CN112862544B

CN112862544B - Object information acquisition method, device and storage medium

Info

Publication number: CN112862544B
Application number: CN202110276637.3A
Authority: CN
Inventors: 孙广宇; 王胜华; 史承毅; 郝龙飞
Original assignee: Chongqing Duxiaoman Youyang Technology Co ltd
Current assignee: Chongqing Duxiaoman Youyang Technology Co ltd
Priority date: 2021-03-15
Filing date: 2021-03-15
Publication date: 2024-05-28
Anticipated expiration: 2041-03-15
Also published as: CN112862544A

Abstract

The invention discloses a method, a device and a storage medium for acquiring object information, wherein the method comprises the following steps: and acquiring behavior data of the target advertisement by the user through the electronic equipment, wherein the behavior data comprises a return identifier, an identifier of an advertisement plan to which the target advertisement belongs, an equipment identifier of the electronic equipment and behavior time for the target advertisement, the user is a user who clicks the target advertisement through a first medium, and/or the user is a user who does not finish target advertisement conversion through a second medium but does not finish target advertisement conversion through the first medium, determining whether the user is a predictive conversion user according to the identifier of the advertisement plan to which the target advertisement belongs and preset configuration information, wherein the configuration information at least comprises the identifier of the advertisement plan or the identifier of an advertiser account, and if the user is determined to be the predictive conversion user, transmitting the information of the user to a media server of the first medium. Thereby increasing the amount of sample data of the ad model on the media server side of the first media.

Description

Object information acquisition method, device and storage medium

Technical Field

The present invention relates to the field of internet technologies, and in particular, to a method and an apparatus for acquiring object information, and a storage medium.

Background

The information flow advertisement refers to an advertisement put in the information flow of social media, information media and audio-visual media by an advertiser, and mainly comprises the forms of pictures, texts and videos. The current process of information flow advertisement acquisition is as follows: the method comprises the steps that a media server displays information flow advertisements through an advertisement position on an interface of electronic equipment, when a user browses the advertisements, the user clicks the advertisements displayed in the advertisement position through the electronic equipment, the electronic equipment responds to clicking operation of the user and sends a browsing request to the media server, the media server jumps to an advertisement landing page according to the browsing request, the user registers on the advertisement landing page through the electronic equipment and downloads an advertisement Application program (APP), and APP login, application, credit and other processes are carried out by using the APP, wherein the user who enters different process nodes such as registration, APP downloading, APP login, application, credit and the like is called a target conversion user. In the target conversion bidding (Optimized Cost Per Click, OCPC) mode in the information stream advertisement acquisition, the advertiser server is required to transmit the information of the target conversion user back to the media server, and after the media server acquires the information of the target conversion user, the information of the target conversion user can be applied to the advertisement model, so that the capability of the advertisement model for identifying the target guest group is improved, further, the advertiser is helped to acquire more effective clients, the conversion rate is improved, and the conversion cost is reduced.

In the related art, the method for the media server to obtain the information of the target conversion user is as follows: the method comprises the steps that a flow node message of a user is obtained through an advertiser server, the flow node message comprises the time of occurrence of the flow node and the value of the flow node, then when the advertiser server confirms that the flow node needs to be returned according to the flow node message and a pre-stored channel return information table, the return identifier of the transparent transmission of an advertisement landing page corresponding to the user is inquired, the return identifier is an identifier generated by a media server when the user clicks the advertisement through electronic equipment, and the unique identifier corresponding to the advertisement is distributed to the user for the media server. The advertiser server sends information of the target conversion user to the media server, wherein the information of the target conversion user comprises the feedback identification, the time of occurrence of the flow node and the value of the flow node.

In the initial stage of new advertisement plan throwing, the advertisement model is in a learning period, and the learning period needs to carry out model learning according to the information of the target conversion user and the user attribute information of the target conversion user, but the accumulation of advertisement display and click quantity in the initial stage of new advertisement plan throwing is less, and the target conversion user is less or even has no target conversion condition, and only the information of less target conversion user can be acquired by the method, so that the advertisement model cannot normally pass the learning period.

Disclosure of Invention

The invention provides a method, a device and a storage medium for acquiring object information, which are used for solving the problem that an advertisement model cannot normally pass a learning period due to the fact that the acquired amount of information of a target conversion user is small.

In a first aspect, the present invention provides a method for acquiring object information, including:

Acquiring behavior data of a target advertisement by a user through electronic equipment, wherein the behavior data comprises a return identifier, an identifier of an advertisement plan to which the target advertisement belongs, an equipment identifier of the electronic equipment and behavior time of the target advertisement, the user is a user who clicks the target advertisement through a first medium, and/or the user is a user who does not finish the conversion of the target advertisement through the first medium but finishes the conversion of the target advertisement through a second medium;

determining whether the user is a predictive conversion user or not according to the identification of the advertisement plan to which the target advertisement belongs and preset configuration information, wherein the configuration information at least comprises the identification of the advertisement plan or the identification of an advertiser account;

And if the user is determined to be the predictive conversion user, sending the information of the user to a media server of the first media, wherein the information of the user comprises the feedback identification and the behavior time of the target advertisement.

Optionally, the user clicks the target advertisement through the first media, and after the behavior data of the user on the target advertisement through the electronic device is obtained, the method further includes:

Determining the model score of the electronic equipment according to the equipment identifier of the electronic equipment and the corresponding relation between the prestored equipment identifier and the model score;

The configuration information further includes a correspondence between an advertisement plan identifier or an advertiser account identifier and model score information, where the model score information includes a model score type to be returned, a numerical range of the model score, and a returned number, and the determining whether the user is a predictive conversion user according to the returned identifier, the advertisement plan identifier to which the target advertisement belongs, and preset configuration information includes:

And determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs, the model score of the electronic equipment and the configuration information.

