Advertisement style adjustment method, device, equipment and storage medium
Obtain the video real-time playback characteristics through the client and enter the ad style prediction model, which solves the problem of low adjustment accuracy of the server model, realizes accurate fine-tuning of the ad style, and improves the click and conversion rate of the ad.
Patent Information
- Application Number
- CN202210623191.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-01
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2042-06-01
AI Technical Summary
In the prior art, the server-side model has low accuracy in adjusting advertising styles, resulting in low advertising conversion rate.
By obtaining the video's real-time playback characteristics, the client enters the advertising style prediction model, and determines the adjustment status of the advertising style based on the prediction results, so as to achieve accurate fine-tuning of the advertising style.
It improves the click and conversion rate of ads, reduces network data traffic, and avoids the leakage of user privacy information.
Smart Images

Figure CN114971729B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present disclosure relate to the field of Internet advertising technology, and in particular to an advertisement style adjustment method, apparatus, device, and storage medium. Background Art
[0002] With the rapid development of the Internet, streaming software is rapidly attracting Internet users and traffic, and advertisements are also beginning to be presented in the form of videos in the streaming field.
[0003] In existing technology, because the display style of advertising videos can influence users' click-to-purchase behavior, server-side models are used to adjust the ad style in the hope of attracting users to click on the ads for conversion. However, this method does not accurately adjust the ad style, resulting in a low conversion rate. Summary of the Invention
[0004] The present disclosure provides an advertisement style adjustment method, apparatus, device and storage medium, so as to enable the client to accurately fine-tune the advertisement style according to the local model and the real-time video playback characteristics, thereby improving the click-through and conversion rate of the advertisement.
[0005] In a first aspect, an embodiment of the present disclosure provides an advertisement style adjustment method, applied to a client, comprising:
[0006] Obtaining real-time video playback features and inputting the real-time video playback features into the advertising style prediction model;
[0007] The adjustment status of the advertisement style of the advertisement to be played is determined according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model.
[0008] In a second aspect, the embodiments of the present disclosure further provide an advertisement style adjustment device, which is applied to a client and includes:
[0009] A feature input module is used to obtain real-time video playback features and input the real-time video playback features into the advertisement style prediction model;
[0010] The adjustment state determination module is used to determine the adjustment state of the advertisement style of the advertisement to be played according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model.
[0011] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:
[0012] one or more processors;
[0013] a storage device for storing one or more programs,
[0014] When one or more programs are executed by one or more processors, the one or more processors implement the advertisement style adjustment method according to the embodiment of the present disclosure.
[0015] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to execute the advertisement style adjustment method as described in an embodiment of the present disclosure.
[0016] The disclosed embodiment obtains the real-time video playback features and inputs the real-time video playback features into an advertising style prediction model; determines the adjustment status of the advertising style of the advertisement to be played based on the advertising behavior prediction results and style adjustment prediction results output by the advertising style prediction model, thereby solving the problem of low adjustment accuracy of the advertising style by the server-side model and enabling the client to accurately fine-tune the advertising style based on the local model and the real-time video playback features, thereby improving the click-through and conversion rates of the advertisement. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.
[0018] Figure 1 This is a flow chart of a method for adjusting an advertisement style provided by an embodiment of the present disclosure;
[0019] Figure 2 This is an overall architecture diagram of an MMOE model provided by an embodiment of the present disclosure;
[0020] Figure 3 This is a schematic diagram of the structure of an advertisement style adjustment device provided by an embodiment of the present disclosure;
[0021] Figure 4 It is a structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0022] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying 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 described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.
[0023] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders 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 respect.
[0024] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.
[0025] It should be noted that the concepts of "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.
[0026] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".
[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0028] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.
[0029] Figure 1 This is a flow chart of an advertisement style adjustment method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to the case where a client adjusts the advertisement style of an advertisement to be played. The method can be executed by an advertisement style adjustment device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC, etc. Figure 1 As shown, the method is applied to the client and includes:
[0030] S110: Acquire real-time video playback features, and input the real-time video playback features into an advertisement style prediction model.
