An advertisement pushing method and device, a cloud server and a storage medium

By building user profile and advertising profile databases in cloud servers and using user identifiers and advertising space identifiers for advertising push, the accuracy and real-time issues of advertising delivery in existing technologies are solved, achieving precise matching between users and commercial advertisements and improving the practicality and real-time nature of advertising.

CN115170168BActive Publication Date: 2026-04-24CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD
Filing Date
2021-04-07
Publication Date
2026-04-24

AI Technical Summary

Technical Problem

The accuracy, real-time nature, and usability of advertising delivery are difficult to guarantee with existing technologies, especially in internet and offline advertising, where the matching between users and commercial advertisements is not fully considered.

Method used

By building user profile and advertising profile databases in cloud servers, using user identifiers and advertising space identifiers to identify target ads, and pushing ads based on the similarity matching between user profiles and advertising profiles, precise matching between users and commercial ads can be achieved.

Benefits of technology

It improves the matching and accuracy of advertisements, enhances their usability and real-time nature, and ensures the effectiveness of advertisement delivery.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115170168B_ABST
    Figure CN115170168B_ABST
Patent Text Reader

Abstract

Embodiments of the present application provide an advertisement pushing method and device, a cloud server and a storage medium. The method comprises: obtaining advertisement demand information sent by a terminal; the advertisement demand information comprises a user identifier of a user to receive a pushed advertisement and an advertisement position identifier; determining a user portrait from a first database according to the user identifier; determining a set of advertisement portraits to be pushed from a second database according to the advertisement position identifier; determining a target advertisement portrait to be pushed from the set of advertisement portraits according to the user portrait; and performing advertisement pushing according to the target advertisement portrait.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to advertising push technology, and more particularly to an advertising push method, apparatus, cloud server, and storage medium. Background Technology

[0002] In related technologies, advertisements in advertising placement are generally selected and placed based on internet data or offline experience, and the accuracy, timeliness, and practicality of the advertisements cannot be guaranteed. Summary of the Invention

[0003] This application aims to provide an advertising push method, apparatus, cloud server, and computer storage medium.

[0004] In a first aspect, embodiments of this application provide an advertising push method applied to a cloud server, the method comprising:

[0005] Obtain advertising demand information sent by the terminal; the advertising demand information includes the user identifier of the user to receive the pushed advertisement and the advertisement slot identifier;

[0006] A user profile is determined from the first database based on the user identifier;

[0007] The set of ad profiles to be pushed is determined from the second database based on the ad slot identifier;

[0008] The target ad profile to be pushed is determined from the ad profile set based on the user profile;

[0009] Ads are pushed based on the target advertising profile.

[0010] Secondly, the embodiments disclosed in this application also provide an advertising push device, the advertising push device comprising: an acquisition module, configured to acquire advertising demand information sent by a terminal; the advertising demand information including a user identifier of a user to receive pushed advertisements and an advertisement slot identifier; a first determination module, configured to determine a user profile from a first database based on the user identifier; a second determination module, configured to determine a set of advertisement profiles to be pushed from a second database based on the advertisement slot identifier; a third determination module, configured to determine a target advertisement profile to be pushed from the set of advertisement profiles based on the user profile; and an advertising push module, configured to push advertisements based on the target advertisement profile.

[0011] Thirdly, embodiments of this application provide a cloud server, including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements the steps in the advertising push method described in the first aspect of embodiments of this application.

[0012] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the advertising push method described in the first aspect of embodiments of this application.

[0013] In this embodiment, since the target advertisement is determined based on the user identifier and the advertisement position identifier, the target advertisement fully considers the matching between the user and the commercial advertisement, and has higher practicality and accuracy. Furthermore, since the target advertisement is a commercial advertisement corresponding to the advertisement profile found directly in the second database in the cloud server, it has strong real-time performance.

[0014] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0016] Figure 1 A schematic diagram illustrating the implementation process of an advertising push method provided in this application embodiment;

[0017] Figure 2 A schematic diagram illustrating the implementation flow of the database creation method provided in this application embodiment;

[0018] Figure 3 A schematic diagram illustrating the implementation process of another advertising push method provided in this application embodiment;

[0019] Figure 4 A schematic diagram illustrating the implementation process of another advertising push method provided in this application embodiment;

[0020] Figure 5 A schematic diagram illustrating the implementation process of another advertising push method provided in this application embodiment;

[0021] Figure 6 A schematic diagram illustrating the implementation flow of the preprocessing method on a cloud server provided in this application embodiment;

[0022] Figure 7 This application provides a schematic diagram illustrating the process of merchant advertising placement.

[0023] Figure 8 This is a schematic diagram of the composition structure of the advertising push device provided in the embodiments of this application;

[0024] Figure 9 This is a schematic diagram of the composition structure of an advertising push system provided in an embodiment of this application.

