Method, device and equipment for generating industrial chain atlas based on model and medium

Abstract

The embodiment of the invention discloses a method, device and equipment for generating an industrial chain atlas based on a model and a medium, and the method comprises the steps: generating a corresponding cue word according to a received industry name and a pre-stored cue word template; according to the generated prompt words and a preset large language model, first industry names of the upstream, the midstream and the downstream of the industry chain of the industry are obtained through networking retrieval, and an industry chain graph of the industry is automatically generated according to all the first industry names and the positions of the corresponding industry chains; therefore, the problem of omission or errors caused by dependence on manpower and subjective experience of the manpower is avoided, and the efficiency of generating the industrial chain atlas is improved.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and in particular to a method, apparatus, equipment and medium for generating industry chain maps based on models. Background Technology

[0002] Supply chain analysis is an important component of modern economic research and business decision-making. It identifies upstream, midstream, and downstream industry nodes by analyzing the supply chain relationships between companies related to a product, such as mobile phones or drones, thereby studying the development trends and risks of the supply chain.

[0003] Current technologies rely on manual research and document analysis, primarily involving securities research institutes or consulting firms manually analyzing each industry chain. The process involves researchers manually extracting industry chain nodes, such as raw material suppliers, manufacturers, and distributors, by reviewing publicly available information like industry reports, company annual reports, and news articles, and then judging the upstream and downstream relationships between these nodes based on experience. Subsequently, charting tools are used to create industry chain maps, marking the connections between nodes. However, this method depends on manual labor and subjective experience, making it prone to omissions or errors, and it is relatively slow. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and medium for generating industry chain maps based on a model, which avoids the problems of omissions, errors, and slow efficiency caused by relying on manual labor and subjective experience when generating industry chain maps.

[0005] In a first aspect, embodiments of this application provide a method for generating industry chain maps based on a model, the method comprising:

[0006] Receive the names of the industries corresponding to the industry chain map to be generated;

[0007] Based on the name and the pre-saved prompt word template, generate corresponding prompt words; input the prompt words into a pre-set large language model, and obtain the names of the primary industries in the upstream, midstream and downstream of the industry chain through network retrieval;

[0008] Based on the names of all primary industries and their corresponding positions in the industrial chain, an industrial chain map of the industry is generated, wherein the position of the industrial chain includes the upstream, midstream and downstream of the industrial chain.

[0009] In one possible implementation, before generating the industry chain map based on all primary industry names and their corresponding industry chain positions, the method further includes:

[0010] For each primary industry name, expand the primary industry name according to a preset template to obtain at least one expanded secondary industry name;

[0011] The process of generating a supply chain map of the industry based on the names of all primary industries and their corresponding positions in the supply chain includes:

[0012] Based on all target industry names and their corresponding positions in the industrial chain, an industrial chain map of the industry is generated, wherein the target industry names include the names of the primary industry and the names of the secondary industry.

[0013] In one possible implementation, before generating the industry chain map based on all target industry names and their corresponding industry chain positions, the method further includes:

[0014] For each target industry name, historical industry names similar to the target industry name are identified in a preset private knowledge base; wherein, the private knowledge base stores a historical knowledge graph, which includes nodes corresponding to each industry name, and there are directed edges between nodes corresponding to industry names that are adjacent in the same industry chain, and the direction of the directed edges is determined according to the order of each position in the industry chain.

[0015] For each historical industry name, determine the node corresponding to the historical industry name. If there are other nodes pointing to the node, find other nodes that are directly or indirectly connected to the node according to the pointing direction. If there are other nodes that the node points to, find other nodes that are directly or indirectly connected to the node according to the pointing direction. The graph that determines the node, other nodes and the pointing relationship between nodes is used as the subgraph corresponding to the historical industry name.

[0016] Merge nodes with the same historical industry name from all the subgraphs to generate the master graph;

[0017] The process of generating a supply chain map of the target industries based on all target industry names and their corresponding supply chain positions includes:

[0018] For each primary industry name, if no similar historical industry name is identified, a node corresponding to the primary industry name is added to the overall graph. Based on the position of the primary industry name in the industry chain, the directed edges between the node corresponding to the primary industry name and other nodes are determined in the overall graph to obtain the industry chain graph of the industry.

[0019] In one possible implementation, the step of searching for other nodes that are directly or indirectly connected to the node in the pointing direction includes:

[0020] Using this node as the current node, perform the following operations in sequence:

[0021] If the historical knowledge graph contains other nodes connected to the current node in the pointing direction, then the current node and the other nodes are treated as nodes in the subgraph, and the other nodes are treated as the current node for subsequent operations. If there are no other nodes connected to the current node in the pointing direction, then only the current node is treated as a node in the subgraph, and the search ends.

[0022] In one possible implementation, determining the directed edges between the node corresponding to the first industry name and other nodes in the overall graph based on the position of the first industry name in the industry chain includes:

[0023] Based on the name of the primary industry and its corresponding position in the industrial chain, determine the name of the first upstream industry and the name of the first downstream industry in the industrial chain corresponding to the name of the primary industry;

[0024] If there is a third industry name in the overall graph that corresponds to the first upstream industry name, then the first node corresponding to the third industry name is determined, and the node corresponding to the first industry name is used as the downstream node of the first node to establish a directed edge in the overall graph.

[0025] If there exists a fourth industry name in the overall graph that corresponds to the first downstream industry name, then the second node corresponding to the fourth industry name is determined, and the node corresponding to the first industry name is used as the upstream node of the second node to establish a directed edge in the overall graph.

