CN106897905B

CN106897905B - Method and device for pushing information and electronic equipment

Info

Publication number: CN106897905B
Application number: CN201710113189.9A
Authority: CN
Inventors: 杨甲东; 姜海军; 陈维良
Original assignee: Chongqing Duxiaoman Youyang Technology Co ltd
Current assignee: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd.
Priority date: 2017-02-28
Filing date: 2017-02-28
Publication date: 2021-09-17
Anticipated expiration: 2037-02-28
Also published as: CN106897905A

Abstract

The application discloses a method and a device for pushing information. One embodiment of the method comprises: receiving click information of a user on the article information presented on the user terminal; determining a first fee deduction number and a maximum fee deduction number for the user to purchase the item indicated by the item information according to the item information; according to the click information and the first expense deduction number, executing the following information pushing steps: determining whether the probability of purchasing the article by the user is greater than or equal to a preset probability threshold value or not according to the click information, the first expense deduction number and a pre-trained probability calculation model; if the first fee deduction number is larger than or equal to the second fee deduction number, pushing information comprising the first fee deduction number to the user terminal; if the first fee deduction number is less than the maximum fee deduction number, increasing the value of the first fee deduction number to update the first fee deduction number, and continuing to execute the information pushing step when the updated first fee deduction number is determined to be less than or equal to the maximum fee deduction number. The embodiment realizes targeted information push.

Description

Method and device for pushing information and electronic equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to the field of internet technologies, and in particular, to a method and an apparatus for pushing information, and an electronic device.

Background

With the rapid development of electronic commerce, more and more users and merchants complete transactions through the electronic commerce platform. In order to increase the enthusiasm of the user for purchasing goods or using services provided by the merchant, the e-commerce platform or the merchant usually issues certain subsidies to the user who purchases the goods, i.e. a certain amount of fee reduction is provided for the user. However, most of the existing subsidy methods directly issue a certain amount of subsidies, and the existing subsidy methods cannot give different differentiated subsidies with different expense deductions according to different users, so that the problem of single subsidy mode exists.

Disclosure of Invention

The present application is directed to an improved method, apparatus and electronic device for pushing information, so as to solve the technical problems mentioned in the above background.

In a first aspect, the present application provides a method for pushing information, the method comprising: receiving click information of a user on the article information presented on the user terminal; determining a first charge exemption number and a maximum charge exemption number of the user for purchasing the article indicated by the article information according to the article information, wherein the first charge exemption number is less than or equal to the maximum charge exemption number; according to the click information and the first expense deduction number, executing the following information pushing steps: determining the probability of the user purchasing the article according to the click information, the first expense deduction number and a pre-trained probability calculation model, wherein the probability calculation model is used for representing the corresponding relation between the click information and the probability of the user purchasing the article when the expense deduction number providing the first expense deduction number for the user is reduced; determining whether the probability is greater than or equal to a preset probability threshold; in response to determining that the probability is greater than or equal to the preset probability threshold, pushing information including a first cost deduction number to the user terminal; and in response to determining that the probability is less than the preset probability threshold, increasing the value of the first cost deduction number to update the first cost deduction number, and continuing to execute the information pushing step when the updated first cost deduction number is determined to be less than or equal to the maximum cost deduction number.

In some embodiments, determining a first fee deduction number and a maximum fee deduction number for the user to purchase the item indicated by the item information according to the item information includes: determining the range of the expense deduction number of the article indicated by the article information in a list for storing the article information and the corresponding expense deduction number range according to the article information; determining a minimum cost deduction number and a maximum cost deduction number for the item from the range of the cost deduction numbers; determining the minimum cost deduction number as a first cost deduction number for the item.

In some embodiments, the above method further comprises: stopping executing the information pushing step in response to the updated first fee deduction number being greater than the maximum fee deduction number; and pushing information including the maximum charge deduction number to the user terminal.

In some embodiments, the method further comprises the step of determining the probability calculation model, and the step of determining the probability calculation model comprises: acquiring user data of a plurality of users from a cache area for storing the user data, wherein the user data comprises click information, expense deduction number and purchase information of the users; and training an initial probability calculation model by using the user data of the plurality of users, and determining the pre-trained probability calculation model.

In some embodiments, the training an initial probability calculation model using the user data of the plurality of users to determine the pre-trained probability calculation model includes: extracting characteristic information from the user data, adding the characteristic information into a characteristic information set to be selected, wherein the characteristic information is used for describing information related to a user or related to an article, and executing the following training process: combining each item of feature information in the feature information set to be selected with feature information in a preset feature information set respectively, and training the initial probability calculation model to obtain a plurality of test probability calculation models; determining a test probability calculation model with the minimum error in the plurality of test probability calculation models as a first test probability calculation model; determining to obtain the characteristic information in the to-be-selected characteristic information set adopted by the first test probability calculation model; comparing the error between the probability calculated by the first test probability calculation model and the actual probability calculated by the initial probability calculation model, responding to the error that the error of the probability of the user for purchasing the goods is calculated by the first test probability calculation model and is larger than the error of the probability of the user for purchasing the goods calculated by the initial probability calculation model, and determining the initial probability calculation model as the pre-trained probability calculation model; and responding to the error of the probability of the first test probability calculation model for calculating the article purchased by the user and being smaller than the error of the probability of the initial probability calculation model for calculating the article purchased by the user, determining the first test probability calculation model as the initial probability calculation model, deleting the feature information from the feature information set to be selected, adding the feature information into the feature information set, and continuing to execute the training process.

