CN112667892A

CN112667892A - Information recommendation method, device, server and storage medium

Info

Publication number: CN112667892A
Application number: CN202011567217.2A
Authority: CN
Inventors: 袁德东; 陆子龙
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-12-25
Filing date: 2020-12-25
Publication date: 2021-04-16
Anticipated expiration: 2040-12-25
Also published as: CN112667892B

Abstract

The disclosure relates to an information recommendation method, an information recommendation device, a server and a storage medium, and relates to the technical field of data processing, so as to at least solve the problem of how to ensure the accuracy of targeted people in the related technology. The method comprises the following steps: acquiring a work conversion rate and at least one behavior operation conversion rate of an account within the statistical time length; the work conversion rate is the conversion rate of a target work in a preset category work, the behavior operation conversion rate is the conversion rate of the target work corresponding to the target behavior operation, the target behavior operation is the behavior operation recorded by an account in the preset category work, and different behavior operations correspond to different behavior operation conversion rates; determining the proportion of each behavior operation conversion rate in the work conversion rate; determining the attention degree of the account to works of a preset category according to the determined ratio of each behavior operation conversion rate to the work conversion rate; and delivering the works to be delivered to the account under the condition that the attention degree is greater than or equal to the attention degree threshold value.

Description

Information recommendation method, device, server and storage medium

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to an information recommendation method, an information recommendation apparatus, a server, and a storage medium.

Background

Currently, in the process of delivering a work, people targeting processing is usually performed on the work to determine a targeted crowd of the work (the targeted crowd includes potential audiences related to the work); the work is then delivered in a targeted population.

Therefore, crowd orientation is a very important link in the work putting process, and the accuracy of the oriented crowd is closely related to the work putting effect. Therefore, how to ensure the accuracy of the targeted population is very important.

Disclosure of Invention

The present disclosure provides an information recommendation method, apparatus, server and storage medium to at least solve the problem of how to ensure the accuracy of targeted people in the related art.

The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided an information recommendation method, including: and acquiring the work conversion rate and at least one behavior operation conversion rate of the account within the statistical time length. The work conversion rate is the conversion rate of a target work in a preset category work, the behavior operation conversion rate is the conversion rate of the target work corresponding to the target behavior operation, the target behavior operation is the behavior operation recorded by the account in the preset category work, and different behavior operations correspond to different behavior operation conversion rates. Determining the proportion of each behavior operation conversion rate in the work conversion rate; and determining the attention degree of the account to the preset type of works according to the determined ratio of each behavior operation conversion rate to the work conversion rate. And delivering the works to be delivered to the account under the condition that the attention degree is greater than or equal to the attention degree threshold value. Wherein, the category to which the works to be released belong is a preset category.

In an implementation manner, the "obtaining at least one behavior operation conversion rate within the statistical time length" may be specifically realized by the following steps: acquiring at least one target behavior operation executed by the account in the preset category of works within the statistical duration; and inquiring the behavior operation conversion rate corresponding to each target behavior operation in the corresponding relation between the target behavior operations and the behavior operation conversion rates, and determining at least one behavior operation conversion rate in the statistical duration.

In an implementable manner, the step of obtaining the correspondence includes: acquiring conversion data, the total number of the first account numbers and the total number of the second account numbers; the conversion data comprises data of conversion operation recorded on a target work by account numbers, the total number of first account numbers is the number of account numbers with target behavior operation recorded in a preset type of target work, and the total number of second account numbers is the number of account numbers with target behavior operation recorded in the preset type of target work and with target operation executed on the target work; determining the behavior operation conversion rate corresponding to the target behavior operation as the proportion of the total number of the second account numbers in the total number of the first account numbers; and generating a corresponding relation containing the behavior operation conversion rate corresponding to each target behavior operation.

In an implementation manner, the "obtaining the conversion rate of the work within the statistical time" may be specifically implemented by the following steps: acquiring conversion data, the total number of the third account and the total number of the fourth account within the statistical time length; the conversion data comprises data of conversion operation recorded on a target work by account numbers, the total number of the third account numbers is the number of the account numbers with behavior operation recorded in the preset category work within the counting time, the total number of the fourth account numbers is the number of the account numbers with behavior operation recorded in the preset category work within the counting time, and the number of the account numbers with the conversion operation is recorded on the target work; and determining the conversion rate of the works in the statistical time length as the proportion of the total number of the fourth account numbers in the total number of the third account numbers.

In a practical manner, the above "determining the percentage of the conversion rate of each behavior operation in the conversion rate of the work" can be realized by the following steps: determining the difference value of the operation conversion rate and the work conversion rate of each behavior; and determining the ratio of the operation conversion rate of each behavior in the conversion rate of the work according to the determined difference and the conversion rate of the work.

In one embodiment, the ratio satisfies the following equation:

wherein,

indicating duty, action _ cvr indicating behavior operation conversion rate, and avg _ cvr indicating work conversion rate.

In an implementable manner, the "determining the attention of the account to the preset type of works according to the determined percentage of each behavior operation conversion rate in the work conversion rate" may specifically be implemented by the following steps: acquiring the number of unit time contained in the statistical time length; and determining the attention of the account to the preset type of works according to the determined ratio and number.

In one embodiment, the above-mentioned attention satisfies the following formula:

wherein S is_xRepresenting the attention, T representing the number, n representing the total number of target behavior operations executed by the account in the works of the preset category,

representing the proportion of the behavior operation conversion rate corresponding to the target behavior operation i in the work conversion rate, wherein i is an integer and is within the range of [1, n ∈]A is more than 0 and less than or equal to 1, b is more than 0 and less than or equal to 1, and a + b is equal to 1.

