A method, apparatus, computer equipment, and storage medium for business relationship mining.

Abstract

This application discloses a method, apparatus, computer device, and storage medium for business relationship mining, belonging to the field of artificial intelligence technology. First, through intelligent analysis of business data, entities and their relationships in key business clues are accurately identified and extracted to construct an initial knowledge graph. Then, these entities and relationships are integrated into a knowledge graph of a professional domain to form a target knowledge graph. Next, association analysis technology is used to identify highly related entity groups, and the common neighbor algorithm is used to quantify the strength of these associations, constructing an association strength matrix. Finally, a weighted undirected graph is constructed based on this matrix, and community detection and clustering algorithms are integrated to perform in-depth clustering, forming closely related business clue clusters. This application also relates to the field of blockchain technology, where business data is stored on blockchain nodes. This application enhances the generalization power of business relationship mining, reduces maintenance costs, accurately captures non-keyword related clues, and comprehensively reveals business relationships.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, specifically relating to a business relationship mining method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Analyzing and mining potential relationships from massive amounts of dialogue data is crucial for businesses to revitalize existing customers and improve service quality. Improving the accuracy of relationship identification and ensuring the authenticity and effectiveness of the mined business relationships poses a significant challenge to industry products. Taking insurance lead mining in insurance sales scenarios as an example, traditional solutions typically use keyword model recognition. This involves pre-setting a keyword set and then using rule matching or AI matching models to traverse dialogue data, identifying whether keywords appear in the conversation, thereby identifying insurance leads related to those keywords. This approach has significant drawbacks: 1) The pre-set keyword set lacks generalization ability, requiring frequent modifications to the keyword table to identify more leads, resulting in high maintenance costs; 2) Traditional methods lack semantic understanding of dialogue content, failing to accurately identify intent based on context, and thus missing insurance leads unrelated to keywords. Summary of the Invention

[0003] The purpose of this application is to propose a business relationship mining method, apparatus, computer equipment, and storage medium to solve the technical problems of weak generalization, high maintenance cost, lack of semantic understanding, and easy omission of non-keyword related clues in traditional keyword model-based business relationship mining.

[0004] To address the aforementioned technical problems, this application provides a business relationship mining method, which employs the following technical solution:

[0005] A business relationship mining method, comprising:

[0006] Acquire business data, identify key business clues in the business data, and perform entity identification and relationship extraction on the key business clues to obtain the entities and entity relationships in the key business clues;

[0007] Import the entities and entity relationships in key business leads into a pre-built business domain knowledge graph to generate the target knowledge graph;

[0008] Perform association analysis on entities in the target knowledge graph to identify related entities;

[0009] The common neighbor algorithm is used to analyze the association strength of associated entities and generate an association strength matrix of associated entities;

[0010] A weighted undirected graph is constructed based on the association strength matrix. Community detection and clustering algorithms are used to perform cluster analysis on the weighted undirected graph to obtain association clue clusters. Business relationships of business data are constructed based on the association clue clusters.

[0011] Furthermore, before importing entities and entity relationships from key business leads into a pre-built business domain knowledge graph to generate the target knowledge graph, the following steps are also included:

[0012] Identify the business domain corresponding to the business data and obtain the business domain tags that match the business data;

[0013] The knowledge graph architecture matching the business domain tags is found in the graph database to obtain the business domain knowledge graph;

[0014] Before acquiring business data, identifying key business leads within the data, and performing entity identification and relationship extraction on these leads to obtain the entities and entity relationships within them, the process also includes:

[0015] Acquire historical business data from different business areas and classify the historical business data to obtain business classification data;

[0016] Entity identification and relationship extraction are performed on the business classification data to obtain the entities and entity relationships in the business classification data;

[0017] Semantic annotation is used to structure entities and entity relationships in business classification data to obtain structured entities and entity relationships.

[0018] Ontology modeling technology is used to map structured entities and entity relationships to ontology models, generating business domain knowledge graphs for different business domains;

[0019] Store business domain knowledge graphs from different business areas in a graph database, and configure corresponding business domain labels for the business domain knowledge graphs from different business areas.

[0020] Furthermore, association analysis is performed on the entities in the target knowledge graph to identify related entities, specifically including:

[0021] Identify two entities in the target knowledge graph as the target entities;

[0022] The path between target entities is traversed using a graph traversal algorithm, and the shortest path between target entities is determined.

[0023] Obtain the entity attributes and entity relationships of the target entity, and calculate the similarity between target entities based on the entity attributes and entity relationships of the target entity;

[0024] Determine whether target entities are related entities based on the shortest path between target entities and the similarity between target entities;

[0025] When the shortest path between target entities is less than a preset path length threshold and the similarity between target entities is greater than a preset similarity threshold, the target entities are determined to be related entities.

[0026] Furthermore, the common neighbor algorithm is used to analyze the association strength of associated entities, generating an association strength matrix of associated entities, specifically including:

[0027] Identify the neighboring nodes of the first entity in the target entity, and identify the neighboring nodes of the second entity, wherein the neighboring nodes include first-order neighboring nodes and second-order neighboring nodes.

[0028] Filter the first-order common neighbor nodes and second-order common neighbor nodes of the first entity and the second entity;

[0029] The entity association score is calculated based on the number of first-order and second-order common neighbor nodes, and the association strength matrix is ​​constructed based on the entity association score.

[0030] Furthermore, an entity association score is calculated based on the number of first-order and second-order common neighbor nodes, and an association strength matrix is ​​constructed based on the entity association score, specifically including:

[0031] Count the number of first-order common neighbor nodes to obtain the number of first-order nodes, and count the number of second-order common neighbor nodes to obtain the number of second-order nodes;

[0032] The first entity is relevance scored based on the number of first nodes to obtain the first entity relevance score, and the second entity is relevance scored based on the number of second nodes to obtain the second entity relevance score.

