Advertisement obtaining method and device and medium

Abstract

The embodiment of the invention provides an advertisement obtaining method and device and a medium. If the object behavior of the target object changes at the first moment, the server side obtains dynamic data of the target object, obtains a to-be-updated portrait of the target object according to the dynamic data, and updates an initial portrait of the target object according to the to-be-updated portrait to obtain a better portrait, namely the target portrait. Wherein the dynamic data indicates data that the object data of the target object changes at the first moment, the initial portrait is a portrait determined based on historical object data of the target object, and the historical object data indicates the object data of the target object before the first moment. The to-be-put advertisement obtained based on the target portrait can accurately reflect the expectation of the target object. And on the basis, the to-be-delivered advertisement is delivered, so that the accuracy is higher, the expectation of the use object can be better met, and the use experience can be better improved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to an advertising acquisition method, apparatus and medium. Background Technology

[0002] Against the backdrop of commercial banks' digital transformation, bank mobile apps have become a primary business channel, necessitating advertising within these apps to improve user experience. However, current advertising methods rely on pre-processed user profiles. Specifically, ads are determined based on these profiles and then placed on the bank mobile app. However, this method lacks precision, meaning the ads don't meet the user's expectations, thus impacting the user experience. Summary of the Invention

[0003] This application provides an advertising acquisition method, apparatus, and medium to improve the accuracy of advertising delivery and enhance the user experience.

[0004] In a first aspect, embodiments of this application provide an advertisement acquisition method, applied on a server, the method comprising:

[0005] If the object behavior of the target object changes at the first moment, the dynamic data of the target object is obtained, and the dynamic data indicates the data in the object data of the target object that changed at the first moment.

[0006] Based on the dynamic data, obtain the target object's profile to be updated; based on the profile to be updated, update the target object's initial profile to obtain the target object's target profile; the initial profile is a profile determined based on the target object's historical object data, and the historical object data indicates the target object's object data before the first moment.

[0007] Based on the target profile, obtain the advertisements to be delivered.

[0008] Optionally, the method further includes:

[0009] Determine the data processing timestamp of the portrait to be updated;

[0010] Based on the image to be updated, update the initial image of the target object, including:

[0011] If the data processing timestamp of the image to be updated is later than the data processing timestamp of the initial image, the initial image of the target object is updated according to the image to be updated.

[0012] Optionally, the method further includes:

[0013] If the data processing timestamp of the image to be updated is not later than the data processing timestamp of the initial image, the initial image of the target object shall be used as the target image of the target object.

[0014] Optionally, determining the advertisement to be delivered based on the target profile includes:

[0015] Based on the target profile and the advertising placement rules of the target profile, the advertisement to be placed is determined; the advertising placement rules of the target object indicate the rules for determining the advertisement to be placed on the target object.

[0016] Optionally, the advertising delivery rules for the target audience include one or more of the following:

[0017] Target audience, ad placement, ad time, display, cache duration, default ad, and ad priority.

[0018] Optionally, determining the advertisement to be delivered based on the target profile and the advertising delivery rules for the target profile includes:

[0019] Based on the target profile, the target ad node is determined from the ad recommendation cluster;

[0020] The advertising recommendation cluster includes multiple advertising nodes, including the target advertising node; the multiple advertising nodes include multiple advertisements and the advertising delivery rules for each of the multiple advertisements;

[0021] Ads that match the same ad delivery rules as the target profile are selected from the target ad nodes and used as the ads to be delivered.

[0022] Optionally, the method further includes:

[0023] Output the advertisement to be delivered to display the advertisement on the target client; the target client refers to the client that is connected to the server and is used by the target object.

[0024] Optionally, the method further includes:

[0025] Obtain the evaluation information of the advertisement to be delivered sent by the target client;

[0026] Based on the evaluation information, the advertising placement rules for the target audience are adjusted.

[0027] Secondly, embodiments of this application provide an advertisement acquisition device, applied on a server side, the device comprising:

[0028] The real-time acquisition unit is used to acquire dynamic data of the target object if the object behavior of the target object changes at a first moment, wherein the dynamic data indicates the data in the object data of the target object that has changed at the first moment.

