User mobility identification method, device, equipment, medium and program product

Abstract

The present disclosure provides a method for identifying user mobility, which can be applied to the field of financial technology. The method for identifying user mobility includes: obtaining the behavior data of multiple users in a first time period and a second time period after user authorization; extracting multiple behavior features of the behavior data in the first time period and the second time period respectively; clustering multiple users based on multiple preset cluster centers and the behavior features of multiple users to obtain user cluster groups of multiple users in the first time period and the second time period respectively; counting the flow quantity of each user cluster group in the first time period flowing to each user cluster group in the second time period to represent the flow situation of multiple users in the first time period and the second time period. The present disclosure also provides a user mobility identification device, equipment, storage medium and program product.

Description

Technical Field

[0001] The present disclosure relates to the field of financial technology, and specifically to a user liquidity identification method, device, equipment, medium and program product. Background Art

[0002] Live streaming is an e-commerce operation model that has developed in recent years. It is a sales model in which live streaming hosts open live streaming rooms on the Internet and sell goods in the live streaming rooms. The sales of live streaming is related to the personal ability of the hosts in the live streaming rooms, the user traffic in the live streaming rooms, and user preferences. If the goods in the live streaming rooms are less attractive to users, it will lead to user loss. If the live streaming format in the live streaming room is attractive, or the discount is increased, it will attract some potential users and stabilize old users. It can be seen that user demand directly affects the traffic in the live streaming room. It is very important for the live streaming sales industry to grasp user demand in a timely manner.

[0003] However, it is difficult to analyze the actual needs of live broadcast users, product sales and other factors that affect sales based on personal ability. How to identify user mobility characteristics from huge network traffic can effectively help the live broadcast industry understand user needs, recover lost users, and even increase user traffic. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a method, apparatus, device, medium and program product for identifying user mobility.

[0005] According to a first aspect of the present disclosure, a user mobility identification method is provided, comprising: obtaining behavior data of multiple users in a first time period and a second time period after user authorization; extracting multiple behavior features of the behavior data in the first time period and the second time period respectively; clustering the multiple users based on multiple preset clustering centers and the behavior features of the multiple users to obtain user cluster groups of the multiple users in the first time period and the second time period respectively; counting the flow number of each user cluster group in the first time period flowing to each user cluster group in the second time period to represent the flow situation of the multiple users in the first time period and the second time period.

[0006] According to an embodiment of the present disclosure, the behavioral data includes at least the user's most recent consumption, consumption frequency and consumption amount, and the extraction of multiple behavioral characteristics of the behavioral data in the first time period and the second time period respectively includes: inputting the most recent consumption, consumption frequency and consumption amount into a preset user stratification model, and calculating the stratification scores of the most recent consumption, consumption frequency and consumption amount, each of the stratification scores representing one of the behavioral characteristics.

[0007] According to an embodiment of the present disclosure, extracting multiple behavioral features of the behavioral data in the first time period and the second time period respectively also includes: calculating a total behavioral score based on the hierarchical scores of the most recent consumption, consumption frequency and consumption amount, and the total behavioral score represents one of the behavioral features.

[0008] According to an embodiment of the present disclosure, the calculation of the total behavior score based on the stratified scores of the most recent consumption, consumption frequency and consumption amount includes: calculating the sum of the squares of the stratified scores of the most recent consumption, consumption frequency and consumption amount to obtain the total behavior score.

[0009] According to an embodiment of the present disclosure, clustering the multiple users based on multiple preset clustering centers and behavioral characteristics of the multiple users to obtain user clustering groups of the multiple users in the first time period and the second time period respectively includes: calculating the distance between the behavioral characteristics of each user and each of the clustering centers for the multiple users in the first time period and the second time period respectively; and dividing each of the users into a user clustering group corresponding to the clustering center closest to the multiple users to obtain multiple user clustering groups of the multiple users in the first time period and the second time period respectively.

[0010] According to an embodiment of the present disclosure, it also includes: when the flow number between the user cluster groups is greater than a preset threshold, obtaining the behavior data of the corresponding mobile users; analyzing the behavior data to identify the user's flow behavior, including: when the consumption frequency and / or consumption amount in the behavior data decreases in the second time period compared to the first time period, it indicates that the corresponding user is losing; when the consumption frequency and / or consumption amount in the behavior data increases in the second time period compared to the first time period, it indicates that the consumption potential of the corresponding user is increasing.