[0026] Secondly, embodiments of this application provide an apparatus for generating industry chain maps based on a model, the apparatus comprising:

[0027] The receiving module is used to receive the names of the industries corresponding to the industry chain map to be generated;

[0028] The processing module is used to generate corresponding prompt words based on the name and pre-saved prompt word templates; input the prompt words into a pre-set large language model, and obtain the names of the upstream, midstream and downstream primary industries of the industry chain through network retrieval; and generate an industry chain map of the industry based on all primary industry names and their corresponding industry chain positions, wherein the industry chain positions include the upstream, midstream and downstream of the industry chain.

[0029] In one possible implementation, the processing module is further configured to expand each first industry name according to a preset template to obtain at least one expanded second industry name.

[0030] The processing module is specifically used to generate an industry chain map based on all target industry names and their corresponding industry chain positions, wherein the target industry names include the first industry name and the second industry name.

[0031] In one possible implementation, the processing module is further configured to, for each target industry name, determine historical industry names similar to the target industry name in a preset private knowledge base; wherein, the private knowledge base stores a historical knowledge graph, which includes nodes corresponding to each industry name, wherein there are directed edges between nodes corresponding to industry names that are adjacent in the same industry chain, and the direction of the directed edges is determined according to the order of each position in the industry chain; for each historical industry name, determine the node corresponding to the historical industry name; if there are other nodes pointing to the node, then search for other nodes that are directly or indirectly connected to the node according to the pointing direction; if there are other nodes that the node points to, then search for other nodes that are directly or indirectly connected to the node according to the pointing direction; the graph determined by the node, other nodes, and the pointing relationships between nodes is used as a subgraph corresponding to the historical industry name; merge the nodes with the same historical industry name in all the obtained subgraphs to generate a master graph;

[0032] The processing module is specifically used to, for each first industry name, if no similar historical industry name is found, add a node corresponding to the first industry name to the overall graph, and determine the directed edges between the node corresponding to the first industry name and other nodes in the overall graph according to the position of the first industry name in the industry chain, so as to obtain the industry chain graph of the industry.

[0033] In one possible implementation, the processing module is specifically used to treat the node as the current node and perform the following operations in sequence: if there are other nodes in the historical knowledge graph that are connected to the current node in the pointing direction, then treat the node and the other nodes as nodes in the subgraph and treat the other nodes as the current node for subsequent operations; if there are no other nodes connected to the current node in the pointing direction, then treat only the current node as a node in the subgraph and end the search.

[0034] In one possible implementation, the processing module is specifically configured to determine, based on the first industry name and its corresponding position in the industry chain, the first upstream industry name and the first downstream industry name corresponding to the first industry name; if a third industry name corresponding to the first upstream industry name exists in the overall graph, then a first node corresponding to the third industry name is determined, and a directed edge is established in the overall graph with the node corresponding to the first industry name as the downstream node of the first node; if a fourth industry name corresponding to the first downstream industry name exists in the overall graph, then a second node corresponding to the fourth industry name is determined, and a directed edge is established in the overall graph with the node corresponding to the first industry name as the upstream node of the second node.

[0035] Thirdly, embodiments of this application also provide an electronic device, the electronic device including a processor, the processor being configured to execute a computer program stored in a memory to implement the steps of any of the methods described above.

[0036] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the methods described above.

[0037] In this embodiment, corresponding prompt words are generated based on the received industry name and pre-saved prompt word templates. Then, based on the generated prompt words and a preset large language model, the names of the upstream, midstream, and downstream first industries of the industry chain are obtained through online retrieval. Based on all the first industry names and their corresponding positions in the industry chain, the industry chain map of the industry is automatically generated. This avoids the problems of omissions or errors caused by relying on manual labor and subjective experience, and improves the efficiency of generating the industry chain map. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This application provides a schematic diagram of a method for generating industry chain maps based on a model.

[0040] Figure 2 A schematic diagram illustrating a method for generating a supply chain map by combining existing, known, and accurate industry names, provided in this application embodiment;

[0041] Figure 3 This application provides a schematic diagram illustrating a method for generating an industry chain map using a smartphone as an example.

[0042] Figure 4 A simplified schematic diagram illustrating a model-based method for generating industry chain maps, provided in an embodiment of this application;

[0043] Figure 5 A schematic diagram of a device structure for generating a supply chain map based on a model, provided for an embodiment of this application;

[0044] Figure 6 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0045] To make the objectives and implementation methods of this application clearer, the exemplary implementation methods of this application will be clearly and completely described below with reference to the accompanying drawings of the exemplary embodiments of this application. Obviously, the exemplary embodiments described are only some embodiments of this application, and not all embodiments.

[0046] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0047] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0048] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0049] The term "module" refers to any known or subsequently developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0051] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the principles and practical applications, thereby enabling those skilled in the art to better utilize the described embodiments and various different variations of embodiments suitable for specific use considerations.

[0052] Example 1:

[0053] Figure 1 This application provides a schematic diagram of a method for generating industry chain maps based on a model, which includes the following steps:

[0054] S101: Receive the names of the industries for which the industry chain map is to be generated.

[0055] The method for generating industry chain maps based on models provided in this application is applied to electronic devices, such as computers (PCs), servers, etc.

[0056] Users input the names of the industries for which the industry chain map is to be generated through the front-end display interface of the electronic device, such as "mobile phones," "new energy vehicles," "photovoltaics," or "semiconductors." The electronic device receives these names as input for subsequent processing.