[0029] The update unit obtains the target object's profile to be updated based on the dynamic data; updates the target object's initial profile based on the profile to be updated to obtain the target object's target profile; the initial profile is a profile determined based on the target object's historical object data, and the historical object data indicates the target object's object data before the first moment.

[0030] The advertisement acquisition unit is used to acquire advertisements to be delivered based on the target profile.

[0031] Thirdly, embodiments of this application provide a computer program product, the computer program product comprising: a computer program (also referred to as code or instructions), which, when the computer program is run, causes the computer to perform the method in any of the possible implementations of any of the above aspects.

[0032] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program (also referred to as code or instructions) that, when run on a computer, causes the computer to perform the method in any of the possible implementations of any of the above aspects.

[0033] Fifthly, embodiments of this application provide a chip system including one or more processors for calling and executing instructions stored in memory, causing the methods in any of the above aspects or possible implementations to be executed. The chip system may be composed of chips or may include chips and other discrete devices.

[0034] This application provides an advertising acquisition method, apparatus, and medium. When executing the method, the server performs the following operations: if the object behavior of a target object changes at a first moment, it acquires dynamic data of the target object; based on the dynamic data, it acquires a target object's profile to be updated; and based on the profile to be updated, it updates the target object's initial profile to obtain a better profile, i.e., the target profile. Here, dynamic data indicates the data of the target object that changes at the first moment, and the initial profile is a profile determined based on the target object's historical object data. Historical object data indicates the target object's object data before the first moment. The first moment is the current moment; that is, this application utilizes real-time changing object data to adjust the previously acquired initial profile. The target profile obtained in this way can accurately depict the target object's object needs. In other words, the advertisement to be delivered based on this target profile can accurately reflect the target object's expectations. Based on this, the advertisement to be delivered is more accurate, better meets the user's expectations, and helps improve the user experience. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a schematic diagram of the structure of an advertising delivery system provided in an embodiment of this application;

[0037] Figure 2 A flowchart of an advertising acquisition method provided in this application embodiment;

[0038] Figure 3 A flowchart of an advertising acquisition method provided in this application embodiment;

[0039] Figure 4 This application provides a schematic diagram of the structure of an advertising acquisition device. Detailed Implementation

[0040] To enable those skilled in the art to better understand the present application, the technical solutions in this embodiment will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0041] As mentioned earlier, relying on pre-processed user profiles and determining the advertising method to be delivered to the bank's client based on these user profiles results in poor advertising accuracy and fails to meet the user's expectations.

[0042] In view of this, this application provides an advertising acquisition method. Specifically, if the object behavior of a target object changes at a first moment, dynamic data of the target object is acquired. Based on the dynamic data, a target object profile to be updated is acquired. Based on the target object profile to be updated, the initial profile of the target object is updated to obtain a profile that better matches the current state of the target object, i.e., the target profile. Here, dynamic data indicates the data where the target object's object data changes at the first moment, and the initial profile is a profile determined based on the target object's historical object data. Historical object data indicates the target object's object data before the first moment. The first moment is the current moment, meaning that this application uses real-time changing dynamic data to adjust the initial profile constructed from previously acquired object data. This method can acquire a target profile that accurately depicts the target object's needs. Therefore, the advertisement to be delivered based on this target profile can accurately reflect the target object's expectations. Based on this, the advertisement to be delivered is more accurate, better meets the user's expectations, and improves the user experience.

[0043] The advertising acquisition method provided in this application embodiment will be described in detail below with reference to the accompanying drawings. It should be noted that the user information or user data involved in this application embodiment are all data obtained through legal and compliant means.

[0044] First, we will introduce the application scenarios of the advertising acquisition method provided in the embodiments of this application.

[0045] For example, Appendix Figure 1 This is a schematic diagram of an advertising delivery system provided in an embodiment of this application. The advertising delivery system includes a client 101 and a server 102. The client 101 and the server 102 are communicatively connected.

[0046] Client 101 is customer-facing and used for interaction with users. Client 10 includes various types, such as electronic devices with display functions, such as laptops, mobile phones, tablets, and smart wearable devices.

