Multimedia content recommendation method, device, equipment and storage medium

Abstract

The present disclosure provides a method, device, equipment and storage medium for recommending multimedia content, which relates to the field of computer technology, and further to artificial intelligence technologies such as computer vision and speech recognition. The specific implementation scheme is: determining the label data of the target user; determining a content stream including at least two multimedia types for the target user based on the label data; and displaying the content stream to the target user through the display unit of the smart speaker. According to the technology disclosed in the present disclosure, it is possible to meet the personalized and diversified needs of users, and provide a new idea for realizing the recommendation of multimedia content in the smart speaker scenario.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to the field of artificial intelligence technologies such as computer vision and speech recognition. Background Art

[0002] With the development of artificial intelligence technology, the emergence of smart speakers has enriched people's lives. However, existing smart speakers cannot recommend multimedia content to users in a targeted manner, and the recommended multimedia types are single, which cannot meet the diverse and personalized needs of users and urgently needs to be improved. Summary of the invention

[0003] The present disclosure provides a method, apparatus, device and storage medium for recommending multimedia content.

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

[0005] Determine the label data of target users;

[0006] Determining, for the target user, a content stream comprising at least two multimedia types according to the tag data;

[0007] The content stream is displayed to the target user through the display unit of the smart speaker.

[0008] According to another aspect of the present disclosure, a multimedia content recommendation device is provided, the device comprising:

[0009] A label data determination module, used to determine the label data of the target user;

[0010] a content stream determination module, configured to determine a content stream including at least two multimedia types for the target user according to the tag data;

[0011] A content stream display module is used to display the content stream to the target user through the display unit of the smart speaker.

[0012] According to another aspect of the present disclosure, there is provided an electronic device, the electronic device comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] 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 so that the at least one processor can execute the multimedia content recommendation method described in any embodiment of the present disclosure.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the multimedia content recommendation method described in any embodiment of the present disclosure.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method for recommending multimedia content according to any one of the embodiments of the present disclosure is implemented.

[0018] The technology disclosed in the present invention can meet the personalized and diversified needs of users and provide a new idea for realizing the recommendation of multimedia content in the smart speaker scenario.

[0019] 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

[0020] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0021] Figure 1 is a flowchart of a multimedia content recommendation method provided according to an embodiment of the present disclosure;

[0022] Figure 2 is a flowchart of another multimedia content recommendation method provided according to an embodiment of the present disclosure;

[0023] Figure 3 is a flowchart of another multimedia content recommendation method provided according to an embodiment of the present disclosure;

[0024] Figure 4A is a flowchart of another multimedia content recommendation method provided according to an embodiment of the present disclosure;

[0025] Figure 4B is a schematic diagram of a display interface provided according to an embodiment of the present disclosure;

[0026] Figure 5 is a structural schematic diagram of a multimedia content recommendation device provided according to an embodiment of the present disclosure;

[0027] Figure 6 The present invention is a block diagram of an electronic device for implementing the method for recommending multimedia content according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] 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.

[0029] Figure 1 This is a flowchart of a multimedia content recommendation method provided according to an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to the case of how to recommend multimedia content to users, and is particularly applicable to the case of a smart speaker equipped with a display unit (such as a display screen) actively recommending multimedia content to users. This embodiment can be executed by a multimedia content recommendation device configured in an electronic device, and the device can be implemented using software and / or hardware. Furthermore, the electronic device can be a smart speaker equipped with a display unit. Figure 1 As shown, the multimedia content recommendation method includes:

[0030] S101, determining tag data of a target user.

[0031] In this embodiment, the so-called target user is the object to which the smart speaker recommends multimedia content. Optionally, when the smart speaker detects a content recommendation event, it may first identify the user's identity to determine the target user; or it may directly use the user bound to the smart speaker as the target user, etc. Among them, there are many ways for the smart speaker to detect a content recommendation event, such as detecting that the current time meets the set content recommendation cycle; it may also be detecting that the distance between the user and the smart speaker collected by the distance sensor in the smart speaker is less than the set distance value; it may also be receiving a recommendation instruction from the user, such as extracting the recommendation instruction from the user's voice information, or determining that the recommendation instruction is received based on the user's sliding operation on the display unit of the smart speaker, etc.; or it may also be receiving a recommendation notification sent by a cloud platform that is connected to the smart speaker.

