Advertisement putting method and device based on user behaviors, equipment and medium

Abstract

The invention relates to an advertisement putting method and device based on user behaviors, equipment and a storage medium, and the method comprises the steps: collecting historical behavior data and user information data of each user in a preset user group, and inputting the historical behavior data and the user information data into a pre-trained advertisement preference prediction model, the method comprises the steps of identifying an advertisement preference type of each user, grouping the users of a preset user group based on the advertisement preference types to obtain at least one user group, calculating the click probability of each user on a to-be-delivered advertisement, and adjusting the advertisement delivery frequency of each user in each user group according to the click probability. According to the method and the device, the advertisement disturbance to sensitive users can be reduced, the advertisement exposure rate of users with high advertisement acceptance is improved, and the advertisement can touch the users with real demands, so that the advertisement putting efficiency is improved, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for delivering advertisements based on user behavior. Background Art

[0002] At present, with the popularity of the Internet and mobile devices, digital advertising has become one of the main marketing tools for enterprises. Some behaviors of users on the Internet can be recorded and used to optimize advertising strategies. However, traditional advertising delivery systems usually use fixed frequencies or simple rules to deliver advertisements. These advertising delivery methods do not fully consider the complexity and dynamic changes of user behavior, making advertising delivery excessively disturbing to users or failing to reach users who really have needs, resulting in low advertising delivery efficiency.

[0003] Therefore, how to improve the efficiency of advertising delivery has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0004] In view of the above, the present application provides a method, device, equipment and storage medium for advertising based on user behavior, which aims to solve the above technical problems.

[0005] In a first aspect, the present application provides an advertisement delivery method based on user behavior, the method comprising:

[0006] Collect historical behavior data and user information data of each user in the preset user group;

[0007] Inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user;

[0008] Grouping users of the preset user group based on the advertisement preference type to obtain at least one user group;

[0009] The click probability of each user on the advertisement to be delivered is calculated, and the advertisement delivery frequency of each user in each user group is adjusted according to the click probability.

[0010] In a second aspect, the present application provides an advertising delivery device based on user behavior, the device comprising:

[0011] Collection module: used to collect historical behavior data and user information data of each user in the preset user group;

[0012] Identification module: used for inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user;

[0013] A grouping module: used for grouping users of the preset user group based on the advertisement preference type to obtain at least one user group;

[0014] Delivery module: used to calculate the click probability of each user on the advertisement to be delivered, and adjust the advertisement delivery frequency of each user in each user group according to the click probability.

[0015] In a third aspect, the present application provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0016] Memory, used to store computer programs;

[0017] The processor is used to implement the user behavior-based advertising delivery method described in any one of the embodiments of the first aspect when executing the program stored in the memory.

[0018] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for delivering advertisements based on user behavior as described in any one of the embodiments of the first aspect is implemented.

[0019] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0020] The present application collects historical behavior data and user information data of each user in a preset user group, inputs the historical behavior data and user information data into a pre-trained advertising preference prediction model, identifies the advertising preference type of each user, groups the users of the preset user group based on the advertising preference type to obtain at least one user group, calculates the click probability of each user on the advertisement to be delivered, and adjusts the advertisement delivery frequency of each user in each user group according to the click probability, which can reduce the advertisement interruption to sensitive users and increase the advertisement exposure rate of users with high acceptance of advertisements, so that the advertisements can reach users who really have needs, thereby improving the efficiency of advertisement delivery and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0023] Figure 1 This is a flow chart of an embodiment of an advertisement delivery method based on user behavior of the present application;

[0024] Figure 2 This is a module diagram of an embodiment of an advertisement delivery device based on user behavior of the present application;

[0025] Figure 3 A schematic diagram of an electronic device embodiment of the present application;

[0026] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0028] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0029] This application provides an advertising method based on user behavior. Figure 1 , which is a method flow diagram of an embodiment of the method for placing advertisements based on user behavior of the present application. The method can be executed by an electronic device, and the electronic device can be implemented by software and / or hardware. The method for placing advertisements based on user behavior includes:

[0030] Step S10: Collect historical behavior data and user information data of each user in the preset user group;

[0031] Step S20: inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user;

[0032] Step S30: grouping users of the preset user group based on the advertisement preference type to obtain at least one user group;

[0033] Step S40: Calculate the click probability of each user for the advertisement to be delivered, and adjust the advertisement delivery frequency of each user in each user group according to the click probability.

