A method and apparatus for user grouping

Abstract

Embodiments of the present application provide a method and device for user grouping, the method comprising: obtaining target grouping configuration information for users in a first application; in the case that the target grouping configuration information contains a user label set and a setting condition for the user label set, generating a target code according to the user label set and the setting condition, the user label set containing user labels for users in a second application; submitting the target code to a data engine for grouping calculation, and receiving grouping user information returned by the data engine for the users in the first application. Through the embodiments of the present application, cross-application user grouping is realized, and the flexibility, accuracy and efficiency of user grouping are improved.

Description

Technical Field

[0001] This invention relates to the field of Internet technology, and in particular to a method and apparatus for user segmentation. Background Technology

[0002] In the internet industry, user tags are highly refined feature identifiers of user behavior information, accurately reflecting user behavioral characteristics, preferences, and habits. Combining user tags allows for the selection of high-value target groups. For example, in the churn recovery and retention operations of game products, targeting users who "have participated in upgrade gameplay more than 500 times in the past six months" and "have logged in for 0 days in the past 7 days" as the target group, and then targeting them with upgrade gameplay gift giveaways, can precisely reach and achieve user retention.

[0003] As the ecosystem develops, different applications may share the same users, but existing user segmentation only applies to a single application and has certain limitations. Summary of the Invention

[0004] In view of the above problems, a method and apparatus for user segmentation are proposed to overcome or at least partially solve the above problems, comprising:

[0005] A method for user segmentation, the method comprising:

[0006] Obtain the target segmentation configuration information for users in the first application;

[0007] If the target segmentation configuration information includes a set of user tags and setting conditions for the set of user tags, target code is generated based on the set of user tags and setting conditions. The set of user tags includes user tags for users in the second application.

[0008] The target code is submitted to the data engine for cluster calculation, and the cluster user information for users in the first application is returned by the data engine.

[0009] Optionally, the target segmentation configuration information includes segmentation subject information, and before generating the target code based on the user tag set and set conditions, it also includes:

[0010] For each user tag in the user tag set, determine the tag primary key information;

[0011] If the user tag set contains a first user tag and a second user tag, convert the second user tag into one or more third user tags;

[0012] Among them, the tag subject information of the first user tag matches the group subject information, the tag subject information of the second user tag does not match the group subject information, and the tag subject information of one or more third user tags matches the group subject information.

[0013] Optionally, the grouping subject information is used to indicate the user level to be output, the tag primary key information is used to indicate the user level to be filtered, and the user level corresponding to one or more third user tags is the user level below the user level corresponding to the second user tag.

[0014] Optionally, target code is generated based on the user tag set and set conditions, including:

[0015] For each user tag in the user tag set, and in conjunction with the filtering conditions for user tags in the settings, generate sub-code for the user tag;

[0016] By combining the combination conditions for all user tags in the user tag set in the settings, the sub-codes corresponding to all user tags are combined to obtain the target code.

[0017] Optionally, it also includes:

[0018] Obtain key performance indicators;

[0019] Based on the key indicator items, obtain the key indicator parameters corresponding to the user group information;

[0020] Generate user profiles for different user groups based on key metrics.

[0021] Optionally, before obtaining the target segmentation configuration information for users in the first application, the method further includes:

[0022] Poll the first database to store the group configuration information; the group configuration information is submitted by the user through the front end and stored in the first database.

[0023] If a specified type of operation is detected corresponding to the target cluster configuration information, cluster calculation is triggered for the target cluster configuration information.

[0024] Optionally, it also includes:

[0025] If no operation of the specified type is detected corresponding to the target cluster configuration information, wait for periodic processing, and during the periodic processing, determine whether the cluster calculation deadline for the target cluster configuration information is greater than the current time.

[0026] If the deadline for cluster calculation of the target cluster configuration information is greater than the current time, wait for the user tags in the user tag set in the target cluster configuration information to be updated, or if the update is not completed but the preset time has arrived, trigger the cluster calculation of the target cluster configuration information.

