Video recommendation method, device, terminal and storage medium

Abstract

The present application provides a video recommendation method, device, terminal and storage medium. The method includes: after monitoring the update of the recommended video in the current recommendation position, determining the recommendation effect score of the recommended video in the current update period according to the number of video recommendation position subscriptions and the number of users who click on the recommended position in the current update period; if the recommendation effect score of the recommended video in the current update period is lower than the first preset threshold, then using any video other than the recommended video corresponding to the current recommendation position in the current recommendation period to replace the recommended video; otherwise, continue to monitor the recommendation effect. The above method can regularly monitor the recommendation effect after the recommended video is on the recommendation position, and determine whether the recommended video continues to be displayed in the recommendation position based on the recommendation effect score, so as to make the click-through rate of the video on the recommendation position higher and improve the video recommendation effect.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a video recommendation method, device, terminal, and storage medium. Background Art

[0002] Internet Protocol Television (IPTV) utilizes the infrastructure of broadband cable television networks. IPTV uses home televisions as the main terminal appliances and provides a variety of digital media services including television programs through Internet protocols.

[0003] Currently, the method for recommending videos on IPTV platforms is usually a manual selection method, which is greatly affected by human factors and has poor recommendation effects. Summary of the Invention

[0004] The present application provides a video recommendation method, device, terminal and storage medium to solve the problem of poor video recommendation effect on IPTV platform.

[0005] In a first aspect, the present application provides a video recommendation method, comprising:

[0006] After monitoring the update of the recommended video in the current recommendation position, the number of video recommendation position subscriptions and the number of recommended position click users of the recommended video are obtained according to the preset update cycle;

[0007] Determine the recommendation effect score of the recommended video in the current update period according to the number of subscriptions to the video recommendation position and the number of users who clicked on the recommendation position of the recommended video in the current update period;

[0008] If the recommendation effect score of the recommended video in the current update cycle is lower than a first preset threshold, the recommended video is replaced with any video other than the recommended video corresponding to the current recommendation position in the current recommendation cycle;

[0009] If the recommendation effect score of the recommended video in the current update cycle is higher than the first preset threshold, the process returns to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update cycle and continues to execute.

[0010] In a second aspect, the present application provides a video recommendation device, comprising:

[0011] The recommendation effect data acquisition module is used to obtain the number of video recommendation position subscriptions and the number of recommended position click users of the recommended video according to a preset update cycle after monitoring the update of the recommended video in the current recommendation position;

[0012] A recommendation effect score acquisition module is used to determine the recommendation effect score of the recommended video in the current update period according to the number of subscriptions to the video recommendation position and the number of users who clicked on the recommendation position of the recommended video in the current update period;

[0013] A recommended video updating module, configured to replace the recommended video with any video other than the recommended video corresponding to the current recommended position in the current recommendation period, if the recommendation effect score of the recommended video in the current update period is lower than a first preset threshold;

[0014] The recommended position video maintaining module is used to return to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update cycle and continue execution if the recommendation effect score of the recommended video in the current update cycle is higher than the first preset threshold.

[0015] In a third aspect, the present application provides a terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the video recommendation method as described in the possible implementation of the first aspect above are implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the video recommendation method described in any possible implementation of the first aspect above are implemented.

[0017] The embodiment of the present application provides a video recommendation method, device, terminal and storage medium. After monitoring the update of the recommended video in the current recommendation position, the method obtains the video recommendation position subscription number and the number of users who click on the recommended position of the recommended video according to the preset update period; determines the recommendation effect score of the recommended video in the current update period based on the video recommendation position subscription number and the number of users who click on the recommended position of the recommended video in the current update period; if the recommendation effect score of the recommended video in the current update period is lower than the first preset threshold, the recommended video is replaced with any video other than the recommended video corresponding to the current recommendation position in the current recommendation period; if the recommendation effect score of the recommended video in the current update period is higher than the first preset threshold, the method returns to the step of obtaining the video recommendation position subscription number and the number of users who click on the recommended position of the recommended video according to the preset update period and continues to execute. The above method can regularly monitor the recommendation effect after the recommended video is on the recommendation position, and determine whether the recommended video continues to be displayed in the recommendation position based on the recommendation effect score, so as to make the click-through rate of the video on the recommendation position higher and improve the video recommendation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a flowchart of the implementation of the video recommendation method provided in the embodiment of the present application;

[0020] Figure 2 Schematic diagram of the structure of the video recommendation device provided in an embodiment of the present application;

[0021] Figure 3 It is a schematic diagram of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0023] In order to make the purpose, technical solutions and advantages of this application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0024] See also Figure 1 , which shows a flow chart for implementing the video recommendation method provided in an embodiment of the present application, as detailed below:

[0025] S101: After monitoring the update of the recommended video in the current recommendation position, the number of video recommendation position subscriptions and the number of users who click on the recommendation position of the recommended video are obtained according to a preset update cycle.

