Push method and device, electronic equipment and storage medium

Abstract

Embodiments of the present disclosure provide a pushing method and device, electronic equipment and a storage medium. The method comprises: obtaining a target category to which a target object belongs, and a first quantity of target objects belonging to each target category; obtaining behavior data of a target user on target objects of each target category within a first preset time period; determining an interest degree of the target user on target objects of each target category according to the behavior data; adjusting the quantity of target objects of each target category pushed to the target user within a second preset time period according to the first quantity and the interest degree of the same target category, to obtain an adjusted quantity; and pushing target objects of each target category to the target user within the second preset time period according to the adjusted quantity. Therefore, embodiments of the present disclosure can push according to the personalized needs of different users, thereby improving the accuracy of the push to a certain extent.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to a pushing method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the continuous progress of science and technology, various application programs emerge in an endless stream. Among them, the pushing service for application programs has gradually matured. For example, after a short video application is started, some short videos will be pushed to the user for the user to watch; after a shopping application program is started, some goods will be pushed to the user for the user to browse.

[0003] Among them, the pushing service of the application program at present is often according to the classification of the user, and different types of objects are pushed to users of different categories. However, each user as a separate individual has its special browsing demand, so that only according to the user classification for pushing, the personalized demand of the user cannot be met. SUMMARY

[0004] In order to solve the technical problems recorded in the background art, the embodiments of the present disclosure provide a pushing method, device, electronic equipment and storage medium, and the technical scheme of the present disclosure is as follows:

[0005] According to the first aspect of the embodiments of the present disclosure, a pushing method is provided, comprising:

[0006] obtaining a target category to which a target object belongs, and a first number of the target objects belonging to each of the target categories, wherein the target object includes an object pushed to a target user within a first preset time period;

[0007] obtaining behavior data of the target user on the target object of each of the target categories within the first preset time period;

[0008] determining an interest degree of the target user on the target object of each of the target categories according to the behavior data;

[0009] adjusting the number of the target object of each of the target categories pushed to the target user within a second preset time period according to the first number and the interest degree belonging to the same target category, to obtain an adjusted number;

[0010] pushing the target object of each of the target categories to the target user within the second preset time period according to the adjusted number.

[0011] Optionally, the behavior data of the target object of a target category includes at least one behavior feature of the target object of the target category and data of each of the behavior features;

[0012] The determining of the interest degree of the target user in the target object of each of the target categories according to the behavior data comprises:

[0013] The following process is sequentially executed when i takes each integer value from 1 to N:

[0014] According to the data of each behavior feature belonging to the i-th target category, a SHAP value of each behavior feature belonging to the i-th target category is calculated by using a Shapley Additive explanations (SHAP) method;

[0015] According to the SHAP value of each behavior feature of the i-th target category, the interest degree of the target user in the target object of the i-th target category is determined.

[0016] Wherein, N is the number of the target categories.

[0017] Optionally, the determining of the interest degree of the target user in the target object of the i-th target category according to the SHAP value of each behavior feature of the i-th target category comprises:

[0018] According to the pre-determined weight of each behavior feature, a weighted average value of the SHAP values of the behavior features belonging to the i-th target category is calculated, to obtain the interest degree of the target user in the target object of the i-th target category.

[0019] Optionally, the adjusting of the number of the target objects of each of the target categories pushed to the target user in the second preset time period according to the first number and the interest degree of the same target category comprises:

[0020] According to the first number, a SHAP value of the target category to which the first number belongs is calculated.

[0021] In a case where the SHAP value of a first category is less than a first preset threshold value, and the interest degree of the first category is greater than or equal to a second preset threshold value, the number of the target objects of the first category pushed to the target user in the second preset time period is increased, the first category being any one of the target categories.

[0022] In a case where the SHAP value of a second category is greater than or equal to the first preset threshold value, and the interest degree of the second category is less than the second preset threshold value, the number of the target objects of the second category pushed to the target user in the second preset time period is reduced, the second category being any one of the target categories.

[0023] Optionally, the target object includes a video, and the behavior feature of the target object of the third category includes at least one of the following:

[0024] a cumulative duration of the video of the third category browsed by the target user within the first preset time period;

[0025] a target number of the video of the third category browsed by the target user within the first preset time period;

[0026] a target number of preset operations of the video of the third category performed by the target user within the first preset time period;

[0027] The preset operation includes at least one of a collection operation, a sharing operation, a comment operation, and a download operation.

[0028] The third category is any one of the target categories.

[0029] Optionally, in a case where the behavior feature of the target object of the third category includes the cumulative duration, the method further includes:

[0030] In a case where the SHAP value of the cumulative duration is less than or equal to a third preset threshold, the number of first preset videos pushed to the target user within the second preset time period is increased, and the first preset video includes a video belonging to the third category and having a duration greater than a first preset duration.

[0031] Optionally, in a case where the behavior feature of the target object of the third category includes the target number, the method further includes:

[0032] In a case where the SHAP value of the target number is less than or equal to a fourth preset threshold, the number of second preset videos pushed to the target user within the second preset time period is increased, and the second preset video includes a video belonging to the third category and having a duration less than a second preset duration.

[0033] Optionally, the method further includes:

[0034] According to a predetermined weight value of each target category, a weighted average value of the SHAP value of each target category is calculated to obtain a first parameter;

[0035] In a case where the first parameter is less than a fifth preset threshold, a preset prompt information is displayed.

[0036] The preset prompt information is used to indicate that a strategy of pushing the target object to the target user needs to be adjusted.

[0037] According to a second aspect of the embodiments of the present disclosure, a pushing device is provided, the device comprising:

[0038] a category information obtaining module configured to obtain target categories to which target objects belong, and a first number of the target objects belonging to each of the target categories, wherein the target objects include objects pushed for a target user in a first preset time period;

[0039] a behavior data obtaining module configured to obtain behavior data of the target user on the target objects of each of the target categories in the first preset time period;

[0040] an interest degree determining module configured to determine an interest degree of the target user on the target objects of each of the target categories according to the behavior data;

[0041] a first pushing number adjusting module configured to adjust a number of the target objects of each of the target categories pushed for the target user in a second preset time period according to the first number and the interest degree of the target objects of the same target category, to obtain an adjusted number;

[0042] a pushing module configured to push the target objects of each of the target categories for the target user in the second preset time period according to the adjusted number.

[0043] Optionally, the behavior data of the target objects of one of the target categories includes at least one behavior feature of the target objects of the target category and data of each of the behavior features;

[0044] The interest degree determining module is specifically configured to:

[0045] the following processes are sequentially executed when i takes each integer value from 1 to N:

[0046] calculate a SHAP value of a Shapley Additive exPlanations (SHAP) method of each behavior feature belonging to the i-th target category according to data of each behavior feature belonging to the i-th target category;

[0047] determine the interest degree of the target user on the target objects of the i-th target category according to the SHAP value of each behavior feature of the i-th target category;

[0048] wherein N is a number of the target categories.