According to a second aspect of the embodiments of the present disclosure, there is provided an information recommendation apparatus including: an acquisition unit and a processing unit.

The obtaining unit is configured to obtain a work conversion rate and at least one behavior operation conversion rate of the account within the statistical time length; the work conversion rate is the conversion rate of a target work in a preset category of works, the behavior operation conversion rate is the conversion rate of the target work corresponding to the target behavior operation, the target behavior operation is the behavior operation executed by the account in the preset category of works, and different behavior operations correspond to different behavior operation conversion rates; a processing unit configured to determine a ratio of the behavior operation conversion rate acquired by each acquisition unit to the work conversion rate acquired by the acquisition unit; the processing unit is further configured to determine the attention degree of the account to works of a preset category according to the determined proportion of each behavior operation conversion rate in the work conversion rate; the processing unit is further configured to release the works to be released to the account under the condition that the attention degree is greater than or equal to the attention degree threshold; wherein, the category to which the works to be released belong is a preset category.

In an implementable manner, the obtaining unit is specifically configured to obtain at least one target behavior operation executed by an account in a preset category of works within a statistical duration; and the processing unit is specifically configured to query the behavior operation conversion rate corresponding to the target behavior operation acquired by each acquisition unit in the corresponding relationship between the target behavior operation and the behavior operation conversion rate, and determine at least one behavior operation conversion rate within the statistical time length.

In an implementation manner, the obtaining unit is specifically configured to obtain the conversion data, the total number of the first account numbers and the total number of the second account numbers; the conversion data comprises data of conversion operation recorded on a target work by account numbers, the total number of first account numbers is the number of account numbers with target behavior operation recorded in a preset type of target work, and the total number of second account numbers is the number of account numbers with target behavior operation recorded in the preset type of target work and with target operation executed on the target work; the processing unit is specifically configured to determine a behavior operation conversion rate corresponding to the target behavior operation as a proportion of the total number of the second account acquired by the acquisition unit to the total number of the first account acquired by the acquisition unit; and the processing unit is specifically configured to generate a corresponding relation containing behavior operation conversion rates corresponding to each target behavior operation.

In an implementation manner, the obtaining unit is specifically configured to obtain the conversion data, the total number of the third account numbers and the total number of the fourth account numbers within the statistical duration; the conversion data comprises data of conversion operation recorded on a target work by account numbers, the total number of the third account numbers is the number of the account numbers with behavior operation recorded in the preset category work within the counting time, the total number of the fourth account numbers is the number of the account numbers with behavior operation recorded in the preset category work within the counting time, and the number of the account numbers with the conversion operation is recorded on the target work; the processing unit is specifically configured to determine the work conversion rate in the statistical duration as a proportion of the total number of the fourth account acquired by the acquiring unit to the total number of the third account acquired by the acquiring unit.

In an implementable manner, the processing unit is specifically configured to determine a difference between the behavior operation conversion rate acquired by each acquisition unit and the work conversion rate acquired by the acquisition unit; and the processing unit is specifically configured to determine the proportion of each behavior operation conversion rate in the work conversion rate according to the determined difference and the work conversion rate acquired by the acquisition unit.

In one implementable manner, the ratio satisfies the following formula:

wherein,

In an implementable manner, the obtaining unit is specifically configured to obtain the number of unit times included in the statistical time length; and the processing unit is specifically configured to determine the attention degree of the account to the preset type of works according to the determined ratio and the number acquired by the acquiring unit.

In one practical approach, the attention satisfies the following equation:

According to a third aspect of the embodiments of the present disclosure, there is provided a server, including:

a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the information recommendation method provided by the first aspect.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions of the storage medium, when executed by a processor of the server provided by the third aspect, enable the server to perform the information recommendation method provided by the first aspect.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product, including instructions that, when executed on a computer, cause the computer to perform the information recommendation method according to the first aspect.

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

according to the information recommendation method, the proportion of each behavior operation conversion rate in the work conversion rate can be determined according to the work conversion rate of the preset category and at least one behavior operation conversion rate of the account. And then, determining the attention of the account to the preset type of works according to the determined ratio of each behavior operation conversion rate to the work conversion rate. And when the attention degree is determined to be greater than or equal to the attention degree threshold value and the category to which the to-be-released work belongs is a preset category, releasing the to-be-released work to the account, so that at least one account for releasing the to-be-released work can be selected according to the attention degree, and the problem of directing people is solved. Meanwhile, the attention degree of each account number in the targeted crowd is larger than or equal to the attention degree threshold value, so that the conversion rate of the works to be released can be improved, and the problem of how to ensure the accuracy of the targeted crowd in the related technology is solved.

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 present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is an architectural diagram illustrating one implementation environment in accordance with an exemplary embodiment.

Fig. 2 is one of flowcharts illustrating an information recommendation method according to an example embodiment.

Fig. 3 is a second flowchart illustrating a method of information recommendation according to an example embodiment.

Fig. 4 is a third flowchart illustrating an information recommendation method according to an example embodiment.

FIG. 5 is a diagram illustrating a table of total praise counts versus behavioral operation conversion rates in accordance with an exemplary embodiment.

Fig. 6 is a diagram illustrating a table of total forwarding numbers versus behavioral operation conversion rates in accordance with an exemplary embodiment.

Fig. 7 is one of schematic structural diagrams of an information recommendation apparatus according to an exemplary embodiment.

