Data analysis method and device based on knowledge graph, equipment, medium and product

Abstract

The invention provides a data analysis method and device based on a knowledge graph, equipment, a medium and a product, and relates to the field of financial science and technology and the field of artificial intelligence. The method comprises the following steps: constructing a corresponding knowledge graph through multi-source data of a plurality of objects on a supply chain, and determining entity tags of a plurality of entity points in the knowledge graph and relationship information between two entity points with an edge relationship; determining an object portrait of each object based on the entity label and the relationship information; then, based on the object portraits of the multiple objects, comprehensively evaluating the objects to obtain a value score corresponding to each object; according to the method, a knowledge graph is constructed, and multi-dimensional and dynamic object portraits can be determined for different types of objects on a supply chain based on labels and relationships in the knowledge graph; meanwhile, based on the object portraits, cognition concrete and tagging of multiple objects on the supply chain are achieved, and quantification and automation of decision making are achieved through value scoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of financial technology and the field of artificial intelligence, in particular to a data analysis method and device based on a knowledge graph, equipment, medium and product. BACKGROUND

[0002] In the field of financial technology, the banking industry increasingly values the sustainability marketing of high-quality core customers and the linkage marketing of upstream and downstream enterprises associated with core customers. Currently, bank marketing personnel mainly rely on the acquired target object list and other means to carry out marketing activities, resulting in low input-output ratio and poor marketing efficiency.

[0003] Before carrying out marketing activities, marketing personnel need to analyze objects in order to carry out personalized marketing. The existing object analysis method mainly relies on the enterprise's basic transaction data, such as order amount, transaction frequency and other structured data. Although the above data can reflect the transaction behavior characteristics of the object to some extent, it is difficult to build a comprehensive and three-dimensional object portrait, and there is a lack of effective evaluation of non-structured factors such as the market influence, industry status and strategic cooperation potential of the object, so as to realize the precise marketing of the object.

[0004] Therefore, how to accurately analyze object data to realize personalized marketing is a problem to be solved at present. SUMMARY

[0005] The present application provides a data analysis method and device based on a knowledge graph, equipment, medium and product, to realize the objectification and labeling of the cognition of multiple objects on a supply chain, so as to realize the quantization and automation of decision-making.

[0006] In a first aspect, the present application provides a data analysis method based on a knowledge graph, which comprises:

[0007] Obtaining multi-source data corresponding to a supply chain, the multi-source data being used to indicate object data of multiple objects on the supply chain;

[0008] Based on the multiple object data, constructing a knowledge graph corresponding to the supply chain, and determining entity labels of multiple entity points in the knowledge graph and relationship information between two entity points with existing edge relationships;

[0009] Based on the entity labels and relationship information, determining an object portrait of each object;

[0010] For any one of the multiple objects, based on the object portrait of the object, comprehensively evaluating the object to obtain an object feature of the object, the object feature being used to indicate a value score of the object.

[0011] In a possible implementation, the constructing the knowledge graph corresponding to the supply chain based on the plurality of object data comprises:

[0012] taking the plurality of objects as entity points of the knowledge graph, and determining a supply relationship between each object and other data based on the plurality of object data;

[0013] taking the supply relationship as an edge between two adjacent entity points to obtain the knowledge graph corresponding to the supply chain.

[0014] In a possible implementation, the object data comprises: a corresponding object type, transaction data, and supply data, and the determining of the entity label of each entity point in the knowledge graph and the relationship information between two entity points having an edge relationship comprises:

[0015] for any first entity point in the plurality of entity points, determining an entity label of the first entity point based on the object type, the transaction data, and the supply data corresponding to the first entity point;

[0016] determining a second entity point having an edge relationship with the first entity point from the knowledge graph, and determining target transaction data and target supply data corresponding to the second entity point from the transaction data and the supply data of the first entity point;

[0017] determining relationship information between the first entity point and the second entity point based on the target transaction data and the target supply data, the relationship information comprising any one of: a business relationship closeness, a business relationship change trend, and a corresponding relationship type.