In some embodiments, the method further comprises the step of determining the probability threshold, and the step of determining the probability threshold comprises: acquiring user data of a plurality of users clicking the article from a cache area for storing the user data, wherein the user data comprises click information and expense deduction numbers; the probability calculation model calculates the probability of each user purchasing the article according to the click information and the expense deduction number of each user; determining the number of users who purchase the articles according to the preset expected purchase proportion of the articles, and determining the number as an expected number; and determining the probability of purchasing the items of the first expected number of the users as the probability threshold value according to the descending order of the probability of purchasing the items of each user.

In a second aspect, the present application provides an apparatus for pushing information, the apparatus comprising: the receiving unit is configured to receive click information of a user on the article information presented on the user terminal; a determination unit configured to determine, based on the item information, a first charge exemption number and a maximum charge exemption number for the user to purchase an item indicated by the item information, the first charge exemption number being less than or equal to the maximum charge exemption number; a pushing unit configured to execute the following information pushing steps according to the click information and the first charge deduction number: determining the probability of the user purchasing the article according to the click information, the first expense deduction number and a pre-trained probability calculation model, wherein the probability calculation model is used for representing the corresponding relation between the click information and the probability of the user purchasing the article when the expense deduction number providing the first expense deduction number for the user is reduced; determining whether the probability is greater than or equal to a preset probability threshold; in response to determining that the probability is greater than or equal to the preset probability threshold, pushing information including the first cost deduction number to the user terminal; and an updating unit configured to, in response to determining that the probability is smaller than the preset probability threshold, increase a value of the first cost deduction number to update the first cost deduction number, and when it is determined that the updated first cost deduction number is smaller than or equal to the maximum cost deduction number, continue to perform the information pushing step.

In some embodiments, the determining unit is further configured to: determining the range of the expense deduction number of the article indicated by the article information in a list for storing the article information and the corresponding expense deduction number range according to the article information; determining a minimum cost deduction number and a maximum cost deduction number for the item from the range of the cost deduction numbers; determining the minimum cost deduction number as a first cost deduction number for the item.

In some embodiments, the update unit is further configured to: stopping executing the information pushing step in response to the updated first fee deduction number being greater than the maximum fee deduction number; and pushing information including the maximum charge deduction number to the user terminal.

In some embodiments, the apparatus further comprises a probabilistic computational model determining unit, the probabilistic computational model determining unit comprising: the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is configured to acquire user data of a plurality of users from a cache region for storing the user data, and the user data comprises click information, cost deduction number and purchase information of the users; and the training module is configured to train an initial probability calculation model by using the user data of the plurality of users, and determine the pre-trained probability calculation model.

In some embodiments, the training module is further configured to: extracting characteristic information from the user data, adding the characteristic information into a characteristic information set to be selected, wherein the characteristic information is used for describing information related to a user or related to an article, and executing the following training process: combining each item of feature information in the feature information set to be selected with feature information in a preset feature information set respectively, and training the initial probability calculation model to obtain a plurality of test probability calculation models; determining a plurality of test probability calculation models with the minimum error as first test probability calculation models; determining to obtain the characteristic information in the to-be-selected characteristic information set adopted by the first test probability calculation model; comparing the error between the probability calculated by the first test probability calculation model and the actual probability calculated by the initial probability calculation model, responding to the error that the error of the probability of the user for purchasing the goods is calculated by the first test probability calculation model and is larger than the error of the probability of the user for purchasing the goods calculated by the initial probability calculation model, and determining the initial probability calculation model as the pre-trained probability calculation model; and responding to the error of the probability of the first test probability calculation model for calculating the article purchased by the user and being smaller than the error of the probability of the initial probability calculation model for calculating the article purchased by the user, determining the first test probability calculation model as the initial probability calculation model, deleting the feature information from the feature information set to be selected, adding the feature information into the feature information set, and continuing to execute the training process.

In some embodiments, the apparatus further comprises a probability threshold determination unit configured to: acquiring user data of a plurality of users clicking the article from a cache area for storing the user data, wherein the user data comprises click information and expense deduction numbers; the probability calculation model calculates the probability of each user purchasing the article according to the click information and the expense deduction number of each user; determining the number of users who purchase the articles according to the preset expected purchase proportion of the articles, and determining the number as an expected number; and determining the probability of purchasing the items of the first expected number of the users as the probability threshold value according to the descending order of the probability of purchasing the items of each user.

In a third aspect, the present application provides an electronic device for pushing information, the electronic device comprising: one or more processors; storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for pushing information as provided in the first aspect above.

In a fourth aspect, the present application provides a computer-readable storage medium for pushing information, on which a computer program is stored, which when executed by a processor, implements the method for pushing information as provided in the first aspect above.

According to the method and the device for pushing the information and the electronic equipment, the cost reduction range of the information of the clicked item is determined by utilizing the click information of the user operated by the user terminal equipment, the probability of the user for purchasing the item is calculated according to the cost reduction range and the information of the user, the cost reduction number of the user is determined according to the probability, the information containing the cost reduction number is pushed to the terminal of the user, and targeted information pushing is achieved.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow diagram of one embodiment of a method for pushing information, according to the present application;

fig. 3a and 3b are schematic diagrams of an application scenario of a method for pushing information according to the present application;

FIG. 4 is a flow diagram of yet another embodiment of a method for pushing information according to the present application;

FIG. 5 is a schematic block diagram illustrating one embodiment of an apparatus for pushing information according to the present application;

FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing a server or an electronic device according to embodiments of the present application.

Detailed Description

The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

Fig. 1 shows an exemplary system architecture 100 to which embodiments of the present method for pushing information or for a push information device may be applied.

As shown in fig. 1, the system architecture 100 may include

user terminals

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

user terminals

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

user terminals

101, 102, 103 to interact with the server 105 over the network 104 to complete a transaction or the like. Various shopping applications, network trading platform applications, social platform software, etc. may be installed on the

user terminals

101, 102, 103.

