Intelligent industrial chain description method and system based on thinking map

Abstract

The invention provides an industrial chain intelligent description method and system based on a thinking map. The method comprises the following steps: determining entity attributes corresponding to different industrial entities in an industrial chain according to multi-source industrial data and an entity relationship between the different industrial entities to construct an industrial chain ontology model, in the process of operating the industrial chain ontology model, using a natural language technology and a graph algorithm extraction technology to obtain operation knowledge corresponding to each industrial entity, generating a knowledge database, using the knowledge database to derive an industrial chain structure and an industrial chain risk of an industrial chain, using the industrial chain ontology model to simulate the industrial chain risk, and using the industrial chain ontology model to simulate the industrial chain risk. According to the method, a plurality of risk features included in an industrial chain structure are determined, a visualization technology is utilized to simulate the industrial chain structure and a scene corresponding to the risk features, a real-time knowledge system of an industrial chain is obtained and displayed, and work such as supply chain optimization and industrial planning can be better served by constructing the dynamically updated industrial chain knowledge system.

Description

Technical Field

[0001] The present invention relates to the field of knowledge description technology, and in particular to a method and system for intelligent description of an industrial chain based on a mind map. Background Art

[0002] The industrial chain refers to the interconnectedness of all links and enterprises involved in the entire process, from raw material procurement, production and processing, logistics and distribution, to sales, all the way to the end consumer. The industrial chain demonstrates how each link works together to support the delivery of the final product or service. It can impact a company's cost structure, market competitiveness, and supply chain risk management. Effective industrial chain management not only helps companies improve operational efficiency but also strengthens their competitive position in the global market.

[0003] In general, the industrial chain is a complex and highly interconnected network. The collaboration and efficiency between each link directly affect the quality of the final product and the competitiveness of the enterprise. Therefore, many means of analyzing the operation process of the industrial chain have been derived. However, the current means have the following defects: 1. The description results are too simple, which is not conducive to users to obtain useful information; 2. The description process delay is too large, and the results obtained are often lagging; 3. The cost is too high, which is not conducive to large-scale popularization.

[0004] Therefore, the present invention provides an intelligent description method and system for an industrial chain based on a mind map. Summary of the Invention

[0005] The present invention provides an intelligent description method and system for the industrial chain based on the mind map, which can better serve the tasks such as supply chain optimization and industrial planning by constructing a dynamically updated industrial chain knowledge system.

[0006] The present invention provides an intelligent description method of an industrial chain based on a mind map, including:

[0007] Step 1: Determine the entity attributes corresponding to different industrial entities in the industrial chain and the entity relationships between different industrial entities based on multi-source industrial data, and build an industrial chain ontology model of the industrial chain;

[0008] Step 2: In the process of running the industrial chain ontology model, natural language technology and graph algorithm extraction technology are used to obtain the operation knowledge corresponding to each of the industrial entities and generate a knowledge database;

[0009] Step 3: deriving the industrial chain structure and industrial chain risks of the industrial chain using the knowledge database, simulating the industrial chain risks using the industrial chain ontology model, and determining a number of risk features contained in the industrial chain structure;

[0010] Step 4: Use visualization technology to simulate the scenario of the industrial chain structure and corresponding risk characteristics, obtain the real-time knowledge system of the industrial chain and display it.

[0011] In one practicable manner,

[0012] The step 1 comprises:

[0013] Step 11: Collect a number of industry data generated in the industry chain, construct multi-source industry data of the industry chain, map the multi-source industry data into a data entity dictionary, determine a number of descriptive data entities contained in the multi-source industry data, and the descriptive content text corresponding to each of the descriptive data entities;

[0014] Step 12: Locate each of the descriptive data entities in the multi-source industry data, construct a data logic diagram of the industry chain based on the descriptive content text, and deduce a number of non-salient data entities included in the industry chain based on the presentation logic of each of the descriptive data entities in the data logic diagram;

[0015] Step 13: Determine the non-salient content text corresponding to the non-salient data entity based on the descriptive content text corresponding to the descriptive data entity and the data logic diagram, determine a number of industrial entities included in the industrial chain, and determine the entity attributes corresponding to each of the industrial entities based on the corresponding content text;

[0016] Step 14: Construct a model framework based on the data logic diagram, determine the entity function corresponding to the industrial entity based on the entity attributes, add the entity function to the model framework for model optimization, and generate an industrial chain ontology model of the industrial chain.

[0017] In one practicable manner,

[0018] The process of collecting a number of industrial data generated in the industrial chain and constructing multi-source industrial data of the industrial chain includes:

[0019] respectively collecting industrial data generated by each data source in the industrial chain, converting the industrial data into binary data frames, and determining the data generation frequency corresponding to the data source according to the frame header of each binary data frame;

[0020] constructing a multi-source data structure according to the data generation frequency;

[0021] Determining the data generation type corresponding to the data source according to the frame tail of each binary data frame;

[0022] The data generation type is used to adjust the structural attributes corresponding to each structural position in the multi-source data structure, and each industrial data is input into the adjusted multi-source data structure respectively, and the industrial data is connected with the corresponding structural position to generate multi-source industrial data of the industrial chain.

