Enterprise portrait generation method, computer device, and computer-readable storage medium

Abstract

Embodiments of the present application disclose a kind of enterprise portrait generation method, computer equipment and computer readable storage medium, related to data processing technical field, method includes obtaining target enterprise information;According to the target enterprise information, determine the entity of the target enterprise information and the association between all entities;Identify the language corresponding to each entity and identify the language identified, obtain identification information;According to all entities, the association and the identification information generation enterprise knowledge graph;According to the enterprise knowledge graph, generate the enterprise portrait corresponding to the target enterprise information.The present application can be based on instruction atlas to carry out multi-dimensional accurate analysis to enterprise, obtain accurate and meet the enterprise portrait of enterprise itself demand, facilitate enterprise to carry out business opportunity mining and clue analysis.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method for generating enterprise profiles, a computer device, and a computer-readable storage medium. Background Technology

[0002] With the deepening of trade liberalization and the increasingly fierce international competition under the background of economic globalization, international trade between enterprises is increasing. However, international trade information is affected by many factors such as language, region and information dispersion, making it difficult for different enterprises to have in-depth understanding. Enterprises need to spend a lot of time and energy to repeatedly collect, compare and analyze information.

[0003] Currently, there are methods to mine data or transaction information of international trade companies, or to create trade company profiles by combining them with the company's Customer Relationship Management (CRM) system. All of these methods focus on displaying the company's own information. However, as the types of traded goods and imports and exports become increasingly diversified, the existing trade company profiles are displaying too much information, which may even cause companies to miss potential business opportunities. Summary of the Invention

[0004] In view of this, one of the objectives of this application is to provide a method for generating enterprise profiles, a computer device, and a computer-readable storage medium, which can at least solve some of the above-mentioned technical problems.

[0005] In a first aspect, embodiments of this application provide a method for generating an enterprise profile, the method comprising:

[0006] Obtain target company information;

[0007] Based on the target enterprise information, determine the entities in the target enterprise information and the relationships between all entities;

[0008] Identify the language corresponding to each entity and label the identified languages ​​to obtain labeling information;

[0009] Generate an enterprise knowledge graph based on all entities, the aforementioned relationships, and the aforementioned identification information;

[0010] Generate an enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph.

[0011] In one possible implementation, obtaining the target company information includes:

[0012] Obtain initial enterprise information from different information sources, wherein the initial enterprise information includes at least two types of initial information items;

[0013] An initial enterprise information set is formed based on at least two of the initial information items, and the target enterprise information is determined based on the initial enterprise information set.

[0014] In one possible implementation, after determining the relationships between entities and all entities in the target enterprise information based on the target enterprise information, the method further includes:

[0015] Set weights for different entities;

[0016] The step of generating an enterprise knowledge graph based on all entities, the relationships, and the identification information includes:

[0017] An enterprise knowledge graph is generated based on all entities, the weights of each entity, the relationships, and the identification information.

[0018] In one possible implementation, after assigning weights to different entities, the method further includes:

[0019] Obtain the information sources for each entity and calculate the similarity between each entity;

[0020] The weight of the first entity is increased by a first value, where the first entity is an entity whose information sources are different and whose content similarity is within a first preset similarity range;

[0021] The weight of the second entity is increased by a second value. The second entity is an entity whose content similarity after translation into a preset language falls within the second preset similarity range.

[0022] In one possible implementation, generating the enterprise knowledge graph based on all entities, the weights corresponding to each entity, the association relationships, and the identification information includes:

[0023] All entities, the weights of each entity, and the identification information are stored in the graph database to obtain graph nodes;

[0024] The relationships are stored in a graph database to obtain the relationship edges;

[0025] The enterprise knowledge graph is determined based on the graph nodes and the relation edges.

[0026] In one possible implementation, after determining the enterprise knowledge graph based on the graph nodes and the relation edges, the method further includes:

[0027] The graph database is updated at preset time intervals;

[0028] The enterprise knowledge graph is regenerated based on the updated database, corresponding to new graph nodes and new relational edges.

