CN114827255A

CN114827255A - Data processing method, data processing device, readable storage medium and electronic device

Info

Publication number: CN114827255A
Application number: CN202210487888.0A
Authority: CN
Inventors: 陈新河; 余晓睿; 曹鼎; 何家荣
Original assignee: Netease Hangzhou Network Co Ltd
Current assignee: Netease Hangzhou Network Co Ltd
Priority date: 2022-05-06
Filing date: 2022-05-06
Publication date: 2022-07-29

Abstract

The invention discloses a data processing method, a data processing device, a readable storage medium and an electronic device. The method comprises the following steps: acquiring a first target object set based on a first trigger condition, wherein behavior data of a first target object in the first target object set meets the first trigger condition; dividing a first target object set into a plurality of sub-object sets; pushing corresponding first target data to each sub-object set to obtain a plurality of pushing results, wherein the plurality of pushing results are in one-to-one correspondence with the plurality of sub-object sets; and determining target policy data based on the plurality of pushing results, wherein the target policy data comprises a second trigger condition and second target data, and the target policy data is used for indicating that the second target data is pushed to the second target object when the behavior data of the second target object in the second target object set meets the second trigger condition. The invention solves the technical problem of low efficiency of final strategy formulation.

Description

Data processing method, data processing device, readable storage medium and electronic device

Technical Field

The present invention relates to the field of computers, and in particular, to a data processing method, device, readable storage medium, and electronic device.

Background

Currently, in the operation of game users, a method of reaching the users is usually adopted to keep long-term contact with the users so as to exert the maximum value of the life cycle of the users. However, when the user touches, the experimental effect of the user touch is mainly obtained manually, and the optimal material is selected manually for final pushing, so that the technical problem of low final strategy making efficiency is caused.

In view of the problem of low efficiency of the final strategy formulation, no effective solution is proposed at present.

Disclosure of Invention

At least some embodiments of the present invention provide a data processing method, an apparatus, a readable storage medium, and an electronic apparatus, so as to at least solve the technical problem of low efficiency of final policy making.

According to an embodiment of the present invention, there is provided a data processing method, including: acquiring a first target object set based on a first trigger condition, wherein behavior data of a first target object in the first target object set meets the first trigger condition; dividing a first target object set into a plurality of sub-object sets; pushing corresponding first target data to each sub-object set to obtain a plurality of pushing results, wherein the plurality of pushing results are in one-to-one correspondence with the plurality of sub-object sets; and determining target policy data based on the plurality of pushing results, wherein the target policy data comprises a second trigger condition and second target data, and the target policy data is used for indicating that the second target data is pushed to the second target object when the behavior data of the second target object in the second target object set meets the second trigger condition.

Optionally, the first trigger condition is determined based on a content type of the first target data, wherein the first target data of different content types correspond to different first trigger conditions.

Optionally, each push result is used to represent a ratio of the number of first target objects, which receive the first target data and operate on the first target data, in the corresponding sub-object set to the number of first target objects, which receive the first target data, in the sub-object set, and the determining of the target policy data based on the multiple push results includes: determining a target pushing result in the plurality of pushing results, wherein the proportion corresponding to the target pushing result is greater than the proportion corresponding to any one of the plurality of pushing results except the target pushing result; and determining target strategy data based on the target push result.

Optionally, determining target policy data based on the target push result includes: and determining the first target data corresponding to the target pushing result as second target data in the target strategy data to obtain the target strategy data.

Optionally, first original policy data is obtained, where the first original policy data includes a third trigger condition and third target data, and the first original policy data is used to indicate that when behavior data of a third target object in a third target object set meets the third trigger condition, the third target data is pushed to the third target object; determining first target data corresponding to the target pushing result as second target data in the target policy data to obtain the target policy data, including: and in the first original strategy data, updating the third target data into the first target data corresponding to the target pushing result, and determining the updated third target data into the second target data to obtain the target strategy data.

Optionally, a sub-object set corresponding to the target pushing result is removed from the third target object set, so as to obtain a second target object set.

Optionally, the first trigger condition and the first target data are obtained from second original policy data, where the second original policy data is used to indicate that the first target data is pushed to the first target object when the behavior data of the first target object in the first target object set meets the first trigger condition.

Optionally, dividing the first target object set into a plurality of sub-object sets, including one of: determining the identification of a first target object in a first target object set, and dividing the first target object set into a plurality of sub-object sets according to the identification of the first target object; and determining the identification of each sub-object set, and determining a first target object identified with the identification of the sub-object set as an element of the sub-object set to obtain a plurality of sub-object sets.

Optionally, pushing the corresponding first target data to each sub-object set includes: and pushing first target data corresponding to the identification of each sub-object set to each sub-object set.

Optionally, in response to the target stop condition, the pushing of the corresponding first target data to each sub-object set is stopped.

According to an embodiment of the present invention, there is also provided a data processing apparatus including: the acquiring unit is used for acquiring a first target object set based on a first trigger condition, wherein behavior data of a first target object in the first target object set meets the first trigger condition; a dividing unit, configured to divide the first target object set into a plurality of sub-object sets; the pushing unit is used for pushing the corresponding first target data to each sub-object set to obtain a plurality of pushing results, wherein the plurality of pushing results are in one-to-one correspondence with the plurality of sub-object sets; and the determining unit is used for determining target strategy data based on the plurality of pushing results, wherein the target strategy data comprises a second trigger condition and second target data, and the target strategy data is used for indicating that the second target data is pushed to a second target object when the behavior data of the second target object in the second target object set meets the second trigger condition.

According to an embodiment of the present invention, there is also provided a readable storage medium, in which a computer program is stored, wherein when the computer program is executed by a processor, the apparatus where the computer readable storage medium is located is controlled to execute the data processing method according to the embodiment of the present invention.

