Advertising Placement Method, Device, Storage Medium and Electronic Device

Abstract

The present disclosure relates to an advertisement delivery method, apparatus, storage medium, and electronic device, which are used to deliver advertisements to more users while ensuring the user conversion rate and improving the advertisement delivery effect. The advertisement delivery method includes: delivering a target advertisement to a first user of a target delivery platform according to a preset targeted delivery strategy; if the user conversion rate corresponding to the target advertisement is less than a first preset conversion rate, determining a first user to be expanded who is similar to the first user among the users of the target delivery platform, and delivering the target advertisement to the first user to be expanded; if the user conversion rate corresponding to the target advertisement reaches a second preset conversion rate, determining a second user to be expanded who has not been delivered the target advertisement among the users of the target delivery platform, and delivering the target advertisement to the second user to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to an advertisement delivery method, device, storage medium, and electronic device. Background Art

[0002] With the continuous development of Internet technology, advertisement delivery has gradually shifted from offline to online, and more and more advertisements are delivered in various application programs or network platforms.

[0003] In related technologies, in order to improve the user conversion rate, a targeted advertisement delivery method is usually adopted. For example, the target audience users of an advertisement are first determined, and then the advertisement is delivered to the target audience users. Although the user conversion rate in the early stage of this method is relatively high, due to the limitation of the number of target audience users, the user conversion rate in the later stage cannot be guaranteed, thus affecting the advertisement delivery effect. Summary of the Invention

[0004] This Summary of the Invention section is provided to introduce concepts in a brief form, which will be described in detail in the following Detailed Implementation section. This Summary of the Invention section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides an advertisement delivery method, the method including:

[0006] Delivering a target advertisement to a first user of a target delivery platform according to a preset targeted delivery strategy;

[0007] If the user conversion rate corresponding to the target advertisement is less than a first preset conversion rate, determining, among the users of the target delivery platform, a first user to be expanded similar to the first user, and delivering the target advertisement to the first user to be expanded;

[0008] If the user conversion rate corresponding to the target advertisement reaches a second preset conversion rate, determining, among the users of the target delivery platform, a second user to be expanded who has not been delivered the target advertisement, and delivering the target advertisement to the second user to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

[0009] In a second aspect, the present disclosure provides an advertisement delivery device, the device including:

[0010] A first delivery module, configured to deliver a target advertisement to a first user of a target delivery platform according to a preset targeted delivery strategy;

[0011] A second delivery module, configured to, when the user conversion rate corresponding to the target advertisement is less than a first preset conversion rate, determine first users to be expanded who are similar to the first user among the users of the target delivery platform, and deliver the target advertisement to the first users to be expanded;

[0012] A third delivery module, configured to, when the user conversion rate corresponding to the target advertisement reaches a second preset conversion rate, determine second users to be expanded who have not been delivered the target advertisement among the users of the target delivery platform, and deliver the target advertisement to the second users to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

[0013] In a third aspect, the present disclosure provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processing device, the steps of the method described in the first aspect are implemented.

[0014] In a fourth aspect, the present disclosure provides an electronic device, including:

[0015] A storage device, on which a computer program is stored;

[0016] A processing device, configured to execute the computer program in the storage device to implement the steps of the method described in the first aspect.

[0017] By the above method, in the first stage, the target advertisement is delivered to the first user through a preset targeted delivery strategy, which can ensure the user conversion rate in the early stage of advertisement delivery. If the user conversion rate corresponding to the target advertisement is less than the first preset conversion rate, the target advertisement is delivered to the first users to be expanded who are similar to the first user, that is, in the second stage, targeted volume expansion delivery is performed for specific users based on the targeted delivery strategy, and the target advertisement can be delivered to more users while ensuring the user conversion rate. After that, if the user conversion rate corresponding to the target advertisement reaches the second preset conversion rate, the target advertisement can be delivered to the second users to be expanded who have not been delivered the target advertisement, that is, in the third stage, after a certain user conversion rate is reached, general delivery of the advertisement is performed to further deliver the target advertisement to more users and ensure the user conversion rate in the later stage of advertisement delivery. Thus, the advertisement can be delivered to more users while ensuring the user conversion rate, improving the advertisement delivery effect.