[0025] Figure 10 This is a schematic diagram of a hardware entity of a cloud server provided in an embodiment of this application. Detailed Implementation

[0026] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the embodiments provided herein are merely illustrative of the present application and are not intended to limit the present application. Furthermore, the embodiments provided below are some embodiments for implementing the present application, and not all embodiments for implementing the present application. Unless otherwise specified, the technical solutions described in the embodiments of the present application can be implemented in any combination.

[0027] It should be noted that, in the embodiments of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a method or apparatus that includes a list of elements includes not only the elements expressly described, but also other elements not expressly listed, or elements inherent to implementing the method or apparatus. Without further limitations, an element defined by the phrase "comprising a..." does not exclude the presence of other related elements (e.g., steps in the method or units in the apparatus, such as portions of circuitry, processors, programs, or software, etc.) in the method or apparatus that includes that element.

[0028] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, U and / or W can represent: U existing alone, U and W existing simultaneously, and W existing alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of U, W, and V can mean including any one or more elements selected from the set consisting of U, W, and V.

[0029] With the rapid development of internet technology, advertising applications are becoming increasingly widespread, such as performance advertising platforms, offline billboards, and pay-per-click advertising. However, currently, advertising generally relies on internet data or offline experience to identify potential customers and select ad locations, and the accuracy, timeliness, and practicality of the data cannot be guaranteed.

[0030] Based on the issues mentioned above, we can consider displaying targeted advertisements to be pushed to users before they open the application (APP) on their devices. Figure 1 This is a schematic diagram illustrating the implementation process of an advertising push method provided in an embodiment of this application. (See attached diagram.) Figure 1 This advertising push method can be applied to cloud servers, and the process may include:

[0031] Step S101: Obtain advertising demand information sent by the terminal; the advertising demand information includes the user identifier of the user to receive the pushed advertisement and the advertisement slot identifier.

[0032] Understandably, the user identifier to receive the ad push can be the user's identity ID number, while the ad slot identifier can be the identifier of the application on the terminal used to display the ad to be pushed. For example, it can be the ID number of the app on the terminal, or it can be the ad type corresponding to the app on the terminal.

[0033] In one possible implementation, obtaining the advertising demand information sent by the terminal can involve the app on the terminal sending the advertising demand information to an advertising platform. The advertising platform then forwards the received advertising demand information to a cloud server, which in turn receives the advertising demand information sent by the terminal. Here, the advertising platform can be an advertising service provider system, which is a third-party application cloud server.

[0034] Step S102: Determine the user profile from the first database based on the user identifier.

[0035] Here, a user profile can be a user role, a virtual representative database of real users, which can be represented by vectors. In one example, a user profile refers to the set of dimensions of a user's basic attributes when entering a 5G base station, for example, user profile a(10, 2, 1, 9). It can be understood that user profile a has 4 dimensions, and 10, 2, 1, and 9 are the metric values ​​under the corresponding dimensions.

[0036] In one possible implementation, the first database may be a database obtained after performing a first preprocessing step on a cloud server. Here, the first preprocessing step may involve storing pre-established user profiles in the first database, and the user profiles may be stored using user IDs as the primary key.

[0037] Understandably, the first database can include user profiles of all users across the entire network.

[0038] The implementation method for determining a user profile from the first database based on the user identifier can be, for example, by searching for the user profile corresponding to the user ID in the first database based on the user ID.

[0039] Step S103: Determine the set of ad profiles to be pushed from the second database based on the ad slot identifier.

[0040] Here, an advertising profile can be a virtual representative database of real advertisements, which can be represented by a vector. In one example, an advertising profile refers to the set of basic attribute dimensions of merchant advertisements suitable for target audiences included under a 5G base station, such as advertising profile b (5, 4, 8, 3). It can be understood that the advertising profile b has 4 dimensions, and 5, 4, 8, and 3 are the metric values ​​under the corresponding dimensions.

[0041] In one possible implementation, the second database can be a database on a cloud server obtained after a second preprocessing step. Here, the second preprocessing step can involve storing pre-built advertising profiles in the second database, where the advertising profile can be stored using the advertising ID as the primary key and with added attribute tags. These attribute tags can be advertising types, i.e., the industries supported by the advertising.

[0042] Here, the second database and the first database can be the same database or different databases.

[0043] Understandably, the second database could include advertising profiles of all merchants across the entire network.

[0044] The implementation method for determining the set of ad profiles to be pushed from the second database based on the ad slot identifier can be exemplified by finding all ad profiles with the same ad type as the ad slot identifier from the second database, and determining the set of ad profiles composed of all ad profiles as the set of ad profiles to be pushed.

[0045] Step S104: Determine the target ad profile to be pushed from the ad profile set based on the user profile.

