Method and apparatus for determining information push object, computer device and storage medium

Abstract

The application relates to a method and device for determining an information push object, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: obtaining object information of a candidate object and an object matching condition for the candidate object; selecting a first target object from the candidate object, wherein the object information of the first target object meets the object matching condition; determining the first target object as a push object of target information; in the case that the push object has updated object information, selecting a second target object from the push object, wherein the updated object information of the second target object meets an object elimination condition; and canceling the second target object as the push object of the target information. The above method can automatically determine the push object of the target information, and is beneficial to improving the data processing efficiency of the information push object determination process.

Description

Technical Field

[0001] This application relates to the field of computer application technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for determining information push targets. Background Technology

[0002] With the rapid development of the Internet in recent years and the increasing popularity of Internet products, in order to gain more user traffic and increase revenue and profits, Internet product developers usually push target information related to Internet products to information push recipients in order to promote the Internet products.

[0003] Traditional methods for determining the target audience for push notifications begin with the internet product developer's marketing team submitting a push notification request to data analysts. The data analysts then use SQL (Structured Query Language) to match the request with target audiences, returning a CSV (Comma-Separated Values) file containing the target audience's information to the marketing team. Finally, the marketing team sends the CSV file to the push notification platform, which then uses this information to send push notifications. As such, traditional methods rely on human-computer interaction, and the lengthy data processing consumes significant computational resources, resulting in low data processing efficiency in the target audience determination process. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the efficiency of data processing for determining information push targets, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for determining the recipients of information push notifications. The method includes:

[0006] Obtain the object information of the candidate object, as well as the object matching conditions for the candidate object;

[0007] From the candidate objects, a first target object whose object information satisfies the object matching condition is selected;

[0008] The first target object is identified as the target information push object;

[0009] If there is updated object information in the push object, a second target object whose updated object information meets the object removal condition is selected from the push object;

[0010] cancel the second target object as the push object of the target information.

[0011] In a second aspect, the present application provides a device for determining a push object of information, and the device comprises:

[0012] an obtaining module, configured to obtain object information of a candidate object and an object matching condition for the candidate object;

[0013] a first target object determining module, configured to filter a first target object from the candidate object, wherein the object information of the first target object satisfies the object matching condition;

[0014] an information push object determining module, configured to determine the first target object as a push object of target information;

[0015] a second target object determining module, configured to filter a second target object from the push object, wherein the second target object satisfies an object elimination condition of updated object information of the push object;

[0016] the information push object determining module is further configured to cancel the second target object as the push object of the target information.

[0017] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0018] obtaining object information of a candidate object and an object matching condition for the candidate object;

[0019] filtering a first target object from the candidate object, wherein the object information of the first target object satisfies the object matching condition;

[0020] determining the first target object as a push object of target information;

[0021] filtering a second target object from the push object, wherein the second target object satisfies an object elimination condition of updated object information of the push object;

[0022] canceling the second target object as the push object of the target information.

[0023] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0024] obtain object information of a candidate object and an object matching condition for the candidate object;

[0025] select, from the candidate objects, a first target object whose object information satisfies the object matching condition;

[0026] determine the first target object as a push object of target information;

[0027] in a case where the push object has updated object information, select, from the push object, a second target object whose updated object information satisfies an object elimination condition;

[0028] cancel the second target object as the push object of the target information.

[0029] In a fifth aspect, the present application further provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the following steps:

[0030] obtain object information of a candidate object and an object matching condition for the candidate object;

[0031] select, from the candidate objects, a first target object whose object information satisfies the object matching condition;

[0032] determine the first target object as a push object of target information;

[0033] in a case where the push object has updated object information, select, from the push object, a second target object whose updated object information satisfies an object elimination condition;

[0034] cancel the second target object as the push object of the target information.

[0035] The above information push object determination method and device, computer equipment, computer readable storage medium and computer program product, first obtain object information of a candidate object and an object matching condition for the candidate object, then select, from the candidate objects, a first target object whose object information satisfies the object matching condition, and determine the first target object as a push object of target information, in a case where the push object has updated object information, select, from the push object, a second target object whose updated object information satisfies an object elimination condition, and cancel the second target object as the push object of the target information, which can automatically determine the push object of the target information, and is conducive to improving the data processing efficiency of the information push object determination process. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1An application environment diagram of the method for determining the information push object in one embodiment;

[0037] Figure 2 A flowchart of the method for determining the information push object in one embodiment;

[0038] Figure 3 A flowchart of the method for determining the information push object in another embodiment;

[0039] Figure 4 An application environment diagram of the method for determining the information push object in another embodiment;

[0040] Figure 5 A flowchart of the method for determining the information push object in yet another embodiment;

[0041] Figure 6 A flowchart of the method for determining the information push object in still another embodiment;

[0042] Figure 7 A process diagram of the method for determining the push object of the backflow advertisement in one embodiment;

[0043] Figure 8 An interface diagram of the configuration of the object matching condition in one embodiment;

[0044] Figure 9 An interface diagram of the model screening condition setting in another embodiment;

[0045] Figure 10 An interface diagram of the display of the object information in one embodiment;

[0046] Figure 11 A structure block diagram of the device for determining the information push object in one embodiment;

[0047] Figure 12 An internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0048] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0049] In one embodiment, the method for determining the information push object provided by the present application can be applied to, for example, Figure 1The application environment shown. Among them, the first terminal 102 and the second terminal 104 can communicate with the server 106 through the network. The data storage system can store the data required by the server 106 to process. The data storage system can be integrated on the server 106, or placed on the cloud or other servers. Specifically, the developer can send the object matching condition for the candidate object to the server 106 through the first terminal 102, and the second terminal 104 is the associated terminal of the candidate object. In the process of determining the information push object, the server 106: obtains the object information of the candidate object and the object matching condition for the candidate object; from the candidate object, filters out the first target object whose object information satisfies the object matching condition; determines the first target object as the push object of the target information; in the case that the push object exists updated object information, from the push object, filter out the second target object whose updated object information satisfies the object elimination condition; cancel the second target object as the push object of the target information.

