An industry chain generation method and device

Abstract

This invention provides a method and apparatus for generating industry chains, relating to the field of data processing technology. The method includes: receiving a target industry pair to be queried; the target industry pair includes primary industry information and secondary industry information; determining at least one candidate industry chain between the primary industry information and the secondary industry information based on the primary industry information, the secondary industry information, and a pre-constructed dynamic knowledge graph; the dynamic knowledge graph is dynamically generated based on industries identified from basic industry data and the relationships between industries; and determining a target industry chain corresponding to the primary industry information and the secondary industry information from at least one candidate industry chain based on the strength and length information of each candidate industry chain. This implementation utilizes a dynamic knowledge graph to generate industry chains based on "point-to-point" indirect industry relationships, effectively improving the generation efficiency, coverage, and depth of industry chains.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and apparatus for generating an industry chain. Background Technology

[0002] Currently, the main methods for generating industrial chains are as follows: (1) Industrial chain generation based on relational databases, where industrial data is usually stored in relational databases and industrial relationships between various industrial data are maintained through preset table structures; (2) Graph databases are introduced to construct static industrial knowledge graphs and industrial chain relationships are displayed based on the knowledge graphs.

[0003] However, the two methods mentioned above can only generate industry chains based on the inherent relationships, and the generated industry chains usually only have direct relationships (first-level relationships). For two industry data with no defined direct relationship or with indirect relationship, it is impossible to effectively generate industry chains, resulting in low comprehensiveness and accuracy of the generated industry chains, which cannot meet the user's needs for industry chain generation. Summary of the Invention

[0004] This invention provides a method and apparatus for generating industry chains. Utilizing a dynamic knowledge graph constructed from industries identified in basic industry data, it can automatically determine at least one candidate industry chain between a target industry pair to be queried, based on information from the first and second industries. Furthermore, based on the strength and length information of each candidate industry chain, it can filter the candidate industry chains, thereby obtaining the target industry chain corresponding to the first and second industry information. Compared to existing technologies that can only generate industry chains based on direct "point-to-point" relationships between industries, this invention can generate industry chains based on indirect "point-to-point" relationships between industries, and the dynamic knowledge graph effectively improves the generation efficiency, coverage, and depth of industry chains.

[0005] This invention provides a method for generating an industry chain, comprising the following steps: receiving a target industry pair to be queried; wherein the target industry pair includes first industry information and second industry information; determining at least one candidate industry chain between the first industry information and the second industry information based on the first industry information, the second industry information, and a pre-constructed dynamic knowledge graph; wherein the dynamic knowledge graph is dynamically generated based on industries identified from basic industry data and the relationships between industries; and determining a target industry chain corresponding to the first industry information and the second industry information from at least one candidate industry chain based on the strength information and length information of each candidate industry chain.

[0006] Optionally, the dynamic knowledge graph is constructed in the following manner: acquiring multiple basic industry data in real time; for each basic industry data: identifying at least one industry included in the basic industry data; determining the heat value between each pair of industries based on the frequency of each pair of industries existing in the same basic industry data; and constructing a dynamic knowledge graph by connecting each pair of industries with the industry as a node and the heat value between each pair of industries.

[0007] Optionally, before the target industry pair to be queried, the method further includes: receiving the tertiary industry to be queried; determining multiple fourth industries that have an industrial chain relationship with the tertiary industry based on the dynamic knowledge graph; generating a dynamic circle corresponding to the tertiary industry based on the multiple fourth industries; and displaying the dynamic circle to the user so that the user can construct an industry pair for querying based on the fourth industries.

[0008] Optionally, the dynamic circle includes multiple sub-circles, each sub-circle corresponding to a different degree of closeness in the industrial chain relationship; the step of generating a dynamic circle corresponding to the tertiary industry based on multiple fourth industries includes: sorting the multiple fourth industries according to a first heat value between each fourth industry and the tertiary industry; and allocating each fourth industry to different sub-circles according to the sorting result to generate a dynamic circle including multiple sub-circles.