[0018] In a possible implementation, the object data further comprises: object basic data, and the determining of the object portrait of each object based on the entity label and the relationship information comprises:

[0019] for any object in the plurality of objects, determining transaction features, preference features, and credit features of the object based on the transaction data of the object;

[0020] determining basic features and business features of the object based on the object basic data and the object type of the object;

[0021] determining the object portrait of the object based on the basic features, the business features, the transaction features, the preference features, and the credit features.

[0022] In a possible implementation, the comprehensive evaluation of the object based on the object portrait of the object to obtain object features of the object comprises:

[0023] According to a plurality of portrait features, determine an evaluation value corresponding to at least one evaluation index;

[0024] Based on the corresponding relationship between the plurality of portrait features and at least one of the evaluation indexes, determine the evaluation weight of each evaluation index;

[0025] Based on at least one evaluation value and the evaluation weight of each evaluation index, determine the object feature of the object.

[0026] In a possible implementation, the method further includes:

[0027] Determine at least one target object that meets a preset condition from a plurality of objects, wherein the preset condition includes at least one of the following: a value score greater than a preset score, the top N with the highest value score, and the top M with the highest value score within the same object type, wherein N and M are positive integers greater than 0;

[0028] Display the object data and the object feature of at least one of the target objects through a display interface.

[0029] In a second aspect, the present application provides a data analysis device based on a knowledge graph, which comprises:

[0030] An acquisition module is configured to acquire multi-source data corresponding to a supply chain, wherein the multi-source data is used to indicate object data of a plurality of objects on the supply chain;

[0031] A processing module is configured to construct a knowledge graph corresponding to the supply chain based on a plurality of object data, and determine entity labels of a plurality of entity points in the knowledge graph and relationship information between two entity points with an existing edge relationship; and determine an object portrait of each object based on the entity labels and the relationship information.

[0032] The processing module is further configured to, for any one of the plurality of objects, perform comprehensive evaluation on the object based on the object portrait of the object to obtain an object feature of the object, wherein the object feature is used to indicate a value score of the object.

[0033] In a possible implementation, the processing module is configured to take the plurality of objects as entity points of the knowledge graph, and determine a supply relationship between each object and other data based on a plurality of object data; and take the supply relationship as an edge between two adjacent entity points to obtain the knowledge graph corresponding to the supply chain.

[0034] In one possible implementation, the object data includes: corresponding object type, transaction data, and supply data. The processing module is configured to, for any one of multiple entity points, determine the entity label of the first entity point based on the object type, transaction data, and supply data corresponding to the first entity point; and determine a second entity point with an edge relationship to the first entity point from the knowledge graph, and determine the target transaction data and target supply data corresponding to the second entity point from the transaction data and supply data of the first entity point.

[0035] The processing module is further configured to determine the relationship information between the first entity point and the second entity point based on the target transaction data and the target supply data. The relationship information includes any one of the following: the degree of closeness of the business relationship, the trend of business relationship changes, and the corresponding relationship type.

[0036] In one possible implementation, the object data further includes: object basic data. The processing module is configured to, for any one of multiple objects, determine the transaction characteristics, preference characteristics, and credit characteristics of the object based on the object's transaction data; determine the basic characteristics and business characteristics of the object based on the object's object basic data and object type; and determine the object profile of the object based on the basic characteristics, business characteristics, transaction characteristics, preference characteristics, and credit characteristics.

[0037] In one possible implementation, the processing module is configured to determine an evaluation value corresponding to at least one evaluation indicator based on multiple profile features; determine the evaluation weight of each evaluation indicator based on the correspondence between the multiple profile features and at least one evaluation indicator; and determine the object features of the object based on at least one evaluation value and the evaluation weight of each evaluation indicator.

[0038] In one possible implementation, the device further includes: a display module;

[0039] The processing module is further configured to determine at least one target object from multiple objects that meets preset conditions, wherein the preset conditions include at least one of the following: value score greater than preset score, the top N with the highest value score, and the top M with the highest value score within the same object type, wherein N and M are both positive integers greater than 0.