Optionally, the acquiring behavior data of the user on the target advertisement through the electronic device includes:

and receiving click data of the target advertisement sent by a media server of the first media, wherein the action time of the target advertisement comprises the click time of the target advertisement.

Optionally, the determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs, the model score of the electronic device and preset configuration information includes:

According to the corresponding relation between the identification of the advertisement plan and the model score information, searching the model score information corresponding to the identification of the advertisement plan, or according to the corresponding relation between the identification of the advertiser account and the model score information and the corresponding relation between the identification of the pre-stored advertiser account and the identification of the advertisement plan, searching the model score information corresponding to the identification of the advertisement plan;

According to the model score information corresponding to the identification of the advertisement plan, if the model score of the electronic equipment is determined to be the model score type needing returning and is in the numerical range of the model score, and the number of the currently returned predictive conversion users is smaller than the returning number, determining that the users are predictive conversion users;

If the model score of the electronic equipment is not the model score type needing returning, determining that the user is not a predictive conversion user;

if the model score of the electronic equipment is determined to be the model score type needing returning but not to be in the numerical range of the model score, determining that the user is not a predictive conversion user;

If the model score of the electronic equipment is determined to be the model score type needing returning and is in the numerical range of the model score, but the number of the prediction conversion users which are returned currently is larger than the returning number, determining that the users are not the prediction conversion users.

Optionally, the model part comprises at least one of a response part, an AB part, a profit part and a small derivative, wherein the response part is the advertisement click probability of the equipment, the AB part is the credit risk level of the equipment, the profit part is the credit probability or the profit probability of the equipment, and the small derivative is the probability of whether the enterprise owner corresponding to the equipment is the small micro enterprise owner.

Optionally, the user is a user who does not complete the target advertisement conversion through the first media but completes the target advertisement conversion through the second media, and the acquiring the behavior data of the user on the target advertisement through the electronic device includes:

Receiving display data of the target advertisement sent by a media server of the first media, wherein the display data of the target advertisement comprises a first equipment identification set and identifications of advertisement plans to which the target advertisement belongs, and equipment identifications in the first equipment identification set are equipment identifications of electronic equipment for displaying the target advertisement in the first media within a first preset time;

obtaining conversion information of a user who completes the target advertisement conversion through the second media and the second equipment identification set within a second preset time, wherein equipment identifications in the second equipment identification set are equipment identifications of equipment corresponding to the user who completes the target advertisement conversion through the second media within the second preset time, the first preset time is a time before the second preset time, and the conversion information comprises a return identification and a conversion occurrence time;

determining an intersection of the first equipment identification set and the second equipment identification set to obtain a third equipment identification set;

And obtaining behavior data of the user on the target advertisement through the electronic equipment according to the third equipment identification set, the identification of the advertisement plan to which the target advertisement belongs and conversion information of the user who completes the conversion of the target advertisement through the second media in a second preset time, wherein the behavior time of the user on the target advertisement is the occurrence time of the conversion.

Optionally, the determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs and preset configuration information includes:

if the identification of the advertisement plan to which the target advertisement belongs is found from the identifications of the advertisement plans included in the configuration information, determining that the user is a predictive conversion user; or alternatively

If the advertisement plan to which the target advertisement belongs is determined to belong to the advertiser account according to the identification of the advertisement plan to which the target advertisement belongs and the advertiser account identification included in the configuration information, determining that the user is a predictive conversion user.

In a second aspect, the present invention provides an apparatus for acquiring object information, including:

The system comprises an acquisition module, a target advertisement acquisition module and a target advertisement conversion module, wherein the acquisition module is used for acquiring behavior data of a target advertisement by a user through electronic equipment, wherein the behavior data comprises a return identifier, an identifier of an advertisement plan to which the target advertisement belongs, an equipment identifier of the electronic equipment and behavior time of the target advertisement, the user clicks the target advertisement through a first medium, and/or the user does not complete the target advertisement conversion through the first medium but completes the target advertisement conversion through a second medium;

The determining module is used for determining whether the user is a predictive conversion user or not according to the identification of the advertisement plan to which the target advertisement belongs and preset configuration information, wherein the configuration information at least comprises the identification of the advertisement plan or the identification of an advertiser account;

and the sending module is used for sending the information of the user to the media server of the first media when the determining module determines that the user is the predictive conversion user, wherein the information of the user comprises the feedback identification and the action time of the target advertisement.

In a third aspect, the present invention provides a server comprising:

A processor; and

A memory for storing executable instructions of the processor;

Wherein the processor is configured to perform the method of obtaining object information according to the first aspect or any of the possible implementations of the first aspect via execution of the executable instructions.

In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement a method for acquiring object information according to the first aspect or any of possible implementation manners of the first aspect.

In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a computer program, where the computer program when executed by a processor implements the method for obtaining object information according to the first aspect or any of the possible implementation manners of the first aspect.

The invention provides a method, a device and a storage medium for acquiring object information, wherein the object information comprises behavior data of a target advertisement by a user through electronic equipment, the behavior data comprises a return identifier, an identifier of an advertisement plan to which the target advertisement belongs, equipment identifier of the electronic equipment and behavior time for the target advertisement, the user clicks the target advertisement through a first medium and/or finishes target advertisement conversion through a second medium after target advertisement conversion is not completed through the first medium, and then the information of the user is sent to a media server of the first medium when the user is a prediction conversion user according to the identifier of the advertisement plan to which the target advertisement belongs and preset configuration information. Therefore, the method and the system realize that the prediction conversion user is determined from the first type user and/or the second type user, wherein the first type user is a user clicking the target advertisement, the second type user is a user showing that the target advertisement is not complete in conversion but the target advertisement is complete in conversion through the second medium through the first medium, and information of the prediction conversion user is sent to the media server of the first medium, so that an advertisement model at the media server side of the first medium can perform model learning according to the information of the prediction conversion user and the user attribute information of the prediction conversion user, the quantity of sample data of the advertisement model at the media server side of the first medium is increased, and the advertisement model can normally pass a learning period.