[0009] Optionally, determining at least one alternative industrial chain between the first industrial information and the second industrial information based on the first industrial information, the second industrial information, and a pre-constructed dynamic knowledge graph includes: using the dynamic knowledge graph to obtain a first alternative industrial chain corresponding to the first industrial information and a second alternative industrial chain corresponding to the second industrial information; and generating the alternative industrial chain based on the target industrial chain, the first industrial information, and the second industrial information when there is the same target industrial chain in the first alternative industrial chain and the second alternative industrial chain.

[0010] Optionally, determining the target industrial chain corresponding to the first industrial information and the second industrial information from at least one of the candidate industrial chains based on the strength information and length information of each candidate industrial chain includes: sorting the candidate industrial chains according to their strength information, selecting at least one sub-candidate industrial chain from the candidate industrial chains; and selecting the sub-candidate industrial chain with the shortest length information as the target industrial chain.

[0011] Optionally, the method further includes storing the dynamic knowledge graph according to a preset time period.

[0012] Optionally, the method further includes: acquiring a historical dynamic knowledge graph corresponding to a historical time period; determining multiple historical fourth industries corresponding to the tertiary industry and a second heat value between each historical fourth industry and the tertiary industry based on the historical dynamic knowledge graph; generating a supply chain change diagram corresponding to the tertiary industry based on a first heat value between each fourth industry and the tertiary industry and a second heat value between each historical fourth industry and the tertiary industry; and displaying the supply chain change diagram to the user.

[0013] The present invention also provides an industrial chain generation device, comprising the following modules: A receiving module is used to receive a target industry pair to be queried; wherein the target industry pair includes primary industry information and secondary industry information; The determination module is used to determine at least one candidate industrial chain between the first industrial information and the second industrial information based on the first industrial information, the second industrial information, and a pre-constructed dynamic knowledge graph; wherein, the dynamic knowledge graph is dynamically generated based on industries identified from basic industrial data and the relationships between industries; The filtering module is used to determine the target industrial chain corresponding to the first industrial chain information and the second industrial chain information from at least one of the candidate industrial chains based on the strength information and length information of each candidate industrial chain.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the supply chain generation method as described above.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the supply chain generation method as described above.

[0016] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the supply chain generation method as described above.

[0017] This invention provides a method and apparatus for generating industry chains. Utilizing a dynamic knowledge graph of industry generation identified from basic industry data, it can automatically determine at least one candidate industry chain between a target industry pair to be queried, based on information from the first and second industries. Furthermore, based on the strength and length information of each candidate industry chain, it can filter the candidate industry chains, thereby obtaining the target industry chain corresponding to the first and second industry information. Compared to existing technologies that can only generate industry chains based on direct "point-to-point" relationships between industries, this invention can generate industry chains based on indirect "point-to-point" relationships between industries, and the dynamic knowledge graph effectively improves the generation efficiency, coverage, and depth of industry chains. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is one of the flowcharts illustrating the industrial chain generation method provided by the present invention.

[0020] Figure 2 This is a flowchart illustrating the construction process of the dynamic knowledge graph provided by this invention.

[0021] Figure 3 This is the second flowchart of the industrial chain generation method provided by the present invention.

[0022] Figure 4 This is the third flowchart of the industrial chain generation method provided by the present invention.

[0023] Figure 5 This is a schematic diagram of the industrial chain generation device provided by the present invention.

[0024] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0026] Figure 1 This is one of the flowcharts illustrating the supply chain generation method provided by the present invention, such as... Figure 1 As shown, the method includes the following: Step 101: Receive the target industry pair to be queried; wherein, the target industry pair includes information on the primary industry and information on the secondary industry; The primary and secondary industry information can be a type of product or a specific industry, such as kitchen appliances, photovoltaic equipment, or lithium battery separators. For example, users can input the target industry pair they wish to query through the interactive page. For instance, the interactive page can have two input boxes, one for receiving the primary industry information and the other for receiving the secondary industry information input by the user.

[0027] Step 102: Based on the information of the primary industry, the information of the secondary industry, and the pre-constructed dynamic knowledge graph, determine at least one alternative industrial chain between the information of the primary industry and the information of the secondary industry; wherein, the dynamic knowledge graph is generated based on the industry dynamics identified from the basic industry data.