[0040] The display module is used to display the object data and object features of at least one of the target objects through a display interface.

[0041] Thirdly, embodiments of this application provide a knowledge graph-based data analysis device, including: a processor, and a memory communicatively connected to the processor;

[0042] The memory stores computer-executed instructions;

[0043] The processor executes computer execution instructions stored in the memory to implement the first aspect and / or various possible implementations of the first aspect.

[0044] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0045] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0046] The knowledge graph-based data analysis method, apparatus, equipment, medium, and product provided in this application construct a corresponding knowledge graph from multi-source data of multiple objects in the supply chain, and determine the entity labels of multiple entity points within the knowledge graph and the relationship information between two entity points with edge relationships. Based on the entity labels and relationship information, an object profile is determined for each object. Then, based on the object profiles of multiple objects, the objects are comprehensively evaluated to obtain a value score corresponding to each object. This method, by constructing a knowledge graph and based on the labels and relationships in the knowledge graph, can determine multi-dimensional and dynamic object profiles for different types of objects in the supply chain. At the same time, based on the object profiles, the cognitive visualization and labeling of multiple objects in the supply chain are realized, and the decision-making is quantified and automated through value scoring. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0048] Figure 1 A flowchart illustrating a knowledge graph-based data analysis and determination method provided in this application embodiment. Figure 1 ;

[0049] Figure 2 A flowchart illustrating a knowledge graph-based data analysis and determination method provided in this application embodiment. Figure 2 ;

[0050] Figure 3 A flowchart illustrating a knowledge graph-based data analysis and determination method provided in this application embodiment. Figure 3 ;

[0051] Figure 4 A schematic diagram of the structure of a knowledge graph-based data analysis and determination device provided in this application embodiment;

[0052] Figure 5 This is a schematic diagram of the structure of a knowledge graph-based data analysis and determination device provided in an embodiment of this application.

[0053] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0054] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0055] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize or refuse.

[0056] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0057] It should be noted that the knowledge graph-based data analysis methods, devices, equipment, media, and products provided in this application can be used in the fields of fintech and artificial intelligence, as well as in any other field. The application fields of the knowledge graph-based data analysis methods, devices, equipment, media, and products in this application are not limited.

[0058] In today's highly competitive business environment, the banking industry is increasingly emphasizing continuous marketing to high-quality core clients and collaborative marketing with upstream and downstream enterprises closely related to these clients. However, currently, bank marketing personnel primarily rely on target client lists obtained through various channels, key personnel recommendations, or cold calling to conduct marketing activities. These methods suffer from low return on investment and poor marketing efficiency. Specifically, the existing marketing model has the following problems: 1. The obtained client lists typically include a large number of core enterprise suppliers, but this information is often incomplete and superficially analyzed, making it difficult to accurately and deeply assess client value; 2. Existing assessment methods struggle to effectively obtain and analyze payment and settlement information from multiple levels of suppliers in the enterprise's supply chain, resulting in the inability to systematically generate target client lists and making it difficult to accurately target specific customer groups.

[0059] Existing customer analysis methods primarily rely on basic transaction data from enterprises, such as structured data like order amounts and transaction frequencies. While this data can reflect customer transaction behavior characteristics to some extent, it is difficult to construct a comprehensive and multi-dimensional customer profile, and it lacks effective assessment of key unstructured factors such as a customer's market influence, industry position, and strategic cooperation potential.

[0060] Furthermore, with the globalization and increasing complexity of supply chain structures, the amount of interactive data between enterprises and customers is growing explosively, including multi-source heterogeneous data such as payment records, invoice information, and business relationship networks. How to efficiently and accurately extract information with business insights from this massive amount of data has become a major technical challenge for banks in determining customer value.