[0057] S102: Generate corresponding prompt words based on the name and the pre-saved prompt word template; input the prompt words into the pre-set large language model, and obtain the names of the upstream, midstream and downstream primary industries of the industry chain through network retrieval.

[0058] A prompt template is a pre-designed text with a fixed structure and guiding statements, stored in an electronic device. Its function is to standardize interaction instructions with large language models, guiding them through online retrieval and ensuring logical correctness in each query. This prompt template typically includes a placeholder variable, such as `{name}`, which receives and inserts the name corresponding to the industry in the generated industry chain map. This generates a clear and well-defined prompt, for example, "Using `{name}` as the target, retrieve and list the specific sub-industry names included in the upstream, midstream, and downstream of the industry chain corresponding to that industry, and provide the function of the industry corresponding to that industry name within the industry chain." Users can customize this prompt template according to their specific needs.

[0059] After receiving the name received in step 101, the electronic device fills the variable placeholders of the prompt word template with the name, thereby generating a complete prompt word with a clear target and clear instructions. For example, if the received name is "smartphone", and the pre-saved prompt word template is "Please use {name} as the target to search and list the specific sub-industry names included in the upstream, midstream, and downstream of the industry chain corresponding to this industry, and give the function of the industry corresponding to the industry name in the industry chain", then the generated prompt word will be "Please use {smartphone} as the target to search and list the specific sub-industry names included in its upstream, midstream, and downstream of the industry chain, and give the function of the industry corresponding to the industry name in the industry chain".

[0060] The generated prompt words are input into a pre-configured large language model. Based on these prompt words, the large language model performs online retrieval and information analysis to obtain the names of the primary industries included in the upstream, midstream, and downstream segments of the industry. This large language model is configured with online retrieval capabilities, enabling it to access the latest publicly available online information, industry databases, or literature, such as the generative pre-trained converter GPT-4, the chat-generating language model ChatGLM, and other similar tools.

[0061] In this application, assuming the received name is "smartphone", and the generated prompt is "Please use {smartphone} as the target to retrieve and list the specific sub-industry names included in its upstream, midstream, and downstream industrial chains, and give the function of the corresponding industry in the industrial chain", then the large language model may return the following content after retrieval:

[0062]

[0063] S103: Based on the names of all primary industries and their corresponding positions in the industrial chain, generate an industrial chain map of the industry, wherein the position of the industrial chain includes the upstream, midstream and downstream of the industrial chain.

[0064] The position in the industrial chain is used to identify the relative stage of each primary industry within the industrial chain. This application primarily categorizes them into three types:

[0065] Upstream refers to the industrial segments that provide raw materials, basic components, or core technology research and development for the target industry; these are typically suppliers. Midstream refers to the industrial segments that process, assemble, and integrate upstream products into the core products or key modules of the target industry; these are typically customers. Downstream refers to the industrial segments involved in the distribution, sales, service, and end-use applications of the target industry's final products; these are typically customers.

[0066] The electronic device determines the position of each primary industry in the upstream, midstream, and downstream segments of the industry chain obtained in step 102. That is, it determines whether each primary industry belongs to the upstream, midstream, or downstream.

[0067] The electronic device then uses each primary industry name as a node and arranges them hierarchically according to their position in the industrial chain. For example, the primary industry name in the upstream of the industrial chain is placed at the top layer, the primary industry name in the midstream of the industrial chain is placed at the middle layer, and the primary industry name in the downstream of the industrial chain is placed at the bottom layer, without making specific restrictions.

[0068] Next, the electronic device generates directed edges between each node, thereby visually constructing a complete industry chain graph, which is then output for users to view and analyze. The force-directed layout algorithm can be used to display the industry chain graph, supporting interactive exploration and multi-layered display. The directed edges between nodes include those between the node corresponding to the first product name in the upstream position and the node corresponding to the first product name in the midstream position, and those between the node corresponding to the first product name in the midstream position and the node corresponding to the first product name in the downstream position.

[0069] The directed edges can point from the node corresponding to the first product name in the upstream position to the node corresponding to the first product name in the midstream position, and the node corresponding to the first product name in the midstream position points to the node corresponding to the first product name in the downstream position; or the node corresponding to the first product name in the downstream position points to the node corresponding to the first product name in the midstream position, and the node corresponding to the first product name in the midstream position points to the node corresponding to the first product name in the upstream position. No specific restrictions are imposed on this.

[0070] In this embodiment, corresponding prompt words are generated based on the received industry name and pre-saved prompt word templates. Then, based on the generated prompt words and a preset large language model, the names of the upstream, midstream, and downstream first industries of the industry chain are obtained through online retrieval. Based on all the first industry names and their corresponding positions in the industry chain, the industry chain map of the industry is automatically generated. This avoids the problems of omissions or errors caused by relying on manual labor and subjective experience, and improves the efficiency of generating the industry chain map.

[0071] Example 2:

[0072] To ensure that the generated industry chain map covers a more comprehensive range of industry names, this application expands each primary industry name to avoid omissions. Specifically, before generating the industry chain map based on all primary industry names and their corresponding industry chain positions, the method further includes:

[0073] For each primary industry name, expand the primary industry name according to a preset template to obtain at least one expanded secondary industry name;

[0074] The process of generating a supply chain map of the industry based on the names of all primary industries and their corresponding positions in the supply chain includes:

[0075] Based on all target industry names and their corresponding positions in the industrial chain, an industrial chain map of the industry is generated, wherein the target industry names include the names of the primary industry and the names of the secondary industry.