There is further provided, according to an embodiment of the present invention, an electronic apparatus including a memory and a processor, the memory having a computer program stored therein, the processor being configured to execute the computer program to perform the data method of any one of the above.

In at least some embodiments of the present invention, a first set of target objects is obtained based on a first trigger condition, where behavior data of a first target object in the first set of target objects satisfies the first trigger condition; dividing a first target object set into a plurality of sub-object sets; pushing corresponding first target data to each sub-object set to obtain a plurality of pushing results, wherein the plurality of pushing results are in one-to-one correspondence with the plurality of sub-object sets; and determining target policy data based on the plurality of pushing results, wherein the target policy data comprises a second trigger condition and second target data, and the target policy data is used for indicating that the second target data is pushed to the second target object when the behavior data of the second target object in the second target object set meets the second trigger condition. That is to say, according to the method and the device for pushing the target strategy data, the first target object set is obtained based on the first trigger condition, the first target object set is divided into the plurality of sub-object sets, the corresponding first target data is finally pushed to each sub-object set, a plurality of pushing results are obtained, the target strategy data are determined based on the plurality of pushing results, the experimental effect achieved by manually obtaining the user touch is avoided, the optimal material is manually selected for final pushing, the purpose of recycling the material effect in a short time can be achieved, the technical effect of improving the efficiency of final strategy making is achieved, and the technical problem that the efficiency of final strategy making is low is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

fig. 1 is a block diagram of a hardware configuration of a mobile terminal of a data processing method according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method of data processing according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of an A/B test core logic according to the related art;

FIG. 4 is a schematic diagram of a core module for automatic A/B testing according to an embodiment of the present invention;

FIG. 5(a) is a schematic diagram of configuring real-time trigger conditions and experimental test information on a front-end page according to an embodiment of the present invention;

fig. 5(b) is a schematic diagram of configuring material information on a front-end page according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of an experimental strategy and a final push strategy for an automated A/B test according to an embodiment of the present invention;

FIG. 7(a) is a schematic diagram of configuring real-time trigger conditions and experimental test information on a front-end page according to another embodiment of the present invention;

fig. 7(b) is a schematic diagram of another arrangement of material information on a front-end page according to an embodiment of the present invention;

fig. 8 is a schematic diagram of a data processing apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

First, some of the nouns or terms appearing in the description of the embodiments of the present application are used for the following explanation:

user-reach means to send a specific message to a specific user through a specific channel in a specific scene based on a specific purpose. Such as: application message pushing, short message pushing, mail pushing and the like are more mainstream user touch modes.

The A/B Test (Test) is used for making two (or more) schemes for the same target, correspondingly dividing user flow into a plurality of groups, enabling users to see different scheme designs on the premise of ensuring that the characteristics of each group of users are the same, and scientifically helping the product to make a decision according to the real data feedback of the users in the plurality of groups.

And (4) embedding points, namely recording and reporting various behaviors of the user on software or a webpage.

Where an embodiment of a data processing method is provided according to one of the embodiments of the present invention, it should be noted that the steps illustrated in the flowchart of the figure may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that presented herein.

The method embodiments may be performed in a mobile terminal, a computer terminal or a similar computing device. Taking the example of the Mobile terminal running on the Mobile terminal, the Mobile terminal may be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, a game console, etc.

Fig. 1 is a block diagram of a hardware structure of a mobile terminal of a data processing method according to an embodiment of the present invention. As shown in fig. 1, the mobile terminal may include one or more (only one shown in fig. 1) processors 102 (the processors 102 may include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Digital Signal Processing (DSP) chip, a Microprocessor (MCU), a programmable logic device (FPGA), a neural Network Processor (NPU), a Tensor Processor (TPU), an Artificial Intelligence (AI) type processor, etc.) and a memory 104 for storing data. Optionally, the mobile terminal may further include a transmission device 106, an input/output device 108, and a display device 110 for communication functions. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration, and does not limit the structure of the mobile terminal. For example, the mobile terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.

The memory 104 may be used to store computer programs, for example, software programs and modules of application software, such as computer programs corresponding to the data processing method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, implementing the data processing method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the mobile terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.

The inputs in the input output Device 108 may come from a plurality of Human Interface Devices (HIDs). For example: keyboard and mouse, game pad, other special game controller (such as steering wheel, fishing rod, dance mat, remote controller, etc.). Some human interface devices may provide output functions in addition to input functions, such as: force feedback and vibration of the gamepad, audio output of the controller, etc.

The display device 110 may be, for example, a head-up display (HUD), a touch screen type Liquid Crystal Display (LCD), and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of the mobile terminal. In some embodiments, the mobile terminal has a Graphical User Interface (GUI) with which a user can interact by touching finger contacts and/or gestures on a touch-sensitive surface, where the human-machine interaction function optionally includes the following interactions: executable instructions for creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, emailing, call interfacing, playing digital video, playing digital music, and/or web browsing, etc., for performing the above-described human-computer interaction functions, are configured/stored in one or more processor-executable computer program products or readable storage media.

In the present embodiment, a data processing method operating in the mobile terminal is provided, and fig. 2 is a flowchart of a data processing method according to an embodiment of the present invention. As shown in fig. 2, the method comprises the steps of:

step S202, a first target object set is obtained based on a first trigger condition, wherein behavior data of a first target object in the first target object set meets the first trigger condition.

In the technical solution provided by step S202 of the present invention, when the behavior data of the first target object satisfies the first trigger condition, the first target object may be added into the first target object set, where the behavior data of the first target object may be real-time behavior data of a player, and the first target object set may be a target group targeted by a policy.