[0050] Among them, the terminal 102 includes but is not limited to mobile phone, computer, smart voice interaction device, smart home appliance, vehicle-mounted terminal, aircraft, etc. The server 106 can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and big data and artificial intelligence platforms, etc. Basic cloud computing services. The first terminal 102 and the second terminal 104 and the server 106 can be directly or indirectly connected through wired or wireless communication, which is not limited in the present application.

[0051] It should be noted that the object information (including but not limited to identification information, feature information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0052] In one embodiment, as Figure 2 shown, a method for determining an information push object is provided. In this embodiment, the method is applied to the server 106 for illustration, and it can be understood that the method can also be applied to the first terminal 102, and can also be applied to a system including the first terminal 102 and the server 106, and realized through the interaction of the first terminal 102 and the server 106. In this embodiment, the method includes the following steps:

[0053] Step S201, obtaining the object information of the candidate object and the object matching condition for the candidate object.

[0054] The candidate object refers to an object that is determined as a candidate in the process of determining the information push object, i.e., the purpose of determining the information push object is to select the push object of the target information from multiple candidate objects. The candidate object can refer to a historical user of a target Internet product associated with the target information, or can refer to a user who has not used the target Internet product. The target Internet product can specifically refer to an application program, a content interaction platform, a service webpage, etc.

[0055] The object information of the candidate object refers to information used to represent the characteristics of the candidate object, and can specifically include object characteristic information, device characteristic information, and behavior characteristic information, etc. The object characteristic information can include object identification, gender, age, education, city, etc. The device characteristic information can include device identification, operating system type, operating system version identification, and device memory, etc. The behavior characteristic information can include behavior identification, behavior type, behavior time, and product type of an Internet product associated with the behavior, etc. The behavior type can specifically include login behavior, consumption behavior, message browsing behavior, message publishing behavior, virtual object operation behavior, etc. The behavior time can specifically include behavior start time, behavior end time, and behavior frequency within a preset time range, etc.

[0056] Further, the object matching condition for the candidate object is the basis for selecting the push object of the target information from multiple candidate objects. The object matching condition can refer to at least one characteristic information in the object information satisfying a characteristic matching condition corresponding to the characteristic information, for example, the object matching condition can include at least one of the characteristic matching conditions such as "device memory is greater than memory threshold", "age is within the age threshold range", "behavior time of the last login behavior for the target Internet product is outside the time threshold range", etc.

[0057] Specifically, the server can obtain the object information of the candidate object from the second terminal operated by the candidate object based on the communication network, and obtain the object matching condition for the candidate object from the first terminal of the developer. The specific manner of the server obtaining the object information of the candidate object and the object matching condition for the candidate object can be active acquisition or passive reception.

[0058] Step S202: From the candidate objects, a first target object whose object information satisfies the object matching condition is selected.

[0059] Step S203: The first target object is determined as the push object of the target information.

[0060] The first target object refers to a candidate object whose object information satisfies the object matching condition. The push object of the target information refers to an object to which the target information is to be pushed. The specific type of the target information is not unique, for example, it can be a combination of one or more of text, picture, voice and video. Specifically, the server can filter the first target object whose object information satisfies the object matching condition from the candidate objects according to the object information of the candidate objects and the object matching condition for the candidate objects, and determine the first target object as the push object of the target information.

[0061] It can be understood that, since the specific content of the object matching condition is not unique, the specific process of filtering the first target object whose object information satisfies the object matching condition from the candidate objects by the server is also not unique.

[0062] In an embodiment, step S202 includes extracting feature information from the object information of the candidate objects, and filtering the first target object whose feature information satisfies the object matching condition from the candidate objects.

[0063] The feature information refers to the object information associated with the object matching condition. For example, the object matching condition is "device memory is greater than the memory threshold", and the corresponding feature information is "device memory". It can be understood that the number of feature information is consistent with the number of object information associated with the object matching condition, and the object matching condition can be associated with one or more object information. For example, the object matching condition is "device memory is greater than the memory threshold and age is within the age threshold range", and the corresponding feature information includes "device memory" and "age".

[0064] Specifically, the developer can set the corresponding object matching condition according to the characteristics of the target Internet product. Taking the case of the target Internet product being an application program as an example. The object matching condition corresponding to the application program with regional characteristics can be set as "the city where the user is located satisfies the target city condition"; the object matching condition corresponding to the game application program can be set as "age is within the age threshold range". On this basis, the server can determine the feature information associated with the object matching condition according to the obtained object matching condition, extract the feature information from the object information of the candidate objects, compare the feature information with the object matching condition, and finally filter the first target object whose feature information satisfies the object matching condition from the candidate objects based on the comparison result.