[0032] Optionally, in this embodiment, there are many ways for the smart speaker to identify the user. For example, the smart speaker can interact with the user through voice to obtain the user's voice information, and obtain the user's voiceprint characteristics based on the user's voice information, and then identify the user's identity based on the user's voiceprint characteristics; or the smart speaker can collect the user's facial image through a collection unit (such as a camera) configured thereon, and then identify the user's identity based on the collected user's facial image.

[0033] Exemplarily, after determining the target user, the smart speaker can determine the label data of the target user. The so-called label data can be used to characterize the characteristics of the user. Optionally, the label data of different users are different. For any user, the label data may include behavioral label data and / or basic label data. The so-called behavioral label data is used to characterize the characteristics of the user from a behavioral perspective, and may include but is not limited to the types of multimedia that the user is interested in and the time period when the user watches multimedia content; the basic label data is used to characterize the characteristics of the user based on the user's attribute information, and may include but is not limited to the user's age, gender and family model. Among them, the family model can be at least one of a child family, a preschool family, an elementary school family, a middle school family, a youth family and an elderly family.

[0034] Optionally, the method of determining different label data is different in this embodiment. For example, the behavior label data can be determined based on the historical usage behavior data of the target user for the smart speaker. Specifically, it can be to use a statistical analysis algorithm to analyze the historical usage behavior data of the target user for the smart speaker to determine the behavior label data of the target user; or it can be based on a pre-trained behavior label recognition model, according to the historical usage behavior data of the target user for the smart speaker, to determine the behavior label data of the target user. Among them, the historical usage behavior data of the target user for the smart speaker may include but is not limited to the time and duration of the target user watching / clicking multimedia content, and the frequency of watching / clicking different multimedia types.

[0035] Furthermore, when the target user is any one of the candidate users associated with the smart speaker, the basic tag data of the target user can be obtained from the configuration information of the smart speaker. Specifically, the attribute information of the target user can be obtained from the configuration information of the smart speaker, and then the basic tag data of the target user can be determined based on the attribute information of the target user. The so-called candidate users associated with the smart speaker are users who have registered in the smart speaker. For any user, the attribute information of the user may include but is not limited to the user's age, gender, family members, and school attendance.

[0036] S102: Determine a content stream including at least two multimedia types for a target user according to the tag data.

[0037] Optionally, in this embodiment, multimedia types include but are not limited to video, audio and text, wherein video includes but is not limited to TV series, movies, variety shows, short videos, dramas and live broadcasts, etc.; audio may include audio books (such as audio novels, audio story books, etc.) and music, etc.; text may include news, etc.

[0038] Specifically, the smart speaker can obtain multimedia content of at least two multimedia types from the resource library according to the tag data, and generate a content stream according to the obtained multimedia content. Optionally, the multimedia content in the resource library can be updated in real time; further, the resource library is preferably configured in an external device.

[0039] Furthermore, the smart speaker can also control the cloud platform to determine a content stream including at least two multimedia types for the target user based on the tag data. For example, the smart speaker can send a content acquisition request including the tag data of the target user to the cloud platform, so that the cloud platform can acquire at least two multimedia types of content to be recommended based on the tag data of the target user, and generate a content stream based on the content to be recommended; and then the smart speaker can acquire the content stream fed back by the cloud platform.

[0040] S103, displaying the content stream to the target user through the display unit of the smart speaker.

[0041] Optionally, the smart speaker can display the content stream on the display unit of the smart speaker in a display order so that the target user can watch it. The display order may include the display order between different multimedia types and the display order between different multimedia content in the same multimedia type. Optionally, the display order in this embodiment can be determined by the smart speaker or the cloud platform based on popularity, update time, and the degree of association between the multimedia content and the tag data of the target user.

[0042] In the technical solution of the embodiment of the present disclosure, the smart speaker obtains at least two types of multimedia content streams for the target user based on the tag data of the target user, and displays the content streams through the configured display unit. Compared with the existing smart speaker solution for recommending multimedia content to users, the above solution realizes personalized recommendation and enriches the types of displayed content, thereby meeting the diverse and personalized needs of users, and provides a new idea for realizing the recommendation of multimedia content in the smart speaker scenario.

