Advertisement delivery method and related device

Abstract

This application provides an advertising delivery method and related apparatus. The method includes: acquiring project information of a target property and determining project characteristics of the target property based on the project information; determining reference user tags that match the project characteristics; sending a query request message carrying the reference user tags to a real estate platform server; receiving a query response message sent by the real estate platform server in response to the query request message, wherein the query response message carries device information of multiple target users; and sending advertisements to the user devices of the multiple target users. This application embodiment can determine target users based on the project information of the target property and can also directly send matching advertisements to the devices of the target users, solving the problems of low advertising delivery efficiency and conversion efficiency, thereby enabling accurate and efficient targeting and advertising delivery to the target audience.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to an advertising delivery method and related apparatus. Background Technology

[0002] Currently, with the development and progress of network technology, online advertising and advertising marketing have become the mainstream in the advertising field. The traditional method of using various channels for large-scale advertising has gradually shifted to targeting specific groups, thereby reducing the investment cost of advertising.

[0003] However, in the early stages of traditional advertising campaigns that rely on data acquisition to target users, advertisers and operators are unable to accurately depict the profiles of their target user groups, resulting in poor advertising efficiency and conversion rates, and wasting a significant amount of time and money. Summary of the Invention

[0004] This application provides an advertising delivery method and related apparatus to improve the efficiency, convenience, and practicality of advertising delivery on servers.

[0005] In a first aspect, embodiments of this application provide an advertising delivery method, including:

[0006] Obtain project information for the target property;

[0007] The project characteristics of the target property are determined based on the project information of the target property, and the project characteristics are used to characterize at least one of the following attributes of the target property: unit type, location and use;

[0008] Determine reference user tags that match the project characteristics, the reference user tags being used to describe the user profile of the target property;

[0009] Send a query request message carrying the reference user tag to the real estate platform server;

[0010] The system receives a query response message from the real estate platform server in response to the query request message. The query response message carries device information of multiple target users, and the user tags of the multiple target users are matched with the reference user tags.

[0011] The advertisement for the target property is sent to the user devices of the multiple target users.

[0012] Secondly, embodiments of this application also provide an advertising delivery method, including:

[0013] The system receives a query request message from the advertising platform server. The query request message includes reference user tags, which are adapted to the project features of the target property. The project features are used to characterize at least one of the following attributes of the target property: apartment type, location, and usage. The reference user tags are used to describe the user profile of the target property.

[0014] In response to the user query request message, a preset original user set is queried to obtain the device information of multiple target users whose user tags match the reference user tags. The original user set includes the correspondence between user tags and user device information.

[0015] Thirdly, embodiments of this application also provide an advertising delivery device, including:

[0016] Acquisition Unit: Used to acquire project information for the target property;

[0017] Project Feature Determination Unit: Used to determine the project features of the target property based on the project information of the target property, wherein the project features are used to characterize at least one of the following attributes of the target property: unit type, location, and use;

[0018] The reference user tag determination unit is used to determine reference user tags that are compatible with the project characteristics, wherein the reference user tags are used to describe the user profile of the target property.

[0019] Sending unit: used to send a query request message carrying the reference user tag to the real estate platform server;

[0020] Receiving unit: used to receive a query response message sent by the real estate platform server in response to the query request message, the query response message carrying device information of multiple target users, and the user tags of the multiple target users matching the reference user tags;

[0021] Delivery unit: Used to send advertisements for the target property to the user devices of the multiple target users.

[0022] Fourthly, embodiments of this application also provide an advertising delivery device, including:

[0023] Receiving unit: used to receive a query request message sent from the advertising platform server. The query request message includes reference user tags, which are adapted to the project features of the target property. The project features are used to characterize at least one of the following attributes of the target property: apartment type, location, and use. The reference user tags are used to describe the user profile of the property.

[0024] Response unit: used to respond to the user query request message, query a preset original user set, and obtain device information of multiple target users whose user tags match the reference user tags. The original user set includes the correspondence between user tags and user device information.

[0025] Sending unit: Used to send a query response message carrying the device information of the multiple target users to the advertising platform server.

[0026] Fifthly, embodiments of this application also provide an advertising platform server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described in the first aspect above.

[0027] In a sixth aspect, embodiments of this application also provide a real estate platform server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described in the second aspect above.

[0028] In a seventh aspect, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the methods of the first aspect or the second aspect as described above.

[0029] Eighthly, embodiments of this application provide a computer program product, wherein the computer program product includes a computer program operable to cause a computer to perform some or all of the steps described in the first or second aspects of embodiments of this application. The computer program product may be a software installation package.

[0030] As can be seen, in this embodiment, the advertising platform server first obtains the project information of the target property, then determines the project characteristics of the target property based on the project information, then determines the appropriate reference user tag based on the project characteristics, then sends a query response message carrying the reference user tag to the property platform server, receives the query response message sent by the property platform server in response to response two, and finally delivers the property-related advertisement to the target user's device based on the device information of the target user carried in the query response message. In this way, different target groups can be determined according to different property projects, and the device information of users matching the target group can be obtained to achieve the delivery of advertisements. This avoids the problem of low advertising efficiency and conversion rate caused by relying on the experience of staff to judge the intention group, improves the efficiency of advertising delivery and the accuracy of target group positioning, and reduces the investment costs paid by advertisers. Attached Figure Description

[0031] 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1a This is a schematic diagram of an advertising delivery system provided in an embodiment of this application;

[0033] Figure 1b This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0034] Figure 1c This is a schematic diagram of the structure of a server provided in an embodiment of this application;

[0035] Figure 2 This is a flowchart illustrating an advertising delivery method provided in an embodiment of this application;

[0036] Figure 3 This is a flowchart illustrating another advertising delivery method provided in an embodiment of this application;

[0037] Figure 4 This is a functional unit block diagram of an advertising delivery device provided in an embodiment of this application;

[0038] Figure 5 This is a functional unit block diagram of another advertising delivery device provided in the embodiments of this application;

[0039] Figure 6 This is a structural block diagram of an advertising delivery device provided in an embodiment of this application;

[0040] Figure 7 This is a structural block diagram of another advertising delivery device provided in the embodiments of this application. Detailed Implementation

[0041] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0042] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0043] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0044] The following is a brief introduction to the relevant terminology used in this application.