[0049] Optionally, when determining the interest degree of the target user to the target object of the i-th target category according to the SHAP value of each behavior feature of the i-th target category, the interest degree determining module is specifically configured to:

[0050] According to the predetermined weight of each behavior feature, a weighted average value of the SHAP values of the behavior features belonging to the i-th target category is calculated to obtain the interest degree of the target user to the target object of the i-th target category.

[0051] Optionally, the first push quantity adjusting module is specifically configured to:

[0052] According to the first quantity, the SHAP value of the target category to which the first quantity belongs is calculated;

[0053] In the case where the SHAP value of the first category is less than a first preset threshold, and the interest degree belonging to the first category is greater than or equal to a second preset threshold, the number of target objects of the first category pushed to the target user in the second preset time period is increased, the first category being any one of the target categories;

[0054] In the case where the SHAP value of the second category is greater than or equal to the first preset threshold, and the interest degree belonging to the second category is less than the second preset threshold, the number of target objects of the second category pushed to the target user in the second preset time period is reduced, the second category being any one of the target categories.

[0055] Optionally, the target object includes a video, and the behavior feature of the target object of the third category includes at least one of the following:

[0056] The cumulative duration of the videos of the third category browsed by the target user in the first preset time period;

[0057] The target number of videos of the third category browsed by the target user in the first preset time period;

[0058] The target number of preset operations of the videos of the third category performed by the target user in the first preset time period;

[0059] Wherein, the preset operation includes at least one of the following: a collection operation, a sharing operation, a comment operation, and a download operation;

[0060] The third category is any one of the target categories.

[0061] Optionally, in a case where the behavior feature of the target object of the third category includes the cumulative duration, the apparatus further includes:

[0062] The second push quantity adjustment module is configured to, in a case where the SHAP value of the cumulative duration is less than or equal to a third preset threshold, increase the quantity of first preset videos pushed to the target user in the second preset time period, the first preset videos including videos belonging to the third category and having a duration greater than a first preset duration.

[0063] Optionally, in a case where the behavior feature of the target object of the third category includes the target quantity, the apparatus further includes:

[0064] The third push quantity adjustment module is configured to, in a case where the SHAP value of the target quantity is less than or equal to a fourth preset threshold, increase the quantity of second preset videos pushed to the target user in the second preset time period, the second preset videos including videos belonging to the third category and having a duration less than a second preset duration.

[0065] Optionally, the apparatus further includes:

[0066] The parameter calculation module is configured to calculate a weighted average value of the SHAP values of the target categories according to the weight values of the target categories, to obtain a first parameter.

[0067] The prompt module is configured to, in a case where the first parameter is less than a fifth preset threshold, display preset prompt information.

[0068] The preset prompt information is used to indicate that the strategy of pushing the target objects to the target user needs to be adjusted.

[0069] According to a third aspect of embodiments of the present disclosure, an electronic device is provided, and the electronic device includes:

[0070] a processor;

[0071] a memory for storing instructions executable by the processor;

[0072] The processor is configured to execute the instructions to implement the push method provided by the present disclosure.

[0073] According to a fourth aspect of embodiments of the present disclosure, a computer-readable storage medium is provided, and when instructions in the storage medium are executed by a processor of an electronic device, the electronic device implements the push method provided by the present disclosure.

[0074] According to a fifth aspect of the embodiments of the present disclosure, a computer program product is provided, comprising computer programs / instructions, which, when executed by a processor, implement the push method provided by the present disclosure.

[0075] Compared with the prior art, the present application has the following advantages:

[0076] The technical solution provided by the embodiments of the present disclosure can obtain the target categories to which the target objects pushed for the target user in the first preset time period and the first quantities of the target objects belonging to each target category, and obtain the behavior data of the target user on the target objects of each target category in the first preset time period, so as to determine the interest degree of the target user on the target objects of each target category according to the behavior data, and then adjust the quantities of the target objects of each target category pushed for the target user in the second preset time period according to the first quantities and the interest degrees of the target objects of the same target category, obtain the adjusted quantities, and push the target objects of each target category for the target user in the second preset time period according to the adjusted quantities.

[0077] It can be seen that, in the technical solution provided by the embodiments of the present disclosure, the interest degree of the user on the target objects of a category is determined according to the behavior data of the user on the target objects of the category, so as to adjust the quantity of the target objects of the category pushed for the user in the second preset time period according to the interest degree and the quantity of the target objects of the category pushed for the user in the first preset time period. Therefore, the technical solution provided by the embodiments of the present disclosure combines the push situation of the target objects of each category with the actual interest degree of the user on the target objects of each category, so as to push according to the individualized needs of different users, and thus the accuracy of the push is improved to a certain extent, and the problem that the existing push method cannot meet the individualized needs of the user is solved.

[0078] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0079] Figure 1 is a flowchart of a push method according to an exemplary embodiment;

[0080] Figure 2 is a flowchart of another push method according to an exemplary embodiment;

[0081] Figure 3 is a schematic diagram of a specific implementation of a push method according to an exemplary embodiment;

[0082] Figure 4 is a block diagram of a push device according to an exemplary embodiment;

[0083] Figure 5 is a block diagram of an electronic device according to an exemplary embodiment;

[0084] Figure 6 is a block diagram of another electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0085] In order for those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings.

[0086] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein. The implementation described in the following exemplary embodiments does not represent all implementations consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0087] In order to solve the problem that the existing push method cannot meet the personalized needs of users, the embodiments of the present disclosure provide a push method, device, system, electronic device and storage medium.

[0088] According to a first aspect of the embodiments of the present disclosure, a push method is provided, as shown in Figure 1 The push method can include the following steps:

[0089] Step 101: Obtain a target category to which a target object belongs, and a first number of the target objects belonging to each of the target categories.

[0090] Among them, the target object includes an object pushed to a target user within a first preset time period. For example, in a short video application program, the videos pushed to user A within the first preset time period include news short videos and movie short videos. In the embodiments of the present disclosure, the number of news short videos and the number of movie short videos pushed to user A within the first preset time period need to be counted.

[0091] In addition, the target object in the embodiments of the present disclosure can be a video, a picture, or music.