[0047] In this embodiment, client 101 is deployed with a banking application. Users can perform banking transactions through this application, such as transferring funds, taking out loans, and managing wealth. After a user triggers a relevant operation in the banking application, the client sends a request to server 102, which then sends advertisements to be displayed to client 101. For example, after logging into the application, users are directly shown advertisements such as loan advertisements and wealth management advertisements.

[0048] Based on the request sent by the client 101, the server 102 obtains the corresponding advertisement to be displayed for the user and sends the advertisement to the client 101 for display.

[0049] In this embodiment, the server 102 is configured to: if the object behavior of the target object changes at a first moment, acquire the dynamic data of the target object, acquire the target object's profile to be updated based on the dynamic data, and update the target object's initial profile based on the profile to be updated, so as to obtain a profile that better reflects the current state of the target object, i.e., the target profile. Here, the dynamic data indicates the data on the target object's object data that has changed at the first moment, and the initial profile is a profile determined based on the target object's historical object data, which indicates the target object's object data before the first moment.

[0050] The server 102 can take various forms, such as a server or a server cluster. A server cluster includes multiple server nodes. Furthermore, the server 102 can also be other types of computing devices; this embodiment does not specifically limit its use.

[0051] It should be noted that the client 101 provided in this application embodiment may include multiple clients. Figure 1 n are shown, where n is an integer greater than or equal to 2.

[0052] It should be noted that the above embodiments are only illustrative and can be adjusted as needed in actual use. The embodiments in this application are not specifically limited.

[0053] The following description, in conjunction with the accompanying drawings, introduces the advertising acquisition method provided in the embodiments of this application.

[0054] Appendix Figure 2 This is a flowchart illustrating an advertising acquisition method provided in an embodiment of this application. Figure 2 As shown, the method includes the following:

[0055] S210. If the object behavior of the target object changes at the first moment, the server 102 obtains the dynamic data of the target object, and the dynamic data indicates the data in the object data of the target object that changed at the first moment.

[0056] The first moment refers to the current moment.

[0057] In this embodiment, the target object refers to an object whose object information can be obtained and identified by the server 102. For example, the target object refers to a customer who uses a banking application to perform banking transactions.

[0058] Object data reflects the behavioral information of the target object, including but not limited to: the target object's account information, transaction records, credit score, login frequency, location information, and usage preferences. In this embodiment, the target object's object data can be used to construct a profile of the target object, and based on this profile, advertisements can be determined for delivery to the target object.

[0059] In this embodiment of the application, if the object behavior of the target object changes, the server 102 obtains the dynamic data of the target object, that is, obtains the object data of the target object that has changed at the first moment, so as to adjust the portrait of the target object that has been obtained in real time according to the dynamic data, thereby improving the portrait accuracy of the target object.

[0060] For example, if at the current time T1, the target object logs into the banking application 3 times a day, while at times before the current time T1, the target object logs into the banking application once every 3 days, then the dynamic data is the target object's login frequency.

[0061] In one specific implementation, the server 102 can identify dynamic data (also known as real-time change data) generated by changes in the object behavior of the target object by scanning the client 101 through a tool, based on the data compilation concept and the preset processing criteria of the customer profile.

[0062] In another specific implementation, client 101 sets up a monitoring mechanism. When a change in the behavior of the target object is detected, dynamic data is sent to server 102 and cached in a distributed message queue. Server 102 then loads the dynamic data from the distributed message queue.

[0063] S220. Based on the dynamic data, obtain the image of the target object to be updated.

[0064] Server 102 can obtain the target object's profile to be updated based on dynamic data. The profile to be updated is used to reflect the latest changes of the target object. For example, if the dynamic data is that the target user logs into the banking application once every 3 days, and then logs into the banking application 3 times on the 1st, then the target object's profile to be updated is "active user".

[0065] The dynamic data is large in volume. To improve data processing speed, in this embodiment, the server 102 includes a real-time processing cluster, which is used to obtain the corresponding profile to be updated based on the dynamic data. The real-time processing cluster includes multiple nodes. The server 102 distributes the dynamic data processing evenly to each node. Each node processes its assigned dynamic data to ultimately obtain the profile to be updated.