[0028] In existing technologies, it's common practice to set identical fields in both upstream and downstream tables and link them based on these fields to enable further queries based on the relationships between the tables. For example, for product 1, if supplier A is A and manufacturer B is B, then supplier A and manufacturer B can maintain a relationship based on the same field "product 1". During a query, inputting "product 1" will retrieve supplier A and manufacturer B, which are directly related to product 1. However, it's impossible to query the entire supply chain based on supplier A, including manufacturer B and even raw material supplier C that provides raw materials to manufacturer B. This is because in existing technologies, industry data is typically stored in relational databases with table structures. When analyzing the entire supply chain, each pair of table structures needs to be analyzed separately, and these table structures must include identical fields to determine if a relationship exists. This manually set table structure and fields affect subsequent query efficiency; without the appropriate table structure or identical fields, queries are impossible.

[0029] In this embodiment of the invention, a dynamic knowledge graph perfectly solves the bottleneck of existing technologies in querying industry chains. Specifically, the dynamic knowledge graph in this embodiment is automatically identified and dynamically constructed based on basic industry data. As the basic industry data continues to expand and change, the dynamic knowledge graph will also change accordingly, and the industries included therein and the relationships between them will also change. Therefore, in this embodiment of the invention, the various industries and the relationships between them do not need to be manually modified or updated; they can be automatically and dynamically updated based on the basic industry data. Furthermore, based on the topological structure of the dynamic knowledge graph, an indirect relationship industry chain can be generated for two industries that do not have a direct relationship, helping users determine the potential connection between information from the first industry and information from the second industry.

[0030] In one alternative embodiment, the construction process of the dynamic knowledge graph is as follows: Figure 2 As shown, it includes: Step 201: Acquire multiple basic industry data in real time; The basic industry data can include industry data from multiple industry dimensions, such as policy and regulatory data, industrial chain and business data, company operation and financial market data, and technology and innovation data. Policy and regulatory data refers to policy documents, industry planning documents, and legal documents issued by government departments at all levels through real-time monitoring and capture. Industrial chain and business data refers to data related to the industrial chain, such as company directories, product and service information, equity relationships, and supply chain relationships. Company operation and financial market data refers to publicly available operating data and financial market data, such as company financial reports, announcements, stock price data, and other financing and investment data. Technology and innovation data refers to data related to professional technology, such as patents, academic journals, papers, and articles in science and technology media. This embodiment of the invention constructs a dynamic knowledge graph by acquiring basic industry data from multiple industry dimensions, directly improving the accuracy of subsequent queries using the dynamic knowledge graph.

[0031] Step 202: For each basic industry data point: Identify at least one industry included in the basic industry data; Specifically, multiple industry keywords can be pre-set based on commonly used industry segmentation tables and national production catalogs in the market. By matching basic industry data with multiple industry keywords, industries in the basic industry data can be identified.

[0032] Step 203: Determine the heat value between each pair of industries based on the frequency with which they exist in the same basic industry data; For example, the frequency with which two industries appear in the same basic industry data can be used as the popularity value. For instance, if industry a and industry b both exist in basic industry data 001 and basic industry data 002, then the popularity value between industry a and industry b would be 2. It is understood that in practical applications, two unrelated industries typically do not appear in the same article or document. Therefore, in this embodiment of the invention, the popularity value between industry a and industry b is defined by the frequency with which industry a and industry b appear in the same basic industry data, to represent the strength of the association between industry a and industry b.

[0033] Step 204: Using industries as nodes, connect the heat values ​​between every two industries to construct a dynamic knowledge graph.

[0034] As can be seen, the dynamic knowledge graph constructed by the embodiments of the present invention can not only represent the relationship between various industries through the connection between points, but also represent the strength of the relationship between various industries based on the heat value of the connection.

[0035] In this embodiment of the invention, a dynamic knowledge graph is used as the query framework to obtain the industrial chain between any two nodes (industries). Specifically, step 102 includes: using the dynamic knowledge graph to obtain a first alternative industry corresponding to the first industry information and a second alternative industry corresponding to the second industry information; if the first alternative industry and the second alternative industry have the same target industry, generating alternative industrial chains based on the target industry, the first industry information, and the second industry information.