[0027] Optionally, it also includes:

[0028] Information is recommended based on user segmentation information.

[0029] A user segmentation device, the device comprising:

[0030] The target segmentation configuration information acquisition module is used to acquire target segmentation configuration information for users in the first application;

[0031] The target code generation module is used to generate target code based on the user tag set and the setting conditions when the target group configuration information includes a user tag set and setting conditions for the user tag set. The user tag set includes user tags for users in the second application.

[0032] The user segmentation information receiving module is used to submit the target code to the data engine for segmentation calculation and to receive the user segmentation information for users in the first application returned by the data engine.

[0033] A server includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the user segmentation method as described above.

[0034] A computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the user grouping method described above.

[0035] The embodiments of the present invention have the following advantages:

[0036] In this embodiment of the invention, by obtaining target segmentation configuration information for users in a first application, and if the target segmentation configuration information includes a set of user tags and setting conditions for the set of user tags, target code can be generated based on the set of user tags and setting conditions. The set of user tags includes user tags for users in a second application. Then, the target code can be submitted to the data engine for segmentation calculation, and the segmentation user information for users in the first application returned by the data engine can be received. This achieves cross-application user segmentation, improves the flexibility and accuracy of user segmentation, and enhances the efficiency of user segmentation. Attached Figure Description

[0037] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating the steps of a user segmentation method according to an embodiment of the present invention;

[0039] Figure 2 This is a schematic diagram of a game user relationship provided in an embodiment of the present invention;

[0040] Figure 3 This is a flowchart of another user segmentation method provided in an embodiment of the present invention;

[0041] Figure 4 This is a flowchart of another user segmentation method provided in an embodiment of the present invention;

[0042] Figure 5 This is a flowchart of another user segmentation method provided in an embodiment of the present invention;

[0043] Figure 6 This is a structural block diagram of a user grouping device provided in an embodiment of the present invention. Detailed Implementation

[0044] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0045] Reference Figure 1 The diagram illustrates a flowchart of a user segmentation method according to an embodiment of the present invention, which may specifically include the following steps:

[0046] Step 101: Obtain the target group configuration information for users in the first application.

[0047] The application can be a game application or other applications, such as an email application. The users in the application can be registered users or users who have used the application before.

[0048] The first application can be a single application or one or more selected applications. For example, the first application can be all product applications that have user segmentation permissions.

[0049] When it is necessary to segment users in the first application, that is, to identify a portion of users from all users of the first application as a user group, the target segmentation configuration information can be obtained.

[0050] Furthermore, the target segmentation configuration information can also be associated with a second application, thereby enabling the optimization of user segmentation for the first application using users in the second application, such as... Figure 2 The first application is game A, and the second application is game B. Game A and game B have the same users and can be merged. Now we need to identify some users in game A, and these users are usually active users in game B. We can select users in game A who are also active users in game B and form them as a user group to achieve cross-application user segmentation.

[0051] Cluster configuration information can include the following two cases:

[0052] 1. Manual import mode

[0053] The target segmentation configuration information can include user information manually uploaded by users. This user information is associated with a second application. For example, the user information can include a user list where users are users in both the first and second applications. Specifically, different list templates can be provided for download, allowing users to upload their own lists. By providing a manual upload method, cross-application list uploads can be used for push notifications, improving the efficiency of segmentation.

[0054] 2. Combined Tag Mode

[0055] The target segmentation configuration information can include a set of user tags and setting conditions for the user tag set. The user tag set can include multiple user tags, which are user tags for users in the second application. Then, the user tag set and setting conditions for the user tag set can be used to determine the segmented user information. For example, the segmented user information can include a user list, in which the users are users in both the first and second applications.

[0056] The settings can include filtering conditions for each user tag and combined conditions for all user tags in the user tag set.

[0057] After a user selects a user tag, filtering conditions can be set for that user tag, such as threshold settings for user tags. The calculation methods include equal to, not equal to, greater than, less than, empty, not empty, contain, not contain, match, not match, within range, not within range, etc.