Fig. 8 is a second schematic structural diagram of an information recommendation apparatus according to an exemplary embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in 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 above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

In the embodiment of the present disclosure, the preset-category work may be a pure video or an image which is produced by an account providing the work and does not include any description information, and the other accounts obtaining the preset-category work can only understand the content of the preset-category work through themselves. Works of the preset category can also be videos or images which are made by the account and carry corresponding text or voice description information so as to explain or transmit the expressed resource content to other accounts, and for the image-text works containing the description information, the actual content of the image-text resource can be determined according to the description information. Teletext refers to a video or image containing textual and/or speech descriptive information.

Crowd targeting refers to the process of screening out potential audiences that are most relevant to a work to be delivered (also referred to as a target work). The potential audience may also be called a targeted user, specifically, a potential recipient who has a high probability of receiving the target work, or a potential recipient who has a high probability of receiving the target work and performs a conversion operation on the target work (for example, filling a form, downloading a preset application program, or communicating with a preset account). Research shows that in the process of delivering a target work, the accuracy of crowd targeting is generally in direct proportion to the work conversion rate (CVR) or Click Through Rate (CTR) of the target work; that is, the higher the accuracy of crowd orientation, the higher the conversion rate of the target works. The work conversion rate can also be called exposure rate, and is the ratio of the number of actual exposure users in the targeted population to the total number of users of the targeted population, wherein the number of the actual exposure users is the number of users who have conversion operation on the target work within the statistical duration; the work conversion rate can be used for measuring the proportion of users who actually have the target work in the targeted crowd, namely the work conversion rate can be used for measuring the proportion of users who actually see the target work in the targeted crowd. For example, if the total number of users in the targeted crowd is 500, and the number of users who have conversion operations on the target work within the statistical time length is 450, the work conversion rate (exposure rate) is equal to 450/500-90%; if the number of users who have conversion operations on the target work within the statistical time period is 200, the work conversion rate (exposure rate) is equal to 200/500-40%. The statistical duration here may be set according to actual service requirements, and this disclosure does not specifically limit this.

Therefore, crowd orientation is a very important link in the process of putting the works to be put; this process of crowd targeting is not left from the perspective of the delivery user (i.e., the user who has a need to deliver the work to be delivered) or from the perspective of the traffic side (e.g., the information recommendation system). For example, for a delivery owner, a low exposure rate means that a budget for delivering a work to be delivered is not effectively consumed, and a user group with a sufficient scale cannot be reached; whereas for the traffic side, low exposure affects the yield. Therefore, in order to better perform crowd orientation to improve the conversion rate of works, the embodiment of the disclosure provides an information recommendation method; the information recommendation method can be applied to an information recommendation system, wherein the information recommendation system can provide an information recommendation media platform and can deliver works on the information recommendation media platform for delivery users.

Fig. 1 is an architecture diagram illustrating an implementation environment in which the following information recommendation method may be applied, as shown in fig. 1, according to an example embodiment. The implementation environment comprises a delivery user 01, a server 02 and a targeted crowd 03 (comprising N users, wherein N is an integer greater than or equal to 0). When the delivery user 01 wants to determine the targeted crowd 03 of the works to be delivered, a crowd targeting request may be sent to a background server (hereinafter referred to as a server) through a front end of the information recommendation system, as shown in fig. 1. After receiving the crowd directing request, the server 02 may respond to the crowd directing request to execute the information recommendation method to determine the preset category to which the work to be delivered belongs and the attention of each user to the work of the preset category, and further determine the targeted crowd 03 interested in the work to be delivered according to the attention.

In an implementation manner, the server 02 may be a server, a server cluster composed of a plurality of servers, or a cloud computing service center. The server 02 may include a processor, memory, and a network interface, among others.

Based on this, in the information recommendation method, according to the work conversion rate of the preset category and at least one behavior operation conversion rate of the account, the ratio of each behavior operation conversion rate in the work conversion rate may be determined. And then, determining the attention of the account to the preset type of works according to the determined ratio of each behavior operation conversion rate to the work conversion rate. When the attention degree is determined to be larger than or equal to the attention degree threshold value and the category to which the to-be-released works belong is a preset category, the to-be-released works are released to the account number, so that at least one account number for releasing the to-be-released works can be selected according to the attention degree, the problem of orienting people is solved, the user experience is guaranteed while the conversion rate of the to-be-released works is improved, the problem of how to guarantee the accuracy of the oriented people in the related technology is solved, and the specific implementation process is as follows:

an execution subject of the information recommendation method provided by the embodiment of the present disclosure may be the information recommendation device, the information recommendation device may be a server, or may also be a functional module and/or a functional entity capable of implementing the information recommendation method in the server, which may be specifically determined according to actual use requirements, and the embodiment of the present disclosure is not limited. The following describes an information recommendation method provided by an embodiment of the present disclosure by taking an execution subject as an information recommendation device as an example.

Those skilled in the art will appreciate that the above-described server is merely exemplary and that other devices, existing or hereafter developed, that may be suitable for use with the present disclosure are also included within the scope of the present disclosure and are hereby incorporated by reference.

The data to which the present disclosure relates may be data that is authorized by a user or sufficiently authorized by parties.

The following describes an information recommendation method provided by an embodiment of the present disclosure by way of example with reference to the accompanying drawings.

Fig. 2 is a flowchart illustrating an information recommendation method according to an exemplary embodiment, where the information recommendation method is used in an information recommendation apparatus as illustrated in fig. 2, and the method includes the following S11-S14.