[0023] In one practicable manner,

[0024] The step 2 comprises:

[0025] Step 21: Run the industry chain ontology model with each of the industry entities as the center to obtain entity operation information corresponding to each of the industry entities, construct a local mind map corresponding to the industry entity based on the entity operation information, and mark several operation items of the industry entity in the local mind map;

[0026] Step 22: The industry brain derives the overall mind map of the industry chain based on the associated running items between different local mind maps, uses the natural language technology to describe the overall mind map, and obtains several description languages ​​of the industry chain. A corresponding priority is assigned to each description language based on the description scope corresponding to each description language;

[0027] Step 23: Utilizing the graph algorithm extraction technology to extract the entity interaction spanning tree corresponding to each of the industrial entities in the overall mind map, and utilizing the description language to adjust and combine the entity interaction spanning trees according to the order of priority to generate a language spanning tree;

[0028] Step 24: Searching the language generation tree for the operation knowledge generated by each of the industrial entities during operation, classifying and summarizing the operation knowledge, and generating a knowledge database for the industrial chain.

[0029] In one practicable manner,

[0030] The step 3 comprises:

[0031] Step 31: constructing a physical industry chain node with corresponding attributes based on the physical attributes corresponding to each of the industrial entities, deducing the industrial execution link corresponding to each of the physical industry chain nodes based on the knowledge database, and selecting virtual industry chain nodes that have an interactive relationship with the physical industry chain nodes in the industrial execution links;

[0032] Step 32: Determine the node execution function corresponding to each of the physical industry chain nodes and each of the virtual industry chain nodes based on the industry execution link, determine the function connection sequence between different industry chain nodes, and construct the industry chain structure of the industry chain;

[0033] Step 33: Determine the node relationships between different industry chain nodes based on the industry chain structure, perform data quality analysis on the knowledge database, obtain several data defects in the industry chain and determine corresponding defect nodes, determine several associated defect nodes in the industry chain based on the node relationships, and deduce the industry chain risk of the industry chain based on the corresponding node attributes;

[0034] Step 34: Use the industrial chain ontology model to simulate the industrial chain risk, obtain the risk presentation position and risk presentation result corresponding to each industrial chain risk, mark the risk presentation result on the risk presentation position corresponding to the industrial chain structure, and capture the corresponding risk characteristics in the industrial chain structure.

[0035] In one practicable manner,

[0036] Also includes:

[0037] The risk outbreak moment and risk outbreak consequences of each risk feature in the industrial chain structure are derived, and a risk visualization dynamic scene of the industrial chain is generated and displayed.

[0038] In one practicable manner,

[0039] The step 4 comprises:

[0040] Step 41: using the visualization technology to simulate each risk feature of the industrial chain structure, and obtaining visual presentation information of each risk feature;

[0041] Step 42: spatially combining the visual presentation information according to the industrial chain structure to obtain a visual operation scene of the industrial chain;

[0042] Step 43: Summarize a number of operation knowledge of the industrial chain in the visual operation scene, generate a real-time knowledge system of the industrial chain and display it.

[0043] In one practicable manner,

[0044] Also includes:

[0045] Retrieving corresponding target-related knowledge in the real-time knowledge system according to the retrieval instruction issued by the user;

[0046] Converting the target-related knowledge into a plurality of knowledge sequences, and identifying the relevant knowledge corresponding to each of the knowledge sequences in the real-time knowledge system;

[0047] Taking each of the knowledge sequences as a starting point, respectively, performing knowledge traversal on the corresponding related knowledge to obtain a plurality of knowledge point sets of each of the industrial chains;

[0048] The industry chain ontology model is used to perform knowledge reasoning on each of the knowledge point sets, and the knowledge graph corresponding to each of the knowledge point sets is obtained and displayed.

[0049] The present invention provides an intelligent description system for an industrial chain based on a mind map, comprising:

[0050] A model building module is used to determine the entity attributes corresponding to different industrial entities in the industrial chain and the entity relationships between different industrial entities based on multi-source industrial data, and to build an industrial chain ontology model of the industrial chain;

[0051] A knowledge extraction module is used to obtain the operation knowledge corresponding to each of the industrial entities by using natural language technology and graph algorithm extraction technology during the operation of the industrial chain ontology model, and generate a knowledge database;

[0052] a risk identification module, configured to derive the industrial chain structure and industrial chain risks of the industrial chain using the knowledge database, simulate the industrial chain risks using the industrial chain ontology model, and determine a number of risk features contained in the industrial chain structure;

[0053] The industry description module is used to simulate the scenario of the industry chain structure and corresponding risk characteristics using visualization technology, obtain the real-time knowledge system of the industry chain and display it.

[0054] In one practicable manner,

[0055] The model building module includes:

[0056] A text recognition unit is used to collect a plurality of industrial data generated in the industrial chain, construct multi-source industrial data of the industrial chain, map the multi-source industrial data into a data entity dictionary, and determine a plurality of descriptive data entities contained in the multi-source industrial data, as well as a descriptive content text corresponding to each of the descriptive data entities;

[0057] an entity determination unit, configured to locate each of the descriptive data entities in the multi-source industry data, construct a data logic diagram of the industry chain based on the descriptive content text, and deduce a number of non-salient data entities included in the industry chain based on the presentation logic of each of the descriptive data entities in the data logic diagram;

[0058] an attribute determination unit, configured to derive the non-salient content text corresponding to the non-salient data entity based on the descriptive content text corresponding to the descriptive data entity in combination with the data logic diagram, determine a plurality of industrial entities included in the industrial chain, and determine the entity attribute corresponding to each of the industrial entities based on the corresponding content text;

[0059] A model building unit is used to build a model framework according to the data logic diagram, determine the entity function corresponding to the industrial entity according to the entity attributes, add the entity function to the model framework for model optimization, and generate an industrial chain ontology model of the industrial chain.