[0092] Optionally, the first preset time period comprises a time period from starting to closing of the target application. The target application is an application that pushes target objects. In addition, the time period from starting to closing of the target application once can be referred to as a once active period. In the embodiments of the present disclosure, the number of target objects of each target category that the target application pushes for the target user in the next time period can be adjusted according to the first number of target objects of each target category that the target application pushes for the target user in the once active period and the behavior data of the target user on the target objects of each target category in the once active period.

[0093] Step 102: Obtain the behavior data of the target user on the target objects of each target category in the first preset time period.

[0094] As can be seen from step 102, in the embodiments of the present disclosure, it is necessary to filter the behavior data of each target category of target objects from the behavior data of the target user in the first preset time period.

[0095] For example, in a short video application, the videos pushed for user A in the first preset time period include news short videos and film and television short videos. In the embodiments of the present disclosure, it is necessary to count the behavior data of user A on the news short videos and the behavior data of user A on the film and television short videos in the first preset time period, that is, it is necessary to filter the behavior data of the news short videos and the behavior data of the film and television short videos from the behavior data of user A in the short video application in the first preset time period.

[0096] Step 103: Determine the interest degree of the target user on the target objects of each target category according to the behavior data.

[0097] The behavior data of the target user on the target objects of each target category can represent the actual demand of the target user on the target objects of each target category. Therefore, the interest degree of the target user on the target objects of each target category can be determined according to the behavior data of the target user on the target objects of each target category.

[0098] Step 104: Adjust the number of target objects of each target category pushed for the target user in a second preset time period according to the first number and the interest degree of the same target category, to obtain an adjusted number.

[0099] Optionally, adjusting the number of target objects of each target category pushed for the target user in the second preset time period according to the first number and the interest degree of the same target category comprises:

[0100] According to the first quantity, the SHAP value of the target category to which the first quantity belongs is calculated;

[0101] In the case that the SHAP value of the first category is less than the first preset threshold, and the interest degree belonging to the first category is greater than or equal to the second preset threshold, the number of the target objects of the first category pushed to the target user is increased in the second preset time period, and the first category is any one of the target categories;

[0102] In the case that the SHAP value of the second category is greater than or equal to the first preset threshold, and the interest degree belonging to the second category is less than the second preset threshold, the number of the target objects of the second category pushed to the target user is reduced in the second preset time period, and the second category is any one of the target categories.

[0103] For example, when the target object is a video, the video tags can be used to represent the categories of the video, and when the target categories include news, film and television, and automobile, the push quantity of the target objects of each target category and the SHAP value of each target category can be as shown in Table 1.

[0104] Table 1 SHAP value of target category

[0105] Video tags Push quantity SHAP value News category X1 S1 Film and television category X2 S2 Automobile category X3 S3

[0106] The SHapley Additive exPlanations (SHAP) model can be used to calculate the marginal contribution of a feature to the model. Thus, the SHAP value of each target category can represent the contribution degree of the push effect of the target object pushed to the target user. When the SHAP value of the first category is less than the first preset threshold, it indicates that the contribution degree of the target object of the first category is small, and when the SHAP value of the second category is greater than or equal to the first preset threshold, it indicates that the contribution degree of the target object of the second category is large.

[0107] When the SHAP value of the first category is less than the first preset threshold, and the interest degree belonging to the first category is greater than or equal to the second preset threshold, it indicates that the contribution degree of the target object of the first category is small, but the target user has a large interest degree in the target object of the first category, which means that the target object pushed to the target user in the first preset time period does not meet the actual needs of the target user, and thus the push quantity of the target object of the first category needs to be increased. Therefore, when the target object is pushed to the target user in the second preset time period, the push quantity of the target object of the first category can be increased.

[0108] Similarly, when the SHAP value of the second category is greater than or equal to the first preset threshold value and the interest degree of the target object belonging to the second category is less than the second preset threshold value, it indicates that the contribution degree of the target object of the second category is large, but the target user has a small interest degree in the target object of the second category, which indicates that the target object pushed to the target user in the first preset time period does not meet the actual needs of the target user, and thus the pushing quantity of the target object of the first category needs to be reduced. Therefore, when the target object is pushed to the target user in the second preset time period, the pushing quantity of the target object of the second category can be reduced.

[0109] Therefore, in the embodiment of the present disclosure, the SHAP value is used to represent the contribution degree of the target object of each target category to the pushing effect, so as to combine the contribution degree with the interest degree of the target user in the target object of each target category, so that the pushing can be performed according to the personalized needs of different users.

[0110] In addition, it should be noted that the pushing in the embodiment of the present disclosure can be pushing the target object to the user in the application when the application is started, or pushing the target object to the target user in the application when the user performs a refresh operation in the application, or pushing the target object to the target user in the application according to the keyword input by the user in the application.

[0111] Step 105: pushing the target object of each target category to the target user in the second preset time period according to the adjusted quantity.

[0112] In summary, the pushing method provided by the embodiment of the present disclosure can obtain the target category to which the target object pushed to the target user in the first preset time period belongs, and the first quantity of the target object belonging to each target category, and obtain the behavior data of the target user in the first preset time period for each target category of target object, so as to determine the interest degree of the target user in each target category of target object according to the behavior data, and then adjust the quantity of the target object of each target category pushed to the target user in the second preset time period according to the first quantity and the interest degree belonging to the same target category, to obtain the adjusted quantity, and push the target object of each target category to the target user in the second preset time period according to the adjusted quantity.

[0113] Therefore, in the pushing method provided by the embodiment of the present disclosure, the interest degree of the user in the target object of a certain category is determined according to the behavior data of the user in the target object of the category, so as to adjust the quantity of the target object of the category pushed to the user in the second preset time period according to the interest degree and the quantity of the target object of the category pushed to the user in the first preset time period.

[0114] The number of target objects of each target category pushed to the target user in the first preset time period represents the pushing situation of the target objects of each target category in the first preset time period, and the interest degree of the target user for the target objects of each target category represents the demand situation of the target user for the target objects of each target category. Therefore, the pushing method provided in the embodiments of the present disclosure combines the pushing situation of the target objects of each category with the actual interest degree of the user for the target objects of each category, so that the pushing can be performed according to the personalized demand of different users, and the accuracy of the pushing is improved to a certain extent, and the problem that the existing pushing method cannot meet the personalized demand of the user is solved.

[0115] According to a second aspect of the embodiments of the present disclosure, a pushing method is provided, as shown in the following. Figure 2 The pushing method can include the following steps.

[0116] Step 201: Obtain a target category to which a target object belongs, and a first number of the target objects belonging to each of the target categories.

[0117] The target objects include objects pushed to a target user in a first preset time period. For example, in a short video application program, the videos pushed to user A in the first preset time period include news short videos and movie short videos. In the embodiments of the present disclosure, the number of news short videos pushed to user A in the first preset time period and the number of movie short videos are counted.