Drawings

Fig. 1 is a schematic view of an application scenario of a method for obtaining object information according to an embodiment of the present invention;

Fig. 2 is a flowchart of a method for obtaining object information according to an embodiment of the present invention;

Fig. 3 is a flowchart of an embodiment of a method for obtaining object information according to an embodiment of the present invention;

fig. 4 is a flowchart of an embodiment of a method for obtaining object information according to an embodiment of the present invention;

FIG. 5 is an interactive flowchart of an embodiment of a method for obtaining object information according to an embodiment of the present invention;

FIG. 6 is an interactive flowchart of an embodiment of a method for obtaining object information according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of an apparatus for acquiring object information according to an embodiment of the present invention;

Fig. 8 is a schematic structural diagram of a server according to an embodiment of the present invention.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.

The terms first and second and the like in the description, the claims and the drawings of embodiments of the invention are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the invention described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

First, some terms in the embodiments of the present invention are explained below to facilitate understanding by those skilled in the art.

1. Target conversion bids (Optimized Cost Per Click, OCPC) to target conversion to click bids in an optimized manner. For example, the user checks the advertiser advertisement in the media and completes the processes of registration, APP login, application, credit and the like in the advertiser APP, the advertiser server returns the target conversion user to the media server, the media server applies the target conversion user to the advertisement model to accurately obtain the rich portrait and the label data of the effective conversion user, the advertisement model optimizes the delivery algorithm according to the rich portrait and the label data, and combines the historical accumulated data to intelligently and dynamically adjust the bid for estimating the conversion rate and competing environment, thereby realizing accurate pushing, further helping the advertiser to reach more effective clients, improving the conversion rate and reducing the conversion cost.

2. Click-Through-Rate (CTR), which refers to the Click-Through Rate of a web advertisement (e.g., a photo advertisement/text advertisement/keyword advertisement/rank advertisement/video advertisement, etc.), that is, the actual number of clicks of the advertisement divided by the advertisement's presentation.

3. Conversion Rate (CVR), which is an indicator of how effective an advertisement is, is the Conversion Rate of users clicking on advertisements to become an active or registered or even paid user.

4. The conversion user specifically refers to a conversion user of a certain advertisement, and the user can be a user registered from an advertiser landing page for a certain advertiser APP, or a user logged in after downloading the advertiser APP, or a user applying for, giving trust or using trust, for example, a user who subscribes to a page through the advertiser landing page or the advertiser APP for the advertiser APP being shopping APP, or the like.

In order to solve the problem that in the initial stage of new advertisement plan delivery, an advertisement model only can acquire less information of target conversion users, model learning can be carried out by taking the less information of the target conversion users and user attribute information of the target conversion users as sample data, and the advertisement model cannot normally pass a learning period, the embodiment of the invention provides a method and a device for acquiring object information and a storage medium, and behavior data of the target advertisement by a user through electronic equipment is acquired, wherein the user clicks the target advertisement through a first medium and/or finishes the target advertisement conversion through a second medium, and then the information of the user is transmitted to a media server of the first medium when the user is determined to be a predicted conversion user according to the identification of the advertisement plan to which the target advertisement belongs and preset configuration information. Therefore, the method and the system realize that the prediction conversion user is determined from the first type user and/or the second type user, wherein the first type user is a user clicking the target advertisement, the second type user is a user showing that the target advertisement is not complete in conversion but the target advertisement is complete in conversion through the second medium through the first medium, and information of the prediction conversion user is sent to the media server of the first medium, so that an advertisement model at the media server side of the first medium can perform model learning according to the information of the prediction conversion user and the user attribute information of the prediction conversion user, the quantity of sample data of the advertisement model at the media server side of the first medium is increased, and the advertisement model can normally pass a learning period.

Next, an application scenario according to an embodiment of the present invention is illustrated.

The method for acquiring object information provided by the embodiment of the invention can be at least applied to the following application scenarios, and is explained below with reference to the accompanying drawings.

Fig. 1 is a schematic view of an application scenario of a method for obtaining object information according to an embodiment of the present invention, as shown in fig. 1, in the application scenario of the present embodiment, an advertiser server 1 and a media server 2 are involved. Wherein communication between the advertiser server 1 and the media server 2 may be based on an internet protocol by wireless or wired means.

Wherein the advertiser server 1 provides an advertiser service platform for serving advertisers with advertisement delivery requirements, and the advertisers can set target audiences of advertisements, delivery areas, advertisement bids and the like on the platform.

The media server 2 provides a platform for carrying out omnibearing analysis and management on advertisement delivery of media information, and the media server 2 can manage advertisement positions of the user and control display of advertisements on a browser and the like. For information stream advertisements, in general, social media, information media, and audiovisual media are all types of media, information streams of various types of media are provided by a media server, and the information stream advertisements are configured in the media servers of the various types of media, and when a user browses the information streams using an electronic device, the media server simultaneously presents the information stream advertisements to the user.

The advertisement model is arranged at the side of the media server, and in the embodiment, the advertisement model predicts CTR and CVR of the user through the bid of the advertiser, advertisement materials and multidimensional data, and finally displays the materials of the advertiser with successful bid to the user.