[0060] The achievable beneficial effects of the above technical solution are: by utilizing the multi-source industrial data generated by the industrial chain to determine the entity attributes of different industrial entities and the entity relationships between different industrial entities, an industrial chain ontology model that can run synchronously with the industrial chain is constructed, and the operation knowledge of each industrial entity presented during the operation of the industrial chain ontology model is obtained through natural language technology and graph algorithm extraction technology, and a knowledge database of the industrial chain is constructed, which can not only obtain the knowledge data of the industrial chain, but also store the data in a unified manner to reduce the risk of data loss. Then, the knowledge database is used to deduce the industrial structure and industrial risks of the industrial chain, and the risk characteristics contained in the industrial chain structure are further determined by simulation. In order to more intuitively show the operation of the industrial chain to users, visualization technology is used to present the risk scenarios in the industrial chain structure, and a real-time knowledge system of the industrial chain is constructed for user reference. In this way, synchronous analysis can be performed during the operation of the industrial chain, and the structure, risks and knowledge generated by the industrial chain during its operation can be presented to users, thereby improving the efficiency and accuracy of users in obtaining relevant knowledge of the industrial chain.

[0061] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0062] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0064] Figure 1 Schematic diagram of the workflow of the method for intelligent description of the industrial chain based on the mind map in an embodiment of the present invention;

[0065] Figure 2 This is a schematic diagram of the composition of the industry chain intelligent description system based on the mind map in an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0067] Example 1

[0068] This embodiment provides an intelligent description method of the industrial chain based on the mind map, such as Figure 1 As shown, including:

[0069] Step 1: Determine the entity attributes corresponding to different industrial entities in the industrial chain and the entity relationships between different industrial entities based on multi-source industrial data, and build an industrial chain ontology model of the industrial chain;

[0070] Step 2: In the process of running the industrial chain ontology model, natural language technology and graph algorithm extraction technology are used to obtain the operation knowledge corresponding to each of the industrial entities and generate a knowledge database;

[0071] Step 3: deriving the industrial chain structure and industrial chain risks of the industrial chain using the knowledge database, simulating the industrial chain risks using the industrial chain ontology model, and determining a number of risk features contained in the industrial chain structure;

[0072] Step 4: Use visualization technology to simulate the scenario of the industrial chain structure and corresponding risk characteristics, obtain the real-time knowledge system of the industrial chain and display it.

[0073] In this example, the industry entity represents the entity that performs the corresponding work in the industry chain;

[0074] In this example, the entity attribute represents the department to which the industrial entity belongs. For example, industrial entity A belongs to the logistics department, and industrial entity B belongs to the sales department.

[0075] In this example, the entity relationships represent the working relationships between different industrial entities;

[0076] In this example, the industrial chain ontology model represents a model used to simulate the operation process of the industrial chain;

[0077] In this instance, natural language technology refers to the technology that converts the data generated by the industrial chain ontology model into human language;

[0078] In this example, the graph algorithm extraction technology represents the process of extracting the graph structure of industrial entities from the industrial chain ontology model;

[0079] In this example, the knowledge database represents the collection of data knowledge generated during the operation of the industrial chain;

[0080] In this example, the industrial chain structure refers to the structure composed of the arrangement of various entities in the industrial chain;

[0081] In this example, the industry chain risk refers to the unsafe phenomena that occur during the operation of the industry chain;

[0082] In this example, the real-time knowledge system refers to the operating system composed of various data knowledge generated during the operation of the industrial chain.

[0083] The working principle and beneficial effects of the above technical solution are as follows: by utilizing the multi-source industrial data generated by the industrial chain to determine the entity attributes of different industrial entities and the entity relationships between different industrial entities, an industrial chain ontology model that can run synchronously with the industrial chain is constructed. Natural language technology and graph algorithm extraction technology are used to obtain the operation knowledge of each industrial entity presented during the operation of the industrial chain ontology model, and a knowledge database of the industrial chain is constructed. This can not only obtain the knowledge data of the industrial chain, but also store the data in a unified manner to reduce the risk of data loss. The knowledge database is then used to deduce the industrial structure and industrial risks of the industrial chain, and the risk characteristics contained in the industrial chain structure are further determined through simulation. In order to more intuitively show the operation of the industrial chain to users, visualization technology is used to present the risk scenarios in the industrial chain structure, and a real-time knowledge system of the industrial chain is constructed for user reference. In this way, synchronous analysis can be performed during the operation of the industrial chain, presenting the structure, risks and knowledge generated by the industrial chain during its operation to users, thereby improving the efficiency and accuracy of users in obtaining relevant knowledge of the industrial chain.