[0026] The implementation entity of this embodiment is an IPTV platform. The video recommendation page of the IPTV platform includes multiple recommendation slots arranged in an array. Each recommendation slot is used to display a recommended video. For each recommendation slot on the video recommendation page, after detecting an update of the recommended video in that slot, the IPTV platform obtains the average viewing time per person of the recommended video, the number of subscriptions to the video recommendation slot, and the number of users who clicked on the recommended slot according to a preset update cycle.

[0027] S102: Determine the recommendation effect score of the recommended video in the current update period according to the number of subscriptions to the video recommendation position and the number of users who click on the recommendation position of the recommended video in the current update period.

[0028] In this embodiment, the IPTV platform obtains the number of video recommendation position subscriptions, the total number of video subscriptions, and the number of users who click on the recommendation position for the recommended video at the current recommendation position in the current update cycle, calculates the recommendation position conversion rate based on the number of video recommendation position subscriptions and the number of users who click on the recommendation position, calculates the recommendation position subscription rate based on the number of video recommendation position subscriptions and the total number of subscriptions for the recommended video, and then determines the recommendation effect score of the recommended video in the current update cycle based on the recommendation position conversion rate and the recommendation position subscription rate of the recommended video at the current recommendation position.

[0029] S103: If the recommendation effect score of the recommended video in the current update cycle is lower than a first preset threshold, the recommended video is replaced with any video other than the recommended video corresponding to the current recommendation position in the current recommendation cycle.

[0030] In this embodiment, one recommendation position corresponds to multiple recommended videos. When the IPTV platform monitors that the recommendation effect score of the recommended video in the current update cycle is lower than the first preset threshold, it means that the recommendation effect of the recommended video in the current recommendation position is poor. In this case, any video other than the recommended video corresponding to the current recommendation position in the current recommendation cycle is used to replace the recommended video, thereby avoiding the problem of poor video subscription rate caused by videos with low conversion rates occupying the recommendation position and improving the video subscription rate.

[0031] It is understandable that since the recommendation positions ranked at the front have a superior position than those ranked at the back, the number of users clicking on the recommendation positions is also higher. Therefore, although the same threshold is used to judge the recommendation effect for different recommendation positions, the recommendation positions ranked at the front need to obtain more video orders to get the same recommendation effect score as the recommendation positions ranked at the back, which puts higher requirements on the recommendation effect of the recommended videos ranked at the front.

[0032] S104: If the recommendation effect score of the recommended video in the current update cycle is higher than the first preset threshold, the process returns to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update cycle and continues to execute.

[0033] If the recommendation effect score of the recommended video in the current update cycle is higher than the first preset threshold, it means that the recommendation effect of the recommended video in the current recommendation position is good and it can continue to be displayed in the recommendation position for promotion.

[0034] The above method can regularly monitor the recommendation effect after the recommended video is placed in the recommendation position, and determine whether the recommended video should continue to be displayed in the recommendation position based on the recommendation effect score, so as to increase the click-through rate of the video in the recommendation position and improve the video recommendation effect.

[0035] In one possible implementation, the specific implementation process of S102 includes:

[0036] Based on the formula , calculating the recommendation effect score of the recommended video in the current update cycle;

[0037] in, Indicates the t Current recommended position within the update cycle i Recommended videos j 's recommendation effect rating; Indicates the t During the update cycle, the user changes from the current recommended position i Order a Recommended Video j Number of video recommendation orders; Indicates the t Current recommended position for update cycles i Number of users who clicked on the recommended position; Indicates recommended video j Total number of orders; are weight values, and .

[0038] For example, .

[0039] In this embodiment, the IPTV platform can also obtain the average viewing time and total video duration of the recommended videos, and then calculate the viewing completion rate of the recommended videos in the recommended position based on the average viewing time and total video duration of the recommended videos. , calculating the recommendation effect score of the recommended video in the current update cycle;

[0040] in, Indicates the t Update cycle from the current recommended position i Watch recommended videos j Average viewing time per person; Indicates recommended video j Total video length; are weight values, and .