[0045] Identifier for Advertising (IDFA): This can be understood as an advertising ID. It is an advertising identifier used to track users and can be used to connect advertisements between different apps.

[0046] International Mobile Equipment Identity number (IMEI): Commonly known as "mobile phone serial number", it is used to identify each unique mobile phone in the GSM mobile network, equivalent to the mobile phone's ID card number.

[0047] To better understand the technical solutions of the embodiments of this application, the advertising delivery system and electronic equipment that may be involved in the embodiments of this application will be introduced below.

[0048] Please see Figure 1a , Figure 1aThis is a schematic diagram of an advertising delivery system provided in an embodiment of this application. As shown in the figure, the advertising delivery system 100 includes an advertising platform server 101, a real estate platform server 102, and an electronic device 103. The advertising platform server 101, the real estate platform server 102, and the electronic device 103 are communicatively connected to each other. The electronic device 103 is used to browse real estate information on the real estate platform server 102. In this way, the real estate platform server 102 can record the browsing information behavior of the user corresponding to the electronic device 103, as well as the device information of the electronic device 103. Then, the real estate platform server 102 tags the browsing information behavior to obtain user tags, and stores them along with the obtained device information in a pre-created set. Thus, after the advertising platform server 101 determines the reference user tags based on the project information of the target real estate and sends the query request information carrying the reference user tags to the real estate platform server 102, the real estate platform server 102 can query the set according to the reference user tags to obtain the device information of the user matching the tag. The target user's device information is then sent back to the advertising platform server 101. Finally, the advertising platform server 101 can send the advertisement to the target user's electronic device 103 based on the target user's device information. One advertising platform server 101 can also correspond to multiple real estate platforms and multiple electronic devices simultaneously, or the advertising delivery system 100 includes multiple advertising delivery servers, each corresponding to one or more real estate platforms and electronic devices.

[0049] Specifically, such as Figure 1a The structure of the electronic device can be found in [reference]. Figure 1b , Figure 1b This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 1b As shown, the electronic device 110 includes a processor 120, a memory 130, a communication interface 140, and one or more programs 131, wherein the one or more programs 131 are stored in the memory 130 and configured to be executed by the processor 120. Figure 1a The structures of the advertising platform server and the real estate platform server can be found in [reference needed]. Figure 1c , Figure 1c This is a schematic diagram of the structure of a server provided in an embodiment of this application. For example... Figure 1cAs shown, the server 210 can implement the steps of the advertising delivery method and another advertising delivery method. The server 210 includes a processor 220, a memory 230, a communication interface 240, and one or more programs 231. The one or more programs 231 are stored in the memory 230 and configured to be executed by the processor 220. The one or more programs 231 include instructions for performing any step in the above method embodiments.

[0050] The communication interface can also be a transceiver, transceiver circuit, etc., used to support communication between the first electronic device and other devices. The memory is used to store the terminal's program code and data. The processor can also be a controller, such as a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an Application-Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, units, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0051] The memory can be volatile memory or non-volatile memory, or it can include both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0052] In a specific implementation, the processor is used to execute any step performed by the electronic device as described in the above method embodiments, and when performing data transmission such as sending, it may selectively call the communication interface to complete the corresponding operation.

[0053] Currently, when advertisers initially establish their advertising campaigns, they need to combine and filter massive amounts of user tags provided by various platforms, relying on the experience of their staff to determine the user tags for their target audience. This results in excessively high demands on staff, and the limitations of advertising budgets prevent advertisers from conducting multiple campaigns. It also makes it impossible to guarantee the accuracy and comprehensiveness of the target audience corresponding to the selected tag combinations, consuming significant resources and resulting in low efficiency.

[0054] To address the aforementioned issues, this application provides an advertising delivery method. This method is applied to an advertising delivery server to deliver advertisements. The method determines the project characteristics of the target property by obtaining its project information, and then determines suitable reference user tags. A query request message carrying the reference user tags is then sent to the property server to obtain a query response message. Finally, advertisements are delivered based on the target user's device information carried in the query response message. This achieves efficient and accurate targeting of the target audience, and improves the conversion rate and efficiency of advertising delivery by allowing advertisements to be delivered based on the device information of users belonging to that target audience.

[0055] The following describes the advertising placement method process involved in the embodiments of this application from the perspective of method implementation.

[0056] Please see Figure 2 , Figure 2 This is a flowchart illustrating an advertising delivery method provided in an embodiment of this application, applied to an advertising platform server. The method includes the following steps:

[0057] Step 201: Obtain project information for the target property;

[0058] The project information of the target property refers to the relevant information of the property development project. The project information may include name, address, project purpose, land acquisition time, number of building floors, residential area, plot ratio, etc. This embodiment does not limit this information. By obtaining the project information of the target property, a comprehensive understanding of the relevant property development project can be obtained, thereby enabling the user to obtain the aspects that are of interest.

[0059] Step 202: Determine the project characteristics of the target property based on the project information of the target property;

[0060] The project features are used to characterize at least one of the following attributes of the target property: unit type, location, and use. That is, based on the project information of the target property, we can determine the geographical location, unit type, use, property rights term, plot ratio, and other related attributes of the target property. This embodiment does not impose any restrictions here.