And S11, the information recommending device acquires the work conversion rate and at least one behavior operation conversion rate of the account within the statistical time length. The work conversion rate is the conversion rate of a target work in a preset category work, the behavior operation conversion rate is the conversion rate of the target work corresponding to the target behavior operation, the target behavior operation is the behavior operation recorded by the account in the preset category work, and different behavior operations correspond to different behavior operation conversion rates.

In an implementation manner, since the classification of the works in the prior art is not accurate enough, the conversion rate of the account to the works of the preset category cannot be accurately obtained. Therefore, a complete classification system for the work needs to be established. Specifically, the preset category to which the work belongs can be determined according to a preset classification model, so that the work can be classified more accurately, and the preset category to which the work belongs can be determined. The training process of the category classification model is as follows:

the information recommendation device obtains the training sample works and the labeling results of the training sample works. The training sample works correspond to the same keyword, the categories comprise at least one keyword, and the labeling result comprises preset categories to which the training sample works belong;

the information recommendation device inputs the training sample works into a preset algorithm.

The information recommendation device determines whether the prediction result of the training sample work output by the preset algorithm is matched with the labeling result or not based on the preset algorithm.

And when the prediction result is not matched with the labeling result, the information recommendation device iteratively updates the network parameters of the preset algorithm repeatedly and circularly until the model converges to obtain the category classification model.

For example, the predetermined algorithm may be BERT (bidirectional Encoder replication from transformations), or FastText.

Specifically, the preset categories sequentially include at least any one of a primary category, a secondary category and a tertiary category.

Illustratively, when it is desired to classify works of education, the primary category may be basic education, the secondary category is primary education, and the tertiary category is grade one, if the preset categories include the primary category, the secondary category, and the tertiary category.

When the works of the mother and the baby need to be classified, if the categories comprise a first-level category, a second-level category and a third-level category, the first-level category can be the mother and the baby, the second-level category is the baby, and the third-level category is 0-12 months.

The above description of the preset category is only an exemplary description, and may be set according to actual requirements, and the present disclosure does not specifically limit this.

Specifically, the behavior operation includes at least one of viewing duration, appreciation, approval, forwarding, comment, attention, click, payment, form submission, and search.

For example, assuming that the user a approves the preset category of work 1 for 3 times and forwards the preset category of work 1 for 3 times, the user a approves the preset category of work 2 for 2 times and forwards the preset category of work 2 for 1 time, the user a approves the preset category of work 3 for 5 times and forwards the preset category of work 3 for 3 times, and the user a performs the target behavior on the preset category of work for 10(3+2+5) times and forwards the preset category of work 3 for 7(3+1+3) times.

In an implementation manner, the information recommendation device can acquire each behavior operation of the user on the preset class of works within the statistical time length through the data source as shown in table 1.

TABLE 1

In an implementation manner, the information recommendation method provided by the embodiment of the disclosure may also classify the author of each work in the preset category based on Natural Language Processing (NLP), such as a teacher engaged in primary education or a teacher of a professional education training institution, so as to determine the preset category to which each author belongs.

Specifically, keywords may be determined according to short text matching and/or text classification, a certain range of authors (each author corresponds to at least one tag (also referred to as a keyword)) is defined according to the keywords, each author is classified through fasttest, erroneous data is labeled, and iteration is performed continuously, so that a category classification model is obtained.

S12, the information recommending device determines the proportion of each action operation conversion rate in the work conversion rate.

And S13, the information recommending device determines the attention degree of the account to the preset type of works according to the determined proportion of each behavior operation conversion rate in the work conversion rate.

And S14, the information recommending device delivers the works to be delivered to the account under the condition that the attention degree is greater than or equal to the attention degree threshold. Wherein, the category to which the works to be released belong is a preset category.

As can be seen from the above, the information recommendation method according to the embodiment of the present disclosure determines the attention degree of the account to the works of the preset category according to the work conversion rate of the preset category and at least one behavior operation conversion rate of the account. And when the attention degree is determined to be greater than or equal to the attention degree threshold value and the attributive category of the works to be released is the preset category, releasing the works to be released to the account, so that the conversion rate of the works to be released is improved, the user experience is guaranteed, and the problem of how to guarantee the accuracy of the targeted population in the related technology is solved.

In an implementation manner, as shown in fig. 3 in conjunction with fig. 2, the above S11 can be specifically realized by the following S110 and S111.

S110, the information recommendation device obtains at least one target behavior operation executed by the account in the works of the preset category within the statistical time length.

S111, the information recommending device inquires the behavior operation conversion rate corresponding to each target behavior operation in the corresponding relation between the target behavior operation and the behavior operation conversion rate, and determines at least one behavior operation conversion rate within the statistical duration.

As can be seen from the above, according to the information recommendation method provided in the embodiment of the disclosure, through the predetermined corresponding relationship, the information recommendation device can query the behavior operation conversion rate corresponding to each target behavior operation in the corresponding relationship, determine at least one behavior operation conversion rate within the statistical duration, conveniently determine at least one behavior operation conversion rate of each account within the statistical duration, and improve user experience.

In a practical manner, in conjunction with fig. 3, as shown in fig. 4, the information recommendation method provided by the embodiment of the present disclosure further includes S15, S16, and S17.

And S15, the information recommendation device acquires the conversion data, the total number of the first account numbers and the total number of the second account numbers. The conversion data comprises data of conversion operation recorded on a target work by account numbers, the total number of first account numbers is the number of account numbers with target behavior operation recorded in a preset type of target work, and the total number of second account numbers is the number of account numbers with target behavior operation recorded in a preset type of target work and with target operation executed on the target work.