[0118] In addition, the target objects in the embodiments of the present disclosure can be videos, pictures, and music.

[0119] Optionally, the first preset time period includes a time period from the start to the closing of a target application program. The target application program is an application program for pushing target objects. In addition, the time period from the start to the closing of the target application program at a time can be referred to as a live cycle, and in the embodiments of the present disclosure, the number of target objects of each target category pushed to the target user in the live cycle of the target application program and the behavior data of the target user for the target objects of each target category in the live cycle can be used to adjust the number of target objects of each target category pushed to the target user when the target application program is started next time.

[0120] Step 202: Obtain behavior data of the target user for the target objects of each target category in the first preset time period.

[0121] As can be seen from step 202, in the embodiments of the present disclosure, the behavior data for the target objects of each target category needs to be filtered from the behavior data of the target user in the first preset time period.

[0122] For example, in a short video application, the videos pushed to user A within a first preset time period include news short videos and film and television short videos. In an embodiment of the present disclosure, the behavior data of user A on the news short videos and the behavior data of user A on the film and television short videos within the first preset time period need to be counted, that is, the behavior data of user A on the news short videos and the behavior data of user A on the film and television short videos within the first preset time period in the short video application need to be filtered out from the behavior data of user A in the short video application.

[0123] In addition, after step 202, the following steps 203 to 204 are sequentially executed when i takes each integer value from 1 to N, N being the number of the target categories.

[0124] Step 203: According to the data of each behavior feature belonging to the i-th target category, calculate the SHAP value of the Shapley Additive explanations model of each behavior feature belonging to the i-th target category.

[0125] Optionally, the target object includes a video, and the behavior feature of the target object of the third category includes at least one of the following:

[0126] The cumulative duration of the video of the third category browsed by the target user within the first preset time period;

[0127] The target number of the video of the third category browsed by the target user within the first preset time period;

[0128] The target number of the video of the third category browsed by the target user within the first preset time period;

[0129] The preset operation includes at least one of the following: a collection operation, a sharing operation, a comment operation, and a download operation.

[0130] It should be noted that the target number includes at least one of the number of collection operations, the number of sharing operations, the number of comment operations, and the number of download operations. The comment operation is specifically an effective comment operation, for example, if the target user continuously posts the same comment on an object multiple times, it can be regarded as an effective comment operation.

[0131] In addition, the cumulative duration, the target number, and the target number represent the behavior of the target user, and the number of these behaviors can represent the interest degree of the user, so that the interest degree of the target user for the target object of the target category can be more accurately determined from the multiple behavior features of the target user for the target object of the target category.

[0132] In addition, when the target object is a video, a video tag can be used to represent the category of the video. When the target categories include news, movies, and cars, the number of target objects in each target category, and the SHAP values of each target category can be as shown in Table 1. In addition, according to the various behavior characteristics of the target user for the video of each video tag, the SHAP values of each behavior characteristic under each video tag can be obtained. For example, the SHAP values of the behavior characteristics of the target user for the news video can be as shown in Table 2.

[0133] Table 2: SHAP values of behavior characteristics of the target user for the news video

[0134] User behavior Specific value SHAP value Cumulative duration of videos browsed X4 S4 Number of news category videos browsed X5 S5 Number of news category videos collected X6 S6 Number of times news category videos are shared X7 S7 Number of effective comments on news category videos X8 S8 Number of news category videos downloaded X9 S9

[0135] Step 204: determining the interest degree of the target user for the target object of the i-th target category according to the SHAP values of each behavior characteristic of the i-th target category.

[0136] Optionally, the step of determining the interest degree of the target user for the target object of the i-th target category according to the SHAP values of each behavior characteristic of the i-th target category includes:

[0137] calculating a weighted average value of the SHAP values of each behavior characteristic belonging to the i-th target category according to the weight of each behavior characteristic, to obtain the interest degree of the target user for the target object of the i-th target category.

[0138] For example, the weight values of each behavior characteristic in Table 2 are k1-k6, and the interest degree of the target user for the news video is k1*S4+k2*S5+k3*S6+k4*S7+k5*S8+k6*S9.

[0139] It should be noted that the weight of each behavior characteristic can have different values under different push targets. For example, in some stage, the number of videos that the user is interested in is more important, and the weight of the number of news videos browsed in Table 2 is larger, and the weight of the total time of the videos browsed is smaller, and the other characteristics remain unchanged. In some stage, the time of the video browsed by the user is more important, and the weight of the total time of the videos browsed in Table 2 is larger, and the weight of the number of news videos browsed is smaller.

[0140] In addition, the SHAP can be used to calculate the marginal contribution of a feature when added to the model. Thus, according to the data of the behavior feature of the i-th target category, the SHAP value of the behavior feature calculated can represent the contribution of the data of the behavior feature in the behavior data of the target object of the i-th target category, so as to realize the quantification of the data of the behavior feature. Thus, the weighted average of the SHAP values of the behavior features of the i-th target category calculated can more accurately represent how much the target user implements the behavior of the target object of the i-th category. And the behavior data of the target user to the target object of each target category can represent the actual demand of the target user to the target object of each target category, and thus the weighted average of the SHAP values of the behavior features of the i-th target category calculated can more accurately represent the interest degree of the target user to the target object of the i-th target category.

[0141] In addition, the i-th parameter can also be used as the acceptance degree of the target user to the i-th target category, so as to classify the target object according to the acceptance degree, that is, to use the acceptance degree as the basis for determining the categories of the target object, and thus the classification of the target object is more easily accepted by the user.

[0142] Step 205: adjusting the number of target objects of each target category to be pushed to the target user in a second preset time period according to the first number and the interest degree of the same target category, to obtain an adjusted number.

[0143] Step 206: pushing the target objects of each target category to the target user in the second preset time period according to the adjusted number.

[0144] As can be seen from the above, the push method of the embodiment of the disclosure quantizes each behavior feature of the target object of each target category of the user by calculating the SHAP value of each behavior feature of the target object of each target category of the user, so as to obtain a more accurate interest degree of the target object of each target category of the user according to the SHAP values, and then adjust the number of target objects of the category to be pushed to the user in a second preset time period according to the interest degree and the number of target objects of the category to be pushed to the user in a first preset time period, so as to further improve the accuracy of the push.

[0145] Optionally, the adjusting the number of target objects of each target category to be pushed to the target user in a second preset time period according to the first number and the interest degree of the same target category comprises:

[0146] According to the first quantity, a SHAP value of the target category to which the first quantity belongs is calculated;

[0147] In a case where the SHAP value of the first category is less than a first preset threshold value and the interest degree belonging to the first category is greater than or equal to a second preset threshold value, the number of the target objects of the first category pushed to the target user is increased in the second preset time period, the first category being any one of the target categories;

[0148] In a case where the SHAP value of the second category is greater than or equal to the first preset threshold value and the interest degree belonging to the second category is less than the second preset threshold value, the number of the target objects of the second category pushed to the target user is reduced in the second preset time period, the second category being any one of the target categories.

