Cross-domain customer portrait generation method and device, computer device, and storage medium

Abstract

This application relates to a method, apparatus, computer device, storage medium, and computer program product for generating user profiles. The method includes: acquiring online user datasets and offline user datasets; extracting online and offline customer segmentation data belonging to the target customer group level from the online and offline user datasets; performing statistical calculations on the online and offline customer segmentation data to obtain the indicator values ​​corresponding to the online and offline customer statistical indicators; and integrating the online and offline customer statistical indicators to obtain a customer profile. This application achieves the construction of customer profiles by connecting and associating online and offline user data while maintaining anonymity in user data collection.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and in particular to a method, apparatus, computer device, storage medium, and computer program product for generating cross-domain customer profiles. Background Technology

[0002] In intelligent applications such as smart retail, smart spaces, and smart communities, user insights are the core of business operations, and user profiles are the foundation of user insights. Rich and accurate user profiles help management and operations personnel gain a deeper and more precise understanding of user behavior and preferences, enabling them to better provide suitable services during interactions, meet diverse needs, and enhance user experience.

[0003] In traditional technologies, the profile generation method involves first acquiring an image to be identified captured by a facial recognition camera, then identifying the image in a preset photo library to obtain the target user's identity information, and then obtaining the target user's life trajectory information, health information, and daily behavior information based on this identity information, and finally generating a user profile of the target user based on this information.

[0004] However, with enhanced data security, all applications are required to avoid collecting users' personal information without their authorization. Therefore, without obtaining the user's true identity information, traditional profiling methods will be unable to construct a complete user profile. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for generating cross-domain customer profiles that can generate profile information without obtaining user identity information, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for generating cross-domain customer profiles. The method includes:

[0007] Obtain online user datasets and offline user datasets;

[0008] Extract the online customer segmentation data and offline customer segmentation data belonging to the target customer segment from the online user dataset and the offline user dataset;

[0009] Statistical calculations are performed on the online customer segmentation data and the offline customer segmentation data to obtain the indicator values ​​corresponding to the online customer statistical indicators and the indicator values ​​corresponding to the offline customer statistical indicators.

[0010] The online customer group statistics indicators, the corresponding indicator values ​​of the online customer group statistics indicators, the offline customer group statistics indicators, and the corresponding indicator values ​​of the offline customer group statistics indicators are integrated to obtain a customer group profile.

[0011] In one embodiment, the method further includes:

[0012] Extract the online customer segmentation data and the offline customer segmentation data that meet the data fusion conditions from the online customer segmentation data and the offline customer segmentation data.

[0013] The online customer segmentation data and the offline customer segmentation data to be merged are merged to obtain the index value corresponding to the customer segmentation index, wherein the customer segmentation index corresponds to the data fusion condition.

[0014] The process of integrating the online customer group statistical indicators, the corresponding indicator values ​​of the online customer group statistical indicators, the offline customer group statistical indicators, and the corresponding indicator values ​​of the offline customer group statistical indicators to obtain a customer group profile includes:

[0015] The customer profile is obtained by concatenating the online customer group statistics indicators, the corresponding indicator values ​​of the online customer group statistics indicators, the offline customer group statistics indicators, the corresponding indicator values ​​of the offline customer group statistics indicators, the customer group integration indicators, and the corresponding indicator values ​​of the customer group integration indicators.

[0016] In one embodiment, the online customer segmentation data and offline customer segmentation data belonging to the target customer segment are extracted from the online user dataset and the offline user dataset, including:

[0017] Extract the online user identifier set and offline user identifier set belonging to the target customer group level from the online user dataset and the offline user dataset;

[0018] Extract the online customer segmentation data corresponding to the online user identifier set from the online user dataset;

[0019] Extract the offline customer segmentation data corresponding to the offline user identifier set from the offline user dataset.

[0020] In one embodiment, the extraction of online customer segmentation data and offline customer segmentation data belonging to the target customer segment from the online user dataset and the offline user dataset includes:

[0021] Based on multiple preset target customer group levels, the online user dataset and the offline user dataset are stratified respectively to obtain online customer group stratification data and offline customer group stratification data for multiple target customer group levels.

[0022] The step of performing statistical calculations on the online customer segmentation data and the offline customer segmentation data to obtain the indicator values ​​corresponding to the online customer segmentation statistical indicators and the offline customer segmentation statistical indicators includes: extracting online customer segmentation data and offline customer segmentation data belonging to the same customer group from the online customer segmentation data and offline customer segmentation data of each target customer group level.

[0023] Statistical calculations are performed on the online customer segmentation data and offline customer segmentation data belonging to the same customer group to obtain the indicator values ​​corresponding to the online customer statistical indicators and the offline customer statistical indicators.