[0066] Furthermore, dynamic data processing can be evenly distributed across each node based on timestamps and random numbers. A timestamp refers to the time a node processes data. Distributing data using timestamps helps determine the timeliness of records and whether user profiles need updating. Distributing data using random numbers enables load balancing, ensuring the data processing load is evenly distributed across nodes and preventing some nodes from being overloaded while others remain idle.

[0067] In addition, to improve processing timeliness, the real-time processing cluster can be horizontally expanded based on random numbers.

[0068] In this embodiment, the rolling timestamps of the two nodes are in the second range. That is, by setting the rolling timestamps within the second range, real-time processing operations at the micro-batch level can be achieved.

[0069] The results processed at each node can be converted into standardized customer profiles according to the preset format requirements of data weaving. This means they are integrated into a standardized customer profile to obtain the profile to be updated.

[0070] For example, the profile to be updated includes at least two fields: customer code and data processing timestamp, to identify the ownership and timeliness of each profile. For example, the profile to be updated is {"Customer Code":"C001","Data Processing Timestamp":"2023-03-22 14:30:15","Interest Level in Financial Products":"High"}.

[0071] Furthermore, after obtaining the profile to be updated, server 102 writes the profile to be updated into the profile database. The profile database stores profiles of at least one customer, including the target object.

[0072] In one example, before writing the image to be updated into the image database, the relationship between the data processing timestamp of the image to be updated (referred to as the first timestamp) and the data processing timestamp of the target object's image stored in the image database (referred to as the second timestamp) is first determined. If the first timestamp is not later than the second timestamp, it is indicated that processing should be repeated and the image to be updated should be discarded. If the first timestamp is later than the second timestamp, the image to be updated is stored, and the corresponding image content in the image database is deleted simultaneously. That is, the existing image of the target object is updated using the image to be updated to obtain the latest target image that reflects the target object.

[0073] It should be noted that, in this embodiment of the application, the portrait stored in the portrait database includes at least the customer code and the data processing timestamp.

[0074] S230. Update the initial image of the target object according to the image to be updated, so as to obtain the target image of the target object; the initial image is a image determined based on the historical object data of the target object, and the historical object data indicates the object data of the target object before the first moment.

[0075] The initial profile is the profile of the target object acquired before the first moment. For ease of explanation, the object data of the target object acquired before the first moment is referred to as historical object data, and the initial profile is a profile determined based on the historical object data.

[0076] However, considering that object data changes in real time, the initial portrait may not accurately reflect the portrait information of the target object. In this embodiment of the application, the initial portrait of the target object is updated using the portrait to be updated, thereby obtaining the target portrait.

[0077] For example, if the initial profile of the target object is {user basic information, historical transaction records, recent login time, browsing preferences, data processing timestamp A}, and the profile to be updated is {fund product interest level: high, data processing timestamp B}, if A is later than B, the initial profile is updated using the profile to be updated, and the resulting target profile is {user basic information, historical transaction records, recent login time, browsing preferences, fund product interest level: high, data processing timestamp B}.

[0078] It should be noted that the above embodiments are incremental updates, that is, inserting non-existent images to be updated into the initial images. In actual use, the original image content can also be replaced as needed. This application embodiment is not specifically limited.

[0079] In one example, the data processing timestamps of the image to be updated and the initial image are determined. If the data processing timestamp of the image to be updated is later than that of the initial image, the initial image is adjusted using the image to be updated to obtain the target image of the target object. If the data processing timestamp of the image to be updated is not later than that of the initial image, the initial image is used as the target image.

[0080] In this embodiment, server 102 uses a parallel approach to periodically acquire profiles of the target objects, referred to as static profiles. For example, server 102 can determine off-peak business periods and perform the following operations during these periods: acquire batches (e.g., billions of data points), including historical object data of the target objects; and determine static profiles of the objects based on the batch customer data, including the static profiles of the target objects. This batch processing of object data ensures that as much historical object data as possible is fully considered, and even if omissions or anomalies occur during real-time data processing, a complete and comprehensive profile of the target objects can be constructed.