[0036] Since a dynamic knowledge graph is composed of nodes and connections, each node can be linked to a first-level divergent node, and further linked to each first-level divergent node, leading to second-level divergent nodes. This process can be repeated to obtain multiple first-optional industries related to the first-industry information and multiple second-optional industries related to the second-industry information. When the first and second-optional industries share the same target industry, it can be considered that the first and second-industry information have achieved a supply chain connection through the target industry. Therefore, alternative supply chains between the first and second-industry information can be obtained based on the connection paths between the target industry and the first-industry information, and between the second-industry information and the target industry. Of course, if the first and second-optional industries do not share the same target industry, it indicates that an effective connection path cannot be established between the first and second-industry information, and therefore no alternative supply chains can be obtained. In this case, an interactive page can be used to display a result similar to "no supply chain exists," and this invention does not impose specific limitations on this.

[0037] Step 103: Based on the strength and length information of each candidate industrial chain, determine the target industrial chain corresponding to the primary industry information and the secondary industry information from at least one candidate industrial chain.

[0038] When there is only one alternative industry chain, it can be directly used as the target industry chain. However, when there are multiple alternative industry chains, it is necessary to consider both strength and length information to screen the multiple alternative industry chains and provide the user with the optimal target industry chain.

[0039] In practical applications, users often aim to uncover key industries that can bring potential opportunities between primary and secondary industry information, or relatively hidden, undiscovered cooperation channels that are strongly related to either primary or secondary industry information. Therefore, strength information is relatively important for candidate industry chains between primary and secondary industry information. Thus, in an optional embodiment of this invention, step 103 may specifically include: sorting each candidate industry chain according to its strength information, and selecting at least one sub-candidate industry chain from the candidate industry chains; selecting the shortest sub-candidate industry chain as the target industry chain. The strength information can be obtained by adding the heat values ​​between every two industry nodes. For example, if candidate industry chain a is: primary industry information - industry a - industry c - industry f - secondary industry information, then the strength information of candidate industry chain a is the sum of the heat values ​​of primary industry information - industry a, industry a - industry c, industry c - industry f, and industry f - secondary industry information. The heat values ​​between every two industry nodes can be directly obtained based on a dynamic knowledge graph.

[0040] In this embodiment of the invention, considering that users may not be very familiar with the names or products of each industry when generating the industry chain, they may face confusion when inputting the first industry information and the second industry information. Therefore, in this embodiment of the invention, a query for related industries can be performed based on one industry to provide users with a basis for querying the industry chain.

[0041] The following is based on Figure 3 For example, another industry chain method provided by the embodiments of the present invention will be illustrated with an example, such as... Figure 3 As shown, it includes: Step 301: Receive the tertiary industry data to be queried; Step 302: Based on the dynamic knowledge graph, identify multiple fourth industries that have a supply chain relationship with the tertiary industry; Step 303: Generate dynamic circles corresponding to the tertiary industry based on multiple tertiary industries; Step 304: Show the user the dynamic circle so that the user can build industry pairs for querying based on the fourth industry; Step 305: Receive the target industry pair to be queried; wherein, the target industry pair includes the tertiary industry and the fifth industry; the fifth industry is any one of the fourth industry; Step 306: Based on the tertiary industry, the fifth industry, and the dynamic knowledge graph, identify at least one alternative industrial chain between the tertiary industry and the fifth industry; Step 307: Based on the strength and length information of each candidate industrial chain, determine the target industrial chain corresponding to the tertiary industry and the 5th industry from at least one candidate industrial chain.

[0042] Steps 301 to 304 essentially provide users with optional industries related to the tertiary sector (i.e., the tertiary sector). The dynamic circle display helps users understand which industries are related to the tertiary sector. Further, based on the fifth industry selected by the user from the tertiary sector, a supply chain query is performed, helping users further understand the specific supply chain relationship between the tertiary and fifth industries. It is evident that displaying the dynamic circle and performing the supply chain query are two progressive steps. When users are clueless about the supply chain query or lack understanding of the industries themselves, the above process guides them to complete the query.