[0061] For example, the project characteristics regarding location can be represented as "Shenzhen City, City Center Area". Project characteristics regarding unit type can be represented as "Large Unit" or "Small Unit". The definition of "Large Unit" can be based on area size, such as a unit with a building area of ​​140 square meters, or it can be determined by the plot ratio, such as a plot ratio below 1.0. The property rights term mainly refers to the land use term occupied by the buildings in the target property project, whether it is 50 years or 70 years. This can also be determined based on whether the property occupies industrial, educational, scientific, cultural, or residential land, as stated in the project information. Project characteristics regarding plot ratio can be represented as "High Plot Ratio" or "Low Plot Ratio". The plot ratio is calculated by dividing the total building area of ​​the property project by the total land area. Generally, a higher plot ratio results in lower resident comfort, and vice versa. Project characteristics regarding usage can be represented as "Residential", "Commercial", "Office", or "Investment" to indicate the actual use of the property project after development.

[0062] Step 203: Determine reference user tags that match the project characteristics;

[0063] The reference user tags are used to describe the user profile of the target property.

[0064] In one possible embodiment, determining the reference user tags that match the project features includes: obtaining a preset set of user tags, the set of user tags including the correspondence between user tags and project features; querying the set of user tags using the project features as the query identifier to obtain the reference user tags corresponding to the project features.

[0065] Specifically, by pre-creating a preset set of user tags and storing the correspondence between user tags and project features within this set, it's equivalent to preparing a matching set in advance. After obtaining the project features of the target property, these features are matched against the corresponding user tags based on the stored correspondence, allowing direct identification of the project's reference user tags. These reference user tags are used to depict the user profile of the target property.

[0066] For example, when the project characteristics of the target property are "located in Shenzhen, large unit, investment", according to the correspondence between project characteristics and user tags stored in the preset user tag set, the corresponding reference user tags can be queried based on the project characteristics as "located in Shenzhen, three-bedroom unit preference, and property type preference". The user profile of the target property is depicted by the reference user tags.

[0067] As can be seen, in this example, by obtaining a preset set of user tags and using the project feature as the query identifier, the user tag set is queried to obtain reference user tags corresponding to the project feature. Therefore, it is possible to conveniently, quickly and accurately depict the user profile of the target real estate project, which facilitates subsequent screening of target users and acquisition of information.

[0068] In one possible embodiment, determining the reference user tag that matches the project feature includes: obtaining a preset set of user tags, the set of user tags including multiple user tags; determining the correlation between each user tag in the set of user tags and the project feature; and using the user tag with the highest correlation as the reference user tag.

[0069] Because the processing steps before and after may differ, the resulting project features and reference user tags may not be entirely identical. However, this can be mitigated by pre-setting the wording to be similar between the project features and the reference user tags. In this way, when determining reference user tags based on project features, the degree of relevance can be determined based on word similarity, and then the user tag with the highest relevance can be selected as the reference user tag based on the number of project features. Project features can represent only one property project attribute or multiple property project attributes. Similarly, user tags can also have only one feature; for example, a user tag can be in the form of "A", "A,B", or "A,B,C", etc., which is not limited in this embodiment.

[0070] For example, the project characteristics of the target property are "large-sized apartments, investment type, and location in Shenzhen". Since there are many types of user tags, as long as the user tags with the highest relevance are selected by word similarity, it is possible to locate user tags that can accurately describe the profile of the target user group, such as "large-sized apartments, investment type, and location in Shenzhen".

[0071] As can be seen in this example, by obtaining a preset set of user tags, the user tags of users classified by the corresponding real estate platform server are obtained, and the correlation between these user tags and project features is determined. By selecting the user tag with the highest correlation as the reference user tag, the accuracy of the user profile is ensured. This ensures that the project features of the target real estate best match the preferences of the user corresponding to the reference user tag. At the same time, it also maintains the flow and consistency of information between the advertising platform server and the real estate platform server, ensuring the efficiency of advertising placement and the improvement of the conversion rate of subsequent advertising placements.

[0072] In one possible embodiment, determining the correlation between each user tag and the item feature in the user tag set includes: inputting each user tag and the item feature into a preset word vector generation model to obtain a first word vector corresponding to each user tag and a second word vector corresponding to the item feature; and obtaining the similarity between each first word vector and the second word vector according to a preset calculation formula, wherein the magnitude of the similarity is used to characterize the degree of correlation between the user tag and the item feature.

[0073] This method transforms the textual problem into a vector space problem by inputting user tags and project features into a pre-defined word vector generation model. Both the first and second word vectors possess the general properties of vectors, namely magnitude and direction. Vector magnitude is measured by its length; generally, the closer the ratio of the lengths of two vectors is to 1, the higher the similarity between the corresponding words. Similarly, the smaller the angle between the two vectors, the higher the similarity between the corresponding words. In summary, the similarity between the first and second word vectors is directly proportional to the angle and length between the two vectors. Of course, weighting the length ratio and angle between the two vectors is necessary to calculate the similarity.

[0074] For example, when the length ratio is weighted at 0.5, the included angle is weighted at 0.5, and the length ratio between the first and second word vectors is 0.4, with an included angle of 60 degrees, the similarity is calculated as 0.5 × 0.4 + (0.5 - 0.5 × 1 / 3) = 0.5333, rounded to four decimal places. Under the condition of equal weighting, the similarity between each first and second word vector is obtained, and the magnitude of the similarity represents the degree of association.

[0075] As can be seen in this example, by obtaining the word similarity between user tags and project features to represent their correlation, the user tags with the highest correlation can be selected based on the magnitude of the similarity. This ensures the accuracy of the user profile of the target property depicted by the obtained reference user tags, thus guaranteeing the efficiency and conversion rate of subsequent advertising.