[0041] Specifically, the total video duration mentioned in this embodiment is the total video duration of a single episode or a single film.

[0042] For example, .

[0043] In one possible implementation, before S103, the method provided in this embodiment further includes:

[0044] S201: Obtain the popularity rating and online time of each video on the platform according to a preset recommendation cycle;

[0045] S202: Determine a freshness score of each video based on the online duration, wherein the online duration is negatively correlated with the freshness score;

[0046] S203: Perform weighted summation of the popularity score and freshness score of each video to determine the current recommendation score of each video;

[0047] S204: Sort all videos in descending order according to the current recommendation score, and determine the N videos corresponding to the current recommendation position based on the ranking of each video and the ranking range corresponding to each recommendation position. .

[0048] In this embodiment, when the IPTV platform first lists a recommended video, it determines the corresponding recommended position based on the current recommendation score of each video on the platform. Each recommended position corresponds to N videos. For each recommended position, one matching video is selected and displayed as the recommended video for that position. Videos corresponding to different recommended positions may overlap, but the recommended videos listed for each recommendation position are unique. Subsequently, the IPTV platform calculates the recommendation score of each video on the platform for the current recommendation period according to a preset recommendation period. Then, based on each video's ranking and the ranking range of each recommended position, it determines the video corresponding to each recommended position.

[0049] Specifically, when calculating the freshness score, the longer the video has been online, the lower the freshness score, and the shorter the video has been online, the higher the freshness score. The freshness score of the video gradually decreases from 100 to 0 as the online time increases. For example, if the online time is less than three days, the freshness score is 100 points, if the online time is less than one week, the freshness score is 70 points, if the online time is less than one month, the freshness score is 50 points, if the online time is less than three months, the freshness score is 30 points, if the online time is less than six months, the freshness score is 20 points, if the online time is less than one year, the freshness score is 10 points, and if the online time exceeds one year, the freshness score is 0 points. In S203, when calculating the current recommendation score of the video, the weight of the popularity score can be 90%, and the weight of the freshness score can be 10%.

[0050] Specifically, when matching the recommendation position and the video, the higher the position of the recommendation position, the higher the ranking of the matching video, and the lower the position of the recommendation position, the lower the ranking of the matching video.

[0051] For example, the first recommendation position corresponds to videos ranked first to third, the second recommendation position corresponds to videos ranked second to fourth, the third recommendation position corresponds to videos ranked third to fifth, and so on, until the video corresponding to the last recommendation position is determined.

[0052] In one possible implementation, the specific implementation process of S201 includes:

[0053] Obtain popularity rankings of each video on the platform on multiple third-party platforms according to a preset recommendation cycle;

[0054] For any video, the popularity score of the video on each third-party platform is determined based on the popularity ranking of the video on each third-party platform in the current recommendation cycle, and the popularity ranking is negatively correlated with the popularity score; the popularity score of the video on each third-party platform in the current recommendation cycle is weighted and summed to obtain the popularity score corresponding to the video in the current recommendation cycle.

[0055] Specifically, the calculation formula for the heat score is:

[0056] ;

[0057] in, Indicates the j The popularity rating of the video, Indicates the j Video in x Popularity rankings of third-party platforms, Indicates the x The weight of a third-party platform, K Indicates the number of third-party platforms. Indicates the total number of preset videos.

[0058] In one possible implementation, the method for updating the video corresponding to each recommendation position further includes:

[0059] Get the recommendation type of the current recommendation page; the recommendation types include TV series, movies, variety shows, cartoons, documentaries and comprehensive, etc.

[0060] According to the recommendation type of the current recommendation page, obtain the popularity ranking of each video in the sub-platform from the popularity list of the corresponding type on multiple third-party platforms;

[0061] Based on the formula Calculate the popularity score of each video in the corresponding recommendation type; Indicates the j Video in The popularity rating in the recommended categories, Indicates the j Video in x The third-party platform Popularity ranking in the recommended type list, Indicates the x The weight of a third-party platform, K Indicates the number of third-party platforms. Indicates the total number of videos, that is, the total number of videos on the list. For example, the popularity list of third-party platforms usually only displays the popularity rankings of the top 50 videos.

[0062] After determining the popularity ratings of each video within the platform for each recommendation type, the IPTV platform calculates the current recommendation rating for each video based on its corresponding freshness rating within the current recommendation cycle and its corresponding popularity rating for each recommendation type. For each recommendation type, the platform then determines the videos corresponding to each recommendation position based on the ranking range of the recommendation position within that recommendation type and the ranking of the current recommendation ratings of each video within that recommendation type.

