CN114785852B

CN114785852B - Push content determining method and device, electronic equipment and storage medium

Info

Publication number: CN114785852B
Application number: CN202210361759.7A
Authority: CN
Inventors: 李宁
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2022-04-07
Filing date: 2022-04-07
Publication date: 2024-04-09
Anticipated expiration: 2042-04-07
Also published as: CN114785852A

Abstract

The disclosure relates to a push content determining method, a push content determining device, an electronic device and a storage medium, wherein the push content determining method comprises the following steps: receiving a current push content determining request sent by a terminal corresponding to a target object; responding to the current push content determining request, and acquiring a current recall content set corresponding to the target object from the candidate content set; acquiring a history selection content set of the target object, wherein the content in the history selection content set is content which responds to the history pushing content determination request selection of the target object; combining the current recall content set and the history selected content to obtain a target recall content set; and determining a target push content set corresponding to the target object based on the target recall content set. In this way, when the push content is determined, the history selection content of the target object is recalled, the history selection content is selected in response to the history push content determination request of the target object, and the push content has higher stability and is matched with the target object, so that the quality of the push content is improved.

Description

Push content determining method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of the internet, and in particular, to a push content determining system, method, apparatus, electronic device, and storage medium.

Background

With the development of internet technology, there is a need for pushing content to users in many scenarios, content pushing generally needs to go through a recall stage, and in the recall stage, a server can obtain a certain amount of content conforming to a user account to be pushed as recall content according to a preset recall policy. However, the quality of content recall is currently poor, resulting in lower accuracy of pushing content.

Disclosure of Invention

The disclosure provides a push content determining method, a push content determining device, electronic equipment and a storage medium, so as to at least solve the problem that in the related art, the quality of content recall is poor, and the accuracy of push content is low. The technical scheme of the present disclosure is as follows:

according to a first aspect of an embodiment of the present disclosure, there is provided a push content determining method, including:

receiving a current push content determining request sent by a terminal corresponding to a target object;

responding to the current push content determining request, and acquiring a current recall content set corresponding to the target object from a candidate content set;

Acquiring a history selection content set of the target object, wherein the content in the history selection content set is content which is selected by a request for determining a history pushing content in response to the target object;

combining the current recall content set and the history selection content to obtain a target recall content set;

and determining a target push content set corresponding to the target object based on the target recall content set.

Optionally, the determining, based on the target recall content set, a target push content set corresponding to the target object includes:

analyzing the target recall content in the target recall content set, and calculating a first index value corresponding to each target recall content, wherein the first index value represents a predicted resource increment value of the target recall content;

screening the reference content from the target recall content based on the first index value, and acquiring a second index value of the reference content, wherein the second index value represents a current resource increment value corresponding to the reference content;

and determining target push contents from the parameter bid contents according to the second index value to obtain a target push content set.

Optionally, after the filtering the bid content from the target recall content based on the first index value and obtaining the second index value of the bid content, the method further includes:

according to the second index value, determining new history selection content corresponding to the target object from the target parameter competition content;

and adding the new history selection content into a history selection content set corresponding to the target object.

Optionally, the current recall content set is obtained based on a preset recall model, and after the second index value of the parameter bid content is obtained, the method further includes:

taking the acquired parameter content as current parameter content, and acquiring parameter content corresponding to a push content determination request sent last time by the target object as historical parameter content;

determining the difference between the second index values of the current reference bidding content and the historical reference bidding content as an index difference value;

and adjusting model parameters of the preset recall model according to the index difference value to obtain an adjusted preset recall model.

Optionally, the acquiring the historical selection content set of the target object includes:

Acquiring a candidate selected content set corresponding to the target object, wherein the content in the candidate selected content set is content which is selected by a request for determining content responding to the historical push content of the target object;

determining a third index value corresponding to each candidate selection content in the candidate selection content set, wherein the third index value represents a current resource increment value corresponding to the candidate selection content;

and screening candidate selected contents of which the third index value meets a threshold value condition to form a history selected content set.

