Knowledge base management system based on artificial intelligence

Abstract

The invention relates to the technical field of knowledge management, in particular to a knowledge base management system based on artificial intelligence, which comprises a knowledge acquisition module, a knowledge arrangement module, a knowledge updating module, a knowledge recommendation module, a user interaction module, a knowledge security module and a system management module. The system automatically obtains and sorts structured and unstructured data from multi-source data, generates a knowledge graph and performs hierarchical classification. The content of the knowledge base is dynamically adjusted and updated through time sequence analysis and a self-adaptive updating mechanism, and personalized recommendation is achieved in combination with user behaviors and historical queries. The system adopts an advanced encryption standard and a role access control technology to ensure the security of the knowledge base, so that the knowledge acquisition, arrangement and recommendation efficiency is remarkably improved, meanwhile, the high availability and data security of the system are ensured, and the system is suitable for a large-scale knowledge management scene.

Description

Technical Field

[0001] The present invention relates to the technical field of knowledge management, and in particular to a knowledge base management system based on artificial intelligence. Background Art

[0002] With the rapid development of information technology and big data, enterprises and organizations have an increasing demand for knowledge management. As an important platform for carrying the core knowledge and information of enterprises, knowledge bases can effectively integrate and utilize internal resources, help enterprises improve operational efficiency, promote innovation, and support decision-making. However, traditional knowledge base management systems usually rely on manual input and maintenance, with a single way of acquiring knowledge, and cannot fully utilize multi-source heterogeneous data inside and outside the enterprise. In addition, faced with the massive emergence of unstructured data (such as text, pictures, audio, and video), traditional knowledge bases are particularly limited in their ability to process and understand semantics, making it difficult to meet the dynamic and efficient knowledge management needs of modern enterprises.

[0003] The existing knowledge base management system has the following main problems: first, the traditional system has technical bottlenecks in the processing of unstructured data, lacks effective natural language processing and deep learning algorithm support, resulting in low efficiency in knowledge extraction and organization; second, the knowledge base update mechanism generally relies on manual operation, which makes it difficult to achieve real-time dynamic update of knowledge, resulting in outdated or redundant knowledge content; finally, the personalized recommendation function is not perfect, and it is difficult to accurately recommend relevant knowledge according to user needs. In addition, the knowledge base security and system stability are insufficient, and it is unable to effectively deal with problems such as sensitive information leakage and system failure. Summary of the invention

[0004] Based on the above objectives, the present invention provides a knowledge base management system based on artificial intelligence.

[0005] A knowledge base management system based on artificial intelligence, comprising a knowledge acquisition module, a knowledge sorting module, a knowledge updating module, a knowledge recommendation module, a user interaction module, a knowledge security module and a system management module, wherein;

[0006] The knowledge acquisition module is used to automatically acquire structured and unstructured data from different data sources, including documents, databases, audio, video and real-time sensor data. The knowledge acquisition module performs semantic analysis on unstructured data through natural language processing algorithms and machine learning models, and extracts core knowledge points therein;

[0007] The knowledge organization module pre-processes the knowledge extracted by the knowledge acquisition module through data cleaning, deduplication and classification algorithms, hierarchically organizes the knowledge using rule-based classification algorithms and deep learning models, and generates a knowledge graph based on the relevance of the knowledge;

[0008] The knowledge update module regularly updates the knowledge content in the knowledge base, adopts a time series-based change detection algorithm and an adaptive model update algorithm, automatically identifies new knowledge and outdated knowledge, and incrementally updates the knowledge base;

[0009] The knowledge recommendation module uses a recommendation algorithm based on collaborative filtering and deep learning based on user behavior and historical query data to provide users with personalized knowledge recommendation services, and dynamically adjusts the recommendation strategy based on user interests and current business scenarios;

[0010] The user interaction module provides users with multiple interaction methods, including text query, voice query and visual query, supports users to retrieve knowledge through natural language, and understands user intentions through semantic analysis algorithms to provide users with knowledge feedback;

[0011] The knowledge security module is used to encrypt and manage permissions for sensitive information in the knowledge base, using role-based access control and data encryption algorithms;

[0012] The system management module is used to monitor and manage the operating status of the system, and adopts an artificial intelligence-based fault prediction model to automatically detect system anomalies and generate repair suggestions.

[0013] Optionally, the knowledge acquisition module includes a data crawling submodule, a document parsing submodule and a real-time data acquisition submodule, wherein;

[0014] The data crawling submodule obtains structured data from web pages, databases and API interfaces through automated scripts;

[0015] The document parsing submodule performs semantic analysis and structural processing on the unstructured data in the document through natural language processing technology, extracts key concepts and knowledge points in the text, and stores them in a temporary database;

[0016] The real-time data acquisition submodule acquires real-time data through sensors and IoT devices, and performs preliminary analysis and storage on the real-time data based on stream processing technology.