[0031] The advertising style prediction model is trained based on the Multi-gate Mixture-of-Experts (MMOE) model. The overall architecture of the MMOE model is as follows: Figure 2As shown in the figure, it can be seen that when defining two task optimization models, feature conversion can be performed at the feature input stage to generate several base learners respectively, and then the gate network is used to represent the final result output at the input corresponding to each task. In this way, the MMOE model can simultaneously predict two interrelated learning objectives, for example, predicting whether the user will click on the link and predicting whether the user will place an order for the product after clicking.
[0032] Optionally, the real-time video playback features include: the duration of each video played within a preset time period, whether each video played is an advertisement, the number of skipped videos, the number of fully played videos, the number of shared videos, and the terminal access method.
[0033] In this embodiment, the process of client video playback is a time-series process, so behavioral data during the client video playback process can be collected to form model input features. At the same time, to reflect real-time video playback characteristics, video playback data can be collected within a relatively short period of time in the past, such as within 30 seconds. This includes: the duration of each video played within 30 seconds: [play_time_0, ..., play_time_9]; whether each video played within 30 seconds is an advertisement: [p_type_ad_0, ..., p_type_ad_9], for example, true indicates an advertisement and false indicates not an advertisement; the number of videos skipped within 30 seconds: skip_cnt; terminal access mode: wifi / 4G / 3G / mobile; the number of videos played completely within 30 seconds: u_finish_cnt; and the number of videos shared within 30 seconds: u_share_cnt.
[0034] In this embodiment, when a user browses a short video on the client, the client inserts a pre-set ad style into the short video playlist and recommends it to the user to attract clicks and conversions. Because ad style influences user playback, to further increase user viewing time and encourage clicks or purchases, real-time video playback features over a short period of time can be collected and input into a local ad style prediction model on the client. The model then predicts two objectives: whether to adjust the ad style and the playback status of the ad.
[0035] In this embodiment, by running the advertising style prediction model on the client, the distance between the user and the prediction model is shortened. The video playback characteristics of the client can be collected in real time and input into the local prediction model to achieve fast and accurate prediction of whether the advertising style needs to be fine-tuned. This eliminates the need to upload user information to the prediction model in the server, reduces network data traffic, and avoids leaking user privacy information.
[0036] Optionally, before obtaining the real-time video playback features and inputting the real-time video playback features into the advertising style prediction model, it may also include: dividing a preset number of client registered users into a first number of user groups, and configuring different style adjustment strategies for each user group; collecting the real-time video playback features of each user group under the corresponding style adjustment strategy as training data; using the training data to perform model training to obtain an advertising style prediction model.
[0037] In this embodiment, whether to adjust the ad style and the playback status of the ad video are two mutually influential learning objectives. To enable the model to accurately predict these two learning objectives, a controlled experiment is conducted on a subset of registered client users to adjust the ad style. This experiment examines how users' playback actions on the ad video change under various style adjustment strategies. For example, five style adjustment strategies are pre-set. For example, strategy 1 maintains the original ad style of a particular ad video, i.e., within the ad video, the click button is displayed at 0 seconds, the button changes color at 1 second, and the shopping cart is displayed at 2 seconds. Strategy 2 delays the display of the original ad style by 1 second, i.e., within the ad video, the click button is displayed at 1 second, the button changes color at 2 seconds, and the shopping cart is displayed at 3 seconds. Accordingly, strategies 3-5 delay the display of the original ad by 2-4 seconds. 5% of the registered client users are randomly selected and evenly divided into five user groups. Each user group is assigned a style adjustment strategy. Ad videos are recommended to the user group according to the style adjustment strategy. Video playback features, such as the duration of each video played within 30 seconds for each user group, are collected as training data. The MMOE model is trained using the training data, and an advertising style prediction model is finally obtained.
[0038] It should be noted that this embodiment only uses the display timing of the advertising style as an example for style adjustment. Therefore, the various style adjustment strategies set up only differ in the display timing of the advertising style. If you want to adjust the type of advertising style, such as adding a favorite button to the advertisement, you need to distinguish the type of advertising style in the various style adjustment strategies to form a strategy control group.
