Disclosure of Invention
The embodiment of the application provides a user-defined crowd division method and a user-defined crowd division system, which are used for at least solving the problem that the analysis of the advertising effect is influenced because the crowd analysis of various application personnel is not integrated in the prior art.
According to one aspect of the application, a method for customizing crowd division is provided, which comprises the following steps: acquiring data that advertisements launched on each of a plurality of application software are processed by a user; classifying the users who process the advertisements on each application software respectively according to the characteristic information of the users who process the advertisements on each application software to obtain the classification result of the users on each application software; acquiring a label corresponding to each type of application software, wherein the label is a predetermined label and is used for indicating characteristic information of the application software; grouping the application software with the same label in the multiple kinds of application software to obtain at least one group; and acquiring the user classification corresponding to the application in each group of the at least one group to obtain the classification result of the user corresponding to each group.
Further, the user processing the advertisement includes at least one of: the user views the advertisement, the user clicks on the advertisement, the user purchases a product in the advertisement, and the user forwards the advertisement.
Further, the characteristic information of the user includes at least one of: gender of the user, age of the user, work industry of the user, income of the user, hobbies of the user.
Further, still include: obtaining tags of preset application software to be advertised, wherein the number of the tags is at least one; acquiring a group including a part or all of tags of the predetermined application software; and determining whether to carry out advertisement putting on the preset application software according to the obtained classification result of the users of the group and the audience group to be put with the advertisement.
Further, determining whether to deliver the advertisement on the predetermined application software according to the obtained classification result of the group of users and the audience group to which the advertisement is to be delivered comprises: determining to launch the advertisement on the predetermined application software under the condition that the obtained classification result of the group of users is consistent with the characteristics of the audience group to launch the advertisement; otherwise, not putting the advertisement.
According to another aspect of the present application, there is also provided a system for customized crowd division, including: the first acquisition module is used for acquiring data processed by a user of advertisements launched on each of the plurality of application software; the classification module is used for classifying the users who process the advertisements on each application software respectively according to the characteristic information of the users who process the advertisements on each application software to obtain the classification result of the users on each application software; the second acquisition module is used for acquiring a label corresponding to each type of application software, wherein the label is a predetermined label and is used for indicating the characteristic information of the application software; the grouping module is used for grouping the application software with the same label in the multiple kinds of application software to obtain at least one group; and the obtaining module is used for obtaining the user classification corresponding to the application in each group in the at least one group and obtaining the classification result of the user corresponding to each group.
Further, the user processing the advertisement includes at least one of: the user views the advertisement, the user clicks on the advertisement, the user purchases a product in the advertisement, and the user forwards the advertisement.
Further, the characteristic information of the user includes at least one of: gender of the user, age of the user, work industry of the user, income of the user, hobbies of the user.
Further, still include: the system comprises a determining module, a judging module and a judging module, wherein the determining module is used for acquiring tags of preset application software to be advertised, and the tags are at least one; acquiring a group including a part or all of tags of the predetermined application software; and determining whether to carry out advertisement putting on the preset application software according to the obtained classification result of the users of the group and the audience group to be put with the advertisement.
Further, the determination module is to: determining to launch the advertisement on the predetermined application software under the condition that the obtained classification result of the group of users is consistent with the characteristics of the audience group to launch the advertisement; otherwise, not putting the advertisement.
In the embodiment of the application, data for acquiring advertisements launched on each of multiple application software and processed by a user is adopted; classifying the users who process the advertisements on each application software respectively according to the characteristic information of the users who process the advertisements on each application software to obtain the classification result of the users on each application software; acquiring a label corresponding to each type of application software, wherein the label is a predetermined label and is used for indicating characteristic information of the application software; grouping the application software with the same label in the multiple kinds of application software to obtain at least one group; and acquiring the user classification corresponding to the application in each group of the at least one group to obtain the classification result of the user corresponding to each group. Through the application, the problem that in the prior art, the analysis of the advertisement putting effect is influenced due to the fact that the crowd analysis of various application personnel is not integrated is solved, so that the accuracy of the analysis of the advertisement putting effect is improved, and data support is provided for accurate putting of advertisements on application software.