[0034] In this embodiment, the preset user group may refer to a registered user group of e-commerce software, information software, or video software, and each user in the preset user group may receive advertising push messages. The historical behavior data of each user in the preset user group may be collected in real time through Web crawler technology, server logs, client tracking tools, etc., and the collected data may be stored in a database for subsequent analysis. The user's historical behavior data may refer to behavior data within a preset number of days from the current time. Specifically, the above-mentioned "step of collecting historical behavior data and user information data of each user in the preset user group" specifically includes:

[0035] Collect the historical browsing records, ad click records, purchase records, and the length of time the user stays on the page for each user in the preset user group.

[0036] The browsing history can be the browsing history of a web page, and can also collect the user's collection behavior and like behavior on the web page. The user's ad click record represents the user's interest in the ad, and the user's purchase record represents the user's past shopping behavior, which can reflect the user's preferences and interests. The length of time the user stays on the page can reflect his or her interest in the page. User information includes the user's basic information, such as the user's gender, the user's age, the city where the user is located, etc. Users of different age groups are usually interested in different products or services, and users in different cities may have different consumption habits. By collecting the user's historical behavior data and user information data, it is helpful to infer the user's potential needs.

[0037] By inputting the collected historical behavior data and user information data into the pre-trained advertising preference prediction model, each user's advertising preference type can be identified. Advertising preference types include preference types for products, such as electronic products, clothing, food, and daily necessities. They also include preference types for services, such as travel, entertainment, fitness, and education and training.

[0038] The training steps of the advertising preference prediction model include:

[0039] Obtain sample behavior data and sample user information of a preset number of sample users, label each sample user with a label of its real advertising preference type, use the sample behavior data and sample user information of each sample user as independent variables, and use the real advertising preference type of each sample user as a dependent variable to generate a sample set;

[0040] Input each independent variable in the sample set into the convolutional neural network model to obtain the predicted preference type of each sample user, read the actual advertising preference type of each sample user in the sample set, and determine the structural parameters of the advertising preference prediction model by minimizing the loss value between the predicted preference type and the actual advertising preference type to obtain a trained advertising preference prediction model.

[0041] Specifically, the above step of “inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user” specifically includes:

[0042] Encoding the historical behavior data and the user information data to obtain historical behavior feature data and user information feature data;

[0043] Splicing the historical behavior feature data and the user information feature data to obtain spliced ​​data;

[0044] The spliced ​​data is input into an advertisement preference prediction model to identify the advertisement preference type of each user.

[0045] The historical behavior data and user information data of each user in the preset user group can be converted into a binary vector by using the unique hot encoding method, thereby obtaining the historical behavior feature data and the user information feature data. The historical behavior feature data and the user information feature data are spliced ​​to obtain the spliced ​​data. The splicing and combining of different types of feature data can enhance the expressiveness of the features. The spliced ​​data is input into the advertising preference prediction model to identify the advertising preference type of each user. Since the user's historical behavior data and user information data reflect the user's interest in different products or services to varying degrees, the accuracy of the advertising preference prediction model can be improved by predicting the historical behavior data and user information data.

[0046] Then, the users of the preset user group are grouped according to the advertisement preference type to obtain at least one user group. For example, the users are grouped by a clustering algorithm so that each user group has the same or similar advertisement preference.

[0047] Specifically, the step of “grouping the users of the preset user group based on the advertisement preference type to obtain at least one user group” specifically includes:

[0048] Performing a clustering operation on the preset user group using a K-means algorithm to obtain at least one cluster;

[0049] Users who belong to the same cluster and have the same advertising preference type are divided into a user group.

[0050] K-means clustering algorithm is an iterative clustering analysis algorithm that divides the preset user group into k groups, randomly selects k users as initial cluster centers, and then calculates the distance between each user and each initial cluster center, and assigns each user to the cluster center closest to it. The cluster center and the users assigned to the cluster center represent a cluster. Users in the same cluster represent users with commonalities. Users who belong to the same cluster and have the same advertising preference type are divided into a user group, so that users in each user group have commonalities and have the same or similar advertising preferences.