[0046] Here, the target ad profile to be pushed can be the ad profile corresponding to the commercial ads that need to be played before the user opens the APP.

[0047] In one possible implementation, the target ad profile to be pushed is determined from the ad profile set based on the user profile. This can be done by determining the ad profile with the highest similarity to the user profile from the ad profile set, and then determining the ad profile with the highest similarity as the target ad profile to be pushed.

[0048] Step S105: Push advertisements based on the target advertisement profile.

[0049] It is understandable that the implementation of ad push based on the target ad profile can be as follows: determine the target ad corresponding to the target ad profile based on the ad ID of the target ad profile, and push the target ad to the APP on the terminal. Specifically, after determining the target ad profile to be pushed, the server can send the ad ID of the target ad profile to the advertising platform. The advertising platform determines the target ad corresponding to the ad ID and sends the target ad to the server for the APP on the terminal to display the ad.

[0050] In practical applications, steps S101 to S105 can be implemented using a control unit in a cloud server. The control unit can be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor.

[0051] In the technical solution provided in this application embodiment, since the target advertisement is determined based on the user identifier and the advertisement position identifier, the target advertisement fully considers the matching between the user and the commercial advertisement, and has higher practicality and accuracy. Furthermore, since the target advertisement is a commercial advertisement corresponding to the advertisement profile found directly in the database of the cloud server, it has strong real-time performance.

[0052] Figure 2 This is a schematic diagram illustrating the implementation flow of the database creation method provided in this application embodiment. This database creation method can be applied to cloud servers, such as... Figure 2 As shown, the process includes:

[0053] Step S201: Obtain multiple user profiles under the first dimension and multiple advertising profiles under the second dimension.

[0054] Here, the first and second dimensions can be the same. The vector dimensions of multiple user profiles and multiple advertising profiles can be the same, but different metrics can be set for different user profiles and different merchant advertising profiles. For example, the dimension of the advertising profile can exclude gender, that is, the metric value of this dimension (gender) can be set to 0.

[0055] In one example, building multiple user profiles and multiple advertising profiles under the same dimension can be achieved by the cloud server receiving collected user information and merchant advertising information and automatically building multiple user profiles and multiple advertising profiles under the same dimension.

[0056] Step S202: Using the user identifier of each user profile in the plurality of user profiles as the primary key, store each user profile in the database to obtain the first database.

[0057] Here, the user identifier can be a user ID.

[0058] In one possible implementation, each user profile in the plurality of user profiles is stored in the database using the user identifier of each user profile in the plurality of user profiles as the primary key, thereby obtaining the database. Alternatively, a first cloud server may use the user identifier of each user profile in the plurality of user profiles as the primary key to store each user profile in the database of the first cloud server, thereby obtaining the first database.

[0059] Step S203: Using the advertisement identifier of each of the multiple advertisement images as the primary key and the advertisement type of each advertisement image as the attribute tag, store each advertisement image in the database to obtain the second database.

[0060] Here, the ad identifier can be the ad ID.

[0061] In one possible implementation, each of the multiple advertising profiles is stored in a database using its advertising identifier as the primary key and its advertising type as the attribute tag, thus creating a second database. This can be achieved using a second cloud server. The first cloud server and the second server can be the same cloud server or different cloud servers.

[0062] In this embodiment, multiple user profiles and multiple advertising profiles under the same dimension are constructed, and each user profile is stored in the database using the user identifier of each user profile as the primary key to obtain a first database; multiple advertising profiles are stored in the database using the advertising identifier of each advertising profile as the primary key and the advertising type of each advertising profile as the attribute label to obtain a second database. Therefore, it is beneficial to quickly filter based on the multiple user profiles and multiple advertising profiles stored in the database.

[0063] Figure 3This is a schematic diagram illustrating the implementation process of another advertising push method provided in an embodiment of this application. This advertising push method can be applied to cloud servers, such as... Figure 3 As shown, the process may include:

[0064] Step S301: Obtain advertising demand information sent by the terminal; the advertising demand information includes the user identifier of the user to receive the pushed advertisement and the advertisement slot identifier;

[0065] Step S302: Determine the user profile from the first database based on the user identifier.

[0066] Step S303: Determine the set of ad profiles to be pushed from the second database according to the ad type corresponding to the ad slot identifier.

[0067] Here, the different ad slot identifiers can correspond to the same or different ad types. For example, ad slot identifier A and ad slot identifier B can both correspond to the catering service industry.

[0068] It is understandable that the second database contains ad profiles for various ad types. The method for determining the set of ad profiles to be pushed from the second database based on the ad type corresponding to the ad placement identifier could be to search the second database for all ad profiles of the same type as the ad type corresponding to the ad placement identifier, form an ad profile set from these ad profiles, and then determine this set as the set of ad profiles to be pushed.