[0033] The first entity correlation score and the second entity correlation score are filled into a preset initial matrix to obtain the correlation strength matrix, wherein the initial matrix is ​​a two-dimensional matrix.

[0034] Furthermore, a weighted undirected graph is constructed based on the association strength matrix. Community detection and clustering algorithms are then used to perform clustering analysis on the weighted undirected graph to obtain association clue clusters. Based on these association clue clusters, business relationships of business data are constructed, specifically including:

[0035] Using entities as nodes and the association strength in the association strength matrix as edge weights, a weighted undirected graph is constructed, where the weighted undirected graph represents the distribution of entity structure and association strength weights;

[0036] A community detection algorithm is used to partition a weighted undirected graph into several community regions.

[0037] Clustering algorithms are used to cluster nodes in each community area to obtain clusters of related clues;

[0038] Determine the dependencies between business data entities based on the cluster of associated clues, and generate business relationships for the business data based on the dependencies.

[0039] Furthermore, the dependencies between business data entities are determined based on the clusters of related clues, and business relationships of the business data are generated based on these dependencies, specifically including:

[0040] By analyzing the node relationships of each associated clue cluster, the association relationships between the business data entities corresponding to each associated clue cluster are determined;

[0041] Calculate the similarity between business data entities based on the relationships between them.

[0042] Determine the dependencies between business data entities based on their similarity.

[0043] The business relationships of business data are determined based on the similarity and dependencies between business data entities.

[0044] To address the aforementioned technical problems, this application also provides a business relationship mining device, which employs the following technical solution:

[0045] A business relationship mining device, comprising:

[0046] The entity processing module is used to acquire business data, identify key business clues in the business data, and perform entity recognition and relationship extraction on the key business clues to obtain the entities and entity relationships in the key business clues.

[0047] The graph construction module is used to import entities and entity relationships from key business leads into a pre-built business domain knowledge graph to generate the target knowledge graph.

[0048] The entity association module is used to perform association analysis on entities in the target knowledge graph and determine associated entities.

[0049] The association analysis module is used to analyze the association strength of associated entities using the common neighbor algorithm and generate an association strength matrix of associated entities.

[0050] The relationship mining module is used to construct a weighted undirected graph based on the association strength matrix, and to perform cluster analysis on the weighted undirected graph using community detection and clustering algorithms to obtain association clue clusters. Based on the association clue clusters, business relationships of business data are constructed.

[0051] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0052] A computer device includes a memory and a processor, the memory storing computer-readable instructions, the processor executing the computer-readable instructions to implement the steps of the business relationship mining method as described in any of the preceding claims.

[0053] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0054] A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the business relationship mining method as described in any one of the preceding descriptions.

[0055] Compared with the prior art, the embodiments of this application have the following main advantages:

[0056] This application discloses a method, apparatus, computer device, and storage medium for business relationship mining, belonging to the field of artificial intelligence technology. First, by intelligently analyzing business data, entities and their relationships in key business leads are accurately identified and extracted to construct an initial knowledge graph. Then, these entities and relationships are integrated into a knowledge graph of a professional domain to form a target knowledge graph. Next, association analysis technology is used to identify highly related entity groups, and the common neighbor algorithm is used to quantify the strength of these associations, constructing an association strength matrix. Finally, a weighted undirected graph is constructed based on this matrix, and community detection and clustering algorithms are integrated to perform in-depth clustering, forming closely related business lead clusters. The solution of this application overcomes the limitations of traditional keyword models for business relationship mining. Through semantic understanding and knowledge graph construction, it enhances the generalization power of business relationship mining, reduces maintenance costs, accurately captures non-keyword related leads, comprehensively reveals business relationships, and improves decision-making accuracy. Attached Figure Description

[0057] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 An exemplary system architecture diagram is shown, in which this application can be applied;

[0059] Figure 2 A flowchart of one embodiment of the business relationship mining method according to this application is shown;

[0060] Figure 3 A schematic diagram of one embodiment of the business relationship mining apparatus according to this application is shown;

[0061] Figure 4 A schematic diagram of the structure of one embodiment of a computer device according to this application is shown. Detailed Implementation

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0063] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0064] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0065] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0066] Customers can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0067] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0068] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103. The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0069] It should be noted that the business relationship mining method provided in this application embodiment is generally executed by a server, and correspondingly, the business relationship mining device is generally set in the server.

[0070] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0071] Continue to refer to Figure 2 The diagram illustrates a flowchart of an embodiment of the business relationship mining method according to this application. Embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0072] Artificial intelligence (AI) foundational technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly include computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning. The aforementioned business relationship mining method includes the following steps:

[0073] S201, acquire business data, identify key business clues in the business data, and perform entity identification and relationship extraction on the key business clues to obtain the entities and entity relationships in the key business clues.

[0074] Specifically, the system acquires business data and, in the initial stages of business data analysis, delves into the data to accurately identify key business clues that significantly impact business decisions. First, it clarifies business objectives and potential risks; second, it uses data mining algorithms to filter high-frequency, anomalous, or trending data; finally, combining business logic and expert experience, it assesses the data's influence on decision-making, thereby accurately identifying key business clues.

[0075] Subsequently, based on these clues, entity recognition methods in Natural Language Processing (NLP), such as Named Entity Recognition (NER), are used to accurately extract the relevant business entities, such as person names, place names, and organization names. Next, relation extraction techniques are applied to parse the complex relationships between these entities, such as affiliation, transactions, and influence, thereby constructing a semantic network of entity relationships.