[0024] In one embodiment, obtaining the offline user dataset includes:

[0025] Obtain the initial offline user dataset;

[0026] The initial offline user dataset is anonymized to obtain the offline user dataset.

[0027] Secondly, this application also provides an apparatus for generating cross-domain customer profiles. The apparatus includes:

[0028] The data acquisition module is used to acquire online user datasets and offline user datasets.

[0029] The data stratification module is used to extract online customer group stratification data and offline customer group stratification data belonging to the target customer group level from the online user dataset and the offline user dataset;

[0030] The data statistics module is used to perform statistical calculations on the online customer segmentation data and the offline customer segmentation data to obtain the indicator values ​​corresponding to the online customer statistical indicators and the indicator values ​​corresponding to the offline customer statistical indicators.

[0031] The data integration module is used to integrate the online customer group statistical indicators, the indicator values ​​corresponding to the online customer group statistical indicators, the offline customer group statistical indicators, and the indicator values ​​corresponding to the offline customer group statistical indicators to obtain a customer group profile.

[0032] In one embodiment, the device further includes:

[0033] The data extraction module is used to extract online customer segmentation data and offline customer segmentation data that meet the data fusion conditions from the online customer segmentation data and the offline customer segmentation data.

[0034] The data fusion module is used to fuse the online customer segmentation data and the offline customer segmentation data to be fused to obtain the index value corresponding to the customer segmentation index, wherein the customer segmentation index corresponds to the data fusion condition.

[0035] The data integration module is specifically used to concatenate the online customer group statistical indicators, the indicator values ​​corresponding to the online customer group statistical indicators, the offline customer group statistical indicators, the indicator values ​​corresponding to the offline customer group statistical indicators, the customer group integration indicators, and the indicator values ​​corresponding to the customer group integration indicators to obtain a customer group profile.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0037] Obtain online user datasets and offline user datasets;

[0038] Extract the online customer segmentation data and offline customer segmentation data belonging to the target customer segment from the online user dataset and the offline user dataset;

[0039] Statistical calculations are performed on the online customer segmentation data and the offline customer segmentation data to obtain the indicator values ​​corresponding to the online customer statistical indicators and the indicator values ​​corresponding to the offline customer statistical indicators.

[0040] The online customer group statistics indicators, the corresponding indicator values ​​of the online customer group statistics indicators, the offline customer group statistics indicators, and the corresponding indicator values ​​of the offline customer group statistics indicators are integrated to obtain a customer group profile.

[0041] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0042] Obtain online user datasets and offline user datasets;

[0043] Extract the online customer segmentation data and offline customer segmentation data belonging to the target customer segment from the online user dataset and the offline user dataset;

[0044] Statistical calculations are performed on the online customer segmentation data and the offline customer segmentation data to obtain the indicator values ​​corresponding to the online customer statistical indicators and the indicator values ​​corresponding to the offline customer statistical indicators.

[0045] The online customer group statistics indicators, the corresponding indicator values ​​of the online customer group statistics indicators, the offline customer group statistics indicators, and the corresponding indicator values ​​of the offline customer group statistics indicators are integrated to obtain a customer group profile.

[0046] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0047] Obtain online user datasets and offline user datasets;

[0048] Extract the online customer segmentation data and offline customer segmentation data belonging to the target customer segment from the online user dataset and the offline user dataset;

[0049] Statistical calculations are performed on the online customer segmentation data and the offline customer segmentation data to obtain the indicator values ​​corresponding to the online customer statistical indicators and the indicator values ​​corresponding to the offline customer statistical indicators.

[0050] The online customer group statistics indicators, the corresponding indicator values ​​of the online customer group statistics indicators, the offline customer group statistics indicators, and the corresponding indicator values ​​of the offline customer group statistics indicators are integrated to obtain a customer group profile.

[0051] The aforementioned method, apparatus, computer equipment, storage medium, and computer program product for generating cross-domain customer profiles extracts segmented online and offline customer data belonging to the target customer group level from collected online and offline user datasets. Then, statistical calculations are performed on this data to obtain the corresponding indicator values ​​for online and offline customer statistical indicators. Finally, a customer profile is constructed based on these online and offline customer statistical indicators and their values. It is understood that the profile in this application is defined at the user group level rather than the individual user level. Therefore, by extracting online and offline user data at the customer group level from online and offline user datasets, performing statistical calculations on the customer group-level data, and establishing the correlation between online and offline statistical dimension profiles, a comprehensive customer profile is obtained. This achieves the construction of customer profiles by connecting and linking online and offline user data while maintaining anonymity in user data collection, thereby effectively assisting in business improvement. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating a method for generating cross-domain customer profiles in one embodiment;