In an implementation manner, when the information recommendation device acquires the conversion data, the form filling record within the statistical duration can be acquired in the background. The form filling record records the conversion operation of the account on the target work.

And S16, the information recommending device determines that the behavior operation conversion rate corresponding to the target behavior operation is the proportion of the total number of the second account in the total number of the first account.

And S17, the information recommendation device generates a corresponding relation containing behavior operation conversion rates corresponding to the target behavior operations.

In an implementation manner, the corresponding relationship may be a relationship table, and the information recommendation device may generate a relationship table including a behavior operation conversion rate corresponding to each target behavior operation, so that when at least one target behavior operation executed by the account in the preset category of works is obtained, the at least one behavior operation conversion rate of the account is determined by querying a behavior operation conversion rate corresponding to each target behavior operation in the relationship table of the target behavior operation and the behavior operation conversion rate.

Illustratively, education is based on preset categories, data is converted into form data, behavior operation is like praise, and the corresponding relation is a relation table, and the relation table is generated by the following steps:

1. and acquiring the total praise number of each account number praise on the basic education works within the statistical duration, and the form data.

2. And acquiring the total number of the accounts with the total praise number N (namely the total number of the first accounts). N is an integer greater than or equal to 0.

3. In the account with the total number of praise N as N, the total number of accounts with conversion operation (i.e. the total number of the second account) is queried in the form data.

4. And determining the behavior operation conversion rate corresponding to the total praise number N as the proportion of the total number of the second accounts in the total number of the first accounts. Wherein, the behavior operation conversion rate corresponding to each total praise number is shown in table 2.

TABLE 2

Total number of praise	1	2	……	N
					Conversion rate of behavior operation	a	b	……	c

5. And drawing a relation table according to the behavior operation conversion rate corresponding to each total praise number recorded in the table 2.

Illustratively, the relationship table is shown in FIG. 5.

Specifically, the obtaining manner of the corresponding relationship of the other behavior operations is the same as the obtaining manner of the corresponding relationship of the praise, and details are not repeated here.

The above description of the corresponding relationship is only an exemplary description, and the corresponding relationship may be determined according to actual requirements, and the disclosure does not specifically limit this.

Therefore, the information recommendation method provided by the embodiment of the disclosure can determine whether the user has a conversion operation on the target work by acquiring the conversion data, and thus can determine the total number of the second account based on the conversion data. Then, a behavior operation conversion rate corresponding to one target behavior operation may be calculated as a ratio of the total number of the second account numbers to the total number of the first account numbers. And finally, generating a corresponding relation containing the behavior operation conversion rate corresponding to each target behavior operation according to the behavior operation conversion rate corresponding to each target behavior operation, so that the subsequent use is facilitated.

In an implementation manner, as shown in fig. 3 in conjunction with fig. 2, the step S11 can be specifically implemented by the following steps S112 and S113.

And S112, the information recommendation device acquires the conversion data, the total number of the third account and the total number of the fourth account within the statistical duration. The conversion data comprises data of conversion operation recorded on a target work by account numbers, the total number of the third account numbers is the number of the account numbers with behavior operation recorded in the preset category work within the counting time, the total number of the fourth account numbers is the number of the account numbers with behavior operation recorded in the preset category work within the counting time, and the number of the account numbers with the conversion operation is recorded on the target work.

Specifically, the converted data in S112 is obtained in a manner similar to that of the converted data in S15, and is not described here again.

S113, the information recommending device determines that the conversion rate of the works in the counting time length is the proportion of the total number of the fourth account in the total number of the third account.

Illustratively, for example, based on education in a predetermined category, the step of converting data into tabular data, determining the conversion rate of the work, is as follows:

1. and acquiring the total number of the account numbers with the behavior operation on the basic education works (namely the total number of the third account numbers) and form data within the counting time length.

2. In the form data, the total number of the account numbers of the conversion operation (i.e., the total number of the fourth account number) exists in the account numbers of the behavior operation on the basic educational works in the statistical time period.

3. And determining the conversion rate of the works in the statistical time length as the proportion of the total number of the fourth account numbers in the total number of the third account numbers.

According to the information recommendation method provided by the embodiment of the disclosure, whether the user has conversion operation on the target work can be determined by acquiring the conversion data, so that the total number of the fourth account can be determined based on the conversion data. Then, the conversion rate of the work within the statistical time length is determined as the proportion of the total number of the fourth account numbers in the total number of the third account numbers. Further, a percentage of each behavioral operational conversion rate of the account in the work conversion rate may be determined based on the work conversion rate. And then, according to the ratio of each behavior operation conversion rate of the account in the conversion rate of the works, determining the attention degree of the account to the works of the preset category, and conveniently improving the conversion rate of the works to be released in the follow-up release.

In an implementation manner, referring to fig. 2, as shown in fig. 3, the above S12 can be specifically realized by the following S120 and S121.

And S120, the information recommending device determines the difference value between the operation conversion rate and the work conversion rate of each behavior.

And S121, determining the proportion of each behavior operation conversion rate in the work conversion rate by the information recommending device according to the determined difference value and the work conversion rate.

As can be seen from the above, the information recommendation method provided in the embodiment of the present disclosure calculates the difference between each behavior operation conversion rate and the work conversion rate, so that the ratio of each behavior operation conversion rate in the work conversion rate can be determined according to the determined difference and the work conversion rate. And then, according to the ratio of each behavior operation conversion rate of the account in the conversion rate of the works, determining the attention degree of the account to the works of the preset category, and conveniently improving the conversion rate of the works to be released in the follow-up release.