[0065] In this embodiment, the feature information associated with the object matching condition is first extracted from the object information of the candidate objects, and then the first target object whose feature information satisfies the object matching condition is filtered from the candidate objects. The algorithm is simple, which is conducive to further improving the data processing efficiency, and the developer can flexibly set the object matching condition according to the characteristics of the target Internet product, which is conducive to improving the accuracy of the matching result.

[0066] In another embodiment, the object matching condition comprises that the predicted push effect meets an expected push effect. In the case of this embodiment, step S202 comprises: performing push effect analysis on the object information of the candidate objects to obtain predicted push effects of the candidate objects; and determining the candidate objects whose predicted push effects meet the expected push effect as the first target objects.

[0067] The expected push effect can comprise at least one of predicted reflow data meeting an expected reflow condition and predicted retention data meeting an expected retention condition.

[0068] Reflow refers to a phenomenon that a lost user who does not use a target Internet product in a period of time reuses the target Internet product. The predicted reflow data can comprise a predicted reflow probability of a single candidate object and a predicted reflow object number or a predicted reflow rate of a candidate object set composed of multiple candidate objects. The predicted reflow rate of the candidate object set refers to a ratio of the predicted reflow object number in the candidate object set to a total number of candidate objects in the candidate object set. The predicted reflow object number can refer to candidate objects in the candidate object set whose predicted reflow probability meets a reflow probability condition. Taking the predicted reflow data as the predicted reflow probability of a single candidate object as an example, the expected reflow condition can refer to that the predicted reflow probability is greater than or equal to a reflow probability threshold, or that the predicted reflow probability is in the top 5%, 10%, or 15%, and the like.

[0069] Retention refers to a phenomenon that a user continues to use a target Internet product after starting to use the target Internet product for a period of time. The predicted retention data can comprise a predicted retention probability of a single candidate object in a preset time and a predicted retention object number or a predicted retention rate of a candidate object set composed of multiple candidate objects in the preset time. The predicted retention rate of the candidate object set refers to a ratio of the predicted retention object number in the candidate object set in the preset time to a total number of candidate objects in the candidate object set. The predicted retention object number can refer to candidate objects in the candidate object set whose predicted retention probability meets a retention probability condition. The preset time can be a day, a week, a month, or the like. Correspondingly, the predicted retention probability can be a predicted day retention probability, a predicted week retention probability, or a predicted month retention probability, and the like. Taking the predicted retention data as the predicted seven-day retention probability of a single candidate object as an example, the expected retention condition can refer to that the predicted seven-day retention probability is greater than or equal to a retention probability threshold, or that the predicted seven-day retention probability is in the top 5%, 10%, or 15%, and the like.

[0070] Specifically, the server can perform push effect analysis on the object information of the candidate object, obtain a predicted push effect of the candidate object, and determine the candidate object whose predicted push effect meets the expected push effect as the first target object. In some specific embodiments, the server can perform machine learning on the object information and the push effect of a sample object marked with an actual push effect, train a neural network model for push effect analysis, and use the neural network model to perform push effect analysis on the object information of the candidate object to obtain the predicted push effect of the candidate object.

[0071] In this embodiment, the candidate object whose predicted push effect meets the expected push effect is determined as the first target object, which can help to screen the first target object from the perspective of optimizing the information push effect when the developer cannot define the characteristic information directly associated with the object matching condition, which not only helps to expand the application scenarios of the determination method of the information push object, but also helps to improve the information push effect.

[0072] In yet another embodiment, step S202 includes: extracting characteristic information from the object information of the candidate object, and screening a first candidate target object whose characteristic information meets a characteristic matching condition from the candidate object; performing push effect analysis on the object information of the first candidate target object to obtain a predicted push effect of the first candidate target object; and determining the first candidate target object whose predicted push effect meets the expected push effect as the first target object.

[0073] Wherein, the specific definitions of the characteristic information and the expected push effect are described above, and will not be repeated here. The characteristic matching condition refers to a matching condition directly associated with the characteristic information. The characteristic matching condition can be associated with one or more characteristic information.

[0074] Specifically, the object matching condition can include that the characteristic information meets the characteristic matching condition and the predicted push effect meets the expected push effect. After the server obtains the characteristic matching condition and the expected push effect, the server first determines the characteristic information associated with the characteristic matching condition, then extracts the characteristic information from the object information of the candidate object, compares the characteristic information with the characteristic matching condition, and screens a first candidate target object whose characteristic information meets the characteristic matching condition from the candidate object based on the comparison result. On this basis, the server further performs push effect analysis on the object information of the first candidate target object to obtain a predicted push effect of the first candidate target object, and finally determines the first candidate target object whose predicted push effect meets the expected push effect as the first target object. Similarly, the server can obtain the predicted push effect of the first candidate target object based on the pre-trained neural network model.

[0075] In this embodiment, the candidate object whose feature information satisfies the feature matching condition and whose predicted push effect satisfies the expected push effect is determined as the first target object, the first target object can be determined in combination with the developer demand and the information push effect, which is beneficial to further improve the accuracy of the first target object and further improve the information push effect.

[0076] In step S209, in the case where the push object has updated object information, the second target object whose updated object information satisfies the object elimination condition is filtered out from the push object.

[0077] In step S210, the push object of the second target object as the target information is cancelled.