The

user terminals

101, 102, 103 may be various electronic devices having display screens and supporting online shopping, network transactions, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, for example, an application server providing management and services for the e-commerce platform, and the application server analyzes and processes received service request information sent by the

user terminals

101, 102, and 103, and feeds back a processing result (for example, subsidy information for the user) to the

user terminals

101, 102, and 103.

It should be noted that the method for pushing information provided by the embodiment of the present application is generally performed by the server 105, and accordingly, the apparatus for pushing information is generally disposed in the server 105.

It should be understood that the number of user terminals, networks and servers in fig. 1 is merely illustrative. There may be any number of user terminals, networks, and servers, as desired for an implementation.

With continued reference to fig. 2, a flow 200 of one embodiment of a method for pushing information in accordance with the present application is shown. The method for pushing the information comprises the following steps:

step 201, receiving click information of the user on the item information presented on the user terminal.

In this embodiment, an electronic device (for example, a server shown in fig. 1) on which the method for pushing information operates may receive click information of the user on item information presented on the user terminal from a user terminal device with which the user performs online shopping or online transaction through a wired connection manner or a wireless connection manner. The article information may be described in a text form, such as information described in a name, a code number, and the like of an article, information described in a picture form, or information described in a web page link form. The click information of the user comprises information related to the user and information related to an article indicated by the article information clicked by the user.

The information related to the user may be information for identifying the identity of the user in the user request information, for example, may be registration information of the user on the e-commerce platform; the information may also be information of a terminal device bound to the user in the e-commerce platform, for example, information of the user who uses the terminal device to perform the transaction. The information related to the item indicated by the item information clicked by the user may be information of an item to be purchased by the user or information of an item focused by the user, such as a name of an item to be purchased by the user, a code of the item, a quantity, a price, and the like.

Step 202, determining a first fee deduction number and a maximum fee deduction number for the user to purchase the item indicated by the item information according to the item information.

In this embodiment, based on the click information obtained in step 201, the electronic device (e.g., the server shown in fig. 1) may determine, according to the click information, a first fee deduction number and a maximum fee deduction number of the item indicated by the item information clicked by the user.

Here, the fee deduction is a subsidy provided by the merchant or the e-commerce platform for the user who purchased the merchant's goods, and may be a voucher or voucher issued by the merchant or the e-commerce platform to encourage the user to purchase the merchant's goods. The fee deduction number is the amount of subsidy that the merchant or e-commerce platform issued the item to the user who purchased the item. As an example, the above-mentioned determining the first charge deduction number and the maximum charge deduction number of the item requested to be purchased by the user according to the click information may be that first, according to information related to the item in the click information, such as a name or a code of the item, record data of a transaction or operation of the item is obtained in an information base for storing the item of the merchant. The record data of the item can include the name, code, price, sales volume, margin of the item, the subsidy amount range available by the merchant for purchasing the item, and the like. Then, the first cost deduction and the maximum cost deduction of the item are obtained from the record data of the item. The first charge reduction number is equal to or less than the maximum charge reduction number.

Step 203, according to the click information and the first fee deduction number, executing the following information pushing step: substeps 2031, 2032, 2033. Wherein:

substep 2031, determining the probability of the user purchasing the item according to the click information, the first charge reduction amount and a pre-trained probability calculation model.

In this embodiment, the electronic device trains a probability calculation model in advance, and the probability calculation model is used for representing a corresponding relationship between click information and a probability of the user purchasing an item when the user is provided with cost deduction of a first cost deduction number. The probability calculation model can determine the probability of purchasing the goods by the user according to the click information and the expense deduction number. The electronic device can import the data of the user and the first expense deduction number into the pre-trained probability calculation model according to the data of the user determined by the information related to the user in the click information, and obtain the probability of purchasing the article when the user issues the subsidy of the first expense deduction number in the merchant or the e-commerce platform.

Sub-step 2032 of determining whether the probability is greater than or equal to a preset probability threshold.

In this embodiment, a probability threshold is pre-stored in the electronic device, and whether the user purchases the item may be determined from the probability threshold, and if the probability that the user purchases the item is greater than the probability threshold, the user may purchase the item, otherwise, the user may not purchase the item. The electronic device may determine whether the probability of the user purchasing the item determined in the step 2031 is greater than or equal to a preset probability threshold by comparing the probability with a preset probability threshold.

Substep 2033, in response to determining that the probability is greater than or equal to the preset probability threshold, pushing information comprising the first charge reduction number to the user terminal.

In this embodiment, if the probability is greater than or equal to the probability threshold based on the determination result of the sub-step 2032, the user will purchase the item if the merchant or the e-commerce platform provides the user with the subsidy of the first charge deduction number. The server pushes information containing the first charge deduction number to the user terminal.

Step 204, in response to determining that the probability is smaller than the preset probability threshold, increasing the value of the first cost deduction number to update the first cost deduction number, and when determining that the updated first cost deduction number is smaller than or equal to the maximum cost deduction number, continuing to perform the information pushing step 203.

In this embodiment, if the probability is smaller than the predetermined probability threshold based on the determination result of the sub-step 2032, it indicates that the user does not purchase the item or the possibility of purchasing the item is low in the case that the merchant or the e-commerce platform provides the user with the subsidy of the first fee deduction number. To encourage the user to purchase the item, the charge exemption credit, i.e., the subsidy credit, may be increased. The first fee deduction number is updated by increasing the value of the first fee deduction number. The first expense deduction number can be updated by increasing the first expense deduction number and using the first expense deduction number after the subsidy amount is increased as a new first expense deduction number. Judging whether the updated first fee deduction number is less than or equal to the maximum first fee deduction number, if so, continuing to execute the information pushing step 203.