[0011] According to an embodiment of the present disclosure, the method further includes: drawing a distribution diagram of each of the user cluster groups in the first time period and the second time period to observe the flow of the multiple users in the first time period and the second time period.

[0012] According to a second aspect of the present disclosure, a user mobility identification device is provided, including: a behavior data acquisition module, used to obtain behavior data of multiple users in a first time period and a second time period after user authorization; a behavior feature extraction module, used to extract multiple behavior features of the behavior data in the first time period and the second time period respectively; a user group clustering module, used to cluster the multiple users based on multiple preset clustering centers and the behavior features of the multiple users, and obtain user cluster groups of the multiple users in the first time period and the second time period respectively; a user mobility data identification module, used to count the flow quantity of each user cluster group in the first time period flowing to each user cluster group in the second time period, so as to represent the mobility of the multiple users in the first time period and the second time period.

[0013] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned user mobility identification method.

[0014] The fourth aspect of the present disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned user mobility identification method.

[0015] The fifth aspect of the present disclosure also provides a computer program product, including a computer program, which implements the above-mentioned user mobility identification method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0017] Figure 1 The application scenario diagram of the user mobility identification method, apparatus, device, medium and program product according to the embodiment of the present disclosure is schematically shown;

[0018] Figure 2 A flowchart of a method for identifying user mobility according to an embodiment of the present disclosure is schematically shown;

[0019] Figure 3 A schematic diagram of an RFM model according to an embodiment of the present disclosure is schematically shown;

[0020] Figure 4 A schematic diagram of selecting the number of cluster centers according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 5A schematic diagram showing a structural block diagram of a user mobility identification device according to an embodiment of the present disclosure; and

[0022] Figure 6 A block diagram of an electronic device suitable for implementing a method for identifying user mobility according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0024] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0025] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0026] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0027] The customer stratification model (RFM for short) is a classic, simple and efficient scoring model. In practical applications, it is not enough to measure customer value based on a single parameter. For example, most people think that customers who spend the most money are the most valuable and loyal customers. In fact, if a customer only bought a product once a long time ago, then he is not the most valuable customer. The RFM model accurately understands customer groups and their lifetime value. The RFM model uses three attributes: the latest consumption, consumption frequency and consumption amount to rank customers. The latest consumption shows the information of the customer's recent purchase order. According to the RFM model, customers who have recently purchased goods from the store have a higher probability of responding to any new initiatives (in terms of product recommendation activities, etc.) than customers who have not purchased goods from the store for a long time. Consumption frequency means that customers often buy items from your store. Customers who shop in the store frequently or more frequently have a higher probability of shopping in the store again than customers who do not shop in the store frequently. With the help of the statistics of purchase frequency, the possibility of the user shopping in the store in the future can be predicted. The consumption amount indicates the amount of money spent by the customer on shopping in the store over a period of time. Customers who spend more in the store are more likely to shop in the store again than customers who spend less in the store. The RFM model assigns multiple levels of scores to the most recent purchase, frequency of purchase, and amount of purchase. The higher the score, the more likely the customer is to respond positively to product recommendations, etc., and the more likely they are to make more purchases at your store again, so the more valuable the customer is. The order of the RFM score helps to rank customers accordingly.

[0028] K-means clustering is an unsupervised learning algorithm that can classify data that does not have a defined category. When there are no labels in the dataset, in this scenario, the task is to find groups of data that are identical to each other in the dataset, which are called clusters. K-means clustering is one of the most popular, simplest, and most general algorithms for partitioning clusters. It can solve the well-known clustering problem and can be applied to any type of grouping. K-means clustering stores k centroids and uses these centroids to define clusters. A point is assigned to a particular cluster and not to any other cluster based on its distance from the centroid of that cluster.