[0081] Furthermore, to improve processing efficiency, server 102 also includes a batch cluster, which consists of multiple nodes distributed across different regions. Server 102 divides customer data into multiple files according to region and sends them to the multiple nodes for processing to obtain a static profile of the target object.

[0082] It should be noted that the obtained static profile and the profile to be updated are in the same format, both including at least a data processing timestamp and a customer code.

[0083] In this embodiment, the obtained static image of the target object can be written into the image database. Specifically, if the processing timestamp of the obtained static image is later than the timestamp of the target object's image in the image database, the static image is used to update the target object's image in the image database. Otherwise, the target object's image is not updated.

[0084] Similarly, to ensure processing efficiency, batch clusters can be expanded horizontally according to the processing location.

[0085] S240. Obtain the advertisement to be delivered based on the target profile.

[0086] Server 102 obtains the ads to be delivered based on the target profile.

[0087] The server 102 can obtain the advertisement to be delivered based on the stored advertisements and the target profile, or it can obtain advertisements from other devices and then obtain the advertisement to be delivered based on the target profile. This application embodiment is not specifically limited.

[0088] In this embodiment of the application, the server 102 can obtain the advertisement to be placed based on the target profile and the advertising placement rules of the target profile.

[0089] The advertising placement rules, developed by experts, determine which ads are delivered to the target audience. These rules include, but are not limited to: target audience, ad placement, timing, display, cache duration, default ad, and ad priority. Furthermore, the rules allow for audience targeting based on different dimensions such as whitelists, geographic region, and device type. For example, a possible rule is: For customers in a region who have been inactive for three months, upon their first login to the mobile banking app, a coupon-type ad in the form of a carousel will be displayed in the center of the homepage.

[0090] In this embodiment, experts can formulate advertising placement rules for target profiles on the visual interface of client 101 and verify the effectiveness of the rules using simulated transactions. The advertising placement rules are then sent to server 102.

[0091] In one specific implementation, server 102 includes an advertising recommendation cluster, which includes multiple advertising nodes. Each advertising node includes multiple advertisements and their attribute information.

[0092] Server 102 selects suitable ad nodes from the ad recommendation cluster based on the target profile to perform ad matching and obtain ads to be delivered. The ad attribute information indicates the ad delivery rules. These rules are the same as those described above and will not be repeated here.

[0093] In another specific implementation, client 101 maintains a long-lived connection with ad nodes in the ad recommendation cluster, and server 102 maintains a mapping relationship between client codes and long-lived connections. For example, server 102 maintains a mapping relationship between client code A1 and long-lived connection A1, a mapping relationship between client code Ai and long-lived connection Ai, and so on. Long-lived connection A1 indicates that client 101 is connected to ad node A1, long-lived connection A2 indicates that client 101 is connected to ad node A2, and so on. Here, i is a positive integer. Therefore, when server 101 obtains the target profile, it can determine the long-lived connection mapped to that client code based on the client code field of the target profile, thereby locating the ad node. Then, at that ad node, the ad to be delivered is determined based on the ad delivery rules.

[0094] In this embodiment, the server 102 is further configured to receive new advertising delivery rules via a distributed message queue and distribute the received rules to each advertising node. Each node polls its long-lived connection with the client side, determines conditions such as customer groups in the rules, and decides whether to synchronize the advertising delivery rules to the client side. Specifically, the target profile is determined. If the target profile matches the new rule, the server 102 initiates synchronization with the client 101; otherwise, synchronization is not initiated.

[0095] Furthermore, in this embodiment, the client 101 pre-installs default advertisements, establishes a long connection with the server 102 upon startup, and monitors the status. When a new advertising rule is received, the new advertising delivery rule is cached, and advertisements are displayed to the client as needed.

[0096] In summary, the advertising acquisition method of this application embodiment involves acquiring dynamic data of the target object if its behavior changes at a first moment. Based on this dynamic data, a profile of the target object to be updated is obtained. Then, the initial profile of the target object is updated based on this profile to achieve a better profile, i.e., the target profile. Here, dynamic data indicates the data of the target object that changes at the first moment, and the initial profile is a profile determined based on the target object's historical data. Historical data indicates the target object's data before the first moment. The first moment refers to the current moment. This application embodiment utilizes real-time changing dynamic data to adjust the initial profile constructed from previously acquired object data. This method allows for the acquisition of a target profile that accurately depicts the target object's needs. Therefore, the advertisement to be delivered based on this target profile can accurately reflect the target object's expectations. On this basis, delivering this advertisement is more accurate, better meets the user's expectations, and improves the user experience.