[0029] In one possible implementation, after generating the enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph, the method further includes:

[0030] Obtain the first enterprise information corresponding to the first user, wherein the first enterprise information includes at least two first information items;

[0031] If the identification information of all entities is the same as the preset identification, calculate the first similarity between all entities and all the first information items according to the preset calculation rules;

[0032] A first enterprise profile is generated based on the enterprise knowledge graph of the third entity, wherein the third entity is the entity corresponding to the first similarity with a preset similarity greater than or equal to the preset similarity.

[0033] In one possible implementation, after generating the enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph, the method further includes:

[0034] Obtain the priority of display permissions for each first information item in the first enterprise information;

[0035] The third entity is determined based on the display permission priority and a first similarity greater than or equal to the preset similarity, and the first enterprise profile is generated based on the enterprise knowledge graph to which the third entity is located.

[0036] Thirdly, embodiments of this application provide a computer device, which includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements the enterprise profile generation method provided in the first aspect.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by one or more processors, implements the enterprise profile generation method provided in the first aspect.

[0038] The enterprise profile generation method provided in this application involves acquiring target enterprise information, determining the entities and relationships between all entities based on the target enterprise information, identifying the language corresponding to each entity and marking the identified language to obtain marking information, generating an enterprise knowledge graph based on all entities, relationships, and marking information, and finally generating an enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph. This method enables multi-dimensional and precise analysis of the enterprise based on the indicator graph, resulting in an accurate enterprise profile that meets the enterprise's own needs, facilitating business opportunity mining and lead analysis for the enterprise. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. It should be understood that the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A flowchart illustrating a method for generating a corporate profile, as provided in an embodiment of this application;

[0041] Figure 2 This is a diagram illustrating the internal structure of a computer device as provided in an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0044] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0045] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0046] In summary of the various embodiments of this application, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.

[0047] In the description of this application, it should be noted that if terms such as "upper," "lower," "inner," or "outer" are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the invention is usually placed during use, they are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0048] Furthermore, the terms "first" and "second" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0049] It should be noted that, where there is no conflict, the features in the embodiments of this application can be combined with each other.

[0050] Please see Figure 1 , Figure 1 The following is a flowchart of a method for generating a corporate profile, which is provided in an embodiment of this application. The steps of the method will be described in detail below.

[0051] S110, Obtain target company information.

[0052] In this embodiment, the target enterprise information can be foreign trade enterprise information or domestic import and export trade enterprise information. Generally, the more enterprise information there is, the wider the coverage, and the more accurate and comprehensive the enterprise analysis can be. Optionally, the target enterprise information can also include other general non-foreign trade enterprise information within China. For ease of description, this embodiment and the following embodiments use "enterprise information" to represent foreign trade enterprise information and general non-foreign trade enterprise information. This embodiment can obtain the target enterprise information using the computer equipment described in the following embodiments.

[0053] Given that corporate information is scattered across various internet platforms, in addition to the company's own official website, it is often found on social media platforms and trade transaction platforms.

[0054] In some embodiments, the name of the target company or other identifiers that can identify the target company are collected. Information from the target company's official website, social media accounts, foreign trade platforms, and publicly available information from overseas customs is then gathered using this name or other identifier. These other identifiers include at least one of the following: company alias, company logo, or unified social credit code. This embodiment allows for the rapid acquisition of relevant information about the target company from the internet using these identifiers.

[0055] In some embodiments, with the authorization licenses obtained from various web pages or platforms, relevant information about the target company can be obtained based on conventional web crawling techniques.

[0056] Optionally, obtain target company information, including:

[0057] Obtain initial enterprise information from different information sources, including at least two initial information items;

[0058] An initial enterprise information set is formed based on at least two initial information items, and the target enterprise information is determined based on the initial enterprise information set.