[0069] Step S304: Determine the similarity between the user profile and each advertising profile in the advertising profile set.

[0070] Here, the similarity between a user profile and each ad profile in the ad profile set can be the cosine of the angle between the user profile and each ad profile in the ad profile set, or the Euclidean distance. It's understandable that similarity metrics could also be represented by Mahaldon distance, Mahalanobis distance, etc. Of course, the similarity between a user profile and each ad profile in the ad profile set can also be the angle between the user profile and each ad profile in the ad profile set.

[0071] For example, the definition of the cosine of the included angle can be found in formula (1).

[0072] cosθ=a*b / (|a||b|) (1);

[0073] The definition of the vector angle between each ad profile in the user profile and ad profile sets is given in formula (2).

[0074] θ=arcos(a*b / (|a||b|)) (2);

[0075] Where a is the representation vector of the user profile, b is the representation vector of the advertising profile, and θ represents the angle between the vectors.

[0076] It can be seen that the cosine of the included angle is inversely proportional to the included angle value.

[0077] In one possible implementation, determining the similarity between the user profile and each advertising profile in the advertising profile set can be achieved by calculating the similarity value between the user profile and each advertising profile in the advertising profile set.

[0078] Step S305: Determine the target ad profile to be pushed from the ad profile set based on the similarity.

[0079] In some possible implementations, determining the target ad profile to be pushed from the ad profile set based on the similarity may involve searching for target ad profiles in the ad profile set whose similarity meets a first preset condition. Here, the first preset condition may be the maximum or minimum similarity.

[0080] Step S306: Send the target advertisement identifier corresponding to the target advertisement profile to the advertising platform, so that the advertising platform can push the target advertisement to the terminal according to the target advertisement identifier.

[0081] Here, the advertising platform can be an advertising service provider's system, which belongs to a third-party application cloud server.

[0082] In one possible implementation, the target ad identifier corresponding to the target ad profile is sent to the advertising platform, so that the advertising platform can push the target ad to the terminal based on the target ad identifier. Alternatively, the cloud server can send the target ad ID corresponding to the target ad profile to the advertising service provider, so that the advertising service provider can determine the corresponding target ad based on the received target ad ID and push the target ad to the terminal.

[0083] In this embodiment of the application, at least one advertising profile is determined from the second database according to the advertising type corresponding to the advertising slot identifier; the advertising profile set consisting of at least one advertising profile is determined as the advertising profile set to be pushed, and an advertising range set of the target advertising to be pushed can be obtained; by determining the similarity between the user profile and each advertising profile in the advertising profile set; the target advertising profile to be pushed is determined from the advertising profile set according to the similarity, and the target advertising profile to be pushed in the advertising profile set whose similarity with the user profile meets the first preset condition can be obtained.

[0084] Figure 4 This is a schematic diagram illustrating the implementation process of another advertising push method provided in this application embodiment. This advertising push method can be applied to cloud servers, such as... Figure 4 As shown, the process may include:

[0085] Step S401: Obtain advertising demand information sent by the terminal; the advertising demand information includes the user identifier of the user to receive the pushed advertisement and the advertisement slot identifier.

[0086] Step S402: Determine the user profile from the first database based on the user identifier.

[0087] Step S403: If the ad slot is identified as the identifier of the application used to display the ad to be pushed on the terminal, determine the set of ad profiles to be pushed from the second database according to the ad type corresponding to the application identifier.

[0088] Step S404: If the ad slot identifier is an ad type, determine the set of ad profiles to be pushed from the second database according to the ad type corresponding to the ad slot identifier.

[0089] Step S405: Determine the similarity between the user profile and each advertising profile in the advertising profile set; the similarity is the vector angle or the cosine of the angle.

[0090] Step S406: When the similarity is equal to the angle between the vectors, the advertising profile corresponding to the minimum similarity is determined as the target advertising profile to be pushed.

[0091] In some possible implementations, when the similarity is the vector angle, the advertising profile corresponding to the minimum similarity is determined as the target advertising profile to be pushed. This can be done by determining the advertising profile with the smallest vector angle value between the advertising profile set and the user profile as the target advertising profile to be pushed.

[0092] Step S407: When the similarity is the cosine of the included angle, the advertising profile corresponding to the maximum similarity is determined as the target advertising profile to be pushed.

[0093] In some possible implementations, when the similarity is the cosine of the angle, the advertising profile corresponding to the maximum similarity is determined as the target advertising profile to be pushed. This can be done by determining the advertising profile with the largest cosine value of the angle between the advertising profile set and the user profile as the target advertising profile to be pushed.

[0094] Step S408: Obtain the target advertisement based on the target advertisement identifier corresponding to the target advertisement profile, and push the target advertisement to the terminal.