Optionally, the history selection content set is obtained from a preset database, the preset database stores a plurality of history selection contents corresponding to the history push content determining requests, each history push content determining request has a corresponding request time, and the obtaining the history selection content set of the target object includes:

determining a difference value between the request time and the current time of each history push content determination request;

according to the difference value, determining the content quantity corresponding to each historical push content determination request, wherein the content quantity and the difference value form a negative correlation;

and according to the content quantity corresponding to each history push content determining request, selecting the history selection content from the selection content corresponding to each history push content determining request to form a history selection content set.

According to a second aspect of embodiments of the present disclosure, there is provided a push content determining apparatus, including:

the receiving unit is configured to execute a current push content determining request sent by a terminal corresponding to the receiving target object;

a response unit configured to execute a current recall content set corresponding to the target object from a candidate content set in response to the current push content determination request;

an acquisition unit configured to perform acquisition of a history selection content set of the target object, the content in the history selection content set being content selected in response to a history push content determination request of the target object;

the combining unit is configured to combine the current recall content set and the history selection content to obtain a target recall content set;

and the determining unit is configured to determine a target push content set corresponding to the target object based on the target recall content set.

Optionally, the determining unit is further configured to perform:

Optionally, the determining unit is specifically configured to perform:

Optionally, the current recall content set is obtained based on a preset recall model, and the determining unit is further configured to perform:

Optionally, the acquiring unit is configured to perform:

Optionally, the history selection content set is acquired from a preset database, the preset database stores a plurality of history selection contents corresponding to the history push content determining requests, each history push content determining request has a corresponding request time, and the acquiring unit is configured to execute:

According to a third aspect of embodiments of the present disclosure, there is provided a push content determination electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the push content determination method of the first item.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer readable storage medium, which when executed by a processor of a push content determining electronic device, causes the push content determining electronic device to perform the push content determining method of the first item above.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program/instruction which, when executed by a processor, implements the push content determination method of the first aspect described above.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

Receiving a current push content determining request sent by a terminal corresponding to a target object; responding to the current push content determining request, and acquiring a current recall content set corresponding to the target object from the candidate content set; acquiring a history selection content set of the target object, wherein the content in the history selection content set is content which responds to the history pushing content determination request selection of the target object; combining the current recall content set and the history selected content to obtain a target recall content set; and determining a target push content set corresponding to the target object based on the target recall content set.

In this way, when the push content is determined, the history selection content of the target object is recalled, the history selection content is selected in response to the history push content determination request of the target object and is also the content matched with the requirement of the target object, and the push content has higher stability, so that the quality of the determined push content is improved, and the accuracy of content push is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

FIG. 1 is a schematic diagram illustrating device interactions in a push content determination procedure, according to an example embodiment.

Fig. 2 is a flow chart illustrating a push content determination method according to an example embodiment.

Fig. 3 is a logical schematic diagram illustrating a push content determination process according to an example embodiment.

Fig. 4 is a logic diagram of one embodiment shown in accordance with an exemplary embodiment.

Fig. 5 is another logical schematic of one present scheme shown in accordance with an exemplary embodiment.

Fig. 6 is a system diagram of the present disclosure, shown according to an example embodiment.

Fig. 7 is a block diagram illustrating a push content determination device, according to an example embodiment.

Fig. 8 is a block diagram illustrating an electronic device for push content determination, according to an example embodiment.

Fig. 9 is a block diagram illustrating an apparatus for push content determination according to an example embodiment.

Detailed Description

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

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

In particular, the push content determination flow may include recall, direction, order, and push. First, after receiving a push request of a data receiver, a recall phase is entered, and data of which part is matched with the data receiver is selected from a candidate data set. And then screening the data selected in the recall stage according to the orientation conditions provided by the data provider, and further, sorting and bidding the data selected in the recall stage in the sorting stage according to the predicted values of various models, and finally, determining the winning push content to the data receiver.

The recall phase may take the form of providing multiple recalls in different directions, e.g., the data that may be of interest to the data receiver may be mined from the level of interest to the data receiver; or recalling the current comparison hot data from the hot data layer; in addition, data liked by similar users of the data receiver can be recalled from the collaborative filtering level, and the like.

As shown in fig. 1, a schematic diagram of device interactions in a process for determining push content is shown. The device in the push content determining process comprises a terminal and a server, wherein the terminal requests content push to the server, then the server responds to the request of the terminal, enters a recall stage, selects partial data matched with the terminal sending the request from a candidate data set, screens the data selected in the recall stage according to the orientation condition provided by the terminal, enters a sorting stage, sorts and bids the data selected in the recall stage according to the pre-estimation values of various models, determines the final push content, and pushes the push content to the terminal.

