TWI621989B - Graph-based method and system for analyzing users - Google Patents

Abstract

A method and system for analyzing a user based on a graph is disclosed. The method includes: A. data feature parsing process, including: parsing data records occurring between users, merchants, and users and merchants to obtain key information, wherein key information includes user identifier, merchant identifier, and user and merchant The consumption information generated between the two uses the acquired key information to generate vertex information and side information of the graph, wherein the user identifier and the merchant identifier are used as vertex information, and the consumption information is used as side information; B. the association analysis process includes: at least based on One or more merchants associated with the first user, analyzing the first user to be associated with other users.

Description

Graph-based method and system for analyzing users

Embodiments of the present invention relate to data analysis and, in particular, to graph-based methods and systems for analyzing users.

With the rapid development of large data technologies, data analysis for individual users has become possible. Traditional user analysis uses user methods such as Bayesian and decision tree to classify and cluster users, and discover the relationship between users. However, in the case of large-scale data, the association classification algorithm for individual users is difficult to perform effectively, which often takes a long calculation time. In particular, model-oriented algorithms for iterative types are extremely inefficient at processing large-scale data. In addition, once the user information is updated, the user's associated classification needs to be recalculated, which will greatly affect the utility of the resulting data.

According to an embodiment of the present invention, a method for analyzing a user based on a graph is disclosed, which maintains an image with an object as a vertex and an association information between the object and the object as an edge, wherein the object includes a user and a merchant. The edge indicates the association relationship between the user and the merchant, and the method includes: A. the data feature parsing process, including: parsing the data records occurring between the user, the merchant, and the user and the merchant to obtain key information, where The key information includes user identification, merchant identification, consumption information generated between the user and the merchant; the key information obtained by the user is used to generate vertex information and side information of the graph, wherein the user identifier and the merchant logo are used as vertex information, and the consumption information is taken as Side information; B. Association analysis process, comprising: analyzing the first user to be associated with other users based at least on one or more merchants associated with the first user.

According to an embodiment of the present invention, a graph-based analysis user system is disclosed, which maintains an image with an object as a vertex and an association information between an object and an object as an edge, wherein the object includes a user and a merchant, and the side indication The relationship between the user and the merchant, the system includes: A. a data feature parsing module configured to: parse data records generated between the user, the merchant, and the user and the merchant to obtain key information, wherein the key The information includes user identification, merchant identification, consumption information generated between the user and the merchant, and uses the acquired key information to generate vertex information and side information of the graph, wherein the user identifier and the merchant logo are used as vertex information, and the consumption information is used as the edge. Information; B. The association analysis module is configured to analyze the first user to be associated with other users based on at least one or more merchants associated with the first user.

The technical solution of the invention can effectively improve the timeliness of the data by shortening the time of data update and data analysis, and improve the efficiency of the association analysis and classification analysis of the massive data in the large data environment. By building users and The merchant's relationship diagram, strong-wet correlation analysis, and edge-segment classification accelerate the speed of analysis and processing. At the same time, based on the instant updateable graph storage architecture, it provides near-instant data analysis capabilities.

Other features and advantages of the embodiments of the present invention will be understood from the description of the appended claims.

200, 210, 220, 300, 310, 320‧ ‧ steps

1 is a schematic diagram of analyzing a user based on a graph in which an object is a vertex and an association information between an object and an object is an edge, according to an embodiment of the present invention.

2 is a flow chart of a method for analyzing a user based on a graph, in accordance with an embodiment of the present invention.

3 is a schematic diagram of a graph-based system for analyzing users in accordance with an embodiment of the present invention.

Hereinafter, the principles of the present invention will be described in conjunction with the embodiments. It is to be understood that the present invention is not limited by the scope of the invention. For example, many specific implementation details are included in the description, and should not be construed as limiting the scope of the invention or the scope of the invention. For example, features described in the context of various embodiments can be implemented in a single embodiment. In a single Features described in the context of the embodiments can be implemented in various embodiments.