[0078] The updated object information refers to the object information that is updated compared with the object information that is acquired last time and used to determine the first target object. The object elimination condition is the basis for selecting the second target object from the plurality of push objects. The object elimination condition can be set in correspondence with the object matching condition, for example, when the object matching condition is “the device memory is greater than the memory threshold value”, the object elimination condition can be “the device memory is less than or equal to the memory threshold value”, in this case, the updated object information refers to the feature information that is associated with both the object matching condition and the object elimination condition; the object elimination condition can also be irrelevant to the object matching condition, for example, when the object matching condition is “the device memory is greater than the memory threshold value”, the object elimination condition can be “there is updated behavior feature information for the target Internet product”, in this case, the updated object information refers to the feature information associated with the object elimination condition.

[0079] Specifically, in the process of determining the push object by the server and pushing the target information to the push object, the object information of the push object can change. For example, the device associated with the push object can have a reduced memory due to the installation of a new application, or the push object has an associated behavior of the target Internet product. In the case where the push object has updated object information, it can lead to a situation where the push object is not suitable for information push, and if the push object is not updated, it can affect the push effect of the target information. For example, in the case where the push object has an associated behavior of the target Internet product, it means that the push object has used the target Internet product, and it is unnecessary to push the target information associated with the target Internet product to the push object. Based on this, in the case where the push object has updated object information, the server acquires the updated object information, and filters out the second target object whose updated object information satisfies the object elimination condition from the push object, and cancels the push object of the second target object as the target information. It can be understood that before step S209, the server also needs to determine the object elimination condition, which can be set by the developer, that is, the server can acquire the object elimination condition from the first terminal.

[0080] The method for determining the information push object, first acquires object information of a candidate object and object matching conditions for the candidate object, then screens a first target object from the candidate object, the object information of which meets the object matching conditions, and determines the first target object as the push object of the target information, in the case that the push object has updated object information, screens a second target object from the push object, the updated object information of which meets the object elimination conditions, and cancels the second target object as the push object of the target information, which can automatically determine the push object of the target information, and is beneficial to improve the data processing efficiency of the information push object determination process. Further, in the case that the push object has updated object information, the push object of the target information is also eliminated based on the updated object information of the push object, which can dynamically adjust the push object of the target information according to the actual situation, and is beneficial to improve the information push effect.

[0081] In one embodiment, as shown in Figure 3 The method for determining the information push object further includes: step S304, sending the object information corresponding to the push object to the information push platform to instruct the information push platform to perform object recognition and filling based on the object information, and determine the target push object of the target information.

[0082] The information push platform refers to a platform that has a certain audience group and can push information to the audience group. For example, the application programs associated with the information push platform A include application program a, application program b and application program c, and the users of the application program a, the application program b and the application program c are the audience of the information push platform A and can be the target push object of the information push platform A. The information push platform A can push the target information to the target push object when the target push object opens or uses the above-mentioned application programs. Further, the information push platform can be a device in the server that is different from the information push object determination device and pushes information based on the push object. In some specific embodiments, the information push platform can also be another server independent of the server. In the case of this embodiment, as shown in Figure 4 The application environment of the method for determining the information push object provided by the present application can further include an information push platform 108. The information push platform 108 can communicate with the server 106 through the network.

[0083] Specifically, as shown in Figure 4For example, after determining the push object, the server 106 sends object information corresponding to the push object to the information push platform 108, and the information push platform 108 identifies available objects within the audience group of the information push platform 108 from the push object according to the audience group, estimates the filling rate of the available objects, determines a target push object based on the filling rate maximization principle, and pushes target information to the target push object.

[0084] It should be noted that the step S304 can be performed after the step S203, or can be performed after the step S210, or can be performed after both the step S203 and the step S210. In the case that the step S304 is performed after the step S203, the server sends object information of the push object satisfying the object matching condition to the information push platform; in the case that the step S304 is performed after the step S210, the server can send object information of a second target object satisfying the object elimination condition in the current push object to the information push platform, or can obtain an updated push object by eliminating the second target object on the basis of the current push object, and send object information of the updated push object to the information push platform.

[0085] In one embodiment, sending the object information corresponding to the push object to the information push platform comprises: determining push configuration information based on the object information of the push object, generating a push request comprising at least the push configuration information, and sending the push request to the information push platform.

[0086] The push configuration information comprises object information of the push object, target information, and a push time, etc. The object information of the push object can comprise a device identifier of the push object. The push request is used to instruct the information push platform to determine a target push object of the target information based on object identification and filling based on the object information. Specifically, the server determines push configuration information based on the object information of the push object, generates a push request comprising at least the push configuration information, and sends the push request to the information push platform. Sending the object information to the information push platform in the form of a request can associate multiple push objects with the same push request, which can facilitate subsequent statistics and analysis, such as statistics of push effects for the push request, or display of object information of the target push object for the push request.

[0087] In the above embodiments, after determining the push object, the object information corresponding to the push object is also sent to the information push platform, and the information push platform determines the target push object, which can reduce the work burden of the server and is beneficial to further improve the work efficiency.

[0088] In one embodiment, as shown in Figure 5 the determination method of the information push object further comprises:

[0089] Step S504, in response to the information processing operation triggered by the push object for the target information, obtaining the target behavior information corresponding to the information processing operation;

[0090] Step S505, determining the target behavior information as the updated object information matched by the push object.