[0084] Example 2

[0085] On the basis of Example 1, the method for intelligent description of the industrial chain based on the mind map, step 1 includes:

[0086] Step 11: Collect a number of industry data generated in the industry chain, construct multi-source industry data of the industry chain, map the multi-source industry data into a data entity dictionary, determine a number of descriptive data entities contained in the multi-source industry data, and the descriptive content text corresponding to each of the descriptive data entities;

[0087] Step 12: Locate each of the descriptive data entities in the multi-source industry data, construct a data logic diagram of the industry chain based on the descriptive content text, and deduce a number of non-salient data entities included in the industry chain based on the presentation logic of each of the descriptive data entities in the data logic diagram;

[0088] Step 13: Determine the non-salient content text corresponding to the non-salient data entity based on the descriptive content text corresponding to the descriptive data entity and the data logic diagram, determine a number of industrial entities included in the industrial chain, and determine the entity attributes corresponding to each of the industrial entities based on the corresponding content text;

[0089] Step 14: Construct a model framework based on the data logic diagram, determine the entity function corresponding to the industrial entity based on the entity attributes, add the entity function to the model framework for model optimization, and generate an industrial chain ontology model of the industrial chain.

[0090] In this example, the data entity dictionary contains the correspondence between several industry entities and their related expression data;

[0091] In this example, industrial data refers to the data generated by different data sources during the operation of the industrial chain;

[0092] In this example, multi-source industry data refers to a structure that aggregates data generated by different data sources in the industry chain, where the data sources can be industry entities;

[0093] In this example, the description data entity represents the industry entity mentioned in the multi-source industry data;

[0094] In this instance, the description content text represents a text used to describe basic information of a description data entity;

[0095] In this example, the data logic diagram represents a diagram used to present the logical relationship between different descriptive data entities in the industrial chain;

[0096] In this example, a non-significant data entity represents an industrial entity that exists in the industrial chain but is not currently operating.

[0097] In this example, entity functions represent functions that an industrial entity can perform.

[0098] The working principle and beneficial effects of the above technical solution are as follows: by aggregating several industrial data generated in the industrial chain to generate multi-source industrial data for the industrial chain, the data entity dictionary is used to determine the descriptive data entities and their descriptive content texts contained in the multi-source industrial data, and then the data logic diagram of the industrial chain is constructed according to the position of the descriptive data entities in the multi-source industrial data combined with the descriptive content text, thereby deducing the non-significant data entities contained in the industrial chain. In this way, all industrial entities contained in the industrial chain have been extracted, and the entity attributes of the industrial entities are further determined in combination with the corresponding content text. Finally, a model framework is established according to the logical diagram, and the entity function tags of the industrial entities are marked in it for model optimization, thereby generating an industrial chain ontology model of the industrial chain. In this way, not only can the industrial entities be located in a short time, but the industrial entities can also be described accordingly, thereby constructing and optimizing the model to achieve the purpose of model construction, and the constructed model contains all industrial entities, and each industrial entity can be processed and analyzed subsequently.

[0099] Example 3

[0100] Based on Example 2, the method for intelligently describing an industrial chain based on a mind map collects a number of industrial data generated in the industrial chain and constructs multi-source industrial data of the industrial chain, including:

[0101] respectively collecting industrial data generated by each data source in the industrial chain, converting the industrial data into binary data frames, and determining the data generation frequency corresponding to the data source according to the frame header of each binary data frame;

[0102] constructing a multi-source data structure according to the data generation frequency;

[0103] Determining the data generation type corresponding to the data source according to the frame tail of each binary data frame;

[0104] The data generation type is used to adjust the structural attributes corresponding to each structural position in the multi-source data structure, and each industrial data is input into the adjusted multi-source data structure respectively, and the industrial data is connected with the corresponding structural position to generate multi-source industrial data of the industrial chain.

[0105] In this example, the binary data frame consists of a frame header, a data portion, a checksum, and a frame trailer;

[0106] In this instance, data generation frequency indicates the frequency with which a data source generates industry data;

[0107] In this example, the multi-source data structure represents a data format structure of multi-source data constructed according to generation frequencies of different data sources.

[0108] The working principle and beneficial effects of the above technical solution: In order to ensure the validity of multi-source data, the industrial data generated by the industrial chain is first converted into a binary data frame, and then the data generation frequency of each data source is analyzed to construct a multi-source data structure, and the data generation type of the data source is determined. The industrial data is input into the multi-source data structure to connect the industrial data with the structural position, and the multi-source industrial data of the industrial chain is constructed. In this way, the time of data generation can be estimated, and then corresponding capture and combination are performed to generate multi-source industrial data of the industrial chain to facilitate subsequent modeling work.

[0109] Example 4

[0110] On the basis of Example 1, the method for intelligent description of the industrial chain based on the mind map, step 2 includes:

[0111] Step 21: Run the industry chain ontology model with each of the industry entities as the center to obtain entity operation information corresponding to each of the industry entities, construct a local mind map corresponding to the industry entity based on the entity operation information, and mark several operation items of the industry entity in the local mind map;

[0112] Step 22: The industry brain derives the overall mind map of the industry chain based on the associated running items between different local mind maps, uses the natural language technology to describe the overall mind map, and obtains several description languages ​​of the industry chain. A corresponding priority is assigned to each description language based on the description scope corresponding to each description language;

[0113] Step 23: Utilizing the graph algorithm extraction technology to extract the entity interaction spanning tree corresponding to each of the industrial entities in the overall mind map, and utilizing the description language to adjust and combine the entity interaction spanning trees according to the order of priority to generate a language spanning tree;

[0114] Step 24: Searching the language generation tree for the operation knowledge generated by each of the industrial entities during operation, classifying and summarizing the operation knowledge, and generating a knowledge database for the industrial chain.

