AI-based intelligent enterprise knowledge and project management system of the present invention includes: an application layer, a service component layer, and a data layer; the data layer is located between the application layer and the service component layer;

[0042] The application layer is used to build an operation interface, directly interact with users through the operation interface, and push enterprise knowledge through user behavior during the interaction process; according to the project management meeting request input by the user, a visual approval process map is generated through intelligent tools and sent to the data layer and the service component layer;

[0043] The data layer is used to store the interactive information inputted from the operation interface and send it to the service component layer, and to store, query and analyze the visual approval process map;

[0044] The service component layer is used to display the visual approval process map.

[0045] The above-mentioned application layer directly interacts with users, provides a wealth of shortcut keys and an intuitive operation interface, and integrates a variety of intelligent tools and auxiliary functions to help users quickly obtain the required information and complete work tasks, thereby improving work efficiency and user experience.

[0046] The service component layer, the core of the system, is responsible for implementing various specific service functions. This creates a highly integrated and flexible service layer capable of meeting complex and ever-changing business needs. This layer utilizes workflow components to manage business processes, database components to provide data persistence and access services, cache components to accelerate data access, API components as system entry points to route requests and perform load balancing, microservice components to support modular development and deployment, log monitoring components to collect and display system operational status, intelligent indexing components to provide full-text search and indexing capabilities, and message queue components to handle asynchronous communication and task scheduling. These components work together to form a highly integrated and flexible service layer capable of meeting complex and ever-changing business needs.

[0047] The data layer is an efficient and scalable data storage and processing platform that integrates and manages various types of enterprise resources, ensuring high stability and strong scalability, and supporting efficient storage, query, and analysis of large-scale data.

[0048] Furthermore, the application layer includes: a knowledge base construction module, an intelligent search and recommendation module, an intelligent office assistance module, a knowledge innovation tool module and a scientific research project management module that are interconnected;

[0049] The knowledge base construction module is used to generate a knowledge graph based on the documents, charts or videos obtained from the operation interface and send it to the intelligent retrieval recommendation module;

[0050] The intelligent search and recommendation module is used to build an operation interface; based on the knowledge graph, it uses the semantic understanding of the large model of the operation interface to directly interact with the user, and pushes enterprise knowledge through user behavior obtained through the operation interface;

[0051] The intelligent office assistance module is used to generate tasks according to the project management meeting request input by the user into the operation interface; based on the task, a visual approval process is generated according to a preset meeting template and sent to the knowledge innovation tool module and the scientific research project management module;

[0052] The knowledge innovation tool module is used to create slides, reports or charts based on the visual approval process using intelligent generation technology;

[0053] The scientific research project management module is used to generate a visual approval process map through intelligent tools based on the visual approval process.

[0054] The aforementioned intelligent tools include knowledge base construction and management, intelligent retrieval and recommendation, intelligent office assistance, knowledge innovation tools, and scientific research project management. The knowledge base construction module realizes automatic classification, labeling, and knowledge graph generation of multi-format resources (documents / charts / videos), and supports structured storage and association analysis; the intelligent retrieval and recommendation module: based on large-scale semantic understanding and knowledge graphs, provides accurate retrieval and personalized recommendations, and optimizes knowledge push through user behavior analysis;

[0055] The intelligent office assistance module integrates permission management, task allocation, and process automation functions, supports multi-person collaborative editing, meeting template application, and approval process visualization;

[0056] The knowledge innovation tool module can automatically create PPT / reports / charts using intelligent generation technology, realizing the rapid transformation of data into visual results;

[0057] The scientific research project management module covers the entire project life cycle management, including progress tracking, experience accumulation and reuse, and a visual approval process map.

[0058] Furthermore, the knowledge base construction module is specifically used to identify the title, paragraph, and keywords of the document based on the document, chart or video obtained from the operation interface; extract metadata from the chart or video through voice recognition technology; classify based on the title, paragraph, keyword or metadata to obtain classification results; and construct a knowledge graph based on the classification results and send it to the intelligent retrieval recommendation module.