[0043] Further, as an optional method of an embodiment of the present disclosure, when the label data includes behavior labels and basic labels, determining a content stream including at least two multimedia types for a target user based on the label data may specifically be determining a content stream including at least two multimedia types for a target user based on the behavior labels and / or basic label data.

[0044] Among them, according to the basic tag data, determining a content stream including at least two multimedia types for the target user can be, for example, determining the content theme of the content to be recommended according to the family model in the basic tag data; according to the age in the basic tag data, obtaining multimedia content of at least two multimedia types from multimedia content related to the content theme to obtain the content stream. The so-called content theme represents the main core intent of the multimedia content, which can include but is not limited to education, entertainment (such as short videos, TV series, variety shows and movies, etc.), sports, knowledge, fashion and life (such as mother and baby, food and clothing, etc.), etc.

[0045] For example, if the family mode is a child family, the content theme of the content to be recommended can be determined as education, and then the content streams including at least two multimedia types can be determined for the target user based on age; for example, if the age is 0-1 years old, music, audio books, and animation related to early education can be used as content streams. For another example, if the family mode is a youth or elderly family, the content theme of the content to be recommended can be determined as entertainment, and then the content streams including at least two multimedia types can be determined for the target user based on age. For example, if the age is 18-25 years old, videos and audio related to entertainment can be used as content streams.

[0046] Furthermore, a content stream including at least two multimedia types may be determined for the target user based on the behavior tag data. Alternatively, a content stream including at least two multimedia types may be determined for the target user based on the basic tag data and the behavior tag data. For example, the first content to be recommended may be determined based on the basic tag data, and the second content to be recommended may be determined based on the behavior tag data, and the first content to be recommended and the second content to be recommended may be used as the content stream.

[0047] It should be noted that new hot multimedia content can be determined based on basic tag data, while the method of determining content flow based on behavior tag data is more suitable for existing multimedia content. The process of determining content flow based on behavior tag data will be described in detail in subsequent embodiments.

[0048] Figure 2 FIG. 1 is a flowchart of another multimedia content recommendation method provided according to an embodiment of the present disclosure. Based on the above embodiment, this embodiment explains how to determine the behavior tag data in the tag data of the target user, and how to determine the content flow based on the behavior tag data. Figure 2 As shown, the multimedia content recommendation method includes:

[0049] S201, determining the behavior tag data of the target user according to the historical usage behavior data of the target user for the auxiliary application and / or the auxiliary terminal, and the historical usage behavior data of the target user for the smart speaker.

[0050] Optionally, the auxiliary application and / or auxiliary terminal are the same as the account information of the smart speaker. The so-called auxiliary terminal may be other electronic devices used by the target user except the smart speaker, and the account information of the other electronic devices is the same as that of the smart speaker, such as smart speakers, smart TVs and smart air conditioners owned by the target user from the same company. The auxiliary application may be an application software used by the target user with the same account information as that of the smart speaker, such as video software and music applications. Furthermore, the number of auxiliary applications may be one, two or more; correspondingly, the number of auxiliary terminals may also be one, two or more.

[0051] In this embodiment, the target user's historical usage behavior data for the auxiliary application may include but is not limited to the time period, duration, and frequency of the target user's use of the auxiliary application, as well as the situation of the target user using the auxiliary application to watch / click on multimedia content, etc. Correspondingly, the target user's historical usage behavior data for the auxiliary terminal may include but is not limited to the time period, duration, and frequency of the target user's use of the auxiliary terminal, as well as the situation of the target user using the auxiliary terminal to watch / click on multimedia content, etc.

[0052] The behavior tag data includes the type of multimedia of interest, and may also include the time period for watching multimedia content, etc. Specifically, the smart speaker can determine the auxiliary application and / or auxiliary terminal with the same account information according to the account information to which it belongs; then the historical usage behavior data of the target user on the auxiliary application and / or auxiliary terminal can be obtained, and the historical usage behavior data of the target user on the smart speaker can be obtained from the log data of the smart speaker; and then the behavior tag data of the target user can be determined according to the obtained historical usage behavior data of the target user on the auxiliary application and / or auxiliary terminal, and the historical usage behavior data of the target user on the smart speaker.

