Video recommendation method and device, electronic equipment and storage medium

Abstract

The invention provides a video recommendation method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence such as intelligent recommendation, Internet and natural language processing. The method comprises the following steps: in response to a monitored behavior of exiting from a live broadcast channel of a short video platform, determining target content from live broadcast content watched before exiting; and in response to the monitored behavior of continuing to watch the non-live video in the short video platform and determining that the recommendation condition is met, selecting a first recommendation video from M recommendation videos corresponding to the target content, and playing the first recommendation video, M being a positive integer.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to video recommendation methods, devices, electronic devices and storage media in the fields of intelligent recommendation, the Internet and natural language processing. Background Art

[0002] Short video platforms are a very popular form of content on the current Internet. They can provide users with rich and diverse content consumption experiences through the display of short videos. Summary of the invention

[0003] The present disclosure provides a video recommendation method, device, electronic device and storage medium.

[0004] A video recommendation method, comprising:

[0005] In response to monitoring an act of exiting a live broadcast channel of a short video platform, determining target content from the live broadcast content watched before the exit;

[0006] In response to monitoring the behavior of continuing to watch non-live videos on the short video platform and determining that the recommendation conditions are met, a first recommended video is selected from M recommended videos corresponding to the target content, and the first recommended video is played, where M is a positive integer.

[0007] A video recommendation device, comprising: a target determination module and a video recommendation module;

[0008] The target determination module is used to determine the target content from the live broadcast content watched before the exit in response to monitoring the exit from the live broadcast channel of the short video platform;

[0009] The video recommendation module is used to respond to monitoring the behavior of continuing to watch non-live videos on the short video platform and determining that the recommendation conditions are met, select a first recommended video from M recommended videos corresponding to the target content, and play the first recommended video, where M is a positive integer.

[0010] An electronic device, comprising:

[0011] at least one processor; and

[0012] a memory communicatively connected to the at least one processor; wherein,

[0013] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0014] A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method as described above.

[0015] A computer program product comprises a computer program / instruction, wherein the computer program / instruction implements the method described above when executed by a processor.

[0016] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0018] Figure 1 A flowchart of an embodiment of the video recommendation method disclosed in the present invention;

[0019] Figure 2 Schematic diagram of the structure of the video recommendation device embodiment 200 of the present disclosure;

[0020] Figure 3 A schematic block diagram of an electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0021] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0022] In addition, it should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0023] Figure 1 Flow chart of an embodiment of the video recommendation method disclosed in the present invention. Figure 1 As shown, the following specific implementation methods are included.

[0024] In step 101, in response to monitoring the behavior of exiting a live broadcast channel of a short video platform, target content is determined from the live broadcast content watched before the exit.

[0025] In step 102, in response to monitoring the behavior of continuing to watch non-live videos on the short video platform and determining that the recommendation conditions are met, a first recommended video is selected from M recommended videos corresponding to the target content, and the first recommended video is played, where M is a positive integer.

[0026] Short video platforms usually provide live broadcast channels through which users can watch live content. According to traditional processing methods, when a user exits the live broadcast channel, if he has not exited the short video platform, the system will recommend videos (short videos) to the user according to the default recommendation algorithm and play them. However, the recommended videos are usually not related to the live content watched by the user.

[0027] By adopting the scheme described in the above method embodiment, based on the live broadcast content watched by the user, videos related to the live broadcast content can be recommended to the user after the user exits the live broadcast channel, thereby utilizing the user's interest information in the live broadcast, thereby improving the accuracy of the recommendation results and the consistency of the content, and improving the user experience, etc.

[0028] In response to monitoring the behavior of exiting the live broadcast channel of the short video platform, that is, determining that the user has exited the live broadcast channel of the short video platform, the target content can be first determined based on the live broadcast content watched before the exit.

[0029] In some embodiments of the present disclosure, in response to determining that the number of live content watched is one, the live content can be determined as the target content, and in response to determining that the number of live content watched is greater than one, a live content selected from the live content can be determined as the target content.

[0030] When a user watches live content on a live broadcast channel, he or she may have watched only one live content, such as the live content of ** brand barbecue buffet, or he or she may have watched multiple live content separately, such as both the live content of ** brand barbecue buffet and the live content of ** brand fast food, etc. If only one live content was watched, then the live content can be directly determined as the target content. If multiple live content were watched separately, then one live content can be selected from them and the selected live content can be determined as the target content.

[0031] In some embodiments of the present disclosure, the following processing can be performed for any live broadcast content: determine the interest evaluation result of the live broadcast content based on the viewing time of the live broadcast content and the interactive behavior that occurs with respect to the live broadcast content; based on the interest evaluation result, select the most interesting live broadcast content from various live broadcast contents, and determine the selected live broadcast content as the target content.