[0076] A preset expansion template refers to a pre-designed and stored template in an electronic device that serves as a guiding text rule or instruction for the specific decomposition of a primary industry name. Its purpose is to break down industry categories into more specific subcategories, technologies, or product forms. For example, the preset expansion template might be "Please list the specific product types or key technology branches under {Primary Industry Name}"; another example is "Please further describe what industry {Primary Industry Name} corresponds to and list the names of secondary industries similar to this industry," without any limitations.

[0077] After obtaining the names of the primary industries in the upstream, midstream, and downstream of the industry chain, the electronic device expands each primary industry name according to a preset template to obtain at least one expanded secondary industry name. Specifically, for each primary industry name obtained in step 102, a guiding text rule for specifying and decomposing the primary industry name is obtained according to the preset expansion template. A new query is generated, and the industry database is queried by calling a large language model to obtain at least one expanded secondary industry name. For example, if the primary industry name is "battery manufacturing", the preset expansion template is "Please list the specific product types or key technology branches under {battery manufacturing}". Then, the electronic device calls the large language model to query the industry database and outputs more specific secondary industry names such as "positive electrode material manufacturing" and "negative electrode material manufacturing".

[0078] The electronic device uses the obtained primary industry name and secondary industry name as target industry names, and specifies the position of the industrial chain corresponding to each target industry name. The position of the industrial chain for the secondary industry name is the same as the position of the corresponding expanded primary industry name. Then, based on all target industry names and their corresponding industrial chain positions, the electronic device generates an industrial chain map for that industry. The specific process of generating the industrial chain map is consistent with the process described in step 103, and will not be repeated here.

[0079] In this embodiment of the application, by expanding the name of the first industry according to a preset template, at least one expanded name of the second industry is obtained. Then, based on the name of the first industry and the name of the second industry and the position of the corresponding industrial chain, an industrial chain map of the industry is generated, which greatly enriches the information content and analytical value of the map, ensures that the generated industrial chain map covers more comprehensive and complete industry names, and avoids omissions.

[0080] Example 3:

[0081] To ensure that the generated industry chain map covers more comprehensive and accurate industry names, this application, after obtaining all target industry names and their corresponding industry chain positions, also combines existing known accurate industry names to generate the industry chain map for that industry, further ensuring the accuracy and comprehensiveness of the industry names in the industry chain. Figure 2 A schematic diagram illustrating a method for generating a supply chain map by combining existing, known, and accurate industry names, as provided in this application embodiment, includes the following steps:

[0082] S201: For each target industry name, determine the historical industry names similar to the target industry name in a preset private knowledge base; wherein, the private knowledge base stores a historical knowledge graph, which includes nodes corresponding to each industry name, wherein there are directed edges between nodes corresponding to industry names that are adjacent in the same industry chain, and the direction of the directed edges is determined according to the order of each position in the industry chain.

[0083] The electronic device pre-stores a preset private knowledge base, which contains a manually verified historical knowledge graph. This historical knowledge graph includes nodes corresponding to various industry names and records the connections between nodes. Specifically, the historical knowledge graph records directed edges between nodes corresponding to industry names that are adjacent in the same industry chain. The direction of these directed edges is determined according to the order of positions in the industry chain. For example, a node corresponding to a product name in an upstream position points to a node corresponding to a product name in a midstream position, or a node corresponding to a product name in a midstream position points to a node corresponding to a product name in a downstream position. Alternatively, a node corresponding to a product name in a downstream position can point to a node corresponding to a product name in a midstream position, or a node corresponding to a product name in a midstream position can point to a node corresponding to a product name in an upstream position. No specific limitation is made in this regard.

[0084] For each target industry name, the electronic device identifies historical industry names similar to the target industry name in a preset private knowledge base. Specifically, this involves: determining the semantic feature vectors corresponding to the target industry name and all historical industry names contained within the historical knowledge graph of the private knowledge base; and for each historical industry name's semantic feature vector, calculating the semantic similarity between the target industry name and the historical industry name using a word vector model, based on the semantic feature vectors corresponding to both. If the similarity exceeds a preset threshold, the historical industry name is determined to be "similar" to the target industry name. For example, "solid-state battery manufacturing" might be considered similar to "lithium battery manufacturing" in the historical knowledge graph. This preset threshold can be set by the user according to their actual needs.

[0085] S202: For each historical industry name, determine the node corresponding to the historical industry name. If there are other nodes pointing to the node, find other nodes that are directly or indirectly connected to the node according to the pointing direction. If there are other nodes that the node points to, find other nodes that are directly or indirectly connected to the node according to the pointing direction. The graph that determines the node, other nodes and the pointing relationship between nodes is used as the subgraph corresponding to the historical industry name.

[0086] For each similar historical industry name identified in step 201, the electronic device locates the node corresponding to that historical industry name in the historical knowledge graph. Then, starting from the node corresponding to that historical industry name, if other nodes point to that node, the device searches for other nodes that are directly or indirectly connected to that node in the direction of that direction, i.e., tracing back to the upstream nodes of that node, and further iterating to find the upstream nodes of these upstream nodes, until all reverse connected paths have been traversed; if other nodes are pointed to by that node, the device searches for other nodes that are directly or indirectly connected to that node in the direction of that direction, i.e., tracing forward to the downstream nodes of that node, and further iterating to find the downstream nodes of these downstream nodes, until all forward connected paths have been traversed. The specific process is as follows:

[0087] Using this node as the current node, perform the following operations in sequence:

[0088] If the historical knowledge graph contains other nodes connected to the current node in the pointing direction, then the current node and the other nodes are treated as nodes in the subgraph, and the other nodes are treated as the current node for subsequent operations. If there are no other nodes connected to the current node in the pointing direction, then only the current node is treated as a node in the subgraph, and the search ends.