[0053] Figure 2 This is a flowchart illustrating a method for generating cross-domain customer profiles in another embodiment;

[0054] Figure 3 This is a flowchart illustrating a supplementary scheme for obtaining offline user datasets in one embodiment;

[0055] Figure 4 This is a structural block diagram of a device for generating cross-domain customer profiles in one embodiment;

[0056] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] In one embodiment, such as Figure 1 As shown, a method for generating cross-domain customer profiles is provided. This embodiment illustrates the application of this method to a server, but it is understood that the method can also be applied to terminals, and to systems including terminals and servers, and is implemented through interaction between the terminal and the server. It should be noted that "domain" refers to an application environment, specifically divided into online and offline environments. Cross-domain processing can be understood as integrating user data from the online environment and user data from the offline environment for processing. For example, integrating user data generated from online consumption and user data generated from offline consumption for subsequent processing constitutes cross-domain data processing. In this embodiment, the method includes the following steps:

[0059] Step S102: Obtain the online user dataset and the offline user dataset.

[0060] In this context, a user dataset refers to a collection of user data. User data refers to data generated by a user's actions. For example, a user's purchase or exercise will generate relevant data. Specifically, the server acquires both online and offline user datasets. For instance, in a shopping scenario, the online user dataset includes data generated from users ordering goods online; the offline user dataset includes data generated from users making purchases at physical stores.

[0061] Step S104: Extract the online customer segmentation data and offline customer segmentation data belonging to the target customer segment from the online user dataset and the offline user dataset.

[0062] The customer segmentation is used to divide the user group into different types of customer segments, thereby achieving the classification of the user dataset. The target customer segmentation can be a pre-defined segmentation or a segmentation selected by the user.

[0063] Specifically, the server extracts the online and offline customer segmentation data belonging to the target customer group level from the online and offline user datasets. Optionally, the server first extracts the online and offline user identifier sets belonging to the target customer group level from the online and offline user datasets. Then, it extracts the online customer segmentation data corresponding to the online user identifier sets from the online user dataset, and the offline customer segmentation data corresponding to the offline user identifier sets from the offline user dataset. In other words, it first identifies the online and offline user groups belonging to the target customer group level, and then extracts the online and offline user data corresponding to these user groups to obtain the online and offline customer segmentation data.

[0064] Step S106: Perform statistical calculations on the online customer segmentation data and the offline customer segmentation data to obtain the indicator values ​​corresponding to the online customer segmentation statistical indicators and the offline customer segmentation statistical indicators.

[0065] Specifically, since the profiles in this embodiment are defined at the group level rather than the individual level, the definition of each profile field becomes a corresponding statistical dimension. For this purpose, the server pre-sets online and offline customer group statistical indicators to be statistically analyzed. Customer group statistical indicators can be, for example, gender, age, dwell time, etc., and this information can be extracted from user data. To obtain the corresponding indicator values, statistical calculations need to be performed on the online and offline customer group segmented data to obtain the indicator values ​​corresponding to the online and offline customer group statistical indicators. Assuming the online customer group segmented data is represented as X and the offline customer group segmented data as Y, then the indicator value corresponding to the online customer group statistical indicator can be represented as h(X), and the indicator value corresponding to the offline customer group statistical indicator can be represented as g(Y).

[0066] Step S108: Integrate the online customer group statistics indicators, the corresponding indicator values ​​of the online customer group statistics indicators, the offline customer group statistics indicators, and the corresponding indicator values ​​of the offline customer group statistics indicators to obtain a customer group profile.

[0067] Specifically, the server integrates online customer statistics metrics, their corresponding values, offline customer statistics metrics, and their corresponding values ​​to obtain a customer profile. In one embodiment, the server concatenates the online customer statistics metrics, their corresponding values, offline customer statistics metrics, and their corresponding values ​​to obtain a customer profile.

[0068] In the aforementioned method for generating user profiles, by extracting segmented online and offline customer data belonging to the target customer group level from the collected online and offline user datasets, statistical calculations are performed on these data to obtain the corresponding indicator values ​​for online and offline customer statistical indicators. A customer profile is then constructed based on these online and offline customer statistical indicators and their values. It is understood that the profile in this application is defined at the user group level rather than the individual user level. Therefore, by extracting online and offline user data at the customer group level from the online and offline user datasets, performing statistical calculations on the customer group data, and establishing the correlation between online and offline statistical dimension profiles, a comprehensive profile of the customer group is obtained. This achieves the construction of customer profiles by connecting and linking online and offline user data while maintaining anonymity in user data collection, thereby effectively assisting in business improvement.

[0069] In order to obtain valuable indicator data in other dimensions to build customer profiles containing more useful information, in one embodiment, the method further includes the following steps:

[0070] Step S1072: Extract the online customer segmentation data and offline customer segmentation data that meet the data fusion conditions from the online customer segmentation data and the offline customer segmentation data.

