A network collaborative knowledge management method and system

Abstract

The present invention discloses a network collaborative knowledge management method and system, which includes: classifying and refining the device data to be processed, obtaining multiple knowledge classifications, and the multiple knowledge classifications contain multiple fine-grained knowledge; wherein the multiple fine-grained knowledge contain unstructured knowledge, traversing the multiple fine-grained knowledge, and using hierarchical classification rules to convert the unstructured knowledge into structured knowledge; using a tree structure to construct a knowledge graph from the multiple knowledge classifications and the multiple fine-grained knowledge, wherein the multiple knowledge classifications serve as the root nodes of the knowledge graph, and the multiple fine-grained knowledge serve as the leaf nodes of the knowledge graph. The present invention greatly improves the efficiency of retrieval and reuse of device data by acquiring fine-grained knowledge and converting unstructured knowledge into structured knowledge to form a knowledge graph.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial data processing, and in particular to a network collaborative knowledge management method and system. Background Art

[0002] Industrial knowledge exists in multiple stages such as design, process, production, and maintenance. This knowledge is crucial to every link in industrial production and affects efficiency and quality. Due to the complexity of industrial knowledge, how to effectively acquire, represent, and reuse this knowledge is a major challenge in industrial knowledge management. Current product data management (PDM) or product lifecycle management (PLM) software stores this knowledge in the form of managed files, such as design manuals, design reports, process flows, drawings, maintenance reports, etc. However, this knowledge stored in documents is difficult to directly retrieve and reuse. Generally, only the corresponding files can be found, and the files need to be opened to search for the corresponding knowledge. Summary of the Invention

[0003] The purpose of the present invention is to provide a network collaborative knowledge management method and system to solve the problem of difficulty in acquiring and reusing unstructured knowledge.

[0004] To achieve the above objectives, the present invention provides a network collaborative knowledge management method, comprising:

[0005] Classifying and refining the device data to be processed to obtain multiple knowledge classifications, wherein the multiple knowledge classifications include multiple fine-grained knowledge; wherein the multiple fine-grained knowledge include unstructured knowledge, traversing the multiple fine-grained knowledge, and converting the unstructured knowledge into structured knowledge using hierarchical classification rules;

[0006] A tree structure is used to construct a knowledge graph by combining the multiple knowledge classifications and the multiple fine-grained knowledge, wherein the multiple knowledge classifications serve as root nodes of the knowledge graph and the multiple fine-grained knowledge serve as leaf nodes of the knowledge graph.

[0007] Preferably, the acquiring of multiple knowledge categories, wherein the multiple knowledge categories contain multiple fine-grained knowledge, includes:

[0008] The plurality of knowledge classifications include requirement classification, function classification, behavior classification, structure classification, and derived classification, wherein links are created between the plurality of knowledge classifications;

[0009] By refining the device data to be processed, fine-grained knowledge corresponding to the functional classification and fine-grained knowledge corresponding to the structural classification are obtained.

[0010] Preferably, after obtaining multiple knowledge classifications, the following steps are included:

[0011] According to association rules, links are created between the plurality of knowledge classifications and the plurality of fine-grained knowledge, so that the knowledge classifications are retrieved and linked to corresponding fine-grained knowledge.

[0012] Preferably, the converting the unstructured knowledge into structured knowledge by adopting a hierarchical classification rule comprises:

[0013] The hierarchical classification rules include first-level classification rules, second-level rules, and third-level rules, wherein the first-level classification rules are used to determine descriptive knowledge in unstructured knowledge, the second-level rules are used to determine procedural knowledge in unstructured knowledge, and the third-level rules are used to determine explanatory knowledge in unstructured knowledge;

[0014] The structured knowledge is constructed according to the determined descriptive knowledge, the procedural knowledge, and the explanatory knowledge.

[0015] Preferably, the method of using a tree structure to classify the plurality of the knowledge and construct a knowledge graph from the plurality of the fine-grained knowledge includes:

[0016] A tree structure is used to add nodes to the plurality of knowledge classifications and the plurality of fine-grained knowledge in a visual interface to form the knowledge graph; wherein each node forms an independent ID, type, content, link and attribute;

[0017] Constructing the knowledge graph also includes displaying the three-dimensional model in the form of three-dimensional visualization.