Detailed Description
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.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
In this embodiment, a method for customizing crowd division is provided, and fig. 1 is a flowchart of the method for customizing crowd division according to the embodiment of the present application, and as shown in fig. 1, the method includes the following processes:
step S102, acquiring data that advertisements put on each application software in a plurality of application software are processed by a user; for example, the user processing the advertisement includes at least one of: the user views the advertisement, the user clicks on the advertisement, the user purchases a product in the advertisement, and the user forwards the advertisement.
Step S104, classifying the users who process the advertisement on each application software respectively according to the characteristic information of the users who process the advertisement on each application software to obtain the classification result of the users on each application software; for example, the characteristic information of the user includes at least one of: gender of the user, age of the user, work industry of the user, income of the user, hobbies of the user.
As another alternative implementation, the feature information of the user may further include behavior information of the user, where the behavior information of the user includes an operation performed by the user on the application software, and the operation may include at least one of: the content browsed by the user, the content collected by the user, the comment issued by the user and the content shielded by the user.
Firstly, the preference characteristics of the user are obtained according to the operation of the user on the application software, then the preference characteristics of all the users are obtained, and for each preference characteristic of the user, the preference characteristics are at least one of the following characteristics according to all the users: the gender of the user, the age of the user, the work industry of the user, the income of the user, the hobbies of the user classify the users who handle the advertisement.
As another optional implementation, obtaining the favorite features of the user according to the operation performed by the user in the application software may be implemented by using a machine learning model based on a neural network, and obtaining multiple sets of artificially labeled training data, where each of the multiple sets of artificially labeled training data includes an operation performed by the user and a favorite label corresponding to the artificially labeled user performing the operation, where the favorite label is used to indicate the favorite of the user. Then, a machine learning model is trained by using a plurality of sets of training data, after a converged machine learning model is obtained, the operation of the user on the application software is input into the machine learning model, and the output preference characteristics of the user are acquired from the machine learning model.
Step S106, obtaining a label corresponding to each application software, wherein the label is a predetermined label and is used for indicating the characteristic information of the application software.
In an alternative embodiment, there are many ways to label each application, as will be described below.
The method comprises the steps of inputting the name of application software, searching for an introduction of the application software corresponding to the name of the application software pre-stored in a database according to the name of the application software, determining the property of the application software according to the introduction of the application software, and determining a corresponding template according to the property of the application software, wherein the template comprises a plurality of labels.
For example, the software introduction is extracted from the data source (the data source may include company official website, company profile, description of the application software, and public information of evaluation of the application software), the extraction may be performed by using a machine learning model, and in this embodiment, the first machine learning model may be trained by using a plurality of sets of first training data to obtain a usable machine learning model. The multiple groups of first training data comprise input data and output data, wherein the input data are the application data source, and the output data are artificially the introduction summarized by the application software. After the converged first machine learning model is obtained by training, it can be used. A data source is input into the first machine learning model, which outputs an introduction to the application software.
Extracting keywords from the introduction of the application software, wherein the keywords are used for indicating the properties of the application software, searching a template which is configured in advance and comprises all the extracted keywords, taking the template as a template corresponding to the application software, and acquiring the label in the template.
It should be noted that the tags included in each template at least include tags that are keywords, and also include tags that are words with similar meaning to the keywords.
And step S108, grouping the application software with the same label in the multiple kinds of application software to obtain at least one group.
Step S110, obtaining a user classification corresponding to the application in each group of the at least one group, and obtaining a classification result of the user corresponding to each group.
Through the steps, the problem that in the prior art, the analysis of the advertisement putting effect is influenced due to the fact that the crowd analysis of various application personnel is not integrated is solved, so that the accuracy of the analysis of the advertisement putting effect is improved, and data support is provided for accurate putting of advertisements on application software.
After the above steps, the advertisement can be delivered by using the above classification result, for example, obtaining tags of predetermined application software to be delivered, where the tags are at least one; acquiring a group including a part or all of tags of the predetermined application software; and determining whether to carry out advertisement putting on the preset application software according to the obtained classification result of the users of the group and the audience group to be put with the advertisement. Determining to launch the advertisement on the predetermined application software under the condition that the obtained classification result of the group of users is consistent with the characteristics of the audience group to launch the advertisement; otherwise, not putting the advertisement.