[0071] Step S1074: Merge the online customer segmentation data to be merged and the offline customer segmentation data to be merged to obtain the index value corresponding to the customer segmentation index.

[0072] Among these, customer group integration indicators correspond to data integration conditions. These indicators are pre-set. Therefore, for example... Figure 2 As shown, based on the required customer group fusion indicator, the server extracts the online and offline customer group segmentation data that meet the data fusion conditions from the online and offline customer group segmentation data, and then merges them to obtain the indicator value corresponding to the customer group fusion indicator. Assuming the online customer group segmentation data is represented as X and the offline customer group segmentation data as Y, the indicator value corresponding to the customer group fusion indicator can be represented as f(X,Y). Optionally, the customer group fusion indicator can be one or more of conversion capability or conversion ratio. The conversion ratio is determined based on the number of transactions and the number of visitors. The conversion capability is determined based on the total transaction amount and the total dwell time.

[0073] Furthermore, in conjunction with the previous embodiment, one embodiment involves a possible implementation of step S108, "integrating online customer group statistical indicators, the corresponding indicator values ​​of online customer group statistical indicators, offline customer group statistical indicators, and the corresponding indicator values ​​of offline customer group statistical indicators to obtain a customer profile." Based on the above embodiment, step S108 can be specifically implemented through the following steps:

[0074] Step S1082: The online customer group statistical indicators, the corresponding indicator values ​​of the online customer group statistical indicators, the offline customer group statistical indicators, the corresponding indicator values ​​of the offline customer group statistical indicators, the customer group integration indicators, and the corresponding indicator values ​​of the customer group integration indicators are concatenated to obtain the customer group profile.

[0075] Specifically, the server concatenates the online customer group statistics indicators, the corresponding indicator value h(X), the offline customer group statistics indicators, the corresponding indicator value g(Y), the customer group integration indicators, and the corresponding indicator value f(X,Y) to obtain the customer group profile.

[0076] In this embodiment, online user data and offline user data are fused and processed after being segmented by customer groups. This can yield valuable customer group fusion indicators in other dimensions, such as conversion ability and conversion rate. This is beneficial for building customer profiles from more perspectives and improving the diversity and reference value of customer profiles.

[0077] In one embodiment, step S104 includes:

[0078] Step S1042: According to multiple preset target customer group levels, the online user dataset and the offline user dataset are respectively stratified to obtain online customer group stratification data and offline customer group stratification data of multiple target customer group levels.

[0079] Further, step S106 includes:

[0080] Step S1062: Extract the online customer segmentation data and offline customer segmentation data belonging to the same customer group from the online customer segmentation data and offline customer segmentation data of each target customer group level.

[0081] Step S1064: Perform statistical calculations on the online customer segmentation data and offline customer segmentation data belonging to the same customer group to obtain the indicator values ​​corresponding to the online customer group statistical indicators and the offline customer group statistical indicators.

[0082] The equivalent customer group is pre-established and stored on the server. The equivalent customer group is used to treat online user data and offline user data as the same data and process them together.

[0083] Specifically, to segment customer groups and accurately classify user datasets, multiple target customer group levels can be pre-defined in the server. After obtaining the online and offline user datasets, the server can, based on these pre-defined target customer group levels, categorize online user data that meets the criteria for each target customer group level into those levels, thus obtaining the corresponding online customer group stratification data. Similarly, the server can categorize offline user data that meets the criteria for each target customer group level into those offline user datasets, thus obtaining the corresponding offline customer group stratification data.

[0084] Optionally, the preset target customer segment includes:

[0085] Time dimension: Active customer groups in calendar year / calendar month; active customer groups in spring / summer / autumn / winter; active customer groups on weekdays / weekends / holidays; active customer groups on weekdays / major promotions; active customer groups in the morning / noon / afternoon / evening.

[0086] Spatial dimension: The active customer base of a certain business type / store; the active customer base shared by certain business types / stores.

[0087] Combination dimension: Active customer groups of different business formats at different times.

[0088] In the e-commerce or retail industry, the term "active customer group" is defined in accordance with business needs. For example, users who log in / enter the platform more than once per calendar month are considered active customers.

[0089] Then, to correlate highly relevant online and offline customer segmentation data to construct accurate customer profiles, equivalent customer groups can be pre-defined on the server. These equivalent customer groups are used to establish highly correlated and closely related relationships between online and offline customer groups. For example, people who shop at store A online and people who browse store A offline can be considered equivalent customer groups. Therefore, the server extracts the online and offline customer segmentation data belonging to equivalent customer groups from the online and offline customer segmentation data at each customer group level, and then performs statistical calculations to obtain more accurate indicator values ​​for online and offline customer statistical indicators, thereby constructing more accurate customer profiles.