The advertiser server 1 configures a display click link on a media advertisement platform through an agent, when the media server 2 displays advertisements to users in advertisement positions and the users click the advertisements, the media server 2 sends click data of the advertisements to the advertiser server 1 through the display link, the advertiser server 1 executes the object information acquisition method provided by the embodiment of the invention according to the click data of the advertisements to the users and preset configuration information, a prediction conversion user is determined, and information of the prediction conversion user is sent to the media server 2, an advertisement model at the side of the media server 2 can perform model learning according to the information of the prediction conversion user and user attribute information of the prediction conversion user, and the number of sample data of the advertisement model at the side of the media server of the first media is increased, so that the advertisement model can normally spend a learning period. In this embodiment, the user attribute information may include information such as the sex of the user, the device type of the electronic device operated by the user, the IP address, and the geographic location.

In another embodiment of the present invention, the advertiser server 1 acquires behavior data of a target advertisement of a user who does not complete the target advertisement conversion through a first medium but completes the target advertisement conversion through a second medium, then executes the object information acquisition method provided in the embodiment of the present invention according to the behavior data of the target advertisement of the user and preset configuration information, determines a predicted conversion user, and sends information of the predicted conversion user to the media server 2, and the advertisement model on the media server 2 side can perform model learning according to the information of the predicted conversion user and user attribute information of the predicted conversion user, so that the number of sample data of the advertisement model on the media server side of the first medium is increased, and thus the advertisement model can normally spend a learning period.

The following describes the technical scheme of the present invention and how the technical scheme of the present invention solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.

Fig. 2 is a flowchart of a method for acquiring object information according to an embodiment of the present invention, where the method for acquiring object information may be performed by an apparatus for acquiring object information, and the apparatus for acquiring object information may be implemented by software and/or hardware. The means for obtaining the object information may specifically be a chip or a circuit of the advertiser server. As shown in fig. 2, the method of the present embodiment may include:

S101, acquiring behavior data of a user on a target advertisement through electronic equipment, wherein the behavior data comprises a feedback identifier, an identifier of an advertisement plan to which the target advertisement belongs, an equipment identifier of the electronic equipment and behavior time of the target advertisement, the user is a user who clicks the target advertisement through a first medium, and/or the user is a user who does not complete the target advertisement conversion through the first medium but completes the target advertisement conversion through a second medium.

Specifically, the execution subject of the present embodiment may be an advertiser server, and specifically may be an advertiser server that provides targeted advertisements. The feedback identification is an identification generated by the media server when the user clicks the advertisement through the electronic equipment, and is a unique identification corresponding to the advertisement, which is distributed to the user by the media server, and the media server can identify the corresponding user according to the feedback identification. The behavior of the user on the target advertisement through the electronic equipment can be the behavior of clicking the target advertisement displayed in the advertisement position through the electronic equipment when the user browses the advertisement, correspondingly, the behavior data of the user on the target advertisement through the electronic equipment can be the clicking data of the user on the target advertisement, and the clicking data of the user on the target advertisement can comprise a return identification, an identification of an advertisement plan to which the target advertisement belongs, an equipment identification of the electronic equipment and the clicking time of the target advertisement. The behavior of the user on the target advertisement through the electronic equipment can also be the behavior of completing the transformation of the target advertisement through the media, correspondingly, the behavior data of the user on the target advertisement through the electronic equipment can be the transformation data of the user on the target advertisement through the electronic equipment, and the transformation data of the user on the target advertisement through the electronic equipment can comprise a return identification, an identification of an advertisement plan to which the target advertisement belongs, an equipment identification of the electronic equipment and the time when the transformation occurs. The device identifier of the electronic device may be a device number of the electronic device.

The users in this embodiment include one type of user (a first type of user or a second type of user described below) or two types of users (a first type of user and a second type of user described below), where the first type of user is a user who clicks on a target advertisement through a first media, that is, a user who clicks on a target advertisement browsed by clicking. Specifically, the first media displays the target advertisement in the advertisement position, the user clicks the target advertisement through the electronic equipment, the electronic equipment responds to clicking operation of the user and sends a browsing request of the target advertisement to the media server, and the media server jumps to an advertisement landing page of the target advertisement according to the browsing request. The second type of user is a user who does not complete target advertisement conversion through the first medium but completes target advertisement conversion through the second medium, the target advertisement is displayed through the first medium, but the user does not complete target advertisement conversion through the first medium, for example, a certain advertisement (called target advertisement) is put on both the first medium and the second medium, the user sees the display of the target advertisement through the first medium before a week, but sees the display of the target advertisement again through the second medium after a week, at this time, the user clicks the target advertisement displayed in the second medium advertisement position through the electronic device, registers on the target advertisement landing page, or further downloads an advertiser APP of the target advertisement through the target advertisement landing page, and uses the APP to perform APP login, application, credit and other processes, become the advertiser user of the target advertisement, and complete target advertisement conversion.

S102, determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs and preset configuration information, wherein the configuration information at least comprises the identification of the advertisement plan or the identification of an advertiser account.

Specifically, one or more advertisement plans may be set under an advertiser account, and a correspondence between an advertiser account identifier and an identifier of the advertisement plan set under the advertiser account may be stored in the advertiser server in advance. The configuration information may include an identification of the advertisement plan, or may include an identification of the advertiser account, if including the identification of the advertiser account, that is, the identification covering all advertisement plans set under the advertiser account.

And S103, if the user is determined to be the predictive conversion user, the information of the user is sent to a media server of the first media, and the information of the user comprises a feedback identification and the behavior time of the target advertisement.

Specifically, the advertiser server determines a predicted conversion user from two types of users, and sends information of the predicted conversion user to a media server of the first media. The information of the prediction conversion user comprises a return identifier and a behavior time for the target advertisement, wherein the return identifier is a unique identifier which is distributed to the user by the media server and corresponds to the target advertisement, and the media server of the first media can identify the target advertisement and the user corresponding to the target advertisement according to the return identifier. Because the actions of the user on the target advertisement are completed through the media server of the first media, the media server of the first media can acquire the user attribute information of the prediction conversion user, and the user attribute information can comprise information such as the gender of the user, the equipment type, the IP address, the geographic position and the like of the electronic equipment operated by the user. Therefore, the advertisement model at the media server side of the first media can perform model learning according to the information of the predictive conversion user and the user attribute information of the predictive conversion user, the number of sample data of the advertisement model at the media server side of the first media is increased, and the advertisement model can normally pass the learning period.

