Multimedia playing method and device, electronic equipment and storage medium

Abstract

The invention relates to a multimedia playing method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the playing characteristics of a target user under the condition that the target playing operation of the target user for multimedia is received, and the playing characteristics comprise the corresponding target characteristics when the user plays the multimedia; obtaining a target playing strategy corresponding to the target category crowd based on the playing characteristics; and controlling the playing of the multimedia based on the target playing strategy. Therefore, when a user watches multimedia such as a video, targeted playing adjustment can be realized through the corresponding playing strategies for different users, so that the watching requirements of the user are met, and the playing efficiency of the video is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of multimedia technology, and in particular to a multimedia playback method, device, electronic device and storage medium. Background Art

[0002] As terminal products such as mobile phones become more and more popular, users can easily watch online videos through mobile phones and other terminals. However, different users may have different situations when watching videos, so different users may react differently to video freezes. If a relatively single video playback strategy is adopted, it may not meet the viewing needs of most users, resulting in low video playback efficiency. Summary of the invention

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

[0004] According to one aspect of the present disclosure, a multimedia playback method is provided, the method comprising:

[0005] When receiving a target play operation of a target user for multimedia, obtaining a play feature of the target user, wherein the play feature includes a target feature corresponding to the user when playing multimedia;

[0006] Acquire a target playback strategy corresponding to the target category of people based on the playback characteristics;

[0007] The playing of the multimedia is controlled based on the target playing strategy.

[0008] According to a second aspect of the present disclosure, a multimedia playback device is provided, the device comprising:

[0009] A play feature acquisition module, configured to acquire the play feature of the target user upon receiving a target play operation of the target user for multimedia, wherein the play feature includes a target feature corresponding to the user when playing multimedia;

[0010] A strategy determination module, used for obtaining a target playback strategy corresponding to the target category of people based on the playback characteristics;

[0011] The playback control module is used to control the playback of the multimedia based on the target playback strategy.

[0012] According to a third aspect of the present disclosure, an electronic device is provided, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0013] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above method of the present disclosure is implemented.

[0014] The multimedia playback method, device, electronic device, and storage medium provided by the embodiments of the present disclosure can obtain the playback characteristics of the target user when receiving the target operation of the target user on the multimedia. The target playback strategy corresponding to the target category of people is obtained based on the playback characteristics, and the playback of the multimedia is controlled based on the target playback strategy. In this way, when the user watches multimedia such as videos, targeted playback adjustments can be implemented for different users through corresponding playback strategies to meet the viewing needs of the users, thereby improving the playback efficiency of the video. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Further details, features and advantages of the present disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0016] Figure 1 A schematic diagram of a scenario provided for an exemplary embodiment of the present disclosure;

[0017] Figure 2 A flowchart of a multimedia playback method provided by an exemplary embodiment of the present disclosure;

[0018] Figure 3 A schematic block diagram of functional modules of a multimedia playback device provided by an exemplary embodiment of the present disclosure;

[0019] Figure 4 A structural block diagram of an electronic device provided for an exemplary embodiment of the present disclosure;

[0020] Figure 5 A structural block diagram of a computer system provided for an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0022] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0023] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0024] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0025] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0026] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0027] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0028] As an optional but non-limiting implementation, in response to receiving an active request from the user, the method of sending a prompt message to the user may be, for example, a pop-up window, in which the prompt message may be presented in text. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device. It is understandable that the above notification and the process of obtaining user authorization are only illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0029] On the end video playback platform, different users may have significant behavioral differences when watching videos. For example, when faced with video freezes or frame drops, users who are highly sensitive to freezes will quickly swipe away, while users who are less sensitive to freezes tend to wait a little longer.

[0030] Therefore, in order to provide users with a better playback performance experience, a common approach is to design a series of user tags based on statistical information, such as the jamming exit rate or image quality sensitivity, to adjust the playback strategy. However, since user performance-related statistical tags often have low coverage or low reliability, for example, if a user has only experienced one jam in the past seven days, then statistical values ​​such as the jamming exit rate will lose their meaning. At the same time, tags such as image quality sensitivity are difficult to measure accurately. In addition, the video playback process involves a variety of internal and external factors, which cannot be accurately described by simple statistical information.

