CN114581138A - Advertisement putting method and related device - Google Patents

Abstract

The embodiment of the application provides an advertisement putting method and a related device, wherein the method comprises the following steps: acquiring project information of a target property, and determining project characteristics of the target property according to the project information; determining a reference user tag adapted to the item feature; sending an inquiry request message carrying the reference user tag to a property platform server, and receiving an inquiry response message sent by the property platform server in response to the inquiry request message, wherein the inquiry response message carries equipment information of a plurality of target users; transmitting an advertisement to user devices of the plurality of target users. By adopting the method and the device, the target user can be determined according to the project information of the target property, the matched advertisement can be directly sent to the equipment of the target user, the problem of low advertisement putting efficiency and conversion efficiency is solved, and the target crowd can be accurately and efficiently positioned and put in the advertisement.

Description

Advertising delivery method and related device

technical field

The present application relates to the field of computer technologies, and in particular, to an advertisement placement method and related devices.

Background technique

At present, with the development and progress of network technology, online advertising and advertising marketing have become the mainstream in the advertising field. The traditional use of various channels for large-scale advertising has gradually changed to targeting specific groups of people, thereby reducing the amount of advertising. cost of investment.

However, in the early stage of advertisement placement under the traditional model of locating target users by acquiring data, advertisers and operators cannot accurately describe the target user group portrait, resulting in poor advertising efficiency and conversion effect, and a lot of waste. time and cost.

SUMMARY OF THE INVENTION

The embodiments of the present application provide an advertisement delivery method and a related device, so as to provide the efficiency, convenience and practicability of advertisement delivery by a server.

In a first aspect, an embodiment of the present application provides an advertisement placement method, including:

Obtain project information of the target property;

Determine the project characteristics of the target real estate according to the project information of the target real estate, and the project characteristics are used to characterize at least one of the following attributes of the target real estate: house type, region and use;

determining a reference user tag adapted to the project feature, where the reference user tag is used to describe the user portrait of the target real estate;

sending a query request message carrying the reference user tag to the real estate platform server;

Receive a query response message sent from the real estate platform server in response to the query request message, the query response message carries the device information of multiple target users, and the user tags of the multiple target users match the reference user tags ;

An advertisement for the target property is sent to user devices of the plurality of target users.

In a second aspect, the embodiment of the present application also provides an advertisement placement method, including:

Receive a query request message sent from the advertising platform server, the query request message includes a reference user tag, and the reference user tag is adapted to the item feature of the target real estate, and the item feature is used to represent the following characteristics of the target real estate. At least one attribute: house type, region and purpose, the reference user tag is used to describe the user portrait of the target real estate;

In response to the user query request message, query a preset original user set to obtain device information of multiple target users whose user tags match the reference user tag, and the original user set includes the relationship between the user tag and the user's device information. the corresponding relationship;

In a third aspect, an embodiment of the present application further provides an advertisement delivery device, including:

Acquisition Unit: Project information used to acquire the target property;

Determining project characteristics unit: used to determine the project characteristics of the target real estate according to the project information of the target real estate, and the project characteristics are used to characterize at least one of the following attributes of the target real estate: house type, region and use;

Determining a reference user tag unit: used to determine a reference user tag adapted to the feature of the project, and the reference user tag is used to describe the user portrait of the target real estate;

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 from the real estate platform server in response to the query request message, the query response message carrying the device information of multiple target users, the user tags of the multiple target users and all The above reference user tag matches;

Delivery unit: used to send the advertisement of the target real estate to the user equipments of the multiple target users.

In a fourth aspect, an embodiment of the present application further provides an advertisement delivery device, including:

Receiving unit: used to receive a query request message sent from the advertising platform server, the query request message includes a reference user tag, and the reference user tag is adapted to the item feature of the target real estate, and the item feature is used to represent the Describe at least one of the following attributes of the target real estate: unit type, region and purpose, and the reference user tag is used to describe the user portrait of the real estate;

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 tag, where the original user set includes user tags and user tags. The corresponding relationship between the device information;

Sending unit: configured to send a query response message carrying the device information of the multiple target users to the advertisement platform server.

In a fifth aspect, an embodiment of the present application further provides an advertising platform server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer The program implements the steps of any of the methods of the first aspect as described above.

In a sixth aspect, an embodiment of the present application further provides a real estate platform server, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer The program implements the steps of any of the methods of the second aspect as described above.

In a seventh aspect, embodiments of the present application further provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements any one of the above-mentioned first aspect The method or the steps of any of the methods of the second aspect.

In an eighth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a computer program, and the computer program is operable to cause a computer to execute as described in the first aspect or the second aspect of the embodiment of the present application some or all of the steps. The computer program product may be a software installation package.

It can be seen that, in the embodiment of the present application, the advertising platform server first obtains the project information of the target real estate, then determines the project characteristics of the target real estate according to the project information, and then determines the reference user tag adapted to it according to the project characteristics, Then send the query response message carrying the reference user tag to the real estate platform server, receive the query response message sent by the real estate platform server due to the second response, and finally deliver the target user's device according to the device information of the target user carried in the query response message. Real estate related advertisements, in this way, different target groups can be determined according to different real estate projects, and the device information of users matching the target groups can be obtained to realize advertisement placement, which avoids relying on the experience of the staff to judge the intended group. This leads to the problems of low advertising efficiency and conversion rate, which improves the efficiency of advertising and the accuracy of targeting the target population, and reduces the investment cost paid by advertisers.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

1a is a schematic diagram of an advertisement delivery system provided by an embodiment of the present application;

FIG. 1b is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

FIG. 1c is a schematic structural diagram of a server provided by an embodiment of the present application;

FIG. 2 is a schematic flowchart of an advertisement delivery method provided by an embodiment of the present application;

3 is a schematic flowchart of another advertisement placement method provided by an embodiment of the present application;

4 is a block diagram of functional units of an advertisement delivery device provided by an embodiment of the present application;

5 is a block diagram of functional units of another advertisement delivery device provided by an embodiment of the present application;

6 is a structural block diagram of an advertisement delivery device provided by an embodiment of the present application;

FIG. 7 is a structural block diagram of another advertisement delivery apparatus provided by an embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of 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 in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

The terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish different objects, rather than 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 device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally also includes For other steps or units inherent to these processes, methods, products or devices.

Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor a separate or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

The related terms involved in this application are first introduced below.

Identifier For Advertising (IDFA): It can be understood as an advertisement ID, which is an advertisement identifier used to track users and can be used to open up advertisements between different apps.

International Mobile Equipment Identity number (IMEI): commonly known as "mobile phone serial number", it is used to identify each independent mobile phone in the GSM mobile network, which is equivalent to the ID number of the mobile phone.

In order to better understand the technical solutions of the embodiments of the present application, an advertisement delivery system and electronic devices that may be involved in the embodiments of the present application are first introduced below.

Please refer to FIG. 1a. FIG. 1a is a schematic diagram of an advertisement delivery system provided by an embodiment of the present application. As shown in the figure, the advertisement delivery system 100 includes an advertisement platform server 101, a real estate platform server 102, and an electronic device 103. The advertising platform shown in the figure The server 101 , the real estate platform server 102 and the electronic device 103 are respectively connected in communication. The electronic device 103 is used to browse the real estate information on the real estate platform server 102 , so that the real estate platform server 102 can record the browsing information behavior of the user corresponding to the electronic device 103 and the device information of the electronic device 103 . Then the real estate platform server 102 tags the browsing information behavior, obtains the user tag, and stores the obtained device information into a pre-created set. In this way, after the advertisement platform server 101 determines the reference user tag according to the item information of the target real estate, and sends the query request information carrying the reference user tag to the real estate platform server 102, the real estate platform server 102 can The reference user tag query set is used to obtain device information of the user matching the tag. Then, the device information of the target user is sent back to the advertising platform server 101, and finally, the advertising platform server 101 can send the advertisement to the electronic device 103 of the target user according to the device information of the target user. One advertisement platform server 101 may also correspond to multiple real estate platforms and multiple electronic devices at the same time, or the advertisement delivery system 100 includes multiple advertisement delivery servers, and each advertisement delivery server corresponds to one or more real estate platforms and electronic devices.

Specifically, for the structure of the electronic device shown in FIG. 1a, reference may be made to FIG. 1b, which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As shown in FIG. 1b, 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 above-mentioned memory 130, and are The configuration is performed by the processor 120 described above. For the structures of the advertisement platform server and the real estate platform server as shown in FIG. 1a, reference may be made to FIG. 1c, which is a schematic structural diagram of a server provided by an embodiment of the present application. As shown in FIG. 1c, the server 210 can implement the steps in the advertisement delivery method and another advertisement delivery method, and the server 210 includes a processor 220, a memory 230, a communication interface 240, and one or more programs 231, wherein , the one or more programs 231 are stored in the above-mentioned memory 230 and configured to be executed by the above-mentioned processor 220, and the one or more programs 231 include instructions for performing any step in the above-mentioned method embodiment.

Wherein, the communication interface may also be a transceiver, a transceiver circuit, etc., for supporting the communication between the first electronic device and other devices. The memory is used to store program codes and data of the terminal. The processor may also be a controller, for example, a central processing unit (Central Processing Unit, CPU), a general-purpose processor, a digital signal processor (Digital SignalProcessor, DSP), an application-specific integrated circuit (Application-Specific Integrated Circuit, ASIC), Field Programmable Gate Array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute the various exemplary logical blocks, units and circuits described in connection with this disclosure. The processor may 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, and the like.

The memory may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory. Volatile memory may be random access memory (RAM), which acts as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access Access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection dynamic random access Memory (synchlink DRAM, SLDRAM) and direct memory bus random access memory (directrambus RAM, DR RAM).

In a specific implementation, the processor is configured to perform any step performed by the electronic device in the above method embodiments, and when performing data transmission such as sending, the communication interface can be selectively invoked to complete corresponding operations.

At present, advertisers need to combine and filter the massive user tags provided by various platforms when they establish an advertisement placement plan in the early stage, and rely on the experience of the staff to determine the user tags of the target group. The problem caused by this is that the requirements for the staff are too high, and the restriction of advertising costs makes it impossible for advertisers to implement multiple advertising, and cannot guarantee the accuracy and comprehensiveness of the group corresponding to the selected tag combination, which consumes a lot of resource and inefficient.

In order to solve the above problems, an embodiment of the present application provides an advertisement placement method, which is applied to an advertisement placement server to place advertisements. The method determines the project characteristics of the target real estate by acquiring the project information of the target real estate, and then determines the adaptation The reference user tag for . Then, send a query request message carrying the reference user tag to the real estate server to obtain a query response message, and finally place advertisements according to the device information of the target user carried in the query response message, so as to achieve efficient and accurate positioning of the target population, and can be based on the information belonging to the target user. The device information of the users of the target group is used for advertising, which improves the conversion rate and efficiency of advertising.

The following describes the process of the advertisement placement method involved in the embodiment of the present application from the perspective of the method embodiment.

Please refer to FIG. 2. FIG. 2 is a schematic flowchart of an advertisement placement method provided by an embodiment of the present application, applied to an advertisement platform server, and the method includes the following steps:

Step 201, obtaining the project information of the target real estate;

Wherein, the project information of the target real estate refers to the relevant information of the real estate development project, and the project information may be the name, address, project purpose, land acquisition time, number of building floors, residential area, floor area ratio, etc. This embodiment There is no limitation here. By obtaining the project information of the target real estate, we can have a comprehensive understanding of the situation of the relevant real estate development projects, so as to obtain the aspects that the user pays attention to.

Step 202: Determine the project characteristics of the target real estate according to the project information of the target real estate;

Wherein, the project feature is used to characterize at least one of the following attributes of the target real estate: house type, region and purpose, that is, according to the project information of the target real estate, we can determine the geographical location, house type, purpose, property right where the target real estate is located Relevant attributes such as age and plot ratio are not limited in this embodiment.

Exemplarily, the item feature about the area can be expressed as "Shenzhen, city center area". The project characteristics of the apartment type can be expressed as "large apartment type" and "small apartment type", of which the definition standard of "large apartment type" can be determined from the size of the area. The combination is determined from the size of the volume ratio, for example, the volume ratio is below 1.0. The property right period mainly refers to the land occupied by the house in the target real estate project is 50 years or 70 years, which can also be based on the information about the target real estate project. to confirm. The characteristics of the project regarding the plot ratio can be expressed as "high plot ratio" and "low plot ratio", where the " plot ratio" is calculated by dividing the total floor area of the real estate project by the total land area. Generally, the higher the plot ratio , the lower the comfort level of residents, and vice versa, the higher the comfort level. The project characteristics about the use can mainly be expressed as "residential", "commercial", "office", "investment" to indicate the actual use of the real estate project after development.