[0043] In a further optional embodiment, the dynamic circle includes multiple sub-circles, each corresponding to a different degree of closeness in the industrial chain relationship. Step 303 can specifically include: sorting the multiple fourth industries according to a first heat value between each fourth industry and the third industry; and assigning each fourth industry to different sub-circles according to the sorting result to generate a dynamic circle including multiple sub-circles. In other words, this embodiment of the invention divides multiple fourth industries based on the first heat value between the fourth and third industries and displays them intuitively through multiple sub-circles, making it easy for users to see at a glance which industries have a closer industrial chain relationship with the third industry and which industries have a more distant industrial chain relationship. For example, when displaying the dynamic circle, different background colors can be set for different sub-circles, and multiple sub-circles can be displayed in a nested manner to represent the radiating or spreading relationship of each fourth industry from the center outwards based on the third industry.

[0044] Furthermore, this embodiment of the invention also stores the dynamic knowledge graph according to a preset time period. For example, the dynamic knowledge graph can be saved using a "snapshot" method at a preset time period, which can be set daily, monthly, or yearly. The advantage of storing the dynamic knowledge graph is that it allows for further analysis of the industry chain based on dynamic knowledge graphs at different time periods, helping users understand changes in the industry chain within a certain time period.

[0045] Specifically, another method for generating an industrial chain provided by the embodiments of the present invention is as follows: Figure 4 As shown, it includes: Step 401: Receive the tertiary industry data to be queried; Step 402: Based on the dynamic knowledge graph, identify multiple fourth industries that have a supply chain relationship with the tertiary industry, as well as the first heat value between each fourth industry and the tertiary industry. Step 403: Obtain the historical dynamic knowledge graph corresponding to the historical time period; Step 404: Determine multiple historical fourth industries corresponding to the tertiary industry and the second heat value between each historical fourth industry and the tertiary industry based on the historical dynamic knowledge graph; Step 405: Generate a supply chain change diagram for the tertiary industry based on the first heat value between each tertiary industry and the tertiary industry and the second heat value between each historical tertiary industry and the tertiary industry. Step 406: Show users a diagram of changes in the industry chain.

[0046] For example, by comparing the fourth industry with the historical fourth industry, newly added industry information can be obtained and highlighted so that users can intuitively see the main changes in the industrial chain.

[0047] In summary, this invention utilizes a dynamic knowledge graph constructed from industries identified in basic industry data. Upon receiving a target industry pair to be queried, it can automatically determine at least one candidate industrial chain between the first and second industry information based on the first and second industry information. Furthermore, based on the strength and length information of each candidate industrial chain, it can filter the candidate industrial chains, thereby obtaining the target industrial chain corresponding to the first and second industry information. Compared to existing technologies that can only generate industrial chains based on direct "point-to-point" relationships between industries, this invention can generate industrial chains based on indirect "point-to-point" relationships between industries, and the dynamic knowledge graph effectively improves the generation efficiency, coverage, and depth of industrial chains.

[0048] The supply chain generation device provided by the present invention is described below. The supply chain generation device described below and the supply chain generation method described above can be referred to in correspondence.

[0049] like Figure 5 As shown, the supply chain generation device 500 provided in this embodiment of the invention specifically includes: The receiving module 501 is used to receive a target industry pair to be queried; wherein the target industry pair includes primary industry information and secondary industry information; The determining module 502 is used to determine at least one candidate industrial chain between the first industrial information and the second industrial information based on the first industrial information, the second industrial information, and a pre-constructed dynamic knowledge graph; wherein, the dynamic knowledge graph is dynamically generated based on industries identified from basic industrial data and the relationships between industries; The filtering module 503 is used to determine, from at least one of the candidate industrial chains, a target industrial chain corresponding to the first industrial information and the second industrial information, based on the strength information and length information of each candidate industrial chain.

[0050] In an optional embodiment of the present invention, the dynamic knowledge graph is constructed in the following manner: acquiring multiple basic industry data in real time; for each basic industry data: identifying at least one industry included in the basic industry data; determining the heat value between each two industries based on the frequency of each two industries existing in the same basic industry data; and constructing a dynamic knowledge graph by connecting the industries as nodes and the heat values ​​between each two industries.