[0051] After the preset user groups are grouped, the click probability of each user in the preset user group for the advertisement to be placed is calculated, and the click probability represents the possibility of the user interacting with the advertisement to be placed. The advertisement to be placed can be placed to each user in the preset user group, or to some users in the preset user group, and the advertisement to be placed has a preset default delivery frequency, for example, once every three days. Since the greater the user's click probability on the advertisement to be placed, the greater the possibility of the user interacting with the advertisement to be placed, and the smaller the user's click probability on the advertisement to be placed, the smaller the possibility of the user interacting with the advertisement to be placed, the advertisement delivery frequency of each user in each user group can be adjusted according to the click probability.

[0052] Specifically, the above step of "calculating the click probability of each user for the advertisement to be delivered, and adjusting the advertisement delivery frequency of each user in each user group according to the click probability" specifically includes:

[0053] Calculate the click probability of each user on the advertisement based on the classification algorithm;

[0054] Determine the target advertisement preference type to which the advertisement to be delivered belongs;

[0055] The advertisement to be delivered is delivered to a target user group corresponding to the target advertisement preference type, and the advertisement delivery frequency for each user in the target user group is adjusted according to the click probability.

[0056] Based on the classification algorithm (e.g., decision tree, random forest algorithm, etc.), the click probability of each user on the advertisement to be delivered is calculated, and the advertisement preference type (recorded as the target advertisement preference type) to which the advertisement to be delivered belongs is determined. Assuming that the advertisement to be delivered belongs to the type of headphones among electronic products, the advertisement is delivered to the user group corresponding to the advertisement preference type of headphones (recorded as the target user group), and the advertisement delivery frequency of each user in the target user group is adjusted accordingly according to the click probability of each user. This allows the advertisement to be delivered accurately while increasing the possibility of user interaction with the advertisement by adjusting the frequency of advertisement delivery.

[0057] Furthermore, adjusting the advertisement delivery frequency for each user in the target user group according to the click probability includes:

[0058] Determine a first user group in the target user group whose click probability is greater than or equal to a first threshold, and increase the frequency of advertisement delivery to the first user group;

[0059] A second user group in the target user group whose click probability is less than or equal to a second threshold is determined, and the advertisement delivery frequency to the second user group is reduced.

[0060] Determine the user group (referred to as the first user group) in the target user group whose click probability is greater than the first threshold. The first threshold can be reasonably set according to actual needs. For example, the first threshold can be 40%, which is not limited here. The first user group refers to the user group that is more likely to interact with the advertisement to be delivered. Therefore, the frequency of advertisement delivery to the first user group can be increased based on the preset default delivery frequency. For example, if users often search for headphones, the frequency of advertisement delivery for such products will be increased.

[0061] A user group (referred to as the second user group) whose click probability is less than or equal to the second threshold value in the target user group is determined. The second threshold value can be reasonably set according to actual needs. The second threshold value is less than the first threshold value. For example, the second threshold value can be 10%. The second user group refers to a user group that is less likely to interact with the advertisement to be delivered. Therefore, the frequency of advertisement delivery to the second user group can be reduced based on the preset default delivery frequency. If the probability of a user clicking on an advertisement is low, the number of delivery of such advertisements will be automatically reduced to avoid excessively disturbing the user.

[0062] It is understandable that for a user group whose click probability is less than the first threshold and greater than the second threshold (referred to as the third user group), the default delivery frequency can be maintained for delivery, thereby reducing disturbance to sensitive users and increasing the advertising exposure rate to users with high advertising acceptance, thereby improving advertising delivery efficiency and user experience.

[0063] In one embodiment, after adjusting the advertisement delivery frequency of each user in each user group, the method further includes:

[0064] Collect user feedback behavior data after the advertisement to be delivered, and update the parameters of the advertisement preference prediction model according to the feedback behavior data.

[0065] By collecting user experience data and conversion data after advertising is delivered, the advertising preference prediction model can be iteratively optimized and the parameters of the advertising preference prediction model can be updated, thereby improving the accuracy of the advertising preference prediction model's predictions and the accuracy of user group segmentation.

[0066] Reference Figure 2 , which is a schematic diagram of the functional modules of the user behavior-based advertising delivery device 100 of the present application.