[0039] S120 : Determine an adjustment status of the advertisement style of the advertisement to be played according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model.
[0040] In this embodiment, the ad style prediction model determines the ad behavior prediction result by predicting the playback duration of the ad video. The ad behavior prediction result may include fast-playing ads and slow-playing ads. When the predicted playback duration of the ad video is greater than a specified threshold, such as 3 seconds, the ad behavior prediction result is determined to be slow-playing ads. When the predicted playback duration of the ad video is less than the specified threshold, such as 3 seconds, the ad behavior prediction result is determined to be fast-playing ads. The style adjustment prediction result includes adjusting the ad style or not adjusting the ad style.
[0041] In this embodiment, since whether to adjust the advertising style and whether to play the advertisement quickly affect each other, adjusting the advertising style will affect the playback time of the advertising video, and the playback time of the advertising video will also affect the adjustment of the advertising style. Therefore, it is necessary to combine the advertising behavior prediction results and the style adjustment prediction results to make a comprehensive decision on whether to adjust the advertising style.
[0042] Optionally, the adjustment status of the advertising style of the advertisement to be played is determined based on the advertising behavior prediction results and the style adjustment prediction results output by the advertising style prediction model, including: determining the adjustment direction of the advertising style based on the advertising behavior prediction results; and judging whether to adjust the advertising style of the advertisement to be played based on the adjustment direction of the advertising style and the style adjustment prediction results.
[0043] In this embodiment, it is assumed that ad style is the sole means of adjustment and that ad style affects ad playback duration. Therefore, it can be assumed that, within the prediction results output by the ad style prediction model, the ad behavior prediction result is generated based on the style adjustment prediction result. Therefore, after obtaining the two prediction results output by the model, the ad style adjustment direction can be determined based on the ad behavior prediction result, with the goal of increasing the user's ad viewing time. Furthermore, the ad style adjustment direction and the style adjustment prediction result can be combined to determine whether to adjust the ad style of the upcoming ad.
[0044] Optionally, the adjustment direction of the advertisement style is determined based on the advertisement behavior prediction result, including: if the advertisement behavior prediction result is fast-playing advertisements, determining the adjustment direction as reverse adjustment; if the advertisement behavior prediction result is slow-playing advertisements, determining the adjustment direction as forward adjustment.
[0045] In this embodiment, if the model outputs a fast-playing ad, meaning a predicted ad duration of less than 3 seconds, since this predicted duration is based on the model's outputted style adjustment prediction, the ad style needs to be adjusted in the opposite direction of the style adjustment prediction to increase the user's viewing time. In this case, if the style adjustment prediction indicates "adjust," then adjusting the style of the next ad will disinterest the user, resulting in a playback duration of less than 3 seconds. Therefore, the ad style cannot be adjusted. If the style adjustment prediction indicates "no adjustment," then not adjusting the style of the next ad will result in a playback duration of less than 3 seconds. Therefore, the ad style needs to be adjusted to attract user interest. If the model outputs a slow-playing ad, meaning a predicted ad duration of more than 3 seconds, then since the goal of attracting user viewing has been achieved and this predicted duration is based on the model's outputted style adjustment prediction, the ad style of the next ad needs to be adjusted according to the style prediction. In other words, if the style adjustment prediction indicates "adjust," then the ad style needs to be adjusted. If the style adjustment prediction indicates "no adjustment," then no adjustment is required.
[0046] Optionally, after determining the adjustment status of the advertising style of the advertisement to be played based on the advertising behavior prediction results and the style adjustment prediction results output by the advertising style prediction model, it also includes: if it is determined that the advertising style of the advertisement to be played is adjusted, then based on the training data classification results corresponding to various style adjustment strategies, a target style adjustment strategy that matches the prediction results output by the advertising style prediction model is selected to adjust the advertising style of the advertisement to be played.