[0076] S202, import the entities and entity relationships in the key business leads into the pre-built business domain knowledge graph to generate the target knowledge graph.

[0077] Specifically, firstly, the entities and entity relationships extracted from key business leads need to be formatted to ensure they conform to the data pattern of the target knowledge graph. Then, using knowledge graph construction techniques, such as ontology design, data mapping, and fusion algorithms, these entities and entity relationships are seamlessly integrated into the pre-built business domain knowledge graph. This process not only requires accurate data matching and transformation but also considers the scalability and consistency maintenance of the knowledge graph, ensuring that newly added entities and relationships enrich and strengthen the existing knowledge graph structure, ultimately generating a target knowledge graph containing business-specific information.

[0078] S203, perform association analysis on entities in the target knowledge graph to identify associated entities.

[0079] Specifically, in the association analysis phase of the target knowledge graph, the knowledge graph is first traversed using graph database queries or graph algorithms (such as depth-first search, breadth-first search, etc.) to identify other entities directly or indirectly connected to a specific entity, forming entity pairs. Then, the strength and importance of these connections are evaluated by calculating metrics such as similarity, co-occurrence frequency, and path length between entities. Finally, based on preset thresholds or business rules, associated entities that meet the criteria are selected.

[0080] S204 uses the common neighbor algorithm to analyze the association strength of related entities and generates an association strength matrix of related entities.

[0081] Specifically, the common neighbor algorithm is used to conduct an in-depth analysis of the association strength between related entities. The common neighbor algorithm is a graph-based similarity measurement method that assesses the strength of the association between two entities by analyzing the number of neighbor nodes they share. In its implementation, the adjacency relationships of related entities are first extracted from the target knowledge graph, and the corresponding graph structure is constructed. Then, each pair of related entities in the graph is traversed, their number of common neighbors is calculated, and weighting factors (such as the importance of neighbor nodes) are introduced for adjustment based on actual conditions. Finally, these association strength values ​​are organized into a matrix form, namely the association strength matrix of related entities.

[0082] S205. A weighted undirected graph is constructed based on the association strength matrix. Community detection and clustering algorithms are used to perform cluster analysis on the weighted undirected graph to obtain association clue clusters. Business relationships of business data are constructed based on the association clue clusters.

[0083] Specifically, by transforming the association strength matrix into a weighted undirected graph, graph analysis techniques are used to delve deeper into the inherent structure of business data. First, the association strength matrix serves as input, with each element directly mapping to the edge weights between nodes in the graph, constructing a weighted undirected graph that intuitively reflects the tightness of relationships between entities. Then, a community detection algorithm is applied to process the weighted undirected graph, automatically dividing it into several community regions by identifying tightly connected node groups. Entities within each region exhibit high correlation, while relationships between regions are relatively sparse. Next, within each community region, a clustering algorithm further refines the node classification, forming more compact clusters of association clues. These clusters not only represent close relationships between entities but also implicitly contain specific patterns or trends in business logic. Finally, based on these clusters of association clues, business relationships within the business data are constructed. These relationships not only reveal direct connections between entities but also delve deeper into their dependencies, influences, and potential business logic chains, providing strong data support for enterprise decision-making, process optimization, and business innovation.

[0084] In the above embodiments, this application discloses a business relationship mining method, belonging to the field of artificial intelligence technology. First, through intelligent analysis of business data, entities and their relationships in key business leads are accurately identified and extracted to construct an initial knowledge graph. Then, these entities and relationships are integrated into a knowledge graph of a professional domain to form a target knowledge graph. Next, association analysis technology is used to identify highly related entity groups, and the common neighbor algorithm is used to quantify the strength of these associations, constructing an association strength matrix. Finally, a weighted undirected graph is constructed based on this matrix, and community detection and clustering algorithms are integrated to perform in-depth clustering, forming closely related business lead clusters. This application also relates to the field of blockchain technology, where business data is stored on blockchain nodes. This application enhances the generalization power of business relationship mining, reduces maintenance costs, accurately captures non-keyword related leads, and comprehensively reveals business relationships.

[0085] Furthermore, before importing entities and entity relationships from key business leads into a pre-built business domain knowledge graph to generate the target knowledge graph, the following steps are also included:

[0086] Identify the business domain corresponding to the business data and obtain the business domain tags that match the business data;

[0087] The knowledge graph architecture matching the business domain tags is found in the graph database to obtain the business domain knowledge graph;

[0088] In this embodiment, before constructing the target knowledge graph, the system identifies the business domain corresponding to the business data, obtains the business domain tags that match the business data, searches the graph database for the knowledge graph architecture that matches the business domain tags, and obtains the business domain knowledge graph.

[0089] For example, consider the business domain knowledge graphs for auto insurance and health insurance. Each business domain is assigned a unique label, such as "auto insurance" and "health insurance." The insurance company maintains a graph database containing multiple business domain knowledge graph architectures, each corresponding to one or more business domain labels. These business domain knowledge graph architectures define models of entities (such as customers, insurance products, vehicle models, etc.) and their relationships (such as purchase, claims, renewal, etc.) within each domain.

[0090] In the above embodiments, this application significantly improves the relevance and applicability of the knowledge graph by adding a business domain identification and tag matching step. By automatically identifying the domain to which the business data belongs and accurately matching the corresponding knowledge graph architecture, not only is manual intervention reduced, but the professionalism and accuracy of the knowledge graph are also ensured.

[0091] Furthermore, before acquiring business data, identifying key business leads within the business data, and performing entity identification and relationship extraction on these key business leads to obtain the entities and entity relationships within them, the process also includes:

[0092] Acquire historical business data from different business areas and classify the historical business data to obtain business classification data;

[0093] Entity identification and relationship extraction are performed on the business classification data to obtain the entities and entity relationships in the business classification data;

[0094] Semantic annotation is used to structure entities and entity relationships in business classification data to obtain structured entities and entity relationships.