[0076] In one possible embodiment, the user tag is used to characterize at least one of the following features of the user: user attributes, geographic characteristics, platform device, property preferences, and content preferences; wherein, the property preferences include property type preferences and property usage preferences.

[0077] The user attributes may include the user's age, gender, occupation, life stage, etc.; the geographical features may include the user's province and city, whether they are located in an urban area or a town, etc.; the platform device may include the user's mobile phone system, mobile phone brand and model, etc.; the real estate preferences may include preferences for new houses, second-hand houses, apartment types, prices, and uses of real estate, etc.; and the content preferences refer to the content of real estate information that the user likes to browse, which may include a preference for real estate policy interpretations, a preference for home buying stories, etc., but this embodiment does not limit these preferences.

[0078] As can be seen in this example, users are categorized from multiple perspectives based on their relevant behaviors on the real estate platform, resulting in multiple user tags. Each user tag can represent the characteristics of a user, enabling multi-angle analysis and accurate identification of users. This allows for the subsequent identification of users who match the user profile based on the reference user tags, thus accurately targeting user groups and improving advertising conversion rates.

[0079] Step 204: Send a query request message carrying the reference user tag to the real estate platform server;

[0080] Step 205: Receive the query response message sent by the real estate platform server in response to the query request message.

[0081] The query response message carries device information of multiple target users, and the user tags of the multiple target users are matched with the reference user tags;

[0082] In one possible embodiment, when the advertising platform server determines the correlation between each user tag and the project feature, after receiving the query response message sent by the real estate platform server in response to the query request message, the method further includes: obtaining the number of target users based on the query response message; determining whether the number of target users is greater than a preset threshold; if not, sending a supplementary query request message to the real estate platform server carrying supplementary user tags with a correlation greater than a preset value, wherein the supplementary user tags refer to user tags with a correlation greater than a preset value other than the user tag with the highest correlation.

[0083] In specific application scenarios, some advertisers have defined metrics in their advertising campaigns, such as the number of users targeted. However, in practice, there may be situations where the number of users corresponding to the reference user tags is less than the advertiser's target number. Therefore, based on the correlation between each user tag and the project characteristics, user tags with a correlation greater than a certain value are identified. These user tags are then used to re-request the target users' device information, ensuring that the number of users targeted by the advertisement meets the advertiser's needs and that the characteristics of these users maximally match the relevant attributes of the real estate project.

[0084] As can be seen, in this embodiment, the number of target users is obtained by receiving query response messages to determine whether the preset threshold is met. When it is determined that the threshold is not met, compensation user tags are determined according to the preset relevance value to re-query and obtain additional users. This can ensure that the advertiser's demand for the number of users is met, and that the obtained users are as close as possible to the user profile of the real estate project, avoiding the situation where the conversion rate of advertising is reduced due to the pursuit of the number of target users.

[0085] In one possible embodiment, the device information includes at least one of the following data: International Mobile Equipment Identity (IMEL), Identifier for Advertising (IDFA), and mobile phone number.

[0086] In this embodiment, the real estate platform server can obtain and collect the device information used by the user when the user browses real estate information. The device information can be any or a combination of the International Mobile Equipment Identity (IMEL), the Identifier for Advertising (IDFA), and the mobile phone number. Of course, it can also include other types of device information, but this embodiment does not impose any restrictions.

[0087] For example, a user logs into the real estate platform using their device and responds to the real estate platform server to access a webpage to browse real estate information. When the real estate platform server responds to the user's device, it obtains the device's information. For devices using Apple operating systems, the Identifier for Advertising (IDFA) is collected first; for devices using Android operating systems, the IMEI (Mobile Serial Number) is collected first. After collecting the device information, the real estate platform server stores the device information in a preset set.

[0088] As can be seen in this example, by sending a query request message to the real estate platform server to obtain the device information of relevant users who match the reference user tags, this device information can be of various types, ensuring that subsequent advertisements can be effectively delivered to the devices of the desired users, allowing users to read the advertisements and ensuring the conversion rate of the advertisements.

[0089] Step 206: Send advertisements for the target property to the user devices of multiple target users.

[0090] In one possible embodiment, before sending the advertisement for the target property to the user devices of the plurality of target users, the method further includes: querying a preset set of original advertisements based on the reference user tags, obtaining at least one target advertisement whose advertisement tags match the reference user tags; and determining that the at least one target advertisement is an advertisement to be delivered.

[0091] The original set of advertisements includes the correspondence between advertisement tags and advertisements, and the multiple advertisement tags and the multiple user tags correspond one-to-one.

[0092] Before delivering ads to the target users' devices, the advertising platform server, which may be commissioned by the advertiser to a third party for ad delivery, will provide the advertiser with multiple ads to prepare in advance. The advertising platform server then queries a pre-set collection of original ads containing multiple ads based on the reference user tags. According to the correspondence between ad tags and ads stored in this collection, and the ad tags corresponding to the multiple user tags, the target ads matching the reference user tags can be obtained, and these target ads can then be delivered to the corresponding users.

[0093] For example, when the reference user tag is "preference for large apartments, preference for new homes, and inclination towards real estate policy interpretation", a corresponding advertisement is matched in the original advertisement set based on the reference user tag. The advertisement tag of the advertisement is "large apartments, new homes, and real estate policy interpretation". Finally, the advertisement is determined as the advertisement to be delivered, and the advertisement delivery platform server delivers the advertisement to the target user based on the user device information obtained in advance.

[0094] As can be seen in this example, by querying the preset set of original advertisements based on reference user tags, advertisements that match the preferences of the user group are obtained and delivered. This can meet the needs of users and improve their experience. It also allows advertisers to provide multiple advertisements to the advertising platform server in a similar way to creating advertisements based on user tags in advance. This allows the advertising platform server to select the most suitable advertisement for user groups with different preferences, which can greatly increase the conversion rate and efficiency of advertising.