[0058] For example, there are users whose tags are: Game 1 user activity days in the last 30 days, with a filter condition of greater than or equal to 1; users whose tags are: Game 2 user card game play times in the last 30 days, with a filter condition of greater than or equal to 1; users whose tags are: Game 3 user login days in the last 30 days, with a filter condition of greater than or equal to 5; and users whose tags are: Game 4 user live stream watch times in the last 7 days, with a filter condition of greater than or equal to 1.

[0059] After a user has identified multiple user tags, combined conditions can be set for these user tags, such as selecting combinations of intersection, union, and difference, which can support multiple levels of nesting.

[0060] For example, take the intersection of the user tag of a user in Game 1 whose number of active days in the past 30 days is greater than or equal to 1 and the number of live streams watched by a user in Game 4 in the past 7 days is greater than or equal to 1.

[0061] In one example, the cluster configuration information may also include basic cluster attribute information, such as cluster name information, cluster description information, and cluster usage permission information, which can be customized by the user.

[0062] In one embodiment of the present invention, before step 101, the following may be included:

[0063] The system polls the first database for cluster configuration information; this information is submitted by the user through the front end and stored in the first database. If a specified type of operation is detected corresponding to the target cluster configuration information, cluster calculation for that target cluster configuration information is triggered.

[0064] In practical implementation, an interactive interface can be provided to users through the front end. The front end can collect the grouping configuration information submitted by users through the interactive interface, and then call the interface to store the grouping configuration information in the first database. The grouping configuration information can also be set to a waiting calculation state. By providing an interactive interface through the front end for users to perform grouping, users do not need to directly perform grouping from the raw logs through code or scripts, which reduces the operation threshold and improves the efficiency and accuracy of grouping.

[0065] For the cluster configuration information stored in the first database, polling can be performed sequentially. When a specified type of operation is detected for the target cluster configuration information, such as a create operation, a modify operation, or a refresh operation, and the target cluster configuration information needs to be processed in real time, it can be set to the calculation state and the cluster calculation can be started. For example, if the target cluster configuration information can contain a set of user tags and setting conditions for the set of user tags, the calculation in steps 102-103 can be triggered.

[0066] For target segmentation configuration information that may include user-uploaded segmentation user information, it can be stored after standardization. For example, after filtering out abnormal data, unifying standards, and defining fields, it can be stored in a distributed file system (Hadoop Distributed File System, HDFS) and mapped to Hive partitions to provide table queries. Furthermore, user-uploaded segmentation user information can be further correlated with the full user table in the first application. If a user from the segmentation user information does not exist in the full user table, that user can be filtered out.

[0067] In one embodiment of the present invention, it may further include:

[0068] If no operation of the specified type is detected corresponding to the target cluster configuration information, wait for periodic processing, and during the periodic processing, determine whether the cluster calculation deadline for the target cluster configuration information is greater than the current time.

[0069] If the deadline for cluster calculation of the target cluster configuration information is greater than the current time, wait for the user tags in the user tag set in the target cluster configuration information to be updated, or if the update is not completed but the preset time has arrived, trigger the cluster calculation of the target cluster configuration information.

[0070] If no operation of the specified type is detected corresponding to the target cluster configuration information, no immediate processing will be performed; instead, it will wait for periodic processing, such as daily processing. During periodic processing, it can be determined whether the cluster calculation deadline for the target cluster configuration information is greater than the current time. If the cluster calculation deadline is less than or equal to the current time, no further processing is required.

[0071] If the deadline for cluster calculation is later than the current time, and the target cluster configuration information can include a set of user tags and settings for the set of user tags, we can wait for the user tags in the target cluster configuration information to be updated to ensure that the user tags are up-to-date and thus ensure the accuracy of the clustering. For example, we can query the update time of the user tags in the second database. When the update time is the same day, it is the latest user tag.

[0072] Once the user tags in the user tag set of the target cluster configuration information are updated, the cluster calculation for the target cluster configuration information can be triggered.