According to the object information acquisition method provided by the embodiment, behavior data of a target advertisement by a user through electronic equipment is acquired, the behavior data comprises a feedback identifier, an identifier of an advertisement plan to which the target advertisement belongs, an equipment identifier of the electronic equipment and behavior time for the target advertisement, the user clicks the target advertisement through a first medium and/or finishes target advertisement conversion through a second medium after target advertisement conversion is completed through the first medium, and then information of the user is sent to a media server of the first medium when the user is a predicted conversion user according to the identifier of the advertisement plan to which the target advertisement belongs and preset configuration information. Therefore, the method and the system realize that the prediction conversion user is determined from the first type user or the second type user, wherein the first type user is a user clicking the target advertisement, the second type user is a user showing that the target advertisement is not completed in conversion but the target advertisement is completed in conversion through the second medium through the first medium, and information of the prediction conversion user is sent to the media server of the first medium, so that an advertisement model at the media server side of the first medium can perform model learning according to the information of the prediction conversion user and the user attribute information of the prediction conversion user, the quantity of sample data of the advertisement model at the media server side of the first medium is increased, and the advertisement model can normally pass a learning period.

Fig. 3 is a flowchart of an embodiment of a method for obtaining object information according to an embodiment of the present invention, as shown in fig. 3, in this embodiment, a specific implementation is described by taking a determination of a prediction conversion user from a first type of users, where the first type of users click on a target advertisement through a first medium, and the method of this embodiment is based on the method shown in fig. 2, and optionally, S101 may be implemented by the following step S201:

S201, receiving click data of a target advertisement, sent by a media server of the first media, of a user, wherein the action time of the target advertisement comprises the click time of the target advertisement.

Specifically, the click data of the target advertisement by the user includes a return identifier, an identifier of an advertisement plan to which the target advertisement belongs, a device identifier of the electronic device, and a click time of the target advertisement.

After S201, the method may further include:

S202, determining the model score of the electronic equipment according to the equipment identification of the electronic equipment and the corresponding relation between the prestored equipment identification and the model score.

The model is divided into scores representing different dimensions of the electronic device, the model is specifically obtained through machine learning, deep learning, reinforcement learning and the like according to historical sample data related to device identification of the electronic device, for example, user groups corresponding to the same type of electronic device may be identical, and click probabilities of different electronic devices on advertisements can be obtained through machine learning.

As one implementation manner, the model part comprises at least one of response part, AB part, profit part and small derivative, wherein the response part is divided into advertisement click probability of the equipment, AB part is divided into credit risk level of the equipment, profit part is divided into credit probability or profit probability of the equipment, and the small derivative is divided into probability of whether a business owner corresponding to the equipment is a small micro-business owner or not.

Alternatively, the correspondence between the pre-stored device identifications and the model scores may be in the form of a table.

S203, determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs and the model score and configuration information of the electronic equipment.

In this embodiment, the configuration information further includes a correspondence between an identifier of the advertisement plan or an identifier of the advertiser account and model score information, where the model score information includes a model score type, a numerical range of the model score, and a number of returns that need to be returned.

Taking the example that the configuration information further includes the correspondence between the identification of the advertisement plan and the model score information, the following table is an example of configuration information:

List one configuration information

It should be noted that the configuration information shown in the table one is only an example, each advertisement plan is configured with only one model classification type, the numerical range of the model classification and the number of the feedback, and multiple model classification types, the numerical range of the model classification and the number of the feedback which need to be transmitted can be configured for each advertisement plan.

If the configuration information further includes a correspondence between the advertiser account identifier and the model score information, the model score information corresponding to the plurality of advertisement plans under the configured advertiser account is the same, and compared with each advertisement plan respectively configured, the configuration complexity can be reduced. But the separate configurations may obtain finer granularity sample data.

Specifically, S203 may specifically be:

S2031, searching model score information corresponding to the identification of the advertisement plan according to the corresponding relation between the identification of the advertisement plan and the model score information, or searching model score information corresponding to the identification of the advertisement plan according to the corresponding relation between the identification of the advertiser account and the model score information and the corresponding relation between the identification of the pre-stored advertiser account and the identification of the advertisement plan.

S2032, determining that the user is a predictive conversion user if the model score of the electronic device is determined to be the model score type needing to be returned and is within the numerical range of the model score according to the model score information corresponding to the identification of the advertisement plan and the number of the predictive conversion users which are currently returned is smaller than the number of returned.

Wherein, the following three situations exist for determining that the user is not the predictive conversion user: if the model score of the electronic equipment is not the model score type needing returning, determining that the user is not a predictive conversion user; if the model score of the electronic equipment is determined to be the model score type needing returning but not to be in the numerical range of the model score, determining that the user is not a predictive conversion user; if the model score of the electronic equipment is determined to be the model score type needing returning and is in the numerical range of the model score, but the number of the prediction conversion users which are returned currently is larger than the returning number, determining that the users are not the prediction conversion users.

S204, if the user is determined to be the predictive conversion user, the user information is sent to a media server of the first media, and the user information comprises a return identifier and click time of the target advertisement.