[0051] In an optional embodiment of the present invention, the receiving module 501 is further configured to receive the tertiary industry to be queried before the target industry pair to be queried; the determining module 502 is further configured to determine multiple fourth industries that have an industrial chain relationship with the tertiary industry based on the dynamic knowledge graph; generate a dynamic circle corresponding to the tertiary industry based on the multiple fourth industries; the industrial chain generation device further includes a display module for displaying the dynamic circle to the user, so that the user can construct an industry pair for querying based on the fourth industry.

[0052] In an optional embodiment of the present invention, the dynamic circle includes multiple sub-circles, each of which corresponds to a different degree of closeness in the industrial chain relationship; the determining module 502 is further configured to sort the multiple fourth industries according to a first heat value between each fourth industry and the third industry; and to assign each fourth industry to different sub-circles according to the sorting result, so as to generate a dynamic circle including multiple sub-circles.

[0053] In an optional embodiment of the present invention, the determining module 502 is further configured to: use the dynamic knowledge graph to obtain a first alternative industry corresponding to the first industry information and a second alternative industry corresponding to the second industry information; and generate the alternative industrial chain based on the target industry, the first industry information and the second industry information when there is the same target industry in the first alternative industry and the second alternative industry.

[0054] In an optional embodiment of the present invention, the screening module 503 is further configured to sort the candidate industrial chains according to the strength information of each candidate industrial chain, and select at least one sub-candidate industrial chain from the candidate industrial chains; and select the sub-candidate industrial chain with the shortest length information among the at least one sub-candidate industrial chain as the target industrial chain.

[0055] In an optional embodiment of the present invention, the industry chain generation device further includes a storage module for storing the dynamic knowledge graph according to a preset time period.

[0056] In an optional embodiment of the present invention, the determining module 502 is further configured to: acquire a historical dynamic knowledge graph corresponding to a historical time period; determine multiple historical fourth industries corresponding to the tertiary industry and a second heat value between each historical fourth industry and the tertiary industry based on the historical dynamic knowledge graph; generate a supply chain change diagram corresponding to the tertiary industry based on a first heat value between each fourth industry and the tertiary industry and a second heat value between each historical fourth industry and the tertiary industry; and display the supply chain change diagram to the user.

[0057] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640, wherein the processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can invoke logical instructions in the memory 630 to execute a supply chain generation method. This method includes: receiving a target industry pair to be queried; wherein the target industry pair includes first industry information and second industry information; determining at least one candidate supply chain between the first industry information and the second industry information based on the first industry information, the second industry information, and a pre-constructed dynamic knowledge graph; wherein the dynamic knowledge graph is dynamically generated based on industries identified from basic industry data and the relationships between industries; and determining a target supply chain corresponding to the first industry information and the second industry information from at least one candidate supply chain based on the strength and length information of each candidate supply chain.

[0058] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0059] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the industry chain generation method provided by the above methods. The method includes: receiving a target industry pair to be queried; wherein the target industry pair includes first industry information and second industry information; determining at least one candidate industry chain between the first industry information and the second industry information based on the first industry information, the second industry information, and a pre-constructed dynamic knowledge graph; wherein the dynamic knowledge graph is dynamically generated based on industries identified from basic industry data and the relationships between industries; and determining a target industry chain corresponding to the first industry information and the second industry information from at least one candidate industry chain based on the strength information and length information of each candidate industry chain.

[0060] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the supply chain generation method provided by the above methods. The method includes: receiving a target industry pair to be queried; wherein the target industry pair includes first industry information and second industry information; determining at least one candidate supply chain between the first industry information and the second industry information based on the first industry information, the second industry information, and a pre-constructed dynamic knowledge graph; wherein the dynamic knowledge graph is dynamically generated based on industries identified from basic industry data and the relationships between industries; and determining a target supply chain corresponding to the first industry information and the second industry information from at least one candidate supply chain based on the strength information and length information of each candidate supply chain.