[0018] The present invention also provides a network collaborative knowledge management system, comprising:

[0019] A data processing module is configured to classify and refine the device data to be processed, obtain multiple knowledge classifications, and each of the multiple knowledge classifications includes multiple fine-grained knowledge; wherein each of the multiple fine-grained knowledge includes unstructured knowledge, traverse the multiple fine-grained knowledge, and convert the unstructured knowledge into structured knowledge using a hierarchical classification rule;

[0020] A construction module is used to construct a knowledge graph by using a tree structure to classify multiple knowledge categories and multiple fine-grained knowledge, wherein multiple knowledge categories serve as root nodes of the knowledge graph and multiple fine-grained knowledge serve as leaf nodes of the knowledge graph.

[0021] Preferably, the data processing module is further used to:

[0022] The plurality of knowledge classifications include requirement classification, function classification, behavior classification, structure classification, and derived classification, wherein links are created between the plurality of knowledge classifications;

[0023] By refining the device data to be processed, fine-grained knowledge corresponding to the functional classification and fine-grained knowledge corresponding to the structural classification are obtained.

[0024] Preferably, the network collaborative knowledge management system further includes an association module, which is used to:

[0025] According to association rules, links are created between the plurality of knowledge classifications and the plurality of fine-grained knowledge, so that the knowledge classifications are retrieved and linked to corresponding fine-grained knowledge.

[0026] Preferably, the data processing module is further used to:

[0027] The hierarchical classification rules include first-level classification rules, second-level rules, and third-level rules, wherein the first-level classification rules are used to determine descriptive knowledge in unstructured knowledge, the second-level rules are used to determine procedural knowledge in unstructured knowledge, and the third-level rules are used to determine explanatory knowledge in unstructured knowledge;

[0028] The structured knowledge is constructed according to the determined descriptive knowledge, the procedural knowledge, and the explanatory knowledge.

[0029] Preferably, the building block is further used to:

[0030] A tree structure is used to add nodes to the plurality of knowledge classifications and the plurality of fine-grained knowledge in a visual interface to form the knowledge graph; wherein each node forms an independent ID, type, content, link and attribute;

[0031] Constructing the knowledge graph also includes displaying the three-dimensional model in the form of three-dimensional visualization

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention classifies and refines the device data to be processed, obtains multiple knowledge classifications, and the multiple knowledge classifications contain multiple fine-grained knowledge; wherein, the multiple fine-grained knowledge contain unstructured knowledge, traverses the multiple fine-grained knowledge, adopts hierarchical classification rules to convert the unstructured knowledge into structured knowledge, and adopts a tree structure to construct a knowledge graph from the multiple knowledge classifications and the multiple fine-grained knowledge, wherein the multiple knowledge classifications serve as the root nodes of the knowledge graph, and the multiple fine-grained knowledge serve as the leaf nodes of the knowledge graph. The present invention greatly improves the efficiency of retrieval and reuse of device data by acquiring fine-grained knowledge and converting unstructured knowledge into structured knowledge to form a knowledge graph.

[0034] Furthermore, hierarchical classification rules are used to convert unstructured knowledge into structured knowledge and display it in a three-dimensional visual form, which greatly facilitates data recording and storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the implementation. Obviously, the drawings described below are only some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 This is a flowchart of a network collaborative knowledge management method provided by an embodiment of the present invention;

[0037] Figure 2 This is a flowchart of a network collaborative knowledge management method provided by an embodiment of the present invention;

[0038] Figure 3 It is a structural diagram of a network collaborative knowledge management system provided by a certain embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0040] It should be understood that the step numbers used herein are only for convenience of description and are not intended to limit the order in which the steps are to be executed.

[0041] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0042] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0043] The term "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items.

[0044] See also Figure 1 , a certain embodiment of the present invention provides a network collaborative knowledge management method. Figure 1 As shown, the network collaborative knowledge management method includes steps S10 to S20. The specific steps are as follows:

[0045] S10: Classify and refine the device data to be processed to obtain multiple knowledge classifications, and the multiple knowledge classifications contain multiple fine-grained knowledge; wherein the multiple fine-grained knowledge contain unstructured knowledge, traverse the multiple fine-grained knowledge, and use hierarchical classification rules to convert the unstructured knowledge into structured knowledge.

[0046] Specifically, taking mechanical equipment as an example, the equipment data to be processed is classified and refined into multiple knowledge categories, including demand classification, function classification, behavior classification, structure classification and derivative classification, wherein links are created between the multiple knowledge categories.

[0047] Fine-grained knowledge is obtained by decomposing a piece of information. The most basic method is to decompose a piece of information into unambiguous information units, that is, knowledge elements, by dividing it into subject, predicate and object.