[0091] In the case of this embodiment, since the push object has updated object information, as shown in Figure 5 Step S209 is updated to step S509: from the push object, filtering out the second target object whose updated object information satisfies the object elimination condition.

[0092] The information processing operation triggered by the target information can refer to the information processing operation triggered by the displayed target information after the target information is pushed to the push object. For example, the information processing operation triggered after the push object clicks the target information, or the information processing operation triggered automatically in the case where the push object does not close the target information. The information processing operation is usually associated with a target Internet product, such as a link to a certain page in a target application.

[0093] Specifically, the server obtains the target behavior information corresponding to the information processing operation triggered by the push object for the target information, and determines the target behavior information as the updated object information matched by the push object.

[0094] In the above embodiment, after the target information is pushed to the push object, the target behavior information associated with the target information is determined as the updated object information matched by the push object, and the updated object information is used to determine the second target object, which is equivalent to dynamically adjusting the push object based on the feedback of the push of the target information, which is beneficial to improve the accuracy of the push object.

[0095] In one embodiment, please continue to refer to Figure 5 The determination method of the information push object further includes:

[0096] Step S506, extracting the time data carried in the updated object information.

[0097] Specifically, since the updated object information is behavior feature information, as described above, the behavior feature information can include behavior time as a feature information, and therefore the updated object information carries time data associated with the target behavior. The time data can include the behavior start time and the behavior end time of the target behavior. Specifically, the server can extract the time data carried in the updated object information according to the character type of the time data.

[0098] Step S507, determining the time information of the information processing operation associated with the updated object information according to the time data.

[0099] The time information of the information processing operation includes a trigger time and a duration. Specifically, the target behavior information corresponds to the information processing operation triggered for the target information, and the target behavior information is matched with the updated object information. Therefore, the server can determine the time information of the information processing operation corresponding to the updated object information according to the time data carried in the updated object information. For example, the server can determine the trigger time of the behavior start time as the trigger time of the corresponding information processing operation, and can determine the time difference between the behavior start time and the behavior end time as the duration of the corresponding information processing operation.

[0100] In step S508, if the time information meets the time condition, it is determined that the updated object information meets the object elimination condition.

[0101] The time condition can include at least one of a trigger time condition and a duration condition. Specifically, the server matches the time information of the information processing operation with the time condition, judges whether the time information meets the time condition, and determines that the updated object information meets the object elimination condition if the time information meets the time condition. It can be understood that if the time information does not meet the time condition, it is determined that the updated object information does not meet the object elimination condition.

[0102] In one embodiment, the time information includes the trigger time of the information processing operation. In the case of this embodiment, step S508 includes: if the trigger time of the information processing operation meets the trigger time condition, it is determined that the updated object information meets the object elimination condition.

[0103] The trigger time condition can mean that the difference between the trigger time and the current time is less than a time threshold, or that the difference between the trigger time and the current time is less than or equal to a time threshold, or that the trigger time is within a set time range. Specifically, if the trigger time of the information processing operation meets the trigger time condition, it means that the target Internet product has been exposed to the push object. On this basis, if the push object has not used the target Internet product, it is possible that the push object is not interested in the target Internet product, and the expected effect of continuing to push the target information is poor. If the push object has used the target Internet product, the purpose of pushing the target information has been achieved, and there is no need to continue to push the target information to the push object. Based on this, the server determines that the updated object information meets the object elimination condition if the trigger time of the information processing operation meets the trigger time condition.

[0104] In another embodiment, the time information includes a duration of the information processing operation. In the case of this embodiment, step S508 includes: determining that the updated object information satisfies the object elimination condition in a case where the duration of the information processing operation satisfies a duration condition.

[0105] The duration condition can refer to a duration greater than a duration threshold, or a duration greater than or equal to a duration threshold. Specifically, in a case where the duration of the information processing operation satisfies the duration condition, it indicates that the target Internet product is continuously exposed to the push object. On this basis, if the push object does not use the target Internet product, it is possible that the push object is not interested in the target Internet product, and the expected effect of continuing to push the target information is poor. If the push object uses the target Internet product, the purpose of pushing the target information has been achieved, and there is no need to continue to push the target information to the push object. Based on this, the server determines that the updated object information satisfies the object elimination condition in a case where the duration of the information processing operation satisfies the duration condition.

[0106] In the above embodiments, based on the time information of the information processing operation triggered by the target information, the updated object information is determined to satisfy the object elimination condition in a case where the time information satisfies the time condition, which is beneficial to improve the accuracy of the push object and further improve the information pushing effect.

[0107] In one embodiment, as shown in Figure 6 the method for determining an information push object includes:

[0108] Step S601: obtaining object information of a candidate object and an object matching condition for the candidate object;

[0109] Step S602: extracting feature information from the object information of the candidate object, and selecting a first candidate target object that satisfies a feature matching condition from the candidate object based on the feature information;

[0110] Step S603: performing push effect analysis on the object information of the first candidate target object to obtain a predicted push effect of the first candidate target object;

[0111] Step S604: determining the first candidate target object whose predicted push effect satisfies an expected push effect as a first target object;

[0112] Step S605: determining the first target object as a push object of the target information;

[0113] Step S606: determining push configuration information based on the object information of the push object, generating a push request including at least the push configuration information, and sending the push request to an information push platform;

[0114] Step S607, in response to the information processing operation triggered by the push object for the target information, obtaining the target behavior information corresponding to the information processing operation;

[0115] Step S608, determining the target behavior information as the updated object information matched by the push object;

[0116] Step S609, extracting the time data carried in the updated object information;

[0117] Step S610, according to the time data, determining the time information of the information processing operation associated with the updated object information;

[0118] Step S611, in the case where the trigger time of the information processing operation meets the trigger time condition, determining that the updated object information meets the object elimination condition;

[0119] Step S612, from the push object, screening out the second target object whose updated object information meets the object elimination condition;

[0120] Step S613, canceling the push object of the second target object as the target information.