Optionally, the first trigger condition may be a real-time trigger condition, and supports a logical relationship combination of "and" or ", and may be set by itself according to a game rule, and if a grouping (optional) is selected, the behavior data of the users in the specific list is triggered when the real-time trigger condition is satisfied; if the blacklist is selected (optional), the triggering is not performed even if the user behavior data in the blacklist meets the real-time triggering condition.

For example, as shown in fig. 7(a), fig. 7(a) is another schematic diagram of configuring a real-time trigger condition and experimental test information on a front-end page according to an embodiment of the present invention, and for a virtual game role for which a login server is a new service official service, a virtual game role of an Internet Protocol (IP) is shielded, if real-time behavior data of a player meets a real-time trigger condition, then: and if the garden grade at the time of login is greater than 2 or the duty point player grade is greater than 2, the player is the target group of the strategy.

Step S204, the first target object set is divided into a plurality of sub-object sets.

In the technical solution provided in step S204 of the present invention, the real-time a/B test splitting method is used to divide the first target object set into a plurality of sub-object sets, wherein the plurality of sub-object sets may be a plurality of different experimental groups.

Optionally, the nature of the real-time a/B test offloading is to add a random a/B test code (abort _ id) field to a user list in the first target object set to ensure uniform offloading, where an a/B test offloading scheme may be set according to an actual situation, and is not limited specifically here.

Step S206, pushing the corresponding first target data to each sub-object set to obtain a plurality of pushing results, where the plurality of pushing results are in one-to-one correspondence with the plurality of sub-object sets.

In the technical solution provided in step S206 of the present invention, after the first target object set is divided into a plurality of sub object sets, the first target data corresponding to the first target object set is respectively pushed to each sub object set, so as to obtain a corresponding pushing result, where the first target data may be a material corresponding to the sub object set, and the pushing result may be a material conversion rate obtained after the first target data corresponding to the first target object set is pushed to the sub object set.

Alternatively, the first target data may include a push document, a push content, a push instruction, and the like, which is not limited herein.

Alternatively, the pushing result may be calculated by counting the number of exposure users and the number of click users of the material, for example, the conversion rate is equal to the number of click users/the number of exposure users.

Step S208, determining target policy data based on the plurality of pushing results, where the target policy data includes a second trigger condition and second target data, and the target policy data is used to indicate that the second target data is pushed to the second target object when the behavior data of the second target object in the second target object set satisfies the second trigger condition.

In the technical solution provided in step S208 of the present invention, according to the experiment termination condition of the service configuration, the push results corresponding to the multiple sub-object sets are automatically evaluated, the first target data corresponding to the sub-object set meeting the second trigger condition is used as the second target data, and the second target data is pushed to the second target object, where the second trigger condition is whether the conversion rate of the material is highest, and the second target object may be another user other than the sub-object set of the second trigger condition.

Alternatively, the experiment termination conditions may include: and (4) testing the total amount and the test deadline, and stopping the operation of the experiment strategy after the total amount or the test deadline is reached.

Through the above steps S202 to S208, a first target object set is obtained based on a first trigger condition, where behavior data of a first target object in the first target object set satisfies the first trigger condition; dividing a first target object set into a plurality of sub-object sets; pushing corresponding first target data to each sub-object set to obtain a plurality of pushing results, wherein the plurality of pushing results are in one-to-one correspondence with the plurality of sub-object sets; and determining target policy data based on the plurality of pushing results, wherein the target policy data comprises a second trigger condition and second target data, and the target policy data is used for indicating that the second target data is pushed to the second target object when the behavior data of the second target object in the second target object set meets the second trigger condition. That is to say, this application obtains first target object set based on first trigger condition to divide first target object set into a plurality of sub-object sets, finally to every sub-object set propelling movement corresponding first target data, obtain a plurality of propelling movement results, avoided obtaining the experimental effect that the user touched through manual, the manual best material of selection carries out final propelling movement, thereby can realize the purpose of retrieving the material effect in the short time, and then reached the technological effect who improves the efficiency that final strategy was formulated, the technical problem of the inefficiency of final strategy formulation has been solved.

The above method of this embodiment is further described below.

As an alternative implementation manner, in step S202, the first trigger condition is determined based on the content type of the first target data, where the first target data of different content types correspond to different first trigger conditions.

In this embodiment, the first trigger condition may be determined according to the content type of the first target data, and when the content type of the first target data changes, the first trigger condition may also be changed accordingly, so as to achieve the purpose of recovering the push result in a shorter time.

As an optional implementation manner, each push result is used to characterize a ratio of a number of first target objects, which receive and operate on first target data, in the corresponding sub-object set to a number of first target objects, which receive the first target data, in the sub-object set, and determine target policy data based on a plurality of push results, including: determining a target pushing result in the plurality of pushing results, wherein the proportion corresponding to the target pushing result is greater than the proportion corresponding to any one of the plurality of pushing results except the target pushing result; and determining target strategy data based on the target push result.

In this embodiment, for each sub-object set, a ratio of the number of first target objects, which operate on first target data, to the number of first target objects, which receive the first target data, in the sub-object set is calculated, ratios corresponding to push results of a plurality of sub-object sets are compared, a push result corresponding to a sub-object set with the highest corresponding ratio in the calculation results is determined as a target push result, and target policy data is determined based on the target push result, where the number of first target objects, which operate on the first target data, in the sub-object set may be the number of users, the number of first target objects, which receive the first target data, in the sub-object set may be the number of users, and the ratio corresponding to the push result may be a material conversion rate or a click rate.

Alternatively, the material conversion rate (click rate) is equal to the number of click users/the number of exposure users.