[0115] In this example, the local mind map represents a mind map centered on one industrial entity;

[0116] In this instance, the industrial brain represents comprehensive digital technologies such as big data, artificial intelligence, and cloud computing;

[0117] In this example, the operation project refers to the project performed by the industrial entity in the process of operating the industrial chain;

[0118] In this example, the description language refers to the language used to describe the operation process of the industrial chain;

[0119] In this instance, the description scope indicates a scope expressed by a description language;

[0120] In this example, the entity interaction spanning tree represents a binary tree consisting of data knowledge generated when different industrial entities interact;

[0121] In this example, the language spanning tree represents a binary tree obtained by interactively processing the description language.

[0122] The working principle and beneficial effects of the above technical solution: In order to improve the breadth and accuracy of the knowledge database, each industrial entity is simulated to obtain the entity operation information of each industrial entity, thereby constructing a corresponding local thinking map, and extracting the operation items of the industrial entity from it, and further using the industrial brain to construct the overall thinking map of the industrial chain ear, and using natural language technology to construct the description language of the industrial chain and set relevant priorities for it. At the same time, the graph algorithm extraction technology is used to extract the entity interaction generation tree between different industrial entities in the overall thinking map, and the position of the entity generation tree is adjusted in combination with the priority to obtain the language generation tree. The operation knowledge of the industrial entity is searched in the language generation tree, and the knowledge database of the industrial chain is constructed. In this way, not only can each industrial entity be processed, but the relationship between different industrial entities can also be determined, and a high-precision knowledge database that meets user needs can be constructed.

[0123] Example 5

[0124] On the basis of Example 1, the method for intelligent description of the industrial chain based on the mind map, step 3 includes:

[0125] Step 31: constructing a physical industry chain node with corresponding attributes based on the physical attributes corresponding to each of the industrial entities, deducing the industrial execution link corresponding to each of the physical industry chain nodes based on the knowledge database, and selecting virtual industry chain nodes that have an interactive relationship with the physical industry chain nodes in the industrial execution links;

[0126] Step 32: Determine the node execution function corresponding to each of the physical industry chain nodes and each of the virtual industry chain nodes based on the industry execution link, determine the function connection sequence between different industry chain nodes, and construct the industry chain structure of the industry chain;

[0127] Step 33: Determine the node relationships between different industry chain nodes based on the industry chain structure, perform data quality analysis on the knowledge database, obtain several data defects in the industry chain and determine corresponding defect nodes, determine several associated defect nodes in the industry chain based on the node relationships, and deduce the industry chain risk of the industry chain based on the corresponding node attributes;

[0128] Step 34: Use the industrial chain ontology model to simulate the industrial chain risk, obtain the risk presentation position and risk presentation result corresponding to each industrial chain risk, mark the risk presentation result on the risk presentation position corresponding to the industrial chain structure, and capture the corresponding risk characteristics in the industrial chain structure.

[0129] In this example, the industry execution link refers to the link formed when a physical industry chain node executes various tasks;

[0130] In this example, the node execution function represents the function that a virtual industry chain node can perform;

[0131] In this example, the determined defective node represents the defective node that has been screened and processed;

[0132] In this example, the risk presentation location indicates the location where the risk phenomenon occurs in the industrial chain, and the risk presentation result indicates the result of the risk occurring in the industrial chain.

[0133] The working principle and beneficial effects of the above technical solution: In order to further determine the risks in the industrial chain, the physical industrial chain nodes are first constructed according to the attributes of the industrial entities, and their industrial execution links are deduced in the knowledge database, thereby determining the virtual industrial chain nodes with interactive relationships, and combining the node execution functions of each virtual industrial chain node to construct the industrial chain structure of the industrial chain, and then derive the defective nodes in the industrial chain, determine the industrial chain risks of the industrial chain, and further analyze and mark them in the industrial chain to obtain the risk characteristics contained in the industrial chain. In this way, not only can the defects of each node in the industrial chain be found and analyzed, but also the risk characteristics contained therein can be determined, thereby improving the user's risk awareness.

[0134] Example 6

[0135] Based on Example 5, the method for intelligently describing an industrial chain based on a mind map further includes:

[0136] The risk outbreak moment and risk outbreak consequences of each risk feature in the industrial chain structure are derived, and a risk visualization dynamic scene of the industrial chain is generated and displayed.

[0137] The working principle and beneficial effects of the above technical solution are as follows: the risks in the industrial chain are presented with visual effects, and users can intuitively feel the harm caused by the risks.

[0138] Example 7

[0139] On the basis of Example 1, the method for intelligent description of the industrial chain based on the mind map, step 4 includes:

[0140] Step 41: using the visualization technology to simulate each risk feature of the industrial chain structure, and obtaining visual presentation information of each risk feature;

[0141] Step 42: spatially combining the visual presentation information according to the industrial chain structure to obtain a visual operation scene of the industrial chain;

[0142] Step 43: Summarize a number of operation knowledge of the industrial chain in the visual operation scene, generate a real-time knowledge system of the industrial chain and display it.

[0143] The working principle and beneficial effects of the above technical solution: Using a visual method to present the real-time knowledge system of the industrial chain can highlight the operation process of the industrial chain in the visual operation scene, thereby improving the user experience.