[0089] The electronic device takes the node corresponding to the historical industry name as the current node. If there are other nodes in the historical knowledge graph connected to the current node in the pointing direction, then this node and the other nodes are added as nodes in a subgraph. The other nodes are then added as the current node again to determine if there are other nodes connected to the current node in the pointing direction. If not, it proves that the source node has been found, and only the current node is added as a node in the subgraph, then the search ends. The pointing direction includes two cases: the node pointing to other nodes, and other nodes pointing to the node.

[0090] For example, suppose there is an industry chain A in the historical knowledge graph, which includes nodes a, b, c, d, and e, and the connection relationship is node a→node b→node c→node d→node e. If the historical industry name corresponds to node c, the electronic device takes node c as the current node. It also determines that the historical knowledge graph has other nodes connected to the current node in the pointing direction, including nodes b and d. Therefore, the electronic device takes node c, along with nodes b and d, as nodes in the subgraph. Then, for node b, the electronic device again takes node b as the current node and determines that other nodes connected in the pointing direction include node a. Therefore, node a is also taken as a node in the subgraph. Since node a has no other connected nodes in the pointing direction, the search in that pointing direction ends. Similarly, for node d, the electronic device again takes node d as the current node and determines that other connected nodes in the pointing direction include node e. Therefore, node e is also taken as a node in the subgraph. Since node e has no other connected nodes in the pointing direction, the search in that pointing direction ends. Therefore, the electronic device ultimately determined that nodes a, b, c, d, and e are all nodes in the subgraph corresponding to the historical industry names.

[0091] The electronic device will identify all the nodes and all the directed edges connecting these nodes, which together form a local network centered on the name of the historical industry, that is, the subgraph corresponding to the name of the historical industry.

[0092] S203: Merge nodes with the same historical industry name in all the obtained subgraphs to generate the master graph.

[0093] After extracting multiple subgraphs for multiple target industry names, these subgraphs may contain nodes with the same historical industry names. For example, multiple industries are associated with the "battery manufacturing" node in the historical knowledge graph.

[0094] The electronic device merges all extracted subgraphs according to the following rules: nodes with the same historical industry name are identified as the same node, and duplicate edges are removed, ultimately forming a master graph. This master graph serves as the basis for generating the final industry chain map.

[0095] S204: The step of generating the industry chain graph based on all target industry names and their corresponding industry chain positions includes: for each first industry name, if no historical industry name similar to the first industry name is determined, then a node corresponding to the first industry name is added to the overall graph, and the directed edges between the node corresponding to the first industry name and other nodes are determined in the overall graph according to the position of the first industry name in the industry chain, so as to obtain the industry chain graph.

[0096] For each primary industry name obtained in step 102, the electronic device determines whether a similar historical industry name has been identified in the historical knowledge graph. If a similar historical industry name has been identified, it means that the primary industry name already exists in the overall graph, and the primary industry name has been integrated into the overall graph through the subgraph, so there is no need to add it again. If no similar historical industry name has been identified, it means that the primary industry name lacks a similar historical industry name in the preset private knowledge base and is an emerging industry. At this time, the electronic device creates a new node for the primary industry name in the overall graph and establishes directed edges between the corresponding node of the primary industry name and other nodes in the overall graph according to the position of the primary industry name in the industry chain.

[0097] The step of determining the directed edges between the node corresponding to the first industry name and other nodes in the overall graph based on the position of the first industry name in the industry chain includes:

[0098] Based on the name of the primary industry and its corresponding position in the industrial chain, determine the name of the first upstream industry and the name of the first downstream industry in the industrial chain corresponding to the name of the primary industry;

[0099] If there is a third industry name in the overall graph that corresponds to the first upstream industry name, then the first node corresponding to the third industry name is determined, and the node corresponding to the first industry name is used as the downstream node of the first node to establish a directed edge in the overall graph.

[0100] If there exists a fourth industry name in the overall graph that corresponds to the first downstream industry name, then the second node corresponding to the fourth industry name is determined, and the node corresponding to the first industry name is used as the upstream node of the second node to establish a directed edge in the overall graph.

[0101] When establishing directed edges between the node corresponding to the primary industry name and other nodes in the overall graph, the electronic device will determine the first upstream industry name and the first downstream industry name corresponding to the primary industry name in the industrial chain based on the primary industry name and the corresponding position in the industrial chain. There may be only the corresponding first upstream industry name, or only the corresponding first downstream industry name, or both the corresponding first upstream industry name and the first downstream industry name.

[0102] Subsequently, if a tertiary industry name corresponding to the first upstream industry name exists in the overall graph, then the first node corresponding to the tertiary industry name is determined, meaning that the first node is the upstream node corresponding to the node corresponding to the first industry name. Then, a directed edge is established in the overall graph with the node corresponding to the first industry name as its downstream node. If a quaternary industry name corresponding to the first downstream industry name exists in the overall graph, then the second node corresponding to the quaternary industry name is determined, meaning that the second node is the downstream node corresponding to the node corresponding to the first industry name. Then, a directed edge is established in the overall graph with the node corresponding to the first industry name as its upstream node.

[0103] Ultimately, after the above integration, supplementation, and connection relationships are established, the resulting industry chain map is a generated industry chain map that combines historical knowledge map and new industry coverage.