When placing an advertisement, the following method for managing the online advertisement bidding process can be used, and is described below.
In the method, a plurality of advertisements are received; receiving a plurality of bids, wherein each bid in the plurality of bids corresponds to an advertisement in the plurality of advertisements, wherein each bid in the plurality of bids includes a bid price and at least one of a mobile device location feature or a user location feature; calculating a score for each of the plurality of advertisements as a function of the bid price and at least one of a mobile device targeting feature or a user targeting feature; receiving device characteristics of a mobile device context of a mobile device; receiving a user characteristic based on a user context; and selectively present one or more of the plurality of advertisements based on the calculated score, the received mobile device characteristics, and the received user characteristics.
Optionally, each bid in the plurality of bids includes a bid, a mobile device location feature, and a user location feature, wherein the function includes a bid, a mobile device location feature, and a user location feature.
Optionally, the mobile device location feature comprises a temporal feature and a location feature, and wherein the user location feature comprises a user segment feature.
Optionally, each bid of the plurality of bids includes a bid price, a category characteristic, and at least one of a mobile device targeting characteristic or a user targeting characteristic, and wherein the function includes at least one of a bid price, a category characteristic, and a mobile device targeting characteristic or a user targeting characteristic.
Optionally, the function includes a bid price, a mobile device targeting characteristic, a user targeting characteristic, and an advertisement effectiveness characteristic.
Optionally, the advertisement effectiveness characteristic includes at least one of an exchange rate, a response rate, a discount amount, community-based feedback, advertiser popularity, product popularity, or service popularity. Optionally, the method further comprises: receiving user feedback corresponding to the selectively presented one or more advertisements; determining an advertisement effectiveness characteristic based on the received user feedback; and selectively presenting one or more advertisements to another user based on the determined advertisement effectiveness.
In this embodiment, an electronic device is provided, comprising a memory in which a computer program is stored and a processor configured to run the computer program to perform the method in the above embodiments.
The programs described above may be run on a processor or may also be stored in memory (or referred to as computer-readable media), which includes both non-transitory and non-transitory, removable and non-removable media, that implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
These computer programs may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks, and corresponding steps may be implemented by different modules.
Such an apparatus or system is provided in this embodiment. The first acquisition module is used for acquiring data processed by a user of advertisements launched on each of the plurality of application software; the classification module is used for classifying the users who process the advertisements on each application software respectively according to the characteristic information of the users who process the advertisements on each application software to obtain the classification result of the users on each application software; the second acquisition module is used for acquiring a label corresponding to each type of application software, wherein the label is a predetermined label and is used for indicating the characteristic information of the application software; the grouping module is used for grouping the application software with the same label in the multiple kinds of application software to obtain at least one group; and the obtaining module is used for obtaining the user classification corresponding to the application in each group in the at least one group and obtaining the classification result of the user corresponding to each group.
The system or the apparatus is used for implementing the functions of the method in the foregoing embodiments, and each module in the system or the apparatus corresponds to each step in the method, which has been described in the method and is not described herein again.
For example, the user processing the advertisement includes at least one of: the user views the advertisement, the user clicks on the advertisement, the user purchases a product in the advertisement, and the user forwards the advertisement. And/or the characteristic information of the user comprises at least one of the following: gender of the user, age of the user, work industry of the user, income of the user, hobbies of the user.
For another example, the method further includes: the system comprises a determining module, a judging module and a judging module, wherein the determining module is used for acquiring tags of preset application software to be advertised, and the tags are at least one; acquiring a group including a part or all of tags of the predetermined application software; and determining whether to carry out advertisement putting on the preset application software according to the obtained classification result of the users of the group and the audience group to be put with the advertisement. Optionally, the determining module is configured to: determining to launch the advertisement on the predetermined application software under the condition that the obtained classification result of the group of users is consistent with the characteristics of the audience group to launch the advertisement; otherwise, not putting the advertisement.
The problem that in the prior art, the analysis of the advertisement putting effect is influenced due to the fact that the crowd analysis of various application personnel is not integrated is solved through the embodiment, the accuracy of the analysis of the advertisement putting effect is improved, and data support is provided for accurate putting of advertisements on application software.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.