With continuing reference to fig. 3a and 3b, fig. 3a and 3b are schematic diagrams of application scenarios of the method for information push according to the present embodiment. In the application scenarios of fig. 3a and 3b, a user clicks information of an item (for example, beef jerky as a commodity) indicated by certain item information through shopping software or a network transaction application installed on a user terminal device; then, the management server of the E-commerce platform receives the click information of the user, and determines a first cost deduction number and a maximum cost deduction number of the article indicated by the article information clicked by the user according to the click information of the user; and finally, the management server determines the subsidy amount of the expense deduction number which can be obtained by the user for purchasing the article according to the click information of the user and the first expense deduction number of the article. As an example, as shown in fig. 3a, the user clicks on information "mars beef jerky" presented on the user terminal through a network transaction application installed on the terminal device, and the information "mars beef jerky" is displayed on the transaction interface, including information of unit price of the item, and information of the number of items selected by the user, as shown at 301 in fig. 3 a. After the user clicks a 'confirm' key in the 'mars beef jerky' information, the management server confirms information related to the 'mars beef jerky' information and information related to the user according to the click information of the user; finally, as shown in fig. 3b, the amount of subsidy of the item indicated by the "mars beef jerk" information purchased by the user from the merchant or the e-commerce platform is determined, and information containing the charge deduction number is pushed to the user terminal, as shown at 302 in fig. 3 b.

According to the method provided by the embodiment, the information related to the user and the information related to the article are obtained through the click information of the user, then the subsidy amount of the expense deduction amount of the article purchased by the user is determined according to the information related to the user and the information related to the article, the information containing the expense deduction amount is pushed to the user terminal, reasonable expense deduction information is provided for the user, and targeted information pushing is achieved.

With further reference to fig. 4, a flow 400 of yet another embodiment of a method for determining a user subsidy amount is illustrated. The process 400 of the method for determining a user subsidy amount includes the steps of:

step 401, receiving click information of the user on the item information presented on the user terminal.

In this embodiment, an electronic device (for example, a server shown in fig. 1) on which the method for pushing information operates may receive click information of a user on item information presented on a user terminal from a terminal with which the user performs a network transaction or online shopping through a wired connection manner or a wireless connection manner. The item information may be information described in the form of text, picture, web page link, or the like, and the click request information of the user includes information related to the user and information related to an item indicated by the item information clicked by the user.

Step 402, determining a first charge exemption number and a maximum charge exemption number for the user to purchase the item indicated by the item information according to the item information.

In this embodiment, based on the click information obtained in step 401, the electronic device may determine, according to the item information in the click information, a first fee deduction number and a maximum fee deduction number of the item indicated by the item information clicked by the user.

The fee deduction is a subsidy provided by the merchant or the e-commerce platform for the user who purchased the merchant's goods, and the fee deduction can be a voucher or voucher issued by the merchant or the e-commerce platform, and the like, so as to encourage the user to purchase the merchant's goods. The fee deduction is the amount of subsidy that the merchant or e-commerce platform issued the item to the user who purchased the item. The merchant or e-commerce platform may preset a range of fee deductions that the item may provide, etc. A first cost reduction and a maximum cost compensation reduction for the item are determined. The first charge reduction number is equal to or less than the maximum charge reduction number.

In some optional implementation manners of this embodiment, in the item information of the click information received in step 401, the electronic device determines, according to the item information, a range of the fee deduction number of the item indicated by the item information in a range list for storing the item information and a corresponding fee deduction number range; determining the minimum cost deduction number and the maximum cost deduction number of the object from the range of the cost deduction numbers; determining the minimum cost deduction number as a first cost deduction number for the item.

The article information may be a name, a code, or the like of the article, which is used to identify the article. The electronic device stores a range of the charge free number of the item in advance, and may show the item information and the range of the charge free number of the item using a list. And the electronic equipment searches the range of the expense deduction number corresponding to the name or the code of the article from the list according to the name or the code of the article. The minimum value of the range of the fee deduction number may be set as the first fee deduction number of the article, and the maximum value of the range of the fee deduction number may be set as the maximum fee deduction number of the article.

Step 403, according to the click information and the first fee deduction number, executing the following information pushing step: substeps 4031, 4032, 4033. Wherein:

and a substep 4031 for determining the probability of the user purchasing the item according to the click information, the first cost deduction number and a pre-trained probability calculation model.

In some optional implementations of this embodiment, the method further includes a step of determining the probability calculation model, where the step of determining the probability calculation model includes: acquiring user data of a plurality of users from a cache area for storing the user data, wherein the user data comprises click information, expense deduction number and purchase information of the users; and importing the user data of the plurality of users into an initial probability calculation model as training data, training the initial probability calculation model by using the user data of the plurality of users, and determining the pre-trained probability calculation model.

Here, characteristic information such as the name of the item clicked by the user, the category to which the item belongs, time information, whether or not to purchase, whether or not to use the subsidy, the amount of money of the subsidy, and the number of purchases can be obtained from the user data. And training the initial probability calculation model according to the characteristic information to obtain a probability calculation model.

In some optional implementations of the present embodiment, the determining of the probability calculation model further includes: extracting characteristic information from the user data, adding the characteristic information into a characteristic information set to be selected, wherein the characteristic information is used for describing information related to a user or related to an article, and executing the following training process: combining each item of feature information in the feature information set to be selected with feature information in a preset feature information set respectively, and training the initial probability calculation model to obtain a plurality of test probability calculation models; determining a test probability calculation model with the minimum error in the plurality of test probability calculation models as a first test probability calculation model; determining to obtain the characteristic information in the to-be-selected characteristic information set adopted by the first test probability calculation model; comparing the first test probability calculation model with the initial probability calculation model to calculate an error of the probability of the user purchasing the item, wherein the error of the probability of the user purchasing the item calculated by the first test probability calculation model is larger than the error of the probability of the user purchasing the item calculated by the initial probability calculation model, and the initial probability calculation model is determined to be the pre-trained probability calculation model;

and responding to the error of the probability of the first test probability calculation model for calculating the article purchased by the user and being smaller than the error of the probability of the initial probability calculation model for calculating the article purchased by the user, determining the first test probability calculation model as the initial probability calculation model, deleting the feature information from the feature information set to be selected, adding the feature information into the feature information set, and continuing to execute the training process.