[0032] Among them, the interactive behavior may include various interactive behaviors such as posting comments, liking, sharing, forwarding, and clicking on product links.

[0033] As a possible implementation method, for any live content, the live content can be scored from two dimensions: the length of time the live content is watched and the interactive behavior that occurs with respect to the live content. Then, the two scores can be multiplied by the corresponding weights respectively, and the two products can be added together to obtain the interest score of the live content, that is, the interest evaluation result. Among them, the scoring principle can be as follows: the longer the viewing time, the higher the corresponding score, and the more types (number of times) of interactive behaviors that occur, the higher the corresponding score. While following the scoring principle, the specific scoring method is not limited. In this way, after obtaining the interest score of each live content respectively, the live content corresponding to the interest score with the largest value can be selected. For the user, the selected live content is the target content of the greatest interest, and the target content of the greatest interest refers to the target content with the highest purchase desire of the user.

[0034] Assume that a user watched the live broadcast content of brand a fast food and the live broadcast content of brand b fast food respectively. When watching brand a fast food, the user watched for 30 seconds and clicked on the corresponding product link, such as a coupon for 3 hamburgers for 59 yuan. Then, the user watched the live broadcast content of brand b fast food for 1 minute and also clicked on the corresponding product link. Obviously, the interest score of the live broadcast content of brand b fast food will be higher than the interest score of the live broadcast content of brand a fast food. Therefore, the live broadcast content of brand b fast food can be determined as the target content.

[0035] It can be seen that by adopting the above processing method, the target content watched by the user can be determined efficiently and accurately based on information such as viewing time and interactive behavior during the viewing process, thus laying a good foundation for subsequent processing.

[0036] After determining that the user has exited the live broadcast channel, if it is determined that the user continues to watch non-live broadcast videos on the short video platform, then when it is determined that the recommendation condition is met, the first recommended video can be selected from the M recommended videos corresponding to the target content, and the first recommended video can be played. The specific value of M can be determined according to actual needs, such as 5.

[0037] In some embodiments of the present disclosure, the M recommended videos may include: M videos matching the keywords selected from videos uploaded to the short video platform based on the keywords corresponding to the target content.

[0038] That is, M recommended videos corresponding to the target content can be pre-set. Specifically, multiple keywords can be determined according to the target content, and the multiple keywords can reflect the main content of the target content. Then, for each video uploaded to the short video platform, according to the tags and other information of each video, M videos that best match the multiple keywords can be determined as the required M recommended videos.

[0039] For example, assuming that the target content is the live broadcast content of ** brand barbecue buffet, the corresponding M recommended videos may include store exploration videos of ** brand barbecue buffet by different store exploration bloggers.

[0040] Through the above processing, it can be ensured that the M recommended videos are all videos that are closely related to the target content in terms of content, thereby improving the coherence of the content and further improving the user experience.

[0041] When it is determined that the recommendation condition is met, the first recommended video can be selected from the M recommended videos, and the first recommended video can be played. How to determine whether the recommendation condition is met can be determined according to actual needs. For example, if it is determined that the user has watched two videos (videos recommended according to the traditional recommendation algorithm) after exiting the live broadcast channel, then it can be considered that the recommendation condition is met, and the first recommended video can be selected from the M recommended videos.

[0042] In some embodiments of the present disclosure, the following processing can be performed for any recommended video: based on the video attribute information and user attribute information of the recommended video, a matching evaluation result between the recommended video and the user is determined; based on the matching evaluation result, the most matching recommended video is selected from M recommended videos, and the selected recommended video is determined as the first recommended video.

[0043] The specific content included in the video attribute information can be determined according to actual needs, such as the number of likes, comments, favorites, reposts, and the number of fans of the blogger (the publisher of the video). For users who are the objects of video recommendation, the specific content included in their user attribute information can also be determined according to actual needs, such as the user's historical viewing behavior, interest tags, age, gender, and fan relationship with the blogger. Among them, the fan relationship with the blogger can refer to whether the blogger is followed. If a user follows a blogger, it means that the user is more recognized by the blogger. Accordingly, recommending relevant videos of the blogger recognized by the user can improve the accuracy of the recommendation results and improve the user experience.

[0044] The matching evaluation result may refer to a matching score. For example, for any recommended video, the video attribute information and user attribute information of the recommended video may be used as inputs of a pre-trained scoring model to obtain an output matching score, and then the recommended video corresponding to the matching score with the largest value may be selected as the first recommended video.