[0053] For example, a statistical analysis algorithm may be used to analyze the acquired historical usage behavior data of the target user on the auxiliary application and / or the auxiliary terminal, and the acquired historical usage behavior data of the target user on the smart speaker, to determine the behavior label data of the target user. Alternatively, the behavior label data of the target user may be determined based on the acquired historical usage behavior data of the target user on the auxiliary application and / or the auxiliary terminal, and the acquired historical usage behavior data of the target user on the smart speaker, based on a pre-trained behavior label recognition model.

[0054] It should be noted that this embodiment not only introduces the user's historical usage behavior data of the smart speaker, but also introduces the user's historical usage behavior data of auxiliary applications and / or auxiliary terminals to determine the behavior tag data of the target user, thereby increasing the accuracy and comprehensiveness of the behavior tag data.

[0055] S202: Determine a content stream including at least two multimedia types for the target user based on the behavior tag data and the historical usage behavior data of the smart speaker by users similar to the target user.

[0056] In this embodiment, users other than the target user whose behavior label data are similar to the behavior label data of the target user are regarded as similar users of the target user.

[0057] Specifically, the first content to be recommended may be determined based on the association between the target user's behavior tag data and resources; the second content to be recommended may be determined based on the historical usage behavior data of the smart speaker by users similar to the target user; and the first content to be recommended and the second content to be recommended may be used as the content flow for the target user.

[0058] For example, the target user's behavior tag data includes that the target user is interested in TV series xx, and the target user's similar users' historical usage behavior data on smart speakers include watching TV series xx, watching variety shows performed by actors who participated in TV series xx, watching food short videos, and watching a function introduction of smart speakers, etc. Furthermore, based on the association between resources, music related to the theme song, interlude, and ending song in TV series xx, as well as audio novels related to TV series xx, can be obtained, and the video related to TV series xx, the obtained music and audio novels can be used as the first content to be recommended; at the same time, the variety shows, food short videos, and function introductions of smart speakers watched by similar users can be used as the second content to be recommended; then, based on the first content to be recommended and the second content to be recommended, a content stream recommended to the target user can be obtained.

[0059] Furthermore, in order to avoid duplicate recommendations, as an optional method of the embodiment of the present disclosure, a content stream including at least two multimedia types can be determined for the target user based on the behavior tag data, the historical usage behavior data of the target user on the smart speaker, and the historical usage behavior data of the target user's similar users on the smart speaker. Specifically, the first content to be recommended and the second content to be recommended are deduplicated based on the historical usage behavior data of the target user on the smart speaker, and the first content to be recommended and the second content to be recommended after deduplication are used as the content stream recommended to the target user.

[0060] Furthermore, in order to enrich the determined content flow, in this embodiment, when determining the second content to be recommended, historical usage behavior data of the auxiliary application and / or the auxiliary terminal by users similar to the target user may also be combined.

[0061] S203, displaying the content stream to the target user through the display unit of the smart speaker.

[0062] The technical solution of the disclosed embodiment determines the behavior label data of the target user by combining the historical usage behavior data of the target user for auxiliary applications and / or auxiliary terminals, and the historical usage behavior data of the target user for smart speakers, thereby increasing the accuracy and comprehensiveness of the behavior label data and providing a new approach for determining the behavior label data. At the same time, the historical usage behavior data of the smart speaker by similar users of the target user is introduced, and based on the behavior label data of the target user, at least two multimedia types of content streams for the target user are obtained, thereby enriching the types of multimedia content in the obtained content streams, thereby meeting the diverse and personalized needs of users.

[0063] Figure 3 FIG. 1 is a flowchart of another multimedia content recommendation method provided according to an embodiment of the present disclosure. Based on the above embodiment, this embodiment explains how to display content streams to target users. Figure 3 As shown, the multimedia content recommendation method includes:

[0064] S301, determining tag data of a target user.

[0065] S302: Determine, according to the tag data, a content stream including at least two multimedia types for a target user.

[0066] S303: Aggregate multimedia contents in the content stream according to multimedia types to obtain content sets corresponding to each multimedia type.

[0067] In this embodiment, the multimedia contents in the content stream may be aggregated according to the three major multimedia types of video, audio, and text to obtain content sets corresponding to the multimedia types involved in the content stream. For example, if the content stream involves two major types of multimedia contents, video and audio, then a content set corresponding to the video and a content set corresponding to the audio may be obtained.