[0017] Optionally, the knowledge arrangement module includes a data cleaning submodule, a knowledge classification submodule and a knowledge graph generation submodule, wherein;

[0018] The data cleaning submodule uses an anomaly detection algorithm based on machine learning to automatically identify and remove duplicate, erroneous or invalid data;

[0019] The knowledge classification submodule adopts a rule-based classification algorithm and a convolutional neural network to classify knowledge hierarchically and generate a multi-level knowledge classification system;

[0020] The knowledge graph generation submodule generates a knowledge graph based on the correlation between knowledge, using a graph database and a graph algorithm, and mines potential knowledge associations through graph structure analysis.

[0021] Optionally, the knowledge updating module includes a time series analysis submodule and an adaptive model updating submodule, wherein;

[0022] The time series analysis submodule analyzes the knowledge change trend through the time series model and predicts the future knowledge update needs;

[0023] The adaptive model updating submodule dynamically adjusts the model parameters of the knowledge base based on the occurrence frequency and weight of the new knowledge.

[0024] Optionally, the knowledge recommendation module includes a collaborative filtering submodule and a deep learning recommendation submodule, wherein;

[0025] The collaborative filtering submodule recommends relevant knowledge content to users through a collaborative filtering algorithm based on the user's historical behavior data;

[0026] The deep learning recommendation submodule provides personalized knowledge recommendations to users through a deep neural network model combined with the user's current query context and historical query records.

[0027] Optionally, the user interaction module includes a natural language understanding submodule and a speech recognition and synthesis submodule, wherein;

[0028] The natural language understanding submodule understands the real intention of the user's query through a semantic analysis algorithm, and converts the user's natural language request into a structured query;

[0029] The speech recognition and synthesis submodule adopts a deep learning model to realize the user's speech input and speech feedback functions, allowing the user to query and acquire knowledge through voice.

[0030] Optionally, the knowledge security module includes a data encryption submodule and a role access control submodule, wherein;

[0031] The data encryption submodule encrypts the sensitive information stored in the knowledge base according to the encryption standard;

[0032] The role access control submodule limits the user's access rights to different types of knowledge according to the user's authority level.

[0033] Optionally, the knowledge acquisition module works in collaboration with the knowledge organization module, and the data crawling and document parsing functions in the knowledge acquisition module are closely integrated with the data cleaning and classification functions in the knowledge organization module, thereby improving the efficiency of knowledge acquisition and organization through automated processes.

[0034] Beneficial effects of the present invention:

[0035] The present invention, through the collaborative work of the knowledge acquisition module and the knowledge organization module, can automatically acquire structured and unstructured data from a variety of data sources, and perform semantic analysis on unstructured data through natural language processing and deep learning algorithms to extract key knowledge points. The system uses advanced classification algorithms and knowledge graph technology to hierarchically organize the acquired knowledge, effectively improving the organizational efficiency and accuracy of knowledge and avoiding the inefficiency and error-proneness of traditional manual processing. At the same time, the deduplication, data cleaning and association analysis technologies used in the knowledge organization process ensure the high quality and simplification of the knowledge base content.

[0036] The present invention realizes personalized knowledge recommendation based on user behavior and query history through the knowledge recommendation module, and can accurately predict the user's knowledge needs and provide users with highly relevant knowledge content by combining collaborative filtering algorithms and deep learning models. Through the knowledge update module, the system can monitor the changes of the knowledge base in real time, and automatically identify new knowledge and outdated information by using time series analysis and adaptive model update algorithms, realize dynamic update of the knowledge base, and ensure the timeliness and foresight of the knowledge content. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 Schematic diagram of a system flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0040] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0041] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0042] like Figure 1 As shown, a knowledge base management system based on artificial intelligence includes a knowledge acquisition module, a knowledge sorting module, a knowledge updating module, a knowledge recommendation module, a user interaction module, a knowledge security module and a system management module, wherein;

[0043] The knowledge acquisition module is used to automatically acquire structured and unstructured data from different data sources, including documents, databases, audio, video, and real-time sensor data. The knowledge acquisition module uses natural language processing algorithms and machine learning models to perform semantic analysis on unstructured data and extract core knowledge points.