[0149] The SHAP can be used to calculate the marginal contribution of a feature when it is added to the model. Thus, the SHAP value of each target category can represent the contribution degree of the pushing effect of the target user pushing the target object. The SHAP value of the first category is less than the first preset threshold value, indicating that the contribution degree of the target object of the first category is small, and the SHAP value of the second category is greater than or equal to the first preset threshold value, indicating that the contribution degree of the target object of the second category is large.

[0150] When the SHAP value of the first category is less than the first preset threshold value and the interest degree belonging to the first category is greater than or equal to the second preset threshold value, it indicates that the contribution degree of the target object of the first category is small, but the target user has a large interest degree in the target object of the first category, which means that the target object pushed to the target user in the first preset time period does not meet the actual needs of the target user, and thus the pushing number of the target object of the first category needs to be increased. Therefore, when the target object is pushed to the target user in the second preset time period, the pushing number of the target object of the first category can be increased.

[0151] Similarly, when the SHAP value of the second category is greater than or equal to the first preset threshold value and the interest degree belonging to the second category is less than the second preset threshold value, it indicates that the contribution degree of the target object of the second category is large, but the target user has a small interest degree in the target object of the second category, which means that the target object pushed to the target user in the first preset time period does not meet the actual needs of the target user, and thus the pushing number of the target object of the first category needs to be reduced. Therefore, when the target object is pushed to the target user in the second preset time period, the pushing number of the target object of the second category can be reduced.

[0152] Therefore, in the embodiment of the present disclosure, the SHAP value is used to represent the contribution of the target object of each target category to the pushing effect, so as to combine the contribution with the interest degree of the target user to the target object of each target category, so that the pushing can be performed according to the personalized needs of different users.

[0153] In addition, it should be noted that the pushing in the embodiment of the present disclosure can be pushing the target object for the user in the application when the application is started, or pushing the target object for the target user in the application when the user performs a refresh operation in the application, or inputting a keyword in the application, and then pushing the target object for the target user in the application according to the keyword.

[0154] Optionally, in the case where the behavior feature of the target object of the third category includes the cumulative duration, the method further includes:

[0155] In the case where the SHAP value of the cumulative duration is less than or equal to a third preset threshold, the number of first preset videos pushed to the target user in the second preset time period is increased, and the first preset video includes a video belonging to the third category and having a duration greater than a first preset duration.

[0156] Therefore, it is also possible to adjust the pushing number of the target object of a certain target category according to the size of the SHAP value of a single behavior feature under the target category. For example, the cumulative duration can represent the depth of the user watching the video, and the greater the SHAP value of the cumulative duration, the greater the depth of the user watching the video, which indicates that the user focuses on watching videos with a longer duration. Therefore, in this case, the number of videos with a longer duration under the target category pushed to the user in the future can be increased to meet the user's viewing needs.

[0157] Optionally, in the case where the behavior feature of the target object of the third category includes the target number, the method further includes:

[0158] In the case where the SHAP value of the target number is less than or equal to a fourth preset threshold, the number of second preset videos pushed to the target user in the second preset time period is increased, and the second preset video includes a video belonging to the third category and having a duration less than a second preset duration.

[0159] Therefore, the push quantity of the target object of the target category can also be adjusted according to the size of the SHAP value of the single behavior feature under the target category. For example, the target quantity can represent how many videos the user watches, and the larger the SHAP value of the target quantity, the more videos the user watches, which means that the user focuses on watching videos with a longer duration. Therefore, in this case, the quantity of videos with a shorter duration in the target category can be increased for subsequent push to the user to meet the user's viewing needs.

[0160] Optionally, the method further comprises:

[0161] According to the predetermined weight value of each target category, a weighted average value of the SHAP value of each target category is calculated to obtain a first parameter;

[0162] In the case where the first parameter is less than a fifth preset threshold, a preset prompt information is displayed;

[0163] The preset prompt information is used to indicate that the strategy for pushing the target object to the target user needs to be adjusted.

[0164] In addition, the first parameter being less than the fifth preset threshold indicates that the effect of pushing the target object to the target user is not good, and the push strategy needs to be adjusted. Therefore, in the embodiment of the present disclosure, when the first parameter is less than the fifth preset threshold, the preset prompt information is displayed, which can prompt the developer to adjust the push strategy.

[0165] In summary, as shown in Figure 3 The specific implementation of pushing user A by using the push method provided by the embodiment of the present disclosure can be as follows:

[0166] First step: the number of each type of video pushed to user A in an active period of an APP (i.e. from starting to closing the APP) is counted, and the SHAP value of each type is calculated according to the number of each type of video pushed, for example, as shown in Table 1 above;

[0167] Second step, the multiple behavior features of each type of video in the active period are counted, and the SHAP value of each behavior feature under each type is calculated, for example, the behavior data of news videos is counted to obtain Table 2 above;

[0168] Third step: the weighted average value of the SHAP value of each behavior feature under each type is calculated as the interest degree of user A to each type of video.

[0169] Step 4: Based on the SHAP value and interest level of each category, adjust the number of videos pushed to user A in the next active cycle to obtain the adjusted number;

[0170] For example, if the SHAP value of news videos is relatively high, but the user's interest level is relatively low, it means that a lot of news videos were pushed to user A during an active period, but the user's behavioral data on news videos is relatively low, that is, the user is not very interested in news videos. In this case, the push of news videos can be reduced in the future.

[0171] For example, if the SHAP value for movies and TV shows is relatively small, but the user shows a high level of interest, it means that fewer movies and TV shows were pushed to user A during an active period. However, there is a lot of data on the user's behavior towards news videos, indicating that the user is more interested in movies and TV shows. Therefore, more movies and TV shows can be pushed to user A in the future.

[0172] The fifth step is to push videos to user A in the next active cycle based on the adjusted quantity.

[0173] Therefore, the push method provided in this embodiment combines the push status of target objects of each category with the user's actual interest in target objects of each category, thereby enabling pushes to be made according to the personalized needs of different users, thus improving the accuracy of pushes to a certain extent and solving the problem that existing push methods cannot meet the personalized needs of users.