[0073] If the user tag has not been updated but the preset time has arrived, i.e. the fallback time, such as 6 PM on the same day, the cluster calculation for the target cluster configuration information can also be triggered.

[0074] Step 102: If the target segmentation configuration information includes a set of user tags and setting conditions for the set of user tags, generate target code based on the set of user tags and setting conditions. The set of user tags includes user tags for users in the second application.

[0075] If the target segmentation configuration information includes a set of user tags and setting conditions for the set of user tags, target code for filtering users in the first application and the second application can be generated based on the set of user tags and setting conditions.

[0076] In one embodiment of the present invention, step 102 may include:

[0077] Sub-step 11: For each user tag in the user tag set, generate sub-code for the user tag by combining the filtering conditions for user tags in the settings.

[0078] Among them, the filtering conditions for user tags can be threshold settings for user tags, and the calculation methods include equal to, not equal to, greater than, less than, empty, not empty, contain, not contain, match, not match, within range, not within range, etc.

[0079] For each user tag, a second database can be queried to obtain a list of tags for that user tag, such as the application it belongs to, the numeric type, the tag primary key, and the latest update time. Then, based on the user tag and the filtering conditions, sub-codes for the user tag can be generated. These sub-codes may include tag type conversion code, data retrieval query code, tag threshold type conversion code, and filter condition generation code.

[0080] Sub-step 12: Combining the combination conditions for all user tags in the user tag set in the settings, combine the sub-codes corresponding to all user tags to obtain the target code.

[0081] Among them, the combined conditions for multiple user tags can be a combination of AND and / or / difference conditions.

[0082] After obtaining the sub-code for each user tag, the sub-codes corresponding to all user tags can be combined according to the combination conditions to obtain the target code.

[0083] In one embodiment of the present invention, the application can have users at different levels, such as Figure 2 In games A through C, there are users at the character level, account level, full account (accounts used across multiple games) level, and natural person level. Users at different levels are interconnected, and an account level user can include multiple character level users.

[0084] Based on this, the target cluster configuration information may include cluster subject information, which can be used to indicate the required user hierarchy for output. Prior to step 102, it may also include:

[0085] For each user tag in the user tag set, determine the tag primary key information; if the user tag set contains a first user tag and a second user tag, convert the second user tag into one or more third user tags.

[0086] Among them, the tag subject information of the first user tag matches the group subject information, the tag subject information of the second user tag does not match the group subject information, and the tag subject information of one or more third user tags matches the group subject information.

[0087] For each user tag, its tag primary key information can be determined. The tag primary key information is used to indicate the user level to be filtered. If the user tag set contains a first user tag and a second user tag, the second user tag can be converted into one or more third user tags. The user level corresponding to one or more third user tags is the user level below the user level corresponding to the second user tag, thereby realizing cross-level user grouping.

[0088] For example, if the group subject information corresponds to users at the role level, and the user tag set contains the first user tag of the user at the corresponding role level and the second user tag of the user at the corresponding account level, then the second user tag of the user at the corresponding account level can be reverted to the third user tag, which corresponds to the user at the role level below the account level.

[0089] In one example, if the user tag set contains only the first user tag and not the second user tag, then a fallback can be avoided and the first user tag can be used directly.

[0090] Step 103: Submit the target code to the data engine for cluster calculation, and receive the cluster user information for users in the first application returned by the data engine.

[0091] After the target code is determined, it can be submitted to the data engine for clustering calculation. The data engine can determine the target users from the users of the first application and the users of the second application based on the target code, and then obtain the clustered user information, such as a user list. The users in this clustered user information are users in the first application and also users in the second application.

[0092] In one example, the user grouping information can be stored on a local server or a distributed file system, and Hive partitions can be mapped to provide table queries.

[0093] In one embodiment of the present invention, it may further include:

[0094] Obtain key metrics; based on the key metrics, obtain the key metrics parameters corresponding to the user group information; based on the key metrics parameters, generate user group profiles.