[0059] The different information sources in this embodiment can be understood as the different official websites or other social media platforms in the above embodiments. The initial information items include the company name or alias, company profile, main business or products, company location, company size, contact information such as position, email and telephone, company size, company establishment time, import and export regions, customs import and export records such as time, region, trading partners, traded products and trade volume, exhibition information such as time, region and products, etc., as well as the information source and information update time corresponding to each initial information item.

[0060] Specifically, each initial information item forms an initial enterprise information set. In this embodiment, the initial information can be filtered based on the initial information set to obtain target enterprise information. Filtering the initial information can remove private or duplicate information to obtain target enterprise information that is highly relevant to the target enterprise. Based on the target enterprise information, the target enterprise can be accurately analyzed.

[0061] S120, Determine the entities in the target enterprise information and the relationships between all entities based on the target enterprise information.

[0062] In this embodiment, information extraction can be performed on the target enterprise information obtained in the above embodiments to determine the entities of the target enterprise information and the relationships between the entities. Specifically, the Universal Information Extraction (UIE) algorithm can be used to extract information from the target enterprise information.

[0063] Specifically, the entity can be a specific name such as Company A, Company B, or Company C, and the relationship can represent the relationship between the three companies, such as Company B and Company C being subsidiaries of Company A.

[0064] S130, identify the language corresponding to each entity and mark the identified language to obtain the marking information.

[0065] Considering that the target enterprise information is mostly international trade enterprise information, the enterprise information exists in multiple languages ​​and the information types are too complicated, this embodiment can identify the language of the entity and mark the identified entity to obtain the corresponding identification information for each entity. The identification information is used based on the language of the corresponding ontology. The identification information includes at least one of pure Arabic numerals, pure English letters, or a combination of Arabic numerals and English letters. The identification information can also be represented by a unified and standardized language such as Chinese. The specific choice can be made according to the actual situation, and this embodiment does not limit it.

[0066] Specifically, in this embodiment, the Language Detect database, an open-source database from Optimaize, can be used to identify the language of entities with high accuracy.

[0067] S140 generates an enterprise knowledge graph based on all entities, relationships, and identification information.

[0068] After obtaining the entities and the relationships between them, this embodiment can store all entities and identification information into nodes, and the relationships between entities can form edges. Based on multiple nodes and multiple edges, an enterprise knowledge graph of the target enterprise information in the above embodiment can be generated, and the target enterprise can be displayed in a multi-dimensional visual graphic.

[0069] S150 generates a corporate profile corresponding to the target corporate information based on the corporate knowledge graph.

[0070] In this embodiment, after obtaining the enterprise knowledge graph, an enterprise profile corresponding to the target enterprise can be generated according to the actual display requirements.

[0071] As can be seen from the above analysis, the enterprise profile generation method provided in this application embodiment obtains target enterprise information, determines the entities of the target enterprise information and the relationships between all entities based on the target enterprise information, then identifies the language corresponding to each entity and marks the identified language to obtain the marking information, then generates an enterprise knowledge graph based on all entities, relationships and marking information, and finally generates an enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph. It can perform multi-dimensional and accurate analysis of the enterprise based on the indicator graph, obtain an accurate enterprise profile that meets the enterprise's own needs, and facilitate the enterprise to conduct business opportunity mining and clue analysis.

[0072] The enterprise knowledge graph generated in the above embodiments can accurately display target enterprise information from multiple dimensions. To further improve the accuracy and usability of the target information display, in one possible implementation, after determining the entities of the target enterprise information and the relationships between all entities based on the target enterprise information, the method further includes:

[0073] Set weights for different entities;

[0074] Generate an enterprise knowledge graph based on all entities, relationships, and identifier information, including:

[0075] A knowledge graph of the enterprise is generated based on all entities, the weights of each entity, their relationships, and identification information.

[0076] In this embodiment, weights can be set for different entities according to actual display requirements. The weights in this embodiment can participate in the process of generating an enterprise knowledge graph. For example, in the enterprise knowledge graph, the node where the entity with the smaller weight is located can be the child node or descendant node of the node of the entity with the larger weight.