[0104] In this embodiment of the application, by adding the name of the emerging primary industry to the existing known and accurate master map of the corresponding industry, the accuracy and comprehensiveness of the generated industrial chain map are improved. It can handle emerging industrial chains and cross-industrial chains that are difficult to cover by traditional methods, and provide a more comprehensive perspective on industrial analysis.

[0105] Example 4:

[0106] The following example will be used to further describe the specific implementation of this application in detail. Figure 3 This application provides a schematic diagram of a method for generating a supply chain map using a smartphone as an example. The process includes the following steps:

[0107] S301: Internet-connected smartphone supply chain.

[0108] Using a large language model to perform online retrieval, with the prompt: "Please use {smartphone} as the target, retrieve and list the specific sub-industry names included in its upstream, midstream, and downstream industrial chains, and provide the function of the corresponding industry in the industrial chain," the following main results were obtained:

[0109]

[0110] The specific process described in step 102 of the above embodiment 1 will not be repeated here.

[0111] S302: Retrieve historical data from a private knowledge base.

[0112] Historical supply chain data related to smartphones is retrieved from a private knowledge base, revealing relevant information on the mobile communication equipment supply chain and the consumer electronics product supply chain. The node relationships within these chains are extracted and then aggregated and deduplicated. This is the specific process described in steps 201-203 of Example 3 above, and will not be repeated here.

[0113] S303: Node fusion and graph generation.

[0114] The online search results are integrated with data from a private knowledge base. A large language model identifies similar nodes and merges them. For example, chip design and integrated circuit design are considered as the same node, ultimately generating a complete smartphone industry chain map. This is the specific process described in step 204 of embodiment 3 above, and will not be repeated here.

[0115] In generating the industry chain map, this application integrates the industry chain retrieval results from the large language model with existing data in the private knowledge base, combining the industry chain data from online retrieval and the private knowledge base to form a unified industry chain map.

[0116] Figure 4 This is a simplified schematic diagram illustrating a model-based method for generating industry chain maps, as provided in an embodiment of this application. Figure 4 As shown, upon receiving a new industry chain theme or industry name, the electronic device will then conduct a network search to determine the upstream and downstream node information of the industry chain, which is the specific process described in Embodiment 1 above, and will not be repeated here. Based on a private knowledge base, it will retrieve the old industry chain and its upstream and downstream node information. Then, based on the determined upstream and downstream node information of the new industry chain and the old industry chain, the information will be merged and deduplicated to obtain a new industry chain map. This is the specific process described in Embodiment 3 above, and will not be repeated here.

[0117] Example 5:

[0118] Based on the same concept, embodiments of this application provide an apparatus for generating industry chain maps based on a model. Figure 5 A schematic diagram of a device structure for generating a supply chain map based on a model is provided in this application embodiment. Please refer to... Figure 5 The device includes:

[0119] The receiving module 501 is used to receive the names of the industries corresponding to the industry chain map to be generated;

[0120] The processing module 502 is used to generate corresponding prompt words based on the name and the pre-saved prompt word template; input the prompt words into a pre-set large language model, and obtain the names of the upstream, midstream and downstream primary industries of the industry chain through network retrieval; and generate the industry chain map of the industry based on all primary industry names and the corresponding positions of the industry chain, wherein the positions of the industry chain include the upstream, midstream and downstream of the industry chain.

[0121] In one possible implementation, the processing module 502 is further configured to expand each first industry name according to a preset template to obtain at least one expanded second industry name.

[0122] The processing module 502 is specifically used to generate an industry chain map based on all target industry names and their corresponding industry chain positions, wherein the target industry names include the first industry name and the second industry name.

[0123] In one possible implementation, the processing module 502 is further configured to, for each target industry name, determine historical industry names similar to the target industry name in a preset private knowledge base; wherein, the private knowledge base stores a historical knowledge graph, which includes nodes corresponding to each industry name, wherein there are directed edges between nodes corresponding to industry names that are adjacent in the same industry chain, and the direction of the directed edges is determined according to the order of each position in the industry chain; for each historical industry name, determine the node corresponding to the historical industry name; if there are other nodes pointing to the node, then search for other nodes that are directly or indirectly connected to the node according to the pointing direction; if there are other nodes that the node points to, then search for other nodes that are directly or indirectly connected to the node according to the pointing direction; the graph determined by the node, other nodes, and the pointing relationships between nodes is used as a subgraph corresponding to the historical industry name; merge the nodes with the same historical industry name in all the obtained subgraphs to generate a master graph;

[0124] The processing module 502 is specifically used to, for each first industry name, if no historical industry name similar to the first industry name is determined, add a node corresponding to the first industry name in the overall graph, and determine the directed edges between the node corresponding to the first industry name and other nodes in the overall graph according to the position of the first industry name in the industry chain, so as to obtain the industry chain graph of the industry.

[0125] In one possible implementation, the processing module 502 is specifically used to treat the node as the current node and perform the following operations in sequence: if there are other nodes in the historical knowledge graph that are connected to the current node in the pointing direction, then treat the node and the other nodes as nodes in the subgraph and treat the other nodes as the current node for subsequent operations; if there are no other nodes connected to the current node in the pointing direction, then treat only the current node as a node in the subgraph and end the search.