[0174] According to a third aspect of the embodiments of this disclosure, a risk prediction device is provided, such as... Figure 4 As shown, the risk prediction device 400 includes:

[0175] The category information acquisition module 401 is configured to acquire the target category to which the target object belongs, and the first number of target objects belonging to each target category, wherein the target objects include objects pushed to the target user within a first preset time period;

[0176] The behavior data acquisition module 402 is configured to acquire the behavior data of the target user towards the target object of each target category within the first preset time period;

[0177] The interest level determination module 403 is configured to determine the target user's interest level in each of the target categories of the target object based on the behavioral data.

[0178] The first push quantity adjustment module 404 is configured to adjust the number of target objects of each target category pushed to the target user within a second preset time period based on the first number of objects belonging to the same target category and the degree of interest, so as to obtain the adjusted quantity.

[0179] The pushing module 405 is configured to push the target objects of each of the target categories to the target user in the second preset time period according to the adjusted number.

[0180] Optionally, the behavior data of the target objects of the target category includes at least one behavior feature of the target objects of the target category and data of each of the behavior features.

[0181] The interest degree determination module 403 is specifically configured to:

[0182] The following process is sequentially executed when i takes each integer value in 1-N:

[0183] According to the data of each behavior feature belonging to the i-th target category, a SHAP value of each behavior feature belonging to the i-th target category is calculated by using a Shapley Additive exPlanations (SHAP) method.

[0184] According to the SHAP value of each behavior feature of the i-th target category, an interest degree of the target user for the target objects of the i-th target category is determined.

[0185] Wherein, N is the number of the target categories.

[0186] Optionally, when determining the interest degree of the target user for the target objects of the i-th target category according to the SHAP value of each behavior feature of the i-th target category, the interest degree determination module 403 is specifically configured to:

[0187] According to a predetermined weight of each behavior feature, a weighted average value of the SHAP values of the behavior features belonging to the i-th target category is calculated to obtain the interest degree of the target user for the target objects of the i-th target category.

[0188] Optionally, the first pushing number adjustment module 404 is specifically configured to:

[0189] According to the first number, a SHAP value of the target category to which the first number belongs is calculated.

[0190] In a case where the SHAP value of the first category is less than a first preset threshold value and the interest degree belonging to the first category is greater than or equal to a second preset threshold value, the number of the target objects of the first category pushed to the target user in the second preset time period is increased, and the first category is any one of the target categories.

[0191] In a case where the SHAP value of the second category is greater than or equal to the first preset threshold value and the interest degree of the second category is less than the second preset threshold value, the number of the target objects of the second category pushed to the target user is reduced in the second preset time period, and the second category is any one of the target categories.

[0192] Optionally, the target object includes a video, and the behavior feature of the target object of the third category includes at least one of the following:

[0193] A cumulative duration of the video of the third category browsed by the target user in the first preset time period;

[0194] A target number of the video of the third category browsed by the target user in the first preset time period;

[0195] A target number of a preset operation of the video of the third category by the target user in the first preset time period;

[0196] The preset operation includes at least one of a collection operation, a sharing operation, a comment operation, and a download operation.

[0197] The third category is any one of the target categories.

[0198] Optionally, in a case where the behavior feature of the target object of the third category includes the cumulative duration, the apparatus further includes:

[0199] The second push number adjustment module 406 is configured to increase the number of the first preset video pushed to the target user in the second preset time period in a case where the SHAP value of the cumulative duration is less than or equal to a third preset threshold value, and the first preset video includes a video belonging to the third category and having a duration greater than a first preset duration.

[0200] Optionally, in a case where the behavior feature of the target object of the third category includes the target number, the apparatus further includes:

[0201] The third push number adjustment module 407 is configured to increase the number of the second preset video pushed to the target user in the second preset time period in a case where the SHAP value of the target number is less than or equal to a fourth preset threshold value, and the second preset video includes a video belonging to the third category and having a duration less than a second preset duration.

[0202] Optionally, the apparatus further includes:

[0203] The parameter calculation module 408 is configured to calculate a weighted average value of SHAP values of each target category according to a predetermined weight value of each target category, to obtain a first parameter.

[0204] The prompt module 409 is configured to display preset prompt information in a case where the first parameter is less than a fifth preset threshold.

[0205] The preset prompt information is used to indicate that a strategy for pushing the target object to the target user needs to be adjusted.

[0206] As can be seen from the above, the pushing device provided in the embodiments of the present disclosure can obtain a target category to which a target object pushed for a target user within a first preset time period and a first quantity of target objects belonging to each target category, and obtain behavior data of the target user on target objects of each target category within the first preset time period, so as to determine an interest degree of the target user on target objects of each target category according to the behavior data, and then adjust a quantity of target objects of each target category pushed for the target user within a second preset time period according to the first quantity and the interest degree of the same target category.

[0207] Therefore, the pushing device provided in the embodiments of the present disclosure can determine an interest degree of a user on target objects of a category according to behavior data of the user on target objects of different categories, so as to adjust a quantity of target objects of the category pushed for the user within a second preset time period according to the interest degree and a quantity of target objects of the category pushed for the user within a first preset time period, and thus the pushing device combines a pushing situation of target objects of each category with an actual interest degree of the user on target objects of each category, so as to push according to individualized needs of different users, and further improve the accuracy of pushing to a certain extent, and solve the problem that the existing pushing method cannot meet the individualized needs of users.

[0208] As to the device in the above embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0209] According to a fourth aspect of the embodiments of the present disclosure, an electronic device is provided. Referring to Figure 5 The electronic device includes:

[0210] a processor 510;

[0211] a memory 520 for storing instructions executable by the processor;

[0212] The processor is configured to execute the instructions to implement the above-mentioned pushing method.

[0213] According to a fifth aspect of the embodiments of the present disclosure, an electronic device is provided. As shown in Figure 6 The electronic device 600 can be a mobile phone, a computer, a digital broadcast electronic device, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0214] Referring to Figure 6 The electronic device 600 can include one or more of the following components: a processing component 602, a memory 604, a power supply component 606, a multimedia component 608, an audio component 610, an input / output (I / O) interface 612, a sensor component 614, and a communication component 616.

[0215] The processing component 602 usually controls overall operations of the electronic device 600, such as operations associated with displaying, making phone calls, data communications, camera operations, and recording operations. The processing component 602 can include one or more processors 620 to execute instructions to complete all or part of steps of the methods described above. In addition, the processing component 602 can include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 can include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.

[0216] The memory 604 is configured to store various types of data to support operations of the electronic device 600. Examples of these data include instructions for any application or method operating on the electronic device 600, contact data, phonebook data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0217] The power supply component 606 provides power for various components of the electronic device 600. The power supply component 606 can include a power supply management system, one or more power supplies, and other components associated with generating, managing and distributing power for the electronic device 600.