[0121] The application also provides an application scenario of information push for a target service webpage, which applies the above-mentioned method for determining the information push object. In the application scenario of information push, the server obtains the object information of the candidate object and the object matching condition for the candidate object; from the candidate object, the first target object whose object information meets the object matching condition is screened out; the first target object is determined as the push object of the target information associated with the target service webpage; in the case where the push object has updated object information, from the push object, the second target object whose updated object information meets the object elimination condition is screened out; the second target object is canceled as the push object of the target information.

[0122] The application also provides an application scenario of backflow advertisement push for a target application program, which applies the above-mentioned method for determining the information push object. In the application scenario of backflow advertisement push, as Figure 7As shown, the developer sends object matching conditions (i.e., Include list filtering conditions) and object exclusion conditions (i.e., Exclude list filtering conditions) for the candidate object to the filtering server through the front end according to the data obtained by operation and burying. The candidate object is the redirected audience of the target application, i.e., the object that has used the target application in the past but no longer uses the target application. The object matching conditions can specifically include one or more of the following: the existence of historical uninstallation behavior, device memory greater than the installation package size of the target application, the existence of usage records of the same type of application as the target application, the upgrade mode and number of times during the use of the target application meet the upgrade conditions, etc. The object exclusion conditions can be that the behavior data of the candidate object meets the active condition, for example, the candidate object has used the target application on the same day, and exists in the active full table of the target application on the same day.

[0123] In one embodiment, as shown, Figure 8 the developer can set feature matching conditions such as operating system type (Operating System), operating system version (OS Versions), device type (Devices), and last login time (Days since last login) for the candidate object through the configuration interface to complete the configuration of the object matching conditions. At the same time, the developer can also select push channels (such as platform A and platform B), target push addresses, push languages, etc. on this interface.

[0124] In one embodiment, the object matching conditions include that the predicted reflow probability of a single candidate object meets the reflow probability condition, and the reflow probability condition is that the predicted reflow probability is within the top percentage range. As shown, Figure 9 the developer can set the top percentage (for example, 5%) on the model filtering condition setting interface to determine the predicted reflow probability condition of the object matching conditions. Further, the developer clicks Figure 9 “save” to complete the configuration of the object matching conditions, and sends both the object matching conditions and the object exclusion conditions to the filtering server.

[0125] The screening server performs data screening based on the screening condition to obtain a matching list (include list) as a push object and an exclusion list (exclude list) excluding the push object, and exports to the same database to obtain a device ID list meeting the object matching condition, i.e., table A, and a device ID of a device using the target application on the same day, i.e., table B. It should be noted that, in the process of performing the first data screening for the target application, since the candidate objects are all redirection audiences of the target application, there is no case meeting the active condition, and therefore the table B generated at this time is an empty set. The screening server repeats the above screening process every day to update the device IDs in tables A and B, i.e., the table B obtained in the next screening is the object meeting the active condition, e.g., the device ID of a device using the target application on the same day, obtained by screening the previous table A.

[0126] Further, the screening server polls the database every 12 hours, removes the historical data, and calls a configuration program provided by the information push platform server to send a push request to the information push platform server. The push request carries device ID and information push platform account information, etc. Further, the push request can carry a set number of device IDs each time, and generate a corresponding push request identifier.

[0127] Then, the information push platform server identifies and fills the device ID, data fuses the identified matching object and the exclusion object, determines the final device ID of the target redirection audience (Combine List), and pushes the backflow advertisement to the target redirection audience. The screening server queries whether the push request corresponding to the push request identifier is identified every 15 minutes, and after the request processing is completed, obtains the object information of the target redirection object, and sends the object information to the front end, and generates a corresponding audience list identifier (Audience ID). As shown in Figure 10 The front end displays the object information according to the audience list identifier, which specifically includes the audience list identifier, the category, the operating system, the push channel, the size of the generated crowd package, and the current state, etc. Among them, the audience list identifier can include characters representing the object matching condition, for example, “redirect-A-D” can represent the redirection object with operating system D and push channel A. In addition, the crowd package refers to a list that can deliver object information, and the size of the crowd package refers to the number of objects contained in the crowd package.

[0128] The screening of the target redirection audience is automatically completed by the server, which can reduce the workload of the developer, improve the operation efficiency, and reduce the operation burden; in the process of pushing the backflow advertisement, the target redirection object is dynamically adjusted based on the use of the target application by the target redirection audience, which can reduce the backflow unit price and save the delivery cost; the object matching condition and the object exclusion condition are reasonably set, which can ensure the accuracy of the target redirection audience and improve the delivery effect of the backflow advertisement.

[0129] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0130] Based on the same inventive concept, the embodiments of the present application also provide a determination device of an information push object for implementing the determination method of the information push object as described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more determination device embodiments of the information push object provided below can refer to the limitations of the determination method of the information push object in the above text, which will not be described here again.