[0095] Ontology modeling technology is used to map structured entities and entity relationships to ontology models, generating business domain knowledge graphs for different business domains;

[0096] Store business domain knowledge graphs from different business areas in a graph database, and configure corresponding business domain labels for the business domain knowledge graphs from different business areas.

[0097] In this embodiment, a systematic data preprocessing and knowledge graph construction process significantly improves the efficiency and accuracy of business relationship mining. First, historical business data from different business domains is extensively collected and categorized. Then, entity recognition and relationship extraction technologies are used to extract entities and entity relationships from the categorized data. Semantic annotation is then used to structure the entities and entity relationships, further enhancing the readability and understandability of the data. Based on this, ontology modeling technology is employed to map the structured entity and entity relationship data to a professional domain ontology model, generating an accurate business domain knowledge graph. Finally, these knowledge graphs are stored in a graph database and labeled with clear business domain tags for easy subsequent rapid retrieval and association analysis.

[0098] In the above embodiments, by integrating historical business data from multiple domains and constructing a refined knowledge graph system, the system's ability to understand complex business relationships is significantly improved. The application of structured processing and ontology modeling techniques ensures the accuracy and usability of the data.

[0099] Furthermore, association analysis is performed on the entities in the target knowledge graph to identify related entities, specifically including:

[0100] Identify two entities in the target knowledge graph as the target entities;

[0101] The path between target entities is traversed using a graph traversal algorithm, and the shortest path between target entities is determined.

[0102] Obtain the entity attributes and entity relationships of the target entity, and calculate the similarity between target entities based on the entity attributes and entity relationships of the target entity;

[0103] Determine whether target entities are related entities based on the shortest path between target entities and the similarity between target entities;

[0104] When the shortest path between target entities is less than a preset path length threshold and the similarity between target entities is greater than a preset similarity threshold, the target entities are determined to be related entities.

[0105] In this embodiment, the relationships between entities are effectively identified and determined through association analysis of the target knowledge graph. First, two target entities are clearly defined as the analysis objects. Then, a graph traversal algorithm is used to explore the path network between these two entities in depth. In particular, by finding the shortest path, the association judgment process in complex networks is greatly simplified, improving analysis efficiency. After obtaining the detailed attributes and relationships of the target entities, this rich information is used to calculate the similarity between entities. By incorporating the relationship features between target entities, the similarity assessment becomes more comprehensive and accurate. Finally, by comprehensively considering the two key indicators of shortest path length and similarity, and setting reasonable thresholds, this scheme can accurately determine which entities do indeed have significant associations.

[0106] When using graph traversal algorithms to explore the path network between two entities, Depth-First Search (DFS) or Breadth-First Search (BFS) are typically chosen. Taking DFS as an example, the algorithm starts from one entity and searches as deep as possible along the edges of the graph until it reaches the target entity or cannot continue, then backtracks and tries other paths. BFS, on the other hand, traverses the nodes of the graph layer by layer, first exploring nodes adjacent to the starting entity, then expanding outwards layer by layer until it finds the target entity or has traversed all reachable nodes. Both methods can effectively discover all possible paths between two entities and select the shortest one as the shortest path.

[0107] Taking customer knowledge graphs in the insurance industry as an example, suppose there are two customers, A and B, and it is necessary to assess the similarity between them to determine whether there is a potential connection or the same points of interest.

[0108] First, obtain detailed attributes of customers A and B, such as basic information like age, occupation, income level, and residential area. Next, further obtain their purchase relationships with different insurance products (such as car insurance, health insurance, and life insurance), as well as the strength (such as purchase amount, number of renewals, etc.) and type (such as individual purchase, family package, etc.) of these relationships.

[0109] Then, a cosine similarity model is used to calculate the similarity between their attributes, such as age and occupation, which can be directly quantified. For attributes that cannot be directly quantified, such as occupation type, they can be converted into one-hot encoding or word embedding representation in vector space before similarity calculation.

[0110] Furthermore, the relationships between these customers and their insurance products are weighted. For example, if both Customer A and Customer B have purchased high-coverage health insurance policies, and both are family packages, this strong and similar purchasing relationship will be given a higher weight. Conversely, if the types of insurance products they purchased are completely different, or the purchase amounts differ significantly, these relationships will be given a lower weight.

[0111] Finally, the attribute similarity and relationship feature similarity are weighted and summed to obtain the comprehensive similarity score between customer A and customer B. The higher this score, the greater the similarity between them and the greater the possibility of a potential connection.

[0112] In the above embodiments, the dual screening mechanism of shortest path filtering and similarity filtering ensures the rigor and reliability of association analysis, improves the accuracy of association analysis, and enhances the value and utility of knowledge graphs in practical business applications.

[0113] Furthermore, the common neighbor algorithm is used to analyze the association strength of associated entities, generating an association strength matrix of associated entities, specifically including:

[0114] Identify the neighboring nodes of the first entity in the target entity, and identify the neighboring nodes of the second entity, wherein the neighboring nodes include first-order neighboring nodes and second-order neighboring nodes.

[0115] Filter the first-order common neighbor nodes and second-order common neighbor nodes of the first entity and the second entity;

[0116] The entity association score is calculated based on the number of first-order and second-order common neighbor nodes, and the association strength matrix is ​​constructed based on the entity association score.