[0048] Hierarchical classification rules include first-level, second-level, and third-level rules. First-level rules identify descriptive knowledge within unstructured knowledge, second-level rules identify procedural knowledge within unstructured knowledge, and third-level rules identify explanatory knowledge within unstructured knowledge. Structured knowledge is then constructed based on the identified descriptive, procedural, and explanatory knowledge. Specifically, knowledge related to a particular device design is classified and refined based on five aspects: requirements classification, function classification, behavior classification, structure classification, and derivative classification, systematically representing knowledge elements and their interrelationships. This knowledge is organized and recorded in a tree-like structure within the knowledge management system. Functional or structural decomposition is performed to break down knowledge into sub-functions or components. Then, Know-What (what) is used as the first-level rules, Know-How (how) as the second-level rules, and Know-Why (why) as the third-level rules. These three levels describe specific knowledge points and structure the unstructured knowledge.

[0049] Unstructured knowledge originates from engineers' minds, work notes, chat records, etc. The present invention provides a method for converting unstructured knowledge into structured knowledge, namely, using first-level rules, second-level rules, and third-level rules to decompose and record this unstructured knowledge, thereby structuring it for convenient computational identification and retrieval reuse.

[0050] Know-What (what) is the first-level rule, Know-How (how to do it) is the second-level rule, and Know-Why (why) is the third-level rule. These three levels are mainly divided according to the type of knowledge element. Know-what is mainly used to represent descriptive knowledge and can be used in most situations to describe a certain object. Know-how is for step-by-step knowledge, describing the method and process of solving a certain problem. Know-why is explanatory knowledge, recording and explaining the internal reasons for a certain phenomenon or a certain solution, focusing on explaining the reasons. These three are actually used as labels to record knowledge elements. When searching the knowledge graph, you can quickly locate relevant knowledge through what, how, and why.

[0051] See also Figure 2 In a specific embodiment, after obtaining multiple knowledge categories in step S10, the method further includes:

[0052] S30: creating links between the plurality of the knowledge classifications and the plurality of the fine-grained knowledge according to association rules, so as to retrieve the knowledge classification links to the corresponding fine-grained knowledge.

[0053] Fine-grained knowledge is obtained by decomposing a piece of information. The most basic method is to decompose a piece of information into unambiguous information units, that is, knowledge elements, by dividing it into subject, predicate and object.

[0054] Multiple knowledge classifications include demand classification, function classification, behavior classification, structure classification and derivative classification. Each classification corresponds to multiple fine-grained knowledge. Each fine-grained knowledge is then converted from unstructured knowledge to structured knowledge through hierarchical classification rules.

[0055] Know-What (what) is the first-level rule, Know-How (how to do it) is the second-level rule, and Know-Why (why) is the third-level rule. These three levels are mainly divided according to the type of knowledge elements. Know-what is mainly used to represent descriptive knowledge and can be used in most situations to describe a certain object. Know-how is for step-by-step knowledge, describing the method and process of solving a certain problem. Know-why is explanatory knowledge, recording and explaining the internal reasons for a certain phenomenon or a certain solution, focusing on explaining the reasons. These three are actually used as labels to record knowledge elements. When searching the knowledge graph, creating links between multiple knowledge categories and multiple fine-grained knowledge can quickly locate relevant knowledge through what, how, and why.

[0056] S20: Use a tree structure to construct a knowledge graph by combining the multiple knowledge classifications and the multiple fine-grained knowledge, wherein the multiple knowledge classifications serve as root nodes of the knowledge graph, and the multiple fine-grained knowledge serve as leaf nodes of the knowledge graph.

[0057] Specifically, a tree structure is used to add nodes to multiple knowledge classifications and multiple fine-grained knowledge in a visual interface to form a knowledge graph, wherein each node forms an independent ID, type, content, link and attribute. Constructing a knowledge graph also includes displaying a three-dimensional model in the form of three-dimensional visualization.

[0058] The knowledge graph records relevant knowledge in the form of knowledge elements and establishes links between them to construct a knowledge structure network and knowledge graph. Related device files can be stored as attachments. This allows searches to directly jump to a specific knowledge point, greatly improving the efficiency of knowledge retrieval and reuse. Furthermore, a wealth of empirical knowledge is accumulated during work. Converting this unstructured knowledge into structured knowledge and systematically recording and storing it greatly improves the efficiency of knowledge retrieval and reuse.