[0029] The embodiment of the present disclosure provides a method for identifying user mobility, which includes: obtaining behavior data of multiple users in a first time period and a second time period after user authorization; extracting multiple behavior features of the behavior data in the first time period and the second time period respectively; clustering multiple users based on multiple preset cluster centers and the behavior features of multiple users to obtain user cluster groups of multiple users in the first time period and the second time period respectively; counting the number of flows of each user cluster group in the first time period to each user cluster group in the second time period, so as to represent the flow of multiple users in the first time period and the second time period. The method can segment users according to user behavior and count the performance differences of user behavior in different time periods, so as to provide a reference for analyzing user needs and accurately positioning users.

[0030] It should be noted that the user mobility identification method and device provided by the present disclosure can be used for user flow analysis in the financial field, and can also be used in any field other than the financial field. The application field of the user mobility identification method and device provided by the present disclosure is not limited.

[0031] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0032] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0033] Figure 1 The application scenario diagram of the user mobility identification method and device according to the embodiments of the present disclosure is schematically shown.

[0034] like Figure 1 As shown, the application scenario 100 according to this embodiment may include user traffic analysis scenarios such as live streaming sales industry, e-commerce industry, etc. The network 104 is used to provide a medium for communication links between terminal devices 101, 102, 103 and server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0035] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0036] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0037] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0038] It should be noted that the user mobility identification method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the user mobility identification device provided in the embodiment of the present disclosure can generally be set in the server 105. The user mobility identification method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the user mobility identification device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0039] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0040] The following will be based on Figure 1 The scene described by Figure 2 to Figure 6 The user mobility identification method of the disclosed embodiment is described in detail.

[0041] Figure 2 The flowchart of the method for identifying user mobility according to an embodiment of the present disclosure is schematically shown.

[0042] like Figure 2 As shown, the user liquidity identification method of this embodiment includes operations S210 to S230, and the transaction processing method can be executed sequentially.

[0043] In operation S210, after user authorization, behavior data of multiple users in a first time period and a second time period are obtained.

[0044] In the embodiments of the present disclosure, users may be e-commerce users, live broadcast users, etc., and the user's behavior data may include the user's consumption record data within a preset time period, specifically including consumption time, consumption location, consumption content (including product category, quantity, etc.), consumption amount, etc. The collection, storage, use, processing, transmission, provision, disclosure and application of the user behavior data involved are all collected with the user's authorization, comply with the relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good customs.

[0045] Optionally, the first time period and the second time period may be divided into units of year, month, week, day, etc. The first time period and the second time period may be two consecutive time periods, such as the first half of 2019 and the second half of 2019. The first time period and the second time period may also be two time periods with a preset interval, such as two consecutive working days separated by Saturday and Sunday.

[0046] In this embodiment, by respectively obtaining the user's behavior data in the first time period and the second time period, the user's consumption behavior characteristics in these two time periods can be further analyzed, and then by comparing the consumption behavior characteristics in these two time periods, the user's consumption behavior changes can be discovered, and corresponding measures can be taken according to the user's behavior changes to stabilize or expand user traffic, thereby helping merchants increase sales.

[0047] In operation S220 , a plurality of behavior features of the behavior data in the first time period and the second time period are respectively extracted.

[0048] In this embodiment, in order to efficiently classify users, the behavioral data used actually includes the most recent consumption, consumption frequency and consumption amount, and the RFM model is used to perform stratified scoring on the above behavioral data, and each stratified score represents one of the behavioral characteristics.

[0049] Figure 3 The schematic diagram of the RFM model according to the embodiment of the present disclosure is schematically shown. Figure 3As shown in the figure, the RFM model uses the most recent consumption, consumption frequency and consumption amount as three scoring attributes. Merchants or analysts can subdivide each scoring attribute into multiple scoring categories based on experience or algorithm analysis. For example, each scoring attribute can be subdivided into 5 categories, so a total of 5×5×5=125 different combinations of scoring attribute values ​​can be generated. If the score of each category is set to 5 scores from 1 to 5, then the scores of the three scoring attributes of the most recent consumption, consumption frequency and consumption amount are combined, and the scoring span can start from the highest "5-5-5" and end at the lowest "1-1-1". The higher the score, the higher the consumption level of the user. The following table schematically shows the scoring of the three consumption behaviors by the RFM model, where R_Score, F_Score, and M_Score correspond to the scores of the most recent consumption, consumption frequency, and consumption amount, respectively.