[0018] Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and that the original elements and elements are not necessarily drawn to scale. In the drawings:

[0020] Figure 1 is a flowchart of an advertising placement method shown according to an exemplary embodiment of the present disclosure;

[0021] Figure 2 is a schematic diagram of the process of targeted volume expansion in an advertising placement method shown according to an exemplary embodiment of the present disclosure;

[0022] Figure 3 is a schematic diagram of the process of determining the user feature vectors of multiple first users in an advertising placement method shown according to an exemplary embodiment of the present disclosure;

[0023] Figure 4 is a block diagram of an advertising placement device shown according to an exemplary embodiment of the present disclosure;

[0024] Figure 5 is a block diagram of an electronic device shown according to an exemplary embodiment of the present disclosure. Detailed Description

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be understood that the various steps recited in the method embodiments of the present disclosure can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0027] As used herein, the term "including" and its variants are open-ended, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. Additionally, it should be noted that the modification of "one" and "multiple" mentioned in this disclosure is illustrative rather than restrictive. Those skilled in the art should understand that unless clearly specified otherwise in the context, it should be understood as "one or more".

[0029] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0030] As described in the background art, in the related art, in order to improve the user conversion rate, the method of targeted advertising is usually adopted. For example, first determine the target audience users of the advertisement, and then target the advertisement to the target audience users. The inventors have found that although the user conversion rate is relatively high in the early stage of this method, due to the limitation of the target audience users, it is impossible to guarantee the user conversion rate in the later stage, thus affecting the advertising effect. In addition, the inventors have also found that the method of blanket advertising, which advertises to all users, although there is no limit on the number of users to whom the advertisement is delivered, cannot guarantee the user conversion rate, thus affecting the advertising effect.

[0031] In view of this, this disclosure provides a new advertising method to deliver advertisements to more users while ensuring the user conversion rate and improving the advertising effect.

[0032] First of all, it should be understood that the user information or user data mentioned in the embodiments of this disclosure are all obtained after the user's authorization. For example, during the process of the user using the application, the user is prompted through pop-up windows or other means whether to authorize the application to obtain the user's own user information for data analysis, and the user is asked which user information of the user himself / herself the application is allowed to obtain. After obtaining the user's confirmation, the user's user information can be used in the advertising method provided by the embodiments of this disclosure.

[0033] Figure 1 is a flowchart of an advertising method shown according to an exemplary embodiment of this disclosure. Refer to Figure 1 , the advertising method includes:

[0034] Step 101, deliver a target advertisement to the first users of the target delivery platform according to a preset targeted delivery strategy.

[0035] Exemplarily, the target delivery platform can be various types of application programs or network platforms, and the embodiments of the present disclosure do not limit this. The preset targeted delivery strategy can be used to deliver advertisements to specific groups of people on the target delivery platform. This targeted delivery strategy can be preset according to the content of the target advertisement. For example, if the target advertisement is an advertisement for office supplies, the targeted delivery strategy can be set to deliver the advertisement to the workplace population, that is, the first user can be the workplace population. It should be understood that the embodiments of the present disclosure do not limit the specific content of the targeted delivery strategy.

[0036] By using the preset targeted delivery strategy for advertisement delivery, the number of users to whom the advertisement is delivered is limited. Therefore, although a relatively high user conversion rate can be achieved in the early stage of advertisement delivery, the user conversion rate cannot be guaranteed in the later stage of advertisement delivery, thus affecting the advertisement delivery effect. Therefore, in the embodiments of the present disclosure, steps 102 and 103 can be continued.

[0037] Step 102, if the user conversion rate corresponding to the target advertisement is less than the first preset conversion rate, then among the users on the target delivery platform, determine the first user to be expanded who is similar to the first user, and deliver the target advertisement to the first user to be expanded.

[0038] Exemplarily, the first preset conversion rate can be set according to the actual situation. For example, the first preset conversion rate can be set to 30%, etc., and the embodiments of the present disclosure do not limit this. Alternatively, the change in the user conversion rate within a preset time interval can be compared first. If the user conversion rate in the second preset time interval is reduced by 30% compared to the user conversion rate in the first preset time interval, then it is determined that the user conversion rate corresponding to the target advertisement is less than the first preset conversion rate.

[0039] In the embodiments of the present disclosure, if the user conversion rate corresponding to the target advertisement is less than the first preset conversion rate, then among the users on the target delivery platform, the first user to be expanded who is similar to the first user can be determined, and the target advertisement can be delivered to the first user to be expanded. Thus, based on the first user, the target advertisement is delivered in a targeted and expanded manner, and the advertisement can be delivered to more users, thereby continuously ensuring the user conversion rate corresponding to the target advertisement and improving the advertisement delivery effect.