[0045] In the above processing method, the video attribute information and the user attribute information are combined to determine the first recommended video recommended to the user, thereby further improving the accuracy of the recommendation result.

[0046] In addition, in some embodiments of the present disclosure, any recommended video may include: a product link of the product corresponding to the recommended video. Accordingly, when the first recommended video is played, the product link corresponding to the first recommended video may be displayed, and in response to monitoring the click behavior on the product link, the corresponding product transaction page may be jumped to display, and the product transaction page refers to the product purchase page.

[0047] For any recommended video, if it originally includes the product link of the corresponding product, then the product link can be used directly. If it does not originally include the product link, then the product link matching the recommended video can be determined, and the determined product link can be mounted on the recommended video in the form of a card.

[0048] In this way, when the first recommended video is played, the product link corresponding to the first recommended video can be displayed at the same time. Moreover, if it is determined that the user clicks on the product link, the product transaction page corresponding to the product link can be jumped and displayed to facilitate the user to purchase the product.

[0049] Through the above processing, the recommended video and the product link can be closely integrated, so that the user can directly purchase the corresponding product when watching the recommended video, thereby reducing the user's operation complexity and improving the user experience.

[0050] In addition, in some embodiments of the present disclosure, in response to determining that a video switching instruction is obtained during the process of playing the first recommended video, and determining that the conditions for continuing recommendation are met, a second recommended video can be selected from unselected recommended videos, and the second recommended video can be played.

[0051] In some embodiments of the present disclosure, the condition for continued recommendation may include: the duration of watching the first recommended video is greater than a predetermined threshold, or a predetermined interactive behavior occurs for the first recommended video. The specific value of the threshold may be determined according to actual needs, and the specific behavior of the predetermined interactive behavior may also be determined according to actual needs.

[0052] When the user is watching the first recommended video, he can issue a video switching instruction, such as by sliding the screen to issue a video switching instruction. To avoid disturbing the user, the video recommended by the traditional recommendation algorithm can be played next, or if it is determined that the continued recommendation condition is met, the second recommended video can be selected from the unselected recommended videos in the M recommended videos and played. For example, if it is determined that the user has watched the first recommended video for a long time, or if it is determined that the user has collected the first recommended video, then it can be considered that the user is more interested in the first recommended video, and accordingly, the second recommended video can continue to be played for the user.

[0053] For example, assuming that the value of M is 5, that is, there are 5 recommended videos in total, namely Recommended Video 1, Recommended Video 2, Recommended Video 3, Recommended Video 4 and Recommended Video 5, and assuming that the first recommended video is Recommended Video 3, then if it is determined that the user has watched Recommended Video 3 for a long time, or if it is determined that the user has collected Recommended Video 3, the second recommended video, such as Recommended Video 2, can be selected from the remaining Recommended Video 1, Recommended Video 2, Recommended Video 4 and Recommended Video 5, and Recommended Video 2 can be played.

[0054] By adopting the above processing method, the subsequent processing method can be dynamically determined by continuously tracking the user's behavior. This is very flexible and convenient, and can achieve more personalized and resonant video recommendations.

[0055] Generally speaking, after playing the second recommended video, other videos recommended in the manner described in the present disclosure will not be played for the user to avoid causing excessive disturbance to the user, affecting the user experience, etc.

[0056] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are expressed as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the described order of actions, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0057] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0058] Figure 2 FIG. 2 is a schematic diagram of the composition structure of the video recommendation device embodiment 200 of the present disclosure. Figure 2 As shown, it may include: a target determination module 201 and a video recommendation module 202.

[0059] The target determination module 201 is used to determine the target content from the live content watched before the exit in response to monitoring the behavior of exiting the live channel of the short video platform.

[0060] The video recommendation module 202 is used to respond to monitoring the behavior of continuing to watch non-live videos on the short video platform and determining that the recommendation conditions are met, select the first recommended video from M recommended videos corresponding to the target content, and play the first recommended video, where M is a positive integer.

[0061] By adopting the scheme described in the above-mentioned device embodiment, based on the live content watched by the user, videos related to the live content can be recommended to the user after the user exits the live channel, thereby utilizing the user's interest information in the live broadcast, thereby improving the accuracy of the recommendation results and the consistency of the content, and improving the user experience, etc.

[0062] In response to monitoring the behavior of exiting the live broadcast channel of the short video platform, that is, determining that the user has exited the live broadcast channel of the short video platform, the target determination module 201 can first determine the target content based on the live broadcast content watched before exiting.

[0063] In some embodiments of the present disclosure, in response to determining that the number of live content watched is one, the target determination module 201 may determine the live content as the target content, and in response to determining that the number of live content watched is greater than one, may determine a live content selected from the live content as the target content.