Step 203, determining a reference user tag adapted to the project feature;

Wherein, the reference user tag is used to describe the user portrait of the target real estate.

In a possible embodiment, the determining a reference user tag adapted to the item feature includes: acquiring a preset user tag set, where the user tag set includes a correspondence between the user tag and the item feature; Using the item feature as a query identifier, query the user tag set to obtain a reference user tag corresponding to the item feature.

Wherein, by creating the preset user tag set in advance, and storing the corresponding relationship between the user tag and the item feature in the user tag set, it is equivalent to preparing a matching set in advance. After we obtain the item features of the target real estate, let the item features be matched to the corresponding user tags according to the corresponding relationship stored in the aggregated collection, and the reference user tags corresponding to the items can be directly found. The reference user tag is used to describe the user portrait of the target real estate.

Exemplarily, when the project feature of the target real estate is "location in Shenzhen, large apartment size, investment", according to the corresponding relationship between the project feature and the user label stored in the preset user label set, the query can be made according to the project feature. Go to the corresponding reference user label as "Shenzhen location, three-bedroom apartment type preference, and real estate type preference", and the reference user label depicts the user portrait of the target real estate.

It can be seen that, in this example, by acquiring a preset user tag set, and using the item feature as a query identifier, the user tag set is queried to obtain the reference user tag corresponding to the item feature, so convenient, Quickly and accurately depict the user portrait of the target real estate project, and follow-up to screen target users and obtain information.

In a possible embodiment, the determining a reference user tag adapted to the item feature includes: acquiring a preset user tag set, where the user tag set includes a plurality of user tags; determining the user tag set The degree of association between each user tag and the item feature; the user tag with the highest degree of association is used as the reference user tag.

Among them, the obtained item features may not be exactly the same as the reference user tag due to the different processing processes of the previous and subsequent steps, but the obtained item features can be similar to the words expressed by the reference user tag through a preset setting. In this way, when the reference user tag is determined according to the item features, the degree of association can be determined according to the similarity of words, and then the user tag with the highest association degree is selected as the reference user tag according to the number of item features. Wherein, the item feature may represent only one property item property, or may represent multiple property property item properties. Correspondingly, the user tag also has only one feature. For example, the form of the user tag may be: "A" or "A, B" or "A, B, C", etc., which is not limited in this embodiment. .

Exemplarily, the project features of the target real estate are "large apartment size, investment type, and location in Shenzhen". Since the types of user tags are abundant, as long as the user tag with the highest correlation is selected by the similarity of words, it can be located. User tags that can correctly describe the portrait of the target user group, such as "large apartment, investment type, location in Shenzhen".

It can be seen that, in this example, by acquiring the preset user tag set, the user tags corresponding to the classified users identified by the real estate platform server are obtained, and the degree of association between these user tags and item features is determined, and the user tag with the highest degree of association is selected by selecting the user tag with the highest degree of association. As a reference user tag to ensure the accuracy of the depicted user portrait, to ensure that the project characteristics of the target real estate best match the preferences of the user corresponding to the reference user tag, and to maintain the circulation and consistency of information between the advertising platform server and the real estate platform server. , which ensures the efficiency of advertisement delivery and the improvement of the conversion rate of subsequent advertisement delivery.

In a possible embodiment, the determining the degree of association between each user tag in the user tag set and the item feature includes: inputting the each user tag and the item feature into a preset In the word vector generation model, the first word vector corresponding to each user tag and the second word vector corresponding to the item feature are obtained; each first word vector and the second word vector are obtained according to a preset calculation formula Similarity between vectors, the size of the similarity is used to represent the degree of association between user tags and item features.

Among them, by inputting user labels and item features into the preset word vector generation model, the problem of text is transformed into a problem of vector space. Wherein, both the first word vector and the second word vector have general properties of vectors, that is, size and direction. The size of a vector is measured by its length. It can be understood that when the length ratio of the two vectors is closer to 1, the similarity of the words corresponding to the two vectors is higher; when the angle between the two vectors is smaller , the similarity of the words corresponding to the two vectors is higher; to sum up, when the similarity between the first word vector and the second word vector is proportional to the angle and length between the two vectors. Of course, the similarity needs to be calculated by weighting the length ratio and the included angle between the two vectors.

Exemplarily, when the weight of the length ratio is 0.5, the weight of the included angle is 0.5, and the obtained length ratio between the first word vector and the second word vector is 0.4, and the number of the included angle is 60 degrees, Similarity = 0.5×0.4+(0.5-0.5×1/3)=0.5333, and the result is four decimal places. According to the same weighting, the similarity of each first word vector and the second word vector is obtained, and the degree of association is represented according to the size of the similarity.

It can be seen that in this example, by obtaining the word similarity between user tags and item features to characterize the degree of association between them, the user tag with the highest degree of association can be selected according to the similarity, which can achieve The accuracy of the obtained user portrait of the target real estate depicted by the reference user tag ensures the efficiency and conversion rate of subsequent advertising.

In a possible embodiment, the user tag is used to represent at least one of the following characteristics of the user: user attributes, regional characteristics, platform equipment, real estate preferences, and content preferences; wherein, the real estate preferences include real estate type preferences and real estate preferences usage preference.

Wherein, the user attribute may include the user's age, gender, occupation, life stage, etc., the geographical feature may include the user's province, city, urban area or township, etc., and the platform device may include the mobile phone of the user equipment system, mobile phone brand and model, etc., the real estate preferences may include new house preference, second-hand house preference, apartment type preference, price preference, real estate use preference, etc. The content preference refers to the content of real estate information that users like to browse, and may include preference for real estate Policies interpretation, tendencies to buy houses, etc., are not limited in this embodiment.

It can be seen that in this example, users are classified in various aspects through their related behaviors on the real estate platform, and multiple user tags are obtained. Each user tag can represent the characteristics of the user, which can realize multi-angle analysis of users It can accurately identify users based on the analysis of user tags, so that users corresponding to user profiles can be obtained according to the reference user tags, which can accurately locate user groups and improve the conversion rate of advertisements.