[0063] In one possible implementation, the specific implementation process of S104 includes:

[0064] S301: If the recommendation effect score of the recommended video is greater than or equal to the first preset threshold and less than the second preset threshold, determine whether the recommended video is the video corresponding to the current recommendation position in the current recommendation period;

[0065] S302: If the recommended video is a video corresponding to the current recommendation position within the current recommendation period, the process returns to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update period;

[0066] S303: If the recommendation effect score of the recommended video is not less than the second preset threshold, the process returns to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update period and continues to execute.

[0067] Specifically, the first preset threshold is smaller than the second preset threshold. The first preset threshold may be 70% to 80%, and the second preset threshold may be 90% to 120%.

[0068] In this embodiment, if the recommendation effect score of the recommended video is greater than or equal to the first preset threshold and less than the second preset threshold, it is determined that the recommendation effect of the recommended video in the current recommendation position is average. If the recommended video is one of the videos corresponding to the current recommendation position in the current recommendation cycle, it means that the popularity ranking of the recommended video matches the current recommendation position and can continue to remain in the current recommendation position. If the recommended video is not the video corresponding to the current recommendation position in the current recommendation cycle, it means that the popularity ranking of the recommended video does not match the current recommendation position, and it is necessary to use a video corresponding to the current recommendation position to replace the recommended video.

[0069] In a possible implementation, after S301, the method provided in this embodiment further includes:

[0070] If the recommended video is not the video corresponding to the current recommendation position in the current recommendation period, any video corresponding to the current recommendation position in the current recommendation period is used to replace the recommended video.

[0071] In this embodiment, after the recommended video is displayed in the recommendation position, the IPTV platform determines whether to replace the recommended video in the recommendation position based on the video recommendation effect of the recommended video, so that the recommended video in the recommendation position is always the best choice among all videos, thereby improving the video recommendation effect.

[0072] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0073] The following are device embodiments of the present application. For details not fully described therein, please refer to the corresponding method embodiments described above.

[0074] Figure 2 The following is a schematic diagram of the structure of the video recommendation device provided in an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown, which are detailed as follows:

[0075] like Figure 2 As shown, the video recommendation device 100 includes:

[0076] The recommendation effect data acquisition module 110 is used to acquire the number of video recommendation position subscriptions and the number of recommended position click users of the recommended video according to a preset update cycle after monitoring the update of the recommended video in the current recommendation position;

[0077] The recommendation effect score acquisition module 120 is used to determine the recommendation effect score of the recommended video in the current update period according to the number of subscriptions to the video recommendation position and the number of users who clicked on the recommendation position of the recommended video in the current update period;

[0078] The recommended video updating module 130 is configured to replace the recommended video with any video other than the recommended video corresponding to the current recommended position in the current recommendation period if the recommendation effect score of the recommended video in the current update period is lower than a first preset threshold;

[0079] The recommended position video maintaining module 140 is used to return to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update cycle and continue execution if the recommendation effect score of the recommended video in the current update cycle is higher than the first preset threshold.

[0080] In one possible implementation, the recommendation effect score acquisition module 120 includes:

[0081] Based on the formula , calculating the recommendation effect score of the recommended video in the current update cycle;

[0082] in, Indicates the t Current recommended position within the update cycle i Recommended videos j 's recommendation effect rating; Indicates the t During the update cycle, the user changes from the current recommended position i Order a Recommended Video j Number of video recommendation orders; Indicates the t Current recommended position for update cycles i Number of users who clicked on the recommended position; Indicates recommended video j Total number of orders; are weight values, and .

[0083] In one possible implementation, the video matching module is configured to include:

[0084] A popularity data acquisition unit is used to obtain the popularity score and online time of each video on the platform according to a preset recommendation cycle;

[0085] A freshness score calculation unit, configured to determine the freshness score of each video based on the online duration, wherein the online duration is negatively correlated with the freshness score;

[0086] The recommendation score calculation unit is used to perform a weighted summation of the popularity score and freshness score of each video to determine the current recommendation score of each video;

[0087] The video matching unit is used to sort all videos in descending order according to the current recommendation score, and determine the N videos corresponding to the current recommendation position based on the ranking of each video and the ranking range corresponding to each recommendation position. .