[0031] Therefore, the disclosed embodiment predicts the user's behavior when the video playback freezes, such as sliding away or staying, in order to learn the playback characteristics of the user group. The playback characteristics can integrate the user's perception of various performance events, alleviate the problem of lack of statistical samples, and take into account the many complex factors of each playback behavior. And the disclosed embodiment integrates the playback characteristics into the video playback strategy optimization process to provide users with better playback strategies and improve the efficiency of video playback. It should be noted that the disclosed embodiment takes video as an example for explanation, and it can also be multimedia such as audio or pictures, and the embodiment is not limited to this. In the embodiment, the playback characteristics can be learned in combination with sparse neural network technology.

[0032] In the embodiment, the complex internal and external factors in the video playback process are divided into user playback, video aspects and environmental aspects, and corresponding features are designed. By constructing a user behavior prediction task when a freeze occurs, such as a binary classification task of sliding away or staying, a large-scale neural network is used for target modeling to learn unique playback features for the user group.

[0033] In the embodiments provided in the present disclosure, playback feature learning can be divided into three parts: task construction, feature design, and model design.

[0034] In the task construction part, in order to highlight the impact of performance-related characteristics on the user's video viewing process, the embodiment of the present disclosure selects events in which the first frame freeze duration during the user's video playback is higher than a certain threshold, or the number of freezes exceeds a certain threshold as samples, and predicts whether the user will slide away or continue to wait in this case.

[0035] In the embodiment, in a freeze event, whether the user slides away or stays to wait is related to the user's own situation, and is also closely related to the severity of freeze, tolerance, and video clarity. Therefore, through training on this task, the user's playback features can be effectively refined, such as the number of plays or the length of play, and multiple features can also be obtained by the user's favorites or likes, avoiding interference from other factors.

[0036] In the model design part, sparse neural networks can be used to model the above multi-class features. The overall model structure is as follows: Figure 1 As shown. Two methods are implemented by using the sparse embedding operation in large-scale machine learning, mapping each feature to its corresponding low-dimensional vector, and concatenating all the vectors as the input of the neural network. Among them, in order to learn the performance-related representation of the user, the embodiment uses the high-dimensional concatenated vector of the target playback feature as input, and compresses it into a low-dimensional vector through the first neural network DNN (Deep Neural Networks), that is, the initial playback feature (user embedding). Then it is concatenated with the vectors of video features and environmental features and input into the second deep neural network DNN, and finally a binary classification model is trained to predict whether the user will slide away or stay. In an embodiment, the target playback feature may include the user's preference for the video or the quality of the network during the historical viewing period.

[0037] Through the above method, the user's playback characteristics can be obtained, and the model can perform incremental learning as new samples appear, thereby dynamically reflecting the user's performance-related preference characteristics. It should be noted that the above prediction of user leaving or staying is for the purpose of obtaining playback characteristics.

[0038] In the embodiment, after obtaining the playback features through the above model training, the video playback strategy can be adjusted and optimized in the following manner.

[0039] Specifically, users with strong performance statistical significance can be obtained, for example, users whose freeze times in a certain historical period exceed a certain threshold can be regarded as users with strong performance statistical significance, and their corresponding playback features are clustered to obtain K cluster families and K cluster centers, where K is a positive integer. For example, clustering can be performed by unsupervised learning k-means.

[0040] For example, if the platform has several users with strong performance statistical significance, clustering can be performed based on the playback characteristics of these users, so that k clusters and k cluster centers can be obtained.

[0041] As for other users with weak statistical significance, for example, users whose freeze times in a certain historical period are lower than a certain threshold can be regarded as users with weak statistical significance. The distances between their playback features and the above-mentioned K cluster centers can be calculated to determine which cluster the user belongs to. For example, the cluster with the smallest distance can be regarded as the cluster to which the user belongs. For example, if the platform has several users with weak statistical significance, the distances between the playback features of these users and the above-mentioned K cluster centers can be calculated, and the cluster to which these users belong can be determined based on the distance. In this way, according to which cluster the user belongs to, the corresponding video playback strategy can be adopted to adjust the user's playback strategy during video playback to improve the efficiency of video playback.

[0042] In the embodiment, in order to obtain the video playback strategies corresponding to the above-mentioned clusters, a crowd analysis can be performed on the users in each cluster, and users with strong performance statistical significance can be obtained from each cluster. According to the performance label values ​​corresponding to the users with strong performance statistical significance, some typical crowd clusters are selected, such as people with high lag sensitivity who have a preference for a certain category, and can participate in the adjustment of subsequent playback strategies. In the embodiment, the video playback strategy corresponding to the typical crowd cluster in the cluster can be used as the video playback strategy of each user in the cluster, and the user adjusts the video playback of the user during the video playback process.