[0077] The above embodiments set weights for different entities based on set detection conditions. For example, if some entities are detected and determined to be the same or similar to preset entities, then the weight of those entities is set to be larger. This can easily overlook the timeliness of the target enterprise information and make it difficult to prioritize the display of entities that need user attention and change rapidly.

[0078] In one possible implementation, after assigning weights to different entities, the method further includes:

[0079] Obtain the information sources for each entity and calculate the similarity between each entity;

[0080] The weight of the first entity is increased by a first value. The first entity is an entity with different information sources and a similarity of content within a first preset similarity range.

[0081] The weight of the second entity is increased by a second value. The second entity is the entity whose content similarity after translation into the preset language falls within the second preset similarity range.

[0082] In this embodiment, the specific content of the information source and the entity can be used to determine the entities that need user attention but are also rapidly changing, and then the weights can be superimposed to improve the display priority of the corresponding entities, thereby enhancing the timeliness, reliability and accuracy of the enterprise knowledge graph and enterprise profile.

[0083] Specifically, if some entities come from different information sources but their similarity is within the first preset similarity range, it indicates that these entities are relatively important, and their corresponding weights can be increased accordingly. Entities whose similarity is not within the first preset similarity range will be displayed in the enterprise knowledge graph according to their original weights.

[0084] The entities corresponding to different identifiers refer to entities in different languages. For entities in different languages, they need to be translated into a unified language such as Chinese or English first. Then, the similarity of the translated content is detected, and the weight of entities whose similarity to the translated content is within the second preset similarity range is increased. Similarly, after the same translation, entities whose similarity is not within the second preset similarity range are displayed in the enterprise knowledge graph according to the original weight.

[0085] The first preset similarity range and the second preset similarity range can be set to the same value, or they can be set to different similarity ranges according to actual needs. The similarity in this embodiment can include the overlap of at least one of characters, words, sentences, and paragraphs.

[0086] It should be noted that after setting the weights, the specific content of each entity is translated into a unified, standardized language such as Chinese, and the translated content is stored.

[0087] Optionally, an enterprise knowledge graph can be generated based on all entities, the weights of each entity, their relationships, and identification information, including:

[0088] Store all entities, their corresponding weights, and identifiers into a graph database to obtain graph nodes;

[0089] Store the relationships in a graph database to obtain the relationship edges;

[0090] The enterprise knowledge graph is determined based on the graph nodes and relation edges.

[0091] After clarifying the entities, their weights, and the relationships between them, graph nodes and relational edges can be obtained by storing them in a graph database. Then, an enterprise knowledge graph can be generated based on the graph nodes and relational edges.

[0092] After generating the enterprise knowledge graph, it is still necessary to ensure that the enterprise knowledge graph is updated in the future. This will improve the effectiveness and accuracy of the enterprise knowledge graph by enabling multi-dimensional and accurate analysis of the enterprise based on the indicator graph.

[0093] In one possible implementation, after determining the enterprise knowledge graph based on graph nodes and relation edges, the method further includes:

[0094] Update the graph database at preset time intervals;

[0095] The enterprise knowledge graph is regenerated based on the updated database, corresponding to new graph nodes and new relational edges.

[0096] In this embodiment, setting a preset time interval enables the graph database to be updated periodically, ensuring the effectiveness and accuracy of the graph database, and thus ensuring the effectiveness and accuracy of the enterprise knowledge graph.

[0097] In one possible implementation, after generating a corporate profile corresponding to the target corporate information based on the corporate knowledge graph, the method further includes:

[0098] Obtain the first enterprise information corresponding to the first user, where the first enterprise information includes at least two first information items;

[0099] If the identification information of all entities is the same as the preset identification, calculate the first similarity between all entities and all first information items according to the preset calculation rules;

[0100] The first enterprise profile is generated based on the enterprise knowledge graph of the third entity, where the third entity is the entity corresponding to the first similarity with a preset similarity greater than or equal to the preset similarity.