[0088] In one possible implementation, the heat data acquisition unit includes:

[0089] Obtain popularity rankings of each video on the platform on multiple third-party platforms according to a preset recommendation cycle;

[0090] For any video, the popularity score of the video on each third-party platform is determined based on the popularity ranking of the video on each third-party platform in the current recommendation cycle, and the popularity ranking is negatively correlated with the popularity score; the popularity score of the video on each third-party platform in the current recommendation cycle is weighted and summed to obtain the popularity score corresponding to the video in the current recommendation cycle.

[0091] In one possible implementation, the recommended video holding module 140 includes:

[0092] If the recommendation effect score of the recommended video is greater than or equal to the first preset threshold and less than the second preset threshold, determining whether the recommended video is the video corresponding to the current recommendation position in the current recommendation period;

[0093] If the recommended video is a video corresponding to the current recommendation position in the current recommendation cycle, then returning to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update cycle and continuing the execution;

[0094] If the recommendation effect score of the recommended video is not less than the second preset threshold, the process returns to the step of obtaining the number of video recommendation position subscriptions and the number of users who click on the recommended position of the recommended video according to the preset update period and continues to execute.

[0095] In one possible implementation, the recommended video holding module 140 further includes:

[0096] If the recommended video is not the video corresponding to the current recommendation position in the current recommendation period, any video corresponding to the current recommendation position in the current recommendation period is used to replace the recommended video.

[0097] The present application also provides a computer program product having a program code, which executes the steps of any of the above-mentioned video recommendation method embodiments when the program code is run in a corresponding processor, controller, computing device or terminal, such as Figure 1Steps S101 to S104 are shown. Those skilled in the art will appreciate that the methods and devices proposed in the embodiments of the present application can be implemented in various forms of hardware, software, firmware, a dedicated processor, or a combination thereof. The dedicated processor may include an application-specific integrated circuit (ASIC), a reduced instruction set computer (RISC), and / or a field programmable gate array (FPGA). The proposed methods and devices are preferably implemented as a combination of hardware and software. The software is preferably installed as an application program on a program storage device. It is typically based on a machine with a computer platform having hardware, such as one or more central processing units (CPUs), a random access memory (RAM), and one or more input / output (I / O) interfaces. An operating system is also typically installed on the computer platform. The various processes and functions described herein may be part of an application program, or a portion thereof may be executed by an operating system.

[0098] Figure 3 Schematic diagram of the terminal provided in the embodiment of the present application. Figure 3 As shown, the terminal 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, the steps in the above-mentioned various video recommendation method embodiments are implemented, such as Figure 1 Alternatively, when the processor 30 executes the computer program 32, the functions of the modules / units in the above-mentioned device embodiments are realized, for example, Figure 2 The functions of the modules 110 to 140 are shown.

[0099] Exemplarily, the computer program 32 may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to complete / implement the solution provided in this application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 32 in the terminal 3.

[0100] The terminal 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that Figure 3 It is only an example of terminal 3 and does not constitute a limitation on terminal 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0101] The processor 30 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0102] The memory 31 can be an internal storage unit of the terminal 3, such as a hard drive or memory of the terminal 3. The memory 31 can also be an external storage device of the terminal 3, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped with the terminal 3. Furthermore, the memory 31 can include both the internal storage unit of the terminal 3 and an external storage device. The memory 31 is used to store the computer program and other programs and data required by the terminal. The memory 31 can also be used to temporarily store data that has been output or is about to be output.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0104] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0105] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0106] In the embodiments provided in this application, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0107] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0108] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0109] If the integrated module / unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned video recommendation method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0110] In addition, the embodiments shown in the drawings of the present application or the features of the various embodiments mentioned in this specification are not necessarily to be understood as independent embodiments. Rather, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the drawings.

[0111] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A video recommendation method, characterized in that: include: After monitoring the update of the recommended video in the current recommendation position, the number of video recommendation position subscriptions and the number of recommended position click users of the recommended video are obtained according to the preset update cycle; Determine the recommendation effect score of the recommended video in the current update period according to the number of subscriptions to the video recommendation position and the number of users who clicked on the recommendation position of the recommended video in the current update period; If the recommendation effect score of the recommended video in the current update cycle is lower than a first preset threshold, the recommended video is replaced with any video other than the recommended video corresponding to the current recommendation position in the current recommendation cycle; If the recommendation effect score of the recommended video in the current update cycle is higher than the first preset threshold, returning to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users of the recommended video according to the preset update cycle and continuing the execution; Determining the recommendation effect score of the recommended video in the current update period according to the number of subscriptions to the video recommendation position and the number of users who clicked on the recommendation position of the recommended video in the current update period includes: Based on the formula Calculate the recommendation effect score of the recommended video in the current update cycle; Among them, S ij,t M represents the recommendation effect score of the recommended video j in the current recommendation position i in the tth update cycle; ij,t M represents the number of video recommendation position subscriptions for the user who subscribed to the recommended video j from the current recommendation position i during the tth update period; i,t M represents the number of users who clicked on the recommended position i in the tth update cycle; j represents the total number of subscriptions for the recommended video j; v and w are weight values, and v+w=1.