[0126] In one possible implementation, the processing module 502 is specifically configured to: determine the first upstream industry name and the first downstream industry name corresponding to the first industry name in the industrial chain based on the first industry name and the corresponding position in the industrial chain; if there is a third industry name corresponding to the first upstream industry name in the overall graph, then determine the first node corresponding to the third industry name, and establish a directed edge in the overall graph with the node corresponding to the first industry name as the downstream node of the first node; if there is a fourth industry name corresponding to the first downstream industry name in the overall graph, then determine the second node corresponding to the fourth industry name, and establish a directed edge in the overall graph with the node corresponding to the first industry name as the upstream node of the second node.

[0127] Example 6:

[0128] Based on the same concept, embodiments of this application provide an electronic device that can implement the steps of the model-based method for generating industry chain maps described above. Figure 6 This application provides a schematic diagram of an electronic device structure, such as... Figure 6 As shown, it includes: processor 601, communication interface 602, memory 603 and communication bus 604, wherein processor 601, communication interface 602 and memory 603 communicate with each other through communication bus 604.

[0129] The memory 603 stores a computer program, which, when executed by the processor 601, causes the processor 601 to perform the following steps:

[0130] Receive the names of the industries corresponding to the industry chain map to be generated;

[0131] Based on the name and the pre-saved prompt word template, generate corresponding prompt words; input the prompt words into a pre-set large language model, and obtain the names of the primary industries in the upstream, midstream and downstream of the industry chain through network retrieval;

[0132] Based on the names of all primary industries and their corresponding positions in the industrial chain, an industrial chain map of the industry is generated, wherein the position of the industrial chain includes the upstream, midstream and downstream of the industrial chain.

[0133] In one possible implementation, the processor 601 is further configured to expand each first industry name according to a preset template to obtain at least one expanded second industry name.

[0134] The processor 601 is specifically used to generate an industry chain map based on all target industry names and their corresponding industry chain positions, wherein the target industry names include the first industry name and the second industry name.

[0135] In one possible implementation, the processor 601 is further configured to, for each target industry name, determine historical industry names similar to the target industry name in a preset private knowledge base; wherein the private knowledge base stores a historical knowledge graph, which includes nodes corresponding to each industry name, wherein nodes corresponding to industry names that are adjacent in the same industry chain have directed edges between them, and the direction of the directed edges is determined according to the order of each position in the industry chain; for each historical industry name, determine the node corresponding to the historical industry name; if there are other nodes pointing to the node, then search for other nodes that are directly or indirectly connected to the node according to the pointing direction; if there are other nodes that the node points to, then search for other nodes that are directly or indirectly connected to the node according to the pointing direction; and use the graph determined by the node, other nodes, and the pointing relationships between nodes as the subgraph corresponding to the historical industry name; merge the nodes with the same historical industry name in all the obtained subgraphs to generate a master graph;

[0136] The processor 601 is specifically used to, for each first industry name, if no historical industry name similar to the first industry name is determined, add a node corresponding to the first industry name in the overall graph, and determine the directed edges between the node corresponding to the first industry name and other nodes in the overall graph according to the position of the first industry name in the industry chain, so as to obtain the industry chain graph of the industry.

[0137] In one possible implementation, the processor 601 is specifically configured to use the node as the current node and perform the following operations in sequence: if there are other nodes in the historical knowledge graph that are connected to the current node in the pointing direction, then the node and the other nodes are used as nodes in the subgraph, and the other nodes are used as the current node for subsequent operations; if there are no other nodes connected to the current node in the pointing direction, then only the current node is used as a node in the subgraph, and the search ends.

[0138] In one possible implementation, the processor 601 is specifically configured to: determine the first upstream industry name and the first downstream industry name corresponding to the first industry name in the industrial chain based on the first industry name and the corresponding position in the industrial chain; if there is a third industry name corresponding to the first upstream industry name in the overall graph, then determine the first node corresponding to the third industry name, and establish a directed edge in the overall graph with the node corresponding to the first industry name as the downstream node of the first node; if there is a fourth industry name corresponding to the first downstream industry name in the overall graph, then determine the second node corresponding to the fourth industry name, and establish a directed edge in the overall graph with the node corresponding to the first industry name as the upstream node of the second node.

[0139] The communication bus mentioned in the aforementioned electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not indicate that there is only one bus or one type of bus. Communication interface 602 is used for communication between the aforementioned electronic device and other devices. The memory can include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory can also be at least one storage device located remotely from the aforementioned processor.

[0140] The processors mentioned above can be general-purpose processors, including central processing units, network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits, field-programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0141] Example 7:

[0142] Based on the same concept, embodiments of this application provide a computer-readable storage medium storing a computer program executable by a processor. When the program runs on the processor, it causes the processor to execute any of the model-based supply chain mapping methods discussed above. Since the principle behind the problem solved by the aforementioned computer-readable storage medium is similar to that of the model-based supply chain mapping method, the implementation of the aforementioned computer-readable storage medium can be found in the implementation of the method; repeated details will not be elaborated further.

[0143] Based on the same concept, this application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to execute any of the model-based supply chain mapping methods discussed above. Since the principle by which the above computer program product solves the problem is similar to that of the model-based supply chain mapping method, the implementation of the above computer program product can refer to the implementation of the method, and repeated details will not be elaborated further.

[0144] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] Computer programs used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing status information from the computer-readable program instructions to implement various aspects of this disclosure.

[0146] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0147] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0148] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0149] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0150] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0151] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for generating industry chain maps based on a model, characterized in that, The method includes: Receive the names of the industries corresponding to the industry chain map to be generated; Based on the name and the pre-saved prompt word template, generate corresponding prompt words; input the prompt words into a pre-set large language model, and obtain the names of the primary industries in the upstream, midstream and downstream of the industry chain through network retrieval; Based on the names of all primary industries and their corresponding positions in the industrial chain, an industrial chain map of the industry is generated, wherein the position of the industrial chain includes the upstream, midstream and downstream of the industrial chain.