[0040] Step 103, if the user conversion rate corresponding to the target advertisement reaches the second preset conversion rate, then among the users on the target delivery platform, determine the second user to be expanded who has not been delivered the target advertisement, and deliver the target advertisement to the second user to be expanded. Wherein the second preset conversion rate is greater than the first preset conversion rate.

[0041] Exemplarily, the second preset conversion rate can be set according to the actual situation, and the embodiments of the present disclosure do not limit this, as long as the second preset conversion rate is greater than the first preset conversion rate.

[0042] Among possible ways, the second preset conversion rate can be determined in the following manner: First, obtain the target user conversion rate corresponding to the pre-trained advertisement placement model, and then determine the target user conversion rate as the second preset conversion rate. Among them, the target user conversion rate is the user conversion rate predicted by the advertisement placement model during the training process of the advertisement placement model when the difference between the predicted user conversion rate of the sample advertisement by the advertisement placement model and the actual user conversion rate of the sample advertisement is less than the preset difference.

[0043] It should be understood that the target user conversion rate is the user conversion rate when the advertisement placement model can stably predict. Taking this target user conversion rate as the second preset conversion rate, when the user conversion rate corresponding to the target advertisement reaches the second preset conversion rate, it indicates that the user conversion rate corresponding to the target advertisement has reached the user conversion rate that the advertisement placement model can predict, and the effect of the targeted expansion placement method on improving the user conversion rate is limited. In this case, advertisement general placement can be performed, that is, the target advertisement can be placed to the second target expansion users who have not been placed with the target advertisement, so as to further place the target advertisement to more users, continuously ensure the user conversion rate of the target advertisement, and improve the advertisement placement effect.

[0044] Through the above method, in the first stage, the target advertisement is placed to the first users through the preset targeted placement strategy, which can ensure the user conversion rate in the early stage of advertisement placement. If the user conversion rate corresponding to the target advertisement is less than the first preset conversion rate, the target advertisement is placed to the first target expansion users similar to the first users, that is, in the second stage, targeted expansion placement is performed for specific users based on the targeted placement strategy, which can place the target advertisement to more users while ensuring the user conversion rate. After that, if the user conversion rate corresponding to the target advertisement reaches the second preset conversion rate, the target advertisement can be placed to the second target expansion users who have not been placed with the target advertisement, that is, in the third stage, advertisement general placement is performed after reaching a certain user conversion rate to further place the target advertisement to more users and ensure the user conversion rate in the later stage of advertisement placement.

[0045] After testing, compared with the single advertisement fixed placement method, the advertisement placement method provided by the present disclosure can increase the user conversion rate by 30%, that is, the advertisement placement method provided by the present disclosure can ensure the user conversion rate throughout the advertisement placement cycle and improve the advertisement placement effect.

[0046] To enable those skilled in the art to better understand the advertisement placement method provided by the present disclosure, the above steps will be described in detail with examples below.

[0047] Among possible ways, determining a first user to be expanded who is similar to the first user may be: determining the user feature vector of the first user, and determining the user feature vectors of each other user among the users on the target delivery platform except the first user, and then for each other user, determining the similarity between the user feature vector of the first user and the user feature vector of the other user. If the similarity is greater than or equal to a preset similarity, then determine the other user as the first user to be expanded who is similar to the first user.

[0048] Exemplarily, the user feature vector may represent user information and / or content that the user is interested in in the form of a vector. For example, the user information and / or content that the user is interested in of the first user may be input into an independent feature extraction model to extract the user feature vector of the first user. Similarly, the user information and / or content that the user is interested in of other users may be input into the feature extraction model to extract the user feature vectors of other users.

[0049] In other possible ways, the user feature vectors of the first user and other users may also be extracted through the user-side network in the advertisement delivery model. Exemplarily, the advertisement delivery model may be first trained based on the user delivery data and user conversion data of other advertisements delivered on the target delivery platform, and then through the user-side network in the trained advertisement delivery model, the user feature vector of the first user and the user feature vectors of each other user among the users on the target delivery platform corresponding to the target advertisement except the first user are determined. Among them, the advertisement delivery model includes a user-side network and an advertisement-side network. The user-side network is used to extract the corresponding user feature vector based on the input user information, and the advertisement-side network is used to extract the corresponding advertisement feature vector based on the input advertisement information.