[0061] To address the aforementioned issues, this application provides a knowledge graph-based data analysis method. This method constructs a corresponding knowledge graph using multi-source data from multiple objects in the supply chain, and determines the entity labels of multiple entity points within the knowledge graph, as well as the relationship information between two entity points with edge relationships. Based on the entity labels and relationship information, an object profile is determined for each object. Then, based on the object profiles of multiple objects, a comprehensive evaluation is performed on the objects to obtain a value score for each object. By constructing a knowledge graph, this method can determine multi-dimensional and dynamic object profiles for different types of objects in the supply chain based on the labels and relationships within the knowledge graph. Simultaneously, based on the object profiles, it realizes the visualization and labeling of cognition of multiple objects in the supply chain, and achieves the quantification and automation of decision-making through value scoring.

[0062] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0063] Figure 1 A flowchart illustrating a knowledge graph-based data analysis method provided in this application embodiment. Figure 1 .like Figure 1 As shown in the embodiments of this application, the knowledge graph-based data analysis method includes:

[0064] S101. Obtain multi-source data corresponding to the supply chain. Multi-source data is used to indicate object data of multiple objects in the supply chain.

[0065] The supply chain can be, for example, a banking supply chain in a fintech scenario, or any other supply chain. Objects can include, for example, physical entities such as customers, suppliers, and financial products within the supply chain.

[0066] Multi-source data can include both structured and unstructured data, such as internal transaction data, external market data, social media data, corporate announcements, and industry reports corresponding to multiple objects. This application does not impose any limitations on this.

[0067] In this embodiment, when acquiring multi-source data, it can be obtained from the database and / or business system corresponding to each object, or it can be crawled from the network, or it can be imported by analysts.

[0068] Understandably, after obtaining multi-source data, preprocessing and preliminary cleaning of the multi-source data can be performed.

[0069] For example, standardizing multi-source data can convert data in different formats into a unified format. Another example is de-identifying sensitive data from multi-source data to ensure the security of personal privacy information and / or sensitive corporate fields within the data.

[0070] S102. Based on multiple object data, construct a knowledge graph corresponding to the supply chain, and determine the entity labels of multiple entity points in the knowledge graph and the relationship information between two entity points with edge relationships.

[0071] Knowledge graphs are a technique for modeling and representing knowledge using graph structures. They typically consist of "nodes" and "edges." In this step, the knowledge graph can be used to characterize the relationships between multiple objects within the supply chain.

[0072] Entity tags can be used to indicate the type of object corresponding to an entity point. Examples include: individual customer type, enterprise customer type, and partner type.

[0073] Multiple entity points can be identified from multiple object data sets. For example, if the transacting parties are identified as object A and object B from certain transaction data, then object A and object B can be taken as the corresponding entity points.

[0074] Relationship information may include, for example, the closeness of the business relationship between the objects corresponding to the two entity points, the trend of changes in the business relationship, and / or the corresponding relationship type.

[0075] The closeness of business relationships can indicate, for example, the strength, depth, and dependency of business interactions between two objects. This can be determined based on the object data corresponding to the two entity points.

[0076] For example, transaction data can typically reflect the transaction size, frequency, and duration of cooperation between the two parties. Based on this information, the closeness of the business relationship between the two parties can be determined.

[0077] Trends in business relationships can, for example, indicate the direction and rate at which the "closeness of business relationships" changes over time. This can be determined, for example, based on the closeness of the business relationship between two entity points.

[0078] For example, by comparing the closeness of business relationships at different times, one can determine how that "closeness of business relationship" changes. These changes could include, for example, an upward trend, a downward trend, or a stable trend.

[0079] Relationship types can indicate the relationship between two entities when they conduct a transaction. Examples include supply relationships, partnerships, and attribution relationships. For instance, if object A is a regular supplier of object B, then the relationship type between object A and object B is a supply relationship; similarly, if object C and object D are strategic partners, then the relationship type between object C and object D is a partnership.