[0117] In this embodiment, a common neighbor algorithm is used to deeply analyze the association strength between related entities, providing insights into understanding and utilizing these relationships. Specifically, the direct adjacent nodes (first-order neighbors) and indirect adjacent nodes (second-order neighbors) of the target entities (i.e., the first entity and the second entity) are first identified. These neighbor nodes act as bridges for information transmission, reflecting the potential connections between entities. Subsequently, by filtering the first-order and second-order neighbor nodes shared between the two entities, i.e., common neighbors, the number of these common neighbors is an important indicator of the association strength between entities. Further, based on the number of first-order and second-order common neighbors, an entity association score is calculated. The association score comprehensively considers the closeness of direct and indirect connections, making the assessment of association strength more comprehensive and accurate. Finally, by constructing an association strength matrix, this scheme visually displays the association strength between different entity pairs.

[0118] The common neighbor algorithm is a graph analysis algorithm that measures the similarity or connection strength between two nodes by calculating the number of common neighbors between them. In social networks, this can intuitively discover mutual friends; in e-commerce, it can identify products of mutual interest. The common neighbor algorithm ignores the direction of edges, making it suitable for recommendation scenarios in e-commerce, social networking, and other fields, and helps infer the potential relationships and similarity between nodes.

[0119] In the above embodiments, the common neighbor algorithm is used to calculate the entity association degree score of related entities in order to determine the association strength matrix of related entities. This not only improves the efficiency of association analysis, but also enhances the depth and accuracy of the analysis.

[0120] Furthermore, an entity association score is calculated based on the number of first-order and second-order common neighbor nodes, and an association strength matrix is ​​constructed based on the entity association score, specifically including:

[0121] Count the number of first-order common neighbor nodes to obtain the number of first-order nodes, and count the number of second-order common neighbor nodes to obtain the number of second-order nodes;

[0122] The first entity is relevance scored based on the number of first nodes to obtain the first entity relevance score, and the second entity is relevance scored based on the number of second nodes to obtain the second entity relevance score.

[0123] The first entity correlation score and the second entity correlation score are filled into a preset initial matrix to obtain the correlation strength matrix, wherein the initial matrix is ​​a two-dimensional matrix.

[0124] In this embodiment, the association strength between entities is effectively evaluated by quantifying the number of first-order and second-order common neighbor nodes, and an intuitive association strength matrix is ​​constructed. First, by counting the number of first-order and second-order common neighbors for each of the two entities, quantitative indicators reflecting the closeness of direct and indirect connections are obtained. Then, based on this quantitative information, association scores are calculated for each of the two entities. This process not only considers the number of common neighbors but also implicitly considers the differences in the contribution of neighbors of different orders to the association strength. Finally, these two association scores are filled into a preset two-dimensional initial matrix to generate the association strength matrix. The association strength matrix is ​​a two-dimensional matrix that intuitively displays the association strength between different entity pairs. In this two-dimensional matrix, rows represent different entity pairs (i.e., target entities), and columns represent the association strength scores between the two entities, including the first entity association score and the second entity association score.

[0125] Suppose there is a customer network of an online shopping platform, where customers can connect by purchasing similar products, joining the same interest groups, or reviewing each other's products. Now, we want to analyze the strength of the association between customer A (entity 1) and customer B (entity 2).

[0126] First-order common neighbor nodes: These are customers who are directly connected to both A and B. For example, if customer C purchased the same smartwatch that both A and B have purchased, and has interacted with both A and B on the platform, then C is a first-order common neighbor. Let's assume there are 5 such first-order common neighbors.

[0127] Counting second-order common neighbors: These customers are connected to some first-order neighbor of A or B, but not directly to A or B. For example, customer D buys a book recommended by A's friend E (also a first-order neighbor of A), but D has not directly interacted with A or B. If D also has a similar relationship with some first-order neighbor of B, then D can be considered a second-order common neighbor. Let's assume the number of second-order common neighbors is 10.

[0128] Considering the different contributions to the association strength, the first entity association score and the second entity association score are calculated by assigning different weights. For example, the weight assigned to a first-order common neighbor is 1, and the weight assigned to a second-order common neighbor is 0.1. For the association score between A and B, the first entity association score is calculated as 5*1=5, and the second entity association score is calculated as 10*0.1=1.

[0129] A two-dimensional matrix is ​​pre-defined, where rows represent different entity pairs, i.e., A+B, and columns represent the first entity relevance score (i.e., 5) and the second entity relevance score (i.e., 1).

[0130] In the above embodiments, by deeply mining and analyzing the common associations between clue entities, a method for quantifying the association strength between clues is provided. This method considers not only direct connections (first-degree common neighbors) but also indirect connections (second-degree common neighbors), and quantifies this association through statistics and weighted scoring, thereby improving the accuracy of entity association analysis.

[0131] Furthermore, a weighted undirected graph is constructed based on the association strength matrix. Community detection and clustering algorithms are then used to perform clustering analysis on the weighted undirected graph to obtain association clue clusters. Based on these association clue clusters, business relationships of business data are constructed, specifically including:

[0132] Using entities as nodes and the association strength in the association strength matrix as edge weights, a weighted undirected graph is constructed, where the weighted undirected graph represents the distribution of entity structure and association strength weights;

[0133] A community detection algorithm is used to partition a weighted undirected graph into several community regions.

[0134] Clustering algorithms are used to cluster nodes in each community area to obtain clusters of related clues;

[0135] Determine the dependencies between business data entities based on the cluster of associated clues, and generate business relationships for the business data based on the dependencies.

[0136] In this embodiment, a weighted undirected graph is constructed and community detection and clustering algorithms are integrated to uncover deep relationships in business data. First, entities are used as nodes, and the strength of relationships between entities is mapped to the edge weights of the graph, visually representing the complex business structure. Then, a community detection algorithm is used to automatically divide the graph structure into multiple closely connected communities, which naturally reflect potential groups or functional modules in the data. Next, clustering is performed within each community to refine internal relationships, forming clusters of relational clues and accurately locating subtle dependencies between data. Finally, business relationships are constructed based on these clusters of clues.