In the related art, due to the instability of the data recall model, the accuracy of the data recall may fluctuate, and the situation that the data difference of the same user recall each time is large occurs, so that the efficiency and quality of the data recall are difficult to ensure, and therefore, the problem that the accuracy of the pushed content is low due to the poor quality of the content recall exists.

According to a first aspect of embodiments of the present disclosure, there is provided a push content determining method, fig. 2 is a flowchart illustrating a push content determining method according to an exemplary embodiment, as shown in fig. 2, the push content determining method comprising the steps of:

in step S11, a current push content determining request sent by a terminal corresponding to the target object is received.

The pushing content may include promotion content, such as product sales information or campaign information, and the like, may also include news content, such as real-time hot news or burst news, and the like, and these contents may be pushed in any data form, such as text data, image data, audio data, and the like, or may also be pushed in a form of a virtual resource locator or a web page link, which is not limited in this disclosure.

In the present disclosure, the push content determining method may be applied to a server, and the terminal corresponding to the target object may be a client, a mobile device, or the like that is communicatively connected to the server, and when the content push condition is satisfied, the terminal corresponding to the target object may send a push content determining request to the server.

For example, the terminal corresponding to the target object may send the push content determining request to the server according to a preset period, or may also send the push content determining request to the server in response to a preset operation of the target object, or the like. In general, a terminal corresponding to a target object may send a plurality of push content determining requests to a server, and for convenience of description, in this disclosure, a currently received push content determining request is referred to as a current push content determining request, and a previously received push content determining request is referred to as a historical push content determining request.

In step S12, in response to the current push content determination request, a current recall content set corresponding to the target object is obtained from the candidate content set.

In this step, in response to the current push content determination request, a current recall content set corresponding to the target object may be obtained from the candidate content set according to a preset recall rule. The preset recall rule may include collaborative filtering, recall a current recall content set by using the idea that "similar target objects like the same content", or may also include CTR (Click-Through-Rate) recall, recall a content with a relatively high Click Rate as a current recall content set, and may further include hot content recall, recall a hot content of a current system as a current recall content set, and so on, which is not specifically limited.

In step S13, a history selection content set of the target object is acquired, and the content in the history selection content set is content requested to be selected in response to the history pushing content determination of the target object.

The content in the history selection content set is content selected according to the history pushing content determination request of the target object, and it can be understood that each time the target object sends a content pushing request, the server selects corresponding content to push the content to the target object according to the content pushing request, and then the content in the history selection content set is the content selected according to the content pushing request sent before the target object. For example, the content selected by the request may be determined based on all push contents sent before the target object, the content selected by the request may be determined based on push contents sent by the target object within a preset length in the past, the content selected by the request may be determined based on a preset number of push contents sent before the target object closest to the current time, etc., which is not limited in particular.

In this step, the step of obtaining the history selection content set of the target object may include the steps of:

Acquiring a candidate selection content set corresponding to the target object, wherein the content in the candidate selection content set is content which is selected by a request for determining historical push content responding to the target object; determining a third index value corresponding to each candidate selection content in the candidate selection content set, wherein the third index value represents a current resource increment value corresponding to the candidate selection content; and screening candidate selected contents of which the third index value meets the threshold value condition to form a history selected content set.

That is, after receiving the current push content determination request, the server determines, as the history selected content set, the candidate selected content whose third index value satisfies the threshold condition from among the candidate selected content sets selected in response to the history push content determination request of the target object.

The candidate selected content set may be a historical recall content set obtained from the candidate content set according to a preset recall rule in response to a historical push content determination request of the target object, or may be a content set further selected from the historical recall content set, for example, a third index value is ordered to a preset number of previous historical recall contents, and so on.

It can be understood that the probability that the candidate selected content with the third index value meeting the threshold value condition accords with the pushing condition in the subsequent content determining process is larger, the system response is more sensitive, any change of the system can be reflected to the candidate selected content with the third index value meeting the threshold value condition, the subsequent content recall result can be changed immediately, and the change of the system can be perceived very quickly, so that the stability of the pushing content determination can be further improved.