In one embodiment, the ratio satisfies the following equation:

wherein,

Exemplarily, assuming that the work conversion rate of the preset category work is 50%, within the statistical time period, the user a approves 1 time of the preset category work 1 and forwards 3 times of the preset category work 1, the user a approves 1 time of the preset category work 2 and forwards 3 times of the preset category work 2, the user B approves 1 time of the preset category work 1 and forwards 5 times of the preset category work 1, the user B approves 1 time of the preset category work 2 and forwards 7 times of the preset category work 2, and then the calculation process of the behavior operation conversion rate is as follows:

according to the total number 2(1+1) of the praise of the user a in the preset works, querying the relation table shown in fig. 5, determining that the behavioral operation conversion rate corresponding to the target behavioral operation (praise 2) of the user a in the preset works is 2%, and knowing from the formula that the percentage of the behavioral operation conversion rate corresponding to the praise 2 of the user a in the preset works in the work conversion rate is equal to or higher than the total product conversion rate of the user a in the preset works of the preset works (1+1)

According to the total number of times 2(1+1) of the approval of the user B in the preset type of work, querying the relation table shown in fig. 5, determining that the behavior operation conversion rate corresponding to the target behavior operation (2 approvals) of the user B in the preset type of work is 2%, and knowing from the above formula that the percentage of the behavior operation conversion rate corresponding to the 2 approvals of the user B in the preset type of work in the work conversion rate is equal to or higher than the work conversion rate

According to the total number of times 6(3+3) of forwarding of the user a on the preset category work, a relation table (including behavior operation conversion rate corresponding to each total forwarding number) shown in fig. 6 is inquired, the behavior operation conversion rate corresponding to the target behavior operation (forwarding 6 times) of the user a on the preset category work is determined to be 2.5%, and the formula shows that the proportion of the behavior operation conversion rate corresponding to the forwarding 6 times of the user a on the preset category work in the work conversion rate is equal to or higher than the work conversion rate

According to the total number of times 12(5+7) of forwarding of the user B on the preset type of works, querying a relation table shown in fig. 6, determining that the behavior operation conversion rate corresponding to the target behavior operation (forwarding 12 times) of the user B on the preset type of works is 2.5%, and knowing from the formula that the ratio of the behavior operation conversion rate corresponding to the forwarding 12 times of the user B on the preset type of works in the work conversion rate is equal to or higher than the work conversion rate

As can be seen from the above, the information recommendation method provided by the embodiment of the present disclosure can determine the ratio of the conversion rate of each behavior operation in the conversion rate of the work by calculating each difference value and the ratio of the conversion rate in the conversion rate of the work. And then, according to the ratio of each behavior operation conversion rate of the account in the conversion rate of the works, determining the attention degree of the account to the works of the preset category, and conveniently improving the conversion rate of the works to be released in the follow-up release.

In an implementation manner, referring to fig. 2, as shown in fig. 3, the above S13 can be specifically realized by the following S130 and S131.

S130, the information recommending device obtains the number of unit time contained in the statistical time length.

In an achievable procedure, the number of time units included in the statistical time duration is equal to 7, if the statistical time duration is one week.

S131, the information recommending device determines the attention degree of the account to the preset type of works according to the determined proportion and number.

Therefore, according to the information recommendation method provided by the embodiment of the disclosure, the number of the unit time included in the statistical duration is calculated, so that the attention degree of the account to the preset type of works can be determined according to the determined proportion and number, and the conversion rate of the subsequent works to be released is conveniently improved.

For example, assuming that a is equal to 0.2, B is equal to 0.8, the statistical duration is 1 week, the unit time is day, both the user a and the user B perform only approval and forwarding on the preset-class work within the statistical duration, the percentage of the behavioral operation conversion rate corresponding to 2 approval times of the user a on the preset-class work in the work conversion rate is 0.96, the percentage of the behavioral operation conversion rate corresponding to 2 approval times of the user B on the preset-class work in the work conversion rate is 0.96, the percentage of the behavioral operation conversion rate corresponding to 6 forwarding times of the user a on the preset-class work in the work conversion rate is 0.95, the percentage of the behavioral operation conversion rate corresponding to 12 forwarding times of the user B on the preset-class work in the work conversion rate is 0.90, and the calculation process of the attention of each user on the preset-class work is as follows:

the degree of attention of the user a to the preset category work is equal to (0.2 × 7) × (0.8 × (0.96+0.95)) -2.1392.

The degree of attention of the user B to the preset category work is equal to (0.2 × 7) × (0.8 × (0.96+0.90)) -2.0832.

Therefore, the information recommendation method provided by the embodiment of the disclosure can determine the attention degree of the account to the preset type of works according to the number of unit time included in the statistical duration and the at least one behavior operation conversion force of the account in the statistical duration based on the formula that the attention degree satisfies, and conveniently improve the conversion rate of the subsequent works for putting the works to be put in.

Fig. 7 is a block diagram illustrating an information recommendation apparatus according to an example embodiment. Referring to fig. 7, the information recommendation apparatus 10 includes an acquisition unit 101 and a processing unit 102.