Step 204, sending a query request message carrying the reference user tag to the real estate platform server;

Step 205: Receive a query response message sent from the real estate platform server in response to the query request message.

Wherein, the query response message carries the device information of multiple target users, and the user tags of the multiple target users match the reference user tag;

In a possible embodiment, in an application scenario where the advertising platform server determines the correlation between each user tag and the item feature, in the received message sent from the real estate platform server in response to the query request message After querying the response message, the method further includes: obtaining the number of target users according to the query response message; judging whether the number of target users is greater than a preset threshold; A supplementary query request message for a set supplementary user tag, where the supplementary user tag refers to a user tag whose relevancy degree is greater than the preset value except the user tag with the highest relevancy degree.

Among them, in specific application scenarios, some advertisers have certain delivery indicators in their advertisement delivery plans, such as the number of users who deliver. Then, in practice, there may be cases where the number of users corresponding to the reference user tag is less than the number of users targeted by the advertiser. Therefore, based on the determined association between each user tag and the item feature, the association is determined. User tags larger than a certain value are used to re-request the device information of the target user through these user tags to ensure that the number of users for advertising can meet the needs of advertisers, and to ensure that the characteristics of these users can also meet the real estate project to the greatest extent. related properties.

It can be seen that, in this embodiment, the number of target users is obtained by receiving the query response message to determine whether the preset threshold is satisfied, and when it is determined that the threshold is not satisfied, the compensation user tag is determined according to the preset correlation degree to re-query Obtaining additional users can not only ensure that advertisers can meet the needs of the number of users, but also ensure that the obtained users are user portraits that can match the real estate project as much as possible, avoiding the pursuit of the target number of users. This occurs when the conversion rate for ad serving decreases.

In a possible embodiment, the device information includes at least one of the following data: an international mobile equipment identity code IMEL, an advertisement identifier IDFA and a mobile phone number.

Among them, in the embodiment, the real estate platform server can acquire and collect the device information used by the user when the user browses the real estate information. One or a combination, etc. Of course, other types of device information may also be included, which is not limited in this embodiment.

Exemplarily, the user logs in to the real estate platform through the user's device, and responds to the real estate platform server to enter a webpage to browse real estate information. When the real estate platform server responds to the user equipment and obtains the information of the user equipment, the advertisement identification number IDFA can be preferentially collected for the device using the Apple system, and the mobile phone serial number IMEL can be preferentially collected for the device using the Android system. After collecting the device information, the real estate platform server stores the device information in a preset set.

It can be seen that, in this example, by sending a query request message to the real estate platform server to obtain the device information of the relevant user that matches the reference user tag, the device information can be of various types, ensuring that subsequent advertisements can be effectively delivered to the desired advertisements. In the user's device, the user can read the advertisement, which ensures the conversion rate of advertisement placement.

Step 206: Send advertisements of target real estate to user equipments of multiple target users.

In a possible embodiment, before the advertisement of the target real estate is sent to the user equipments of the multiple target users, the method further includes: querying a preset original advertisement set according to the reference user tag, Acquire at least one target advertisement whose advertisement label matches the reference user label; and determine the at least one target advertisement as an advertisement to be placed.

Wherein, the original advertisement set includes correspondence between advertisement tags and advertisements, and the multiple advertisement tags are in one-to-one correspondence with the multiple user tags.

Among them, before the advertisement is placed on the obtained user equipment of the target user, since the advertisement platform server may be entrusted by the advertiser to a third party to place the advertisement, the advertiser will give the advertisements a plurality of advertisements that he wants to prepare in advance. Platform server. Afterwards, the advertisement platform server queries the preset original advertisement set storing multiple advertisements according to the reference user tag, and according to the correspondence between the advertisement tags and advertisements stored in the set, and the advertisement tags corresponding to the multiple user tags , target advertisements matching the reference user tag can be obtained, and these target advertisements can be delivered to the corresponding users subsequently.

Exemplarily, when the reference user tag is "large apartment preference, new house preference, and preference for real estate policy interpretation", a corresponding advertisement is matched in the original advertisement set according to the reference user tag, and the advertisement label of the advertisement is "large apartment type". , New House, Real Estate Policy Interpretation", and finally determine the advertisement as an advertisement to be placed, and the advertisement placement platform server will place the advertisement on the target user according to the user equipment information obtained in advance.

It can be seen that, in this example, by querying the preset original advertisement set according to the reference user tag, the advertisements that meet the preferences of the user group are obtained for delivery, which can meet the needs of users, improve the user's experience, and allow advertisements The main method is to provide multiple advertisements to the advertising platform server in a similar way of creating advertisements according to user tags in advance, so that the advertising platform server can select the most suitable advertisements for delivery when targeting user groups with different preferences, which greatly increases the conversion rate of advertising delivery. and efficiency.

In a possible embodiment, before querying the preset original advertisement set according to the reference user tag, the method further includes: inputting the plurality of advertisements into a pre-trained advertisement tag model to obtain the plurality of advertisement labels, respectively corresponding to one or more advertisements; and storing the correspondence between the advertisement labels and the advertisements to a pre-created original advertisement set.

Among them, through the pre-trained advertising label model, the advertisements are classified with the advertisement labels corresponding to the user labels, and the correspondence between the advertisement labels and the advertisements is stored in the set that is created preferentially, so that the advertisements of the advertisements are placed. It can be completed in the early stage, and the selection of advertisements to be placed can be efficiently and conveniently performed after the start of the placement operation, and the pre-trained advertisement label model and the original advertisement set can be reused, so that whether new advertisements will be used in the follow-up. It is more convenient and practical to carry out labeling processing or a new round of advertising work.

Wherein, in the aspect of training the advertisement label model, training the advertisement label model includes: acquiring training data, the training data refers to the plurality of advertisements that have been labeled with advertisement labels; The model is trained until the accuracy of the label prediction of the advertisement by the mathematical model reaches a preset value; the advertisement label model is obtained by converging the mathematical model. The mathematical model may be any deep learning model, such as a gated recurrent unit (Gate Recurrent Unit, GRU) model, a recurrent neural network (Recurrent Neural Networks, RNN) and the like.