The characteristic information is information which can be used for describing information related to the user and/or information related to the article indicated by the article information in the user data. The information related to the user may be information for identifying the identity of the user, and may be operation behavior information of the user, where the operation behavior of the user may be operation behavior of clicking item information, placing an order, purchasing an item, and so on. As an example, the characteristic information may be: a time interval during which the user purchases or clicks on item information is described (e.g., the user mostly clicks on to view the item at 10-12, purchases the item at 20-21), the user's gender, whether to use the subsidy/cost deduction (e.g., the user purchases the item when the item has the subsidy/cost deduction), etc. The information related to the article indicated by the article information may be the category of the article (food, clothing, traffic, home, etc.), and charge free information of the article (presence or absence of a patch, a range of patches, etc.).

The error of the test probability calculation model may be a difference between a probability that the user purchases the item and a probability that the user actually purchases the item. It is understood that the probability that the user actually purchases an item is 0 or 100% as described above. If the user does not purchase the item, the probability of actually purchasing the item is 0; if the user purchases the item, the probability of actually purchasing the item is 100%.

As an example, the candidate feature information set includes two items of feature information, where the first feature information is that the purchase time is holiday, the second feature information is that the article name is cup, the first feature information and the second feature information are respectively added to the feature information set, and the initial probability calculation model is trained to obtain two test probability calculation models, which are the first test probability calculation model and the second test probability calculation model.

The error of the performance of the two test probability calculation models is determined, and the error can be the error value of the probability that the test probability calculation model calculates the user purchases the article and the probability that the user actually purchases the article. For example, the data of the user a, the user B, and the user C are respectively imported into the test probability calculation model. The two test probability calculation models calculate that the probability of purchasing the goods by the user A, the user B and the user C is 0.85, 0.2, 0.90, 0.7, 0.4 and 0.75. While the above-mentioned user a and user C actually purchase the item, the user B does not purchase the item. The probability calculated by the first test probability calculation model is closer to the fact, the performance is better, namely the error is small, and the first test probability calculation model is determined to be the first test probability calculation model.

And a sub-step 4032 for determining whether the probability is greater than or equal to a predetermined probability threshold.

In this embodiment, a probability threshold is prestored in the electronic device. The electronic device may determine whether the probability that the user purchased the item, determined in sub-step 4031, is greater than or equal to the predetermined probability threshold by performing a difference.

In some optional implementations of the present embodiment, the probability threshold may be determined by: acquiring user data of a plurality of users clicking the article indicated by the article information from a cache area for storing the user data, wherein the user data comprises click information and a charge deduction number; the probability calculation model calculates the probability of each user purchasing the article according to the click information and the expense deduction number of each user; determining the number of users who purchase the articles according to the preset expected purchase proportion of the articles, and determining the number as an expected number; and determining the probability of the expected number of the users purchasing the articles as the probability threshold value according to the descending order of the probability of each user purchasing the articles.

The user data of the plurality of users who click on the item indicated by the item information may be user data of a different user who clicks on the same item information, which is obtained from a cache area for storing user data, for example, user data of a user who clicks on the "xxx" space cup information, which is obtained from the cache area for storing user data. The above-mentioned users clicking on the "xxx" space cup information include users who purchase the "xxx" space cup and users who only click on the focus without purchasing.

Click information and the charge deduction number of the user are obtained from each user data. The fee deduction number of the user is the amount of subsidy which can be provided for the user to purchase the item by the merchant or the E-commerce platform. If the user purchases the item, providing the cost deduction for the user according to the amount provided by the cost deduction number; if the user does not purchase the item, no fee deduction is provided, and the user does not purchase the item when the merchant or the platform provides the credit subsidy of the fee deduction number.

The predetermined expected purchase ratio of the item is a predetermined ratio, and is a ratio of users who purchase the item among users who click the item information, which is expected by a merchant or an e-commerce platform. For example, if 100 users click on the "xxx" space cup, the merchant or the e-commerce platform may estimate a conversion rate of 30%, i.e., 30 users may choose to purchase the item among the 100 users.

The determining of the probability threshold is to determine a user who purchases an item from the expected purchase ratio, and to select a minimum probability of purchasing the item from the determined users as the probability threshold.

The above-mentioned determining the probability threshold may be implemented by the following processes: determining the number of users, and calculating the number of the users desiring to purchase the goods according to the desired purchase proportion and the number of the users as a desired number; and determining the probability threshold value as the probability value of the probability of purchasing the goods of the first expected number of the users according to the descending order of the probability of purchasing the goods of each user.

As an example, 100 users in the sample click the item information, the expected purchase proportion estimated by the merchant is 30%, and 30 users are expected to purchase items in all the 100 users; and calculating the probability of purchasing the articles by the 100 users, sorting the articles according to the sequence from the highest probability to the lowest probability, and selecting the probability of the user sorted at the 30 th position as a probability threshold value.

In some specific implementations, the determining the probability threshold may be: a desired number of users are selected from the plurality of users. Wherein the probability that any user of the selected plurality of users desires to purchase the item is greater than the probability that other users except the selected plurality of users desire to purchase the item. Determining a minimum probability as the probability threshold from the probabilities of the selected desired number of users purchasing the item.