[0090] In one embodiment, such as Figure 3 The diagram illustrates one possible implementation of "obtaining the offline user dataset" in step S102. Based on the above embodiment, step S102 can be specifically implemented through the following steps:

[0091] Step S1022: Obtain the initial offline user dataset;

[0092] Step S1024: Anonymize the initial offline user dataset to obtain the offline user dataset.

[0093] Specifically, to ensure user privacy, the server obtains an initial offline user dataset and then anonymizes it to obtain the final offline user dataset. In one embodiment, the server uses a trajectory-based customer flow system to obtain each user's shopping trajectory events and extracts the corresponding initial offline user data from these events. By aggregating the initial offline user data from multiple users, the server obtains the initial offline user dataset.

[0094] Optionally, the offline user dataset or the online user dataset includes one or more of the following: basic user attributes or user behavior events. Basic user attributes include, but are not limited to, hairstyle, headwear, clothing, shoes and bags, and peer attributes. User behavior events include, but are not limited to, exit events, floor entry / exit events, and store entry / exit events.

[0095] In one embodiment, the server anonymizes user identifiers (e.g., names), for example, by using user serial numbers (1, 2, ...) to distinguish the user corresponding to each piece of offline user data, thus obtaining the offline user dataset shown in Table 1. The server stores the data according to records, and at this time, the server cannot know the individual user's identity information.

[0096]

[0097]

[0098] Table 1

[0099] In one embodiment, the indicator value of the customer group statistics indicator includes one or more of the indicator distribution or indicator proportion. The indicator distribution includes one or more of the maximum, minimum, median, mean, or frequency. Based on this, in one embodiment, a possible implementation of the above step S106, "to perform statistical calculations on the online customer group stratification data and offline customer group stratification data belonging to the same customer group in each customer group level to obtain the indicator value corresponding to the online customer group statistics indicator and the indicator value corresponding to the offline customer group statistics indicator," is provided.

[0100] Based on the above embodiments, step S106 can be implemented through the following steps:

[0101] Step S106a: Extract online user identifiers, online statistical data corresponding to online user identifiers, offline user identifiers, and offline statistical data corresponding to offline user identifiers from the online customer group stratification data and offline customer group stratification data belonging to the same customer group in each customer group level.

[0102] Step S106b: Based on the online user identifier and the online data to be collected corresponding to the online user identifier, obtain the online indicator distribution and / or the proportion of online indicators corresponding to the online customer group statistical indicators.

[0103] Step S106c: Based on the offline user identifier and the offline data to be collected corresponding to the offline user identifier, obtain the distribution of offline indicators and / or the proportion of offline indicators corresponding to the offline customer group statistical indicators.

[0104] Optionally, the user identifier can be a user serial number. The user serial number is obtained based on anonymization. The server extracts online user serial numbers, corresponding online statistical data, offline user serial numbers, and corresponding offline statistical data from online and offline customer group stratification data belonging to the same customer group at each customer group level. Then, the server maps the online user serial numbers and corresponding online statistical data to a preset online indicator coordinate system to obtain the online indicator distribution corresponding to the online customer group statistical indicators. The horizontal axis of this online indicator coordinate system represents the online user serial number, and the vertical axis represents the online statistical data. On the other hand, the server maps offline user serial numbers and corresponding offline statistical data to a preset offline indicator coordinate system to obtain the offline indicator distribution corresponding to the offline customer group statistical indicators. The horizontal axis of this offline indicator coordinate system represents the offline user serial number, and the vertical axis represents the offline statistical data.

[0105] In other embodiments, other data distribution methods can also be used to obtain the indicator distribution, such as bar charts.

[0106] In one embodiment, the server can generate a distribution curve based on the indicator distribution and display it to the user through the terminal.

[0107] For example, taking a spatial dimension as an example, the server statistically analyzes the profiles of customers interested in store A. Please refer to Tables 2 and 3.

[0108]

[0109] Table 2

[0110]

[0111] Table 3

[0112] The total dwell time refers to the time spent in the mall from entering to exiting. The number of stores visited refers to the total number of stores visited from entering to exiting the mall.

[0113] In this embodiment, the original, irregular online and offline customer segmentation data belonging to the same customer group are statistically calculated to obtain regularly distributed online and offline customer statistical indicators, such as indicator distribution. Based on the customer group statistical indicators, valuable information such as the implicit distribution pattern and user group behavior pattern in cross-domain online and offline user data can be analyzed.

[0114] For example, the customer profile is shown in Table 4.

[0115]

[0116]

[0117] Table 4

[0118] Among them, a single cycle refers to a certain time period, such as a day, week, month, or quarter.