[0080] In one possible implementation, the specific process of constructing a knowledge graph may include, for example:

[0081] Multiple objects are used as entity points in the knowledge graph, and the supply relationship between each object and other data is determined based on the data of multiple objects. Then, the supply relationship is used as the edge between two adjacent entity points to obtain the knowledge graph corresponding to the supply chain.

[0082] S103. Based on entity tags and relationship information, determine the object profile for each object.

[0083] Among them, the multi-dimensional profile features corresponding to the object can be determined based on entity tags and relationship information, and then the corresponding object profile can be constructed based on the multi-dimensional profile features.

[0084] Multidimensional profile features may include, for example, the object's basic characteristics, business characteristics, credit status, preferences and needs, and settlement characteristics.

[0085] This step can integrate multi-dimensional feature data, making the identified object profile more comprehensive, three-dimensional and accurate.

[0086] S104. For any one of the multiple objects, perform a comprehensive evaluation based on the object's object profile to obtain the object's object characteristics.

[0087] Among these features, object characteristics can indicate the object's value rating, for example.

[0088] In one possible implementation, the comprehensive evaluation process includes, for example:

[0089] Based on multiple profile features corresponding to the object profile, determine the evaluation value corresponding to at least one evaluation indicator; based on the correspondence between multiple profile features and at least one evaluation indicator, determine the evaluation weight of each evaluation indicator; then, based on at least one evaluation value and the evaluation weight of each evaluation indicator, determine the object features of the object.

[0090] Profile features may include, for example, basic features, business features, transaction features, preference features, credit features, settlement features, and operational features.

[0091] Evaluation indicators may include, for example, value contribution indicators, cooperation potential indicators, and credit risk indicators.

[0092] Value contribution indicators can indicate the value contribution of an entity; cooperation potential indicators can be determined based on market expansion capabilities and innovation capabilities; credit risk indicators can be determined through the entity's credit rating, debt repayment ability, and operational capabilities.

[0093] In this step, the correlation between multiple profile features and at least one evaluation indicator can be determined first. For example, it can be determined that the value contribution indicator may be correlated with transaction features, and the credit risk indicator may be correlated with credit features and settlement features, etc.

[0094] After obtaining the correlation, the evaluation values ​​of the evaluation indicators with correlation are determined based on the profile features.

[0095] Furthermore, the evaluation weight of each evaluation indicator can be determined based on this relationship.

[0096] For example, if there are three features related to the value contribution indicator, and all three features are relatively important, then the indicator weight of the value contribution indicator can be increased. Alternatively, the analytic hierarchy process (AHP) can be used to determine the indicator weights. This application does not impose any restrictions on this.

[0097] When determining object characteristics, for example, the object characteristics can be obtained by weighted summation of at least one evaluation value and the evaluation weight of each evaluation indicator.

[0098] In one possible implementation, after obtaining the object characteristics of multiple objects, these object characteristics can be displayed, as follows:

[0099] Identify at least one target object from multiple objects that meets preset conditions, and display the object data and object characteristics of at least one target object through a display interface.

[0100] The preset conditions include at least one of the following: the value score is greater than the preset score, the top N with the highest value scores, and the top M with the highest value scores within the same object type, where N and M are both positive integers greater than 0.

[0101] This step can display objects with high value scores to uncover high-value objects.

[0102] The knowledge graph-based data analysis method provided in this application acquires multi-source data from the supply chain and constructs a knowledge graph, transforming the originally scattered and heterogeneous data into a semantically related network structure. This solves the problem of data silos in the supply chain. Furthermore, by constructing object profiles based on entity tags of entity points and edge relationship information between entities in the knowledge graph, it overcomes the one-sidedness caused by relying on single, static data in traditional methods. This makes the object profiles more accurate, comprehensive, and three-dimensional, truly reflecting the role, attributes, and correlation strength of objects in the supply chain network. Moreover, comprehensive evaluation based on object profiles can more accurately extract feature indicators reflecting the stability, reliability, importance, or risk level of objects, thereby achieving intelligent identification of key core enterprises, potential weak links, or high-risk entities in the supply chain. This provides data-driven decision support for supply chain risk management, supplier selection, and optimization, greatly improving the predictability and proactivity of supply chain management.