[0047] In this embodiment, since the prediction results output by the prediction model only determine whether to adjust the ad style, but not the specific adjustment methods, when an ad style adjustment is needed, a style adjustment strategy can be selected from the various style adjustment strategies corresponding to the training data. For example, for each style adjustment strategy, the training data can be classified according to whether the user prefers to play the ad quickly or slowly, and the probabilities of fast and slow playback of the ad under that strategy can be calculated. When the model predicts no adjustment and the ad behavior predicts fast playback, the style adjustment strategy with the highest probability of slow playback among the various style adjustment strategies can be selected as the target style adjustment strategy. When the model predicts adjustment and the ad behavior predicts slow playback, a style adjustment strategy with a higher probability of slow playback than fast playback can be randomly selected as the target style adjustment strategy. Alternatively, when an ad style adjustment is needed, a style adjustment strategy can be randomly selected from the various style adjustment strategies as the target style adjustment strategy. Of course, a style adjustment strategy can also be generated in real time based on the real-time video playback characteristics to adjust the style of the next ad.
[0048] The disclosed embodiment obtains the real-time video playback features and inputs the real-time video playback features into an advertising style prediction model; determines the adjustment status of the advertising style of the advertisement to be played based on the advertising behavior prediction results and style adjustment prediction results output by the advertising style prediction model, thereby solving the problem of low adjustment accuracy of the advertising style by the server-side model and enabling the client to accurately fine-tune the advertising style based on the local model and the real-time video playback features, thereby improving the click-through and conversion rates of the advertisement.
[0049] Figure 3 This is a schematic diagram of the structure of an advertisement style adjustment device provided by an embodiment of the present disclosure, such as Figure 3 As shown, the device is applied to a client, and includes: a feature input module 310 and an adjustment state determination module 320.
[0050] A feature input module 310 is used to obtain real-time video playback features and input the real-time video playback features into the advertisement style prediction model;
[0051] The adjustment state determination module 320 is configured to determine the adjustment state of the advertisement style of the advertisement to be played according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model.
[0052] The technical solution provided by the embodiments of the present disclosure obtains real-time video playback features and inputs the real-time video playback features into an advertising style prediction model; based on the advertising behavior prediction results and style adjustment prediction results output by the advertising style prediction model, the adjustment status of the advertising style of the advertisement to be played is determined, thereby solving the problem of low adjustment accuracy of the advertising style by the server-side model, and enabling the client to accurately fine-tune the advertising style according to the local model and the real-time video playback features, thereby improving the click-through and conversion rates of the advertisement.
[0053] In the above scheme, the adjustment state determination module 320 includes: an adjustment direction determination unit, which is used to determine the adjustment direction of the advertising style based on the advertising behavior prediction result; an adjustment judgment unit, which is used to judge whether to adjust the advertising style of the advertisement to be played based on the adjustment direction of the advertising style and the style adjustment prediction result.
[0054] In the above solution, the adjustment direction determining unit is specifically configured to: determine the adjustment direction as reverse adjustment if the advertising behavior prediction result is fast advertising playback; and determine the adjustment direction as forward adjustment if the advertising behavior prediction result is slow advertising playback.
[0055] In the above scheme, the real-time behavior characteristics include: the duration of each video played within a preset time period, whether each video played is an advertisement, the number of skipped videos, the number of fully played videos, the number of shared videos, and the terminal access method.
[0056] Furthermore, the advertising style adjustment device provided by this embodiment may also include: a model training module, which is used to divide a preset number of client registered users into a first number of user groups before obtaining real-time video playback features and inputting the real-time video playback features into the advertising style prediction model, and configure different style adjustment strategies for each user group; collect the real-time video playback features of each user group under the corresponding style adjustment strategy as training data; use the training data to perform model training to obtain an advertising style prediction model.
[0057] Furthermore, the advertising style adjustment device provided by this embodiment may also include: a style adjustment module, which is used to determine the adjustment status of the advertising style of the advertisement to be played based on the advertising behavior prediction result and the style adjustment prediction result output by the advertising style prediction model. If it is determined that the advertising style of the advertisement to be played is to be adjusted, then according to the training data classification results corresponding to various style adjustment strategies, a target style adjustment strategy that matches the prediction result output by the advertising style prediction model is selected to adjust the advertising style of the advertisement to be played.