[0101] In this embodiment, the first user can be understood as a user who wants to view a company. Before obtaining the first company information corresponding to the first user, the computer device can verify the login request information of the first user, and after the verification is successful, obtain the company information of the first user based on the login request information, that is, the first company information.

[0102] The first enterprise information includes at least two of the following: the enterprise's import / export products, the industry it operates in, the enterprise's main import / export regions, the supported import / export freight methods, historical or typical trade records, import / export scale, import / export regions, and the size or type of the trading partner enterprise.

[0103] Before displaying a company profile to the first user, computer equipment needs to make a correlation judgment between the various entities of the company being displayed and the various information items of the first company to which the first user belongs. The company profiles corresponding to entities with high correlation can be displayed to the first user, thereby improving the accuracy and reliability of the company profiles displayed to the first user.

[0104] The preset calculation rule in this embodiment can be a word vector calculation method based on the Word2vec model. Specifically, the first type of word vector of each entity after translation in the above embodiment can be determined firstly based on the Word2vec model, and then the second type of word vector of each first information item of the first enterprise information can be determined based on the Word2vec model. Then, the similarity between the first user's search term and the extended term corresponding to the search term can be calculated based on the first type of word vector and the second type of word vector. The preset similarity in this embodiment is different from the first preset similarity range and the second preset similarity range in the above embodiment.

[0105] In some embodiments, the similarity between the first user's search term and the corresponding extended terms is calculated as cosine similarity.

[0106] In addition, the Word2vec model in the above embodiments can be trained based on product encyclopedia information and product description text, or it can be trained by combining massive amounts of trade product description information.

[0107] This embodiment can determine the enterprise profile to be displayed to the first user by calculating the similarity between the first type of word vectors of each entity after translation in the above embodiment and the second type of word vectors of each first information item of the first enterprise information. If the similarity is sorted from high to low and the enterprise profiles corresponding to the third entities with the top 10 similarity are displayed to the first user, the enterprise profile that meets the actual needs of the first user can be displayed, which is highly practical.

[0108] In one possible implementation, after generating a corporate profile corresponding to the target corporate information based on the corporate knowledge graph, the method further includes:

[0109] Priority for displaying each first information item in the first enterprise information;

[0110] The third entity is determined based on the display permission priority and the first similarity score which is greater than or equal to the preset similarity score, and the first enterprise profile is generated based on the enterprise knowledge graph of the third entity.

[0111] In this embodiment, the display permission priority of all first information items in the first enterprise information can be preset. Based on the similarity determined in the above embodiment and the display permission priority of each first information item obtained in this embodiment, the enterprise profile to be displayed to the first user is determined.

[0112] Specifically, the similarities determined in the above embodiments can be multiplied by the display permission priority of the corresponding first information item, and the product results can be arranged in descending order from largest to smallest. The enterprise profiles of the entities corresponding to the top 10 product results can be displayed to the first user. By introducing the display permission priority of each first information item, this embodiment can further improve the accuracy and practicality of displaying enterprise profiles to the first user.

[0113] In summary, the enterprise profile generation method provided in this application obtains target enterprise information, determines the entities and relationships between all entities based on the target enterprise information, identifies the language corresponding to each entity and marks the identified language to obtain marking information, then generates an enterprise knowledge graph based on all entities, relationships, and marking information, and finally generates an enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph. This method enables multi-dimensional and accurate analysis of enterprises based on the indicator graph, and can further determine the enterprise profile to be displayed to users based on the display permission priority of the first information item closely related to the user and the similarity between the first information item and the entity, resulting in an accurate enterprise profile that meets the enterprise's own needs, facilitating business opportunity mining and lead analysis for enterprises.

[0114] This application also provides a computer device; please refer to [link to relevant documentation]. Figure 2 , Figure 2 This is a diagram illustrating the internal structure of a computer device according to an embodiment of this application. The computer device includes a processor, a memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement the enterprise profile generation method applied to the computer device in the above embodiment. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute the enterprise profile generation method. Those skilled in the art will understand that… Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0115] This application also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the enterprise profile generation method as described in the method embodiment.