As an example, the above 100 users click on the item information, the conversion rate estimated by the merchant is 30%, and 30 users are expected to purchase items; calculating the probability of the 100 users purchasing the article, selecting 30 users with the highest probability from the 100 users, and determining the probability of the user with the lowest probability of purchasing the article from the selected 30 users as a probability threshold.

Substep 4033, in response to determining that the probability is greater than or equal to the predetermined probability threshold, pushing information including the first cost deduction number to the user terminal.

In this embodiment, if the probability is greater than or equal to the probability threshold based on the execution result of sub-step 4032, the user will purchase the item if the merchant or the e-commerce platform provides the user with a subsidy of the first fee deduction number. And taking the first fee deduction number as the user subsidy amount of the user. The server pushes information containing the expense deduction number to the user terminal.

Step 404, in response to determining that the probability is smaller than the preset probability threshold, increasing the value of the first fee deduction number to update the first fee deduction number, and when determining that the updated first fee deduction number is smaller than or equal to the maximum fee deduction number, continuing to perform the information pushing step 403.

In this embodiment, based on the execution result of sub-step 4032, if the probability is smaller than the predetermined threshold probability, it indicates that the user has a low possibility of purchasing the item in the case that the merchant or the e-commerce platform provides the user with the subsidy of the first fee deduction number. The user is incentivized to stock the item by increasing the value of the first fee deduction number to update the first fee deduction number. And taking the first expense deduction number after the subsidy limit is increased as a new first expense deduction number. Determining whether the updated first charge exemption number is less than or equal to the maximum first charge exemption number, and if the updated first charge exemption number is less than or equal to the maximum first charge exemption number, continuing to execute the information pushing step 403.

Step 405, in response to the updated first charge exemption number being greater than the maximum charge exemption number, stopping executing the information pushing step 403, and pushing information including the maximum charge exemption number to the user terminal.

In this embodiment, the maximum charge deduction number is the maximum subsidy amount that the merchant or the e-commerce platform can provide to the user who purchased the item for the item.

If the updated first fee deduction number in step 404 is greater than the maximum fee deduction number, the possibility of the user purchasing the item is low. At the same time, the fee deduction number also reaches the upper limit of the subsidy, so the information pushing step 403 is stopped. And pushing information including the maximum charge deduction number to the user terminal.

As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, the flow 400 of the method for determining user right information in this embodiment highlights the method for pushing information of the user with a lower probability of purchasing an item after increasing the fee deduction number, so as to push information containing a more comprehensive fee deduction number to the user terminal.

With further reference to fig. 5, as an implementation of the method shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for determining user right information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 5, the apparatus 500 for pushing information of the present embodiment includes: a receiving unit 501, a determining unit 502, a pushing unit 503 and an updating unit 504. The receiving unit 501 is configured to receive click information of a user on item information presented on a user terminal. The determining unit 502 is configured to determine a first fee deduction number and a maximum fee deduction number for the user to purchase the item indicated by the item information according to the item information, wherein the first fee deduction number is less than or equal to the maximum fee deduction number. The pushing unit 503 is configured to perform the following information pushing steps according to the click information and the first fee deduction number: determining the probability of the user purchasing the article according to the click information, the first expense deduction number and a pre-trained probability calculation model, wherein the probability calculation model is used for representing the corresponding relation between the click information and the probability of the user purchasing the article when the expense deduction number providing the first expense deduction number for the user is reduced; determining whether the probability is greater than or equal to a preset probability threshold; and in response to determining that the probability is greater than or equal to the preset probability threshold, pushing information including the first charge deduction number to the user terminal. The updating unit 504 is configured to, in response to determining that the probability is smaller than the preset probability threshold, increase the value of the first fee deduction number to update the first fee deduction number, and when determining that the updated first fee deduction number is smaller than or equal to the maximum fee deduction number, continue to perform the information pushing step.

In this embodiment, based on the click information received in the receiving unit 501, the determining unit 502 determines a cost deduction range of the item, the pushing unit 503 determines a cost deduction number of the user according to the click information and the cost deduction range, and pushes information including the cost deduction number to the user terminal, and the updating unit is configured to update the first cost deduction number so as to push information including a reasonable cost deduction number to the user.

In this embodiment, the receiving unit 501 of the apparatus for pushing information 500 may receive click information of the user on item information presented on the user terminal from a terminal with which the user performs online shopping or online transaction through a wired connection manner or a wireless connection manner. The article information may be information of an article described in the form of a text or a picture, or may be information of an article described in the form of a web page link. The click information of the user comprises information related to the user and information related to the article.

In the present embodiment, the determination unit 502 determines the range of the charge deduction number for the user to purchase the item indicated by the item information according to the click information received by the receiving unit 501, thereby determining the first charge deduction number and the maximum charge deduction number. The range of the fee deduction number can be the range of subsidies provided by the merchant or the e-commerce platform for the user who purchases the item; the merchant or e-commerce platform may preset the range of the fee deduction number.

In this embodiment, the pushing unit 503 adjusts the charge deduction number to increase the probability of the user purchasing the item, and the probability that the user purchases the item is greater than the preset probability threshold and is the corresponding first charge deduction number, as the charge deduction amount provided when the user purchases the item. Information comprising the first charge deduction number is pushed to the user terminal.

In this embodiment, the updating unit 504 may indicate that the possibility of the user purchasing the item is low in the case of providing the user with the subsidy of the first fee deduction number according to the fact that the probability of the user purchasing the item calculated in the pushing unit 503 is smaller than the preset probability threshold. The first fee deduction number is updated by increasing the value of the first fee deduction number to encourage the user to purchase the item.