[0103] Figure 2 A flowchart illustrating a knowledge graph-based data analysis method provided in this application embodiment. Figure 1 The object data in this embodiment may include, for example, the corresponding object type, transaction data, and supply data. The execution object of this application may, for example, be any one of multiple entity points in a knowledge graph. This embodiment of the application is... Figure 2Based on the embodiments, this paper explains a possible implementation method for determining the entity labels of multiple entity points within a knowledge graph and the relationship information between two entity points with edge relationships. For example... Figure 3 As shown in the embodiments of this application, the knowledge graph-based data analysis method includes:

[0104] S201. Determine the entity label of the first entity point based on the object type, transaction data, and supply data corresponding to the first entity point.

[0105] The object types can include, for example, supplier types, manufacturer types, individual customer types, enterprise customer types, and partner types.

[0106] Entity tags can be categorized by the type of an object, or they can reflect the importance of that entity within the entire supply chain. Examples of entity tags include general supplier, key partner, high-value producer, and strategic supplier.

[0107] This step determines the entity label of an entity point based on multi-dimensional object data, thereby making the entity label more accurate.

[0108] S202. Determine the second entity point from the knowledge graph that has an edge relationship with the first entity point.

[0109] S203. Determine the target transaction data and target supply data corresponding to the second entity point from the transaction data and supply data of the first entity point.

[0110] After obtaining the second entity point, target transaction data and target supply data that have a transaction relationship or supply relationship with the second entity point can be determined from the transaction data and supply data of the first entity point.

[0111] S204. Based on the target transaction data and the target supply data, determine the relationship information between the first entity point and the second entity point.

[0112] The relationship information may include, for example, the closeness of the business relationship between the objects corresponding to the two entity points, the trend of changes in the business relationship, and / or the corresponding relationship type.

[0113] The knowledge graph-based data analysis method provided in this application determines entity labels for entity points through multi-dimensional data, thereby making the determined entity labels more accurate. Simultaneously, by identifying a second entity point with an edge relationship to the first entity point, and then determining the target transaction data and target supply data corresponding to the second entity point from the object data of the first entity point, the relationship information between the two entity points is determined based on the target transaction data and target supply data. This achieves in-depth quantification and dynamic updating of entity relationships in the supply chain knowledge graph, overcoming the shortcomings of traditional graph relationship information being coarse, static, and subjective.

[0114] Figure 3 A flowchart illustrating a knowledge graph-based data analysis method provided in this application embodiment. Figure 2 The object data in this embodiment may further include, for example, object base data. The execution object of this application may be, for example, any one of multiple objects in the supply chain. This embodiment of the application is... Figure 3 Based on the embodiments, this paper explains a possible implementation method for determining the object profile of each object based on entity tags and relationship information. For example... Figure 4 As shown in the embodiments of this application, the knowledge graph-based data analysis method includes:

[0115] S301. Based on the object's transaction data, determine the object's transaction characteristics, preference characteristics, and credit characteristics.

[0116] Among them, transaction characteristics can indicate the scale and stability of the business dealings of the object; preference characteristics can be, for example, characteristics that indicate the behavioral habits and intrinsic needs of the object; credit characteristics can be, for example, characteristics that assess the object's willingness and ability to perform its obligations, which are the core of risk management.

[0117] In this step, data analysis and aggregation calculations can be performed on the transaction data to obtain the aforementioned transaction characteristics, preference characteristics, and credit characteristics.

[0118] S302. Based on the object's basic data and object type, determine the object's basic characteristics and business characteristics.

[0119] Among them, basic characteristics may include basic information such as the object's identity information; business characteristics may include the object's role and importance in the supply chain, such as indicating the industry, business scale, market share, corporate qualifications, and corresponding supplier level.

[0120] S303. Based on basic features, business features, transaction features, preference features, and credit features, determine the object profile of the object.