[0119] It should be understood that although the steps in the flowcharts of the embodiments described above 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 flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0120] Based on the same inventive concept, this application also provides a user profile generation apparatus for implementing the user profile generation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more user profile generation apparatus embodiments provided below can be found in the limitations of the user profile generation method described above, and will not be repeated here.

[0121] In one embodiment, such as Figure 4 As shown, a user profile generation device is provided, including: a data acquisition module 202, a data layering module 204, a data statistics module 206, and a data integration module 208, wherein:

[0122] The data acquisition module 202 is used to acquire online user datasets and offline user datasets;

[0123] The data stratification module 204 is used to extract online customer group stratification data and offline customer group stratification data belonging to the target customer group level from the online user dataset and the offline user dataset;

[0124] The data statistics module 206 is used to perform statistical calculations on online customer segmentation data and offline customer segmentation data to obtain the indicator values ​​corresponding to the online customer segmentation statistical indicators and the indicator values ​​corresponding to the offline customer segmentation statistical indicators.

[0125] The data integration module 208 is used to integrate online customer group statistical indicators, the corresponding indicator values ​​of online customer group statistical indicators, offline customer group statistical indicators, and the corresponding indicator values ​​of offline customer group statistical indicators to obtain customer group profiles.

[0126] In one embodiment, the data acquisition module 202 is specifically used to acquire an initial offline user dataset; and to anonymize the initial offline user dataset to obtain the offline user dataset.

[0127] In one embodiment, the device further includes: a data extraction module, used to extract online customer segmentation data and offline customer segmentation data that meet the data fusion conditions from online customer segmentation data and offline customer segmentation data; a data fusion module, used to fuse the online customer segmentation data and offline customer segmentation data to be fused to obtain the indicator value corresponding to the customer segmentation indicator, wherein the customer segmentation indicator corresponds to the data fusion conditions; the data integration module 208 is specifically used to splice together the online customer segmentation statistical indicator, the indicator value corresponding to the online customer segmentation statistical indicator, the offline customer segmentation statistical indicator, the indicator value corresponding to the offline customer segmentation statistical indicator, the customer segmentation indicator, and the indicator value corresponding to the customer segmentation indicator to obtain a customer profile.

[0128] In one embodiment, the data stratification module 204 is specifically used to extract the online user identifier set and offline user identifier set belonging to the target customer group level from the online user dataset and the offline user dataset; extract the online customer group stratification data corresponding to the online user identifier set from the online user dataset; and extract the offline customer group stratification data corresponding to the offline user identifier set from the offline user dataset.

[0129] In one embodiment, the data stratification module 204 is specifically used to stratify the online user dataset and the offline user dataset according to multiple preset target customer group levels, respectively, to obtain online customer group stratification data and offline customer group stratification data for multiple target customer group levels; the data statistics module 206 is specifically used to extract online customer group stratification data and offline customer group stratification data belonging to the same customer group from the online customer group stratification data and offline customer group stratification data of each target customer group level; and to perform statistical calculations on the online customer group stratification data and offline customer group stratification data belonging to the same customer group to obtain the indicator values ​​corresponding to the online customer group statistical indicators and the indicator values ​​corresponding to the offline customer group statistical indicators.

[0130] The modules in the aforementioned user profile generation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0131] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for generating user profiles.

[0132] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0133] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0134] Obtain online user datasets and offline user datasets;

[0135] Extract the online and offline customer segmentation data belonging to the target customer segment from the online and offline user datasets;

[0136] Statistical calculations were performed on online and offline customer segmentation data to obtain the corresponding indicator values ​​for online and offline customer statistical indicators.

[0137] By integrating online customer statistics indicators, their corresponding values, offline customer statistics indicators, and their corresponding values, a customer profile is obtained.

[0138] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0139] Obtain the initial offline user dataset; anonymize the initial offline user dataset to obtain the final offline user dataset.

[0140] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0141] From online and offline customer segmentation data, extract the online and offline customer segmentation data that meet the data fusion criteria; merge the online and offline customer segmentation data to obtain the indicator values ​​corresponding to the customer segmentation indicators; and concatenate the online customer statistics indicators, the corresponding indicator values ​​of the online customer statistics indicators, the offline customer statistics indicators, the corresponding indicator values ​​of the offline customer statistics indicators, the customer segmentation indicators, and the corresponding indicator values ​​of the customer segmentation indicators to obtain the customer profile.

[0142] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0143] Extract the online user identifier set and offline user identifier set belonging to the target customer group level from the online user dataset and offline user dataset; extract the online customer group segmentation data corresponding to the online user identifier set from the online user dataset; extract the offline customer group segmentation data corresponding to the offline user identifier set from the offline user dataset.