[0043] In the embodiment, the adjustment of the playback strategy mainly affects the video selection and preloading process on the terminal. For example, for users who are highly sensitive to lags, the image quality during playback can be appropriately reduced to ensure smooth playback. For users who are less sensitive to lags, the playback image quality can be appropriately improved to improve the user's playback experience and improve video playback efficiency.

[0044] Based on the above embodiments, in another embodiment provided by the present disclosure, the present disclosure also provides a multimedia playback method, such as Figure 2 As shown, the method may include the following steps:

[0045] In step S210, when a target user's target playback operation for multimedia is received, playback features of the target user are acquired.

[0046] The playback features include target features corresponding to the user when playing multimedia.

[0047] In an embodiment, the playback feature may include relevant features generated by the user when playing multimedia, such as user-related playback features, which may include the user's playback duration or playback operation, etc., and may also include device-related features, such as device type, network status, or freeze conditions, etc. In the embodiment, the multimedia is still described as a video, and the embodiment is not limited to this. In an embodiment, the target feature may include one or a combination of the target playback feature, video feature, and environmental feature in the above-mentioned embodiment. The target playback feature may be some of the above-mentioned playback features, etc.

[0048] It should be noted that when it is necessary to obtain the user's relevant characteristics or related information, the user will be reminded through pop-up windows or other means, and the information will only be obtained after obtaining the user's consent.

[0049] In the embodiment, the target playback operation may be a viewing operation of the target user on the multimedia, or may be a forwarding, collection or downloading operation, etc., but the embodiment is not limited thereto.

[0050] In an embodiment, the playback features can be used as the input of the first preset model to output the initial playback features. The initial playback features, video features and environmental features are used as the input of the second preset model to output the playback features. Among them, the first preset model is used to compress the spliced ​​features into a low-dimensional vector. The first preset model and the second preset model can be the first DNN model and the second DNN model corresponding to the above embodiments respectively. For details, please refer to the description of the above embodiments, which will not be repeated here.

[0051] In step S220, a target playback strategy corresponding to the target category of people is obtained based on the playback characteristics.

[0052] In an embodiment, the target category population described by the target user can be determined based on the playback characteristics of the target user, so as to control the video watched by the target user through the playback strategy corresponding to the target category population, for example, pushing or switching videos to the target user with fluency as the priority, or pushing or switching videos to the target user with clarity as the priority, etc.

[0053] In an embodiment, the crowd can be divided into multiple categories in advance, and each category of the crowd has a corresponding playback strategy. For example, the user group is divided into a group of people who are highly sensitive to freezes, a group of people who prefer a certain category, or a group of people who are less sensitive to freezes, etc. For example, for the group of people who are highly sensitive to freezes, the corresponding playback strategy can be to adjust the clarity of the video when the user often freezes, and try to avoid freezes during video playback. For example, for a group of people who prefer a certain category, since this group of people is more enthusiastic about a certain preference, the corresponding playback strategy can be that when pushing a certain category preference video to users in the group, the clarity of the video can be given priority to ensure the playback quality of the video, so that even when the video freezes, the user can accept it. For the group of people who are less sensitive to freezes, the clarity of the played video can be guaranteed as much as possible to meet the viewing quality of the user.

[0054] Therefore, based on the playback characteristics of the target user, the target category population to which the target user belongs can be determined, and the target playback strategy corresponding to the target category population can be obtained, so as to adjust the video playback of the target user when playing the video through the target playback strategy to meet the user's viewing needs.

[0055] In step S230, the multimedia playback is controlled based on the target playback strategy.

[0056] In an embodiment, if the target user belongs to a group of users with low sensitivity to freezes, this type of user pays more attention to the quality of the video and is not too sensitive to freezes. Therefore, the corresponding playback strategy may be, for example, to ensure the clarity and quality of the video as much as possible, and the user can accept it even if freezes occur.

[0057] The multimedia playback method provided by the embodiment of the present disclosure can obtain the playback characteristics of the target user when receiving the target operation of the target user on the multimedia. Based on the playback characteristics, the target category of people to which the target user belongs can be determined, and by obtaining the target playback strategy corresponding to the target category of people, the playback of the multimedia can be controlled based on the target playback strategy. In this way, when the user watches multimedia such as videos, targeted playback adjustments can be implemented for different users through corresponding playback strategies to meet the viewing needs of the users, thereby improving the playback efficiency of the video.