[0050] Exemplarily, the advertisement delivery model may be a two-tower model such as DeepFM, etc., and the embodiments of the present disclosure do not limit this. The user delivery data refers to the user information data of the users to whom other advertisements are delivered, and the user conversion data refers to the user information data of the users who have successfully converted among the users to whom other advertisements are delivered. Training the advertisement delivery model through the user delivery data and user conversion data of other advertisements delivered on the target delivery platform can enable the user-side network of the advertisement delivery model to have the ability to extract user feature vectors. Subsequently, inputting the user information of the first user into the advertisement delivery model can obtain the Embedding output by the user-side network in the advertisement delivery model, that is, the user feature vector of the first user can be obtained. Similarly, the user information of other users can be input into the advertisement delivery model to obtain the user feature vector Embedding output by the user-side network, that is, the user feature vectors of other users can be obtained. Thus, the user feature vector of the first user and the user feature vectors of other users can be obtained through the user-side network of the advertisement delivery model.

[0051] Alternatively, in a possible way, the user feature vectors of all users of the target delivery platform can be pre-determined through the user-side network of the advertising delivery model, and then the user feature vectors of each user can be saved. For example, the user feature vector of the first user can be saved through the IndexService data service, and the user feature vectors of other users except the first user can be saved through the Abase database. Then, with reference to Figure 2 , when the present disclosure is specifically implemented, in response to the user traffic obtained from the target delivery platform, the user feature vector of the first user can be obtained from the IndexService data service, and the user feature vectors of other users can be obtained from the Abase database. Then, the similarity can be calculated based on the user feature vector of the first user and the user feature vectors of other users, so as to perform targeted expansion delivery of the target advertisement.

[0052] Among them, to determine the similarity between the user feature vector of the first user and the user feature vectors of other users, for example, the distance between the user feature vector of the first user and the user feature vectors of other users can be calculated. The present disclosure embodiments do not limit the calculation method of the similarity between vectors.

[0053] In a possible way, if there are multiple first users, the user feature vectors of the multiple first users can be first fitted through a preset feature fitting model to obtain a target user feature vector for representing the common features of the multiple first users, and then the similarity between the target user feature vector and the user feature vectors of other users can be determined.

[0054] Exemplarily, the feature fitting model can be any model capable of performing feature vector fitting, such as an LR (Logistic Regression) model, etc. The present disclosure embodiments do not limit this. When there are multiple first users, determining the first user to be expanded through the similarity between the user feature vector of a certain first user and the user feature vectors of other users may result in the situation that the first user to be expanded has a high similarity only with that first user, but a low similarity with the remaining first users, thus affecting the effect of targeted expansion delivery. In the present disclosure embodiments, in order to improve the effect of targeted expansion delivery, the user feature vectors of the multiple first users can be first fitted through a preset feature fitting model to obtain a target user feature vector for representing the common features of the multiple first users, and then the similarity between the target user feature vector and the user feature vectors of other users can be determined.

[0055] For example, with reference to Figure 3, after obtaining the user feature vectors based on multiple first users, store them in the Abase database, and then obtain the user feature vectors of the multiple first users from the Abase database. After that, use the LR model to perform feature fitting on the user feature vectors of the multiple first users to obtain a target user feature vector representing the common features of the multiple first users, and then store the target user feature vector in the IndexService data service. After that, the target user feature vector can be obtained from the IndexService data service for similarity calculation.

[0056] After obtaining the similarity between the user feature vector of the first user and the user feature vectors of other users, it is possible to determine whether the other users are first to-be-expanded users similar to the first user according to the numerical relationship between the similarity and the preset similarity. Among them, if the similarity is greater than or equal to the preset similarity, it means that the user information or the content of interest of the other user is more similar to that of the first user, so it can be determined that the other user is a first to-be-expanded user similar to the first user. On the contrary, if the similarity is less than the preset similarity, it means that the user information or the content of interest of the other user is quite different from that of the first user, so the other user is not determined as a first to-be-expanded user similar to the first user.

[0057] Exemplarily, the preset similarity can be set according to the actual situation, and the embodiments of the present disclosure do not limit this. It should be understood that by setting the value of the preset similarity, the number of first to-be-expanded users can be controlled. For example, the larger the preset similarity, the fewer users may satisfy being greater than or equal to the preset similarity, that is, the fewer first to-be-expanded users. On the contrary, the smaller the preset similarity, the more users may satisfy being greater than or equal to the preset similarity, that is, the more first to-be-expanded users.