[0059] On the one hand, the present invention classifies equipment data and then directly records fine-grained knowledge in the knowledge graph. At the same time, it also displays files related to fine-grained knowledge and corresponding three-dimensional models of product parts to facilitate subsequent retrieval and search. On the other hand, it converts unstructured knowledge into structured knowledge through hierarchical classification rules, greatly solving the problem of knowledge reuse. The unstructured knowledge and experience in the minds of engineers are systematically recorded in the form of Know-what, Know-how, and Know-why. It improves the management and reuse efficiency of industrial knowledge and lays the foundation for knowledge automation in industrial production processes.

[0060] In a specific embodiment, taking a mechanical device such as a shield machine as an example, the process of acquiring and representing knowledge using the method described in the present invention is divided into the following aspects:

[0061] 1. Functional / structural decomposition.

[0062] Decompose the equipment into various systems (such as power system, transmission system, execution system, lubrication system, etc.), subsystems, mechanisms, components, and parts according to their functions.

[0063] 2. When the structure is decomposed into the smallest unit, such as parts, the three forms of What, How, and Why will be used to record the three knowledge elements of "what", "how", and "why".

[0064] 3. For objects that record knowledge, they are displayed in a three-dimensional visual form in the box on the left side of the system webpage, and the corresponding three-dimensional model is displayed through Canvas technology to facilitate engineers' understanding of the recorded knowledge.

[0065] 4. The backend uses the Neo4j graph database to represent the knowledge recorded on the front-end web pages and generate a knowledge graph. The nodes in the graph database correspond one-to-one with the nodes recorded on the front-end web pages, and the hierarchical relationships of the front end are recorded through the semantic relationships of the database.

[0066] 5. Knowledge reuse is achieved through semantic search and intelligent question-answering / recommendations. Reuse involves semantic search to quickly search for relevant knowledge elements. Based on the engineer's work context, it finds knowledge representations relevant to their tasks, allowing them to selectively apply the retrieved knowledge elements. Intelligent question-answering, on the other hand, retrieves the knowledge engineers seek through a question-and-answer approach. Intelligent recommendations use a relevant recommendation algorithm to push the retrieved knowledge elements to engineers, sorted by similarity.

[0067] See also Figure 3 Another embodiment of the present invention provides a network collaborative knowledge management system, including:

[0068] The data processing module 11 is configured to classify and refine the device data to be processed, obtain multiple knowledge classifications, and each of the multiple knowledge classifications includes multiple fine-grained knowledge; wherein each of the multiple fine-grained knowledge includes unstructured knowledge, traverse the multiple fine-grained knowledge, and convert the unstructured knowledge into structured knowledge using a hierarchical classification rule;

[0069] Construction module 12 is used to construct a knowledge graph by using a tree structure to classify multiple knowledge categories and multiple fine-grained knowledge, wherein multiple knowledge categories serve as root nodes of the knowledge graph and multiple fine-grained knowledge serve as leaf nodes of the knowledge graph.

[0070] Preferably, the data processing module is further configured to: the plurality of knowledge classifications include requirement classification, function classification, behavior classification, structure classification, and derivative classification, wherein links are created between the plurality of knowledge classifications;

[0071] By refining the device data to be processed, fine-grained knowledge corresponding to the functional classification and fine-grained knowledge corresponding to the structural classification are obtained.

[0072] Preferably, the network collaborative knowledge management system further includes an association module, which is used to: create links between multiple knowledge classifications and multiple fine-grained knowledge according to association rules, so as to retrieve the knowledge classification links to the corresponding fine-grained knowledge.

[0073] Preferably, the data processing module is further configured to: the hierarchical classification rules include first-level classification rules, second-level rules, and third-level rules, wherein the first-level classification rules are used to determine descriptive knowledge in unstructured knowledge, the second-level rules are used to determine procedural knowledge in unstructured knowledge, and the third-level rules are used to determine explanatory knowledge in unstructured knowledge;

[0074] The structured knowledge is constructed according to the determined descriptive knowledge, the procedural knowledge, and the explanatory knowledge.

[0075] Preferably, the construction module is further configured to: add nodes to the plurality of the knowledge classifications and the plurality of the fine-grained knowledge in a visual interface using a tree structure to form the knowledge graph; wherein each node forms an independent ID, type, content, link, and attribute;

[0076] Constructing the knowledge graph also includes displaying the three-dimensional model in the form of three-dimensional visualization.