[0061] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0062] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating an industrial chain, characterized in that, include: Receive the target industry pair to be queried; wherein, the target industry pair includes primary industry information and secondary industry information; Based on the first industry information, the second industry information, and the pre-constructed dynamic knowledge graph, at least one alternative industry chain between the first industry information and the second industry information is determined; wherein, the dynamic knowledge graph is dynamically generated based on industries identified from basic industry data and the relationships between industries; Based on the strength and length information of each of the candidate industrial chains, a target industrial chain corresponding to the first industrial information and the second industrial information is determined from at least one of the candidate industrial chains.

2. The industrial chain generation method according to claim 1, characterized in that, The dynamic knowledge graph is constructed in the following manner: Real-time acquisition of data from multiple fundamental industries; For each of the aforementioned basic industry data: identify at least one industry included in the basic industry data; The heat value between each pair of industries is determined based on the frequency with which each pair of industries exists in the same basic industry data. Using the industries mentioned above as nodes, and connecting the heat values ​​between any two industries, a dynamic knowledge graph is constructed.

3. The industrial chain generation method according to claim 2, characterized in that, Before the target industry pair to be queried, it also includes: Receive queries for the tertiary sector; Based on the dynamic knowledge graph, multiple fourth industries that have a supply chain relationship with the tertiary industry are identified; Based on multiple fourth industries, dynamic circles are generated that correspond to the third industry; The dynamic circle is displayed to the user so that the user can construct industry pairs for querying based on the fourth industry.

4. The industrial chain generation method according to claim 3, characterized in that, The dynamic circle includes multiple sub-circles, and the degree of closeness of the industrial chain relationship corresponding to each sub-circle is different; The generation of a dynamic circle corresponding to the tertiary industry based on multiple fourth industries includes: The fourth industries are ranked according to a first heat value between each of the fourth industries and the third industry; Based on the sorting results, each of the fourth industries is assigned to different sub-layers to generate a dynamic circle that includes multiple sub-layers.

5. The industrial chain generation method according to claim 2, characterized in that, The step of determining at least one candidate industrial chain between the first industrial information and the second industrial information based on the first industrial information, the second industrial information, and a pre-constructed dynamic knowledge graph includes: The dynamic knowledge graph is used to obtain a first candidate industry corresponding to the first industry information and a second candidate industry corresponding to the second industry information; If the first and second candidate industries have the same target industry, the candidate industrial chain is generated based on the target industry, the information of the first industry, and the information of the second industry.

6. The method for generating an industrial chain according to claim 5, characterized in that, The step of determining the target industrial chain corresponding to the first industrial chain information and the second industrial chain information from at least one of the candidate industrial chains based on the strength information and length information of each candidate industrial chain includes: Based on the strength information of each of the candidate industrial chains, at least one sub-candidate industrial chain is selected from the candidate industrial chains. The target industrial chain is selected from at least one of the aforementioned sub-candidate industrial chains that has the shortest length information.

7. The method for generating an industrial chain according to claim 3, characterized in that, Also includes: The dynamic knowledge graph is stored according to a preset time period.

8. The method for generating an industrial chain according to claim 7, characterized in that, Also includes: Obtain the historical dynamic knowledge graph corresponding to the historical time period; Based on the historical dynamic knowledge graph, multiple historical fourth industries corresponding to the tertiary industry are determined, as well as a second heat value between each historical fourth industry and the tertiary industry. Based on the first heat value between each of the fourth industries and the third industry and the second heat value between each of the historical fourth industries and the third industry, a change diagram of the industrial chain corresponding to the third industry is generated; Show users the aforementioned industry chain change diagram.

9. A supply chain generation device, characterized in that, include: A receiving module is used to receive a target industry pair to be queried; wherein the target industry pair includes primary industry information and secondary industry information; The determination module is used to determine at least one candidate industrial chain between the first industrial information and the second industrial information based on the first industrial information, the second industrial information, and a pre-constructed dynamic knowledge graph; wherein, the dynamic knowledge graph is dynamically generated based on industries identified from basic industrial data and the relationships between industries; The filtering module is used to determine the target industrial chain corresponding to the first industrial chain information and the second industrial chain information from at least one of the candidate industrial chains based on the strength information and length information of each candidate industrial chain.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the supply chain generation method as described in any one of claims 1 to 8.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the supply chain generation method as described in any one of claims 1 to 8.

Images