[0058] In the above scheme, the advertising style prediction model is trained based on the multi-task learning model MMOE.
[0059] The advertisement style adjustment device provided in the embodiments of the present disclosure can execute the advertisement style adjustment method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
[0060] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.
[0061] Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 4 , which shows an electronic device (eg Figure 4 The terminal device in the embodiments 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), and fixed terminals such as digital TVs and desktop computers. Figure 4 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.
[0062] like Figure 4 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can 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. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An edit / output (I / O) interface 505 is also connected to the bus 504.
[0063] Typically, 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 by wire to exchange data. Although Figure 4The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.
[0064] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the 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-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
[0065] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0066] The electronic device provided in the embodiment of the present disclosure and the advertisement style adjustment method provided in the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.
[0067] An embodiment of the present disclosure provides a computer storage medium having a computer program stored thereon. When the program is executed by a processor, the advertisement style adjustment method provided in the above embodiment is implemented.
[0068] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media may 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, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.
[0069] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0070] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0071] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:
[0072] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the real-time video playback characteristics, and inputs the real-time video playback characteristics into the advertising style prediction model; determines the adjustment status of the advertising style of the advertisement to be played based on the advertising behavior prediction results and style adjustment prediction results output by the advertising style prediction model.
[0073] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving 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., via the Internet using an Internet service provider).
[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0075] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.
[0076] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary 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), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.
[0077] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, 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 foregoing.
[0078] According to one or more embodiments of the present disclosure, Example 1 provides an advertisement style adjustment method, applied to a client, including:
[0079] Obtaining real-time video playback features and inputting the real-time video playback features into the advertising style prediction model;
[0080] The adjustment status of the advertisement style of the advertisement to be played is determined according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model.
[0081] According to one or more embodiments of the present disclosure, Example 2, based on the method of Example 1, determines the adjustment status of the advertisement style of a to-be-played advertisement according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model, including:
[0082] Determine the direction of adjusting the advertising style based on the advertising behavior prediction results;
[0083] According to the adjustment direction of the advertisement style and the style adjustment prediction result, it is determined whether the advertisement style of the advertisement to be played should be adjusted.
[0084] According to one or more embodiments of the present disclosure, Example 3, based on the method of Example 2, determines the direction of adjusting the advertisement style according to the advertisement behavior prediction result, including:
[0085] If the advertising behavior prediction result is to play the advertisement quickly, the adjustment direction is determined to be a reverse adjustment;
[0086] If the advertising behavior prediction result is to play the advertisement slowly, the adjustment direction is determined to be a positive adjustment.
[0087] According to one or more embodiments of the present disclosure, Example 4, based on the method of Example 1, the real-time video playback features include: the duration of each video played within a preset time period, whether each video played is an advertisement, the number of skipped videos, the number of fully played videos, the number of shared videos, and the terminal access method.
[0088] According to one or more embodiments of the present disclosure, Example 5, based on the method of Example 4, further includes: obtaining real-time video playback features and inputting the real-time video playback features into the advertisement style prediction model before:
[0089] Dividing a preset number of client registered users into a first number of user groups, and configuring a different style adjustment strategy for each user group;
[0090] Collect the real-time video playback features of each user group under the corresponding style adjustment strategy as training data;
[0091] Use the training data to train the model and obtain the advertising style prediction model.
[0092] According to one or more embodiments of the present disclosure, Example 6, based on the method of Example 5, further includes, after determining the adjustment status of the advertisement style of the to-be-played advertisement based on the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model:
[0093] If it is determined to adjust the advertising style of the advertisement to be played, then based on the classification results of the training data corresponding to various style adjustment strategies, a target style adjustment strategy that matches the prediction results output by the advertising style prediction model is selected to adjust the advertising style of the advertisement to be played.
[0094] According to one or more embodiments of the present disclosure, in Example 7, according to the method of any one of Examples 1-5, the advertisement style prediction model is trained based on a multi-task learning model MMOE.
[0095] According to one or more embodiments of the present disclosure, Example 8 provides an advertisement style adjustment device, applied to a client, including:
[0096] A feature input module is used to obtain real-time video playback features and input the real-time video playback features into the advertisement style prediction model;
[0097] The adjustment state determination module is used to determine the adjustment state of the advertisement style of the advertisement to be played according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model.