The present invention proposes an instant storage and update of the material to be processed based on the graph storage model. A graph is a data structure defined as: graph = (V, E). V is a non-empty finite set representing vertices (nodes), and E is a set of edges, generally represented by (Vx, Vy), where Vx, Vy belong to V. If there is an edge connection between the two nodes U and V, the two nodes U and V are said to be associated. A weighted graph can be used to represent relationships other than the connected relationship between two adjacent vertices.

Based on such a concept, the present invention proposes to maintain an image with the object as a vertex and the associated information between the object and the object as an edge, so as to improve the association analysis between the object (user or merchant) based on the association model and algorithm of the graph. Performance and efficiency of data analysis. In the present invention, the user may be a user such as a bank card or any user using a web service (e.g., online shopping), and the merchant may be any entity (e.g., a physical merchant or an online merchant) that provides a product or service.

1 is a schematic diagram of analyzing a user based on a graph in which an object is a vertex and an association information between an object and an object is an edge, according to an embodiment of the present invention. FIG. 1 shows users 1-7, merchants 1-4, which are linked by a user's consumption (purchase product or service) behavior, and form a map. For example, after the user 1 consumes the merchant 1, the connection between the user 1 and the merchant 1 is established. The vertices of the graph in Figure 1 represent objects, and the edges between vertices and vertices indicate association information between the two vertices. For example, the user ID and the merchant ID are used as vertex information. The associated information as side information may be information about consumption occurring between the user and the merchant. For example, the user is at the merchant The time, time of day, location, frequency, consumption amount, type of consumer goods, or merchant identification of the occurrence of the consumer event. The present invention proposes to generate a graph with the user and the merchant as vertices according to the consumption behavior characteristics of the user, and estimate the association between the user and the merchant, the user, and the user according to the map.

In the example shown in FIG. 1, the vertices in FIG. 1 can be filtered based on the merchant identification and consumption information according to the needs of the particular analysis.

In one example, when analyzing user 1, a merchant 3 (eg, a convenience store) having a specific merchant identification may be first filtered, and then among the remaining merchants associated with the user 1, the search has a predetermined number or more with the user 1 ( Strong correlation degree) of users of jointly associated merchants. For example, the predetermined number can be set to 3, and in this example, the degree of association between the user 4 and the user 1 is strong.

In one example, the relationship between the users associated with merchant 2 is directly specified. Then, the filtering condition can be set such that the amount consumed by the merchant 2 within a certain period of time is greater than a predetermined value (strong correlation degree). According to the filtering condition, considering the consumption information (side information) between the users 1, 4, 5, and 7 and the merchant 2, it can be known which of the users 1, 4, 5, and 7 are highly correlated with respect to the merchant 2.

It will be understood by those skilled in the art that one or more pieces of information (eg, time, time of day, location, frequency, amount of consumption, amount of consumer goods, and various combinations thereof) based on the merchant identification and consumption information may also be used. ) to analyze the relationship between a user and a merchant, and the user and other users.

Quickly analyze with graph-based correlation analysis Household groups, specific user preferences, and potential preferences. Other examples are also described below to facilitate an understanding of the present invention. However, these examples should not be considered limiting.

2 is a flow chart of a method for analyzing a user based on a graph, in accordance with an embodiment of the present invention. In the method, the relationship information between the object and the object is maintained as a vertex of the object, wherein the object includes a user and a merchant, and the edge indicates a relationship between the user and the merchant, and the method includes data. Feature resolution process 200 and association analysis process 300.

The data feature parsing process 200 includes: Step 210: Parsing data records generated between the user, the merchant, and the user and the merchant to obtain key information, wherein the key information includes the user identifier, the merchant identifier, and the user and the merchant. Inter-generational consumption information; Step 220: Using the acquired key information to generate vertex information and side information of the graph, wherein the user identifier and the merchant identifier are used as vertex information, and the consumption information is used as side information; the association analysis process 300 includes: The first user is analyzed to be associated with other users based on one or more merchants associated with the first user.