[0044] The knowledge organization module pre-processes the knowledge extracted by the knowledge acquisition module through data cleaning, deduplication and classification algorithms, uses rule-based classification algorithms and deep learning models to organize the knowledge hierarchically, and generates a knowledge graph based on the relevance of the knowledge;

[0045] The knowledge update module regularly updates the knowledge content in the knowledge base, using a time series-based change detection algorithm and an adaptive model update algorithm to automatically identify new knowledge and outdated knowledge, and perform incremental updates on the knowledge base;

[0046] The knowledge recommendation module uses collaborative filtering and deep learning-based recommendation algorithms based on user behavior and historical query data to provide users with personalized knowledge recommendation services and dynamically adjust the recommendation strategy based on user interests and current business scenarios.

[0047] The user interaction module provides users with a variety of interaction methods, including text query, voice query and visual query, supports users to retrieve knowledge through natural language, and understands user intentions through semantic analysis algorithms to provide users with knowledge feedback;

[0048] The knowledge security module is used to encrypt and manage permissions for sensitive information in the knowledge base, using role-based access control and data encryption algorithms to ensure the security and compliance of knowledge;

[0049] The system management module is used to monitor and manage the operating status of the system. It adopts an artificial intelligence-based fault prediction model to automatically detect system anomalies and generate repair suggestions to ensure the high availability and stability of the system.

[0050] The knowledge acquisition module includes a data crawling submodule, a document parsing submodule and a real-time data acquisition submodule, among which;

[0051] The data crawling submodule obtains structured data from web pages, databases, and API interfaces through automated scripts;

[0052] The document parsing submodule uses natural language processing technology to perform semantic analysis and structural processing on the unstructured data in the document, extract key concepts and knowledge points in the text, and store them in a temporary database;

[0053] The real-time data acquisition submodule obtains real-time data through sensors and IoT devices, and performs preliminary analysis and storage on the real-time data based on stream processing technology.

[0054] The knowledge organization module includes a data cleaning submodule, a knowledge classification submodule and a knowledge graph generation submodule, among which;

[0055] The data cleaning submodule uses an anomaly detection algorithm based on machine learning to automatically identify and remove duplicate, erroneous or invalid data;

[0056] The knowledge classification submodule uses a rule-based classification algorithm and convolutional neural network to classify knowledge hierarchically and generate a multi-level knowledge classification system;

[0057] The knowledge graph generation submodule generates a knowledge graph based on the correlation between knowledge, using graph databases and graph algorithms, and mines potential knowledge associations through graph structure analysis.

[0058] The knowledge updating module includes a time series analysis submodule and an adaptive model updating submodule, wherein;

[0059] The time series analysis submodule analyzes the knowledge change trend through the time series model and predicts the future knowledge update needs;

[0060] The adaptive model update submodule dynamically adjusts the model parameters of the knowledge base based on the frequency and weight of new knowledge to ensure the accuracy and timeliness of the knowledge base.

[0061] The knowledge recommendation module includes a collaborative filtering submodule and a deep learning recommendation submodule, where;

[0062] The collaborative filtering submodule recommends relevant knowledge content to users through collaborative filtering algorithms based on the user's historical behavior data;

[0063] The deep learning recommendation submodule provides users with personalized knowledge recommendations through a deep neural network model, combining the user's current query context and historical query records.

[0064] The user interaction module includes a natural language understanding submodule and a speech recognition and synthesis submodule, wherein;

[0065] The natural language understanding submodule uses semantic analysis algorithms to understand the true intent of user queries and converts the user's natural language requests into structured queries;

[0066] The speech recognition and synthesis submodule adopts a deep learning model to realize the user's voice input and voice feedback functions, allowing users to query and acquire knowledge through voice.

[0067] The knowledge security module includes a data encryption submodule and a role access control submodule, wherein;

[0068] The data encryption submodule encrypts the sensitive information stored in the knowledge base using the Advanced Encryption Standard;

[0069] The role access control submodule limits users’ access rights to different types of knowledge according to their permission levels, ensuring the security of sensitive knowledge.

[0070] The knowledge acquisition module works in collaboration with the knowledge organization module. The data crawling and document parsing functions in the knowledge acquisition module are closely integrated with the data cleaning and classification functions in the knowledge organization module, improving the efficiency of knowledge acquisition and organization through automated processes.