It can be seen that in this example, by pre-training the advertisement label model, the advertising platform server can classify advertisements and select appropriate advertisements for the corresponding users who refer to the user labels, which can not only improve the user's experience, but also meet the corresponding needs of these users.

In a possible embodiment, before the advertisement of the target real estate is sent to the plurality of target user equipments, the method further includes: acquiring the project introduction website of the target real estate, and querying the pre-defined website according to the reference user tag. set up a set of advertising materials, obtain at least one target image and at least one target copy whose material tag matches the reference user tag; The generation model obtains at least one target advertisement; and the at least one target advertisement is determined as an advertisement to be placed.

Wherein, the set of advertising materials includes a correspondence between material tags and copy, and a correspondence between material tags and pictures, and the multiple material tags are in one-to-one correspondence with the multiple user tags.

Further, before querying a preset set of advertising materials according to the reference user tag, the method further includes: inputting the plurality of pictures and a plurality of copy texts into a pre-trained material label model to obtain the The multiple material tags correspond to one or more pictures and one or more texts respectively; store the correspondence between the material tags and the pictures, and the correspondence between the material tags and the copy to a pre-created set of creatives.

Wherein, in the aspect of training the material labeling model, training the material labeling model includes: acquiring training data, where the training data refers to the plurality of pictures and the plurality of texts that have been labeled with material labels; The data performs model training on the specified mathematical model until the accuracy of the label prediction for the user by the mathematical model reaches a preset value; and the material label model is obtained by converging the mathematical model. Wherein, the mathematical model can be any deep learning model, such as GRU model, RNN and so on.

Exemplarily, there is a situation in which the advertising platform server is operated by the advertiser. In this case, after obtaining the reference user tag, the advertising platform server can use its own pre-created set of advertising materials to edit and generate target advertisements, and use pictures. Add copy and the project introduction URL of the target property to generate multiple advertisements.

It can be seen that in this example, through the pre-trained material labeling model, the advertising platform server can label the material it owns, and the determined label is consistent with the connected real estate advertising server. The effect of reproducing advertisements with reference to user tags greatly reduces the cost of advertisement placement, and there is no need to worry about the situation that the advertisements do not meet the preferences of the target user group.

It can be seen that in FIG. 2, a schematic flowchart of an advertisement placement method provided in the embodiment of the present application, by first obtaining the project information of the target real estate, then determining the project characteristics of the real estate according to the project information, and then matching to a suitable reference according to the project characteristics. User tag, and finally send a query request message to the corresponding real estate platform server to obtain the device information of the user that matches the reference user tag, and deliver to the target user according to the device information. In this way, through the layer-by-layer progression from project information to project features to matching the adapted reference user tags, the target users are locked according to the obtained reference user tags for delivery, and the project information can be completed only after obtaining the project information. The precise positioning of the target group of users does not require a lot of upfront costs, which greatly reduces the investment cost of advertisers, and by obtaining the user's device information, it is possible to accurately place advertisements on the target users, ensuring the conversion rate of advertisement placement.

Please refer to FIG. 3 . FIG. 3 is a schematic flowchart of another advertisement placement method provided by an embodiment of the present application, which provides an advertisement placement method, which is applied to a real estate platform server. The method includes the following steps:

Step 301, receiving a query request message sent from an advertising platform server;

Wherein, the query request message includes a reference user tag, and the reference user tag is adapted to the item characteristics of the target real estate, and the item characteristics are used to represent at least one of the following attributes of the target real estate: house type, region and use, The reference user tag is used to describe the user portrait of the target real estate;

In a 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, where the user data includes user browsing behavior information and device information, The at least one group of user data corresponds to one user respectively; the tag prediction is performed according to the at least one group of user browsing behavior information and the pre-trained user tag model, and the at least one type of user tag is obtained; the user tag and the user tag are stored. The corresponding relationship between the device information, the at least one group of device information, and the at least one type of user tag to the original user set.

Wherein, in the aspect of training the user label model, training the user label model includes acquiring training data, where the training data refers to the multiple groups of user browsing behavior information that have been labeled with user labels; The model performs model training until the accuracy of the label prediction for the user by the mathematical model reaches a preset value; the user label model is obtained by converging the mathematical model. Wherein, the mathematical model can be any deep learning model, such as GRU model, RNN and so on.

Among them, since the user will log in to the real estate platform to browse information or related web pages, the real estate platform server can record the relevant user data, including the user's browsing behavior information and the user's device information. After that, a user tag model is pre-trained, so that the model can tag users according to the user's browsing behavior information, so that the user tags can represent the user's various preferences, and then the user tags and the user's device information. The correspondence, at least one set of device information, and at least one type of user tag are stored in the original user set.

It can be seen that in this example, by obtaining the user's browsing behavior information and device information, each user whose information is recorded can be tagged, so that the user can be classified by extracting and processing user-related information, which is convenient In the follow-up, the relevant users can be selected and their device information can be obtained according to the tags, which shortens the time of advertisement placement operations. After tagging, the original user set can be reused according to different business needs, which greatly improves the efficiency of advertising. practicality.

In a possible embodiment, the user browsing behavior information includes: click operation, page stay time and page content information.

Exemplarily, if a user enters a real estate project page on the real estate platform, and he stays on this page for more than a preset time, such as 3 minutes, it is determined that the user is interested in the content of this webpage. By acquiring the content of the webpage that the user is interested in, the real estate platform server can determine the relevant preferences of the user according to the keywords of the webpage content, such as "investment real estate, new house preference, small apartment preference". And through the user information filling box set when entering the real estate platform, the platform server can also obtain the relevant attributes and geographical characteristics of the user, such as "30 years old, male, lawyer, city Huizhou".

It can be seen that in this example, the obtained user browsing behavior information can be converted into user tags by using various forms, and the user can be tagged and classified, so that the final advertisement delivered to the target user is consistent with Its demand, to ensure the conversion rate of advertising.

Step 302, in response 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;

Wherein, the original user set includes a correspondence between user tags and user device information.

In a possible embodiment, the querying the preset original user set includes: matching a plurality of user tags stored in the original user set according to the reference user tag, and determining a target user tag; The corresponding relationship between the device information of the users determines the device information of the multiple target users.

Wherein, the reference user tag may be one or more user tags, the target user tag is determined according to the reference user tag, and the corresponding relationship between the user tag and user equipment information stored in the set is obtained, and the corresponding user tag of each target user tag is obtained. Device information for one or more target users.