[0059] Furthermore, the data layer includes: a database module, a data processing module and a data source module that are communicatively connected to each other;

[0060] The database module is used to store the interactive information input through the operation interface and the visual approval process map;

[0061] The data processing module is used to parse the contents of technical documents and operation manuals in the interactive information using preset rules; and extract image data features in the interactive information using a convolutional neural network for storage;

[0062] The data source module is used to store the visual approval process map; based on the visual approval process map, query and analyze the interactive information input into the operation interface.

[0063] The above-mentioned data layer may include an SQL database for storing structured project task data and its association with metadata, ensuring efficient relational data management and query capabilities; it may also include a vector database, which converts unstructured documents into high-dimensional vectors through an embedding model, thereby realizing semantic retrieval and supporting more accurate information retrieval and similarity calculation; it may also include a knowledge graph database, which represents the logical associations between technical documents based on an entity-relationship network, and helps to systematically store and understand technical documents and their internal connections; it may also include a question-and-answer database, which represents the logical associations between technical documents based on an entity-relationship network, and asks and answers questions; it may also include an interface database, which stores the time series data stream of external system API interactions in real time, optimizes data transmission efficiency, and reduces external system access latency.

[0064] The data processing module is also used to use structured knowledge processing to parse the hierarchical content of technical documents and operating manuals according to preset rules; use unstructured processing to extract image data features using convolutional neural networks and process audio recordings through speech recognition models; use the data vectorization engine to generate semantic vector encoding of research reports using pre-trained language models; perform data feature extraction and intelligent data conversion;

[0065] The data source module contains technical document library, development experience, research reports, operation manuals, task and project data, user behavior data, image data, and metadata.

[0066] Furthermore, the data source module is specifically used to identify the user's query intention based on the interactive information input into the operation interface based on the visual approval process map; and perform query and analysis based on the query intention.

[0067] Furthermore, the data layer is also used to convert the unstructured document input by the user into a multi-dimensional vector through an embedding model; and perform semantic retrieval on the unstructured document based on the multi-dimensional vector.

[0068] Furthermore, the application layer is also used to obtain user interaction information, and based on the interaction information, record the search history in the interaction information, the click behavior in the interaction information, and the dwell time in the interaction information; build a user interest model based on the search history, the click behavior, and the dwell time; based on the user interest model, recommend information to the user according to the obtained user's current input.

[0069] Furthermore, the meeting template includes a meeting agenda, meeting participants, meeting minutes, and a simplified meeting organization process.

[0070] Furthermore, the scientific research project management module is also used to automatically trigger the approval task according to the preset process based on the visual approval process map, and monitor the progress of the approval task in real time through the visual approval process map.

[0071] The service component layer handles workflow management, provides data persistence and access services for the database component, accelerates data access with a cache component, and uses a built-in API component as the system entry point to route requests and perform load balancing. It supports modular development and deployment, and the log monitoring component collects and displays system operating status. The intelligent indexing component provides full-text search and indexing capabilities, while the message queue component handles asynchronous communication and task scheduling. These components work together to form a highly integrated and flexible service layer capable of meeting complex and ever-changing business needs.

[0072] The above system can also set up permission management and sharing, and set access rights to knowledge resources based on user roles (such as administrator, editor, viewer). It supports internal sharing and external collaboration of knowledge resources, ensuring the security and controllability of knowledge.

[0073] The system of the present invention can solve many challenges faced by enterprise knowledge management, including knowledge fragmentation, low retrieval efficiency, difficulty in collaborative office, insufficient knowledge innovation and other problems.

[0074] Example 2:

[0075] Based on the same concept, the present invention also proposes a method for adopting an AI-based intelligent enterprise knowledge and project management system, including:

[0076] Utilize the application layer to build an operation interface, which is used to directly interact with users and push enterprise knowledge based on user behavior during the interaction process; generate a visual approval process map through intelligent tools based on project management meeting requests input by users;

[0077] Utilize the data layer to store the interactive information inputted into the operation interface and to store, query and analyze the visual approval process map;

[0078] The service component layer is used to display the visual approval process map.