2. The video recommendation method according to claim 1, characterized in that Before replacing the recommended video with any video other than the recommended video corresponding to the current recommendation position in the current recommendation period, the method further includes: Obtain the popularity rating and online time of each video on the platform according to the preset recommendation cycle; Determine the freshness score of each video based on the online time, and the online time is negatively correlated with the freshness score; Perform a weighted summation of each video's popularity score and freshness score to determine the current recommendation score for each video; Sort all videos in descending order according to the current recommendation score, and determine the N videos corresponding to the current recommendation position based on the ranking of each video and the ranking range corresponding to each recommendation position, where N≥2.

3. The video recommendation method according to claim 2, characterized in that The popularity score of each video on the platform is obtained according to the preset recommendation cycle, including: Obtain popularity rankings of each video on the platform on multiple third-party platforms according to a preset recommendation cycle; For any video, the popularity score of the video on each third-party platform is determined based on the popularity ranking of the video on each third-party platform in the current recommendation cycle, and the popularity ranking is negatively correlated with the popularity score; the popularity score of the video on each third-party platform in the current recommendation cycle is weighted and summed to obtain the popularity score corresponding to the video in the current recommendation cycle.

4. The video recommendation method according to claim 1, wherein: If the recommendation effect score of the recommended video in the current update cycle is higher than the first preset threshold, returning to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users of the recommended video according to the preset update cycle and continuing to execute, including: If the recommendation effect score of the recommended video is greater than or equal to the first preset threshold and less than the second preset threshold, determining whether the recommended video is the video corresponding to the current recommendation position in the current recommendation period; If the recommended video is a video corresponding to the current recommendation position in the current recommendation cycle, then returning to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update cycle and continuing the execution; If the recommendation effect score of the recommended video is not less than the second preset threshold, the process returns to the step of obtaining the number of video recommendation position subscriptions and the number of users who click on the recommended position of the recommended video according to the preset update period and continues to execute.

5. The video recommendation method according to claim 4, characterized in that After determining whether the recommended video is a video corresponding to the current recommendation position within a current recommendation period, the method further includes: If the recommended video is not the video corresponding to the current recommendation position in the current recommendation period, any video corresponding to the current recommendation position in the current recommendation period is used to replace the recommended video.

6. A video recommendation device, characterized in that: include: The recommendation effect data acquisition module is used to obtain the number of video recommendation position subscriptions and the number of recommended position click users of the recommended video according to a preset update cycle after monitoring the update of the recommended video in the current recommendation position; A recommendation effect score acquisition module is used to determine the recommendation effect score of the recommended video in the current update period according to the number of subscriptions to the video recommendation position and the number of users who clicked on the recommendation position of the recommended video in the current update period; A recommended video updating module, configured to replace the recommended video with any video other than the recommended video corresponding to the current recommended position in the current recommendation period, if the recommendation effect score of the recommended video in the current update period is lower than a first preset threshold; a recommended video holding module configured to return to the step of obtaining the number of video recommendation position subscriptions and the number of recommended position click users for the recommended video according to the preset update period if the recommendation effect score of the recommended video in the current update period is higher than the first preset threshold; The recommendation effect score acquisition module includes: Based on the formula Calculate the recommendation effect score of the recommended video in the current update cycle; Among them, S ij,t M represents the recommendation effect score of the recommended video j in the current recommendation position i in the tth update cycle; ij,t M represents the number of video recommendation position subscriptions for the user who subscribed to the recommended video j from the current recommendation position i during the tth update period; i,t M represents the number of users who clicked on the recommended position i in the tth update cycle; j represents the total number of subscriptions for the recommended video j; v and w are weight values, and v+w=1.

7. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the video recommendation method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the video recommendation method according to any one of claims 1 to 5 are implemented.

Images