[0050] Table 1 RFM scores

[0051] Customer ID Latest consumption (days) Consumption frequency Consumption amount (yuan) R_Score F_Score M_Score 101 1 32 2048 3 3 3 102 7 16 1024 3 3 3 103 28 6 512 2 2 2 104 128 1 64 1 1 1 105 256 2 4096 1 1 3

[0052] As shown in Table 1, if in the RFM model, the level of the most recent consumption within a week is set to 3, then the R_Score of customer ID101 and 102 is 3. Similarly, if the level of users with a consumption frequency of 5-10 times is set to 2, the F_Score of customer ID103 is 2. Therefore, according to the segmentation rules, multiple attribute scores of each user can be obtained, and the users can be segmented into multiple categories. Among them, each score combination of R_Score, F_Score, and M_Score corresponds to a user classification. As shown in Table 1, the score combination of "3-3-3" represents a user class, and customer ID101 and 102 belong to this user class. The score combination of "1-1-3" represents another user class, and customer ID105 belongs to this user class.

[0053] It can be understood that each scoring attribute of the RFM model can be divided into multiple levels according to application requirements. For example, each scoring attribute can be subdivided into 3 categories, so there are a total of 3×3×3=27 different combinations of scoring attribute values. The number of categories of each scoring attribute can be different. For example, the most recent consumption can be divided into 5 categories, the consumption frequency can be divided into 4 categories, and the consumption amount can be divided into 3 categories, so there are a total of 5×4×3=60 different combinations of scoring attribute values.

[0054] The RFM model method is simple, has a fast processing speed when the data volume is huge, is easy to implement and explain the clustering results, and can relatively maintain computational efficiency while reducing computational costs.

[0055] Furthermore, in order to increase the descriptiveness of user behavior characteristics, in this embodiment, the total behavior score can also be calculated based on the hierarchical scores of the most recent consumption, consumption frequency and consumption amount, and the total behavior score can be used to represent a behavior characteristic.

[0056] Generally speaking, the calculation formula for the total behavior score can be:

[0057] Total_RFM_Score=R_Score+F_Score+M_Score;

[0058] Due to the huge amount of online sales data and the high degree of data overlap, the scores of the most recent consumption, consumption frequency and consumption amount are collinear with the total behavior score.

[0059] In this embodiment, the total behavior score can be obtained by calculating the sum of squares of the hierarchical scores of the most recent consumption, consumption frequency, and consumption amount. The calculation formula is as follows:

[0060] Total_RFM_Score=R_Score 2 +F_Score 2 +M_Score 2 ;

[0061] According to the above formula, the problem of collinearity between the scores of the most recent consumption, consumption frequency and consumption amount and the total behavior score is solved.

[0062] In operation S230, the multiple users are clustered based on the multiple preset cluster centers and the behavior characteristics of the multiple users to obtain user cluster groups of the multiple users in the first time period and the second time period.

[0063] In the k-means algorithm, there are many parameters that can affect the final clustering results of the k-means algorithm, such as the number of clusters k, cluster initialization and distance measurement. In k-means clustering, different methods help determine the number of clusters, such as elbow method, silhouette method, based on experience, cross-validation, etc.

[0064] Figure 4 The schematic diagram of selecting the number of cluster centers according to the elbow method is shown schematically. Figure 4 As shown, in this curve, we see an inflection point at 3. Therefore, in this example, the optimal number of clusters is 3.

[0065] In this embodiment, cluster analysis can be performed through historical data to obtain multiple preset cluster centers for clustering users. The input data for clustering is the score of the most recent consumption, consumption frequency, consumption amount, and total behavior score, and finally multiple user groups about multiple cluster centers are obtained. Among them, clustering is performed on users in the first time period and the second time period respectively, and user cluster groups in the first time period and the second time period are obtained for each cluster center.

[0066] The clustering process specifically includes operations S231 to S232.

[0067] In operation S231, for a plurality of users in a first time period and a second time period, the distance between the behavior feature of each user and each cluster center is calculated.