[0137] A weighted undirected graph is a graph structure in which nodes represent objects or entities, edges represent connections between nodes, and these edges are undirected. At the same time, each edge is assigned a weight value, which can represent the strength of the connection between nodes, distance, cost, or any other quantifiable metric.

[0138] Community detection algorithms are algorithms that identify and divide graph data into sets of nodes (i.e., communities) with tight internal connections and sparse external connections. By analyzing the connections between nodes, they reveal the hidden community structure in the network, helping to understand the organizational patterns and functional partitions in complex networks.

[0139] Node clustering is the process of dividing nodes in a graph into different clusters (or groups) according to a certain similarity metric using a specific algorithm, thus obtaining clusters of association clues. In weighted undirected graphs, node clustering considers the connection weights between nodes, i.e., the association strength, to evaluate the similarity between nodes. Commonly used clustering algorithms such as K-means, hierarchical clustering, or density-based clustering can all be applied to node clustering. By effectively clustering nodes, nodes with similar characteristics or close connections can be grouped into one class, thus forming clusters of association clues. These clusters reflect the potential association patterns and structural features of the graph.

[0140] In the above embodiments, by combining weighted undirected graphs with community discovery and clustering algorithms, the complex and deep relationship patterns in business data are accurately revealed. This not only effectively divides data entities into closely related communities, but also further refines them into specific clusters of relationship clues, greatly improving the accuracy and efficiency of data insight and analysis.

[0141] Furthermore, the dependencies between business data entities are determined based on the clusters of related clues, and business relationships of the business data are generated based on these dependencies, specifically including:

[0142] By analyzing the node relationships of each associated clue cluster, the association relationships between the business data entities corresponding to each associated clue cluster are determined;

[0143] Calculate the similarity between business data entities based on the relationships between them.

[0144] Determine the dependencies between business data entities based on their similarity.

[0145] The business relationships of business data are determined based on the similarity and dependencies between business data entities.

[0146] This embodiment delves into the intrinsic connections within business data, systematically revealing the complex relationship network between business data entities through the construction and analysis of association clue clusters. First, it meticulously analyzes the relationships between nodes within each clue cluster, clarifying the direct connections between business entities. Then, it utilizes similarity calculations to quantitatively assess the tightness of these connections, thereby accurately identifying the dependencies between business data entities. Finally, by comprehensively considering both similarity and dependencies, a business relationship model that fully reflects business logic and operational mechanisms is constructed. This process not only enhances the depth and breadth of data insights but also provides strong data support for enterprise decision-making, process optimization, and business development.

[0147] First, similarity algorithms (such as cosine similarity) are used to calculate the similarity between entities, quantifying the degree of closeness in their attributes or behaviors. Next, dependencies are analyzed to identify which entities have direct or indirect dependencies in business logic. Then, combining similarity and dependencies, a business relationship graph is constructed, where nodes represent entities, edges represent relationships, and weights reflect the strength of similarity and dependency. Finally, based on the business relationship graph, the business logic chains and interaction patterns between entities are clarified, forming a complete description of business relationships.

[0148] In the above embodiments, by deeply mining clusters of related clues, a precise network of relationships and dependencies between business data entities is constructed. Combined with similarity calculation, not only are the intrinsic connections between entities revealed, but the dependency chains of business operations are also clarified, providing a solid foundation for building a comprehensive and detailed business relationship model and effectively improving business insight and decision-making efficiency.

[0149] In this embodiment, the business relationship mining method runs on an electronic device (e.g., Figure 1 The server shown can receive instructions or acquire data via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wideband) connections, and other currently known or future wireless connection methods.

[0150] It should be emphasized that, to further ensure the privacy and security of the aforementioned business data, the data can also be stored in a blockchain node.

[0151] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When executed, the computer-readable instructions can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0153] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0154] Further reference Figure 3 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of a business relationship mining device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0155] like Figure 3 As shown, the business relationship mining device 300 described in this embodiment includes:

[0156] The entity processing module 301 is used to acquire business data, identify key business clues in the business data, and perform entity identification and relationship extraction on the key business clues to obtain the entities and entity relationships in the key business clues.

[0157] The graph construction module 302 is used to import entities and entity relationships in key business leads into a pre-built business domain knowledge graph to generate a target knowledge graph.

[0158] The entity association module 303 is used to perform association analysis on entities in the target knowledge graph and determine the associated entities.

[0159] The association analysis module 304 is used to analyze the association strength of associated entities using the common neighbor algorithm and generate an association strength matrix of associated entities.

[0160] The relationship mining module 305 is used to construct a weighted undirected graph based on the association strength matrix, and to perform cluster analysis on the weighted undirected graph using community detection and clustering algorithms to obtain association clue clusters. Based on the association clue clusters, business relationships of business data are constructed.

[0161] Furthermore, the business relationship mining device 300 also includes:

[0162] The graph matching module is used to identify the business domain corresponding to the business data and obtain the business domain labels that match the business data; it searches the graph database for the knowledge graph architecture that matches the business domain labels to obtain the business domain knowledge graph.

[0163] Furthermore, the business relationship mining device 300 also includes:

[0164] The graph database construction module is used to acquire historical business data from different business domains, classify the historical business data to obtain business category data, perform entity recognition and relation extraction on the business category data to obtain entities and entity relations in the business category data, perform structuring processing on the entities and entity relations in the business category data through semantic annotation to obtain structured entities and entity relations, use ontology modeling technology to map the structured entities and entity relations into the ontology model to generate business domain knowledge graphs for different business domains, store the business domain knowledge graphs for different business domains in the graph database, and configure corresponding business domain labels for the business domain knowledge graphs for different business domains.