According to the object information acquisition method provided by the embodiment, click data of a user on a target advertisement sent by a media server of a first medium is received, the click data comprises a return identifier, an identifier of an advertisement plan to which the target advertisement belongs, an equipment identifier of electronic equipment and click time on the target advertisement, then model scores of the electronic equipment are determined according to the corresponding relation between the equipment identifier of the electronic equipment and pre-stored equipment identifiers and model scores, then whether the user is a predictive conversion user is determined according to the identifier of the advertisement plan to which the target advertisement belongs, the model scores of the electronic equipment and configuration information, and if the user is determined to be the predictive conversion user, the information of the user is sent to the media server of the first medium. The prediction conversion users are screened out through the click data of the target advertisements by the users and the corresponding relation between different equipment identifiers and model scores obtained through model learning, so that the advertisement models of the media server side of the first media can perform model learning according to the information of the prediction conversion users and the user attribute information of the prediction conversion users, the number of sample data of the advertisement models of the media server side of the first media is increased, and the advertisement models can normally spend a learning period.

Fig. 4 is a flowchart of an embodiment of a method for obtaining object information according to an embodiment of the present invention, as shown in fig. 4, in this embodiment, a specific implementation is described by taking a determination of a predicted conversion user from a second type of users, where the second type of users is users who complete target advertisement conversion through a first medium but complete target advertisement conversion through a second medium, and the method according to the embodiment is based on the method shown in fig. 2, and optionally, S101 may be implemented by the following steps S301 to S304:

S301, receiving display data of a target advertisement sent by a media server of a first media, wherein the display data of the target advertisement comprises a first equipment identification set and an identification of an advertisement plan to which the target advertisement belongs, and equipment identification in the first equipment identification set is equipment identification of electronic equipment of which the target advertisement is displayed by the first media within a first preset time.

Wherein the first preset time is, for example, 3 days, 5 days, 7 days, or the like.

S302, conversion information of a user who completes target advertisement conversion through second media and a second equipment identification set are obtained, equipment identifications in the second equipment identification set are equipment identifications of equipment corresponding to the user who completes target advertisement conversion through second media in second preset time, the first preset time is time before the second preset time, and the conversion information comprises a return identification and conversion occurrence time.

Specifically, the second preset time may be the time when the conversion is completed, and may also be the day when the conversion is completed. The first preset time is a time before the second preset time, for example, a user finishes the target advertisement conversion through the second medium 3 months and 8 days, and the first preset time may be 5 days before 3 months and 8 days, may include 3 months and 8 days, or may not include 3 months and 8 days.

S303, determining an intersection of the first equipment identification set and the second equipment identification set to obtain a third equipment identification set.

S304, according to the third equipment identification set, the identification of the advertisement plan to which the target advertisement belongs, and the conversion information of the user who finishes the target advertisement conversion through the second media in the second preset time, obtaining the behavior data of the user to the target advertisement through the electronic equipment, wherein the behavior time to the target advertisement is the occurrence time of the conversion.

Specifically, in this embodiment, the behavior data of the user on the target advertisement through the electronic device includes a backhaul identifier, an identifier of an advertisement plan to which the target advertisement belongs, a device identifier of the electronic device, and a time when the conversion occurs. The users corresponding to the device identifiers in the third device identifier set are conversion users, the third device identifier set is an intersection set of the first device identifier set and the second device identifier set, for each target device identifier in the third device identifier set, the identifier of the advertisement plan to which the target advertisement corresponding to the target device identifier belongs can be obtained according to the first device identifier set, the conversion information of the user corresponding to the target device identifier can be obtained according to the second device identifier set, and the conversion information comprises the backhaul identifier and the time of occurrence of the conversion, so that for each target device identifier in the third device identifier set, the backhaul identifier corresponding to each target device identifier, the identifier of the advertisement plan to which the target advertisement belongs and the time of occurrence of the conversion can be obtained, namely the behavior data of the user on the target advertisement through the electronic device.

S305, determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs and preset configuration information, wherein the configuration information comprises the identification of the advertisement plan or the identification of an advertiser account.

Specifically, when the configuration information includes an identification of the advertisement plan, S305 may be: if the identification of the advertisement plan to which the target advertisement belongs is found from the identifications of the advertisement plans included in the configuration information, determining that the user is a predictive conversion user. When the configuration information includes an advertiser account identification, S305 may be: if the advertisement plan to which the target advertisement belongs is determined to belong to the advertiser account according to the identification of the advertisement plan to which the target advertisement belongs and the advertiser account identification included in the configuration information, determining that the user is a predictive conversion user.

And S306, if the user is determined to be the predicted conversion user, the information of the user is sent to the media server of the first media, and the information of the user comprises a feedback identification and the time when the conversion occurs.

According to the object information acquisition method provided by the embodiment, the behavior data of the target advertisement, which comprises the feedback identification, the identification of the advertisement plan to which the target advertisement belongs, the equipment identification of the electronic equipment and the time when the conversion occurs, of the user who does not finish the target advertisement conversion through the first medium and finishes the target advertisement conversion through the second medium is acquired, then the predicted conversion user is determined according to the identification of the advertisement plan to which the target advertisement belongs in the behavior data and preset configuration information, so that an advertisement model at a media server side of the first medium can perform model learning according to the information of the predicted conversion user and the user attribute information of the predicted conversion user, the number of sample data of the advertisement model at a media server side of the first medium is increased, and the advertisement model can normally spend a learning period.

The detailed procedure of the method for acquiring object information provided by the present invention will be described with reference to a specific embodiment.

Fig. 5 is an interaction flow chart of an embodiment of a method for obtaining object information, which is provided in the embodiment of the present invention, taking determining a predicted conversion user from first users as an example, where the first users click on a target advertisement through a first medium, as shown in fig. 5, the method of the embodiment may include:

S401, the media server of the first media displays the target advertisement through the advertisement position of the first media.

S402, the media server of the first media responds to the operation that the user clicks the target advertisement through the electronic equipment, and jumps to the advertisement landing page of the target advertisement according to the browsing request.