[0068] In operation S232, each user is divided into a user cluster group corresponding to a cluster center that is closest to the user, and a plurality of user cluster groups of the plurality of users in the first time period and the second time period are obtained.

[0069] In the above clustering process, the cluster center can be continuously updated by calculating the internal mean of the group until the cluster center and the user cluster group no longer change.

[0070] The clustering effect can be evaluated based on the ratio of the "total sum of squares" (totss) and the "between sum of squares" (betweens) of the clustering results. The closer the ratio is to 1, the better the clustering effect is. The "total square value" is defined as the sum of the squared distances from all data points to the center, and the "between sum of squares" shows the variability between clusters.

[0071] Table 2 schematically shows a clustering result. As shown in Table 2, the current users are divided into 5 categories. The table shows the average value of the most recent consumption, consumption frequency and consumption amount of each category of users. It can be seen that there are obvious differences in the payment amount and number of payments between different groups.

[0072] Table 2 User clustering group analysis

[0073]

[0074]

[0075] In operation S240 , the number of users flowing from each user cluster group in the first time period to each user cluster group in the second time period is counted to indicate the flow of multiple users in the first time period and the second time period.

[0076] In this embodiment, according to the user clustering groups of the first time period and the second time period obtained in operation S230, the number of each user clustering group can be compared, as well as the number of each user clustering group flowing to other types of user clustering groups in the second time period compared to the first time period. Table 3 schematically shows a table of migration of user clustering groups, wherein the first time period is the first half of 2019, the second time period is the second half of 2019, and the user groups are divided into 5 categories, wherein each row of cells represents the number of a group in the first half of the year that migrated to each group in the second half of the year and the total number of the group in the first half of the year.

[0077] Table 3

[0078]

[0079] From the results in Table 3, we can see that most customer groups are stable, with only some groups migrating. These migrations indicate that customer consumption patterns have changed.

[0080] According to the above data, when the flow quantity between user cluster groups is greater than a preset threshold, the behavior data of the corresponding mobile users is obtained for specific analysis.

[0081] Analyze behavioral data to identify user mobility behaviors, including at least the following two situations:

[0082] When the consumption frequency and / or consumption amount in the behavior data decreases in the second time period compared to the first time period, it indicates that the corresponding user is churned;

[0083] When the consumption frequency and / or consumption amount in the behavior data increases in the second time period compared to the first time period, it indicates that the consumption potential of the corresponding user is increasing.

[0084] Merchants can send personalized email product recommendation campaigns to these customers, especially potential customers, to increase sales, long-term customer retention rate and lifetime value. For users who are losing, merchants can analyze their consumption tendencies, push products that they are interested in and provide preferential policies to retain them.

[0085] In this embodiment, distribution diagrams of user cluster groups in the first time period and the second time period are drawn so that merchants can observe the flow of multiple users in the first time period and the second time period.

[0086] According to the user mobility identification method provided by the embodiment of the present disclosure, the users in two time periods are segmented through the model, and the users are clustered, and the users are divided into multiple cluster groups to compare the changes in the user groups in the two time periods. According to the changes in the user groups, the changes in the user's consumption behavior can be effectively analyzed, thereby helping merchants to identify potential customers and lost customers, so that merchants can take further measures against these users to stabilize the users, thereby helping merchants to improve their sales capabilities.

[0087] Based on the above user mobility identification method, the present disclosure also provides a user mobility identification device. Figure 5 The device is described in detail.

[0088] Figure 5 The structure block diagram of the user mobility identification device according to an embodiment of the present disclosure is schematically shown.

[0089] like Figure 5 As shown, the user mobility identification device 500 of this embodiment includes a behavior data acquisition module 510 , a behavior feature extraction module 520 , a user group clustering module 530 and a user mobility data identification module 540 .

[0090] The behavior data acquisition module 510 is used to acquire the behavior data of multiple users in the first time period and the second time period after the user authorization. In one embodiment, the behavior data acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0091] The behavior feature extraction module 520 is used to extract multiple behavior features of the behavior data in the first time period and the second time period, respectively. In one embodiment, the behavior feature extraction module 520 can be used to perform the operation S220 described above, which will not be described in detail here.