In some optional implementations of the present embodiment, the determining unit 502 is further configured to: determining the range of the expense deduction number of the article indicated by the article information in a list for storing the article information and the corresponding expense deduction number range according to the article information; determining a minimum cost deduction number and a maximum cost deduction number of the article from a range of the cost deduction numbers; the minimum cost deduction number is determined as the first cost deduction number for the item. Here, the information push apparatus 500 stores a list of item information and a charge reduction number range in advance, and the charge reduction number range can be found from the list based on information for identifying the item, such as the name or code of the item information. The first cost deduction number may be the minimum of a range of cost deduction numbers; the maximum cost deduction number may be the maximum value in the range of cost deduction numbers.

In some optional implementations of this embodiment, the updating unit 504 is further configured to: stopping executing the information pushing step in response to the updated first expense deduction number being larger than the maximum expense deduction number; and pushing information including the maximum charge deduction number to the user terminal. Here, if the updated first charge deduction number is greater than the maximum charge deduction number, the possibility that the user purchases the item is low. Meanwhile, the expense deduction number also reaches the upper limit of subsidy, so the information pushing step is stopped. And pushing information including the maximum charge deduction number to the user terminal.

In some optional implementations of the present embodiment, the apparatus 500 for pushing information further includes a probability calculation model determining unit, including: the device comprises an acquisition module and a training module. The acquisition module is configured to acquire user data of a plurality of users from a cache area for storing the user data, wherein the user data includes click information of the users, cost deduction number and purchase information of the users. And the training module is configured to train an initial probability calculation model by using the user data of the plurality of users, and determine the pre-trained probability calculation model. Here, information such as the name of the item clicked by the user, the category to which the item belongs, time information, whether or not to purchase, whether or not to use the subsidy, the amount of money of the subsidy, and the number of purchases can be obtained from the user data. And training the initial probability calculation model according to the characteristic information to obtain a probability calculation model.

In some optional implementations of this embodiment, the training module is further configured to: extracting characteristic information from the user data, adding the characteristic information into a characteristic information set to be selected, wherein the characteristic information is used for representing information related to user behaviors or articles, and executing the following training process:

combining each item of feature information in the feature information set to be selected with feature information in a preset feature information set respectively, and training the initial probability calculation model to obtain a plurality of test probability calculation models; determining a test probability calculation model with the minimum error in a plurality of test probability calculation models as a first test probability calculation model, and determining to obtain the feature information in the feature information set to be selected adopted by the first test probability calculation model;

comparing the error of the probability calculated by the first test probability calculation model and the initial probability calculation model with the actual probability, responding to the error that the error of the probability of the user for purchasing the goods calculated by the first test probability calculation model is larger than the error that the probability of the user for purchasing the goods calculated by the initial probability calculation model, and determining the initial probability calculation model as the pre-trained probability calculation model;

The characteristic information is information which can be used for describing the behavior of the user and/or information related to the article indicated by the article information in the user data.

The error of the test probability calculation model may be a difference between a probability that the user purchases the item and a probability that the user actually purchases the item. It is understood that the probability of the user actually purchasing an item is 0 or 100%. If the user does not purchase the item, the probability of actually purchasing the item is 0; if the user purchases the item, the probability of actually purchasing the item is 100%.

In some optional implementations of the present embodiment, the apparatus 500 for pushing information further includes a probability threshold determining unit, where the probability threshold determining unit is configured to:

acquiring user data of a plurality of users clicking the article indicated by the article information from a cache area for storing the user data, wherein the user data comprises click information and a charge deduction number; the probability calculation model calculates the probability of each user purchasing the article according to the click information and the expense deduction number of each user; determining the number of users who purchase the articles according to the preset expected purchase proportion of the articles, and determining the number as an expected number; and determining the probability of the first expected number of users purchasing the item as a probability threshold value according to the sequence of the probability of each user purchasing the item from large to small.

Here, the plurality of user data are user data of users who click the same item information. The expected purchase proportion is a proportion preset by the merchant or the e-commerce platform and is a proportion of users who purchase the item in the users who click the item information concerned by the merchant or the e-commerce platform.

The present application also provides an electronic device, including: one or more processors; a storage device, configured to store one or more programs, which when executed by one or more processors, cause the one or more processors to implement the method described in the corresponding embodiment of fig. 2 or any alternative implementation of this embodiment.

Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use in implementing a server or electronic device of an embodiment of the present application. The server or the electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 601.

It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a receiving unit, a determining unit, a pushing unit, and an updating unit. Here, the names of the units do not constitute a limitation to the units themselves in some cases, and for example, the receiving unit may also be described as a "unit that receives click information of the user on the item information presented on the user terminal".

As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: receiving click information of a user on the article information presented on the user terminal; determining a first charge exemption number and a maximum charge exemption number for the user to purchase the item indicated by the item information according to the item information, wherein the first charge exemption number is less than or equal to the maximum charge exemption number; according to the click information and the first expense deduction number, executing the following information pushing steps: determining the probability of the user purchasing the article according to the click information, the first expense deduction number and a pre-trained probability calculation model, wherein the probability calculation model is used for describing the corresponding relation between the click information and the probability of the user purchasing the article when the expense deduction of the first expense deduction number is provided for the user; determining whether the probability is greater than or equal to a preset probability threshold; in response to determining that the probability is greater than or equal to the preset probability threshold, pushing information including the first cost deduction number to the user terminal; and in response to determining that the probability is less than the preset probability threshold, increasing the value of the first cost deduction number to update the first cost deduction number, and continuing to execute the information pushing step when the updated first cost deduction number is determined to be less than or equal to the maximum cost deduction number.

The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.