S403, the media server of the first media sends click data of the target advertisement to the advertiser server.

The click data of the target advertisement by the user comprises a return identifier, an identifier of an advertisement plan to which the target advertisement belongs, a device identifier of the electronic device and click time of the target advertisement. The advertiser server is an advertiser server for targeted advertising.

S404, determining the model score of the electronic equipment according to the equipment identification of the electronic equipment and the corresponding relation between the prestored equipment identification and the model score.

S405, determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs and the model score and configuration information of the electronic equipment.

The configuration information comprises an identification of an advertisement plan or a corresponding relation between an advertiser account identification and model score information, wherein the model score information comprises a model score type, a numerical range of the model score and a return number which need to be returned.

In this embodiment, the specific process of S404-S405 may be referred to the description of the embodiment shown in fig. 3, and will not be repeated here.

Fig. 6 is an interaction flow chart of an embodiment of a method for obtaining object information according to an embodiment of the present invention, as shown in fig. 6, in this embodiment, a specific implementation is described by taking a determination of a predicted conversion user from a second class of users, where the second class of users is users who do not complete target advertisement conversion through a first medium but complete target advertisement conversion through a second medium, and the method of this embodiment may include:

s501, the media server of the first media displays the target advertisement through the advertisement space of the first media.

S502, the media server of the first media sends display data of the target advertisement in a first preset time to the advertiser server.

The display data of the target advertisement comprises a first equipment identification set and an identification of an advertisement plan to which the target advertisement belongs, wherein equipment identification in the first equipment identification set is the equipment identification of the electronic equipment of which the target advertisement is displayed by the first media within a first preset time.

S503, the media server of the second media displays the target advertisement through the advertisement space of the second media.

S504, conversion information of a user who finishes target advertisement conversion through the second media in a second preset time and a second equipment identification set are obtained.

The device identifiers in the second device identifier set are device identifiers of devices corresponding to users who finish target advertisement conversion through the second media in a second preset time, the first preset time is time before the second preset time, and the conversion information comprises a feedback identifier and conversion occurrence time.

S505, determining an intersection of the first equipment identification set and the second equipment identification set to obtain a third equipment identification set.

S506, according to the third equipment identification set, the identification of the advertisement plan to which the target advertisement belongs, and conversion information of the user who finishes target advertisement conversion through the second media in the second preset time, behavior data of the user to the target advertisement through the electronic equipment is obtained.

S507, determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs and preset configuration information, wherein the configuration information comprises the identification of the advertisement plan or the identification of an advertiser account.

And S508, if the user is determined to be the predictive conversion user, the information of the user is sent to a media server of the first media.

Wherein the information of the user comprises a backhaul identification and a time at which the conversion occurred.

In this embodiment, the specific process of S504-S508 can be referred to the description of the embodiment shown in fig. 4, and will not be repeated here.

In another embodiment of the present invention, it is possible to determine a predictive conversion user from among a first type user and a second type user, the first type user being a user who clicks on a target advertisement, the second type user being a user who shows that the target advertisement conversion is not completed through the first medium but completes the target advertisement conversion through the second medium, and send information of the predictive conversion user to a media server of the first medium, so that an advertisement model on the media server side of the first medium may perform model learning according to the information of the predictive conversion user and user attribute information of the predictive conversion user, the number of sample data of the advertisement model on the media server side of the first medium is increased, and the advertisement model may normally spend a learning period. The specific process of determining the predictive conversion user from the first type of users may be described with reference to the embodiment shown in fig. 5, and the specific process of determining the predictive conversion user from the second type of users may be described with reference to the embodiment shown in fig. 6, which is not repeated here.

The following are embodiments of the apparatus of the present application that may be used to perform the above-described method embodiments of the present application. For details not disclosed in the embodiments of the device according to the application, reference is made to the above-described method embodiments of the application.

Fig. 7 is a schematic structural diagram of an apparatus for acquiring object information according to an embodiment of the present invention, as shown in fig. 7, an apparatus of this embodiment may include: the system comprises an acquisition module 11, a determination module 12 and a sending module 13, wherein the acquisition module 11 is used for acquiring behavior data of a target advertisement by a user through electronic equipment, the behavior data comprises a return identifier, an identifier of an advertisement plan to which the target advertisement belongs, a device identifier of the electronic equipment and behavior time of the target advertisement, the user is a user who clicks the target advertisement through a first medium, and/or the user is a user who does not finish the conversion of the target advertisement through the first medium but finishes the conversion of the target advertisement through a second medium;

The determining module 12 is configured to determine whether the user is a predictive conversion user according to an identifier of an advertisement plan to which the target advertisement belongs and preset configuration information, where the configuration information at least includes an identifier of the advertisement plan or an identifier of an advertiser account;

The sending module 13 is configured to send information of the user to a media server of the first media when the determining module determines that the user is a predictive conversion user, where the information of the user includes the backhaul identification and a time of action on the target advertisement.

In an embodiment, the determining module 12 is further configured to determine, after the obtaining module 11 obtains the behavior data of the user on the target advertisement through the electronic device, a model score of the electronic device according to the device identifier of the electronic device and a corresponding relationship between a pre-stored device identifier and the model score.

Correspondingly, the configuration information further includes a correspondence between an advertisement plan identifier or an advertiser account identifier and model score information, where the model score information includes a model score type, a numerical range of the model score, and a number of returns that need to be returned, and the determining module 12 is configured to determine, according to the advertisement plan identifier to which the target advertisement belongs, the model score of the electronic device, and the configuration information, whether the user is a predicted conversion user.

Further, the obtaining module 11 is specifically configured to receive click data of the target advertisement sent by the media server of the first media, where the action time of the target advertisement includes a click time of the target advertisement.