[0068] Furthermore, since the three multimedia types of video, audio and text can also have corresponding subcategories, for example, video can have subcategories such as TV series, movies, variety shows, short videos, dramas and live broadcasts, the aggregation results of content streams based on the three multimedia types of video, audio and text can be aggregated again to obtain the final result. For example, the content set corresponding to the video can be aggregated again to obtain the content set corresponding to the TV series, the content set corresponding to the movie, and the content set corresponding to the variety show.

[0069] It should be noted that, in order to improve user satisfaction, this embodiment preferably adopts a more fine-grained aggregation result, that is, a result after secondary aggregation.

[0070] S304: Determine the display order of each content set according to the association degree between the content set and the tag data.

[0071] In this embodiment, the degree of association between the content set and the tag data is used to characterize the degree of association between the content set and the user characteristics (such as the type of multimedia of interest). Furthermore, the degree of association between the content set and the tag data can be represented by the degree of association between the multimedia content in the content set and the tag data, which can be determined specifically by the following process: for each content set, the degree of association between each multimedia content in the content set and the tag data can be determined, and the degree of association between each determined multimedia content and the tag data can be added to obtain the degree of association between the content set and the tag data. Among them, the degree of association between the multimedia content and the tag data can be represented by a score or a percentage. For example, if the multimedia content is a clip of the xx TV series, and the tag data is that the target user is interested in the xx TV series, it means that the multimedia content and the tag data are highly correlated. Assuming that the score for complete correlation is 10, a higher score, such as 9, can be assigned at this time.

[0072] In order to facilitate users to see the content they are interested in first, this embodiment preferably sorts the content sets according to the degree of association between the content sets and the tag data from large to small to obtain the display order of each content set. In other words, the content set with a greater degree of association with the tag data is ranked higher.

[0073] S305 , displaying the multimedia contents in each content set on the display interface of the display unit in a display order.

[0074] Optionally, the display order determined in step S304 is actually the display order between different multimedia types, which can also be called the external display order; further, for each content set, the display order between the multimedia contents in the content set, that is, the internal display order, can be determined based on popularity, update time, and the degree of association between the multimedia content and tag data.

[0075] Furthermore, in this embodiment, the multimedia content in each content set may be displayed on the display interface of the display unit according to the external display order and the internal display order.

[0076] It is understandable that since the three major multimedia types of video, audio and text can have corresponding subcategories, and users have different levels of interest in each subcategory, this embodiment preferably uses a more fine-grained aggregation result, that is, the result after secondary aggregation, which can ensure that the content that users are interested in is ranked first. At the same time, this embodiment displays by content collection, which can make the content displayed on the display interface more neat and orderly, and more readable.

[0077] According to the technical solution of the embodiment of the present disclosure, the smart speaker obtains at least two multimedia types of content streams for the target user based on the tag data of the target user, and then aggregates the multimedia content in the content stream based on the multimedia type to obtain multiple content sets, and displays the multimedia content in each content set according to the display order of each content set determined based on the degree of association between the content set and the tag data. In the above solution, when the types of displayed content are diversified, each multimedia content is displayed based on the display order, so that the content displayed on the display interface is more neat and orderly, and the readability is better.

[0078] Figure 4A FIG. 1 is a flowchart of another multimedia content recommendation method provided according to an embodiment of the present disclosure. Based on the above embodiment, this embodiment further explains how to display content streams to target users. Figure 4A As shown, the multimedia content recommendation method includes:

[0079] S401, determining tag data of a target user.

[0080] S402: Determine a content stream including at least two multimedia types for a target user according to the tag data.

[0081] S403: Aggregate the multimedia contents in the content stream according to the multimedia types to obtain a content set corresponding to each multimedia type.

[0082] S404: Determine the display order of each content set according to the association degree between the content set and the tag data.

[0083] S405 , allocating a display area for each content set on a display interface of a display unit according to a display order and a set direction.

[0084] In this embodiment, the so-called set direction is a preset way of displaying multimedia content in the content stream. For example, in order to facilitate user browsing and meet the habits of many users using smart speakers, the length direction of the smart speaker, that is, the vertical direction, can be used as the set direction.