[0079] like Figure 2 As shown, the method can implement the knowledge base construction and management technology based on the system of embodiment 1, including:

[0080] To upload knowledge resources, users can select local files or drag and drop files through the platform interface. Multiple formats are supported. The system performs format verification and pre-processing on uploaded files to ensure file integrity and readability.

[0081] Knowledge resource parsing: Text extraction from document resources, identifying titles, paragraphs, keywords, and other content. For multimedia resources like images and videos, text information is extracted using OCR and speech recognition technologies. Metadata is extracted from files for subsequent classification and labeling.

[0082] Automatic classification and labeling: Based on machine learning algorithms or deep learning models, knowledge resources are automatically categorized. Natural language processing techniques are used to extract keywords and topics from text and generate labels. Classification results and labels are used as nodes in the knowledge graph to establish preliminary knowledge associations.

[0083] Knowledge graph construction uses named entity recognition technology to extract entities from text. Relationship extraction algorithms are used to identify relationships between entities. Entities and relationships are used as nodes and edges to construct a knowledge graph and store it in a graph database.

[0084] Structured storage stores parsed knowledge resources, classification results, labels, and knowledge graphs in a distributed database, establishes a full-text index for knowledge resources, and supports efficient retrieval.

[0085] Permission management and sharing: Set access rights to knowledge resources based on user roles (e.g., administrator, editor, viewer). Support internal sharing and external collaboration of knowledge resources to ensure the security and controllability of knowledge.

[0086] like Figure 3 As shown, the method can implement intelligent retrieval and recommendation technology based on the system of embodiment 1, including:

[0087] Query input: Users enter queries through the platform interface, including natural language questions or keywords. After receiving the input, the system performs preprocessing, such as word segmentation and stop word removal, to optimize the query structure and prepare for subsequent processing.

[0088] Semantic understanding uses pre-trained large models to understand the semantics of query statements and extract query intent and key information. Classification models identify the user's query intent, such as finding documents, obtaining data, or generating reports, providing a foundation for accurate retrieval.

[0089] Knowledge graph association analysis extracts entities from the query and matches them with nodes in the knowledge graph. Based on the associations in the knowledge graph, it infers knowledge resources related to the query and expands related concepts and topics based on the query context, improving the comprehensiveness of the search.

[0090] Precise search, combined with the associated results of the knowledge graph, retrieves relevant documents, charts, videos, and other resources in the full-text index. Search results are sorted and filtered based on relevance, time, popularity, and other dimensions to ensure that the most relevant results are displayed first, improving the user experience.

[0091] User behavior analysis records user search history, click behavior, dwell time, and other data. Based on user behavior data, a user interest model is constructed to identify user preferences and needs, providing data support for personalized recommendations.

[0092] Personalized recommendation generates a personalized recommendation list based on collaborative filtering, content recommendation or hybrid recommendation algorithms, and dynamically adjusts the recommended content according to the user's latest behavior to ensure the timeliness and accuracy of the recommendation and meet the user's personalized needs.

[0093] like Figure 4 As shown, the method can implement intelligent assisted office technology based on the system 1 of the embodiment, including:

[0094] Permission management and collaborative document editing: The system sets document access and editing permissions based on user roles (such as administrator, editor, and viewer) to ensure data security. In addition, integrated collaborative editing tools support real-time collaboration among multiple users on the same document, automatically saving document versions and supporting version rollback and history review.

[0095] For task assignment and progress tracking, users can create tasks within the platform, setting information such as task name, description, responsible person, and deadline. Tasks can be automatically or manually assigned based on team member roles and workloads. Visual tools like Gantt charts and Kanban boards allow real-time tracking of task progress, supporting task status updates (e.g., in progress, completed), and task reminders, which can be set to notify relevant personnel via email or in-site messages.

[0096] For meeting management, the platform provides standardized meeting templates, including meeting agendas, attendees, and minutes, simplifying the meeting organization process. It supports meeting scheduling, conference room reservations, and attendee invitations. It also allows for uploading of meeting recordings or summaries, intelligently generates meeting minutes, and supports archiving and sharing of meeting content.