[0058] In a possible way, when the user conversion rate corresponding to the target advertisement does not reach the second preset conversion rate, more to-be-expanded users can be obtained by controlling the preset similarity, so as to ensure the user conversion rate. Exemplarily, after the target advertisement is delivered to the first to-be-expanded user, if the user conversion rate of the target advertisement does not reach the second preset conversion rate, the preset similarity can be reduced to obtain a target similarity, and third to-be-expanded users who have not received the target advertisement are determined among the users of the target delivery platform. The similarity between the user feature vector of the first user and the user feature vector of each third to-be-expanded user is determined, and then for each third to-be-expanded user, if the similarity between the user feature vector of the first user and the user feature vector of the third to-be-expanded user is greater than or equal to the target similarity, the target advertisement is delivered to the third to-be-expanded user.

[0059] It should be understood that when the user conversion rate corresponding to the target advertisement fails to reach the second preset conversion rate, it indicates that the user conversion rate corresponding to the target advertisement can still be significantly improved. Therefore, based on the targeted placement strategy, targeted expansion placement can continue to be carried out for the specific users (i.e., the first users) targeted, that is, to determine the third group of users to be expanded for the placement of the target advertisement. If the user conversion rate of the target advertisement still fails to reach the second preset conversion rate after the target advertisement is placed for the third group of users to be expanded, the preset similarity can be reduced again to obtain a new target similarity, and then the above process can be repeated until the user conversion rate of the target advertisement reaches the second preset conversion rate.

[0060] Through any of the above advertisement placement methods, in the first stage, the target advertisement is targeted to the first users through the preset targeted placement strategy, which can ensure the user conversion rate in the early stage of advertisement placement. If the user conversion rate corresponding to the target advertisement is less than the first preset conversion rate, the target advertisement is placed for the first group of users to be expanded who are similar to the first users. That is, in the second stage, targeted expansion placement is carried out for the specific users targeted by the targeted placement strategy, and the target advertisement can be placed for more users while ensuring the user conversion rate. After that, if the user conversion rate corresponding to the target advertisement reaches the second preset conversion rate, the target advertisement can be placed for the second group of users to be expanded who have not been placed with the target advertisement. That is, in the third stage, after a certain user conversion rate is reached, general advertisement placement is carried out to further place the target advertisement for more users and ensure the user conversion rate in the later stage of advertisement placement. Thus, the advertisement can be placed for more users while ensuring the user conversion rate, and the advertisement placement effect can be improved.

[0061] Based on the same inventive concept, an embodiment of the present disclosure further provides an advertisement placement device. The advertisement placement device can become part or all of an electronic device in a manner of software, hardware, or a combination of both. Referring to Figure 4 , the advertisement placement device 400 may include:

[0062] A first placement module 401, configured to place a target advertisement for a first user on a target placement platform according to a preset targeted placement strategy;

[0063] A second placement module 402, configured to, when the user conversion rate corresponding to the target advertisement is less than the first preset conversion rate, determine a first group of users to be expanded who are similar to the first user among the users on the target placement platform, and place the target advertisement for the first group of users to be expanded;

[0064] A third placement module 403, configured to, when the user conversion rate corresponding to the target advertisement reaches the second preset conversion rate, determine a second group of users to be expanded who have not been placed with the target advertisement among the users on the target placement platform, and place the target advertisement for the second group of users to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

[0065] Optionally, the second delivery module 402 is configured to:

[0066] Determine the user feature vector of the first user, and determine the user feature vector of each other user among the users of the target delivery platform except the first user;

[0067] For each of the other users, determine the similarity between the user feature vector of the first user and the user feature vector of the other user. When the similarity is greater than or equal to a preset similarity, determine the other user as the first user to be expanded who is similar to the first user.

[0068] Optionally, the apparatus 400 further includes:

[0069] A training module, configured to train an advertisement delivery model based on the user delivery data and user conversion data of other advertisements delivered on the target delivery platform. The advertisement delivery model includes a user-side network and an advertisement-side network. The user-side network is configured to extract a corresponding user feature vector based on the input user information, and the advertisement-side network is configured to extract a corresponding advertisement feature vector based on the input advertisement information;

[0070] The second delivery module 402 is configured to:

[0071] Through the user-side network in the trained advertisement delivery model, determine the user feature vector of the first user and the user feature vector of each other user among the users of the target delivery platform corresponding to the target advertisement except the first user.