[0131] In one embodiment, as shown in Figure 11 a determination device 1100 of an information push object is provided, comprising: an acquisition module 1101, a first target object determination module 1102, an information push object determination module 1103, and a second target object determination module 1104, wherein:

[0132] The acquisition module 1101 is configured to acquire object information of a candidate object and an object matching condition for the candidate object.

[0133] The first target object determination module 1102 is configured to screen a first target object whose object information satisfies the object matching condition from the candidate object.

[0134] The information push object determination module 1103 is configured to determine the first target object as a push object of target information.

[0135] The second target object determination module 1104 is configured to, in a case where the push object has updated object information, filter a second target object from the push object, the updated object information of the second target object satisfying an object elimination condition.

[0136] The information push object determination module 1103 is further configured to cancel the second target object as the push object of the target information.

[0137] In an embodiment, the information push object determination apparatus 1100 further includes a sending module configured to send the object information corresponding to the push object to the information push platform, so as to instruct the information push platform to perform object identification and filling based on the object information, and determine the target push object of the target information.

[0138] In an embodiment, the sending module is specifically configured to determine push configuration information based on the object information of the push object, generate a push request including at least the push configuration information, and send the push request to the information push platform, where the push request is used to instruct the information push platform to perform object identification and filling based on the object information, and determine the target push object of the target information.

[0139] In an embodiment, the first target object determination module 1102 is specifically configured to extract feature information from the object information of the candidate object, filter a first candidate target object from the candidate object, the feature information of the first candidate target object satisfying a feature matching condition, perform push effect analysis on the object information of the first candidate target object, and obtain a predicted push effect of the first candidate target object, and determine the first candidate target object whose predicted push effect satisfies an expected push effect as the first target object.

[0140] In another embodiment, the object matching condition includes that the predicted push effect satisfies the expected push effect. In the case of this embodiment, the first target object determination module 1102 is specifically configured to perform push effect analysis on the object information of the candidate object, obtain a predicted push effect of the candidate object, and determine the candidate object whose predicted push effect satisfies the expected push effect as the first target object.

[0141] In an embodiment, the obtaining module 1101 is further configured to, in response to an information processing operation triggered by the push object for the target information, obtain target behavior information corresponding to the information processing operation. In the case of this embodiment, the information push object determination apparatus 1100 further includes an updated object information determination module configured to determine the target behavior information as the updated object information matched by the push object.

[0142] In an embodiment, the information push object determination apparatus 1100 further includes a time data extraction module configured to extract time data carried in the updated object information; a time information determination module configured to determine time information of the information processing operation associated with the updated object information according to the time data; and a rejection determination module configured to determine that the updated object information satisfies the object rejection condition when the time information satisfies a time condition.

[0143] In an embodiment, the time information includes a trigger time of the information processing operation. In this embodiment, the rejection determination module is specifically configured to determine that the updated object information satisfies the object rejection condition when the trigger time of the information processing operation satisfies a trigger time condition.

[0144] In another embodiment, the time information includes a duration of the information processing operation. In this embodiment, the rejection determination module is specifically configured to determine that the updated object information satisfies the object rejection condition when the duration of the information processing operation satisfies a duration condition.

[0145] The modules in the information push object determination apparatus described above can be implemented in whole or in part by software, hardware, or a combination thereof. The modules described above can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to the modules described above.

[0146] In an embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 12 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store object information. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with terminals outside through a network connection. The computer program is executed by the processor to implement an information push object determination method. Those skilled in the art can understand that Figure 12The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. Specifically, the computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0147] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0148] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implements the steps in the above method embodiments when executed by a processor.

[0149] In one embodiment, a computer program product is provided, including a computer program, and the computer program implements the steps in the above method embodiments when executed by a processor.

[0150] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0151] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0152] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method of determining an information push object, characterized by, The method comprises: obtaining object information of candidate objects and object matching conditions for the candidate objects; the candidate objects refer to redirected audiences of a target internet product associated with target information; wherein the redirected audiences refer to objects that have used the target internet product in the past but no longer use the target internet product; from the candidate objects, filtering out first target objects whose object information satisfies the object matching conditions; determining the first target objects as push objects of the target information, and obtaining a matching list of push objects; in the case where the push objects have updated object information, from the push objects, filtering out second target objects whose updated object information satisfies an object exclusion condition; the updated object information includes target behavior information of the push objects triggered by an information processing operation for the target information; the information processing operation is associated with the target internet product; the object exclusion condition includes that behavior data of the push objects for the target internet product satisfies an active condition; canceling the second target objects as push objects of the target information, and obtaining an exclusion list of push objects; after data fusion of matching objects in the matching list obtained in the same round of selection and exclusion objects in the exclusion list, the matching objects and the exclusion objects are used to determine target push objects for the target information in the round; wherein the exclusion list of the first round is an empty set, and the exclusion list of each round other than the first round is filtered out in the matching list of the previous round.

2. The method of claim 1, wherein, The method further comprises: extracting feature information from the object information of the candidate objects, and filtering out first candidate target objects whose feature information satisfies a feature matching condition from the candidate objects; performing push effect analysis on the object information of the first candidate target objects, and obtaining predicted push effects of the first candidate target objects; determining the first candidate target objects whose predicted push effects satisfy expected push effects as first target objects.