[0144] Example 8

[0145] Based on Example 7, the method for intelligently describing an industrial chain based on a mind map further includes:

[0146] Retrieving corresponding target-related knowledge in the real-time knowledge system according to the retrieval instruction issued by the user;

[0147] Converting the target-related knowledge into a plurality of knowledge sequences, and identifying the relevant knowledge corresponding to each of the knowledge sequences in the real-time knowledge system;

[0148] Taking each of the knowledge sequences as a starting point, respectively, performing knowledge traversal on the corresponding related knowledge to obtain a plurality of knowledge point sets of each of the industrial chains;

[0149] The industry chain ontology model is used to perform knowledge reasoning on each of the knowledge point sets, and the knowledge graph corresponding to each of the knowledge point sets is obtained and displayed.

[0150] In this instance, the knowledge sequence represents the result of transforming the target-related knowledge into a single piece of knowledge;

[0151] In this instance, knowledge traversal refers to the process of analyzing knowledge relationships of related knowledge starting from the knowledge sequence;

[0152] In this example, the knowledge point set represents a collection of knowledge points included in the industrial chain.

[0153] The working principle and beneficial effects of the above technical solution are as follows: when a user searches for relevant knowledge of the industrial chain, the target-related knowledge that the user wants is first extracted, and then converted into a sequence to search for relevant knowledge. Then, the knowledge point set of the industrial chain is constructed through knowledge traversal, and finally, a knowledge graph is generated through model reasoning for the user to view, providing the user with a comprehensive and clear knowledge structure.

[0154] Example 9

[0155] This embodiment provides an intelligent description system for the industrial chain based on the mind map, such as Figure 2 As shown, including:

[0156] A model building module is used to determine the entity attributes corresponding to different industrial entities in the industrial chain and the entity relationships between different industrial entities based on multi-source industrial data, and to build an industrial chain ontology model of the industrial chain;

[0157] A knowledge extraction module is used to obtain the operation knowledge corresponding to each of the industrial entities by using natural language technology and graph algorithm extraction technology during the operation of the industrial chain ontology model, and generate a knowledge database;

[0158] a risk identification module, configured to derive the industrial chain structure and industrial chain risks of the industrial chain using the knowledge database, simulate the industrial chain risks using the industrial chain ontology model, and determine a number of risk features contained in the industrial chain structure;

[0159] The industry description module is used to simulate the scenario of the industry chain structure and corresponding risk characteristics using visualization technology, obtain the real-time knowledge system of the industry chain and display it.

[0160] In this example, the industry entity represents the entity that performs the corresponding work in the industry chain;

[0161] In this example, the entity attribute represents the department to which the industrial entity belongs. For example, industrial entity A belongs to the logistics department, and industrial entity B belongs to the sales department.

[0162] In this example, the entity relationships represent the working relationships between different industrial entities;

[0163] In this example, the industrial chain ontology model represents a model used to simulate the operation process of the industrial chain;

[0164] In this instance, natural language technology refers to the technology that converts the data generated by the industrial chain ontology model into human language;

[0165] In this example, the graph algorithm extraction technology represents the process of extracting the graph structure of industrial entities from the industrial chain ontology model;

[0166] In this example, the knowledge database represents the collection of data knowledge generated during the operation of the industrial chain;

[0167] In this example, the industrial chain structure refers to the structure composed of the arrangement of various entities in the industrial chain;

[0168] In this example, the industry chain risk refers to the unsafe phenomena that occur during the operation of the industry chain;

[0169] In this example, the real-time knowledge system refers to the operating system composed of various data knowledge generated during the operation of the industrial chain.

[0170] The working principle and beneficial effects of the above technical solution are as follows: by utilizing the multi-source industrial data generated by the industrial chain to determine the entity attributes of different industrial entities and the entity relationships between different industrial entities, an industrial chain ontology model that can run synchronously with the industrial chain is constructed. Natural language technology and graph algorithm extraction technology are used to obtain the operation knowledge of each industrial entity presented during the operation of the industrial chain ontology model, and a knowledge database of the industrial chain is constructed. This can not only obtain the knowledge data of the industrial chain, but also store the data in a unified manner to reduce the risk of data loss. The knowledge database is then used to deduce the industrial structure and industrial risks of the industrial chain, and the risk characteristics contained in the industrial chain structure are further determined through simulation. In order to more intuitively show the operation of the industrial chain to users, visualization technology is used to present the risk scenarios in the industrial chain structure, and a real-time knowledge system of the industrial chain is constructed for user reference. In this way, synchronous analysis can be performed during the operation of the industrial chain, presenting the structure, risks and knowledge generated by the industrial chain during its operation to users, thereby improving the efficiency and accuracy of users in obtaining relevant knowledge of the industrial chain.

[0171] Example 10

[0172] On the basis of Example 9, the industry chain intelligent description system based on the mind map, the model building module includes:

[0173] A text recognition unit is used to collect a plurality of industrial data generated in the industrial chain, construct multi-source industrial data of the industrial chain, map the multi-source industrial data into a data entity dictionary, and determine a plurality of descriptive data entities contained in the multi-source industrial data, as well as a descriptive content text corresponding to each of the descriptive data entities;

[0174] an entity determination unit, configured to locate each of the descriptive data entities in the multi-source industry data, construct a data logic diagram of the industry chain based on the descriptive content text, and deduce a number of non-salient data entities included in the industry chain based on the presentation logic of each of the descriptive data entities in the data logic diagram;

[0175] an attribute determination unit, configured to derive the non-salient content text corresponding to the non-salient data entity based on the descriptive content text corresponding to the descriptive data entity in combination with the data logic diagram, determine a plurality of industrial entities included in the industrial chain, and determine the entity attribute corresponding to each of the industrial entities based on the corresponding content text;

[0176] A model building unit is used to build a model framework according to the data logic diagram, determine the entity function corresponding to the industrial entity according to the entity attributes, add the entity function to the model framework for model optimization, and generate an industrial chain ontology model of the industrial chain.