[0095] To provide a more accurate description of the segmented user groups, user-defined key metrics can be obtained. Then, the key metric parameters corresponding to the key metrics can be obtained from the full user table of the segmented user information. Based on the key metric parameters, a segmented user profile can be generated and stored in the first database for front-end access.

[0096] Specifically, when generating target code, it can associate the target code with key metrics and the full user table, thereby directly obtaining user segment information and key metrics parameters through the target code, or it can generate code to obtain key metrics parameters after obtaining user segment information.

[0097] In one embodiment of the present invention, it may further include:

[0098] Information is recommended based on user segmentation information.

[0099] After obtaining user segment information, information can be recommended to users corresponding to the segment information, thereby achieving cross-product reach and improving the reach rate of information recommendations.

[0100] In one example, users corresponding to the user group information can be filtered, that is, secondary combination can be performed, such as removing users from the blacklist, to further improve the reach of information recommendations.

[0101] In this embodiment of the invention, by obtaining target segmentation configuration information for users in a first application, and if the target segmentation configuration information includes a set of user tags and setting conditions for the set of user tags, target code can be generated based on the set of user tags and setting conditions. The set of user tags includes user tags for users in a second application. Then, the target code can be submitted to the data engine for segmentation calculation, and the segmentation user information for users in the first application returned by the data engine can be received. This achieves cross-application user segmentation, improves the flexibility and accuracy of user segmentation, and enhances the efficiency of user segmentation.

[0102] Reference Figure 3 The diagram illustrates a flowchart of another user segmentation method provided by an embodiment of the present invention, which may specifically include the following steps:

[0103] Step 301: Obtain target group configuration information for users in the first application; wherein, the target group configuration information includes a group subject information, which is used to indicate the user hierarchy to be output.

[0104] Step 302: If the target segmentation configuration information includes a set of user tags and setting conditions for the set of user tags, determine the tag primary key information for each user tag in the set of user tags; wherein, the tag primary key information is used to indicate the user level to be filtered, and the set of user tags includes user tags for users in the second application.

[0105] Step 303: If the user tag set contains a first user tag and a second user tag, convert the second user tag into one or more third user tags; wherein, the tag subject information of the first user tag matches the group subject information, the tag subject information of the second user tag does not match the group subject information, the tag subject information of one or more third user tags matches the group subject information, and the user level corresponding to one or more third user tags is the user level below the user level corresponding to the second user tag.

[0106] Step 304: For each user tag in the user tag set, generate sub-code for the user tag by combining the filtering conditions for user tags in the settings.

[0107] Step 305: Combine the combination conditions for all user tags in the user tag set in the settings to obtain the target code by combining the sub-codes corresponding to all user tags.

[0108] Step 306: Submit the target code to the data engine for cluster calculation, and receive the cluster user information for users in the first application returned by the data engine.

[0109] Reference Figure 4 The diagram illustrates a flowchart of another user segmentation method provided by an embodiment of the present invention, which may specifically include the following steps:

[0110] Step 401: Poll the first database for the group configuration information stored therein; wherein, the group configuration information is submitted by the user through the front end and stored in a preset database.

[0111] Step 402: If a specified type of operation is detected corresponding to the target cluster configuration information, cluster calculation is triggered for the target cluster configuration information.

[0112] Step 403: Obtain the target group configuration information for users in the first application.

[0113] Step 404: Generate target code based on the user tag set and setting conditions in the target group configuration information. The user tag set contains user tags for users in the second application.

[0114] Step 405: Submit the target code to the data engine for cluster calculation, and receive the cluster user information for the users in the first application returned by the data engine.

[0115] Reference Figure 5 The diagram illustrates a flowchart of another user segmentation method provided by an embodiment of the present invention, which may specifically include the following steps:

[0116] Step 501: Poll the first database for the group configuration information stored therein; wherein, the group configuration information is submitted by the user through the front end and stored in the preset database.