In one implementation, the history selection content set is obtained from a preset database, where the preset database stores history selection contents corresponding to a plurality of history push content determination requests. Then, each history push content determining request has a corresponding request time, and acquiring the history selection content set of the target object may include the following steps:

determining a difference value between the request time and the current time of each history push content determination request; according to the difference value, determining the content quantity corresponding to each historical push content determination request, wherein the content quantity and the difference value form a negative correlation; and according to the content quantity corresponding to each history push content determining request, selecting the history selection content from the selection content corresponding to each history push content determining request to form a history selection content set.

That is, in the case where there are a plurality of history push content determination requests, the number of contents corresponding to each history push content determination request may be obtained according to the request time of the history push content determination request, where in the obtained history selection content set, the history push content determination request that is longer than the current time has a smaller number of contents, whereas the history push content determination request that is closer to the current time has a larger number of contents. Therefore, the obtained history selection content set has stronger timeliness and better final pushing effect.

Or, the number of the contents corresponding to each history push content determining request may be equal to the number of the contents corresponding to each history push content determining request, so that for each history push content determining request, the more the number of the contents corresponding to the history push content determining request is, the more the contents corresponding to the history push content determining request is in the history select content set, otherwise, the fewer the number of the contents corresponding to the history push content determining request is, and the fewer the number of the contents corresponding to the history push content determining request is. Thus, the probability that the content corresponding to each history push content determining request is selected is similar, and the obtained history selected content set is more stable.

In addition, feedback information after content is pushed to the target object each time can be referred to, and a history selection content set of the target object can be obtained, wherein the feedback information can include clicking, browsing and subsequent income conditions of push content. According to the feedback information, it can be determined which contents can obtain a more numbered pushing effect after pushing, and further, when the history selection content set of the target object is obtained, the probability that the content with the better pushing effect is selected to the history selection content set is higher, otherwise, the probability that the content with the worse pushing effect is selected to the history selection content set is lower. Thus, the obtained history selection content set has stronger pertinence and better final pushing effect.

In step S14, the current recall content set and the history selection content are combined to obtain a target recall content set.

It can be appreciated that the historical selection content determined according to the recalled content in the multiple recall processes within a preset period of time has higher stability compared with the content recalled in the single content recall process, namely the current recall content set, so that the new historical selection content is added as a part of the target recall content, the cost of model retrieval can be further reduced, and the stability of content recall is improved.

In this step, the target recall content set has a larger order of magnitude, and generally, the data volume of the target recall content set is maintained above a thousand orders of magnitude, so as to ensure the operability of the subsequent screening and sorting processes, and further improve the quality of the pushed content determination.

In step S15, a target push content set corresponding to the target object is determined based on the target recall content set.

In this step, the step of determining the target push content set corresponding to the target object based on the target recall content set may include:

analyzing the target recall content in the target recall content set, and calculating a first index value corresponding to each target recall content, wherein the first index value represents a predicted resource increment value of the target recall content; screening the parameter bid content from the target recall content based on the first index value, and acquiring a second index value of the parameter bid content, wherein the second index value represents a current resource increment value corresponding to the parameter bid content; and determining target push contents from the reference bid contents according to the second index value to obtain a target push content set.

The first index value refers to a predicted resource increment value of the recall content, and it can be understood that the purpose of pushing the content to the terminal is to expect to obtain a corresponding resource increment, and the resource increment may be an exposure rate increased by operations such as clicking, browsing, etc. of the target object on the target recall content, or may be some virtual resources possibly obtained by the system after pushing the target recall content to the target object, etc., which is not particularly limited. The higher the first index value of the target recall content, the higher the resource increment that may be acquired after pushing the target recall content to the terminal, in other words, the higher the first index value, the more worth pushing the target recall content. In this step, a first index value corresponding to each target recall content may be calculated using a predictive model obtained by training in advance.

For example, the first index value may be a virtual resource that can be obtained by prediction after any target recall content is pushed to the target object, and then, based on the first index value, the parameter content is selected from the target recall content, that is, each target recall content is calculated, the value of the corresponding virtual resource that can be obtained is predicted, and based on the prediction result, the parameter content is selected from the target recall content, for example, the predicted value is ranked in a first preset number of target recall contents before, or the predicted value is beyond a preset first threshold, or the like.