[0218] The multimedia component 608 includes a screen to provide an output interface between the electronic device 600 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, and a gesture on the touch panel. The touch sensor can not only sense a boundary of a touching or a sliding action, but also detect duration and intensity of the touching or sliding action. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the electronic device 600 is in an operating mode, such as a camera mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zooming capability.

[0219] The audio component 610 is configured to output and / or input an audio signal. For example, the audio component 610 includes a microphone (MIC) to receive an external audio signal when the electronic device 600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, the audio component 610 also includes a speaker to output an audio signal.

[0220] The I / O interface 612 provides an interface between the processing component 602 and peripheral interface modules, which can be a keypad, a click wheel, buttons, and the like. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0221] The sensor component 614 includes one or more sensors to provide various state assessments for the electronic device 600. For example, the sensor component 614 can detect an open / closed state of the electronic device 600, relative positioning of components, such as a display and a keypad of the electronic device 600, a change in position of the electronic device 600 or a component of the electronic device 600, presence or absence of user contact with the electronic device 600, an orientation or acceleration / deceleration of the electronic device 600, and a temperature change of the electronic device 600. The sensor component 614 can include a proximity sensor configured to detect presence of a nearby object without any physical touch. The sensor component 614 can also include a light sensor, such as a CMOS or CCD image sensor, for use in an imaging application. In some embodiments, the sensor component 614 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0222] The communication component 616 is configured to facilitate wired or wireless communication between the electronic device 600 and other devices. The electronic device 600 can access a wireless network based on a communication standard, such as WiFi, a cellular network standard (such as 2G, 3G, 8G, or 5G), or a combination thereof. In an example embodiment, the communication component 616 receives broadcast signals or broadcast-related information from external broadcast management systems via a broadcast channel. In an example embodiment, the communication component 616 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) techniques, infrared data association (IrDA) techniques, ultra-wideband (UWB) techniques, Bluetooth (BT) techniques, and other techniques.

[0223] In an example embodiment, the electronic device 600 can be implemented with one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements, for performing the push method described above.

[0224] In an example embodiment, a non-transitory computer-readable storage medium including instructions, such as the memory 604 including instructions, is also provided, which, when executed by the processor 620 of the electronic device 600, can complete the method described above. Alternatively, for example, the storage medium can be a non-transitory computer-readable storage medium, such as a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, and the like.

[0225] In yet another aspect of the embodiments of the present disclosure, the embodiments of the present disclosure also provide a storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the push method described above.

[0226] According to yet another aspect of the embodiments of the present disclosure, a computer program product including instructions is provided, which, when executed by a processor, implements the push method described above.

[0227] The push scheme provided herein is not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used with programs in accordance with the teachings herein, or it can prove convenient to construct more specialized systems to perform the required method steps. The required structure for a system to implement the scheme of the application will be apparent from the description above. In addition, the present application is not described with reference to any particular programming language. It will be appreciated that a variety of programming languages can be used to implement the teachings of the application as described herein, and any references below to specific languages are provided for disclosure of enablement only.

[0228] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been described in detail in order not to obscure the understanding of this description.

[0229] Similarly, it is to be understood that the mechanical details of the application sometimes are presented in terms of certain spatially-related or geometrical configurations and / or descriptions. It will be appreciated by those skilled in the art that such descriptions or configurations are illustrative of the principles of the application and are not intended to limit the scope of the application. For example, the spatially-related terms such as "front," "back," "top," "bottom," "side," "under," "over," "upper," "lower," "horizontal," "vertical," and the like, are used herein, but are not to be interpreted literally or are used in accordance with their normal usage in the art, unless otherwise noted. It is to be understood that the spatially-related terms are intended to encompass different orientations of the described or illustrated device or structure, unless otherwise noted. Accordingly, the various examples of the application described herein can be implemented in a number of different fashions and with various components. It is contemplated that specific examples of the application can be implemented in one or more of the following, or in some other combination:

[0230] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adapted and placed in one or more devices other than the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and further can be divided into more modules or units or components. Any combination of all the features disclosed in the specification (including the accompanying claims, abstract and drawings), and any method or process or steps of any method or process so disclosed, can be made in any combination. Unless specifically stated otherwise, each feature disclosed in the specification (including the accompanying claims, abstract and drawings) can be replaced by alternative features that serve the same, equivalent or similar purpose, unless the context explicitly dictates otherwise.

[0231] Furthermore, those skilled in the art will recognize that, while certain embodiments described herein include certain features that are not included in other embodiments, combinations of those features from different embodiments are within the scope of the application and form different embodiments. For example, in the claims, any of the claimed embodiments can be used in any combination.

[0232] Various component embodiments of the application can be implemented in hardware, or as software modules running in one or more processors, or in combinations thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functionality of some or all of the components in an information extraction scheme according to embodiments of the present disclosure. The application can also be implemented as a program of instructions for performing part or all of the methods described herein, e.g., as a computer program and a computer program product. Such program of the application can be stored on a computer readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0233] It is noted that the foregoing examples have been provided merely for the purpose of explanation and are in no way to be construed as limiting of the present application. While the application has been described with reference to preferred embodiments, it is understood that the words which have been used herein are words of description, and that changes can be made within the scope and spirit of the application. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word comprising does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the system claims enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not imply any order. These words have been used to name the elements for the sake of ease of reading only.

Claims

1. A push method, characterized by, The method comprises: obtaining a target category to which a target object belongs, and a first quantity of the target objects belonging to each of the target categories, wherein the target objects include objects pushed to a target user within a first preset time period; obtaining behavior data of the target objects of each of the target categories in the first preset time period by the target user; determining an interest degree of the target objects of each of the target categories by the target user according to the behavior data; adjusting the quantity of the target objects of each of the target categories pushed to the target user within a second preset time period according to the first quantity and the interest degree belonging to the same target category, to obtain an adjusted quantity; pushing the target objects of each of the target categories to the target user within the second preset time period according to the adjusted quantity.

2. The push method of claim 1, wherein, The behavior data of the target objects of each of the target categories comprises at least one behavior feature of the target objects of the target category and data of each of the behavior features; The determination of the interest degree of the target objects of each of the target categories by the target user according to the behavior data comprises: performing the following processes in sequence when i takes each integer value from 1 to N: calculating a SHAP value of each of the behavior features belonging to the i-th target category according to the data of each of the behavior features belonging to the i-th target category; determining the interest degree of the target objects of the i-th target category by the target user according to the SHAP value of each of the behavior features of the i-th target category; wherein N is the number of the target categories.

3. The push method of claim 2, wherein, The determination of the interest degree of the target objects of the i-th target category by the target user according to the SHAP value of each of the behavior features of the i-th target category comprises: calculating a weighted average value of the SHAP values of the behavior features belonging to the i-th target category according to a predetermined weight of each of the behavior features, to obtain the interest degree of the target objects of the i-th target category by the target user.