[0058] Based on the above embodiment, in another embodiment provided by the present disclosure, the method may also include:

[0059] In step S240, a target playback feature set is obtained, where the target playback feature set includes playback features corresponding to a plurality of users meeting the target condition.

[0060] In an embodiment, the playback features corresponding to multiple users who meet the target conditions can be obtained by the method in the above embodiment, wherein the target condition can be that the number of freezes in multimedia playback during a preset historical period exceeds a threshold, that is, users whose freezes exceed a certain number of times during a preset historical period, for example, users whose freezes exceed 5 times in the past 48 hours. Since users who experience multiple freezes may affect the user's viewing experience when playing the video, if not handled properly, it is likely to cause user loss. Therefore, by obtaining the playback features of these users whose multimedia playback freezes exceed the threshold during a preset historical period, in order to classify these users, different categories of people may react differently when facing freezes, so it is necessary to generate corresponding playback strategies for different categories of people so as to make targeted strategy adjustments during video playback.

[0061] In an embodiment, the target condition may also be users whose playback operation times exceed a threshold within a preset historical period. For example, in the past period of time, some users continuously swiped away videos recommended by the platform while watching videos, indicating that the videos recommended by the platform to these users may not be liked by the users, or that the users who recommended the videos often experience freezes during playback. Therefore, the playback characteristics of these users who meet the target conditions can be obtained to dig into these users, and by classifying the population, etc., corresponding playback strategies can be generated for different categories of people.

[0062] In step S250, the target playback feature set is clustered to obtain multiple clusters, wherein the multiple clusters correspond to multiple categories of people, and each category of people carries a target playback label.

[0063] In an embodiment, when classifying a target playback feature set for a certain group of people, the playback features in the target playback feature set may be clustered, for example, by performing clustering in an unsupervised learning manner, specifically, unsupervised clustering may be performed by k-means, for example, K clusters and K cluster centers may be obtained, and the distance between each cluster center may be greater than a preset distance threshold.

[0064] In step S260, the playback strategies corresponding to the different categories of people are determined based on the target playback tags.

[0065] The target playback feature set is clustered in the above manner to obtain multiple clusters. Each cluster can represent a category of people. When obtaining the target playback tags of each category of people in the embodiment, for example, for any category of people in multiple categories of people, the target playback tags of each user in the corresponding cluster can be obtained. The target playback characterizes what type of user the user belongs to, such as a user who is highly sensitive to freezes, a user who is not sensitive to freezes, or a user who prefers a certain category, etc. The target playback tags belonging to the cluster can be determined according to the number of each type of target playback tags. For example, if the target playback tags corresponding to the user who is highly sensitive to freezes in the cluster are the largest, the category of people corresponding to the cluster can be determined as the user group that is highly sensitive to freezes, and then the video playback of the corresponding user is adjusted according to the playback strategy corresponding to the user group that is highly sensitive to freezes.

[0066] In the embodiment, the category population corresponding to the clusters may be further subdivided, for example, into multiple categories of sub-populations, so as to obtain the playback strategy corresponding to each sub-category population, thereby achieving more refined adjustment of the playback strategy.

[0067] Based on the above embodiment, in another embodiment provided by the present disclosure, the above step S220 may further include the following steps:

[0068] In step S221, the distances between the target user's playback features and a plurality of cluster centers are obtained.

[0069] In step S222, the target category of people corresponding to the target user is determined based on the distance.

[0070] In an embodiment, after obtaining multiple clusters in the above manner, for example, when it is detected that a target user is watching a video, the playback characteristics of the target user can be obtained, and the distances between the playback characteristics of the target user and the cluster centers of each cluster are calculated respectively. If the target user belongs to a category of people corresponding to a cluster in each cluster, that is, the playback characteristics of the target user meet the target conditions, then the distance between the playback characteristics of the target user and the cluster is 0, or the distance is less than a threshold.

[0071] In an embodiment, for users whose playback characteristics do not meet the target conditions, such users are general users. The distance between the user's playback characteristics and the above-mentioned multiple cluster centers can be calculated, and the target category population corresponding to the cluster cluster with the smallest distance is taken as the category population described by the user, so as to obtain the playback strategy corresponding to the target category population.