[0077] For the specific definition of the network collaborative knowledge management system, please refer to the definition of the network collaborative knowledge management method above, which will not be repeated here. The various modules in the above-mentioned network collaborative knowledge management system can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0078] The above is 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 principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A network collaborative knowledge management method, characterized in that: include: Classifying and refining the device data to be processed to obtain multiple knowledge classifications, wherein the multiple knowledge classifications include multiple fine-grained knowledge; wherein the multiple fine-grained knowledge include unstructured knowledge, traversing the multiple fine-grained knowledge, and converting the unstructured knowledge into structured knowledge using hierarchical classification rules; A tree structure is used to construct a knowledge graph for multiple knowledge classifications and multiple fine-grained knowledge, wherein multiple knowledge classifications serve as root nodes of the knowledge graph and multiple fine-grained knowledge serve as leaf nodes of the knowledge graph, including: using a tree structure to add nodes for multiple knowledge classifications and multiple fine-grained knowledge in a visual interface to form the knowledge graph; wherein each node forms an independent ID, type, content, link and attribute; constructing the knowledge graph also includes displaying a three-dimensional model in the form of three-dimensional visualization.

2. The network collaborative knowledge management method according to claim 1, characterized in that: The acquiring of multiple knowledge categories, wherein the multiple knowledge categories contain multiple fine-grained knowledge, includes: The plurality of knowledge classifications include requirement classification, function classification, behavior classification, structure classification, and derived classification, wherein links are created between the plurality of knowledge classifications; By refining the device data to be processed, fine-grained knowledge corresponding to the functional classification and fine-grained knowledge corresponding to the structural classification are obtained.

3. The network collaborative knowledge management method according to claim 2, characterized in that: After acquiring multiple knowledge categories, including: According to association rules, links are created between the plurality of knowledge classifications and the plurality of fine-grained knowledge, so that the knowledge classifications are retrieved and linked to corresponding fine-grained knowledge.

4. The network collaborative knowledge management method according to claim 1, characterized in that: The converting of the unstructured knowledge into structured knowledge by adopting hierarchical classification rules includes: The hierarchical classification rules include first-level classification rules, second-level rules, and third-level rules, wherein the first-level classification rules are used to determine descriptive knowledge in unstructured knowledge, the second-level rules are used to determine procedural knowledge in unstructured knowledge, and the third-level rules are used to determine explanatory knowledge in unstructured knowledge; The structured knowledge is constructed according to the determined descriptive knowledge, the procedural knowledge, and the explanatory knowledge.

5. A network collaborative knowledge management system, characterized in that: include: A data processing module is configured to classify and refine the device data to be processed, obtain multiple knowledge classifications, and each of the multiple knowledge classifications includes multiple fine-grained knowledge; wherein each of the multiple fine-grained knowledge includes unstructured knowledge, traverse the multiple fine-grained knowledge, and convert the unstructured knowledge into structured knowledge using a hierarchical classification rule; A construction module is used to construct a knowledge graph by using a tree structure to classify multiple knowledge categories and multiple fine-grained knowledge, wherein multiple knowledge categories serve as root nodes of the knowledge graph, and multiple fine-grained knowledge serve as leaf nodes of the knowledge graph, including: using a tree structure to add nodes to the multiple knowledge categories and multiple fine-grained knowledge in a visual interface to form the knowledge graph; wherein each node forms an independent ID, type, content, link and attribute; constructing the knowledge graph also includes displaying a three-dimensional model in the form of three-dimensional visualization.

6. The network collaborative knowledge management system according to claim 5, characterized in that: The data processing module is further used to: The plurality of knowledge classifications include requirement classification, function classification, behavior classification, structure classification, and derived classification, wherein links are created between the plurality of knowledge classifications; By refining the device data to be processed, fine-grained knowledge corresponding to the functional classification and fine-grained knowledge corresponding to the structural classification are obtained.

7. The network collaborative knowledge management system according to claim 6, characterized in that: It also includes an association module, wherein the association module is used to: According to association rules, links are created between the plurality of knowledge classifications and the plurality of fine-grained knowledge, so that the knowledge classifications are retrieved and linked to corresponding fine-grained knowledge.

8. The network collaborative knowledge management system according to claim 5, characterized in that: The data processing module is further used to: The hierarchical classification rules include first-level classification rules, second-level rules, and third-level rules, wherein the first-level classification rules are used to determine descriptive knowledge in unstructured knowledge, the second-level rules are used to determine procedural knowledge in unstructured knowledge, and the third-level rules are used to determine explanatory knowledge in unstructured knowledge; The structured knowledge is constructed according to the determined descriptive knowledge, the procedural knowledge, and the explanatory knowledge.

Images