[0092] The user group clustering module 530 is used to cluster multiple users based on multiple preset cluster centers and the behavioral characteristics of multiple users to obtain user clustering groups of multiple users in the first time period and the second time period. In one embodiment, the user group clustering module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0093] The user flow data identification module 540 is used to count the flow quantity of each user cluster group in the first time period flowing to each user cluster group in the second time period, so as to indicate the flow situation of multiple users in the first time period and the second time period. In one embodiment, the user group clustering module 540 can be used to perform the operation S240 described above, which will not be described in detail here.

[0094] According to an embodiment of the present disclosure, the behavior data acquired by the behavior data acquisition module 510 specifically includes the most recent consumption, consumption frequency and consumption amount; the behavior feature extraction module 520 inputs the most recent consumption, consumption frequency and consumption amount into a preset user stratification model, and calculates the stratification scores of the most recent consumption, consumption frequency and consumption amount, and each stratification score represents one of the behavior features respectively; the user group clustering module 530 calculates the distance between the behavior characteristics of each user and each of the cluster centers for the multiple users in the first time period and the second time period, and divides each of the users into the user cluster groups corresponding to the cluster centers closest to the multiple users, and obtains multiple user cluster groups of the multiple users in the first time period and the second time period respectively; the user flow data identification module 540 identifies the users and potential users who are losing based on the migration change data of each user group, thereby helping merchants to expand user traffic and increase sales.

[0095] Furthermore, the behavior feature extraction module 520 can also be used to calculate a total behavior score based on the stratified scores of the most recent consumption, consumption frequency, and consumption amount, where the total behavior score represents one of the behavior features, and the user behavior is described using the total behavior score and the stratified scores of the most recent consumption, consumption frequency, and consumption amount as multiple behavior features.

[0096] The method of calculating the total behavior score based on the hierarchical scores of the most recent consumption, consumption frequency and consumption amount includes: calculating the sum of squares of the hierarchical scores of the most recent consumption, consumption frequency and consumption amount to obtain the total behavior score. This method can eliminate the linear relationship between the hierarchical scores of the most recent consumption, consumption frequency and consumption amount and the total behavior score.

[0097] The user flow data identification module 540 may identify the user flow type by: when the flow number between the user cluster groups is greater than a preset threshold, obtaining the behavior data of the corresponding mobile users; analyzing the behavior data to identify the user's flow behavior. The user flow data identification module 540 includes at least two types of analysis: when the consumption frequency and / or consumption amount in the behavior data decreases in the second time period compared to the first time period, it indicates that the corresponding user is losing, thereby identifying the lost user; when the consumption frequency and / or consumption amount in the behavior data increases in the second time period compared to the first time period, it indicates that the corresponding user's consumption potential is increasing, thereby identifying potential users.

[0098] In this embodiment, the user mobility identification device 500 may further include a group distribution diagram module for drawing distribution diagrams of the user cluster groups in the first time period and the second time period to observe the mobility of the multiple users in the first time period and the second time period.

[0099] According to an embodiment of the present disclosure, any multiple modules of the behavior data acquisition module 510, the behavior feature extraction module 520, the user group clustering module 530, and the user flow data identification module 540 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the behavior data acquisition module 510, the behavior feature extraction module 520, the user group clustering module 530, and the user flow data identification module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in an appropriate combination of any of them. Alternatively, at least one of the behavior data acquisition module 510, the behavior feature extraction module 520, the user group clustering module 530 and the user flow data identification module 540 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0100] Figure 6 A block diagram of an electronic device suitable for implementing a method for identifying user mobility according to an embodiment of the present disclosure is schematically shown.

[0101] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0102] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0103] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0104] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0105] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0106] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the item recommendation method provided by the embodiment of the present disclosure.

[0107] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 601. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0108] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0109] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, apparatus, module, unit, etc. described above can be implemented by a computer program module.