[0097] The above describes only one method for obtaining advertisements. The following section will describe in detail the method for obtaining advertisements provided in the embodiments of this application, with specific implementation details.

[0098] Appendix Figure 3 A flowchart of an advertisement acquisition method provided in this application embodiment is included, the method comprising the following:

[0099] S310 and server 102 use a real-time processing framework to process real-time customer behavior data streams based on the data weaving concept, in order to generate real-time customer profiles.

[0100] Specifically, server 102 continuously acquires real-time data streams from a real-time processing cluster using a real-time processing framework. This cluster is formed by caching customer activity data through a distributed message queue. The real-time data stream covers all immediate customer actions on the bank's client, such as login frequency or product browsing activity. By evenly distributing real-time data across processing nodes and performing micro-batch operations using second-level time windows, server 102 can quickly generate standardized customer profile data. When updating the database, the system checks the data's timestamp. If the real-time processed data is updated, the customer profile is updated accordingly; otherwise, it is considered duplicate data and discarded. Simultaneously, the corresponding values ​​in the distributed cache are cleared to maintain data freshness.

[0101] S320 and server 102 use a batch processing framework to process historical customer data and build complete customer profiles.

[0102] Server 102 utilizes a data platform system to extract data from source systems in batches during off-peak hours, creating files and importing them into an MPP-architected database for processing. This batch data is used to build initial customer profiles, serving as the foundation for real-time profiling. Parallel processing of large amounts of data by region improves processing efficiency. The initial batch processing lays the groundwork, while subsequent batch processing corrects for deficiencies in real-time data, ensuring the comprehensiveness and accuracy of customer profiles.

[0103] It should be noted that S310 and S320 are parallel processing procedures, and the two steps do not affect each other.

[0104] S330 and server 102 merge real-time profiles with batch profiles to update customer profiles in the target database.

[0105] By integrating real-time and batch-processed profile data, the server 102 updates the existing customer profiles in the target database to form a complete profile that integrates historical behavior and real-time changes. This step ensures the timeliness and accuracy of the customer profile.

[0106] S340 and server 102 receive and process the advertising placement rules.

[0107] Operators define advertising rules on the client's visual interface, such as displaying coupon ads to inactive customers in a specific region upon their first login. These rules are then transmitted in real-time to server 102 via a distributed message queue. The server preprocesses these rules in preparation for personalized ad recommendations.

[0108] S350 and server 102 preprocess advertising rules based on customer profiles and prepare to push personalized ads to the client.

[0109] The client and server maintain synchronization via a persistent connection. Server 102 determines whether the ad recommendation list needs to be updated based on the client's group criteria. If the client meets the new rules, server 102 pushes the latest personalized ad list to the client, which then caches these ads to display to the user at the appropriate time, while simultaneously collecting user feedback data.

[0110] S360 and server 102 retrieve ads to be delivered from the ad recommendation cluster based on customer profiles and ad delivery rules.

[0111] A dedicated channel between the server (102) and the client ensures a continuous, long-term connection, facilitating real-time synchronization of ad recommendation rules. The server analyzes real-time customer profiles and pre-processed ad rules to select ads matching the customer profiles from the ad recommendation cluster, forming a list of ads to be delivered.

[0112] S370: The client receives and displays the advertisements to be placed.

[0113] After receiving the advertisement to be delivered from the server, the client selects an appropriate time and location to display the advertisement based on the advertising rules and the current context to achieve the best marketing results.

[0114] S380 and server 102 collect customer feedback and adjust advertising rules based on the feedback.