In one embodiment, the association analysis process 300 includes:

Step 310: Filter the merchant according to the predetermined condition with respect to the first user.

Step 320: Filter other users according to predetermined conditions with respect to the first user.

Thus, by filtering for business and consumer information Conditions, the first user can be quickly analyzed in the figure to find a merchant or other user who has strong affinity with the first user.

In one example, in the association analysis process, the one or more merchants associated with the first user are filtered according to the merchant identity to obtain the filtered one or more merchants. For example, a convenience store, a specific department store, a utility payment unit, and a specific hotel are excluded from the one or more merchants by a merchant logo. These excluded merchants can be considered as objects with weak relevance or low analytical value to the first user in a particular analysis. However, depending on the needs of the analysis, in other examples, these merchants can be considered.

In another example, during the association analysis process, the one or more merchants associated with the first user are filtered according to the consumption information to obtain the filtered one or more merchants. For example, the merchant in the consumption information is excluded from the merchant whose amount of the consumption amount is less than the predetermined value, and/or the merchant in the consumption information before the time of the last consumption event is excluded before the specific time. Alternatively, the frequency of consumption, the type of consumer product, or the type of service in the consumer information can also be considered.

It can be understood that the merchants in the merchants associated with the first user can be filtered in conjunction with the merchant identification and consumption information. As described above, by setting filter conditions for merchant identification and consumption information, the first user can quickly analyze in the figure to find a merchant that has strong relevance to the first user or that is in a specific association.

In one embodiment, other users associated with the filtered one or more merchants are determined in the map during the association analysis process. through By first identifying the merchant and then associating the first user to other users, the amount of calculation can be greatly reduced and the analysis efficiency can be improved.

In an example, in the association analysis process, a user having strong affinity with the first user is further selected from other users according to the merchant identifier, wherein the first user and another user are determined according to the following preset conditions. Strongly associative: the number of merchants that the first user and another user are associated with exceeds a predetermined value. For example, a user who has more than five merchants associated with the first user is considered to be a group that meets a specific analysis target.

In another example, in the association analysis process, the strength of the association between the first user and other users is further determined according to the consumption information. For example, for the same merchant, when it is judged that the consumption frequency of the first user and another user within a certain time period (for example, between two dates, or a certain time of day) is in the same range (for example When the consumption is 5 to 10 times a month, the two are considered to have strong correlation. For another example, for the same merchant, when it is determined that the consumption amount of the first user and another user in a certain time period is in the same range (for example, 5 to 10 times a month), the two are regarded as strong. Relevance. For another example, for the same merchant, when it is determined that the first user and the other user consume the same type of product or service, the two are regarded as having strong relevance. It can be understood that one or more consumption factors can be combined to determine the relevance between users. For example, the location of a consumer event can also be taken into account.

One of the embodiments in accordance with the present invention is described below. An example. In this example, the user-to-business side information is first weakly identified. The weak association relationship is defined as follows: the merchant identification indicates a merchant of a convenience store, a specific department store, or a public utility payment unit. Correlate analysis for specific user A to obtain all non-weakly associated merchants. Then, through these non-weakly associated merchants, all corresponding non-weakly associated multiple user Bs are obtained, and the common merchants and consumption information between B1 and Bn and A are recorded. When the number of merchants associated with user A and user B1 reaches more than half of all non-weakly associated merchants of A and/or the consumer information has strong correlation (for example, as described above), A and B1 may be considered to belong to the same group. . Thereby, user classification and merchant classification can be realized, the analysis efficiency of the user-oriented association relationship is improved, and the quality of the data service is improved.

In a preferred embodiment, the entire map may be divided according to predetermined conditions, and edges that do not satisfy the predetermined condition are deleted to obtain one or more groups.