It can be seen that, in this example, by matching the user tags in the original user set according to the reference user tags, the device information of multiple desired target users can be obtained, which ensures the efficiency and convenience of advertisement placement.

In a possible embodiment, the matching user tags stored in the original user set according to the reference user tags includes: judging whether each user tag exists in the reference user tag; if so, determining The currently processed user tag is the target user tag.

Wherein, since the reference user tag corresponds to a plurality of 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 tag.

It can be seen that, in this example, by setting the label consistency between the advertisement platform server and the real estate platform server, the target user label can be determined and selected through a simple judgment process.

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

It can be seen that FIG. 3 is a schematic flowchart of another advertisement delivery method provided by the embodiment of the present application. By receiving and responding to the query request message sent by the advertisement delivery platform server, it is found in the original user set that the user tag matches the reference user tag. In this way, the user tags of the target users can be quickly determined through the interaction of the two platform servers, and the device information of these target users can be obtained, which improves the efficiency and practicability of advertising.

The following are apparatus embodiments of the present application. The apparatus embodiments of the present application and the method embodiments of the present application belong to the same concept, and are used to execute the methods described in the embodiments of the present application. For the convenience of description, the device embodiments of the present application only show the parts related to the device embodiments of the present application. If the specific technical details are not disclosed, please refer to the description of the method embodiments of the present application, which will not be repeated here.

An advertisement delivery device provided by an embodiment of the present application may be an advertisement platform server. Specifically, the advertisement delivery device is configured to execute the steps performed by the advertisement platform server in the above advertisement delivery method. The advertisement delivery apparatus provided by the embodiment of the present application may include modules corresponding to corresponding steps.

In this embodiment of the present application, the advertisement delivery device can be divided into functional modules according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware, or can be implemented in the form of software function modules. The division of modules in the embodiments of the present application is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

In the case where each functional module is divided according to each function, FIG. 4 is a block diagram showing the composition of functional units of an advertisement delivery apparatus provided by an embodiment of the present application. As shown in FIG. 4 , the advertisement delivery device 400 includes: an acquiring unit 401 for acquiring item information of a target real estate; a determining item feature unit 402 for determining the item characteristics of the target real estate according to the item information of the target real estate , the item feature is used to characterize at least one of the following attributes of the target real estate: house type, region and purpose; the determining reference user tag unit 403 is used to determine a reference user tag adapted to the item feature, the reference user tag The user tag is used to describe the user portrait of the target real estate; the sending unit 404 is used to send a query request message carrying the reference user tag to the real estate platform server; the receiving unit 405 is used to receive the response from the real estate platform server. The query response message sent by the query request message, the query response message carries the device information of multiple target users, and the user tags of the multiple target users match the reference user tags; The user equipment of the plurality of target users transmits the advertisement of the target real estate.

In a possible embodiment, in the aspect of determining the reference user tag adapted to the item feature, the determining reference user tag unit 403 is specifically configured to: acquire a preset user tag set, the user tag set Including the correspondence between user tags and item features; using the item features as a query identifier, query the user tag set to obtain the reference user tags corresponding to the item features.

In a possible embodiment, in the aspect of determining the reference user tag adapted to the item feature, the determining reference user tag unit 403 is specifically configured to: acquire a preset user tag set, the user tag set Including multiple user tags; determining the degree of association between each user tag in the user tag set and the item feature; and taking the user tag with the highest degree of association as the reference user tag.

In a possible embodiment, in the aspect of determining the degree of association between each user tag in the user tag set and the item feature, the determining reference user tag unit 403 is specifically configured to: Each user label and the item feature are input into the preset word vector generation model, and the first word vector corresponding to each user label and the second word vector corresponding to the item feature are obtained; The similarity between each of the first word vector and the second word vector, the size of the similarity is used to represent the level of the correlation between the user tag and the item feature.

In a possible embodiment, in the aspect of determining the reference user tag adapted to the item feature, the determining reference user tag unit 403 is specifically configured to: the user tag is used to represent at least one of the following users Features: user attributes, geographical features, platform equipment, real estate preferences, and content preferences; wherein, the real estate preferences include real estate house type preferences and real estate use preferences.

In a possible embodiment, in terms of receiving the query response message, the receiving unit 405 is specifically configured to: the device information includes at least one of the following data: an international mobile equipment identity code IMEL, an advertisement identifier IDFA and mobile number.

In a possible embodiment, in the aspect of sending the advertisement of the target real estate to the user equipments of the multiple target users, the delivery unit 406 is specifically configured to: query a preset original according to the reference user tag an advertisement set, obtaining at least one target advertisement whose advertisement tag matches the reference user tag, the original advertisement set includes the correspondence between advertisement tags and advertisements, the multiple advertisement tags and the multiple user tags one by one Corresponding; determining that the at least one target advertisement is an advertisement to be delivered.

In a possible embodiment, in the aspect of querying the preset original advertisement set according to the reference user tag, the delivering unit 406 is specifically configured to: input the plurality of advertisements into a pre-trained advertisement tag model , obtain the plurality of advertisement labels, and the plurality of advertisement labels correspond to one or more advertisements respectively; and store the correspondence between the advertisement labels and the advertisements to a pre-created original advertisement set.

It can be seen that, the advertisement delivery device provided by the embodiment of the present application can realize by first obtaining the project information of the target real estate, then determining the project characteristics of the real estate according to the project information, and then matching the appropriate reference user tags according to the project characteristics, and finally Send a query request message to the corresponding real estate platform server to obtain the device information of the user that matches the reference user tag, and deliver the target user according to the device information. In this way, through the layer-by-layer progression from project information to project features to matching the adapted reference user tags, the target users are locked according to the obtained reference user tags for delivery, and the project information can be completed only after obtaining the project information. The precise positioning of the target group of users does not require a lot of upfront costs, which greatly reduces the investment cost of advertisers, and by obtaining the user's device information, it is possible to accurately place advertisements on the target users, ensuring the conversion rate of advertisement placement.

The embodiment of the present application further provides another advertisement placing device, and the advertisement placing device may be a real estate platform server. Specifically, the advertisement placement device is configured to execute the steps described by the real estate platform server in the above advertisement placement method. The advertisement delivery apparatus provided by the embodiment of the present application may include modules corresponding to corresponding steps.