[0121] The knowledge graph-based data analysis method provided in this application determines the transaction characteristics, preference characteristics, and credit characteristics of an object based on its transaction data. It then determines the object's basic characteristics and business characteristics based on the object's basic data and object type. Finally, based on these basic characteristics, business characteristics, transaction characteristics, preference characteristics, and credit characteristics, it determines the object's profile. This method, by integrating multi-dimensional feature data, makes the determined object profile more comprehensive, three-dimensional, and accurate.

[0122] Figure 4 This is a schematic diagram of the structure of a knowledge graph-based data analysis device provided in an embodiment of this application. Figure 5 As shown, the knowledge graph-based data analysis device 400 provided in this application embodiment includes:

[0123] The acquisition module 401 is used to acquire multi-source data corresponding to the supply chain. The multi-source data is used to indicate object data of multiple objects in the supply chain.

[0124] The processing module 402 is used to construct a knowledge graph corresponding to the supply chain based on multiple object data, and determine the entity labels of multiple entity points in the knowledge graph and the relationship information between two entity points with edge relationships; and determine the object profile of each object based on the entity labels and relationship information.

[0125] The processing module 402 is also used to perform a comprehensive evaluation of any one of the multiple objects based on the object profile of the object, and obtain the object characteristics of the object, which are used to indicate the value score of the object.

[0126] In one possible implementation, the processing module 402 is used to treat multiple objects as entity points of a knowledge graph, and based on the multiple object data, determine the supply relationship between each object and other data; and treat the supply relationship as an edge between two adjacent entity points to obtain the knowledge graph corresponding to the supply chain.

[0127] In one possible implementation, the object data includes: corresponding object type, transaction data, and supply data. The processing module 402 is used to determine the entity label of any first entity point among multiple entity points based on the object type, transaction data, and supply data corresponding to the first entity point; and to determine a second entity point with an edge relationship with the first entity point from the knowledge graph, and to determine the target transaction data and target supply data corresponding to the second entity point from the transaction data and supply data of the first entity point.

[0128] The processing module 402 is also used to determine the relationship information between the first entity point and the second entity point based on the target transaction data and the target supply data. The relationship information includes any one of the following: the degree of closeness of the business relationship, the trend of business relationship changes, and the corresponding relationship type.

[0129] In one possible implementation, the object data further includes: object basic data, and processing module 402, which is used to determine the transaction characteristics, preference characteristics, and credit characteristics of any one of the multiple objects based on the object's transaction data; determine the basic characteristics and business characteristics of the object based on the object's object basic data and object type; and determine the object profile of the object based on the basic characteristics, business characteristics, transaction characteristics, preference characteristics, and credit characteristics.

[0130] In one possible implementation, the processing module 402 is configured to determine the evaluation value corresponding to at least one evaluation indicator based on multiple profile features; determine the evaluation weight of each evaluation indicator based on the correspondence between the multiple profile features and at least one evaluation indicator; and determine the object features of the object based on at least one evaluation value and the evaluation weight of each evaluation indicator.

[0131] In one possible implementation, the device further includes: a display module 403;

[0132] Processing module 402 is further configured to determine at least one target object from multiple objects that meets preset conditions, wherein the preset conditions include at least one of the following: value score greater than preset score, the top N with the highest value score, and the top M with the highest value score within the same object type, where N and M are both positive integers greater than 0.

[0133] Display module 403 is used to display and process the object data and object characteristics of at least one target object through a display interface.

[0134] The knowledge graph-based data analysis device provided in this embodiment can execute the methods provided in the above-described method embodiments. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0135] Figure 5 This is a schematic diagram of the structure of a knowledge graph-based data analysis device provided in an embodiment of this application. ​ As shown, the knowledge graph-based data analysis device 500 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 500 also includes a communication interface 503. The processor 501, memory 502, and communication interface 503 are connected via a bus 504.