Claims

1. A method for pushing information, the method comprising:

receiving click information of a user on the article information presented on the user terminal;

determining a first fee deduction number and a maximum fee deduction number of the user for purchasing the goods indicated by the goods information according to the goods information, wherein the first fee deduction number is less than or equal to the maximum fee deduction number;

according to the click information and the first expense deduction number, executing the following information pushing steps: determining the probability of the user purchasing the article according to the click information, the first expense deduction number and a pre-trained probability calculation model, wherein the probability calculation model is used for representing the corresponding relation between the click information and the probability of the user purchasing the article when the expense deduction of the first expense deduction number is provided for the user; determining whether the probability is greater than or equal to a preset probability threshold; in response to determining that the probability is greater than or equal to the preset probability threshold, pushing information including the first cost deduction number to the user terminal;

in response to determining that the probability is less than the preset probability threshold, increasing the value of the first cost deduction number to update the first cost deduction number, and when it is determined that the updated first cost deduction number is less than or equal to the maximum cost deduction number, continuing to perform the information pushing step;

in response to the updated first cost deduction number being greater than the maximum cost deduction number, stopping executing the information pushing step, and pushing information including the maximum cost deduction number to the user terminal;

the method further comprises the step of determining the probabilistic computational model, the step of determining the probabilistic computational model comprising:

acquiring user data of a plurality of users from a cache area for storing the user data, wherein the user data comprises click information, expense deduction number and purchase information of the users;

and training an initial probability calculation model by using the user data of the plurality of users, and determining the pre-trained probability calculation model.

2. The method of claim 1, wherein the determining a first fee deduction number and a maximum fee deduction number for the user to purchase the item indicated by the item information according to the item information comprises:

according to the item information, determining the range of the expense deduction number of the item indicated by the item information in a list for storing the item information and the corresponding expense deduction number range;

determining a minimum cost deduction number and a maximum cost deduction number for the item from the range of cost deduction numbers;

determining the minimum cost deduction number as a first cost deduction number for the item.

3. The method of claim 1, wherein training an initial probabilistic calculation model using the user data of the plurality of users to determine the pre-trained probabilistic calculation model comprises:

extracting characteristic information from the user data, adding the characteristic information into a characteristic information set to be selected, wherein the characteristic information is used for describing information related to a user or related to an article, and executing the following training process:

combining each item of feature information in the feature information set to be selected with feature information in a preset feature information set respectively, and training the initial probability calculation model to obtain a plurality of test probability calculation models; determining a test probability calculation model with the minimum error in the plurality of test probability calculation models as a first test probability calculation model; determining to obtain feature information in a feature information set to be selected adopted by the first test probability calculation model;

comparing the error of the probability calculated by the first test probability calculation model and the initial probability calculation model with the actual probability, responding to the error that the error of the probability of the user for purchasing the goods calculated by the first test probability calculation model is larger than the error that the probability of the user for purchasing the goods calculated by the initial probability calculation model, and determining that the initial probability calculation model is the pre-trained probability calculation model;

and responding to the error of the probability that the first test probability calculation model calculates the user purchases the goods and is smaller than the error of the probability that the initial probability calculation model calculates the user purchases the goods, determining that the first test probability calculation model is the initial probability calculation model, deleting the feature information from the feature information set to be selected, adding the feature information into the feature information set, and continuing to execute the training process.

4. The method of claim 1, further comprising the step of determining the probability threshold, the step of determining the probability threshold comprising:

acquiring user data of a plurality of users clicking the item from a cache area for storing the user data, wherein the user data comprises click information and a cost deduction number;

the probability calculation model calculates the probability of each user purchasing the article according to the click information and the expense deduction number of each user;

determining the number of users who purchase the articles according to the expected purchase proportion preset by the articles, and determining the number as an expected number;

and determining the probability of purchasing the items of the first expected number of the users as the probability threshold value according to the sequence of the probability of purchasing the items of each user from large to small.

5. An apparatus for pushing information, the apparatus comprising:

the receiving unit is configured to receive click information of a user on the article information presented on the user terminal;

a determining unit configured to determine, according to the item information, a first fee deduction number and a maximum fee deduction number for the user to purchase an item indicated by the item information, where the first fee deduction number is less than or equal to the maximum fee deduction number;

a pushing unit configured to perform the following information pushing steps according to the click information and the first fee deduction number: determining the probability of the user purchasing the article according to the click information, the first expense deduction number and a pre-trained probability calculation model, wherein the probability calculation model is used for representing the corresponding relation between the click information and the probability of the user purchasing the article when the expense deduction of the first expense deduction number is provided for the user; determining whether the probability is greater than or equal to a preset probability threshold; in response to determining that the probability is greater than or equal to the preset probability threshold, pushing information including the first cost deduction number to the user terminal;

an updating unit, configured to, in response to determining that the probability is smaller than the preset probability threshold, increase a value of the first cost deduction number to update the first cost deduction number, and when it is determined that the updated first cost deduction number is smaller than or equal to the maximum cost deduction number, continue to perform the information pushing step; and

the update unit is further configured to: stopping executing the information pushing step in response to the updated first fee deduction number being greater than the maximum fee deduction number; pushing information including the maximum cost deduction number to the user terminal;

the apparatus further includes a probability calculation model determination unit including:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is configured to acquire user data of a plurality of users from a cache region for storing the user data, and the user data comprises click information, cost deduction number and purchase information of the users;

and the training module is configured to train an initial probability calculation model by using the user data of the plurality of users, and determine the pre-trained probability calculation model.

6. The apparatus of claim 5, wherein the determining unit is further configured to:

7. The apparatus of claim 5, wherein the training module is further configured to:

combining each item of feature information in the feature information set to be selected with feature information in a preset feature information set respectively, and training the initial probability calculation model to obtain a plurality of test probability calculation models; determining a test probability calculation model with the minimum error as a first test probability calculation model; determining to obtain feature information in a feature information set to be selected adopted by the first test probability calculation model;

8. The apparatus of claim 5, further comprising a probability threshold determination unit configured to:

9. An electronic device for pushing information, the electronic device comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-4.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-4.