[0072] Optionally, the apparatus 400 further includes:

[0073] A first determination module, configured to, after delivering the target advertisement to the first user to be expanded, when the user conversion rate of the target advertisement does not reach the second preset conversion rate, reduce the preset similarity to obtain a target similarity, and determine a third user to be expanded who has not been delivered the target advertisement among the users of the target delivery platform, and determine the similarity between the user feature vector of the first user and the user feature vector of each third user to be expanded;

[0074] A fourth delivery module, configured to, for each of the third users to be expanded, when the similarity between the user feature vector of the first user and the user feature vector of the third user to be expanded is greater than or equal to the target similarity, deliver the target advertisement to the third user to be expanded.

[0075] Optionally, the apparatus 400 further includes:

[0076] A fitting module, configured to, after determining the user feature vectors of the first users, when there are multiple first users, fit the user feature vectors of the multiple first users through a preset feature fitting model to obtain a target user feature vector for characterizing the common features of the multiple first users;

[0077] The second delivery module 402 is configured to:

[0078] Determine the similarity between the target user feature vector and the user feature vectors of the other users.

[0079] Optionally, the second preset conversion rate is determined by the following module:

[0080] An acquisition module, configured to acquire the target user conversion rate corresponding to a pre-trained advertisement delivery model, where the target user conversion rate is the user conversion rate predicted by the advertisement delivery model during the training process of the advertisement delivery model when the difference between the predicted user conversion rate of the sample advertisement by the advertisement delivery model and the actual user conversion rate of the sample advertisement is less than a preset difference;

[0081] A second determination module, configured to determine the target user conversion rate as the second preset conversion rate.

[0082] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0083] Based on the same inventive concept, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of any of the above advertisement delivery methods are implemented.

[0084] Based on the same inventive concept, an embodiment of the present disclosure further provides an electronic device, including:

[0085] A memory, on which a computer program is stored;

[0086] A processor, configured to execute the computer program in the memory to implement the steps of any of the above advertisement delivery methods.

[0087] Next, referring to Figure 5 , which shows a schematic structural diagram of an electronic device 500 suitable for implementing an embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.Figure 5 The illustrated electronic device is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present disclosure.

[0088] As Figure 5 shown, the electronic device 500 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 501, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0089] Generally, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 5 the electronic device 500 with various devices is shown, it should be understood that it is not required to implement or include all the shown devices. Instead, more or fewer devices may be implemented or included.

[0090] Specifically, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above functions defined in the methods of the embodiments of the present disclosure are executed.

[0091] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0092] In some embodiments, communication can be carried out using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0093] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; or it can exist separately and not be assembled into the electronic device.

[0094] The above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: deliver a target advertisement to a first user of a target delivery platform according to a preset targeted delivery strategy; if the user conversion rate corresponding to the target advertisement is less than a first preset conversion rate, determine a first user to be expanded, who is similar to the first user, among the users of the target delivery platform, and deliver the target advertisement to the first user to be expanded; if the user conversion rate corresponding to the target advertisement reaches a second preset conversion rate, determine a second user to be expanded, who has not received the target advertisement, among the users of the target delivery platform, and deliver the target advertisement to the second user to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

[0095] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that, in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0097] The modules involved in the embodiments of the present disclosure can be implemented in software or in hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0098] The functions described above herein can be performed, at least in part, by one or more hardware logic components. By way of example, and without limitation, the types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on a chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0099] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0100] According to one or more embodiments of the present disclosure, Example 1 provides an advertising placement method, including:

[0101] Delivering a target advertisement to a first user of a target delivery platform according to a preset targeted delivery strategy;

[0102] If the user conversion rate corresponding to the target advertisement is less than a first preset conversion rate, then among the users of the target delivery platform, determining a first user to be expanded similar to the first user, and delivering the target advertisement to the first user to be expanded;

[0103] If the user conversion rate corresponding to the target advertisement reaches a second preset conversion rate, then among the users of the target delivery platform, determining a second user to be expanded to whom the target advertisement has not been delivered, and delivering the target advertisement to the second user to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

[0104] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, where determining, among the users of the target delivery platform, a first user to be expanded similar to the first user includes:

[0105] Determine the user feature vector of the first user, and determine the user feature vector of each other user among the users of the target delivery platform except the first user;

[0106] For each of the other users, determine the similarity between the user feature vector of the first user and the user feature vector of the other user. If the similarity is greater than or equal to a preset similarity, determine that the other user is a first user to be expanded similar to the first user.