[0097] The Approval Process Map provides a visual approval process design tool that supports custom approval nodes and process rules. It automatically triggers approval tasks based on pre-set processes, supports multi-level and parallel approvals, and monitors approval progress in real time through the Approval Process Map, supporting process exception handling and reminders.

[0098] AI-powered assistance automatically generates meeting minutes, task reports, and other documents based on key user input, and automatically sends reminders based on task progress and deadlines. AI algorithms analyze task execution efficiency and team collaboration, providing optimization suggestions and improving team productivity.

[0099] like Figure 5 As shown, the method can be based on the knowledge innovation tool technology of the embodiment 1 system, including:

[0100] User input and data preprocessing: Users input topics, keywords or upload data files through the platform interface. The system cleans, formats and standardizes the input data to ensure data quality and provide a high-quality input foundation for subsequent intelligent content generation.

[0101] Intelligent content generation: The system automatically generates PPT outlines, report structures, and visualizations based on user-entered topics or data. The PPT generation module utilizes natural language generation technology to populate content, and combines knowledge graphs to recommend relevant charts and case studies, supporting user-defined templates and styles. The report generation module produces structured reports, integrating data analysis results to provide data-driven content. The chart generation module generates a variety of visualizations based on input data, supporting chart type recommendations, style optimization, and online editing and modification.

[0102] The platform combines knowledge graphs and professional knowledge bases to recommend knowledge resources (such as cases, documents, data, etc.) related to the topics input by users, and enhances the relevance and depth of generated content through association analysis of knowledge graphs, thereby improving the accuracy and richness of the content.

[0103] User interaction and optimization: Users can interactively edit generated PPTs, reports, and charts, adjusting content and style. Based on user feedback and editing behavior, the system automatically optimizes generated content, continuously improving user experience and content quality.

[0104] Output and sharing: The platform supports outputting generated content into various formats, including PPT, PDF, and Word, to meet the needs of different scenarios. Users can share content with one click via link or email, supporting team collaboration and knowledge sharing, improving team efficiency and knowledge circulation.

[0105] like Figure 6 As shown, the method can be based on the system 1 of the embodiment to implement scientific research project management technology, including:

[0106] Project task assignment uses form tools to enter and submit task information, supports hierarchical task management, and uses a tree structure to store task relationships to ensure that task assignment is clear and easy to manage.

[0107] Progress tracking: Use Gantt charts or Kanban tools to visualize task progress, integrate reminder services (such as emails and in-site messages) to implement task reminders, and ensure that team members are aware of task progress in a timely manner and complete tasks on time.

[0108] Experience accumulation: With the help of document management system, knowledge resources can be archived and managed. Experience summary reports can be automatically generated based on template engine to ensure efficient accumulation and reuse of project experience.

[0109] The approval process map uses the process engine to implement the design and execution of the approval process, provides a visual approval process map, supports real-time monitoring and exception handling of the process, and improves approval efficiency and transparency.

[0110] Full life cycle management: Use project management tools to manage the entire project life cycle, integrate data analysis tools to generate performance reports and visual charts, and provide comprehensive support for project management.

[0111] Example 3:

[0112] The present invention also provides an electronic device, which may be a computer, a single-chip microcomputer, a smart mobile device, or the like. The electronic device in this embodiment may include a processor, a memory, a transceiver component, and the like. The memory, processor, and transceiver component are connected via a bus; the memory may be used to store an execution program, which may include instructions; and the processor may be used to execute the instructions stored in the memory. The memory may also be used to store data, which may be accessed and / or modified during the execution of the instructions.

[0113] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the storage medium to implement the corresponding method flow or corresponding function, so as to realize the steps of an enterprise knowledge and project management method based on AI intelligence in the above embodiment.

[0114] Example 4:

[0115] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It can be understood that the storage medium here can include both built-in storage media in the electronic device and, of course, extended storage media supported by the electronic device. The storage medium provides a storage space that stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more execution programs (including program code). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of an enterprise knowledge and project management method based on AI intelligence in the above embodiment.