[0067] The user behavior-based advertising delivery device 100 described in the present application can be installed in an electronic device. According to the functions implemented, the user behavior-based advertising delivery device 100 may include a collection module 110, an identification module 120, a grouping module 130 and a delivery module 140. The module described in the present application may also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0068] In this embodiment, the functions of each module / unit are as follows:

[0069] Collection module 110: used to collect historical behavior data and user information data of each user in a preset user group;

[0070] Identification module 120: used to input the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user;

[0071] Grouping module 130: used to group users of the preset user group based on the advertisement preference type to obtain at least one user group;

[0072] The delivery module 140 is used to calculate the click probability of each user on the advertisement to be delivered, and adjust the advertisement delivery frequency of each user in each user group according to the click probability.

[0073] In one embodiment, the collecting of historical behavior data and user information data of each user in the preset user group includes:

[0074] Collect the historical browsing records, ad click records, purchase records, and the length of time the user stays on the page for each user in the preset user group.

[0075] In one embodiment, the inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user includes:

[0076] Encoding the historical behavior data and the user information data to obtain historical behavior feature data and user information feature data;

[0077] Splicing the historical behavior feature data and the user information feature data to obtain spliced ​​data;

[0078] The spliced ​​data is input into an advertisement preference prediction model to identify the advertisement preference type of each user.

[0079] In one embodiment, grouping the users of the preset user group based on the advertisement preference type to obtain at least one user group includes:

[0080] Performing a clustering operation on the preset user group using a K-means algorithm to obtain at least one cluster;

[0081] Users who belong to the same cluster and have the same advertising preference type are divided into a user group.

[0082] In one embodiment, the calculating the click probability of each user for the advertisement to be delivered, and adjusting the advertisement delivery frequency of each user in each user group according to the click probability, includes:

[0083] Calculate the click probability of each user on the advertisement based on the classification algorithm;

[0084] Determine the target advertisement preference type to which the advertisement to be delivered belongs;

[0085] The advertisement to be delivered is delivered to a target user group corresponding to the target advertisement preference type, and the advertisement delivery frequency for each user in the target user group is adjusted according to the click probability.

[0086] In one embodiment, adjusting the advertisement delivery frequency of each user in the target user group according to the click probability includes:

[0087] Determine a first user group in the target user group whose click probability is greater than or equal to a first threshold, and increase the frequency of advertisement delivery to the first user group;

[0088] A second user group in the target user group whose click probability is less than or equal to a second threshold is determined, and the advertisement delivery frequency to the second user group is reduced.

[0089] In one embodiment, the user behavior-based advertising delivery device further includes an updating module, which is used to collect user feedback behavior data after the advertisement to be delivered, and update the parameters of the advertisement preference prediction model according to the feedback behavior data.

[0090] Reference Figure 3 , which is a schematic diagram of a preferred embodiment of the electronic device of the present application.

[0091] The electronic device includes a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other via the communication bus 114;

[0092] Memory 113, for storing computer programs, for example, an advertisement delivery program based on user behavior;

[0093] In some embodiments, the processor 111 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 111 is generally used to control the overall operation of the electronic device, such as performing control and processing related to data interaction or communication. In this embodiment, the processor 111 is used to run the program code stored in the memory 113 or process data, such as running the program code of the advertising delivery program based on user behavior.

[0094] The communication interface 112 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and the communication interface 112 may also be used to establish a communication connection between the electronic device and other electronic devices.

[0095] The memory 113 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 113 can be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. In other embodiments, the memory 113 can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped with the electronic device. Of course, the memory 113 can also include both the internal storage unit of the electronic device and its external storage device. In this embodiment, the memory 113 is generally used to store the operating system and various computer programs installed in the electronic device, such as the program code of the advertisement delivery program based on user behavior, etc. In addition, the memory 113 can also be used to temporarily store various types of data that have been output or are to be output.

[0096] Figure 3 Only an electronic device having components 111 - 114 is shown, but it is understood that implementing all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0097] In one embodiment of the present application, the processor 111 is configured to execute a program stored in the memory 113 to implement the user behavior-based advertising method provided by any of the aforementioned method embodiments, including:

[0098] Collect historical behavior data and user information data of each user in the preset user group;

[0099] Inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user;

[0100] Grouping users of the preset user group based on the advertisement preference type to obtain at least one user group;

[0101] The click probability of each user on the advertisement to be delivered is calculated, and the advertisement delivery frequency of each user in each user group is adjusted according to the click probability.