3. The method of claim 1, wherein, The object matching condition includes that the predicted push effects satisfy the expected push effects; the method further comprises: performing push effect analysis on the object information of the candidate objects, and obtaining predicted push effects of the candidate objects; determining the candidate objects whose predicted push effects satisfy expected push effects as first target objects.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: in response to an information processing operation triggered by the push objects for the target information, obtaining target behavior information corresponding to the information processing operation; determining the target behavior information as updated object information matched by the push objects.

5. The method of claim 4, wherein, The method further comprises: extracting time data carried in the updated object information; determining time information of an information processing operation associated with the updated object information according to the time data; in the case where the time information satisfies a time condition, determining that the updated object information satisfies an object exclusion condition.

6. The method of claim 5, wherein, The time information includes a trigger time of the information processing operation; The determining that the updated object information meets the object elimination condition in the case that the time information meets the time condition includes: The determining that the updated object information meets the object elimination condition in the case that the trigger time of the information processing operation meets a trigger time condition.

7. The method of claim 5, wherein, The time information includes a duration of the information processing operation; The determining that the updated object information meets the object elimination condition in the case that the time data meets the time condition includes: The determining that the updated object information meets the object elimination condition in the case that the duration of the information processing operation meets a duration condition.

8. The method of claim 1, wherein, The method further includes: sending object information corresponding to the push object to an information push platform, to instruct the information push platform to perform object identification and filling based on the object information, and determine a target push object of the target information.

9. The method of claim 8, wherein, The sending of the object information corresponding to the push object to the information push platform includes: determining push configuration information based on the object information of the push object, generating a push request including at least the push configuration information; sending the push request to the information push platform; the push request is used to instruct the information push platform to perform object identification and filling based on the object information, and determine a target push object of the target information.

10. An apparatus for determining a push object, the apparatus comprising: a push object determination module configured to determine a push object based on a push object determination rule. The apparatus includes: an acquisition module configured to acquire object information of a candidate object and an object matching condition for the candidate object; the candidate object refers to a redirected audience of a target internet product associated with target information; the redirected audience refers to an object that has used the target internet product in the past but no longer uses the target internet product; a first target object determination module configured to filter, from the candidate object, a first target object for which the object information meets the object matching condition; an information push object determination module configured to determine the first target object as a push object of the target information, and obtain a matching list of push objects; a second target object determination module configured to filter, from the push object, a second target object for which updated object information meets an object elimination condition, in a case that the push object has the updated object information; the updated object information includes target behavior information of an information processing operation triggered by the push object for the target information; the information processing operation is associated with the target internet product; and the object elimination condition includes that behavior data of the push object for the target internet product meets an active condition; the information push object determination module is further configured to cancel the second target object as the push object of the target information, and obtain an elimination list of push objects; the matching objects in the matching list and the eliminated objects in the elimination list obtained in the same round of screening are fused to determine a target push object of the target information in the round; the elimination list of the first round is an empty set, and the elimination list of each round other than the first round is filtered from a matching list of a previous round.

11. The apparatus of claim 10, wherein, The information push object determination module is specifically configured to: extract feature information from the object information of the candidate object, and screen a first candidate target object from the candidate object, wherein the feature information of the first candidate target object satisfies a feature matching condition; perform push effect analysis on the object information of the first candidate target object to obtain a predicted push effect of the first candidate target object; determine the first candidate target object as a first target object when the predicted push effect of the first candidate target object satisfies an expected push effect.

12. The apparatus of claim 10, wherein, The object matching condition includes that the predicted push effect satisfies the expected push effect; and the information push object determination module is specifically configured to: perform push effect analysis on the object information of the candidate object to obtain a predicted push effect of the candidate object; determine the candidate object as a first target object when the predicted push effect of the candidate object satisfies an expected push effect.

13. The apparatus of any one of claims 10 to 12, wherein, The acquisition module is further configured to: acquire target behavior information corresponding to an information processing operation triggered by the push object for the target information in response to the information processing operation; The information push object determination module further includes an updated object information determination module configured to determine the target behavior information as updated object information matched by the push object.

14. The apparatus of claim 13, wherein, The device further includes: a time data extraction module configured to extract time data carried in the updated object information; a time information determination module configured to determine time information of an information processing operation associated with the updated object information according to the time data; a rejection judgment module configured to determine that the updated object information satisfies an object rejection condition when the time information satisfies a time condition.

15. The apparatus of claim 14, wherein, The time information includes a trigger time of the information processing operation; and the rejection judgment module is specifically configured to: determine that the updated object information satisfies an object rejection condition when the trigger time of the information processing operation satisfies a trigger time condition.

16. The apparatus of claim 14, wherein, The time information includes a duration of the information processing operation; and the rejection judgment module is specifically configured to: determine that the updated object information satisfies an object rejection condition when the duration of the information processing operation satisfies a duration condition.

17. The apparatus of claim 10, wherein, The device further includes a sending module configured to: send object information corresponding to the push object to an information push platform to instruct the information push platform to perform object recognition and filling based on the object information, and determine a target push object of the target information.

18. The apparatus of claim 17, wherein, The sending module is specifically configured to: determine push configuration information based on the object information of the push object, generate a push request including at least the push configuration information, and send the push request to an information push platform; the push request is used to instruct the information push platform to perform object recognition and filling based on the object information, and determine a target push object of the target information. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 9. 19.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-18. The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 9.

20. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 9.

21. A computer program product comprising a computer program, characterized in that, ​

Images