The various blocks shown in FIG. 2 may be considered as method steps, and/or as operations resulting from running computer program code, and/or as a plurality of coupled logic circuit elements constructed to implement the associated functions. Although the operations are depicted in the figures in a particular order, this should not be construed as requiring that the operations are performed in the particular order shown or in the order of the order, or that all illustrated operations are performed to achieve the desired results. In some cases, multiplex parallel processing may be advantageous.

3 is a schematic diagram of a graph-based system for analyzing users in accordance with an embodiment of the present invention. As shown in the figure, the system includes a data feature analysis module, an association analysis module, and an optional index module. Feature analysis module for Maintaining the object as a vertex, the association information between the object and the object is a graph of the edge, wherein the object includes a user and a merchant, and the edge indicates the relationship between the user and the merchant.

According to an embodiment, the data feature parsing module is configured to: parse data records generated between the user, the merchant, and the user and the merchant to obtain key information, wherein the key information includes the user identifier, the merchant identifier, and the The consumption information generated between the user and the merchant; the key information obtained by the user is used to generate vertex information and side information of the graph, wherein the user identifier and the merchant logo are used as vertex information, and the consumption information is used as side information. The association analysis module is configured to analyze the first user to be associated with other users based on at least one or more merchants associated with the first user.

The consumption information generated between the user and the merchant includes one or more of the following: time, time, location, frequency, consumption amount, and type of consumer goods.

In other embodiments, the association analysis module is configured to: filter the one or more merchants associated with the first user according to the merchant identity to obtain the filtered one or more merchants.

In other embodiments, the association analysis module is configured to: filter the one or more merchants associated with the first user according to the consumption information to obtain the filtered one or more merchants.

In other embodiments, the association analysis module is configured to determine other users associated with the filtered one or more merchants in the map.

In other embodiments, the association analysis module is configured Further: selecting, according to the merchant identifier, a user having strong affinity with the first user from among other users, wherein the first user and another user are determined to have strong affinity according to the following preset conditions: the first The number of merchants that the user and the other user are associated with exceeds a predetermined value.

In other embodiments, the association analysis module is configured to: further determine, according to the consumption information, the strength of the association between the first user and other users.

In other embodiments, the indexing module is configured to maintain an index of the auxiliary information by using one of the key information of the object as a key and the location information of the object in the figure. As an example, the indexing module is configured to use the index to locate the position of the first object in the figure by using the index information of the first object, and find the location according to the position of the first object in the figure. Other objects associated with an object. The indexing module can be configured to maintain an item (eg, user ID or merchant ID) of the key information of the object as a key, and the position information of the object in the figure as an index of the auxiliary information. Here, the location information indicates the positional relationship of the vertex corresponding to the object with other objects in the storage structure of the graph (for example, the adjacency matrix, the adjacency list, etc.). The graph analysis module can quickly locate the position of the object in the graph by indexing.

Based on the data feature analysis module, the association analysis module, and the index module, the update operation and the analysis operation can be performed efficiently. During the update operation, when the key information of the object changes, the vertex information and the side information of the object in the figure are updated in real time.

Exemplary embodiments may be in hardware, software, or a combination thereof Implementation. For example, certain aspects of the invention may be implemented in a hardware, while other aspects may be implemented in a software. Although aspects of the exemplary embodiments of the present invention may be shown and described as a block diagram, a flowchart, it is well understood that the devices, or methods described herein may be implemented in a system that is a non-limiting example It is a function module. Furthermore, the above-described apparatus should not be construed as requiring such separation in all embodiments, but it should be understood that the described program elements and systems can generally be integrated into a single software product or packaged into multiple software products. .

Various modifications and variations of the above-described exemplary embodiments of the present invention will become apparent to those skilled in Therefore, the embodiments of the invention are not limited to the specific embodiments disclosed, and the modifications and other embodiments are intended to be included within the scope of the appended claims.