[0144] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0145] Based on multiple pre-defined target customer group levels, the online user dataset and the offline user dataset are stratified separately to obtain online customer group stratification data and offline customer group stratification data for multiple target customer group levels. From the online and offline customer group stratification data of each target customer group level, the online and offline customer group stratification data belonging to the same customer group are extracted. Statistical calculations are performed on the online and offline customer group stratification data belonging to the same customer group to obtain the indicator values ​​corresponding to the online and offline customer group statistical indicators.

[0146] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0147] Obtain online user datasets and offline user datasets;

[0148] Extract the online and offline customer segmentation data belonging to the target customer segment from the online and offline user datasets;

[0149] Statistical calculations were performed on online and offline customer segmentation data to obtain the corresponding indicator values ​​for online and offline customer statistical indicators.

[0150] By integrating online customer statistics indicators, their corresponding values, offline customer statistics indicators, and their corresponding values, a customer profile is obtained.

[0151] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0152] Obtain the initial offline user dataset; anonymize the initial offline user dataset to obtain the final offline user dataset.

[0153] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0154] From online and offline customer segmentation data, extract the online and offline customer segmentation data that meet the data fusion criteria; merge the online and offline customer segmentation data to obtain the indicator values ​​corresponding to the customer segmentation indicators; and concatenate the online customer statistics indicators, the corresponding indicator values ​​of the online customer statistics indicators, the offline customer statistics indicators, the corresponding indicator values ​​of the offline customer statistics indicators, the customer segmentation indicators, and the corresponding indicator values ​​of the customer segmentation indicators to obtain the customer profile.

[0155] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0156] Extract the online user identifier set and offline user identifier set belonging to the target customer group level from the online user dataset and offline user dataset; extract the online customer group segmentation data corresponding to the online user identifier set from the online user dataset; extract the offline customer group segmentation data corresponding to the offline user identifier set from the offline user dataset.

[0157] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0158] Based on multiple pre-defined target customer group levels, the online user dataset and the offline user dataset are stratified separately to obtain online customer group stratification data and offline customer group stratification data for multiple target customer group levels. From the online and offline customer group stratification data of each target customer group level, the online and offline customer group stratification data belonging to the same customer group are extracted. Statistical calculations are performed on the online and offline customer group stratification data belonging to the same customer group to obtain the indicator values ​​corresponding to the online and offline customer group statistical indicators.

[0159] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0160] Obtain online user datasets and offline user datasets;

[0161] Extract the online and offline customer segmentation data belonging to the target customer segment from the online and offline user datasets;

[0162] Statistical calculations were performed on online and offline customer segmentation data to obtain the corresponding indicator values ​​for online and offline customer statistical indicators.

[0163] By integrating online customer statistics indicators, their corresponding values, offline customer statistics indicators, and their corresponding values, a customer profile is obtained.

[0164] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0165] Obtain the initial offline user dataset; anonymize the initial offline user dataset to obtain the final offline user dataset.

[0166] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0167] From online and offline customer segmentation data, extract the online and offline customer segmentation data that meet the data fusion criteria; merge the online and offline customer segmentation data to obtain the indicator values ​​corresponding to the customer segmentation indicators; and concatenate the online customer statistics indicators, the corresponding indicator values ​​of the online customer statistics indicators, the offline customer statistics indicators, the corresponding indicator values ​​of the offline customer statistics indicators, the customer segmentation indicators, and the corresponding indicator values ​​of the customer segmentation indicators to obtain the customer profile.

[0168] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0169] Extract the online user identifier set and offline user identifier set belonging to the target customer group level from the online user dataset and offline user dataset; extract the online customer group segmentation data corresponding to the online user identifier set from the online user dataset; extract the offline customer group segmentation data corresponding to the offline user identifier set from the offline user dataset.

[0170] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0171] Based on multiple pre-defined target customer group levels, the online user dataset and the offline user dataset are stratified separately to obtain online customer group stratification data and offline customer group stratification data for multiple target customer group levels. From the online and offline customer group stratification data of each target customer group level, the online and offline customer group stratification data belonging to the same customer group are extracted. Statistical calculations are performed on the online and offline customer group stratification data belonging to the same customer group to obtain the indicator values ​​corresponding to the online and offline customer group statistical indicators.