[0165] Furthermore, the entity association module 303 is specifically used for:

[0166] Two entities in the target knowledge graph are identified as target entities. A graph traversal algorithm is used to traverse the paths between the target entities and determine the shortest path between them. Entity attributes and relationships of the target entities are obtained, and the similarity between them is calculated. The shortest path and similarity between the target entities are used to determine whether they are related entities. If the shortest path between the target entities is less than a preset path length threshold and the similarity between them is greater than a preset similarity threshold, the target entities are determined to be related entities.

[0167] Furthermore, the correlation analysis module 304 is specifically used for:

[0168] Identify the neighboring nodes of the first entity and the second entity in the target entity, where the neighboring nodes include first-order neighboring nodes and second-order neighboring nodes; filter the first-order common neighboring nodes and second-order common neighboring nodes of the first and second entities; calculate the entity association score based on the number of first-order common neighboring nodes and second-order common neighboring nodes, and construct the association strength matrix based on the entity association score.

[0169] Furthermore, the correlation analysis module 304 is further used for:

[0170] The number of first-order common neighbor nodes is counted to obtain the number of first nodes, and the number of second-order common neighbor nodes is counted to obtain the number of second nodes. The first entity is scored based on the number of first nodes to obtain the first entity correlation score, and the second entity is scored based on the number of second nodes to obtain the second entity correlation score. The first entity correlation score and the second entity correlation score are filled into a preset initial matrix to obtain the correlation strength matrix, where the initial matrix is ​​a two-dimensional matrix.

[0171] Furthermore, the relationship mining module 305 is specifically used for:

[0172] Using entities as nodes and the association strength in the association strength matrix as edge weights, a weighted undirected graph is constructed, where the weighted undirected graph represents the distribution of entity structure and association strength weights;

[0173] A community detection algorithm is used to partition a weighted undirected graph into several community regions.

[0174] Clustering algorithms are used to cluster nodes in each community area to obtain clusters of related clues;

[0175] Determine the dependencies between business data entities based on the cluster of associated clues, and generate business relationships for the business data based on the dependencies.

[0176] Furthermore, the relationship mining module 305 is further used for:

[0177] By analyzing the node relationships of each associated clue cluster, the association relationships between the business data entities corresponding to each associated clue cluster are determined; based on the association relationships between the business data entities, the similarity between the business data entities is calculated; based on the similarity between the business data entities, the dependency relationships between the business data entities are determined; based on the similarity between the business data entities and the dependency relationships between the business data entities, the business relationships of the business data are determined.

[0178] In the above embodiments, this application discloses a business relationship mining device, belonging to the field of artificial intelligence technology. First, through intelligent analysis of business data, entities and their relationships in key business leads are accurately identified and extracted to construct an initial knowledge graph. Then, these entities and relationships are integrated into a knowledge graph of a professional domain to form a target knowledge graph. Next, association analysis technology is used to identify highly related entity groups, and the common neighbor algorithm is used to quantify the strength of these associations, constructing an association strength matrix. Finally, a weighted undirected graph is constructed based on this matrix, and community detection and clustering algorithms are integrated to perform in-depth clustering, forming closely related business lead clusters. This application enhances the generalization power of business relationship mining, reduces maintenance costs, accurately captures non-keyword related leads, and comprehensively reveals business relationships.

[0179] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0180] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0181] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the customer via a keyboard, mouse, remote control, touchpad, or voice control.

[0182] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for business relationship mining methods. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0183] In some embodiments, the processor 42 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute computer-readable instructions for the business relationship mining method.

[0184] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0185] In the above embodiments, this application discloses a computer device belonging to the field of artificial intelligence technology. First, through intelligent analysis of business data, entities and their relationships in key business leads are accurately identified and extracted to construct an initial knowledge graph. Then, these entities and relationships are integrated into a knowledge graph of a professional domain to form a target knowledge graph. Next, association analysis technology is used to identify highly related entity groups, and the common neighbor algorithm is used to quantify the strength of these associations, constructing an association strength matrix. Finally, a weighted undirected graph is constructed based on this matrix, and community detection and clustering algorithms are integrated to perform in-depth clustering, forming closely related business lead clusters. This application enhances the generalization power of business relationship mining, reduces maintenance costs, accurately captures non-keyword related leads, and comprehensively reveals business relationships.

[0186] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the business relationship mining method described above.

[0187] In the above embodiments, this application discloses a computer-readable storage medium belonging to the field of artificial intelligence technology. First, through intelligent analysis of business data, entities and their relationships in key business leads are accurately identified and extracted to construct an initial knowledge graph. Then, these entities and relationships are integrated into a knowledge graph of a professional domain to form a target knowledge graph. Next, association analysis technology is used to identify highly related entity groups, and the common neighbor algorithm is used to quantify the strength of these associations, constructing an association strength matrix. Finally, a weighted undirected graph is constructed based on this matrix, and community detection and clustering algorithms are integrated to perform in-depth clustering, forming closely related business lead clusters. This application enhances the generalization power of business relationship mining, reduces maintenance costs, accurately captures non-keyword related leads, and comprehensively reveals business relationships.

[0188] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0189] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0190] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A business relationship mining method, characterized in that, include: Acquire business data, identify key business clues in the business data, and perform entity recognition and relationship extraction on the key business clues to obtain the entities and entity relationships in the key business clues; Import the entities and entity relationships in the key business leads into a pre-built business domain knowledge graph to generate the target knowledge graph; Perform association analysis on the entities in the target knowledge graph to determine the associated entities; The association strength of the associated entities is analyzed using the common neighbor algorithm, and an association strength matrix of the associated entities is generated. A weighted undirected graph is constructed based on the association strength matrix. Community detection and clustering algorithms are used to perform cluster analysis on the weighted undirected graph to obtain association clue clusters. Business relationships of the business data are constructed based on the association clue clusters.