As an optional implementation, determining the target policy data based on the target push result includes: and determining the first target data corresponding to the target pushing result as second target data in the target strategy data to obtain the target strategy data.

In this embodiment, a target pushing result is obtained by calculating and comparing the pushing results of the multiple sub-object sets, and the first target data of the sub-object set corresponding to the target pushing result is determined as the second target data in the target policy data, where the second target data may be the material content with the highest material conversion rate, that is, the optimal material.

As an optional implementation manner, first original policy data is obtained, where the first original policy data includes a third trigger condition and third target data, and the first original policy data is used to indicate that when behavior data of a third target object in a third target object set meets the third trigger condition, the third target data is pushed to the third target object; determining first target data corresponding to the target pushing result as second target data in the target policy data to obtain the target policy data, including: and in the first original strategy data, updating the third target data into the first target data corresponding to the target pushing result, and determining the updated third target data into the second target data to obtain the target strategy data.

In this embodiment, first original policy data is obtained, in the first original policy data, third target data is updated to first target data corresponding to a target push result, and the updated third target data is determined to be second target data, so as to obtain target policy data, where the first original policy data may be a push-to-end policy to be updated, the third target data may be target data corresponding to a user under the push-to-end policy to be updated, and the target policy may be the updated push-to-end policy.

As an optional implementation manner, the sub-object set corresponding to the target pushing result is removed from the third target object set, so as to obtain the second target object set.

In this embodiment, the sub-object set that has been pushed by using the target policy in the third target object set is deleted to obtain a list corresponding to the final push policy, that is, the second target object set, and finally the final push policy is triggered and started.

Optionally, when the corresponding first target data is pushed to each sub-object set, a list which has been pushed is recorded, and the list can be used as a blacklist of a push-to-terminate policy, so that the optimal material on the push-to-terminate policy can be ensured, and the same user can not be reached any more.

As an optional implementation manner, the first trigger condition and the first target data are obtained from second original policy data, where the second original policy data is used to indicate that when the behavior data of the first target object in the first target object set satisfies the first trigger condition, the first target data is pushed to the first target object.

In this embodiment, a first trigger condition and first target data are obtained from second original policy data, and when behavior data of a first target object meets the first trigger condition, the first target data is pushed to the first target object, where the second original policy data may be experiment policy data, the behavior data of the first target object may be real-time behavior data of a player, and the first target object may be a target user of an experiment policy.

Optionally, the first trigger condition may be a real-time trigger condition, support and/or combination, and may be set by itself according to the game rule, and if grouping (optional) is selected, the behavior data of the users in the specific list is triggered when the real-time trigger condition is satisfied; if the blacklist is selected (optional), the triggering is not performed even if the user behavior data in the blacklist meets the real-time triggering condition.

As an optional implementation, dividing the first target object set into a plurality of sub-object sets includes one of: determining the identification of a first target object in a first target object set, and dividing the first target object set into a plurality of sub-object sets according to the identification of the first target object; and determining the identification of each sub-object set, and determining a first target object identified with the identification of the sub-object set as an element of the sub-object set to obtain a plurality of sub-object sets.

In this embodiment, the first target object set is divided into a plurality of sub-object sets, an identifier of a first target object in the first target object set may be determined randomly first, and then the first target object set is divided into the plurality of sub-object sets according to the identifier of the first target object, or an identifier of each sub-object set may be determined randomly first, and then the first target object identified with the identifier of the sub-object set is determined as an element of the sub-object set, so as to obtain the plurality of sub-object sets, where the identifier of the first target object may be a sequence number, and the identifier of the sub-object set may be a random number.

For example, the first target objects in the first target object set may be randomly numbered 0-99, and if the experimental strategy is divided into three experimental groups, 0-32 is experimental group 1, 33-65 is experimental group 2, and 66-99 is experimental group 3.

For another example, 1 to 3 random numbers may be randomly assigned to the first target objects in the first target object set, and the random numbers respectively correspond to three experimental groups: the random number 1 corresponds to the experiment group 1, the random number 2 corresponds to the experiment group 2, and the random number 3 corresponds to the experiment group 3, and then according to the random number of the first target object, the split sub-object list can be directly output, wherein the data format of the sub-object list may include: role account (role _ id), server (server), account information (account id) and test group code (attest _ id).

As an optional implementation, pushing the corresponding first target data to each sub-object set includes: and pushing first target data corresponding to the identification of each sub-object set to each sub-object set.

In this embodiment, after the push service takes the split list, the sub-object set corresponding to the split list may be found according to the test field of the list, and the corresponding material is selected according to the identifiers of different sub-object sets for pushing, where the identifier of the sub-object set may be an experimental group code (id).

As an optional implementation manner, in response to the target stop condition, the pushing of the corresponding first target data to each sub-object set is stopped.

In this embodiment, the policy evaluation module may stop pushing the corresponding first target data to each sub-object set according to a target stop condition, where the target stop condition may be an experiment termination condition.

Alternatively, the target stop condition may include: and (4) testing the total amount and the test deadline, and stopping the operation of the experiment strategy after the total amount or the test deadline is reached.

For example, assuming that the operation of the experimental strategy is finished at 10 points, the effect evaluation is performed after the service is set for 2 hours. The evaluation module will obtain the material effect data of each experimental group of the experimental strategy at 12 points.

In the embodiment, the problems that the push crowd is limited, the material recovery effect is poor, the trigger mechanism is not flexible enough and the like in the existing automatic experiment strategy push can be solved through the scheme, the technical effect of improving the final strategy making efficiency is further achieved, and the technical problem that the final strategy making efficiency is low is solved.

The technical solutions of the embodiments of the present invention are further described below with reference to preferred embodiments.