[0095] In one possible implementation, obtaining a target advertisement based on the target advertisement identifier corresponding to the target advertisement profile and pushing the target advertisement to the terminal can be achieved by a cloud server obtaining the target advertisement from an advertising service provider based on the target advertisement identifier corresponding to the target advertisement profile, and then pushing the obtained target advertisement to the terminal. Here, the implementation of the cloud server obtaining the target advertisement from the advertising service provider based on the target advertisement identifier corresponding to the target advertisement profile can be achieved by the cloud server sending the target advertisement identifier corresponding to the target advertisement profile to the advertising service provider, the advertising service provider determining the target advertisement corresponding to the target advertisement identifier, and returning the determined target advertisement to the cloud server.

[0096] In another possible implementation, the target advertisement is obtained based on the target advertisement identifier corresponding to the target advertisement profile, and the target advertisement is pushed to the terminal. This can be achieved by storing commercial advertisements corresponding to the advertisement identifier in a cloud server, directly obtaining the target advertisement corresponding to the target advertisement profile from the cloud server based on the target advertisement identifier corresponding to the target advertisement profile, and then pushing the obtained target advertisement to the terminal.

[0097] In this embodiment of the application, when the ad slot identifier is the identifier of an application on the terminal used to display the ad to be pushed, the set of ad profiles to be pushed is determined from the second database according to the ad type corresponding to the application identifier; when the ad slot identifier is an ad type, the set of ad profiles to be pushed is determined from the second database according to the ad type corresponding to the ad slot identifier, thus obtaining a set of ad ranges for the target ad to be pushed.

[0098] In this embodiment, when the similarity is equal to the angle between the vectors, the advertising profile corresponding to the minimum similarity is determined as the target advertising profile to be pushed; when the similarity is equal to the cosine of the angle, the advertising profile corresponding to the maximum similarity is determined as the target advertising profile to be pushed. Therefore, the target advertising profile corresponding to the target advertising profile to be pushed, determined based on the similarity between the target advertising profile to be pushed and the user profile, is more in line with the user's needs and can meet the requirements of practicality and accuracy.

[0099] Figure 5 This is a schematic diagram illustrating the implementation process of another advertising push method provided in the embodiments of this application, such as... Figure 5 As shown, the process may include:

[0100] Step S501: The terminal in the advertising push system sends advertising demand information to the advertising platform in the system; the advertising demand information includes the user identifier of the user to receive the pushed advertisement and the advertisement slot identifier.

[0101] Step S502: The advertising platform in the system receives the advertising demand information and sends the advertising demand information to the cloud server in the system.

[0102] Step S503: The cloud server in the system receives the advertising demand information; determines the user profile from the first database based on the user identifier in the advertising demand information; determines the set of advertising profiles to be pushed from the second database based on the ad slot identifier in the advertising demand information; determines the target advertising profile to be pushed from the set of advertising profiles based on the user profile; and sends the target ad identifier corresponding to the target advertising profile to the advertising platform in the system.

[0103] Step S504: The advertising platform in the system receives the target advertisement identifier, determines the target advertisement corresponding to the target advertisement identifier, and pushes the target advertisement to the terminal in the system.

[0104] Step S505: The terminal in the system receives the target advertisement.

[0105] In this embodiment, the corresponding target ad profile to be pushed is searched in the database by the user identifier and the ad slot identifier, and the ad identifier of the target ad profile is sent to the ad platform. The ad platform pushes the target ad corresponding to the ad identifier to the terminal. Therefore, the practicality and accuracy are both high, and the real-time performance is also strong.

[0106] In related technologies, physical advertising, while leveraging the big data analytics capabilities of telecom operators, cannot achieve real-time ad delivery. Furthermore, offline advertising is significantly limited by geographical and spatial constraints, hindering the promotion and effectiveness of large stores. Ad pushes via user terminal information face challenges in information completeness. Additionally, the accuracy of information obtained from uninstalled or incorrectly installed software on users' phones is uncertain, presenting significant limitations. Moreover, using user profiles for marketing lacks practicality and timeliness, and fails to consider the matching of merchant ads with users, resulting in a biased approach.

[0107] Based on the above-mentioned technical problems, this application provides a method for real-time regional internet advertising push under 5G, which greatly leverages the accuracy of 5G base station positioning and the big data analysis capabilities of operators to accurately identify potential marketing customers, and delivers the analysis results to users in a timely manner through internet media, truly realizing the combination of 5G and advertising marketing.

[0108] Figure 6 This is a schematic diagram illustrating the implementation flow of the preprocessing method on a cloud server provided in the embodiments of this application, as shown below. Figure 6 As shown, the implementation steps of this preprocessing method are as follows:

[0109] Step S601: Select the vector dimensions of the user profile and the merchant advertising profile.

[0110] Here, the vector dimensions of user profiles and merchant advertising profiles can be selected either automatically by the server or by the developers.