[0064] Specifically, in some embodiments of the present disclosure, the target determination module 201 can perform the following processing for any live broadcast content: determine the interest evaluation result of the live broadcast content based on the viewing time of the live broadcast content and the interactive behavior that occurs with respect to the live broadcast content; based on the interest evaluation result, select the most interesting live broadcast content from various live broadcast contents, and determine the selected live broadcast content as the target content.

[0065] Among them, the interactive behavior may include various interactive behaviors such as posting comments, liking, sharing, forwarding, and clicking on product links.

[0066] As a possible implementation method, for any live content, the live content can be scored from two dimensions: the length of time the live content is watched and the interactive behavior that occurs with respect to the live content. The two scores can then be multiplied by the corresponding weights, and the two products can be added together to obtain the interest score of the live content, i.e., the interest evaluation result. In this way, after obtaining the interest scores of each live content, the live content corresponding to the interest score with the largest value can be selected and determined as the target content.

[0067] After determining that the user has exited the live broadcast channel, if the video recommendation module 202 determines that the user continues to watch non-live broadcast videos on the short video platform, then when it is determined that the recommendation conditions are met, the first recommended video can be selected from the M recommended videos corresponding to the target content and played.

[0068] In some embodiments of the present disclosure, the M recommended videos may include: M videos matching the keywords selected from videos uploaded to the short video platform based on the keywords corresponding to the target content.

[0069] In addition, in some embodiments of the present disclosure, the video recommendation module 202 may perform the following processing for any recommended video: determine a matching evaluation result between the recommended video and the user based on the video attribute information and user attribute information of the recommended video, select the most matching recommended video from the M recommended videos based on the matching evaluation result, and determine the selected recommended video as the first recommended video.

[0070] The matching evaluation result may refer to a matching score. For example, for any recommended video, the video attribute information and user attribute information of the recommended video may be used as inputs of a pre-trained scoring model to obtain an output matching score, and then the recommended video corresponding to the matching score with the largest value may be selected as the first recommended video.

[0071] In addition, in some embodiments of the present disclosure, any recommended video may include: a product link of the product corresponding to the recommended video. Accordingly, when playing the first recommended video, the video recommendation module 202 may display the product link corresponding to the first recommended video, and in response to detecting a click on the product link, may jump to display the corresponding product transaction page.

[0072] Furthermore, in some embodiments of the present disclosure, in response to determining that a video switching instruction is obtained during the process of playing the first recommended video and determining that the conditions for continuing recommendation are met, the video recommendation module 202 can select a second recommended video from the recommended videos that have not been selected, and can play the second recommended video.

[0073] In some embodiments of the present disclosure, the condition for continuing recommendation may include: the duration of watching the first recommended video is greater than a predetermined threshold, or a predetermined interactive behavior occurs for the first recommended video.

[0074] When the user is watching the first recommended video, he can issue a video switching instruction, such as by sliding the screen to issue a video switching instruction. To avoid disturbing the user, the video recommended by the traditional recommendation algorithm can be played next, or if it is determined that the continued recommendation condition is met, the second recommended video can be selected from the unselected recommended videos in the M recommended videos and played. For example, if it is determined that the user has watched the first recommended video for a long time, or if it is determined that the user has collected the first recommended video, it can be considered that the user is more interested in the first recommended video, and accordingly, the second recommended video can continue to be played for the user.

[0075] Figure 2 The specific working process of the illustrated device embodiment can refer to the relevant description in the aforementioned method embodiment and will not be described in detail.

[0076] In summary, by adopting the solution described in the present disclosure, live broadcast content, user behavior, and product mounting can be combined to provide users with a personalized and intelligent video recommendation experience, and improve the accuracy of recommendation results.

[0077] The solution disclosed in the present invention can be applied to the field of artificial intelligence, especially in the fields of intelligent recommendation, Internet and natural language processing. Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It has both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing. Artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0078] The live broadcast content and recommended videos in the embodiments described in this disclosure are not targeted at a specific user and do not reflect the personal information of a specific user. In the technical solution of this disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0079] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0080] Figure 3 A schematic block diagram of an electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0081] like Figure 3As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0082] A number of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0083] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI, Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSP, Digital Signal Processing), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the methods described in the present disclosure. For example, in some embodiments, the methods described in the present disclosure may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the methods described in the present disclosure may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute the method described in the present disclosure in any other appropriate manner (for example, by means of firmware).