[0107] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 2, and the method further includes:

[0108] Train an advertisement delivery model based on the user delivery data and user conversion data of other advertisements delivered on the target delivery platform. The advertisement delivery model includes a user-side network and an advertisement-side network. The user-side network is used to extract a corresponding user feature vector based on the input user information, and the advertisement-side network is used to extract a corresponding advertisement feature vector based on the input advertisement information;

[0109] The step of determining the user feature vector of the first user and determining the user feature vector of each other user among the users of the target delivery platform except the first user includes:

[0110] Through the user-side network in the trained advertisement delivery model, determine the user feature vector of the first user and the user feature vector of each other user among the users of the delivery platform corresponding to the target advertisement except the first user.

[0111] According to one or more embodiments of the present disclosure, Example 4 provides the method of Example 2. After delivering the target advertisement to the first user to be expanded, the method further includes:

[0112] If the user conversion rate of the target advertisement does not reach the second preset conversion rate, reduce the preset similarity to obtain a target similarity, and determine a third user to be expanded who has not received the target advertisement among the users of the target delivery platform, and determine the similarity between the user feature vector of the first user and the user feature vector of each third user to be expanded;

[0113] For each of the third users to be expanded, if the similarity between the user feature vector of the first user and the user feature vector of the third user to be expanded is greater than or equal to the target similarity, deliver the target advertisement to the third user to be expanded.

[0114] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 2. After determining the user feature vector of the first user, the method further includes:

[0115] If there are multiple first users, a target user feature vector for characterizing the common features of the multiple first users is obtained by fitting the user feature vectors of the multiple first users through a preset feature fitting model;

[0116] The determining the similarity between the user feature vector of the first user and the user feature vectors of other users includes:

[0117] Determining the similarity between the target user feature vector and the user feature vectors of other users.

[0118] According to one or more embodiments of the present disclosure, Example 6 provides the method according to any one of Examples 1-5. The second preset conversion rate is determined in the following manner:

[0119] Obtaining the target user conversion rate corresponding to a pre-trained advertisement placement model, where the target user conversion rate is the user conversion rate predicted by the advertisement placement model during the training process of the advertisement placement model when the difference between the predicted user conversion rate of the sample advertisement by the advertisement placement model and the actual user conversion rate of the sample advertisement is less than a preset difference;

[0120] Determining the target user conversion rate as the second preset conversion rate.

[0121] According to one or more embodiments of the present disclosure, Example 7 provides an advertisement placement device, and the device includes:

[0122] A first placement module, configured to place a target advertisement to a first user on a target placement platform according to a preset targeted placement strategy;

[0123] A second placement module, configured to, when the user conversion rate corresponding to the target advertisement is less than a first preset conversion rate, determine a first user to be expanded similar to the first user among the users on the target placement platform, and place the target advertisement to the first user to be expanded;

[0124] A third placement module, configured to, when the user conversion rate corresponding to the target advertisement reaches a second preset conversion rate, determine a second user to be expanded that has not been placed with the target advertisement among the users on the target placement platform, and place the target advertisement to the second user to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

[0125] According to one or more embodiments of the present disclosure, Example 8 provides the device of Example 7, and the second placement module is used for:

[0126] Determine the user feature vector of the first user, and determine the user feature vector of each other user among the users of the target delivery platform except the first user;

[0127] For each of the other users, determine the similarity between the user feature vector of the first user and the user feature vector of the other user. If the similarity is greater than or equal to a preset similarity, determine that the other user is a first user to be expanded similar to the first user.

[0128] According to one or more embodiments of the present disclosure, Example 9 provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processing device, the steps of the method described in any one of Examples 1-6 are implemented.

[0129] According to one or more embodiments of the present disclosure, Example 10 provides an electronic device, including:

[0130] A storage device on which a computer program is stored;

[0131] A processing device for executing the computer program in the storage device to implement the steps of the method described in any one of Examples 1-6.

[0132] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0133] In addition, although the operations are depicted in a specific order, this should not be construed as requiring the operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, the various features described in the context of a single embodiment can also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0134] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms for implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method and will not be elaborated herein.