An obtaining unit 101 configured to obtain a work conversion rate and at least one behavior operation conversion rate of an account within a statistical time length; the work conversion rate is the conversion rate of a target work in a preset category of works, the behavior operation conversion rate is the conversion rate of the target work corresponding to the target behavior operation, the target behavior operation is the behavior operation executed by the account in the preset category of works, and different behavior operations correspond to different behavior operation conversion rates; a processing unit 102 configured to determine a ratio of the behavior operation conversion rate acquired by each acquisition unit 101 to the work conversion rate acquired by the acquisition unit 101; the processing unit 102 is further configured to determine the attention degree of the account to the works of the preset category according to the determined percentage of each behavior operation conversion rate in the work conversion rate; the processing unit 102 is further configured to deliver the works to be delivered to the account under the condition that the attention degree is greater than or equal to the attention degree threshold; wherein, the category to which the works to be released belong is a preset category.

In an implementable manner, the obtaining unit 101 is specifically configured to obtain at least one target behavior operation executed by an account in a preset category of works within a statistical duration; the processing unit 102 is specifically configured to query, in the correspondence between the target behavior operation and the behavior operation conversion rate, a behavior operation conversion rate corresponding to the target behavior operation acquired by each acquiring unit 101, and determine at least one behavior operation conversion rate within the statistical duration.

In an implementation manner, the obtaining unit 101 is specifically configured to obtain the conversion data, the total number of the first account numbers and the total number of the second account numbers; the conversion data comprises data of conversion operation recorded on a target work by account numbers, the total number of first account numbers is the number of account numbers with target behavior operation recorded in a preset type of target work, and the total number of second account numbers is the number of account numbers with target behavior operation recorded in the preset type of target work and with target operation executed on the target work; the processing unit is specifically configured to determine a behavior operation conversion rate corresponding to the target behavior operation as a proportion of the total number of the second account acquired by the acquisition unit 101 to the total number of the first account acquired by the acquisition unit 101; and the processing unit is specifically configured to generate a corresponding relation containing behavior operation conversion rates corresponding to each target behavior operation.

In an implementation manner, the obtaining unit 101 is specifically configured to obtain the conversion data, the total number of the third account and the total number of the fourth account within the statistical duration; the conversion data comprises data of conversion operation recorded on a target work by account numbers, the total number of the third account numbers is the number of the account numbers with behavior operation recorded in the preset category work within the counting time, the total number of the fourth account numbers is the number of the account numbers with behavior operation recorded in the preset category work within the counting time, and the number of the account numbers with the conversion operation is recorded on the target work; the processing unit 102 is specifically configured to determine the work conversion rate in the statistical duration as a proportion of the total number of the fourth account acquired by the acquiring unit 101 to the total number of the third account acquired by the acquiring unit 101.

In an implementable manner, the processing unit 102 is specifically configured to determine a difference between the behavior operation conversion rate acquired by each acquisition unit 101 and the work conversion rate acquired by the acquisition unit 101; the processing unit 102 is specifically configured to determine a ratio of each behavior operation conversion rate in the work conversion rate according to the determined difference and the work conversion rate acquired by the acquisition unit 101.

In one implementable manner, the ratio satisfies the following formula:

wherein,

In an implementable manner, the obtaining unit 101 is specifically configured to obtain the number of unit times included in the statistical time length; the processing unit 102 is specifically configured to determine, according to the determined ratio and the number acquired by the acquiring unit 101, a degree of attention of the account to works of a preset category.

In one practical approach, the attention satisfies the following equation:

Of course, the information recommendation device 10 provided by the embodiment of the present disclosure includes, but is not limited to, the above modules, for example, the information recommendation device 10 may further include the storage unit 105. The storage unit 105 may be used for storing the program code of the writing information recommendation device 10, and may also be used for storing data generated by the writing information recommendation device 10 during operation, such as data in a writing request.

In addition, when the information recommendation device 10 provided in the above embodiment implements the functions thereof, only the division of the above functional modules is illustrated, and in practical applications, the above functions may be distributed by different functional modules according to needs, that is, the internal structure of the information recommendation device 10 may be divided into different functional modules to implement all or part of the above described functions.

Fig. 8 is a schematic structural diagram of an information recommendation device 10 according to an embodiment of the present disclosure, and as shown in fig. 8, the information recommendation device 10 may include: at least one processor 51, a memory 52, a communication interface 53 and a communication bus 54.

The following describes each component of the information recommendation device 10 in detail with reference to fig. 8:

the processor 51 is a control center of the information recommendation apparatus 10, and may be a single processor or a collective term for a plurality of processing elements. For example, the processor 51 is a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present disclosure, such as: one or more DSPs, or one or more Field Programmable Gate Arrays (FPGAs).

In particular implementations, processor 51 may include one or more CPUs such as CPU0 and CPU1 shown in fig. 8 as one example. Also, as an example, the information recommendation device 10 may include a plurality of processors, such as the processor 51 and the processor 55 shown in fig. 8. Each of these processors may be a Single-core processor (Single-CPU) or a Multi-core processor (Multi-CPU). A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).

The Memory 52 may be a Read-Only Memory (ROM) or other type of static storage device that can store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that can store information and instructions, an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 52 may be self-contained and coupled to the processor 51 via a communication bus 54. The memory 52 may also be integrated with the processor 51.

In a particular implementation, the memory 52 is used for storing data and software programs for implementing the present invention. The processor 51 may perform various functions of the air conditioner by running or executing software programs stored in the memory 52 and calling data stored in the memory 52.

The communication interface 53 is a device such as any transceiver, and is used for communicating with other devices or communication Networks, such as a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), a terminal, and a cloud. The communication interface 53 may include a receiving unit implementing a receiving function.

The communication bus 54 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 8, but this is not intended to represent only one bus or type of bus.