[0084] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard parts (ASSPs), system on chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0085] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0086] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM, Electronically Programmable Read-Only Memory), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM, Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0087] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0088] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by digital data communication (e.g., a communication network) in any form or medium. Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0089] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0090] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0091] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A video recommendation method, comprising: In response to monitoring an act of exiting a live broadcast channel of a short video platform, determining target content from the live broadcast content watched before the exit; In response to monitoring the behavior of continuing to watch non-live videos on the short video platform and determining that the recommendation conditions are met, a first recommended video is selected from M recommended videos corresponding to the target content, and the first recommended video is played, where M is a positive integer.

2. The method according to claim 1, wherein: Determining the target content from the live broadcast content watched before exiting includes: In response to determining that the number of the watched live content is one piece, determining the live content as the target content; In response to determining that the number of the watched live content is greater than one, a live content selected from the live content is determined as the target content.

3. The method according to claim 2, wherein: The step of determining a live content selected from various live content as the target content includes: For any live broadcast content, the following processing is performed respectively: combining the viewing time of the live broadcast content and the interactive behavior occurring with respect to the live broadcast content, determining the interest evaluation result of the live broadcast content; According to the interest evaluation result, the most interesting live content is selected from various live content, and the selected live content is determined as the target content.

4. The method according to claim 1, wherein: The M recommended videos include: M videos matching the keywords selected from videos uploaded to the short video platform according to the keywords corresponding to the target content.

5. The method according to claim 1, wherein: The selecting the first recommended video from the M recommended videos corresponding to the target content comprises: For any recommended video, the following processing is performed respectively: according to the video attribute information of the recommended video and the user attribute information of the user as the video recommendation object, the matching evaluation result between the recommended video and the user is determined; According to the matching evaluation result, the most matching recommended video is selected from the M recommended videos, and the selected recommended video is determined as the first recommended video.

6. The method according to claim 1, wherein: Each recommended video includes: a product link of the product corresponding to the recommended video; The playing of the first recommended video includes: displaying a product link corresponding to the first recommended video, and in response to detecting a click on the product link, jumping to display a corresponding product transaction page.

7. The method according to any one of claims 1 to 6, further comprising: In response to determining that a video switching instruction is obtained during the playing of the first recommended video, and determining that a continued recommendation condition is met, a second recommended video is selected from unselected recommended videos, and the second recommended video is played.

8. The method according to claim 7, wherein: The condition for continuing recommendation includes: the duration of watching the first recommended video is greater than a predetermined threshold, or a predetermined interactive behavior occurs for the first recommended video.

9. A video recommendation device, comprising: Target determination module and video recommendation module; The target determination module is used to determine the target content from the live broadcast content watched before the exit in response to monitoring the exit from the live broadcast channel of the short video platform; The video recommendation module is used to respond to monitoring the behavior of continuing to watch non-live videos on the short video platform and determining that the recommendation conditions are met, select a first recommended video from M recommended videos corresponding to the target content, and play the first recommended video, where M is a positive integer.

10. The device according to claim 9, wherein: In response to determining that the number of live content watched is one, the target determination module determines the live content as the target content, and in response to determining that the number of live content watched is greater than one, determines one live content selected from the live content as the target content.

11. The device according to claim 10, wherein: The target determination module performs the following processing for any live broadcast content: determines the interest evaluation result of the live broadcast content based on the viewing time of the live broadcast content and the interactive behavior on the live broadcast content; based on the interest evaluation result, selects the most interesting live broadcast content from various live broadcast contents, and determines the selected live broadcast content as the target content.

12. The device according to claim 9, wherein: The M recommended videos include: M videos matching the keywords selected from videos uploaded to the short video platform according to the keywords corresponding to the target content.

13. The device according to claim 9, wherein: The video recommendation module performs the following processing for any recommended video: determines a matching evaluation result between the recommended video and the user based on the video attribute information of the recommended video and the user attribute information of the user to whom the video is recommended; selects the most matching recommended video from the M recommended videos based on the matching evaluation result, and determines the selected recommended video as the first recommended video.

14. The device according to claim 9, wherein: Each recommended video includes: a product link of the product corresponding to the recommended video; When playing the first recommended video, the video recommendation module displays the product link corresponding to the first recommended video, and in response to detecting a click on the product link, jumps to display the corresponding product transaction page.

15. The device according to any one of claims 9 to 14, wherein: The video recommendation module is further used to, in response to determining that a video switching instruction is obtained during the playing of the first recommended video and determining that a continued recommendation condition is met, select a second recommended video from unselected recommended videos and play the second recommended video.

16. The device according to claim 15, wherein: The condition for continuing recommendation includes: the duration of watching the first recommended video is greater than a predetermined threshold, or a predetermined interactive behavior occurs for the first recommended video.

17. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1 to 8.

19. A computer program product, comprising a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images