In this embodiment of the present application, the advertisement delivery device can be divided into functional modules according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware, or can be implemented in the form of software function modules. The division of modules in the embodiments of the present application is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

In the case where each functional module is divided according to each function, FIG. 5 is a block diagram of functional units of another advertisement delivery apparatus provided by the embodiment of the present application. As shown in FIG. 5 , the advertisement delivery device 500 includes: a receiving unit 501, configured to receive a query request message sent from the advertisement platform server, where the query request message includes a reference user tag, the reference user tag and the target real estate The project features are adapted to represent at least one of the following attributes of the target real estate: house type, region and use, and the reference user tag is used to describe the user portrait of the real estate; the response unit 502 is used to respond The user query request message queries a preset original user set to obtain device information of multiple target users whose user tags match the reference user tag, and the original user set includes the relationship between the user tag and the user's device information. A corresponding relationship; the sending unit 503 is configured to send a query response message carrying the device information of the multiple target users to the advertisement platform server.

In a possible embodiment, in terms of 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, where the user data includes user browsing behavior information and device information, the at least one group of user data corresponds to one user respectively; perform tag prediction according to the at least one group of user browsing behavior information and the pre-trained user tag model to obtain the at least one type of user tag; store the The correspondence between the user tag and the user's device information, the at least one group of device information, and the at least one type of user tag are to the original user set.

In a possible embodiment, in terms of receiving the query request message sent from the advertising platform server, the receiving unit 501 is specifically configured to: the user browsing behavior information includes: click operation, page stay time and page content information.

In a possible embodiment, in terms of querying the preset original user set, the response unit 502 is specifically configured to: determine according to the reference user tag matching a plurality of user tags stored in the original user set, and determine Target user tags; determine the device information of the multiple target users according to the correspondence between the user tags and the user's device information.

In a possible embodiment, in the aspect of matching the user tags stored in the original user set according to the reference user tag, the response unit 502 is specifically configured to: determine whether each user tag exists in the Refer to the user tag; if so, determine the currently processed user tag as the target user tag.

It can be seen that another advertisement delivery device provided by the embodiment of the present application can realize that by receiving and responding to the query request message sent by the advertisement delivery platform server, the target user whose user tag matches the reference user tag can be queried in the original user set. In this way, the user tags of target users can be quickly determined through the interaction of the two platform servers, and the device information of these target users can be obtained, which improves the efficiency and practicability of advertising.

It should be noted that the advertisement delivery apparatus described in this embodiment of the apparatus 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 by each "unit" may be, for example, an integrated circuit ASIC, a single circuit, for executing one or more software or solid state Program processors (shared, dedicated, or chipset) and memory, combinational logic circuits, and/or other suitable components that provide the functions described above.

In the case of using an integrated unit, as shown in FIG. 6 , FIG. 6 is a structural block diagram of an advertisement delivery apparatus provided by an embodiment of the present application. In FIG. 6 , the advertisement delivery apparatus 600 includes: a processing module 602 and a communication module 601 . The processing module 602 is used to control and manage the actions of the advertisement delivery device, for example, the steps of the acquiring unit 401, the determining item feature unit 402, the determining reference user tag unit 403, the sending unit 404, the receiving unit 405 and the delivering unit 406, and/ or other processes for performing the techniques described herein. The communication module 601 is used to support the interaction between the advertisement delivery initiating apparatus and other devices. As shown in FIG. 6 , the advertisement delivery apparatus may further include a storage module 603, and the storage module 603 is configured to store program codes and data of the data verification apparatus.

The processing module 602 may be a processor or a controller, such as a central processing unit (Central Processing Unit, CPU), a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), ASIC, FPGA or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logical blocks, modules and circuits described in connection with this disclosure. The processor may 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, and the like. The communication module 601 may be a transceiver, an RF circuit, a communication interface, or the like. The storage module 603 may be a memory.

In the case of using an integrated unit, as shown in FIG. 7 , FIG. 7 is a structural block diagram of another advertisement delivery apparatus provided by an embodiment of the present application. In FIG. 7 , the advertisement delivery apparatus 700 includes: a processing module 702 and a communication module 701 . The processing module 702 is used to control and manage the actions of the advertisement delivery device, eg, the steps of the receiving unit 501 , the responding unit 502 and the sending unit 503 , and/or other processes for performing the techniques described herein. The communication module 701 is used to support the interaction between the advertisement delivery apparatus and other devices. As shown in FIG. 7 , the labeling processing apparatus may further include a storage module 703, and the storage module 703 is configured to store program codes and data of the labeling processing apparatus.

The processing module 702 may be a processor or a controller, such as a central processing unit (Central Processing Unit, CPU), a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), ASIC, FPGA or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logical blocks, modules and circuits described in connection with this disclosure. The processor may 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, and the like. The communication module 701 may be a transceiver, an RF circuit, a communication interface, or the like. The storage module 703 may be a memory.

The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of 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 the present application are generated. The computer may be a general purpose computer, special purpose computer, computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server, or data center Transmission by wire or wireless to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server, a data center, or the like containing one or more sets of available media. The usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media. The semiconductor medium may be a solid state drive.

Embodiments of the present application further provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes the computer to execute part or all of the steps of any method described in the above method embodiments , the above computer includes electronic equipment.

Embodiments of the present application further provide a computer program product, where the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute any one of the method embodiments described above. some or all of the steps of the method. The computer program product may be a software installation package, and the computer includes an electronic device.

It should be understood that, in various embodiments of the present application, the size of the sequence numbers of the above-mentioned processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not be dealt with in the embodiments of the present application. implementation constitutes any limitation.

In the several embodiments provided in this application, it should be understood that the disclosed method, apparatus and system may be implemented in other manners. For example, the device embodiments described above are only illustrative; for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included individually, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional units.

The above-mentioned integrated units implemented in the form of software functional units can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM for short), Random Access Memory (RAM for short), magnetic disk or CD, etc. that can store program codes medium.

Although the present invention is disclosed above, the present invention is not limited thereto. Any person skilled in the art, without departing from the spirit and scope of the present invention, can easily think of changes or substitutions, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including the implementation of software and hardware. The methods are all within the protection scope of the present invention.