[0085] Specifically, in this embodiment, a display area may be allocated to each content set in sequence in a display interface of the display unit along a set direction (such as a vertical direction) according to a display order.

[0086] S406: Display the multimedia content in the corresponding content set in the allocated display area.

[0087] Optionally, after allocating a display area to each content set, the multimedia content in the corresponding content set can be displayed in the allocated display area. Furthermore, in order to facilitate users to intuitively understand the displayed content set, each display area has a display theme; the so-called display theme is used to summarize the commonalities of the multimedia content in the corresponding content set, such as classic dramas, the entire network new song list, etc.

[0088] Optionally, as an optional method of the embodiment of the present disclosure, displaying the multimedia content in the corresponding content set in the allocated display area can be: setting a content display frame and an identification attribute of the multimedia type of the content display frame in the allocated display area; displaying the multimedia content in the content set in the content display frame, and assigning a value to the identification attribute of the multimedia type of the content display frame according to the multimedia content corresponding to the content display frame.

[0089] Among them, the content display frame refers to an interface for displaying multimedia content, and each content display frame corresponds to a multimedia content; optionally, for each display area, the number of content display frames can be determined according to the number of multimedia content in the content set corresponding to the display area. In addition, each content display frame has an identification attribute; further, the identification attribute of the content display frame is related to the multimedia type, and the identification attributes of different multimedia types are different. For example, if the multimedia type is a TV series, the identification attribute is the number of updated episodes; if the multimedia type is a movie, the identification attribute is the rating; if the multimedia type is music, the identification attribute is the playback control; if the multimedia type is a variety show, the identification attribute is the number of updated issues; if the multimedia type is news, the identification attribute is the update date; if the multimedia type is a short video, the identification attribute is the playback duration; if the multimedia type is a drama, the identification attributes are the playback controls and the number of episodes; if the multimedia type is an audiobook, the identification attributes are the playback controls and the number of chapters, etc.

[0090] Optionally, the value of the identification attribute can be determined based on the multimedia content displayed in the content display box. For example, if the multimedia content displayed in a content display box is xx TV series, the value of the identification attribute can be updated to X episodes; for another example, if the multimedia content displayed in a content display box is xx movie, the value of the identification attribute can be 9.0; for another example, if the multimedia content displayed in a content display box is xx variety show, the value of the identification attribute can be 20210219 episodes, etc. Further, when the identification attribute is a playback control, the value of the identification attribute can be, for example, a play pause symbol; when the identification attribute is a playback control and the number of episodes, the value of the identification attribute can be, for example, a play pause symbol and a total of X episodes; when the identification attribute is an update date, the value of the identification attribute can be, for example, 20210219; when the identification attribute is a playback duration, the value of the identification attribute can be, for example, 03:17, etc.

[0091] Specifically, for each allocated display area, the number of content display frames can be determined according to the number of multimedia contents in the content set corresponding to the display area, and the content display frames can be arranged in sequence in the display area according to the size of each content display frame and the size of the smart speaker display unit (such as a display screen). Figure 4B In the display area 41 in the display interface shown, 5 content display frames are sequentially arranged. Each content display frame displays a multimedia content. Assuming that the display area 1 is used to display a TV series, the value of the identification attribute of each content display frame is updated to X episodes.

[0092] In addition, it should be noted that, usually, a screenshot of the corresponding recommended content will be set in the content display box, so that users can intuitively understand what the content to be displayed in the content display box is, and it also provides convenience for users to quickly capture the recommended content they want. Furthermore, the screenshot set in the content display box can be a representative screen of the content to be recommended, or a collection of one or more screens therein.

[0093] Furthermore, in order to facilitate users to distinguish various types of multimedia content, in this embodiment, different content display frames may be set for different content sets; specifically, the size information of the content display frames of different content sets is different.

[0094] It is worth noting that the introduction of a content display frame to display multimedia content in this embodiment is equivalent to introducing boundaries between adjacent multimedia content, making it easier for users to quickly locate different multimedia content; at the same time, different identification attributes are set for different multimedia types, making it easier for users to intuitively distinguish between various types of multimedia content.