Further, the determining module 12 is specifically configured to search for model score information corresponding to the identifier of the advertisement plan according to the correspondence between the identifier of the advertisement plan and the model score information, or search for model score information corresponding to the identifier of the advertisement plan according to the correspondence between the identifier of the advertiser account and the model score information and the correspondence between the identifier of the pre-stored advertiser account and the identifier of the advertisement plan;

In one embodiment, the model part comprises at least one of a response part, an AB part, a profit part and a small derivative, wherein the response part is divided into advertisement click probability of the equipment, the AB part is divided into credit risk level of the equipment, the profit part is divided into credit probability or profit probability of the equipment, and the small derivative is divided into probability of whether a business owner corresponding to the equipment is a small micro business owner or not.

In an embodiment, the obtaining module 11 is configured to:

In one embodiment, the determining module 12 is configured to determine that the user is a predictive conversion user if the identifier of the advertisement plan to which the target advertisement belongs is found from the identifiers of the advertisement plans included in the configuration information; or alternatively

The device provided in the embodiment of the present invention may execute the above method embodiment, and the specific implementation principle and technical effects of the device may be referred to the above method embodiment, and this embodiment is not described herein again.

It should be noted that, it should be understood that the division of the modules of the above apparatus is merely a division of a logic function, and may be fully or partially integrated into a physical entity or may be physically separated. And these modules may all be implemented in software in the form of calls by the processing element; or can be realized in hardware; the method can also be realized in a form of calling software by a processing element, and the method can be realized in a form of hardware by a part of modules. For example, the processing module may be a processing element that is set up separately, may be implemented in a chip of the above-mentioned apparatus, or may be stored in a memory of the above-mentioned apparatus in the form of program codes, and the functions of the above-mentioned processing module may be called and executed by a processing element of the above-mentioned apparatus. The implementation of the other modules is similar. In addition, all or part of the modules can be integrated together or can be independently implemented. The processing element here may be an integrated circuit with signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in a software form.

For example, the modules above may be one or more integrated circuits configured to implement the methods above, such as: one or more Application SPECIFIC INTEGRATED Circuits (ASIC), or one or more microprocessors (DIGITAL SIGNAL processors, DSP), or one or more field programmable gate arrays (field programmable GATE ARRAY, FPGA), etc. For another example, when a module above is implemented in the form of processing element scheduler code, the processing element may be a general purpose processor, such as a central processing unit (central processing unit, CPU) or other processor that may invoke the program code. For another example, the modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.) means from one website, computer, server, or data center. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc., that contain an integration of one or more available media. Usable media may be magnetic media (e.g., floppy disks, hard disks, magnetic tape), optical media (e.g., DVD), or semiconductor media (e.g., solid state disk STATE DISK (SSD)), among others.

Fig. 8 is a schematic structural diagram of a server according to an embodiment of the present invention, as shown in fig. 8, the server of the present embodiment may include a processor 21 and a memory 22,

Wherein the memory 22 is used for storing executable instructions of the processor 21.

The processor 21 is configured to perform the method of acquiring object information in the above-described method embodiment via execution of executable instructions.

Alternatively, the memory 22 may be separate or integrated with the processor 21.

When the memory 22 is a device independent from the processor 21, the server of the present embodiment may further include:

A bus 23 for connecting the memory 22 and the processor 21.

Optionally, the server of the present embodiment may further include: a communication interface 24, the communication interface 24 being connectable with the processor 21 via a bus 23.

The present application also provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed on a computer, cause the computer to perform the method of acquiring object information as in the above-described embodiments.

The embodiment of the application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the method for acquiring the object information in the embodiment.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.

Claims

1.A method for acquiring object information, comprising:

if the user is determined to be a predictive conversion user, sending information of the user to a media server of the first media, wherein the information of the user comprises the feedback identification and the action time of the target advertisement,

The user clicks the target advertisement through the first media, and after the behavior data of the user on the target advertisement through the electronic device is obtained, the method further comprises:

2. The method of claim 1, wherein the obtaining behavior data of the user for the targeted advertisement via the electronic device comprises:

3. The method according to claim 1, wherein the determining whether the user is a predictive conversion user according to the identification of the advertisement plan to which the target advertisement belongs, the model score of the electronic device, and preset configuration information includes:

4. A method according to any of claims 1-3, wherein the model component comprises at least one of a response component, an AB component, a profit component, and a small derivative, the response component being a probability of advertising clicks by the device, the AB component being a trust risk level of the device, the profit component being a probability of trust or a probability of profit by the device, and the small derivative being a probability of whether the device's corresponding business owner is a small micro business owner.

5. The method of claim 1, wherein the user is a user who does not complete the targeted advertisement conversion through a first medium but does complete the targeted advertisement conversion through a second medium, the obtaining behavior data of the user for the targeted advertisement through the electronic device, comprising:

Obtaining conversion information of a user completing the target advertisement conversion through the second media and a second equipment identification set within a second preset time, wherein equipment identifications in the second equipment identification set are equipment identifications of equipment corresponding to the user completing the target advertisement conversion through the second media within the second preset time, the first preset time is time before the second preset time, and the conversion information comprises a return identification and conversion occurrence time;

6. The method of claim 5, wherein determining whether the user is a predictive conversion user based on the identification of the advertisement plan to which the targeted advertisement belongs and preset configuration information comprises:

7. An object information acquisition apparatus, comprising:

A sending module, configured to send information of the user to a media server of the first media when the determining module determines that the user is a predictive conversion user, where the information of the user includes the backhaul identification and a time of action on the target advertisement,

8. A server, comprising:

A processor; and

A memory for storing executable instructions of the processor;

Wherein the processor is configured to perform the method of obtaining object information of any of claims 1-6 via execution of the executable instructions.

9. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the object information acquisition method according to any one of claims 1-6.