Claims (18)

A method for analyzing a user based on a graph, maintaining a graph in which an object is a vertex, and an association information between the object and the object is an edge, wherein the object includes a user and a merchant, and the edge indicates an association relationship between the user and the merchant. The method includes: A. a data feature parsing process, comprising: parsing data records generated between a user, a merchant, and a user and a merchant, and obtaining key information, wherein the key information includes a user identifier, a merchant identifier, and a user Consumption information generated between merchants; using the acquired key information to generate vertex information and side information of the graph, wherein the user identifier and the merchant logo are used as vertex information, and the consumer information is used as side information; B. the association analysis process includes: at least And analyzing, by the one or more merchants associated with the first user, the first user is associated with another user, and in the association analysis process, filtering the one or more merchants associated with the first user according to the merchant identifier, and obtaining filtering One or more merchants. The method of claim 1, wherein the consumption information generated between the user and the merchant comprises one or more of the following: a time, a time slot, a place, a frequency, a consumption amount, and a consumer product category in which the consumption event occurs. The method of claim 1, wherein In the association analysis process, the one or more merchants associated with the first user are filtered according to the consumption information, and the filtered one or more merchants are obtained. The method of claim 1 or 3, wherein in the association analysis process, other users associated with the filtered one or more merchants are determined in the map. The method of claim 1 or 3, wherein, in the association analysis process, the user who has strong affinity with the first user is further selected from other users according to the merchant identifier, wherein the determined condition is determined according to the following preset conditions. The first user and the other user have strong affinity: the number of merchants jointly associated with the first user and another user exceeds a predetermined value. The method of claim 1 or 3, wherein in the association analysis process, the strength of the association between the first user and other users is further determined according to the consumption information. The method of claim 1, wherein the method comprises: maintaining one of the key information of the object as a key, and using the location information of the object in the figure as an index of the auxiliary information. The method of claim 7, wherein the index of the first object is located by the index of the first object, and the position of the first object in the figure is determined according to the position of the first object in the figure. Other objects associated with the first object. The method of claim 8, wherein the map and the index are stored by a decentralized architecture. A graph-based analysis user system maintains an object with a vertices, and the association information between the object and the object is a side graph, wherein the object includes a user and a merchant, and the edge indicates a relationship between the user and the merchant. The system includes: A. a data feature parsing module configured to parse data records generated between a user, a merchant, and a user and a merchant to obtain key information, wherein the key information includes a user identifier, a merchant identifier, The consumption information generated between the user and the merchant; the key information obtained by the user is used to generate the vertex information and the side information of the graph, wherein the user identifier and the merchant logo are used as vertex information, and the consumption information is used as side information; B. association analysis module And configured to: associate the first user with other users based on at least one or more merchants associated with the first user, the association analysis module configured to: filter the association associated with the first user according to the merchant identifier Describe one or more merchants to get filtered one or more merchants. The system of claim 10, wherein the consumption information generated between the user and the merchant comprises one or more of the following: a time, a time, a place, a frequency of the consumption event, and a consumption gold Amount, the type of consumer goods. The system of claim 10, wherein the association analysis module is configured to: filter the one or more merchants associated with the first user based on the consumption information to obtain the filtered one or more merchants. The system of claim 10 or 12, wherein the association analysis module is configured to determine other users associated with the filtered one or more merchants in the map. The system of claim 10 or 12, wherein the association analysis module is configured to: further select, according to the merchant identifier, a user having strong affinity with the first user from among other users, wherein The condition determines that the first user and another user have strong affinity: the number of merchants that the first user and another user are associated with exceeds a predetermined value. The system of claim 10 or 12, wherein the association analysis module is configured to: further determine, according to the consumption information, the strength of the association between the first user and other users. The system of claim 10, wherein the system further comprises: an indexing module configured to maintain an index of the auxiliary information by using one of the key information of the object as a key and the location information of the object in the figure. . The system of claim 16, wherein The indexing module is configured to use the index to locate the position of the first object in the figure by using the index information of the first object, and find the association with the first object according to the position of the first object in the figure. Other objects. The system of claim 17, wherein the system stores the map and the index through a decentralized architecture.