4. The push method of claim 1, wherein, The adjustment of the quantity of the target objects of each of the target categories pushed to the target user within the second preset time period according to the first quantity and the interest degree belonging to the same target category comprises: calculating a SHAP value of the target category to which the first quantity belongs according to the first quantity; in a case where the SHAP value of a first category is less than a first preset threshold value, and the interest degree belonging to the first category is greater than or equal to a second preset threshold value, increasing the quantity of the target objects of the first category pushed to the target user within the second preset time period, the first category being any one of the target categories; In a case where the SHAP value of the second category is greater than or equal to the first preset threshold value and the interest degree of the second category is less than the second preset threshold value, the number of the target objects of the second category pushed to the target user is reduced in the second preset time period, and the second category is any one of the target categories.

5. The push method of claim 2, wherein, The target objects include videos, and the behavior feature of the target objects of the third category includes at least one of the following: A cumulative duration of the videos of the third category browsed by the target user in the first preset time period; A target number of the videos of the third category browsed by the target user in the first preset time period; A target number of preset operations of the videos of the third category by the target user in the first preset time period; The preset operation includes at least one of a collection operation, a sharing operation, a comment operation, and a download operation; The third category is any one of the target categories.

6. The push method of claim 5, wherein, In a case where the behavior feature of the target objects of the third category includes the cumulative duration, the method further includes: In a case where the SHAP value of the cumulative duration is less than or equal to a third preset threshold value, the number of first preset videos pushed to the target user is increased in the second preset time period, and the first preset video includes a video belonging to the third category and having a duration greater than a first preset duration.

7. The push method of claim 5, wherein, In a case where the behavior feature of the target objects of the third category includes the target number, the method further includes: In a case where the SHAP value of the target number is less than or equal to a fourth preset threshold value, the number of second preset videos pushed to the target user is increased in the second preset time period, and the second preset video includes a video belonging to the third category and having a duration less than a second preset duration.

8. The push method of claim 4, wherein, The method further includes: According to a predetermined weight value of each target category, a weighted average value of the SHAP value of each target category is calculated to obtain a first parameter; In a case where the first parameter is less than a fifth preset threshold value, a preset prompt information is displayed; The preset prompt information is used to indicate that the strategy of pushing the target objects to the target user needs to be adjusted.

9. A pushing device, characterized in that The device includes: A category information acquisition module configured to acquire a target category to which a target object belongs and a first number of the target objects belonging to each target category, wherein the target object includes an object pushed to a target user in a first preset time period; A behavior data acquisition module configured to acquire behavior data of the target user on the target objects of each target category in the first preset time period; An interest degree determination module configured to determine an interest degree of the target user on the target objects of each target category according to the behavior data; and An interest degree determination module configured to determine an interest degree of the target user on the target objects of each target category according to the behavior data. The first push quantity adjustment module is configured to adjust the quantity of the target objects of each of the target categories to be pushed to the target user in a second preset time period according to the first quantity and the interest degree, and obtain an adjusted quantity. The push module is configured to push the target objects of each of the target categories to the target user in the second preset time period according to the adjusted quantity.

10. The push device of claim 9, wherein, The behavior data of the target objects of one of the target categories includes at least one behavior feature of the target objects of the target category and data of each of the behavior features; The interest degree determination module is specifically configured to: perform the following processes in sequence when i takes each integer value in 1 to N: calculate a SHAP value of each of the behavior features belonging to the i-th target category according to the data of each of the behavior features belonging to the i-th target category; determine the interest degree of the target user for the target objects of the i-th target category according to the SHAP value of each of the behavior features of the i-th target category; wherein N is the number of the target categories.

11. The push device of claim 10, wherein, When the interest degree determination module determines the interest degree of the target user for the target objects of the i-th target category according to the SHAP value of each of the behavior features of the i-th target category, the interest degree determination module is specifically configured to: calculate a weighted average value of the SHAP values of the behavior features belonging to the i-th target category according to a predetermined weight of each of the behavior features, and obtain the interest degree of the target user for the target objects of the i-th target category.

12. The push device of claim 9, wherein, The first push quantity adjustment module is specifically configured to: calculate a SHAP value of the target category to which the first quantity belongs according to the first quantity; in a case where the SHAP value of a first category is less than a first preset threshold value and the interest degree belonging to the first category is greater than or equal to a second preset threshold value, increase the quantity of the target objects of the first category to be pushed to the target user in the second preset time period, the first category being any one of the target categories; in a case where a SHAP value of a second category is greater than or equal to the first preset threshold value and the interest degree belonging to the second category is less than the second preset threshold value, decrease the quantity of the target objects of the second category to be pushed to the target user in the second preset time period, the second category being any one of the target categories.

13. The push device of claim 10, wherein, The target objects include videos, and the behavior features of the target objects of a third category include at least one of the following: cumulative duration of the videos of the third category browsed by the target user in the first preset time period; target quantity of the videos of the third category browsed by the target user in the first preset time period; target number of preset operations of the videos of the third category by the target user in the first preset time period; The preset operation includes at least one of a collection operation, a sharing operation, a comment operation, and a download operation. The third category is any one of the target categories.

14. The push device of claim 13, wherein, In a case where the behavior feature of the target object of the third category includes the cumulative duration, the device further includes: The second push quantity adjustment module is configured to, in a case where the SHAP value of the cumulative duration is less than or equal to a third preset threshold, increase the number of first preset videos pushed to the target user in the second preset time period, the first preset videos including videos belonging to the third category and having a duration greater than a first preset duration.

15. The push device of claim 13, wherein, In a case where the behavior feature of the target object of the third category includes the target quantity, the device further includes: The third push quantity adjustment module is configured to, in a case where the SHAP value of the target quantity is less than or equal to a fourth preset threshold, increase the number of second preset videos pushed to the target user in the second preset time period, the second preset videos including videos belonging to the third category and having a duration less than a second preset duration.

16. The push device of claim 12, wherein, The device further includes: The parameter calculation module is configured to calculate a weighted average value of the SHAP values of the target categories according to the weight values of the target categories, to obtain a first parameter. The prompt module is configured to, in a case where the first parameter is less than a fifth preset threshold, display preset prompt information. The preset prompt information is used to indicate that the strategy of pushing the target objects to the target user needs to be adjusted.

17. An electronic device, comprising: comprise: a processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the push method of any one of claims 1-8.

18. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can implement the push method of any one of claims 1-8.

19. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions implement the push method of any one of claims 1-8 when executed by the processor.

Images