2. The method according to claim 1, characterized in that, Before generating the industry chain map based on all primary industry names and their corresponding industry chain positions, the method further includes: For each primary industry name, expand the primary industry name according to a preset template to obtain at least one expanded secondary industry name; The process of generating a supply chain map of the industry based on the names of all primary industries and their corresponding positions in the supply chain includes: Based on all target industry names and their corresponding positions in the industrial chain, an industrial chain map of the industry is generated, wherein the target industry names include the names of the primary industry and the names of the secondary industry.

3. The method according to claim 2, characterized in that, Before generating the industry chain map based on all target industry names and their corresponding industry chain positions, the method further includes: For each target industry name, historical industry names similar to the target industry name are identified in a preset private knowledge base; wherein, the private knowledge base stores a historical knowledge graph, which includes nodes corresponding to each industry name, and there are directed edges between nodes corresponding to industry names that are adjacent in the same industry chain, and the direction of the directed edges is determined according to the order of each position in the industry chain. For each historical industry name, determine the node corresponding to the historical industry name. If there are other nodes pointing to the node, find other nodes that are directly or indirectly connected to the node according to the pointing direction. If there are other nodes that the node points to, find other nodes that are directly or indirectly connected to the node according to the pointing direction. The graph that determines the node, other nodes and the pointing relationship between nodes is used as the subgraph corresponding to the historical industry name. Merge nodes with the same historical industry name from all the subgraphs to generate the master graph; The process of generating a supply chain map of the target industries based on all target industry names and their corresponding supply chain positions includes: For each primary industry name, if no similar historical industry name is identified, a node corresponding to the primary industry name is added to the overall graph. Based on the position of the primary industry name in the industry chain, the directed edges between the node corresponding to the primary industry name and other nodes are determined in the overall graph to obtain the industry chain graph of the industry.

4. The method according to claim 3, characterized in that, The step of searching for other nodes that are directly or indirectly connected to the current node in the specified direction includes: Using this node as the current node, perform the following operations in sequence: If the historical knowledge graph contains other nodes connected to the current node in the pointing direction, then the current node and the other nodes are treated as nodes in the subgraph, and the other nodes are treated as the current node for subsequent operations. If there are no other nodes connected to the current node in the pointing direction, then only the current node is treated as a node in the subgraph, and the search ends.

5. The method according to claim 3, characterized in that, Based on the position of the primary industry name in the industry chain, determining the directed edges between the node corresponding to the primary industry name and other nodes in the overall graph includes: Based on the name of the primary industry and its corresponding position in the industrial chain, determine the name of the first upstream industry and the name of the first downstream industry in the industrial chain corresponding to the name of the primary industry; If there is a third industry name in the overall graph that corresponds to the first upstream industry name, then the first node corresponding to the third industry name is determined, and the node corresponding to the first industry name is used as the downstream node of the first node to establish a directed edge in the overall graph. If there exists a fourth industry name in the overall graph that corresponds to the first downstream industry name, then the second node corresponding to the fourth industry name is determined, and the node corresponding to the first industry name is used as the upstream node of the second node to establish a directed edge in the overall graph.

6. A device for generating industry chain maps based on models, characterized in that, The device includes: The receiving module is used to receive the names of the industries corresponding to the industry chain map to be generated; The processing module is used to generate corresponding prompt words based on the name and pre-saved prompt word templates; input the prompt words into a pre-set large language model, and obtain the names of the upstream, midstream and downstream primary industries of the industry chain through network retrieval; and generate an industry chain map of the industry based on all primary industry names and their corresponding industry chain positions, wherein the industry chain positions include the upstream, midstream and downstream of the industry chain.

7. The apparatus according to claim 6, characterized in that, The processing module is also used to expand each primary industry name according to a preset template to obtain at least one expanded secondary industry name. The processing module is specifically used to generate an industry chain map based on all target industry names and their corresponding industry chain positions, wherein the target industry names include the first industry name and the second industry name.

8. The apparatus according to claim 7, characterized in that, The processing module is further configured to, for each target industry name, determine historical industry names similar to the target industry name in a preset private knowledge base; wherein, the private knowledge base stores a historical knowledge graph, which includes nodes corresponding to each industry name, wherein nodes corresponding to industry names that are adjacent in the same industry chain have directed edges between them, and the direction of the directed edges is determined according to the order of each position in the industry chain; for each historical industry name, determine the node corresponding to the historical industry name; if there are other nodes pointing to the node, then search for other nodes that are directly or indirectly connected to the node according to the pointing direction; if there are other nodes that the node points to, then search for other nodes that are directly or indirectly connected to the node according to the pointing direction; the graph determined by the node, other nodes, and the pointing relationships between nodes is used as the subgraph corresponding to the historical industry name; merge the nodes with the same historical industry name in all the obtained subgraphs to generate the overall graph; The processing module is specifically used to, for each first industry name, if no similar historical industry name is found, add a node corresponding to the first industry name to the overall graph, and determine the directed edges between the node corresponding to the first industry name and other nodes in the overall graph according to the position of the first industry name in the industry chain, so as to obtain the industry chain graph of the industry.

9. An electronic device, characterized in that, The electronic device includes a processor for implementing the method as described in any one of claims 1-5 when executing a computer program stored in a memory.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-5.

Images