2. The business relationship mining method as described in claim 1, characterized in that, Before importing the entities and entity relationships from the key business leads into a pre-built business domain knowledge graph to generate the target knowledge graph, the process also includes: Identify the business domain corresponding to the business data and obtain the business domain tag that matches the business data; The knowledge graph for the business domain is obtained by searching the knowledge graph architecture that matches the business domain tags in the graph database. Before acquiring business data, identifying key business clues within the business data, and performing entity identification and relationship extraction on the key business clues to obtain the entities and entity relationships within the key business clues, the process further includes: Acquire historical business data from different business areas, and classify the historical business data to obtain business classification data; Entity identification and relationship extraction are performed on the business classification data to obtain the entities and entity relationships in the business classification data; The entities and entity relationships in the business classification data are structured by semantic annotation to obtain structured entities and entity relationships. The structured entities and entity relationships are mapped to the ontology model using ontology modeling technology to generate business domain knowledge graphs for different business domains; The business domain knowledge graphs of the different business domains are stored in the graph database, and corresponding business domain labels are configured for the business domain knowledge graphs of the different business domains.

3. The business relationship mining method as described in claim 1, characterized in that, Perform association analysis on entities in the target knowledge graph to determine associated entities, specifically including: Two entities in the target knowledge graph are identified as target entities; The path between the target entities is traversed using a graph traversal algorithm, and the shortest path between the target entities is determined. Obtain the entity attributes and entity relationships of the target entity, and calculate the similarity between the target entities based on the entity attributes and entity relationships of the target entity; The determination of whether a target entity is an associated entity is based on the shortest path between the target entities and the similarity between the target entities; When the shortest path between the target entities is less than a preset path length threshold and the similarity between the target entities is greater than a preset similarity threshold, the target entities are determined to be associated entities.

4. The business relationship mining method as described in claim 3, characterized in that, The common neighbor algorithm is used to analyze the association strength of the associated entities, generating an association strength matrix for the associated entities, specifically including: Identify the neighboring nodes of a first entity in the target entity, and identify the neighboring nodes of a second entity, wherein the neighboring nodes include first-order neighboring nodes and second-order neighboring nodes; Filter the first-order common neighbor nodes and second-order common neighbor nodes of the first entity and the second entity; The entity association score is calculated based on the number of first-order common neighbor nodes and the number of second-order common neighbor nodes, and the association strength matrix is ​​constructed based on the entity association score.

5. The business relationship mining method as described in claim 4, characterized in that, Entity association score is calculated based on the number of first-order and second-order common neighbor nodes. The association strength matrix is ​​then constructed based on the entity association score, specifically including: The number of first-order common neighbor nodes is counted to obtain the number of first nodes, and the number of second-order common neighbor nodes is counted to obtain the number of second nodes; A first entity relevance score is obtained by scoring the first entity's relevance based on the first number of nodes, and a second entity relevance score is obtained by scoring the second entity's relevance based on the second number of nodes. The first entity correlation score and the second entity correlation score are filled into a preset initial matrix to obtain the correlation strength matrix, wherein the initial matrix is ​​a two-dimensional matrix.

6. The business relationship mining method as described in claim 1, characterized in that, A weighted undirected graph is constructed based on the association strength matrix. Community detection and clustering algorithms are used to perform cluster analysis on the weighted undirected graph to obtain association clue clusters. Based on these association clue clusters, business relationships of the business data are constructed, specifically including: Using the entities as nodes and the association strengths in the association strength matrix as edge weights, a weighted undirected graph is constructed, wherein the weighted undirected graph represents the distribution of entity structure and association strength weights; A community detection algorithm is used to divide the weighted undirected graph into regions to form several community regions on the weighted undirected graph; In each of the community areas, the clustering algorithm is used to cluster nodes to obtain the cluster of related clues; The dependencies between business data entities are determined based on the associated clue clusters, and the business relationships of the business data are generated based on the dependencies.

7. The business relationship mining method as described in claim 6, characterized in that, The step of determining the dependencies between business data entities based on the associated clue clusters, and generating business relationships for the business data based on the dependencies, specifically includes: By analyzing the node relationships of each of the associated clue clusters, the association relationships between the business data entities corresponding to each associated clue cluster are determined; Based on the relationships between the business data entities, the similarity between the business data entities is calculated; The dependencies between the business data entities are determined based on the similarity between them. The business relationships of the business data are determined based on the similarity between the business data entities and the dependencies between the business data entities.

8. A business relationship mining device, characterized in that, include: The entity processing module is used to acquire business data, identify key business clues in the business data, and perform entity recognition and relationship extraction on the key business clues to obtain the entities and entity relationships in the key business clues. The graph construction module is used to import the entities and entity relationships in the key business clues into a pre-built business domain knowledge graph to generate the target knowledge graph. The entity association module is used to perform association analysis on entities in the target knowledge graph and determine associated entities; The association analysis module is used to analyze the association strength of the associated entities using the common neighbor algorithm and generate the association strength matrix of the associated entities. The relationship mining module is used to construct a weighted undirected graph based on the association strength matrix, perform cluster analysis on the weighted undirected graph using community detection and clustering algorithms to obtain association clue clusters, and construct the business relationships of the business data based on the association clue clusters.

9. A computer device, characterized in that, The method includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the business relationship mining method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the business relationship mining method as described in any one of claims 1 to 7.

Images