[0115] Server 102 is responsible for evaluating the effectiveness of ad campaigns. By collecting customer response data on the client side (such as click-through rate and conversion rate), also known as evaluation information, Server 102 can analyze the performance of ad campaign rules. For rules that are not performing well, it can adjust and optimize strategies in a timely manner to ensure that ad campaigns always align with customer needs and improve the accuracy and efficiency of marketing.

[0116] Specifically, server 102 polls customer groups for specific advertising rules, queries the advertising results for each hit customer, establishes an evaluation mechanism based on the results, and uses a funnel model to conduct multi-level conversion rate analysis of the advertising to judge the overall advertising effect. If the effect does not meet the target, the advertising rules can be optimized in a targeted manner.

[0117] Therefore, this application's embodiments employ a processing method combining real-time and batch processing frameworks, enabling customer profile processing to be completed within seconds, thus improving the real-time nature and accuracy of ad placement. The use of edge-cloud collaboration technology reduces data transmission and lowers ad placement time. Furthermore, through an evaluation loop, the effectiveness of ad placement is intuitively obtained during the ad placement process, allowing for timely responses to business marketing needs and supporting adjustments to ad placement rules at any time.

[0118] In addition, this application also provides an advertising acquisition device.

[0119] Appendix Figure 4 This application provides a schematic diagram of the structure of an advertisement acquisition device. For example... Figure 4 As shown, the device 400 includes:

[0120] Real-time acquisition unit 401 is used to acquire dynamic data of the target object if the object behavior of the target object changes at the first moment, wherein the dynamic data indicates the data in the object data of the target object that has changed at the first moment.

[0121] The update unit 402 obtains the target object's portrait to be updated based on the dynamic data; updates the target object's initial portrait based on the portrait to be updated to obtain the target object's target portrait; the initial portrait is a portrait determined based on the target object's historical object data, and the historical object data indicates the target object's object data before the first moment.

[0122] The advertisement acquisition unit 403 is used to acquire advertisements to be delivered based on the target profile.

[0123] Optionally, update unit 401 is specifically used for:

[0124] Determine the data processing timestamp of the portrait to be updated;

[0125] If the data processing timestamp of the image to be updated is later than the data processing timestamp of the initial image, the initial image of the target object is updated according to the image to be updated.

[0126] Optionally, the update unit 401 is further configured to: if the data processing timestamp of the image to be updated is not later than the data processing timestamp corresponding to the initial image, use the initial image of the target object as the target image of the target object.

[0127] The advertising acquisition unit 403 is specifically used for: acquiring the advertisement to be delivered based on the target profile and the advertising delivery rules of the target profile; the advertising delivery rules of the target object indicate the rules for determining the advertisement to be delivered to the target object.

[0128] Optionally, the advertising delivery rules for the target audience include one or more of the following: target audience, ad placement, delivery time, display, cache duration, default ad, and ad delivery priority.

[0129] Optionally, obtaining the advertisement to be delivered based on the target profile and the advertising delivery rules of the target profile includes:

[0130] Based on the target profile, a target ad node is determined from the ad recommendation cluster; wherein, the ad recommendation cluster includes multiple ad nodes, and the multiple ad nodes include the target ad node; the multiple ad nodes include multiple ads and the ad delivery rules for each of the multiple ads; ads that have the same ad delivery rules as the target profile are matched from the target ad node as the ads to be delivered.

[0131] Optionally, the device 400 further includes an output unit, which is configured to: output the advertisement to be delivered to display the advertisement on a target client; the target client is a client that is communicatively connected to the server and is used by the target object;

[0132] Optionally, the device 400 further includes an evaluation feedback unit, which is used to: obtain evaluation information of the advertisement to be delivered sent by the target client; and adjust the advertising delivery rules of the target object based on the evaluation information.

[0133] In summary, the advertising acquisition device of this application utilizes real-time dynamic data to adjust the initial profile constructed from previously acquired object data. This method enables the acquisition of a target profile that accurately depicts the target object's needs. Therefore, the advertisements to be delivered based on this target profile can accurately reflect the target object's expectations. Furthermore, delivering these advertisements with greater accuracy and better alignment with the user's expectations enhances the user experience.