At present, in order to exert the life cycle value of a user to the maximum, in the operation of a game user, there are many scenes in which the user needs to be contacted so as to keep long-term contact with the user, for example, platform drainage, game maintenance, promotion of activity, user loss and recall, and common contact ways include: short messages, emails, phone calls, application push, etc. In the process of user touch, what material is used for touching the user is one of the core problems, and the conversion effect is often directly influenced by the quality of material selection.

In the related art, in the case of multiple materials, the most common practice is to perform a/B Test (Test) experiment, and manually select the optimal material for final pushing according to the experiment effect. The traditional A/B test lacks an automatic effect recovery link, so the automatic A/B test becomes the standard in the industry. Fig. 3 is a schematic diagram of a core logic for a/B test according to the related art, as shown in fig. 3, the core logic is: and for the target population, carrying out a small-flow experiment, tracking the conversion rate of each material in real time, and selecting the optimal material to carry out automatic incremental pushing. That is to say, in the prior art, a target population is divided into different experimental groups, different materials are pushed to the different experimental groups, that is, a small-flow a/B test experiment is performed, conversion effect data of each material is counted in real time on the downstream based on a buried point log, material effect data is obtained based on a set experiment termination condition, and an optimal material is selected for incremental pushing.

However, in the automatic a/B test experiment adopted in the prior art, because a target pushing crowd needs to be specified in advance (mostly, a user group is obtained based on a combined offline label), the experiment and the pushing crowd are limited, and when the user is offline, a lot of invalid issues are caused, and the experiment is forced to be performed only by increasing the duration of the experiment (which easily causes missing of gold time for pushing), or increasing the experiment crowd (which causes reduction of the number of people who finally push the best materials), and the material recovery effect is poor. In addition, the triggering mechanism of the method is not flexible enough, and only the user is pushed, and different types of materials cannot be triggered by different behaviors.

However, the present application provides a data processing method, which triggers push based on real-time real behavior of a user, and can solve the technical problems of limited push population, poor material recovery effect, and low efficiency of final policy making caused by an inflexible triggering mechanism in the existing automatic a/B test push

Next, a core module of an automatic a/B testing apparatus based on real-time user behavior in user reach according to an embodiment of the present application is described, as shown in fig. 4, where fig. 4 is a schematic diagram of a core module for automatic a/B testing according to an embodiment of the present invention, and the core module 400 includes: a user behavior real-time detection module 401, an effect real-time statistic module 404, and a policy evaluation module 403.

The user behavior real-time detection module 401 is connected to the effect real-time statistics module 404, and is responsible for detecting whether the user meets the trigger condition set by the service in real time according to the service configuration, if so, further determining whether the user is in the corresponding policy list, and if so, performing real-time a/B test shunting on the user.

Optionally, the real-time user behavior detection module 401 includes: the real-time log loading module 4011 is configured to load a real-time log stream generated by a user in a game process; the strategy configuration analysis module 4012 is configured to analyze the strategy configuration data in the experimental strategy automatically generated by the business front-end configuration real-time automatic a/B test strategy; and the policy list loading module 4013 is configured to load policy list data in the experimental policy automatically generated by the service front-end configuration real-time automatic a/B test policy, and distribute the cache loading list to generate the bloom filter.

And the effect real-time counting module 404 is connected with the user behavior real-time detection module 401 and the effect real-time counting module 404, and is used for counting the embedded point logs in real time, counting material conversion effects of different experimental groups, and writing the material conversion effects into a database for subsequent use. Optionally, the effect real-time statistics module selects a corresponding material for a push service based on the real-time distribution information sent by the user behavior real-time detection module, and provides a push list to the policy evaluation module.

Optionally, the effect real-time statistics module performs real-time statistics on material conversion effects of different experimental groups based on the buried point logs of the real-time statistics to obtain policy diversion effect data, and provides the policy diversion effect data for the policy evaluation module in real time.

And the policy evaluation module 403 is connected to the effect real-time statistics module 404, and is responsible for automatically evaluating the conversion effect of the material according to the service configuration, updating the material information and the list information of the push-to-end policy, and triggering the push-to-end policy to start.

Optionally, the policy evaluation module updates the material information and the list information of the push-to-end policy in real time according to the experiment cutoff condition (experiment cutoff condition and experiment maximum push amount) configured by the service, and when the experiment cutoff condition is met, updates the push-to-end policy based on the material information and the list information pushed by the effect real-time statistics module last time, triggers the push-to-end policy to be started, and enters real-time push based on the optimal material.

Optionally, the policy evaluation module may update the push list in real time for the push list provided by the push-to-finish policy filtering effect real-time statistics module.

Optionally, the policy evaluation module may process the policy splitting effect data provided by the effect real-time statistics module, and select an optimal material for the final push policy, where the optimal material may be a material with a highest conversion rate.

The following further introduces core steps of an automatic a/B testing method based on real-time user behaviors in user reach provided by an embodiment of the present application, where the steps include:

firstly, the business configures a real-time automatic A/B test strategy at the front end.

As shown in fig. 5, the service is mainly configured with real-time trigger conditions, experimental test information, material information, and the like at the front end. Fig. 5(a) is a schematic diagram of configuring real-time trigger conditions and experimental test information on a front-end page according to an embodiment of the present invention, and fig. 5(b) is a schematic diagram of configuring material information on the front-end page according to an embodiment of the present invention.

And the real-time trigger condition supports and/or combines the real-time tags which are successfully verified to form the real-time trigger condition. If grouping (optional) is selected, triggering is carried out when the behavior of the users of the specific list meets the real-time triggering condition. If the blacklist is selected (optional), the triggering is not performed even if the behavior of the user in the blacklist meets the triggering condition.