[0177] In this example, the data entity dictionary contains the correspondence between several industry entities and their related expression data;

[0178] In this example, industrial data refers to the data generated by different data sources during the operation of the industrial chain;

[0179] In this example, multi-source industry data refers to a structure that aggregates data generated by different data sources in the industry chain, where the data sources can be industry entities;

[0180] In this example, the description data entity represents the industry entity mentioned in the multi-source industry data;

[0181] In this instance, the description content text represents a text used to describe basic information of a description data entity;

[0182] In this example, the data logic diagram represents a diagram used to present the logical relationship between different descriptive data entities in the industrial chain;

[0183] In this example, a non-significant data entity represents an industrial entity that exists in the industrial chain but is not currently operating.

[0184] In this example, entity functions represent functions that an industrial entity can perform.

[0185] The working principle and beneficial effects of the above technical solution are as follows: by aggregating several industrial data generated in the industrial chain to generate multi-source industrial data for the industrial chain, the data entity dictionary is used to determine the descriptive data entities and their descriptive content texts contained in the multi-source industrial data, and then the data logic diagram of the industrial chain is constructed according to the position of the descriptive data entities in the multi-source industrial data combined with the descriptive content text, thereby deducing the non-significant data entities contained in the industrial chain. In this way, all industrial entities contained in the industrial chain have been extracted, and the entity attributes of the industrial entities are further determined in combination with the corresponding content text. Finally, a model framework is established according to the logical diagram, and the entity function tags of the industrial entities are marked in it for model optimization, thereby generating an industrial chain ontology model of the industrial chain. In this way, not only can the industrial entities be located in a short time, but the industrial entities can also be described accordingly, thereby constructing and optimizing the model to achieve the purpose of model construction, and the constructed model contains all industrial entities, and each industrial entity can be processed and analyzed subsequently.

[0186] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. The intelligent description method of the industrial chain based on the mind map is characterized by: include: Step 1: Determine the entity attributes corresponding to different industrial entities in the industrial chain and the entity relationships between different industrial entities based on multi-source industrial data, and build an industrial chain ontology model of the industrial chain; Step 2: In the process of running the industrial chain ontology model, natural language technology and graph algorithm extraction technology are used to obtain the operation knowledge corresponding to each of the industrial entities and generate a knowledge database; Step 3: deriving the industrial chain structure and industrial chain risks of the industrial chain using the knowledge database, simulating the industrial chain risks using the industrial chain ontology model, and determining a number of risk features contained in the industrial chain structure; Step 4: Use visualization technology to simulate the scenario of the industrial chain structure and corresponding risk characteristics, obtain the real-time knowledge system of the industrial chain and display it.

2. The method for intelligent description of the industrial chain based on the mind map according to claim 1, characterized in that: The step 1 comprises: Step 11: Collect a number of industry data generated in the industry chain, construct multi-source industry data of the industry chain, map the multi-source industry data into a data entity dictionary, determine a number of descriptive data entities contained in the multi-source industry data, and the descriptive content text corresponding to each of the descriptive data entities; Step 12: Locate each of the descriptive data entities in the multi-source industry data, construct a data logic diagram of the industry chain based on the descriptive content text, and deduce a number of non-salient data entities included in the industry chain based on the presentation logic of each of the descriptive data entities in the data logic diagram; Step 13: Determine the non-salient content text corresponding to the non-salient data entity based on the descriptive content text corresponding to the descriptive data entity and the data logic diagram, determine a number of industrial entities included in the industrial chain, and determine the entity attributes corresponding to each of the industrial entities based on the corresponding content text; Step 14: Construct a model framework based on the data logic diagram, determine the entity function corresponding to the industrial entity based on the entity attributes, add the entity function to the model framework for model optimization, and generate an industrial chain ontology model of the industrial chain.

3. The method for intelligent description of the industrial chain based on the mind map according to claim 2 is characterized in that: The process of collecting a number of industrial data generated in the industrial chain and constructing multi-source industrial data of the industrial chain includes: respectively collecting industrial data generated by each data source in the industrial chain, converting the industrial data into binary data frames, and determining the data generation frequency corresponding to the data source according to the frame header of each binary data frame; constructing a multi-source data structure according to the data generation frequency; Determining the data generation type corresponding to the data source according to the frame tail of each binary data frame; The data generation type is used to adjust the structural attributes corresponding to each structural position in the multi-source data structure, and each industrial data is input into the adjusted multi-source data structure respectively, and the industrial data is connected with the corresponding structural position to generate multi-source industrial data of the industrial chain.