[0095] In one possible embodiment, before querying the preset original ad set according to the reference user tags, the method further includes: inputting the plurality of ads into a pre-trained ad tag model to obtain the plurality of ad tags, wherein the plurality of ad tags correspond to one or more ads respectively; and storing the correspondence between the ad tags and the ads in a pre-created original ad set.

[0096] In this process, a pre-trained ad tagging model is used to categorize ads by ad tags corresponding to user tags. The correspondence between ad tags and ads is stored in a pre-created set, allowing the ad placement work to be completed in the early stages. Once the placement operation begins, the selection of ads to be placed can be done efficiently and conveniently. Furthermore, the pre-trained ad tagging model and the original ad set can be reused, making subsequent tagging of new ads and the launch of a new round of ad placement work more convenient and practical.

[0097] Specifically, training the ad labeling model includes: acquiring training data, which refers to the multiple ads that have already been labeled; training a specified mathematical model based on the training data until the accuracy of the mathematical model in predicting ad labels reaches a preset value; and converging the mathematical model to obtain the ad labeling model. The mathematical model can be any deep learning model, such as a Gate Recurrent Unit (GRU) model, a Recurrent Neural Network (RNN), etc.

[0098] As can be seen in this example, by pre-training the ad tag model, the ad platform server can classify ads by tags and select appropriate ads for users with corresponding reference user tags. This not only improves the user experience but also meets the corresponding needs of these users.

[0099] In one possible embodiment, before sending the advertisement for the target property to the plurality of target user devices, the method further includes: obtaining the project introduction URL of the target property, querying a preset set of advertising materials according to the reference user tags, obtaining at least one target image and at least one target text that match the material tags with the reference user tags; obtaining at least one target advertisement based on the at least one target image, at least one target text, the project introduction URL, and a preset advertisement generation model; and determining the at least one target advertisement as an advertisement to be delivered.

[0100] The advertising material set includes the correspondence between material tags and text, the correspondence between material tags and images, and a one-to-one correspondence between the multiple material tags and the multiple user tags.

[0101] Furthermore, before querying the preset set of advertising materials based on the reference user tags, the method further includes: inputting the multiple images and multiple texts into a pre-trained material tag model to obtain the multiple material tags, wherein the multiple material tags correspond to one or more images and one or more texts respectively; and storing the correspondence between the material tags and the images, and the correspondence between the material tags and the texts, into a pre-created set of advertising materials.

[0102] Specifically, training the material labeling model includes: acquiring training data, which refers to the multiple images and multiple texts that have already been labeled with material tags; training a specified mathematical model based on the training data until the accuracy of the mathematical model in predicting user tags reaches a preset value; and converging the mathematical model to obtain the material labeling model. The mathematical model can be any deep learning model, such as a GRU model, RNN, etc.

[0103] For example, there are cases where the advertising platform server is operated by the advertiser themselves. In this case, after obtaining the reference user tags, the advertising platform server can use its pre-created set of advertising materials to edit and generate target ads. Multiple ads can be generated by using images, text, and the project introduction URL of the target property.

[0104] As can be seen in this example, the pre-trained material tagging model allows the advertising platform server to tag its own materials. The identified tags are consistent with the real estate advertising server it connects to. This enables the generation of advertisements based on reference user tags, significantly reducing the cost of advertising and eliminating concerns about advertisements not matching the preferences of the target user group.

[0105] It can be seen that, in Figure 2 This application provides a flowchart illustrating an advertising placement method. The method involves first obtaining project information for the target property, then determining the property's characteristics based on this information, followed by matching suitable reference user tags based on these characteristics, and finally sending a query request message to the corresponding property platform server to obtain device information of users matching the reference user tags. The advertising is then targeted to the target users based on this device information. This step-by-step approach, from obtaining project information to identifying project characteristics and matching suitable reference user tags, and then targeting specific users based on these tags, achieves precise positioning of the target user group from the moment project information is obtained. This eliminates the need for significant upfront costs, greatly reducing advertisers' investment expenses. Furthermore, by obtaining user device information, precise ad placement is achieved, ensuring a high conversion rate for advertising.

[0106] Please see Figure 3 , Figure 3 This is a flowchart illustrating another advertising delivery method provided in this application embodiment. The method, applied to a real estate platform server, includes the following steps:

[0107] Step 301: Receive a query request message sent from the advertising platform server;

[0108] The query request message includes reference user tags, which are adapted to the project features of the target property. The project features are used to characterize at least one of the following attributes of the target property: apartment type, location, and use. The reference user tags are used to describe the user profile of the target property.

[0109] In one possible embodiment, before receiving the query request message sent from the advertising platform server, the method further includes: acquiring at least one set of user data, the user data including user browsing behavior information and device information, the at least one set of user data corresponding to one user; performing tag prediction based on the at least one set of user browsing behavior information and a pre-trained user tag model to obtain the at least one type of user tag; and storing the correspondence between the user tag and the user's device information, the at least one set of device information, and the at least one type of user tag to the original user set.

[0110] Specifically, training the user tagging model includes: acquiring training data, which refers to the multiple sets of user browsing behavior information that have been tagged; training a specified mathematical model based on the training data until the accuracy of the mathematical model in predicting user tags reaches a preset value; and converging the mathematical model to obtain the user tagging model. The mathematical model can be any deep learning model, such as a GRU model or an RNN.