In addition, the second index value, that is, the current resource increment value corresponding to the reference content, is a determined value that can be obtained in real time, rather than a predicted value, compared with the first index value, and the higher the second index value of the reference content, the higher the resource increment that can be obtained in real time, that is, the higher the second index value, the more worth pushing the reference content, if it is determined to push the reference content to the terminal.

For example, the second index value may be some virtual resource that can be obtained by the system after the parameter content is pushed to the target object, and then, according to the second index value, the target push content is determined from the parameter content, so as to obtain a target push content set, that is, the second index value of each parameter content is obtained, and then, the target push content is determined from the parameter content, for example, the second index value may be a second preset number of parameter content ranked before, or the second index value may be a parameter content exceeding a preset second threshold, and so on, which is not limited in particular.

In this step, the target recall content may be ranked based on the first index value; and then, screening out the preset number of target parameter bidding contents from the target recall contents according to the sequence of the sequencing result from small to large. The preset number can be set according to the requirement of the target object and the computing capability of the system, generally tens to hundreds, and is not limited in particular. Thus, the first index value of the target parameter content is higher, further screening of the target recall content is realized, and the quality of the follow-up push content determination is improved.

Further, after the reference bidding content is screened from the target recall content based on the first index value and the second index value of the reference bidding content is obtained, a new history selection content corresponding to the target object can be determined from the target reference bidding content according to the second index value; and adding the new history selection content into a history selection content set corresponding to the target object.

In one implementation, after the target parameter content is screened out, the target parameter content may be stored in a preset database, and correspondingly, after the push content determination request is received again, the target parameter content stored in the preset database by the terminal in a preset time period may be acquired as a part of the target recall content. Therefore, the target parameter content can be iterated from new to old continuously along with the time, so that the latest preference and habit of the user are learned, and the quality and stability of the subsequent push content determination can be further improved.

In the present disclosure, the second index value refers to a current resource increment value of the reference bid data, and it can be understood that, after determining the push content to the terminal, the data provider provides a corresponding resource increment value as a return, and the higher the second index value, the higher the return provided by the data provider.

In this step, the target parameter content with the maximum second index value may be determined as the new history selection content, or the target parameter content with the second index value greater than the preset threshold may be both determined as the new history selection content, and may be set according to the requirements of the terminal, which is not specifically limited.

It can be understood that this step may be a bidding process, which is a stage that all the determining methods of the recalled content need to go through, so that recalling the historically selected content is equivalent to rescreening the result of each recall to a better result, so that the screened result can pass through the recall and participate in the bidding, which is equivalent to the "length of the collection of hundreds of people", thereby improving the efficiency and quality of the content recall.

In one implementation manner, the current recall content set is obtained based on a preset recall model, after the second index value of the parameter bid content is obtained, the obtained parameter bid content can be used as the current parameter bid content, and the parameter bid content corresponding to the push content determination request sent last time by the target object is obtained and used as the history parameter bid content; determining the difference between the second index values of the current parameter content and the historical parameter content as an index difference value; and adjusting model parameters of the preset recall model according to the index difference value to obtain an adjusted preset recall model.

Specifically, the higher the second index value is, the higher the quality of the parameter content is, and then in the iterative training of the preset recall model, the higher effect of the current parameter content than the second index value of the history parameter content is generally required to be pursued, so that the model parameters of the preset recall model can be adjusted based on the difference between the second index values of the current parameter content and the history parameter content as index difference values, so that the preset recall model has better recall effect.

For example, if the current recall content is video data, the model parameters of the preset recall model may include control parameters for video duration of the previous recall content, for example, the video duration of the current recall content is limited not to exceed the duration corresponding to the model parameters, and after calculating a difference between the second index values of the current reference bid content and the historical reference bid content as the index difference value, if the difference value is a negative number, the second index value of the current reference bid content is lower than the second index value of the historical reference bid content, that is, the second index value corresponding to the current recall content is lower, and the resource increment is less, so that the model parameters of the preset recall model may be modified, for example, a new model parameter may be determined by adopting a dichotomy or the like. Thus, with the increase of the iteration times, the model parameters of the preset recall model gradually tend to the optimal solution, so that the preset recall model has a better recall effect, the second index value corresponding to each content recall is improved, and the resource increment brought by the recall content is increased.