[0111] Understandably, since a user's base station is determined based on their location, and a user's location is variable, to ensure consistency in the vector dimension measured under the same 5G base station, the vector dimension of all user profiles and all merchant advertising profiles within the network can be set to the same dimension. However, different metric values ​​can be set for different user profiles and different merchant advertising profiles. For example, the dimension for advertising profiles can exclude gender; that is, the metric value for that dimension can be set to 0.

[0112] In this embodiment of the application, under the same 5G base station, the vector dimensions of user profiles and merchant advertisements are selected. The dimensions need to be measurable (out of 10). The dimensions include gender (male: 5 points, female: 10 points), age (actual age divided by 10 and rounded down), distance to residence (1 point per kilometer, 10 points for distances over 10 kilometers), and spending power (2 points per star level, with a maximum of 10 points). The dimensions can be determined according to the specific merchants under the 5G base station, and it is necessary to ensure that the dimensions of user profiles and merchant advertisements are consistent.

[0113] Step S602: Create merchant advertising profiles under 5G cells, and classify them by industry, with merchant advertising as the primary key. Store the merchant advertising profile data in the database for quick filtering.

[0114] Here, the merchant advertising profile vector can be created according to the vector dimensions defined in S801, and the corresponding dimension measures such as merchant advertising profile b(5, 4, 8, 3) can be filled in respectively. At the same time, the advertising ID of the merchant advertising profile is used as the primary key, and an industry field is added to distinguish the merchant's industry. The created merchant advertising profile is then written into the database for storage.

[0115] Step S603: Create user profiles. Each user profile needs a unique user ID. User profile data needs to be stored in the database with the user ID as the primary key for quick filtering.

[0116] Here, user profile vectors can be created based on the vector dimensions defined in S801. The corresponding dimension measures, such as user profile a(10, 2, 1, 9), are filled in according to the mobile tag data. At the same time, the user ID is used as the primary key, and the created user profile is written to the database for storage.

[0117] After preprocessing on the cloud server, when a user enters a 5G cell and opens an app with an ad slot, the advertising platform synchronizes the user ID and ad type to the data service backend. The data service backend then enters matching mode and selects the optimal merchant ad for placement based on the ad type and the angle between the user vectors.

[0118] Figure 7 This application provides a schematic diagram illustrating the process of merchant advertising placement, as shown in the embodiments. Figure 7 As shown, the advertising placement process includes:

[0119] Step S701: The user enters the 5G base station.

[0120] Step S702: The user opens the APP with the advertising space.

[0121] Here, when a user opens a mobile app after entering a 5G base station, the ad placement request information is triggered. This information includes the industries that support the ad and the user's identification ID.

[0122] Step S703: The advertising platform receives the ad space request information sent by the APP and synchronizes the information to the data service backend.

[0123] Here, the server backend can be a type of cloud server implementation; the database in the server backend contains a user profile database with user ID as the primary key and a merchant advertising profile database with advertising ID as the primary key and industry as the distinguishing field.

[0124] Step S704: The data service backend obtains user profiles based on user identification IDs, and then filters out merchant advertising profiles that match the supported industries.

[0125] Step S705: The data service backend sequentially calculates the vector angle between the user profile vector and the advertising profile vector of each merchant that matches the industry to obtain the vector angle set.

[0126] Here, the set of vector angles can be represented as θ[arcos(a*b / (|a||b|))], where a is the representation vector of the user profile and b is the representation vector of the merchant advertising profile.

[0127] Step S706: The data service backend selects the merchant ad profile with the smallest angle between the push vectors as the target ad profile to be pushed.

[0128] Here, the merchant's advertising profile with the smallest vector angle is represented as min(θ[arcos(a*b / (|a||b|))]).

[0129] Step S707: The data service backend sends the merchant ad ID corresponding to the target ad profile to be pushed to the ad platform.

[0130] Step S708: The advertising platform determines the merchant advertisement corresponding to the merchant advertisement ID and pushes it to the terminal.

[0131] Figure 8 This is a schematic diagram of the composition structure of the advertising push device provided in the embodiments of this application, as shown below. Figure 8 As shown, the advertising push device 800 includes:

[0132] The acquisition module 801 is used to receive advertising demand information sent by the terminal; the advertising demand information includes the user identifier of the user to receive the pushed advertisement and the advertisement slot identifier;

[0133] The first determining module 802 is used to determine a user profile from the first database based on the user identifier;

[0134] The second determining module 803 is used to determine the set of advertising profiles to be pushed from the second database based on the advertising position identifier;

[0135] The third determining module 804 is used to determine the target advertisement profile to be pushed from the advertisement profile set based on the user profile;

[0136] The advertising push module 805 is used to push advertisements based on the target advertising profile.