[0116] Those skilled in the art will appreciate that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0117] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the application, but these changes, modifications or equivalent substitutions are all within the scope of protection of the pending claims.

Claims

1. An AI-based enterprise knowledge and project management system, characterized by: include: Application layer, service component layer, data layer; The data layer is located between the application layer and the service component layer; The application layer is used to build an operation interface, use the operation interface to directly interact with users, and push enterprise knowledge through user behavior during the interaction process; According to the project management meeting request input by the user, a visual approval process map is generated by an intelligent tool and sent to the data layer and the service component layer; The data layer is used to store the interactive information inputted from the operation interface and send it to the service component layer, and to store, query and analyze the visual approval process map; The service component layer is used to display the visual approval process map.

2. The system according to claim 1, wherein: The application layer includes: a knowledge base construction module, an intelligent search and recommendation module, an intelligent office assistance module, a knowledge innovation tool module and a scientific research project management module that are interconnected; The knowledge base construction module is used to generate a knowledge graph based on the documents, charts or videos obtained from the operation interface and send it to the intelligent retrieval recommendation module; The intelligent search and recommendation module is used to build an operation interface; based on the knowledge graph, it uses the semantic understanding of the large model of the operation interface to directly interact with the user, and pushes enterprise knowledge through user behavior obtained through the operation interface; The intelligent office assistance module is used to generate tasks according to the project management meeting request input by the user into the operation interface; based on the task, a visual approval process is generated according to a preset meeting template and sent to the knowledge innovation tool module and the scientific research project management module; The knowledge innovation tool module is used to create slides, reports or charts based on the visual approval process using intelligent generation technology; The scientific research project management module is used to generate a visual approval process map through intelligent tools based on the visual approval process.

3. The system according to claim 2, characterized in that The knowledge base construction module is specifically used to identify titles, paragraphs, and keywords of documents, charts, or videos obtained from the operation interface; and to extract metadata of charts or videos using speech recognition technology; Classify based on the title, the paragraph, the keyword or the metadata to obtain a classification result; Based on the classification results, a knowledge graph is constructed and sent to the intelligent retrieval recommendation module.

4. The system according to claim 1, wherein: The data layer includes: a database module, a data processing module and a data source module that are interconnected; The database module is used to store the interactive information input through the operation interface and the visual approval process map; The data processing module is used to parse the contents of technical documents and operation manuals in the interactive information using preset rules; and extract image data features in the interactive information using a convolutional neural network for storage; The data source module is used to store the visual approval process map; based on the visual approval process map, query and analyze the interactive information input into the operation interface.

5. The system according to claim 4, characterized in that The data source module is specifically configured to identify the user's query intention based on the interactive information input into the operation interface based on the visual approval process map; Based on the query intent, query and analysis are performed.

6. The system according to claim 4, characterized in that The data layer is further used to convert the unstructured document input by the user into a multi-dimensional vector through an embedding model; and perform semantic retrieval on the unstructured document based on the multi-dimensional vector.

7. The system according to claim 2, wherein: The application layer is further used to obtain user interaction information and, based on the interaction information, record search history, click behavior, and dwell time in the interaction information; A user interest model is constructed based on the search history, the click behavior, and the dwell time; and information is recommended to the user based on the user interest model and the acquired current input.

8. The system according to claim 2, wherein: The meeting template includes a meeting agenda, meeting participants, meeting minutes, and a simplified meeting organization process.

9. The system according to claim 2, wherein: The scientific research project management module is also used to automatically trigger approval tasks according to a preset process based on the visual approval process map, and monitor the progress of the approval tasks in real time through the visual approval process map.

10. An enterprise knowledge and project management method based on AI intelligence, characterized by: include: Utilize the application layer to build an operation interface, use the operation interface to directly interact with users, and push enterprise knowledge through user behavior during the interaction process; Generate a visual approval process map through intelligent tools based on the project management meeting request entered by the user; Utilize the data layer to store the interactive information inputted into the operation interface and to store, query and analyze the visual approval process map; The service component layer is used to display the visual approval process map.

Images