[0098] According to one or more embodiments of the present disclosure, Example 9 provides an electronic device, the electronic device including:
[0099] one or more processors;
[0100] a storage device for storing one or more programs,
[0101] When the one or more programs are executed by one or more processors, the one or more processors implement the advertisement style adjustment method as described in any one of Examples 1-7.
[0102] According to one or more embodiments of the present disclosure, Example 10 provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the advertisement style adjustment method of any one of Examples 1-7.
[0103] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. 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-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.
[0104] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.
[0105] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.
Claims
1. A method for adjusting an advertisement style, characterized in that: Applied to the client, including: Acquire real-time video playback features, and input the real-time video playback features into an advertisement style prediction model; Determining an adjustment state of the advertisement style of the advertisement to be played according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model; The step of determining the adjustment state of the advertisement style of the advertisement to be played according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model includes: Determining the direction of adjusting the advertisement style according to the advertisement behavior prediction result; Determining whether to adjust the advertisement style of the advertisement to be played according to the adjustment direction of the advertisement style and the style adjustment prediction result; The step of determining the adjustment direction of the advertisement style according to the advertisement behavior prediction result includes: If the advertising behavior prediction result is to play the advertisement quickly, determining the adjustment direction to be a reverse adjustment; If the advertising behavior prediction result is slow advertising playback, determining the adjustment direction to be a positive adjustment; The fast-playing advertisement includes an advertisement whose playing time is less than a preset time, and the slow-playing advertisement includes an advertisement whose playing time is greater than a preset time.
2. The method according to claim 1, characterized in that The real-time video playback features include: the duration of each video played within a preset time period, whether each video played is an advertisement, the number of skipped videos, the number of fully played videos, the number of shared videos, and the terminal access method.
3. The method according to claim 2, characterized in that Before obtaining the real-time video playback feature and inputting the real-time video playback feature into the advertisement style prediction model, the method further includes: Dividing a preset number of client registered users into a first number of user groups, and configuring a different style adjustment strategy for each user group; Collect the real-time video playback features of each user group under the corresponding style adjustment strategy as training data; The training data is used to perform model training to obtain an advertisement style prediction model.
4. The method according to claim 3, characterized in that After determining the adjustment state of the advertisement style of the advertisement to be played according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model, the method further includes: If it is determined to adjust the advertising style of the advertisement to be played, then based on the classification results of the training data corresponding to various style adjustment strategies, a target style adjustment strategy that matches the prediction result output by the advertising style prediction model is selected to adjust the advertising style of the advertisement to be played.
5. The method according to any one of claims 1 to 4, characterized in that The advertisement style prediction model is obtained based on the multi-task learning model MMOE training.
6. An advertisement style adjustment device, characterized in that: Applied to the client, including: A feature input module, used to obtain real-time video playback features and input the real-time video playback features into an advertisement style prediction model; An adjustment state determination module, used to determine the adjustment state of the advertisement style of the advertisement to be played according to the advertisement behavior prediction result and the style adjustment prediction result output by the advertisement style prediction model; Wherein, the adjustment state determination module includes: an adjustment direction determination unit, which is used to determine the adjustment direction of the advertisement style according to the advertisement behavior prediction result; An adjustment decision unit, used to determine whether to adjust the advertisement style of the advertisement to be played according to the adjustment direction of the advertisement style and the style adjustment prediction result; The adjustment direction determining unit is specifically used to: if the advertising behavior prediction result is fast advertising playback, determine the adjustment direction as reverse adjustment; If the advertising behavior prediction result is to play the advertisement slowly, then the adjustment direction is determined to be a positive adjustment; The fast-playing advertisement includes an advertisement whose playing time is less than a preset time, and the slow-playing advertisement includes an advertisement whose playing time is greater than a preset time.
7. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the advertisement style adjustment method according to any one of claims 1 to 5.
8. A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to perform the advertisement style adjustment method according to any one of claims 1 to 5 when executed by a computer processor.