[0137] In one embodiment, the advertising push module 805 is used to send the target advertising identifier corresponding to the target advertising profile to the advertising platform, so that the advertising platform can push the target advertisement to the terminal according to the target advertising identifier; or, obtain the target advertisement according to the target advertising identifier corresponding to the target advertising profile and push the target advertisement to the terminal.

[0138] In one embodiment, the cloud server further includes: a first preprocessing module, configured to acquire multiple user profiles under a first dimension and multiple advertising profiles under a second dimension; and to store each user profile in a database using the user identifier of each user profile as the primary key, thereby obtaining a first database; and a second preprocessing module, configured to store each advertising profile in a database using the advertising identifier of each advertising profile as the primary key and the advertising type of each advertising profile as the attribute tag, thereby obtaining a second database.

[0139] In one embodiment, the second determining module 803 is used to determine the set of advertising profiles to be pushed from the second database according to the advertising type corresponding to the advertising slot identifier.

[0140] In one embodiment, the second determining module 803 is configured to, when the ad slot identifier is the identifier of an application on the terminal for displaying an ad to be pushed, determine the set of ad profiles to be pushed from the second database according to the ad type corresponding to the identifier of the application; and when the ad slot identifier is an ad type, determine the set of ad profiles to be pushed from the second database according to the ad type corresponding to the ad slot identifier.

[0141] In one embodiment, the third determining module 804 is used to determine the similarity between the user profile and each advertising profile in the advertising profile set; and to determine the target advertising profile to be pushed from the advertising profile set based on the similarity.

[0142] In one embodiment, the similarity is the vector angle or the cosine of the angle. The third determining module 804 is used to determine the advertising profile corresponding to the minimum similarity as the target advertising profile to be pushed when the similarity is the vector angle; and to determine the advertising profile corresponding to the maximum similarity as the target advertising profile to be pushed when the similarity is the cosine of the angle.

[0143] In practical applications, the acquisition module 801, the first determination module 802, the second determination module 803, the third determination module 804, the advertisement push module 805, the first preprocessing module, and the second preprocessing module can be implemented using a processor in a cloud server. The processor can be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor.

[0144] Figure 9 This is a schematic diagram of the composition structure of an advertising push system according to an embodiment of this application, as shown below. Figure 9As shown, the advertising push system 900 includes: a cloud server 901, an advertising platform 902, and a terminal 903, wherein,

[0145] The cloud server 901 is used to receive advertising demand information sent by the advertising platform 902; the advertising demand information includes the user identifier and the ad slot identifier of the user to receive the pushed advertisement; determine the user profile from the first database based on the user identifier; determine the set of ad profiles to be pushed from the second database based on the ad slot identifier; determine the target ad profile to be pushed from the set of ad profiles based on the user profile; and send the target ad identifier corresponding to the target ad profile to the advertising platform 902.

[0146] The advertising platform 902 is used to receive the advertising demand information and send the advertising demand information to the cloud server 901; receive the target advertising identifier corresponding to the target advertising profile, determine the target advertising corresponding to the target advertising identifier, and push the target advertising to the terminal 903;

[0147] The terminal 903 is used to send the advertising demand information to the advertising platform 902 and receive the target advertisement.

[0148] The description of the cloud server embodiments above is similar to the description of the method embodiments of the first aspect above, and has similar beneficial effects as the method embodiments of the first aspect. For technical details not disclosed in the cloud server embodiments of this application, please refer to the description of the method embodiments of the first aspect of this application for understanding.

[0149] It should be noted that, in the embodiments of this application, if the above-mentioned advertising push method is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause the cloud server to execute all or part of the methods described in the first aspect of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0150] Correspondingly, embodiments of this application provide a cloud server. Figure 10 This is a schematic diagram of a hardware entity of a cloud server provided in an embodiment of this application, such as... Figure 10As shown, the hardware entity of the cloud server 1000 includes a memory 1001 and a processor 1002. The memory 1001 stores a computer program that can run on the processor 1002. When the processor 1002 executes the program, it implements the steps in the advertising push method of the first aspect provided in the above embodiments.

[0151] In practical applications, the aforementioned memory 1001 may be volatile memory, such as RAM; or non-volatile memory, such as ROM, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 1002.

[0152] The processor 1002 described above can be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor. Understandably, for different augmented reality cloud platforms, the electronic device used to implement the above processor functions can also be other types, and this application embodiment does not limit the specific type.

[0153] Correspondingly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the advertising push method of the first aspect provided in the above embodiments.

[0154] It should be noted that the descriptions of the storage media and cloud server embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage media and cloud server embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0155] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0156] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0157] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0158] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this application may all be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the integrated unit may be implemented in hardware or in a combination of hardware and software functional units.