Claims

1. An advertising placement method, characterized in that, The method includes: Delivering a target advertisement to a first user of a target delivery platform according to a preset targeted delivery strategy; If the user conversion rate corresponding to the target advertisement is less than a first preset conversion rate, then among the users of the target delivery platform, determining first users to be expanded who are similar to the first user, and delivering the target advertisement to the first users to be expanded; If the user conversion rate corresponding to the target advertisement reaches a second preset conversion rate, then among the users of the target delivery platform, determining second users to be expanded who have not received the target advertisement, and delivering the target advertisement to the second users to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

2. The method according to claim 1, wherein, The determining, among the users of the target delivery platform, first users to be expanded who are similar to the first user includes: Determining the user feature vector of the first user, and determining the user feature vector of each other user among the users of the target delivery platform except the first user; For each of the other users, determining the similarity between the user feature vector of the first user and the user feature vector of the other user, and if the similarity is greater than or equal to a preset similarity, determining the other user as a first user to be expanded who is similar to the first user.

3. The method according to claim 2, wherein The method further includes: Training an advertisement delivery model based on the user delivery data and user conversion data of other advertisements delivered on the target delivery platform, where the advertisement delivery model includes a user-side network and an advertisement-side network, the user-side network is used to extract a corresponding user feature vector based on the input user information, and the advertisement-side network is used to extract a corresponding advertisement feature vector based on the input advertisement information; The determining the user feature vector of the first user and determining the user feature vector of each other user among the users of the target delivery platform except the first user includes: Determining the user feature vector of the first user and the user feature vector of each other user among the users of the target delivery platform corresponding to the target advertisement except the first user through the user-side network in the trained advertisement delivery model.

4. The method according to claim 2, characterized in that, After delivering the target advertisement to the first users to be expanded, the method further includes: If the user conversion rate of the target advertisement does not reach the second preset conversion rate, then reducing the preset similarity to obtain a target similarity, and among the users of the target delivery platform, determining third users to be expanded who have not received the target advertisement, and determining the similarity between the user feature vector of the first user and the user feature vector of each of the third users to be expanded; For each of the third users to be expanded, if the similarity between the user feature vector of the first user and the user feature vector of the third user to be expanded is greater than or equal to the target similarity, then delivering the target advertisement to the third users to be expanded.

5. The method according to claim 2, wherein After determining the user feature vector of the first user, the method further includes: If there are multiple first users, a target user feature vector for characterizing the common features of the multiple first users is obtained by fitting the user feature vectors of the multiple first users through a preset feature fitting model; The determining the similarity between the user feature vector of the first user and the user feature vectors of other users includes: Determining the similarity between the target user feature vector and the user feature vectors of other users.

6. The method according to any one of claims 1-5, characterized in that, The second preset conversion rate is determined in the following manner: Obtaining the target user conversion rate corresponding to a pre-trained advertisement placement model, where the target user conversion rate is the user conversion rate predicted by the advertisement placement model when the difference between the predicted user conversion rate of the sample advertisement by the advertisement placement model and the actual user conversion rate of the sample advertisement is less than a preset difference during the training process of the advertisement placement model; Determining the target user conversion rate as the second preset conversion rate.

7. An advertising placement device, characterized in that, The device includes: A first placement module, configured to place a target advertisement to a first user on a target placement platform according to a preset targeted placement strategy; A second placement module, configured to, when the user conversion rate corresponding to the target advertisement is less than a first preset conversion rate, determine a first user to be expanded similar to the first user among the users on the target placement platform, and place the target advertisement to the first user to be expanded; A third placement module, configured to, when the user conversion rate corresponding to the target advertisement reaches a second preset conversion rate, determine a second user to be expanded that has not been placed with the target advertisement among the users on the target placement platform, and place the target advertisement to the second user to be expanded, where the second preset conversion rate is greater than the first preset conversion rate.

8. The device according to claim 7, characterized in that, The second placement module is configured to: Determine the user feature vector of the first user, and determine the user feature vector of each other user except the first user among the users on the target placement platform; For each of the other users, determine the similarity between the user feature vector of the first user and the user feature vector of the other user. If the similarity is greater than or equal to a preset similarity, determine the other user as a first user to be expanded similar to the first user.

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

10. An electronic device, characterized in that, Including: A storage device on which a computer program is stored; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1-6.

Images