[0134] According to the method provided in the embodiments of this application, this application also provides a chip system, which includes one or more processors for calling and executing instructions stored in memory, thereby causing the method described in the embodiments of this application to be executed. The chip system may be composed of chips or may include chips and other discrete devices.

[0135] The chip system may include input circuits or interfaces for transmitting information or data, and output circuits or interfaces for receiving information or data.

[0136] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute the various steps or processes executed by the network device or terminal device in any of the foregoing method embodiments.

[0137] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code, which, when run on a computer, causes the computer to execute the various steps or processes executed by the network device or terminal device in any of the foregoing method embodiments.

[0138] The computer-readable storage medium may be the aforementioned volatile memory or non-volatile memory, or it may include both volatile memory and non-volatile memory.

[0139] In the embodiments of this application, the terms and English abbreviations are exemplary examples given for ease of description and should not be construed as limiting the application in any way. This application does not preclude the possibility of defining other terms that can achieve the same or similar functions in existing or future agreements.

[0140] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

Claims

1. A method for acquiring advertisements, characterized in that, Applied to the server side, the method includes: If the object behavior of the target object changes at the first moment, the dynamic data of the target object is obtained, and the dynamic data indicates the data in the object data of the target object that changed at the first moment. Based on the dynamic data, obtain the target object's profile to be updated; based on the profile to be updated, update the target object's initial profile to obtain the target object's target profile; the initial profile is a profile determined based on the target object's historical object data, and the historical object data indicates the target object's object data before the first moment. Based on the target profile, obtain the advertisements to be delivered.

2. The acquisition method according to claim 1, characterized in that, The method further includes: Determine the data processing timestamp of the portrait to be updated; Based on the image to be updated, update the initial image of the target object, including: If the data processing timestamp of the image to be updated is later than the data processing timestamp of the initial image, the initial image of the target object is updated according to the image to be updated.

3. The acquisition method according to claim 2, characterized in that, The method further includes: If the data processing timestamp of the image to be updated is not later than the data processing timestamp of the initial image, the initial image of the target object shall be used as the target image of the target object.

4. The acquisition method according to claim 1, characterized in that, The step of obtaining the advertisement to be delivered based on the target profile includes: Based on the target profile and the advertising placement rules of the target profile, the advertisement to be placed is obtained; the advertising placement rules of the target object indicate the rules for determining the advertisement to be placed on the target object.

5. The acquisition method according to claim 4, characterized in that, The advertising delivery rules for the target audience include one or more of the following: Target audience, ad placement, ad time, display, cache duration, default ad, and ad priority.

6. The acquisition method according to claim 4, characterized in that, The step of obtaining the advertisement to be delivered based on the target profile and the advertising delivery rules of the target profile includes: Based on the target profile, the target ad node is determined from the ad recommendation cluster; The advertising recommendation cluster includes multiple advertising nodes, including the target advertising node; the multiple advertising nodes include multiple advertisements and the advertising delivery rules for each of the multiple advertisements; Ads that match the same ad delivery rules as the target profile are selected from the target ad nodes and used as the ads to be delivered.

7. The acquisition method according to claim 4, characterized in that, The method further includes: Output the advertisement to be delivered to display the advertisement on the target client; the target client refers to the client that is connected to the server and is used by the target object.

8. The acquisition method according to claim 7, characterized in that, The method further includes: Obtain the evaluation information of the advertisement to be delivered sent by the target client; Based on the evaluation information, the advertising placement rules for the target audience are adjusted.

9. An advertising acquisition device, characterized in that, Applied to the server side, the device includes: The real-time acquisition unit is used to acquire dynamic data of the target object if the object behavior of the target object changes at a first moment, wherein the dynamic data indicates the data in the object data of the target object that has changed at the first moment. The update unit obtains the target object's profile to be updated based on the dynamic data; updates the target object's initial profile based on the profile to be updated to obtain the target object's target profile; the initial profile is a profile determined based on the target object's historical object data, and the historical object data indicates the target object's object data before the first moment. The advertisement acquisition unit is used to acquire advertisements to be delivered based on the target profile.

10. A computer program product, characterized in that, The computer program product includes: a computer program that, when run, causes a computer to perform the advertising acquisition method as described in any one of claims 1-8.

Images