[0159] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks. Alternatively, if the integrated units of this application are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the related technology, can be embodied in the form of software products. These computer software products are stored in a storage medium and include several instructions to cause computer devices (which may be mobile phones, tablets, desktops, personal digital assistants, navigators, digital phones, video phones, televisions, sensing devices, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0160] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined to obtain new method embodiments without conflict. The features disclosed in the several product embodiments provided in this application can be arbitrarily combined to obtain new product embodiments without conflict. The features disclosed in the several method or apparatus embodiments provided in this application can be arbitrarily combined to obtain new method embodiments or apparatus embodiments without conflict.

[0161] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An advertising push method, characterized in that, include: In response to the terminal's location information being within the coverage area of ​​the base station, the advertising demand information sent by the terminal is obtained; The advertising demand information includes the user identifier of the user who wants to receive the pushed advertisement and the advertisement slot identifier; A user profile is determined from the first database based on the user identifier; The user profile is a set of basic attributes of the user who enters the base station; The set of advertising profiles to be pushed is determined from the second database based on the advertising slot identifier; the set of advertising profiles is the set of basic attributes of the advertisements of the merchants included under the base station; The target advertising profile is determined from the advertising profile set based on the user profile; Advertisements are pushed based on the target advertising profile; Before determining the user profile from the first database based on the user identifier, the method further includes: Obtain multiple user profiles under the first dimension and multiple advertising profiles under the second dimension; the user profiles and advertising profiles under the same base station have the same dimension; Using the user identifier of each user profile in the plurality of user profiles as the primary key, each user profile is stored in the database to obtain the first database; Using the ad placement identifier of each ad image in the plurality of ad images as the primary key and the ad type of each ad image as the attribute tag, each ad image is stored in the database to obtain the second database.

2. The method according to claim 1, characterized in that, The step of pushing advertisements based on the target advertising profile includes: The target ad identifier corresponding to the target ad profile is sent to the advertising platform, so that the advertising platform can push the target ad to the terminal based on the target ad identifier; or... The target advertisement is obtained based on the target advertisement identifier corresponding to the target advertisement profile, and the target advertisement is pushed to the terminal.

3. The method according to claim 1 or 2, characterized in that, The step of determining the set of ad profiles to be pushed from the second database based on the ad slot identifier includes: The set of ad profiles to be pushed is determined from the second database based on the ad type corresponding to the ad slot identifier.

4. The method according to claim 1, characterized in that, The step of determining the set of ad profiles to be pushed from the second database based on the ad type corresponding to the ad slot identifier includes: If the ad slot is identified as the identifier of an application on the terminal used to display the ad to be pushed, the ad profile set to be pushed is determined from the second database according to the ad type corresponding to the application identifier. If the ad slot is identified as an ad type, the set of ad profiles to be pushed is determined from the second database based on the ad slot identifier.

5. The method according to claim 1 or 2, characterized in that, The step of determining the target ad profile to be pushed from the ad profile set based on the user profile includes: Determine the similarity between the user profile and each advertising profile in the advertising profile set; The target ad profile to be pushed is determined from the ad profile set based on the similarity.

6. The method according to claim 5, characterized in that, The similarity is the vector angle or the cosine of the angle. Determining the target ad profile to be pushed from the ad profile set based on the similarity includes: When the similarity is equal to the angle between the vectors, the ad profile corresponding to the minimum similarity is determined as the target ad profile to be pushed. When the similarity is equal to the cosine of the included angle, the ad profile corresponding to the maximum similarity is determined as the target ad profile to be pushed.

7. An advertising push device, characterized in that, include: The acquisition module is used to acquire advertising demand information sent by the terminal in response to the terminal's location information being within the coverage area of ​​the base station; The advertising demand information includes the identifier of the user to receive the advertising push and the identifier of the advertising slot; The first determining module is used to determine a user profile from the first database based on the user identifier; The user profile is a set of basic attributes of the user who enters the base station; The second determining module is used to determine the set of advertising profiles to be pushed from the second database based on the advertising slot identifier; The advertising profile set is the set of basic attributes of the advertisements of the merchants included under the base station; The third determining module is used to determine the target advertisement profile to be pushed from the advertisement profile set based on the user profile; The ad push module is used to push ads based on the target ad profile; The first preprocessing module is used to obtain multiple user profiles under the first dimension and multiple advertising profiles under the second dimension. User profiles and advertising profiles share the same dimensions under the same base station. Using the user identifier of each user profile in the plurality of user profiles as the primary key, each user profile is stored in the database to obtain a first database; using the ad slot identifier of each ad profile in the plurality of ad profiles as the primary key, and the ad type of each ad profile as the attribute tag, each ad profile is stored in the database to obtain a second database.

8. A cloud server, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the advertising push method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the advertising push method according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • Advertisement putting method, device and system

    CN101996371A

  • Method and device for improving the accuracy of advertisement delivery electronic device and storage medium

    CN109034864A