[0117] Step 502: If no operation of the specified type is detected corresponding to the target cluster configuration information, wait for periodic processing, and during the periodic processing, determine whether the cluster calculation deadline for the target cluster configuration information is greater than the current time.

[0118] Step 503: If the deadline for cluster calculation of the target cluster configuration information is greater than the current time, wait for the user tags in the user tag set in the target cluster configuration information to be updated, or if the update is not completed but the preset time has been reached, trigger the cluster calculation of the target cluster configuration information.

[0119] Step 504: Obtain the target group configuration information for users in the first application.

[0120] Step 505: Generate target code based on the user tag set and setting conditions in the target group configuration information. The user tag set contains user tags for users in the second application.

[0121] Step 506: Submit the target code to the data engine for cluster calculation, and receive the cluster user information for users in the first application returned by the data engine.

[0122] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0123] Reference Figure 6The diagram shows a schematic representation of a user segmentation device according to an embodiment of the present invention, which may specifically include the following modules:

[0124] The target group configuration information acquisition module 601 is used to acquire target group configuration information for users in the first application.

[0125] The target code generation module 602 is used to generate target code based on the user tag set and the setting conditions when the target group configuration information includes a user tag set and setting conditions for the user tag set. The user tag set includes user tags for users in the second application.

[0126] The user segmentation information receiving module 603 is used to submit the target code to the data engine for segmentation calculation and to receive the user segmentation information for users in the first application returned by the data engine.

[0127] In one embodiment of the present invention, the target cluster configuration information includes cluster subject information, and may further include:

[0128] The tag primary key information determination module is used to determine the tag primary key information for each user tag in the user tag set.

[0129] The user tag conversion module is used to convert a second user tag into one or more third user tags when the user tag set contains a first user tag and a second user tag.

[0130] Among them, the tag subject information of the first user tag matches the group subject information, the tag subject information of the second user tag does not match the group subject information, and the tag subject information of one or more third user tags matches the group subject information.

[0131] In one embodiment of the present invention, the grouping subject information is used to indicate the user level to be output, the tag primary key information is used to indicate the user level to be filtered, and the user level corresponding to one or more third user tags is the user level below the user level corresponding to the second user tag.

[0132] In one embodiment of the present invention, the target code generation module 602 includes:

[0133] The sub-code generation submodule is used to generate sub-code for each user tag in the user tag set, combined with the filtering conditions for user tags in the settings.

[0134] The sub-code combination submodule is used to combine the sub-codes corresponding to all user tags in the user tag set with the combination conditions in the settings to obtain the target code.

[0135] In one embodiment of the present invention, it may further include:

[0136] The key indicator acquisition module is used to acquire key indicators.

[0137] The key indicator parameter acquisition module is used to obtain the key indicator parameters corresponding to the user group information based on the key indicator items.

[0138] The user segmentation and profiling generation module is used to generate user segments based on key indicator parameters.

[0139] In one embodiment of the present invention, it may further include:

[0140] The database polling module is used to poll the group configuration information stored in the first database; the group configuration information is submitted by the user through the front end and stored in the first database.

[0141] The first cluster calculation triggering module is used to trigger cluster calculation for the target cluster configuration information when a specified type of operation is detected corresponding to the target cluster configuration information.

[0142] In one embodiment of the present invention, it further includes:

[0143] The deadline determination module is used to wait for periodic processing when no operation of a specified type corresponding to the target cluster configuration information is detected. During the periodic processing, it determines whether the cluster calculation deadline for the target cluster configuration information is greater than the current time.

[0144] The second cluster calculation triggering module is used to wait for the user tags in the user tag set in the target cluster configuration information to be updated after the cluster calculation deadline for the target cluster configuration information is greater than the current time, or to trigger the cluster calculation for the target cluster configuration information after the user tags in the user tag set in the target cluster configuration information have not been updated but the preset time has been reached.

[0145] In one embodiment of the present invention, it may further include:

[0146] The information recommendation module is used to recommend information based on user group information.