For example, as shown in fig. 7(a), fig. 7(a) is another schematic diagram of configuring real-time trigger conditions and experimental test information on a front-end page according to an embodiment of the present invention, and for a virtual game role for which a login server is a new service official service, a virtual game role of an Internet Protocol (IP) is shielded, and if a real-time behavior of a player, such as a garden level >2 at login or a duty-point player level >2, is a target group of a policy.

Optionally, the experimental test information of this embodiment mainly includes: the number of test groups, test comparison indexes, test comparison rules, test evaluation time, test total amount, test cut-off time and the like.

For example, as shown in fig. 7, fig. 7(a) is another schematic diagram of configuring real-time trigger conditions and experimental test information on a front-end page according to an embodiment of the present invention, a target group of a policy is divided into three test groups, effect comparison is performed 2 hours after the policy is released (total test amount or test deadline is reached), and a material with a maximum hit rate of god H5 is used as an optimal material.

Material information, as shown in fig. 5(b), fig. 5(b) is a schematic diagram of configuring material information on a front end page according to an embodiment of the present invention, and filling material contents corresponding to each test experiment group respectively, where the material includes, but is not limited to: push documents, push content, push instructions, etc.

For example, as shown in fig. 7(b), fig. 7(b) is another schematic diagram of configuring material information on a front-end page according to an embodiment of the present invention, which better attracts a user to jump to a god page after clicking, compared with three benefit center instructions (each of which essentially triggers a different benefit presentation interface), thereby completing the stream guidance of a game to the god software.

And secondly, the front end writes the configuration information into a database through an interface provided by the rear end, and automatically generates an experiment strategy and a final push strategy on a page.

As shown in fig. 6, fig. 6 is a schematic diagram of an experimental policy and a final push policy of an automatic a/B test according to an embodiment of the present invention, where the experimental policy is started, but the final push policy lacks optimal material information and blacklist information, and the start is triggered only after information is supplemented by a policy evaluation module.

And thirdly, after the experimental strategy is started, detecting which users meet the triggering condition of the strategy in real time according to the configuration of the service based on a distributed open source computing (flink) user real-time behavior detection module facing data stream processing and batch data processing.

The main logic of the method is as follows: reading a game log stream from a theme (kafka topic) of a corresponding game in real time based on an open source stream processing platform; loading the configuration of the real-time strategy and the real-time conditions configured by the strategy from a strategy configuration table; if the real-time strategy selects grouping or blacklist (optional), loading a corresponding strategy related list from a Distributed File System (HDFS for short), and traversing to generate a bloom filter (based on bitmap storage, the use of a memory can be greatly reduced); detecting whether the behaviors of the users meet the trigger conditions set by the strategy or not in real time and whether the behaviors are in an appointed list or not; outputting a list meeting the requirements, wherein the data format of the list is mainly as follows: namely, role account (role id), server (server), and account information (account id).

And fourthly, carrying out real-time A/B test shunting on users meeting the triggering conditions, and transmitting the users to the push service in real time through the open source flow processing platform.

And (3) carrying out real-time A/B test shunting, wherein the essence is to add a random A/B test code (attest _ id) field to the list to ensure uniform shunting.

For example, a/B test shunting schemes may be various, such as: random numbers of 0-99 are randomly drawn, if the experimental strategy is divided into three experimental groups, 0-32 is experimental group 1, 33-65 is experimental group 2, and 66-99 is experimental group 3. For another example: randomly adding 1-3 random numbers to the list, respectively corresponding to the three experimental groups, outputting the list after shunting, wherein the list data format is mainly as follows: role account (role _ id), server (server), account information (account id) and test group code (attest _ id).

And fifthly, after the push service takes the list, different experimental groups take corresponding materials to push according to the A/B test coding field of the list, and simultaneously record the list which is pushed.

After pushing, the user can be touched, and the behavior conditions of exposure, click and the like of the user can be recorded in a buried point log of a downstream system, wherein a list which is pushed is required to be recorded, and the list can be used as a blacklist of a final push strategy so as to ensure that the optimal material on the final push strategy can not be touched to the same user, otherwise, the user experience can be influenced.

And sixthly, the effect real-time counting module can count the buried point logs of the pushing records in real time, count the material conversion effects of different experimental groups, and store the material conversion effects into the database for the evaluation module to use.

The push service can call an interface provided by the game, push messages to users in the game, and push different material contents for users in different groups. After receiving the push message, the user generates an exposure log, and if the user clicks, a click log is generated.

According to the comparison indexes selected by the experiment strategies, a distributed open source calculation program is started, the log condition is consumed in real time, the effect data is summarized in real time according to the buried point condition, and the effect data is written into a database for storage.

According to the exposure log and the click log, the conversion rates of different materials can be calculated in real time, and then the conversion rate data of each material is written into a database for storage, so that the evaluation module can take the material conversion rate data to evaluate and select the best conversion rate.

For example, as shown in fig. 7(b), fig. 7(b) is a schematic diagram of material information configured on a front-end page by another service according to an embodiment of the present invention, and the comparative index is the god H5 conversion rate, so the number of exposure users and the number of click users of different experimental group materials need to be counted, and then calculated as: the conversion rate is equal to the number of clicks/the number of exposure users.

And seventhly, the strategy evaluation module automatically evaluates the conversion effect of the material according to the experiment termination condition of the service configuration, updates the material information and the list information of the final push strategy and triggers the start of the final push strategy.

The experimental strategy termination conditions mainly comprise: and (4) testing the total amount and the test deadline, and stopping the operation of the experiment strategy after the total amount and the test deadline are reached.