FIG. 3 is a logical schematic diagram of a push content determination process, including targeting, recall, ordering, and presentation. Firstly, determining a candidate content set according to a targeting condition provided by a content provider, then entering a recall stage after receiving a push request of a content receiver, selecting contents with parts matched with the content receiver from the candidate content set, and further, ordering and bidding the contents selected in the recall stage according to the pre-evaluation values of various models in an ordering stage, and finally, pushing the winning contents, namely the target push content set.

In addition, as shown in fig. 4, a logic schematic diagram of the present solution is shown, where the logic schematic diagram includes a new recall, that is, a recall of a history selection content, and then, a target recall content set is subjected to orientation, frequency control, diversity front, effect layer interception, and increment layer, and further, coarse ranking, interception, fine ranking, filtering, ordering, and bidding are further performed, so that the issue of the target push content set is finally realized, where the target push content set may be stored in a database for the next data recall.

The targeting refers to determining the receiving range of each content according to the requirements of a content provider, and comprises crowd targeting, user information, regional targeting and the like. The frequency control refers to control of the push frequency of each content, for example, the push frequency of a certain content may be preset to be once every 10 minutes, and then the content is not pushed to the target object again within 10 minutes. The diversity front-end refers to the diversity setting of the content pushing mode, for example, popup pushing, page plug-in pushing and the like can be adopted when pushing content, and the content of different pushing modes can be selected as far as possible according to the requirement of a target object, so that the diversity of the content pushing is realized. The effect layer cut-off layer is used for further optimizing the push content, further screening can be carried out from the content which is subjected to directional, frequency control and diversity front-end, a part of the content is reserved, and further the screened content is supplemented through the increment layer, so that the more diversified content push is realized. Further, coarse ranking and truncation means that under the condition of large data volume, a coarser ranking model is adopted to perform preliminary ranking on the content according to the predicted resource increment of the content, and a part of the content is intercepted to perform subsequent fine ranking, so that the processing speed and the processing efficiency are improved. Fine ranking refers to further ranking of content based on predicted resource increments using a finer ranking model, and filtering according to ranking results. Finally, the fine-ranked filtered content may enter a ranking and bidding stage from which a final target push content set is determined based on the predicted and current resource increment values, respectively.

Fig. 5 shows another logic diagram of the present solution. In response to the current push content determination request, a target recall content set may be determined, where the target recall content set includes a current recall content set and a history selection content, the current recall content set may include multiple ways, different recall paths perform content recall based on different preset recall rules, respectively, to obtain different current recall content sets, and the history selection content set is a content selected in response to the history push content determination request of the target object. Then, through the steps of directional intersection, sequencing, bidding and the like, a target push content set corresponding to the target object can be determined from the target recall content set, and further, the target push content set is stored in a database and used for obtaining a history selection content set from the target push content set next time. After determining the target push content set, the server may push the target push content set to the terminal of the target object.

Specifically, as shown in fig. 6, a system schematic diagram of the present disclosure is shown, where the system includes a terminal and a server, first, the terminal sends a current push content determining request, and the server receives the current push content determining request sent by the terminal corresponding to the target object; responding to the current push content determining request, and acquiring a current recall content set corresponding to the target object from a candidate content set; acquiring a history selection content set of the target object, wherein the content in the history selection content set is content which is selected by a request for determining a history pushing content in response to the target object; combining the current recall content set and the history selection content to obtain a target recall content set; determining a target push content set corresponding to the target object based on the target recall content set; and pushing the target pushing content set to the terminal of the target object. Thereby realizing content pushing to the terminal of the target object.

From the above, it can be seen that, in the technical solution provided by the embodiments of the present disclosure, when determining push content, the history selection content of the target object is recalled, where the history selection content is selected in response to the history push content determination request of the target object, and is also a content matching with the requirement of the target object, and the method has higher stability, so that the quality of the determined push content is improved, and the accuracy of content push is improved.