[0111] Since users log in to the real estate platform to browse information or related web pages, the platform's server can record relevant user data, including user browsing behavior information and user device information. A user tagging model is then pre-trained to tag users based on their browsing behavior information, allowing these tags to represent various user preferences. The correspondence between user tags and user device information, at least one set of device information, and at least one type of user tag are then stored in the original user set.

[0112] As can be seen in this example, by obtaining users' browsing behavior information and device information, each user whose information is recorded can be tagged. This allows for the extraction and processing of user-related information to classify users, making it easier to select relevant users and obtain their device information based on tags. This shortens the time required for ad placement. Moreover, after tagging, the original user set can be reused according to different business needs, greatly improving its practicality.

[0113] In one possible embodiment, the user browsing behavior information includes: click operations, page dwell time, and page content information.

[0114] For example, if a user enters a property project page on a real estate platform and stays on that page for more than a preset time, such as 3 minutes, it is determined that the user is interested in the content of that webpage. By obtaining the content of the webpage that the user is interested in, the real estate platform server can determine the user's relevant preferences based on the keywords in the webpage content, such as "investment properties, new homes, small apartments". Furthermore, through the user information input box set when entering the real estate platform, the platform server can also obtain the user's relevant attributes and geographical characteristics, such as "30 years old, male, lawyer, city: Huizhou".

[0115] As can be seen in this example, the obtained user browsing behavior information can be transformed into user tags in various forms, enabling the user to be tagged and classified, so that the advertisements finally delivered to the target user meet their needs and ensure the conversion rate of the advertisement delivery.

[0116] Step 302: Respond to the user query request message, query the preset original user set, and obtain the device information of multiple target users whose user tags match the reference user tags;

[0117] The original user set includes the correspondence between user tags and user device information.

[0118] In one possible embodiment, querying the preset original user set includes: matching multiple user tags stored in the original user set with the reference user tags to determine target user tags; and determining the device information of the multiple target users based on the correspondence between the user tags and the user's device information.

[0119] The reference user tag can be one or more user tags. The target user tag is determined based on the reference user tag. Then, based on the correspondence between user tags and user device information stored in the set, the device information of one or more target users corresponding to each target user tag is obtained.

[0120] As can be seen in this example, by matching user tags in the original user set with reference user tags, it is possible to obtain device information of multiple target users, ensuring the efficiency and convenience of ad delivery.

[0121] In one possible embodiment, matching the user tags stored in the original user set according to the reference user tags includes: determining whether each user tag exists in the reference user tags; if so, determining the currently processed user tag as the target user tag.

[0122] Since the reference user tags correspond to multiple user tags classified by the user tag model, the target user tag can be determined by judging whether each user tag is in the reference user tags.

[0123] As can be seen in this example, by setting the tags of the advertising platform server and the real estate platform server to be consistent, the target user tags can be determined and selected through a simple judgment process.

[0124] Step 303: Send a query response message carrying device information of multiple target users to the advertising platform server.

[0125] It can be seen that, in Figure 3 This is a flowchart illustrating another advertising delivery method provided in this application embodiment. By receiving and responding to query request messages sent by the advertising delivery platform server, the device information of target users whose user tags match the reference user tags can be found in the original user set. This enables the rapid determination of user tags of target users and the acquisition of device information of these target users through the interaction of the two platform servers, thereby improving the efficiency and practicality of advertising delivery.

[0126] The following are embodiments of the apparatus of this application. These embodiments of the apparatus and the embodiments of the method of this application belong to the same concept and are used to execute the methods described in the embodiments of this application. For ease of explanation, only the parts related to the apparatus embodiments of this application are shown in the embodiments of this application. For specific technical details not disclosed, please refer to the description of the embodiments of the method of this application, which will not be repeated here.

[0127] This application provides an advertising delivery device, which can be an advertising platform server. Specifically, the advertising delivery device is used to execute the steps described by the advertising platform server in the above advertising delivery method. The advertising delivery device provided in this application may include modules corresponding to the respective steps.

[0128] This application embodiment can divide the advertising delivery device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. The module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0129] When dividing each function into modules according to its corresponding function. Figure 4 This is a functional unit block diagram of an advertising delivery device provided in an embodiment of this application. For example... Figure 4 As shown, the advertising delivery device 400 includes: an acquisition unit 401 for acquiring project information of a target property; a project feature determination unit 402 for determining project features of the target property based on the project information, wherein the project features characterize at least one of the following attributes of the target property: apartment type, location, and usage; a reference user tag determination unit 403 for determining reference user tags that match the project features, wherein the reference user tags describe the user profile of the target property; a sending unit 404 for sending a query request message carrying the reference user tags to a real estate platform server; a receiving unit 405 for receiving a query response message sent by the real estate platform server in response to the query request message, wherein the query response message carries device information of multiple target users, and the user tags of the multiple target users match the reference user tags; and a delivery unit 406 for sending an advertisement of the target property to the user devices of the multiple target users.

[0130] In one possible embodiment, in determining the reference user tags that are compatible with the project features, the reference user tag determining unit 403 is specifically used to: obtain a preset set of user tags, the set of user tags including the correspondence between user tags and project features; query the set of user tags using the project features as the query identifier, and obtain the reference user tags corresponding to the project features.

[0131] In one possible embodiment, in determining the reference user tag that is compatible with the project feature, the reference user tag determining unit 403 is specifically used to: obtain a preset set of user tags, the set of user tags including multiple user tags; determine the degree of correlation between each user tag in the set of user tags and the project feature; and take the user tag with the highest degree of correlation as the reference user tag.

[0132] In one possible embodiment, in determining the correlation between each user tag and the item feature in the user tag set, the reference user tag determination unit 403 is specifically used to: input each user tag and the item feature into a preset word vector generation model to obtain a first word vector corresponding to each user tag and a second word vector corresponding to the item feature; and obtain the similarity between each first word vector and the second word vector according to a preset calculation formula, wherein the magnitude of the similarity is used to characterize the degree of correlation between the user tag and the item feature.