[0147] An embodiment of the present invention also provides a server, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the above-described user segmentation method.

[0148] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, it implements the above-described user grouping method.

[0149] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0150] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0151] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0152] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0153] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0155] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0156] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0157] The above provides a detailed description of the user segmentation method and apparatus. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method of user segmentation, characterized in that, The method comprises: obtaining target clustering configuration information for a user in a first application; in the case that the target clustering configuration information contains a user label set and a setting condition for the user label set, generating a target code according to the user label set and the setting condition, the user label set containing a user label for a user in a second application; submitting the target code to a data engine for clustering calculation, and receiving clustering user information returned by the data engine for the user in the first application; the target clustering configuration information comprises a clustering subject information, and before the target code is generated according to the user label set and the setting condition, the method further comprises: determining label primary key information for each user label in the user label set; in the case that the user label set contains a first user label and a second user label, converting the second user label into one or more third user labels; wherein the label subject information of the first user label matches the clustering subject information, the label subject information of the second user label does not match the clustering subject information, and the label subject information of the one or more third user labels matches the clustering subject information; the clustering subject information is used to indicate the required output user level.

2. The method of claim 1, wherein, the label primary key information is used to indicate the required filtering user level, and the user level corresponding to the one or more third user labels is a user level lower than the user level corresponding to the second user label.

3. The method according to any of claims 1-2, characterized in that, the target code is generated according to the user label set and the setting condition, comprising: for each user label in the user label set, combining the filtering condition for the user label in the setting condition to generate a sub code for the user label; combining the combination condition for all user labels in the setting condition to combine the sub codes corresponding to all user labels to obtain the target code.

4. The method of claim 1, wherein, further comprising: obtaining a key indicator item; obtaining a key indicator parameter corresponding to the clustering user information according to the key indicator item; generating a clustering user portrait according to the key indicator parameter.

5. The method of claim 1, wherein, before the target clustering configuration information for a user in a first application is obtained, the method further comprises: polling the clustering configuration information stored in a first database; wherein the clustering configuration information is submitted by a user through a front end and stored in the first database; in the case that it is detected that the target clustering configuration information corresponds to a specified type of operation, triggering clustering calculation for the target clustering configuration information.

6. The method of claim 5, wherein, further comprising: in the case that it is not detected that the target clustering configuration information corresponds to a specified type of operation, waiting for periodic processing, and during the periodic processing, determining whether the clustering calculation deadline for the target clustering configuration information is greater than the current time; in the case that the clustering calculation deadline for the target clustering configuration information is greater than the current time, waiting for the user label update of the user label set in the target clustering configuration information to be completed, or not being updated but reaching a preset time, triggering clustering calculation for the target clustering configuration information.

7. The method of claim 1, wherein, further comprising: According to the user group information, information recommendation is performed.

8. An apparatus for user grouping, the apparatus comprising: The apparatus comprises: a target group configuration information obtaining module, configured to obtain target group configuration information for users in a first application; a target code generating module, configured to, in a case where the target group configuration information contains a user label set and setting conditions for the user label set, generate a target code according to the user label set and the setting conditions, the user label set containing user labels for users in a second application; a group user information receiving module, configured to submit the target code to a data engine for group calculation, and receive group user information for users in the first application returned by the data engine; the target group configuration information comprises a group subject information, and further comprises: a label primary key information determining module, configured to determine label primary key information for each user label in the user label set; a user label converting module, configured to, in a case where the user label set contains a first user label and a second user label, convert the second user label into one or more third user labels; wherein the label subject information of the first user label matches the group subject information, the label subject information of the second user label does not match the group subject information, and the label subject information of the one or more third user labels matches the group subject information; the group subject information is used to indicate a required output user level.

9. A server, characterized by The computer program is stored on the computer readable storage medium and can be run on the processor, and when the computer program is executed by the processor, the method for user grouping according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium and can be run on the processor, and when the computer program is executed by the processor, the method for user grouping according to any one of claims 1 to 7 is implemented.

Images