[0102] For a detailed description of the above steps, please refer to the above Figure 1 Description of a flowchart of an embodiment of a method for delivering advertisements based on user behavior.

[0103] In addition, the embodiment of the present application also proposes a computer-readable storage medium, which can be non-volatile or volatile. The computer-readable storage medium includes a data storage area and a program storage area, and the program storage area stores an advertisement delivery program based on user behavior. When the advertisement delivery program based on user behavior is executed by a processor, the following operations are implemented:

[0104] Collect historical behavior data and user information data of each user in the preset user group;

[0105] Inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user;

[0106] Grouping users of the preset user group based on the advertisement preference type to obtain at least one user group;

[0107] The click probability of each user on the advertisement to be delivered is calculated, and the advertisement delivery frequency of each user in each user group is adjusted according to the click probability.

[0108] The specific implementation of the computer-readable storage medium of the present application is roughly the same as the specific implementation of the above-mentioned user behavior-based advertising method, and will not be repeated here.

[0109] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0111] It should be noted that the descriptions involving "first", "second", etc. in this application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0112] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0113] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A method for delivering advertisements based on user behavior, characterized in that: The method comprises: Collect historical behavior data and user information data of each user in the preset user group; Inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user; Grouping users of the preset user group based on the advertisement preference type to obtain at least one user group; The click probability of each user on the advertisement to be delivered is calculated, and the advertisement delivery frequency of each user in each user group is adjusted according to the click probability.

2. The method for placing advertisements based on user behavior according to claim 1, characterized in that: The collecting of historical behavior data and user information data of each user in the preset user group includes: Collect the historical browsing records, ad click records, purchase records, and the length of time the user stays on the page for each user in the preset user group.

3. The method for placing advertisements based on user behavior according to claim 1, characterized in that: The step of inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user includes: Encoding the historical behavior data and the user information data to obtain historical behavior feature data and user information feature data; Splicing the historical behavior characteristic data and the user information characteristic data to obtain spliced ​​data; The spliced ​​data is input into an advertisement preference prediction model to identify the advertisement preference type of each user.

4. The method for placing advertisements based on user behavior according to claim 1, characterized in that: The step of grouping the users of the preset user group based on the advertisement preference type to obtain at least one user group includes: Performing a clustering operation on the preset user group using a K-means algorithm to obtain at least one cluster; Users who belong to the same cluster and have the same advertising preference type are divided into a user group.

5. The method for placing advertisements based on user behavior according to claim 1, characterized in that: The calculating the click probability of each user for the advertisement to be delivered, and adjusting the advertisement delivery frequency of each user in each user group according to the click probability, comprises: Calculate the click probability of each user on the advertisement based on the classification algorithm; Determine the target advertisement preference type to which the advertisement to be delivered belongs; The advertisement to be delivered is delivered to a target user group corresponding to the target advertisement preference type, and the advertisement delivery frequency for each user in the target user group is adjusted according to the click probability.

6. The method for placing advertisements based on user behavior as claimed in claim 5, characterized in that: The step of adjusting the advertisement delivery frequency for each user in the target user group according to the click probability includes: Determine a first user group in the target user group whose click probability is greater than or equal to a first threshold, and increase the frequency of advertisement delivery to the first user group; A second user group in the target user group whose click probability is less than or equal to a second threshold is determined, and the advertisement delivery frequency to the second user group is reduced.

7. The method for placing advertisements based on user behavior according to claim 1, characterized in that: The method further comprises: Collect user feedback behavior data after the advertisement to be delivered, and update the parameters of the advertisement preference prediction model according to the feedback behavior data.

8. An advertisement delivery device based on user behavior, characterized in that: The device comprises: Collection module: used to collect historical behavior data and user information data of each user in the preset user group; Identification module: used for inputting the historical behavior data and the user information data into a pre-trained advertising preference prediction model to identify the advertising preference type of each user; A grouping module: used for grouping users of the preset user group based on the advertisement preference type to obtain at least one user group; Delivery module: used to calculate the click probability of each user on the advertisement to be delivered, and adjust the advertisement delivery frequency of each user in each user group according to the click probability.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor is used to implement the user behavior-based advertising method described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for delivering advertisements based on user behavior as claimed in any one of claims 1 to 7 is implemented.

Images