[0071] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0072] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A knowledge base management system based on artificial intelligence, characterized in that: It includes knowledge acquisition module, knowledge organization module, knowledge update module, knowledge recommendation module, user interaction module, knowledge security module and system management module, among which; The knowledge acquisition module is used to automatically acquire structured and unstructured data from different data sources, including documents, databases, audio, video and real-time sensor data. The knowledge acquisition module performs semantic analysis on unstructured data through natural language processing algorithms and machine learning models, and extracts core knowledge points therein; The knowledge organization module pre-processes the knowledge extracted by the knowledge acquisition module through data cleaning, deduplication and classification algorithms, hierarchically organizes the knowledge using rule-based classification algorithms and deep learning models, and generates a knowledge graph based on the relevance of the knowledge; The knowledge update module regularly updates the knowledge content in the knowledge base, adopts a time series-based change detection algorithm and an adaptive model update algorithm, automatically identifies new knowledge and outdated knowledge, and incrementally updates the knowledge base; The knowledge recommendation module uses a recommendation algorithm based on collaborative filtering and deep learning based on user behavior and historical query data to provide users with personalized knowledge recommendation services, and dynamically adjusts the recommendation strategy based on user interests and current business scenarios; The user interaction module provides users with multiple interaction methods, including text query, voice query and visual query, supports users to retrieve knowledge through natural language, and understands user intentions through semantic analysis algorithms to provide users with knowledge feedback; The knowledge security module is used to encrypt and manage permissions for sensitive information in the knowledge base, using role-based access control and data encryption algorithms; The system management module is used to monitor and manage the operating status of the system, and adopts an artificial intelligence-based fault prediction model to automatically detect system anomalies and generate repair suggestions.

2. The knowledge base management system based on artificial intelligence according to claim 1, characterized in that: The knowledge acquisition module includes a data crawling submodule, a document parsing submodule and a real-time data acquisition submodule, wherein; The data crawling submodule obtains structured data from web pages, databases and API interfaces through automated scripts; The document parsing submodule performs semantic analysis and structural processing on the unstructured data in the document through natural language processing technology, extracts key concepts and knowledge points in the text, and stores them in a temporary database; The real-time data acquisition submodule acquires real-time data through sensors and IoT devices, and performs preliminary analysis and storage on the real-time data based on stream processing technology.

3. The knowledge base management system based on artificial intelligence according to claim 2 is characterized in that: The knowledge arrangement module includes a data cleaning submodule, a knowledge classification submodule and a knowledge graph generation submodule, wherein; The data cleaning submodule uses an anomaly detection algorithm based on machine learning to automatically identify and remove duplicate, erroneous or invalid data; The knowledge classification submodule adopts a rule-based classification algorithm and a convolutional neural network to classify knowledge hierarchically and generate a multi-level knowledge classification system; The knowledge graph generation submodule generates a knowledge graph based on the correlation between knowledge, using a graph database and a graph algorithm, and mines potential knowledge associations through graph structure analysis.

4. The knowledge base management system based on artificial intelligence according to claim 1, characterized in that: The knowledge updating module includes a time series analysis submodule and an adaptive model updating submodule, wherein; The time series analysis submodule analyzes the knowledge change trend through the time series model and predicts the future knowledge update needs; The adaptive model updating submodule dynamically adjusts the model parameters of the knowledge base based on the occurrence frequency and weight of the new knowledge.

5. The knowledge base management system based on artificial intelligence according to claim 1 is characterized in that: The knowledge recommendation module includes a collaborative filtering submodule and a deep learning recommendation submodule, wherein; The collaborative filtering submodule recommends relevant knowledge content to users through a collaborative filtering algorithm based on the user's historical behavior data; The deep learning recommendation submodule provides personalized knowledge recommendations to users through a deep neural network model combined with the user's current query context and historical query records.

6. The knowledge base management system based on artificial intelligence according to claim 1, characterized in that: The user interaction module includes a natural language understanding submodule and a speech recognition and synthesis submodule, wherein; The natural language understanding submodule understands the real intention of the user's query through a semantic analysis algorithm, and converts the user's natural language request into a structured query; The speech recognition and synthesis submodule adopts a deep learning model to realize the user's speech input and speech feedback functions, allowing the user to query and acquire knowledge through voice.

7. The knowledge base management system based on artificial intelligence according to claim 1 is characterized in that: The knowledge security module includes a data encryption submodule and a role access control submodule, wherein; The data encryption submodule encrypts the sensitive information stored in the knowledge base according to the encryption standard; The role access control submodule limits the user's access rights to different types of knowledge according to the user's authority level.

8. The artificial intelligence-based knowledge base management system according to claim 3, characterized in that: The knowledge acquisition module works in collaboration with the knowledge organization module. The data crawling and document parsing functions in the knowledge acquisition module are closely integrated with the data cleaning and classification functions in the knowledge organization module, thereby improving the efficiency of knowledge acquisition and organization through automated processes.

Images