And (5) assuming that the operation of the experiment strategy at 10 points is finished, and performing effect evaluation after the service is set for 2 hours. The evaluation module obtains the material effect data of each experimental group of the experimental strategy at 12 points; obtaining material configuration with optimal effect according to the obtained effect data and the set comparison rule (generally maximum or minimum); and updating the optimal material configuration to a final push strategy, taking a push list pushed by the experimental strategy as a blacklist of the final push strategy, and finally triggering and starting the final push strategy.

And eighthly, starting a final pushing strategy, and entering real-time pushing based on the optimal materials.

The application brings the following beneficial effects: triggering pushing based on real-time real behaviors of a user, and defining different triggering conditions according to different types of materials; the effect of the materials can be recovered in a shorter time, the optimal materials are automatically selected for release, and the conversion effect of the strategy is improved; improve the retention rate and the payment rate of the user, and the like.

The automatic A/B testing method and device based on the real-time behavior of the user in the user reach of the embodiment comprise the following steps: an automatic A/B testing device based on real-time behaviors of a user in user touch mainly comprises three modules: the system comprises a user behavior real-time detection module, an effect real-time statistic module and a strategy evaluation module; the business configures a real-time automatic A/B test strategy at the front end; the front end writes the configuration information into a database based on an interface provided by the back end, and automatically generates an experiment strategy and a final push strategy on a page; starting an experimental strategy, and detecting users meeting the trigger condition of the strategy in real time by a user real-time behavior detection module according to the configuration of the service; for users meeting the triggering conditions, carrying out real-time A/B test shunting and transmitting the shunting to a push service in real time; after the push service gets the list, finding out the corresponding experimental group according to the A/B test coding field of the list, selecting corresponding materials for pushing aiming at different experimental groups, and simultaneously recording the list which is pushed; the embedded point logs of the pushing records are counted in real time through an effect real-time counting module, the material conversion effects of different experimental groups are counted, and the material conversion effects are written into a database; the strategy evaluation module automatically evaluates the conversion effect of the material according to the experiment termination condition of the service configuration, updates the material information and the list information of the push-to-finish strategy and triggers the push-to-finish strategy to start; the method has the advantages that a final push strategy is started, based on the optimal materials, links of list detection and pushing are entered, so that the effect of recovering the materials in a shorter time is achieved, the optimal materials are automatically selected for incremental delivery, the conversion effect of the strategy is improved, the problems that in the pushing of the existing automatic experiment strategy, the pushing crowd is limited, the material recovery effect is poor, the triggering mechanism is not flexible enough and the like are solved, and the technical problem that the efficiency of final strategy formulation is low is further solved.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

In this embodiment, a data processing apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and details are not repeated for what has been described. As used hereinafter, the terms "unit", "module" and "modules" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 8 is a schematic diagram of a data processing apparatus according to an embodiment of the present invention, and as shown in fig. 8, the data processing apparatus 800 may include: an acquisition unit 801, a dividing unit 802, a pushing unit 803, and a determination unit 804.

An obtaining unit 801, configured to obtain a first target object set based on a first trigger condition, where behavior data of a first target object in the first target object set satisfies the first trigger condition.

A dividing unit 802, configured to divide the first target object set into a plurality of sub-object sets.

The pushing unit 803 is configured to push the corresponding first target data to each sub-object set to obtain multiple pushing results, where the multiple pushing results are in one-to-one correspondence with the multiple sub-object sets.

The determining unit 804 is configured to determine target policy data based on the multiple pushing results, where the target policy data includes a second trigger condition and second target data, and the target policy data is used to indicate that the second target data is pushed to a second target object when behavior data of the second target object in the second target object set satisfies the second trigger condition.

Optionally, the apparatus further comprises: the first determining unit is used for determining a first trigger condition based on the content type of the first target data, wherein the first target data of different content types correspond to different first trigger conditions.

Optionally, the determining unit 804 includes: the first determining module is used for determining a target pushing result in the plurality of pushing results, wherein the proportion corresponding to the target pushing result is greater than the proportion corresponding to any one of the plurality of pushing results except the target pushing result; and the second determining module is used for determining target strategy data based on the target pushing result.

Optionally, the second determining module includes: and the second sub-determining module is used for determining the first target data corresponding to the target pushing result as second target data in the target strategy data so as to obtain the target strategy data.

Optionally, the apparatus further comprises: the first obtaining unit is configured to obtain first original policy data, where the first original policy data includes a third trigger condition and third target data, and the first original policy data is used to indicate that when behavior data of a third target object in a third target object set meets the third trigger condition, the third target data is pushed to the third target object.

Optionally, the second sub-determining module is further configured to determine, as second target data in the target policy data, the first target data corresponding to the target push result, so as to obtain the target policy data, by: and in the first original strategy data, updating the third target data into the first target data corresponding to the target pushing result, and determining the updated third target data into the second target data to obtain the target strategy data.

Optionally, the apparatus further comprises: and the second obtaining unit is used for obtaining a first trigger condition and first target data from second original strategy data, wherein the second original strategy data is used for indicating that the first target data is pushed to the first target object when the behavior data of the first target object in the first target object set meets the first trigger condition.

Optionally, the dividing unit 802 includes: the dividing module is used for determining the identification of a first target object in the first target object set and dividing the first target object set into a plurality of sub-object sets according to the identification of the first target object; and the third determining module is used for determining the identifier of each sub-object set, and determining the first target object identified with the identifier of the sub-object set as an element of the sub-object set to obtain a plurality of sub-object sets.

Optionally, the pushing unit 803 includes: and the pushing module is used for pushing the first target data corresponding to the identification of each sub-object set to each sub-object set.