Claims (18)

1. An advertisement putting method is applied to an advertisement platform server, and the method comprises the following steps:

acquiring project information of a target property;

determining project characteristics of the target property according to the project information of the target property, wherein the project characteristics are used for representing at least one of the following attributes of the target property: house type, region and use;

determining a reference user tag adapted to the project characteristic, the reference user tag being used to describe a user representation of the target property;

sending a query request message carrying the reference user tag to a house 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 the device information of a plurality of target users, and the user tags of the plurality of target users are matched with the reference user tags;

sending an advertisement for the target property to user devices of the plurality of target users.

2. The method of claim 1, wherein determining a reference user tag that fits the item feature comprises:

acquiring a preset user tag set, wherein the user tag set comprises a corresponding relation between a user tag and a project characteristic;

and querying the user tag set by taking the item features as query identifiers to obtain reference user tags corresponding to the item features.

3. The method of claim 1, wherein determining a reference user tag that fits the item feature comprises:

acquiring a preset user tag set, wherein the user tag set comprises a plurality of user tags;

determining a degree of association between each user tag in the set of user tags and the item feature;

and taking the user label with the highest relevance as the reference user label.

4. The method of claim 3, wherein the determining a degree of association between each user tag in the set of user tags and the item feature comprises:

inputting each user label and the project feature into a preset word vector generation model to obtain a first word vector corresponding to each user label and a second word vector corresponding to the project feature;

and obtaining the similarity between each first word vector and each second word vector according to a preset calculation formula, wherein the similarity is used for representing the degree of association between the user label and the project characteristic.

5. The method of claim 1, wherein the user tag is used to characterize at least one of the following characteristics of the user: user attributes, regional characteristics, platform equipment, house property preferences and content preferences; wherein the property preferences include property household preferences and property usage preferences.

6. The method of claim 1, wherein the device information comprises at least one of the following data: international mobile equipment identity IMEL, advertisement identifier IDFA, and cell phone number.

7. The method of claim 1, wherein prior to said sending the advertisement for the target property to the user devices of the plurality of target users, the method further comprises:

inquiring a preset original advertisement set according to the reference user tags to obtain at least one target advertisement with the advertisement tags matched with the reference user tags, wherein the original advertisement set comprises a corresponding relation between the advertisement tags and the advertisements, and the advertisement tags are in one-to-one correspondence with the user tags;

and determining the at least one target advertisement as an advertisement to be delivered.

8. The method of claim 7, wherein prior to said querying a pre-set original set of advertisements from said reference user tags, said method further comprises:

inputting the multiple advertisements into a pre-trained advertisement label model to obtain multiple advertisement labels, wherein the multiple advertisement labels correspond to one or more advertisements respectively;

and storing the corresponding relation between the advertisement label and the advertisement to a pre-created original advertisement set.

9. An advertisement putting method is applied to a real estate platform server, and comprises the following steps:

receiving a query request message sent by the advertisement platform server, wherein the query request message comprises a reference user tag, the reference user tag is adapted to an item feature of a target property, and the item feature is used for characterizing at least one of the following attributes of the target property: a house type, a region and a purpose, the reference user tag is used for describing a user portrait of the target property;

responding to the user query request message, querying a preset original user set, and acquiring the device information of a plurality of target users with user tags matched with the reference user tags, wherein the original user set comprises the corresponding relation between the user tags and the device information of the users;

and sending a query response message carrying the equipment information of the plurality of target users to the advertisement platform server.

10. The method of claim 9, wherein querying the predetermined set of original users comprises:

matching a plurality of user tags stored in the original user set according to the reference user tag, and determining a target user tag;

and determining the equipment information of the target users according to the corresponding relation between the user tags and the equipment information of the users.

11. The method of claim 10, wherein the matching the user tags stored in the original user set according to the reference user tag comprises:

judging whether each user tag exists in the reference user tags or not;

and if so, determining that the currently processed user tag is the target user tag.

12. The method of claim 9, wherein prior to receiving the query request message from the advertising platform server, the method further comprises:

acquiring at least one group of user data, wherein the user data comprises user browsing behavior information and equipment information, and the at least one group of user data corresponds to one user respectively;

performing label prediction according to the at least one group of user browsing behavior information and a pre-trained user label model to obtain at least one type of user labels;

and storing the corresponding relation between the user tags and the equipment information of the users, the at least one group of equipment information and the at least one type of user tags into the original user set.

13. The method of claim 12, wherein the user browsing behavior information comprises: click operation, page dwell time and page content information.

14. An advertisement putting device, which is applied to an advertisement platform server, the device comprising:

an acquisition unit: the system comprises a database, a database and a database, wherein the database is used for storing project information of a target property;

determining item feature units: the project characteristic of the target property is determined according to the project information of the target property, and the project characteristic is used for representing at least one of the following attributes of the target property: house type, region and use;

determining a reference user tag unit: a reference user tag for determining a user representation that is adapted to the project characteristic, the reference user tag describing the target property;

a transmission unit: the system comprises a server, a property platform server and a database, wherein the server is used for sending a query request message carrying the reference user tag to the property platform server;

a receiving unit: the system comprises a real estate platform server, a reference user tag and a query response message, wherein the query response message is used for receiving the query response message sent by the real estate platform server in response to the query request message, the query response message carries equipment information of a plurality of target users, and user tags of the target users are matched with the reference user tag;

a releasing unit: for sending advertisements of the target property to user devices of the plurality of target users.

15. An advertisement putting device, characterized in that is applied to a house property platform server, the device includes:

a receiving unit: the system is used for receiving a query request message sent by the advertisement platform server, wherein the query request message comprises a reference user tag, the reference user tag is matched with an item feature of a target property, and the item feature is used for characterizing at least one of the following attributes of the target property: a house type, territory and purpose, the reference user tag being used to describe a user representation of a property;

a response unit: the system comprises a user query request message sending unit, a reference user tag sending unit, a user query request message sending unit, a user query unit and a user query unit, wherein the user query request message is used for responding to the user query request message, querying a preset original user set and obtaining device information of a plurality of target users matched with the user tag and the reference user tag, and the original user set comprises a corresponding relation between the user tag and the device information of the user;

a transmission unit: and the query response message carrying the equipment information of the target users is sent to the advertisement platform server.

16. An advertising platform server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method according to any one of claims 1 to 8.

17. A property platform server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method according to any of claims 9-13.

18. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-8 or 9-13.

Images