[0072] In the case of dividing each functional module according to each function, an embodiment of the present disclosure provides a multimedia playback device, which may be a server or a chip applied to a server. Figure 3This is a schematic block diagram of the functional modules of a multimedia playback device provided by an exemplary embodiment of the present disclosure. Figure 3 As shown, the multimedia playback device includes:

[0073] The play feature acquisition module 10 is used to acquire the play feature of the target user when receiving the target play operation of the target user for the multimedia, wherein the play feature includes the target feature corresponding to the user when playing the multimedia;

[0074] A strategy determination module 20, configured to obtain a target playback strategy corresponding to the target category of people based on the playback characteristics;

[0075] The playback control module 30 is used to control the playback of the multimedia based on the target playback strategy.

[0076] In another embodiment provided by the present disclosure, the device further includes:

[0077] A target playback feature set acquisition module, used to acquire a target playback feature set, wherein the target playback feature set includes playback features corresponding to a plurality of users meeting the target condition;

[0078] A clustering module, used for clustering the target playback feature set to obtain a plurality of clusters; wherein the plurality of clusters correspond to a plurality of categories of people, each category of people carries a target playback label;

[0079] The playback strategy determination module is used to determine the playback strategies corresponding to each category of people based on the target playback tag.

[0080] In another embodiment provided by the present disclosure, the plurality of clusters respectively have a plurality of cluster centers;

[0081] The strategy determination module is specifically used for:

[0082] Obtaining the distances between the playback features of the target user and the multiple cluster centers respectively;

[0083] A target category of people corresponding to the target user is determined based on the distance.

[0084] In another embodiment provided by the present disclosure, the target feature includes: at least one of a target playback feature, a video feature, and an environmental feature.

[0085] In another embodiment provided by the present disclosure, the device further includes:

[0086] A target feature acquisition module, used to acquire the target feature of the target user when playing multimedia in a preset historical period;

[0087] A playback feature generation module is used to generate the playback feature based on the target feature.

[0088] In another embodiment provided by the present disclosure, the device further includes:

[0089] An initial playback feature acquisition module, used to splice the features included in the target playback features, and use the spliced ​​features as input of the first preset model to output the initial playback features;

[0090] The playback feature acquisition module is used to use the initial playback feature, the video feature and the environment feature as inputs of a second preset model and output playback features.

[0091] In another embodiment provided by the present disclosure, the target condition includes: the number of freezes in multimedia playback within a preset historical period exceeds a threshold.

[0092] The relevant device embodiments correspond to the above method embodiments. Please refer to the description of the above method embodiments for details, which will not be repeated here.

[0093] The multimedia playback device provided by the embodiment of the present disclosure can obtain the playback characteristics of the target user when receiving the target operation of the target user on the multimedia. Based on the playback characteristics, the target category of people to which the target user belongs can be determined, and by obtaining the target playback strategy corresponding to the target category of people, the playback of the multimedia can be controlled based on the target playback strategy. In this way, when the user watches multimedia such as videos, targeted playback adjustments can be implemented for different users through corresponding playback strategies to meet the viewing needs of the users, thereby improving the playback efficiency of the video.

[0094] An embodiment of the present disclosure also provides an electronic device, comprising: at least one processor; and a memory for storing instructions executable by the at least one processor; wherein the at least one processor is configured to execute the instructions to implement the above method disclosed in the embodiment of the present disclosure.

[0095] Figure 4 The structure diagram of an electronic device provided by an exemplary embodiment of the present disclosure is shown in FIG. Figure 4 As shown, the electronic device 1800 includes at least one processor 1801 and a memory 1802 coupled to the processor 1801 , and the processor 1801 can execute corresponding steps in the above method disclosed in the embodiment of the present disclosure.

[0096] The processor 1801 may also be referred to as a central processing unit (CPU), which may be an integrated circuit chip having signal processing capabilities. Each step in the method disclosed in the embodiment of the present disclosure may be completed by an integrated logic circuit of hardware in the processor 1801 or by instructions in the form of software. The processor 1801 may be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present disclosure may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a memory 1802, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, or other mature storage media in the art. The processor 1801 reads the information in the memory 1802 and completes the steps of the method in combination with its hardware.

[0097] In addition, when various operations / processes according to the present disclosure are implemented by software and / or firmware, they can be transmitted from a storage medium or a network to a computer system having a dedicated hardware structure, such as Figure 5 The computer system 1900 shown is installed with the programs constituting the software. When the various programs are installed, the computer system can perform various functions, including the functions described above. Figure 5 A structural block diagram of a computer system provided for an exemplary embodiment of the present disclosure.