[0133] In one possible embodiment, in determining the reference user tags that are adapted to the project characteristics, the reference user tag determining unit 403 is specifically used for: the user tags being used to characterize at least one of the following characteristics of the user: user attributes, geographic characteristics, platform device, property preferences, and content preferences; wherein, the property preferences include property type preferences and property usage preferences.

[0134] In one possible embodiment, in receiving the query response message, the receiving unit 405 is specifically configured to: the device information includes at least one of the following data: International Mobile Equipment Identity (IMEL), Identifier for Advertising (IDFA), and mobile phone number.

[0135] In one possible embodiment, in sending the advertisement for the target property to the user devices of the plurality of target users, the delivery unit 406 is specifically configured to: query a preset original advertisement set according to the reference user tags, obtain at least one target advertisement whose advertisement tags match the reference user tags, the original advertisement set including the correspondence between advertisement tags and advertisements, the plurality of advertisement tags and the plurality of user tags being one-to-one correspondence; and determine the at least one target advertisement as an advertisement to be delivered.

[0136] In one possible embodiment, in the step of querying a preset set of original advertisements based on the reference user tags, the delivery unit 406 is specifically configured to: input the plurality of advertisements into a pre-trained advertisement tag model to obtain the plurality of advertisement tags, wherein the plurality of advertisement tags correspond to one or more advertisements respectively; and store the correspondence between the advertisement tags and the advertisements in a pre-created set of original advertisements.

[0137] As can be seen, the advertising delivery device provided in this application embodiment can achieve the following: first, obtain the project information of the target property; then, determine the project characteristics of the property based on the project information; next, match suitable reference user tags based on the project characteristics; and finally, send a query request message to the corresponding real estate platform server to obtain the device information of users who match the reference user tags. Based on this device information, the advertising is then delivered to the target users. In this way, through a progressive process from project information to project characteristics to matching suitable reference user tags, and then locking in the target users based on the obtained reference user tags, precise positioning of the target user group can be achieved simply by obtaining the project information. This eliminates the need for significant upfront costs, greatly reducing the advertiser's investment costs. Furthermore, by obtaining the user's device information, precise advertising delivery to the target users can be achieved, ensuring a high conversion rate for advertising.

[0138] This application also provides another advertising delivery device, which can be a real estate platform server. Specifically, the advertising delivery device is used to execute the steps described in the above advertising delivery method performed by the real estate platform server. The advertising delivery device provided in this application may include modules corresponding to the respective steps.

[0139] This application embodiment can divide the advertising delivery device into functional modules based on the above method example. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. The module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0140] When dividing each function into modules according to its corresponding function. Figure 5 This is a functional unit block diagram of another advertising delivery device provided in an embodiment of this application. For example... Figure 5As shown, the advertising delivery device 500 includes: a receiving unit 501, configured to receive a query request message sent from the advertising platform server, the query request message including reference user tags, the reference user tags being adapted to the project features of the target property, the project features being used to characterize at least one of the following attributes of the target property: apartment type, location, and usage, the reference user tags being used to describe the user profile of the property; a response unit 502, configured to respond to the user query request message, query a preset original user set, and obtain device information of multiple target users whose user tags match the reference user tags, the original user set including the correspondence between user tags and user device information; and a sending unit 503, configured to send a query response message carrying the device information of the multiple target users to the advertising platform server.

[0141] In one possible embodiment, regarding receiving the query request message sent from the advertising platform server, the receiving unit 501 is specifically configured to: acquire at least one set of user data, the user data including user browsing behavior information and device information, the at least one set of user data corresponding to one user; perform tag prediction based on the at least one set of user browsing behavior information and a pre-trained user tag model to obtain the at least one type of user tag; and store the correspondence between the user tag and the user's device information, the at least one set of device information, and the at least one type of user tag to the original user set.

[0142] In one possible embodiment, in receiving the query request message sent from the advertising platform server, the receiving unit 501 is specifically used to: include the user browsing behavior information as: click operation, page dwell time, and page content information.

[0143] In one possible embodiment, regarding the query of a preset original user set, the response unit 502 is specifically configured to: match the reference user tag with multiple user tags stored in the original user set to determine a target user tag; and determine the device information of the multiple target users based on the correspondence between the user tag and the user's device information.

[0144] In one possible embodiment, in matching user tags stored in the original user set according to the reference user tags, the response unit 502 is specifically configured to: determine whether each user tag exists in the reference user tags; if so, determine that the currently processed user tag is the target user tag.

[0145] As can be seen, the other advertising delivery device provided in this application embodiment can receive and respond to query request messages sent by the advertising delivery platform server, and query the device information of target users whose user tags match the reference user tags in the original user set. This enables the rapid determination of user tags of target users and the acquisition of device information of these target users through the interaction of the two platform servers, thereby improving the efficiency and practicality of advertising delivery.

[0146] It should be noted that the advertising delivery device described in this embodiment is presented in the form of functional units. The term "unit" as used herein should be understood in the broadest possible sense, and the object used to implement the functions described in each "unit" may be, for example, an integrated circuit ASIC, a single circuit, a processor (shared, dedicated, or chipset) and memory for executing one or more software or solid-state programs, combinational logic circuits, and / or other suitable components that provide the above functions.

[0147] When using integrated units, such as Figure 6 As shown, Figure 6 This is a structural block diagram of an advertising delivery device provided in an embodiment of this application. Figure 6 In this document, the advertising delivery device 600 includes a processing module 602 and a communication module 601. The processing module 602 controls and manages the actions of the advertising delivery device, including steps such as the acquisition unit 401, the project feature determination unit 402, the reference user tag determination unit 403, the sending unit 404, the receiving unit 405, and the delivery unit 406, and / or other processes for executing the techniques described herein. The communication module 601 supports interaction between the advertising delivery device and other devices. Figure 6 As shown, the advertising delivery device may also include a storage module 603, which is used to store the program code and data of the data verification device.