[0110] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0111] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0113] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for identifying user mobility, characterized in that: include: After the user authorizes, the behavior data of multiple users in the first time period and the second time period are obtained; Extracting a plurality of behavior features of the behavior data in a first time period and a second time period respectively; Clustering the multiple users based on multiple preset cluster centers and behavioral characteristics of the multiple users to obtain user cluster groups of the multiple users in the first time period and the second time period respectively; Counting the number of flows from each of the user cluster groups in the first time period to each of the user cluster groups in the second time period, so as to indicate the flow of the plurality of users in the first time period and the second time period; The behavior data at least includes the user's most recent consumption, consumption frequency, and consumption amount, and the extracting of multiple behavior features of the behavior data in the first time period and the second time period respectively includes: Inputting the most recent consumption, consumption frequency and consumption amount into a preset user stratification model, calculating stratification scores of the most recent consumption, consumption frequency and consumption amount, each stratification score representing one of the behavioral characteristics; When the number of flows between the user cluster groups is greater than a preset threshold, obtaining the behavior data of the corresponding mobile users; Analyzing the behavior data to identify the user's mobile behavior includes at least: When the consumption frequency and / or the consumption amount in the behavior data decreases in the second time period compared to the first time period, it indicates that the corresponding user is losing; When the consumption frequency and / or consumption amount in the behavior data increases in the second time period compared to the first time period, it indicates that the consumption potential of the corresponding user is increasing.

2. The method according to claim 1, characterized in that The extracting of a plurality of behavior features of the behavior data in the first time period and the second time period respectively further comprises: A total behavior score is calculated based on the stratified scores of the most recent consumption, consumption frequency, and consumption amount, and the total behavior score represents one of the behavior characteristics.

3. The method according to claim 2, characterized in that The stratified scoring based on the most recent consumption, consumption frequency and consumption amount to calculate the total behavior score includes: The sum of squares of the stratified scores of the most recent consumption, consumption frequency, and consumption amount is calculated to obtain the total behavior score.

4. The method according to claim 1, characterized in that: The clustering of the multiple users based on the multiple preset cluster centers and the behavioral characteristics of the multiple users to obtain user cluster groups of the multiple users in the first time period and the second time period respectively includes: For the plurality of users in the first time period and the second time period, respectively, calculating the distance between the behavior feature of each user and each of the cluster centers; Each of the users is divided into a user cluster group corresponding to a cluster center that is closest to the user, to obtain a plurality of user cluster groups of the plurality of users in the first time period and the second time period respectively.

5. The method according to claim 1, characterized in that Also includes: A distribution diagram of each of the user cluster groups in the first time period and the second time period is drawn to observe the flow of the multiple users in the first time period and the second time period.

6. A user mobility identification device, comprising: A behavior data acquisition module, used to acquire behavior data of multiple users in a first time period and a second time period after user authorization; A behavior feature extraction module, used to extract a plurality of behavior features of the behavior data in a first time period and a second time period respectively; A user group clustering module, configured to cluster the multiple users based on multiple preset cluster centers and behavioral characteristics of the multiple users, and obtain user cluster groups of the multiple users in a first time period and a second time period respectively; A user flow data identification module, used for counting the flow quantity of each user cluster group flowing from the first time period to each user cluster group flowing from the second time period, so as to indicate the flow situation of the plurality of users in the first time period and the second time period; The behavior data at least includes the user's most recent consumption, consumption frequency, and consumption amount, and the extracting of multiple behavior features of the behavior data in the first time period and the second time period respectively includes: Inputting the most recent consumption, consumption frequency and consumption amount into a preset user stratification model, calculating stratification scores of the most recent consumption, consumption frequency and consumption amount, each stratification score representing one of the behavioral characteristics; When the number of flows between the user cluster groups is greater than a preset threshold, obtaining the behavior data of the corresponding mobile users; Analyzing the behavior data to identify the user's mobile behavior includes at least: When the consumption frequency and / or the consumption amount in the behavior data decreases in the second time period compared to the first time period, it indicates that the corresponding user is losing; When the consumption frequency and / or consumption amount in the behavior data increases in the second time period compared to the first time period, it indicates that the consumption potential of the corresponding user is increasing.

7. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors execute the user mobility identification method according to any one of claims 1 to 5.

8. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the user mobility identification method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for identifying user mobility according to any one of claims 1 to 5 is implemented.

Images