4. The method for intelligent description of the industrial chain based on the mind map according to claim 1 is characterized in that: The step 2 comprises: Step 21: Run the industry chain ontology model with each of the industry entities as the center to obtain entity operation information corresponding to each of the industry entities, construct a local mind map corresponding to the industry entity based on the entity operation information, and mark several operation items of the industry entity in the local mind map; Step 22: The industry brain derives the overall mind map of the industry chain based on the associated running items between different local mind maps, uses the natural language technology to describe the overall mind map, and obtains several description languages ​​of the industry chain. A corresponding priority is assigned to each description language based on the description scope corresponding to each description language; Step 23: Utilizing the graph algorithm extraction technology to extract the entity interaction spanning tree corresponding to each of the industrial entities in the overall mind map, and utilizing the description language to adjust and combine the entity interaction spanning trees according to the order of priority to generate a language spanning tree; Step 24: Searching the language generation tree for the operation knowledge generated by each of the industrial entities during operation, classifying and summarizing the operation knowledge, and generating a knowledge database for the industrial chain.

5. The method for intelligent description of the industrial chain based on the mind map according to claim 1 is characterized in that: The step 3 comprises: Step 31: constructing a physical industry chain node with corresponding attributes based on the physical attributes corresponding to each of the industrial entities, deducing the industrial execution link corresponding to each of the physical industry chain nodes based on the knowledge database, and selecting virtual industry chain nodes that have an interactive relationship with the physical industry chain nodes in the industrial execution links; Step 32: Determine the node execution function corresponding to each of the physical industry chain nodes and each of the virtual industry chain nodes based on the industry execution link, determine the function connection sequence between different industry chain nodes, and construct the industry chain structure of the industry chain; Step 33: Determine the node relationships between different industry chain nodes based on the industry chain structure, perform data quality analysis on the knowledge database, obtain several data defects in the industry chain and determine corresponding defect nodes, determine several associated defect nodes in the industry chain based on the node relationships, and deduce the industry chain risk of the industry chain based on the corresponding node attributes; Step 34: Use the industrial chain ontology model to simulate the industrial chain risk, obtain the risk presentation position and risk presentation result corresponding to each industrial chain risk, mark the risk presentation result on the risk presentation position corresponding to the industrial chain structure, and capture the corresponding risk characteristics in the industrial chain structure.

6. The method for intelligent description of the industrial chain based on the mind map according to claim 5, characterized in that: Also includes: The risk outbreak moment and risk outbreak consequences of each risk feature in the industrial chain structure are derived, and a risk visualization dynamic scene of the industrial chain is generated and displayed.

7. The method for intelligent description of industrial chain based on mind map according to claim 1, characterized in that: The step 4 comprises: Step 41: using the visualization technology to simulate each risk feature of the industrial chain structure, and obtaining visual presentation information of each risk feature; Step 42: spatially combining the visual presentation information according to the industrial chain structure to obtain a visual operation scene of the industrial chain; Step 43: Summarize a number of operation knowledge of the industrial chain in the visual operation scene, generate a real-time knowledge system of the industrial chain and display it.

8. The method for intelligent description of the industrial chain based on the mind map according to claim 7, characterized in that: Also includes: Retrieving corresponding target-related knowledge in the real-time knowledge system according to the retrieval instruction issued by the user; Converting the target-related knowledge into a plurality of knowledge sequences, and identifying the relevant knowledge corresponding to each of the knowledge sequences in the real-time knowledge system; Taking each of the knowledge sequences as a starting point, respectively, performing knowledge traversal on the corresponding related knowledge to obtain a plurality of knowledge point sets of each of the industrial chains; The industry chain ontology model is used to perform knowledge reasoning on each of the knowledge point sets, and the knowledge graph corresponding to each of the knowledge point sets is obtained and displayed.

9. The intelligent description system of the industrial chain based on the mind map is characterized by: include: A model building module is used to determine the entity attributes corresponding to different industrial entities in the industrial chain and the entity relationships between different industrial entities based on multi-source industrial data, and to build an industrial chain ontology model of the industrial chain; A knowledge extraction module is used to obtain the operation knowledge corresponding to each of the industrial entities by using natural language technology and graph algorithm extraction technology during the operation of the industrial chain ontology model, and generate a knowledge database; a risk identification module, configured to derive the industrial chain structure and industrial chain risks of the industrial chain using the knowledge database, simulate the industrial chain risks using the industrial chain ontology model, and determine a number of risk features contained in the industrial chain structure; The industry description module is used to simulate the scenario of the industry chain structure and corresponding risk characteristics using visualization technology, obtain the real-time knowledge system of the industry chain and display it.

10. The industry chain intelligent description system based on mind map according to claim 9, characterized in that: The model building module includes: A text recognition unit is used to collect a plurality of industrial data generated in the industrial chain, construct multi-source industrial data of the industrial chain, map the multi-source industrial data into a data entity dictionary, and determine a plurality of descriptive data entities contained in the multi-source industrial data, as well as a descriptive content text corresponding to each of the descriptive data entities; an entity determination unit, configured to locate each of the descriptive data entities in the multi-source industry data, construct a data logic diagram of the industry chain based on the descriptive content text, and deduce a number of non-salient data entities included in the industry chain based on the presentation logic of each of the descriptive data entities in the data logic diagram; an attribute determination unit, configured to derive the non-salient content text corresponding to the non-salient data entity based on the descriptive content text corresponding to the descriptive data entity in combination with the data logic diagram, determine a plurality of industrial entities included in the industrial chain, and determine the entity attribute corresponding to each of the industrial entities based on the corresponding content text; A model building unit is used to build a model framework according to the data logic diagram, determine the entity function corresponding to the industrial entity according to the entity attributes, add the entity function to the model framework for model optimization, and generate an industrial chain ontology model of the industrial chain.

Images