[0148] The processing module 602 can be a processor or controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication module 601 can be a transceiver, RF circuitry, or a communication interface, etc. The storage module 603 can be a memory.

[0149] When using integrated units, such as Figure 7 As shown, Figure 7 This is a structural block diagram of another advertising delivery device provided in the embodiments of this application. Figure 7 In this document, the advertising delivery device 700 includes a processing module 702 and a communication module 701. The processing module 702 controls and manages the operation of the advertising delivery device, for example, the steps of the receiving unit 501, the response unit 502, and the sending unit 503, and / or other processes for executing the techniques described herein. The communication module 701 supports interaction between the advertising delivery device and other devices. Figure 7 As shown, the tagging processing device may further include a storage module 703, which is used to store the program code and data of the tagging processing device.

[0150] The processing module 702 can be a processor or controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication module 701 can be a transceiver, RF circuitry, or a communication interface, etc. The storage module 703 can be a memory.

[0151] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0152] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0153] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0154] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the 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.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and other division methods may exist in actual implementation; 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, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0156] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0157] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can be physically comprised separately, or two or more units can be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0158] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0159] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of the present invention, and various modifications and alterations can be made, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of the present invention.

Claims

1. An advertising placement method, characterized in that, Applied to an advertising platform server, the method includes: Obtain project information for the target property; The project characteristics of the target property are determined based on the project information of the target property, and the project characteristics are used to characterize at least one of the following attributes of the target property: unit type, location and use; Determining reference user tags that match the project features includes: obtaining a preset set of user tags, the set of user tags including the correspondence between user tags and the project features, the set of user tags including multiple user tags, the user tags being used to characterize at least one of the following features of a user: user attributes, geographic features, platform devices, property preferences, and content preferences; wherein, property preferences include property type preferences and property usage preferences; inputting each user tag and the project feature into a preset word vector generation model to obtain a first word vector corresponding to each user tag and a second word vector corresponding to each project feature; obtaining the similarity between each first word vector and the second word vector according to a preset calculation formula, the magnitude of the similarity being used to characterize the degree of correlation between the user tag and the project feature; and using the user tag with the highest correlation as the reference user tag, the reference user tag being a tag used to describe the user profile of the target property, determined by querying the preset set of user tags or calculating the correlation between the user tag and the project feature. Send a query request message carrying the reference user tag to the real estate platform server; The system receives a query response message from the real estate platform server in response to the query request message. The query response message carries device information of multiple target users, and the user tags of the multiple target users are matched with the reference user tags. Multiple advertisements are input into a pre-trained advertisement tagging model to obtain multiple advertisement tags, each of which corresponds to one or more advertisements; the correspondence between the multiple advertisement tags and advertisements is stored in a pre-created original advertisement set; Based on the reference user tags, a preset set of original advertisements is queried to obtain at least one target advertisement whose advertisement tags match the reference user tags. The original advertisement set includes the correspondence between the advertisement tags and the advertisements, and the multiple advertisement tags correspond one-to-one with the multiple user tags. The at least one target advertisement is determined to be an advertisement to be delivered. The advertisement for the target property is sent to the user devices of the multiple target users.

2. The method according to claim 1, characterized in that, The device information includes at least one of the following data: International Mobile Equipment Identity (IMEL), Identifier for Advertising (IDFA), and mobile phone number.

3. An advertising delivery device, characterized in that, The device, applied to an advertising platform server, includes: Acquisition Unit: Used to acquire project information for the target property; Project Feature Determination Unit: Used to determine the project features of the target property based on the project information of the target property, wherein the project features are used to characterize at least one of the following attributes of the target property: unit type, location, and use; The reference user tag determination unit is used to determine reference user tags that are compatible with the project features. This includes: obtaining a preset set of user tags, which includes a correspondence between user tags and the project features. The user tag set includes multiple user tags, each representing at least one of the following user characteristics: user attributes, geographic features, platform device, property preferences, and content preferences; wherein, property preferences include property type preferences and property usage preferences; inputting each user tag and the project feature into a preset word vector generation model to obtain a first word vector corresponding to each user tag and a second word vector corresponding to the project feature; obtaining the similarity between each first word vector and the second word vector according to a preset calculation formula, the magnitude of which represents the degree of correlation between the user tag and the project feature; and using the user tag with the highest correlation as the reference user tag, which is a tag used to describe the user profile of the target property, determined by querying the preset set of user tags or calculating the correlation between the user tag and the project feature. Sending unit: used to send a query request message carrying the reference user tag to the real estate platform server; Receiving unit: used to receive a query response message sent by the real estate platform server in response to the query request message, the query response message carrying device information of multiple target users, and the user tags of the multiple target users matching the reference user tags; Multiple advertisements are input into a pre-trained advertisement tagging model to obtain multiple advertisement tags, each of which corresponds to one or more advertisements; the correspondence between the multiple advertisement tags and advertisements is stored in a pre-created original advertisement set; the original advertisement set is queried based on the reference user tags to obtain at least one target advertisement whose advertisement tags match the reference user tags, the original advertisement set includes the correspondence between the advertisement tags and advertisements, and the multiple advertisement tags and multiple user tags correspond one-to-one; the at least one target advertisement is determined as an advertisement to be delivered; Delivery unit: Used to send advertisements for the target property to the user devices of the multiple target users.

4. An advertising platform server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in claim 1 or 2.

5. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in claim 1 or 2.

Images