In the data processing apparatus of this embodiment, the obtaining unit obtains the first target object set based on the first trigger condition, the dividing unit divides the first target object set into a plurality of sub-object sets, the pushing unit pushes corresponding first target data to each sub-object set to obtain a plurality of pushing results, and the determining unit determines target policy data based on the plurality of pushing results, thereby achieving the effect of recovering materials in a shorter time and automatically selecting optimal materials for incremental delivery, improving the conversion effect of policies, solving the problems of limited pushing population, poor material recovery effect, inflexible trigger mechanism, and the like in the existing automatic experimental policy pushing, further realizing the technical effect of improving the efficiency of final policy making, and solving the technical problem of low efficiency of final policy making.

It should be noted that, the above units and modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the units and the modules are all positioned in the same processor; alternatively, the units and modules may be located in different processors in any combination.

Embodiments of the present invention also provide a non-volatile storage medium having a computer program stored therein, wherein the computer program is configured to perform the steps of any of the above method embodiments when executed.

Alternatively, in the present embodiment, the above-mentioned nonvolatile storage medium may be configured to store a computer program for executing the steps of:

s1, acquiring a first target object set based on a first trigger condition, wherein the behavior data of a first target object in the first target object set meets the first trigger condition; dividing a first target object set into a plurality of sub-object sets;

s2, pushing the corresponding first target data to each sub-object set to obtain a plurality of pushing results, wherein the pushing results are in one-to-one correspondence with the sub-object sets;

and S3, determining target strategy data based on the plurality of pushing results, wherein the target strategy data comprises a second trigger condition and second target data, and the target strategy data is used for indicating that the second target data is pushed to a second target object when the behavior data of the second target object in the second target object set meets the second trigger condition.

Optionally, in this embodiment, the nonvolatile storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.

Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.

Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.

Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:

Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

1. A data processing method, comprising:

acquiring a first target object set based on a first trigger condition, wherein behavior data of a first target object in the first target object set meets the first trigger condition;

dividing the first target object set into a plurality of sub-object sets;

pushing corresponding first target data to each sub-object set to obtain a plurality of pushing results, wherein the pushing results are in one-to-one correspondence with the sub-object sets;

determining target policy data based on the plurality of pushing results, wherein the target policy data comprises a second trigger condition and second target data, and the target policy data is used for indicating that the second target data is pushed to a second target object in a second target object set when behavior data of the second target object meets the second trigger condition.

2. The method of claim 1, further comprising:

determining the first trigger condition based on a content type of the first target data, wherein the first target data of different content types correspond to different first trigger conditions.

3. The method of claim 1, wherein each of the push results is used for characterizing a ratio of a number of the first target objects in the corresponding set of sub-objects that receive the first target data and operate on the first target data to a number of the first target objects in the set of sub-objects that receive the first target data, and determining target policy data based on the push results comprises:

determining a target pushing result in the plurality of pushing results, wherein the proportion corresponding to the target pushing result is greater than the proportion corresponding to any pushing result except the target pushing result in the plurality of pushing results;

and determining the target strategy data based on the target push result.

4. The method of claim 3, wherein determining the target policy data based on the target push result comprises:

and determining the first target data corresponding to the target pushing result as the second target data in the target policy data to obtain the target policy data.

5. The method of claim 4,

the method further comprises the following steps: acquiring first original strategy data, wherein the first original strategy data comprises a third trigger condition and third target data, and the first original strategy data is used for pushing the third target data to a third target object when behavior data of the third target object in a third target object set meets the third trigger condition;

determining the first target data corresponding to the target pushing result as the second target data in the target policy data to obtain the target policy data, including: in the first original policy data, updating the third target data to the first target data corresponding to the target pushing result, and determining the updated third target data to be the second target data to obtain the target policy data.

6. The method of claim 5, further comprising:

and removing the sub-object set corresponding to the target pushing result from the third target object set to obtain the second target object set.

7. The method of claim 1, further comprising:

and acquiring the first trigger condition and the first target data from second original policy data, wherein the second original policy data is used for indicating that the first target data is pushed to the first target object when the behavior data of the first target object in the first target object set meets the first trigger condition.

8. The method of claim 1, wherein dividing the first set of target objects into a plurality of sets of sub-objects comprises one of:

determining the identifier of the first target object in the first target object set, and dividing the first target object set into a plurality of sub-object sets according to the identifier of the first target object;

and determining the identifier of each sub-object set, and determining the first target object identified with the identifier of the sub-object set as an element of the sub-object set to obtain a plurality of sub-object sets.

9. The method of claim 8, wherein pushing the corresponding first target data to each of the sub-object sets comprises:

pushing the first target data corresponding to the identification of each sub-object set to each sub-object set.

10. The method according to any one of claims 1 to 9, further comprising:

and in response to a target stop condition, stopping pushing the corresponding first target data to each sub-object set.

11. A data processing apparatus, comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a first target object set based on a first trigger condition, and the behavior data of a first target object in the first target object set meets the first trigger condition;

a dividing unit, configured to divide the first target object set into a plurality of sub-object sets;

the pushing unit is used for pushing corresponding first target data to each sub-object set to obtain a plurality of pushing results, wherein the plurality of pushing results are in one-to-one correspondence with the plurality of sub-object sets;

a determining unit, configured to determine target policy data based on the multiple pushing results, where the target policy data includes a second trigger condition and second target data, and the target policy data is used to indicate that the second target data is pushed to a second target object in a second target object set when behavior data of the second target object satisfies the second trigger condition.

12. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, controls an apparatus in which the computer-readable storage medium is located to carry out the method of any one of claims 1 to 10.

13. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to be executed by the processor to execute the computer program to perform the method of any of claims 1 to 10.