According to a second aspect of the embodiments of the present disclosure, there is provided a push content determining apparatus, fig. 7 is a block diagram of a push content determining apparatus according to an exemplary embodiment, as shown in fig. 7, the push content determining apparatus including:

a receiving unit 201 configured to execute a current push content determining request sent by a terminal corresponding to a receiving target object;

a response unit 202 configured to perform obtaining, in response to the current push content determination request, a current recall content set corresponding to the target object from a candidate content set;

an acquisition unit 203 configured to perform acquisition of a history selection content set of the target object, the content in the history selection content set being a content selected in response to a history push content determination request of the target object;

A combining unit 204 configured to perform combining the current recall content set and the history selection content to obtain a target recall content set;

a determining unit 205 configured to perform determining a target push content set corresponding to the target object based on the target recall content set.

In an implementation, the determining unit is further configured to perform:

In one implementation, the determining unit is specifically configured to perform:

In an implementation, the current recall content set is obtained based on a preset recall model, and the determining unit is further configured to perform:

In one implementation, the acquiring unit is configured to perform:

In one implementation, the history selection content set is acquired from a preset database, the preset database stores a plurality of history selection contents corresponding to the history push content determination requests, each history push content determination request has a corresponding request time, and the acquiring unit is configured to perform:

The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory, comprising instructions executable by a processor of an electronic device to perform the above-described method. Alternatively, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, a computer program product is also provided which, when run on a computer, causes the computer to implement the method of push content determination described above.

Fig. 9 is a block diagram illustrating an apparatus 800 for push content determination, according to an example embodiment.

For example, apparatus 800 may be a mobile phone, computer, digital broadcast electronic device, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to fig. 9, apparatus 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices 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 memory, flash memory, magnetic or optical disk.

Power supply component 807 provides power to the various components of device 800. Power supply component 807 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for device 800.

The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the device 800 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the apparatus 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the apparatus 800, the sensor assembly 814 may also detect a change in position of the apparatus 800 or one component of the apparatus 800, the presence or absence of user contact with the apparatus 800, an orientation or acceleration/deceleration of the apparatus 800, and a change in temperature of the apparatus 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communication between the apparatus 800 and other devices, either in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi, an operator network (e.g., 2G, 3G, 4G, or 5G), or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by 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, microcontrollers, microprocessors or other electronic elements for executing the methods described in the first and second aspects.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including instructions executable by processor 820 of apparatus 800 to perform the above-described method. Alternatively, for example, the storage medium may be a non-transitory computer-readable storage medium, which may be, for example, ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.

In an exemplary embodiment, a computer program product containing instructions is also provided which, when run on a computer, causes the computer to perform the push content determination method described in the above embodiments.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A push content determination method, comprising:

determining a target push content set corresponding to the target object based on the target recall content set;

the obtaining the historical selection content set of the target object includes:

screening candidate selected contents of which the third index value meets a threshold value condition to form a history selected content set;

the determining the target push content set corresponding to the target object based on the target recall content set comprises the following steps:

2. The push content determination method of claim 1, wherein after the screening of the parameter content from the target recall content based on the first index value and the acquisition of the second index value of the parameter content, the method further comprises:

3. The push content determination method of claim 1, wherein the current set of recall content is derived based on a preset recall model, the method further comprising, after the obtaining the second index value for the reference content:

4. The push content determining method according to claim 1, wherein the set of history selected content is obtained from a preset database storing a plurality of history selected content corresponding to the history push content determining requests, each history push content determining request having a corresponding request time, the obtaining the set of history selected content of the target object comprising:

5. A push content determination device, comprising:

A determining unit configured to perform determining a target push content set corresponding to the target object based on the target recall content set;

the acquisition unit is configured to perform:

the determining unit is further configured to perform:

6. The push content determining device according to claim 5, wherein the determining unit is specifically configured to perform:

7. The push content determination device of claim 5, wherein the current set of recall content is derived based on a preset recall model, the determination unit further configured to perform:

8. The push content determining device according to claim 5, wherein the set of history selected content is obtained from a preset database storing a plurality of history selected content corresponding to the history push content determining requests, each history push content determining request having a corresponding request time, the obtaining unit being configured to perform:

9. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the push content determination method of any one of claims 1 to 6.

10. A computer readable storage medium, wherein instructions in the computer readable storage medium, when executed by a processor of a push content determining electronic device, enable the push content determining electronic device to perform the push content determining method of any of claims 1 to 4.

11. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the push content determining method of any of claims 1 to 4.