As an example, in conjunction with fig. 7, the acquisition unit 101 in the information recommendation device 10 implements the same function as the communication interface 53 in fig. 8, the processing unit 102 implements the same function as the processor 51 in fig. 8, and the storage unit 103 implements the same function as the memory 52 in fig. 8.

Another embodiment of the present invention further provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to perform the method shown in the above method embodiment.

In some embodiments, the disclosed methods may be implemented as computer program instructions encoded on a computer-readable storage medium in a machine-readable format or encoded on other non-transitory media or articles of manufacture.

In an exemplary embodiment, the disclosed embodiment also provides a storage medium including instructions, for example, a memory 102 including instructions, which are executable by a processor 101 of the information recommendation device 10 to perform the above method. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a Read-Only Memory (ROM), a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, the disclosed embodiments also provide a computer program product comprising one or more instructions executable by the processor 101 of the information recommendation device 10 to perform the above-described method.

Through the above description of the embodiments, it is clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the modules or units is only one logical functional division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another device, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

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

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

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present disclosure may be implemented in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the methods according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only an embodiment of the present disclosure, but the scope of the present disclosure is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. An information recommendation method, comprising:

acquiring a work conversion rate and at least one behavior operation conversion rate of an account within the statistical time length; the work conversion rate is the conversion rate of a target work in a preset category of works, the behavior operation conversion rate is the conversion rate of the target work corresponding to a target behavior operation, the target behavior operation is the behavior operation recorded by the account in the preset category of works, and different behavior operations correspond to different behavior operation conversion rates;

determining a percentage of each of the behavioral operational conversion rates in the work conversion rate;

determining the attention of the account to the works of the preset category according to the ratio of each determined behavior operation conversion rate in the work conversion rate;

delivering the works to be delivered to the account under the condition that the attention degree is greater than or equal to an attention degree threshold value; and the category to which the works to be released belong is the preset category.

2. The information recommendation method according to claim 1, wherein said obtaining at least one behavior operation conversion rate within a statistical time duration comprises:

acquiring at least one target behavior operation executed by the account in the preset category of works within the statistical duration;

and inquiring the behavior operation conversion rate corresponding to each target behavior operation in the corresponding relation between the target behavior operation and the behavior operation conversion rate, and determining at least one behavior operation conversion rate in the statistical time length.

3. The information recommendation method according to claim 2, wherein the obtaining of the correspondence relationship comprises:

acquiring conversion data, the total number of the first account numbers and the total number of the second account numbers; the conversion data comprises data of conversion operation recorded on the target work by account numbers, the total number of the first account numbers is the number of the account numbers of the target behavior operation recorded in the preset-category work, and the total number of the second account numbers is the number of the account numbers of the target behavior operation recorded in the preset-category work and the target operation executed on the target work;

determining a behavior operation conversion rate corresponding to the target behavior operation as a ratio of the total number of the second accounts to the total number of the first accounts;

and generating a corresponding relation containing behavior operation conversion rates corresponding to the target behavior operations.

4. The information recommendation method of claim 1, wherein said obtaining the conversion rate of the work over a statistical time period comprises:

acquiring conversion data, the total number of the third account and the total number of the fourth account within the statistical time length; the conversion data comprises data of conversion operations recorded by account numbers on the target works, the total number of the third account numbers is the number of the account numbers with behavior operations recorded in the preset-category works within the counting time, the total number of the fourth account numbers is the number of the account numbers with behavior operations recorded in the preset-category works within the counting time, and the number of the account numbers with conversion operations is recorded on the target works;

and determining the conversion rate of the works in the statistical time length as the ratio of the total number of the fourth account numbers to the total number of the third account numbers.

5. The information recommendation method according to claim 1, wherein said determining a percentage of each action operation conversion rate in the work conversion rate comprises:

determining a difference between each of the behavioral operational conversion rates and the work conversion rate;

and determining the proportion of each behavior operation conversion rate in the work conversion rate according to the determined difference and the work conversion rate.

6. The information recommendation method according to claim 1, wherein the determining of the attention of the account to the works of the preset category according to the ratio of each determined behavior operation conversion rate in the work conversion rate comprises:

acquiring the number of unit time contained in the statistical time length;

and determining the attention of the account to the works of the preset category according to the determined proportion and the number.

7. An information recommendation apparatus, comprising: an acquisition unit and a processing unit;

the obtaining unit is configured to obtain a work conversion rate and at least one behavior operation conversion rate of the account within a statistical time length; the work conversion rate is the conversion rate of a target work in a preset category of works, the behavior operation conversion rate is the conversion rate of the target work corresponding to a target behavior operation, the target behavior operation is the behavior operation executed by the account in the preset category of works, and different behavior operations correspond to different behavior operation conversion rates;

the processing unit is configured to determine the proportion of the behavior operation conversion rate acquired by each acquiring unit in the work conversion rate acquired by the acquiring unit;

the processing unit is further configured to determine the attention degree of the account to the works of the preset category according to the ratio of each determined behavior operation conversion rate in the work conversion rate;

the processing unit is further configured to release the work to be released to the account under the condition that the attention degree is greater than or equal to an attention degree threshold; and the category to which the works to be released belong is the preset category.

8. A server, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the information recommendation method of any one of claims 1-6.

9. A computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of a server, enable the server to perform the information recommendation method of any one of claims 1-6.

10. A computer program product, comprising instructions for causing a computer to perform the information recommendation method according to any one of claims 1-6, when the computer program product is run on the computer.