[0136] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0137] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0138] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0139] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0140] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0141] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0142] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0143] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0144] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0145] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0146] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0148] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0149] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0150] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0151] It should be further noted that although the steps in the flowchart are shown sequentially according to 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 flowchart 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. The execution order of these sub-steps or stages 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.

[0152] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0153] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0154] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0155] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0156] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0157] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0158] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A data analysis method based on knowledge graphs, characterized in that, The method includes: Acquire multi-source data corresponding to the supply chain, wherein the multi-source data is used to indicate object data of multiple objects in the supply chain; Based on multiple object data, a knowledge graph corresponding to the supply chain is constructed, and the entity labels of multiple entity points in the knowledge graph and the relationship information between two entity points with edge relationships are determined. Based on the entity tags and relationship information, an object profile for each object is determined; For any one of multiple objects, based on the object profile of the object, a comprehensive evaluation is performed on the object to obtain the object characteristics, which are used to indicate the value score of the object.

2. The method according to claim 1, characterized in that, The construction of the knowledge graph corresponding to the supply chain based on multiple object data includes: Multiple objects are used as entity points in the knowledge graph, and based on the data of multiple objects, the supply relationship between each object and other data is determined; The supply relationship is used as an edge between two adjacent entity points to obtain the knowledge graph corresponding to the supply chain.

3. The method according to claim 2, characterized in that, The object data includes: corresponding object types, transaction data, and supply data. Determining the entity labels of multiple entity points within the knowledge graph and the relationship information between two entity points with edge relationships includes: For any first entity point among multiple entity points, determine the entity label of the first entity point based on the object type, transaction data, and supply data corresponding to the first entity point; From the knowledge graph, determine a second entity that has an edge relationship with the first entity; from the transaction data and supply data of the first entity, determine the target transaction data and target supply data corresponding to the second entity. Based on the target transaction data and the target supply data, the relationship information between the first entity point and the second entity point is determined. The relationship information includes any one of the following: the degree of closeness of the business relationship, the trend of changes in the business relationship, and the corresponding relationship type.

4. The method according to claim 3, characterized in that, The object data also includes: basic object data, and the process of determining the object profile for each object based on the entity tags and relationship information includes: For any one of a plurality of objects, based on the object's transaction data, determine the object's transaction characteristics, preference characteristics, and credit characteristics; Based on the object's basic data and object type, determine the object's basic characteristics and business characteristics; Based on the aforementioned basic features, business features, transaction features, preference features, and credit features, an object profile is determined for the object.

5. The method according to claim 1, characterized in that, The object profile based on the object is used to comprehensively evaluate the object and obtain the object characteristics of the object, including: Based on multiple profile features, determine the evaluation value corresponding to at least one evaluation indicator; Based on the correspondence between multiple profile features and at least one of the evaluation indicators, the evaluation weight of each evaluation indicator is determined. The object characteristics of the object are determined based on at least one evaluation value and the evaluation weight of each evaluation indicator.

6. The method according to claim 1, characterized in that, The method further includes: Determine at least one target object from a plurality of objects that meets preset conditions, wherein the preset conditions include at least one of the following: value score greater than preset score, the top N with the highest value score, and the top M with the highest value score within the same object type, wherein N and M are both positive integers greater than 0; The object data and object characteristics of at least one of the target objects are displayed through a display interface.

7. A data analysis device based on knowledge graphs, characterized in that, The device includes: The acquisition module is used to acquire multi-source data corresponding to the supply chain, wherein the multi-source data is used to indicate object data of multiple objects in the supply chain; The processing module is used to construct a knowledge graph corresponding to the supply chain based on multiple object data, and determine the entity labels of multiple entity points in the knowledge graph and the relationship information between two entity points with edge relationships; and determine the object profile of each object based on the entity labels and relationship information. The processing module is also used to perform a comprehensive evaluation of any one of the multiple objects based on the object profile of the object, and obtain the object features of the object, which are used to indicate the value score of the object.

8. A knowledge graph-based data analysis device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images