[0116] The enterprise profile generation method, computer equipment, and computer-readable storage medium provided in this application acquire target enterprise information, determine the entities of the target enterprise information and the relationships between all entities based on the target enterprise information, identify the language corresponding to each entity and mark the identified language to obtain mark information, then generate an enterprise knowledge graph based on all entities, relationships, and mark information, and finally generate an enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph. It can perform multi-dimensional and accurate analysis of enterprises based on the indicator graph, obtain accurate enterprise profiles that meet the enterprise's own needs, and facilitate enterprises to conduct business opportunity mining and clue analysis.

[0117] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRD RAM), and memory bus dynamic RAM (RDRAM).

[0118] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method of generating a business portrait, characterized by, The method, applicable to scenarios where enterprise profiles are generated based on foreign trade enterprise information in multiple languages, includes: Obtain target company information; Based on the target enterprise information, determine the entities in the target enterprise information and the relationships between all entities; Identify the language corresponding to each entity and label the language corresponding to the identified entity to obtain the labeling information of the language corresponding to the entity; Translate the specific content of each entity into a preset language; All entities and their identification information, uniformly translated into the preset language, are stored in the node; The relationships between the various entities are formed into edges; Generate an enterprise knowledge graph based on multiple nodes and edges; Generate an enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph; After determining the entities and relationships between all entities in the target enterprise information based on the target enterprise information, the method further includes: setting weights for different entities to represent the display priority of the entities; calculating the similarity of each entity; increasing the weight of the second entity by a second value, wherein the second entity is an entity whose identification information in the corresponding language is different and whose content similarity after translation into a preset language is within a second preset similarity range.

2. The method of claim 1, wherein The acquisition of target company information includes: Obtain initial enterprise information from different information sources, wherein the initial enterprise information includes at least two types of initial information items; An initial enterprise information set is formed based on at least two of the initial information items, and the target enterprise information is determined based on the initial enterprise information set.

3. The method of claim 1, wherein After assigning weights to different entities, the method further includes: Obtain information sources for each entity; The weight of the first entity is increased by a first value. The first entity is an entity whose information source is different and whose content similarity is within a first preset similarity range.

4. The method of claim 1, wherein The step of uniformly translating all entities into the preset language, the weights corresponding to each entity, and the identification information into the node includes: storing all entities uniformly translated into the preset language, the weights corresponding to each entity, and the identification information into the graph database to obtain graph nodes; The step of forming edges from the relationships between entities includes: storing the relationships in a graph database to obtain relationship edges; The step of generating an enterprise knowledge graph based on multiple nodes and multiple edges includes: determining the enterprise knowledge graph based on the graph nodes and the relational edges.

5. The method of claim 4, wherein After determining the enterprise knowledge graph based on the graph nodes and the relation edges, the method further includes: The graph database is updated at preset time intervals; The enterprise knowledge graph is regenerated based on the updated database, corresponding to new graph nodes and new relational edges.

6. The method for generating a corporate profile as described in claim 1, characterized in that, After generating the enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph, the method further includes: Obtain the first enterprise information corresponding to the first user, wherein the first enterprise information includes at least two first information items; Calculate the first similarity between all entities and all the first information items according to the preset calculation rules; A first enterprise profile is generated based on the enterprise knowledge graph of the third entity, wherein the third entity is the entity corresponding to the first similarity with a preset similarity greater than or equal to the preset similarity.

7. The method for generating a corporate profile as described in claim 6, characterized in that, After generating the enterprise profile corresponding to the target enterprise information based on the enterprise knowledge graph, the method further includes: Obtain the priority of display permissions for each first information item in the first enterprise information; The third entity is determined based on the display permission priority and a first similarity greater than or equal to the preset similarity, and the first enterprise profile is generated based on the enterprise knowledge graph to which the third entity is located.

8. A computer device, characterized in that, The computer device includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, implements the method for generating an enterprise profile according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by one or more processors, implements the method for generating an enterprise profile as described in any one of claims 1-7.

Images