[0172] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0173] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0174] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for generating cross-domain customer profiles, characterized in that, The method includes: Obtain the online user dataset and the initial offline user dataset; The user identifiers in the initial offline user dataset are anonymized to obtain the offline user dataset; the online user dataset includes data generated by users ordering goods online, and the offline user dataset includes data generated by users making purchases at offline physical stores. Based on multiple preset target customer group levels, the online user dataset and the offline user dataset are respectively stratified to obtain online customer group stratification data and offline customer group stratification data of multiple target customer group levels; the target customer group level includes at least time dimension, spatial dimension and combination dimension. From the online and offline customer segmentation data of each target customer group level, extract the online and offline customer segmentation data that belong to the same customer group; the same customer group is a pre-set data in the server, representing closely related online and offline customer groups that can merge user data. Statistical calculations are performed on the online customer group segmentation data and offline customer group segmentation data belonging to the same customer group to obtain the indicator values ​​corresponding to the online customer group statistical indicators and the indicator values ​​corresponding to the offline customer group statistical indicators. The online customer group statistics indicators, the corresponding indicator values ​​of the online customer group statistics indicators, the offline customer group statistics indicators, and the corresponding indicator values ​​of the offline customer group statistics indicators are integrated to obtain a customer group profile.

2. The method according to claim 1, characterized in that, The method further includes: Extract the online customer segmentation data and the offline customer segmentation data that meet the data fusion conditions from the online customer segmentation data and the offline customer segmentation data. The online customer segmentation data and the offline customer segmentation data to be merged are merged to obtain the index value corresponding to the customer segmentation index, wherein the customer segmentation index corresponds to the data fusion condition. The process of integrating the online customer group statistical indicators, the corresponding indicator values ​​of the online customer group statistical indicators, the offline customer group statistical indicators, and the corresponding indicator values ​​of the offline customer group statistical indicators to obtain a customer group profile includes: The customer profile is obtained by concatenating the online customer group statistics indicators, the corresponding indicator values ​​of the online customer group statistics indicators, the offline customer group statistics indicators, the corresponding indicator values ​​of the offline customer group statistics indicators, the customer group integration indicators, and the corresponding indicator values ​​of the customer group integration indicators.

3. The method according to claim 1, characterized in that, Extracting online and offline customer segmentation data belonging to the target customer segment from the online and offline user datasets, including: Extract the online user identifier set and offline user identifier set belonging to the target customer group level from the online user dataset and the offline user dataset; Extract the online customer segmentation data corresponding to the online user identifier set from the online user dataset; Extract the offline customer segmentation data corresponding to the offline user identifier set from the offline user dataset.

4. The method according to claim 1, characterized in that, The user identifier is a user serial number obtained based on anonymization.

5. A device for generating cross-domain customer profiles, characterized in that, The device includes: The data acquisition module is used to acquire an online user dataset and an initial offline user dataset; anonymize the user identifiers in the initial offline user dataset to obtain the offline user dataset; the online user dataset includes data generated by users ordering goods online, and the offline user dataset includes data generated by users making purchases at offline physical stores; The data stratification module is used to stratify the online user dataset and the offline user dataset according to multiple preset target customer group levels, respectively, to obtain online customer group stratification data and offline customer group stratification data of multiple target customer group levels; the target customer group level includes at least a time dimension, a spatial dimension, and a combination dimension. The data statistics module is used to extract online and offline customer segmentation data belonging to equivalent customer groups from the online and offline customer segmentation data of each target customer group level; the equivalent customer groups are pre-set in the server and represent closely related online and offline customer groups that can merge user data. Statistical calculations are performed on the online customer group segmentation data and offline customer group segmentation data belonging to the same customer group to obtain the indicator values ​​corresponding to the online customer group statistical indicators and the indicator values ​​corresponding to the offline customer group statistical indicators. The data integration module is used to integrate the online customer group statistical indicators, the indicator values ​​corresponding to the online customer group statistical indicators, the offline customer group statistical indicators, and the indicator values ​​corresponding to the offline customer group statistical indicators to obtain a customer group profile.

6. The apparatus according to claim 5, characterized in that, The device further includes: The data extraction module is used to extract online customer segmentation data and offline customer segmentation data that meet the data fusion conditions from the online customer segmentation data and the offline customer segmentation data. The data fusion module is used to fuse the online customer segmentation data and the offline customer segmentation data to be fused to obtain the index value corresponding to the customer segmentation index, wherein the customer segmentation index corresponds to the data fusion condition. The data integration module is specifically used to concatenate the online customer group statistical indicators, the indicator values ​​corresponding to the online customer group statistical indicators, the offline customer group statistical indicators, the indicator values ​​corresponding to the offline customer group statistical indicators, the customer group integration indicators, and the indicator values ​​corresponding to the customer group integration indicators to obtain a customer group profile.

7. The apparatus according to claim 5, characterized in that, The layered module is also used for: Extract the online user identifier set and offline user identifier set belonging to the target customer group level from the online user dataset and the offline user dataset; Extract the online customer segmentation data corresponding to the online user identifier set from the online user dataset; Extract the offline customer segmentation data corresponding to the offline user identifier set from the offline user dataset.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images