[0098] Computer system 1900 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processing, 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 claimed herein.

[0099] like Figure 5As shown, the computer system 1900 includes a computing unit 1901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1902 or a computer program loaded from a storage unit 1908 to a random access memory (RAM) 1903. In the RAM 1903, various programs and data required for the operation of the computer system 1900 can also be stored. The computing unit 1901, the ROM 1902, and the RAM 1903 are connected to each other via a bus 1904. An input / output (I / O) interface 1905 is also connected to the bus 1904.

[0100] A plurality of components in the computer system 1900 are connected to the I / O interface 1905, including: an input unit 1906, an output unit 1907, a storage unit 1908, and a communication unit 1909. The input unit 1906 may be any type of device capable of inputting information to the computer system 1900, and the input unit 1906 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 1907 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1908 may include, but is not limited to, a disk, an optical disk. The communication unit 1909 allows the computer system 1900 to exchange information / data with other devices over a network such as the Internet, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0101] The computing unit 1901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1901 performs the various methods and processes described above. For example, in some embodiments, the above methods disclosed in the embodiments of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1908. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1900 via the ROM 1902 and / or the communication unit 1909. In some embodiments, the computing unit 1901 may be configured to perform the above methods disclosed in the embodiments of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0102] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the above method disclosed in the embodiment of the present disclosure.

[0103] The computer-readable storage medium in the disclosed embodiments 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. The computer-readable storage 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. More specifically, the computer-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 (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0104] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0105] The embodiments of the present disclosure further provide a computer program product, including a computer program, wherein when the computer program is executed by a processor, the above method disclosed in the embodiments of the present disclosure is implemented.

[0106] In embodiments of the present disclosure, computer program codes for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.

[0107] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] The modules, components or units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the names of the modules, components or units do not, in some cases, limit the modules, components or units themselves.

[0109] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0110] The above descriptions are only some embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, a technical solution formed by replacing the above features with the technical features with similar functions disclosed in the present disclosure (but not limited to).

[0111] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A multimedia playback method, characterized in that: The method comprises: When receiving a target play operation of a target user for multimedia, obtaining a play feature of the target user, wherein the play feature includes a target feature corresponding to the user when playing multimedia; Based on the playback characteristics, obtaining a target playback strategy corresponding to the target category of people; The playing of the multimedia is controlled based on the target playing strategy.

2. The method according to claim 1, characterized in that The method further comprises: Acquire a target playback feature set, where the target playback feature set includes playback features corresponding to a plurality of users meeting a target condition; The target playback feature set is clustered to obtain a plurality of clusters; wherein the plurality of clusters correspond to a plurality of categories of people, and each category of people carries a target playback label; The playback strategies corresponding to the respective categories of people are determined based on the target playback tags.

3. The method according to claim 2, characterized in that The multiple clusters respectively have multiple cluster centers; The determining the target category population to which the target user belongs includes: Obtaining the distances between the playback features of the target user and the multiple cluster centers respectively; A target category of people corresponding to the target user is determined based on the distance.

4. The method according to claim 1, characterized in that: The target feature includes at least one of a target playback feature, a video feature and an environmental feature.

5. The method according to claim 4, characterized in that The method further comprises: Acquire the target features of the target user when playing multimedia in a preset historical period; The playback feature is generated based on the target feature.

6. The method according to claim 5, characterized in that The method further comprises: splicing the features included in the target playback features, and using the spliced ​​features as input of a first preset model, and outputting initial playback features; The initial playback feature, the video feature and the environment feature are used as inputs of a second preset model, and playback features are output.

7. The method according to claim 2, characterized in that: The target condition includes: the number of freezes in multimedia playback during a preset historical period exceeds a threshold.

8. A multimedia playback device, characterized in that: The device comprises: A play feature acquisition module, configured to acquire the play feature of the target user upon receiving a target play operation of the target user for multimedia, wherein the play feature includes a target feature corresponding to the user when playing multimedia; A strategy determination module, used to determine the target category population to which the target user belongs based on the playback characteristics, and obtain the target playback strategy corresponding to the target category population; wherein different categories of population have corresponding different playback strategies; The playback control module is used to control the playback of the multimedia based on the target playback strategy.

9. An electronic device, characterized in that: include: at least one processor; a memory for storing the at least one processor-executable instruction; The at least one processor is configured to execute the instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method as claimed in any one of claims 1 to 7.

Images