[0095] The technical solution of the disclosed embodiment, when the types of displayed content are diversified, introduces a display area to display multimedia content in a corresponding content set, which not only increases the neatness of the display interface, but also makes it easier for users to intuitively distinguish between various types of multimedia content, thereby improving the user's visual perception.

[0096] It should be noted that in the technical solution of the present invention, the acquisition, storage and application of the user's historical usage behavior data of smart speakers, the user's historical usage behavior data of auxiliary applications and / or auxiliary terminals, and the user's attribute information, etc., all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0097] Figure 5: is a schematic diagram of the structure of a multimedia content recommendation device provided according to an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to the case of how to recommend multimedia content to users, and is particularly applicable to the case of a smart speaker equipped with a display unit (such as a display screen) actively recommending multimedia content to users. The device can be implemented using software and / or hardware, and the device can be integrated into a smart speaker equipped with a display unit. The device can execute the multimedia content recommendation method described in any embodiment of the present disclosure. Figure 5 As shown, the multimedia content recommendation device 500 includes:

[0098] The tag data determination module 501 is used to determine the tag data of the target user;

[0099] A content stream determination module 502, configured to determine a content stream including at least two multimedia types for a target user according to the tag data;

[0100] The content stream display module 503 is used to display the content stream to the target user through the display unit of the smart speaker.

[0101] In the technical solution of the embodiment of the present disclosure, the smart speaker obtains at least two types of multimedia content streams for the target user based on the tag data of the target user, and displays the content streams through the configured display unit. Compared with the existing smart speaker solution for recommending multimedia content to users, the above solution realizes personalized recommendation and enriches the types of displayed content, thereby meeting the diverse and personalized needs of users, and provides a new idea for realizing the recommendation of multimedia content in the smart speaker scenario.

[0102] Exemplarily, the content stream display module 503 includes:

[0103] An aggregation unit, used to aggregate multimedia contents in the content stream according to multimedia types to obtain a content set corresponding to each multimedia type;

[0104] A display order determination unit, used to determine the display order of each content set according to the degree of association between the content set and the tag data;

[0105] The display unit is used to display the multimedia contents in each content set on the display interface of the display unit according to the display order.

[0106] Exemplarily, the display unit includes:

[0107] A display area allocation subunit, used to allocate a display area for each content set in a display interface of the display unit according to a display order and a set direction;

[0108] The display subunit is used to display the multimedia content in the corresponding content set in the allocated display area.

[0109] Exemplarily, the display subunit is specifically used for:

[0110] Setting a content display frame and a multimedia type identification attribute of the content display frame in the allocated display area;

[0111] The multimedia content in the content collection is displayed in the content display frame, and the identification attribute of the multimedia type of the content display frame is assigned a value according to the multimedia content corresponding to the content display frame.

[0112] Exemplarily, the identification attribute of the multimedia type includes at least one of the following:

[0113] If the multimedia type is a TV series, the identification attribute is the updated episode number;

[0114] If the multimedia type is movie, the identification attribute is rating;

[0115] If the multimedia type is music, the identification attribute is the playback control;

[0116] If the multimedia type is variety show, the identification attribute is the update issue number;

[0117] If the multimedia type is news, the identification attribute is the update date.

[0118] Exemplarily, the label data includes behavior label data, and the label data determination module 501 is specifically used for:

[0119] Determine the target user's behavior tag data based on the target user's historical usage behavior data of auxiliary applications and / or auxiliary terminals, as well as the target user's historical usage behavior data of smart speakers; wherein the auxiliary applications and / or auxiliary terminals, and the account information to which the smart speakers belong are the same, and the behavior tag data includes the multimedia types of interest.

[0120] Exemplarily, the content flow determination module 502 is specifically configured to:

[0121] Based on the behavior tag data and the historical usage behavior data of the smart speaker by users similar to the target user, a content stream including at least two multimedia types is determined for the target user.

[0122] Exemplarily, the label data includes basic label data, and the label data determination module 501 is specifically used for:

[0123] The basic label data of the target user is obtained from the configuration information of the smart speaker; wherein the basic label data includes age and family mode, and the family mode includes at least one of a child family, a preschool family, an elementary school family, a youth family and an elderly family.

[0124] 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.

[0125] Figure 6 A schematic block diagram of an example electronic device 600 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, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 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 required herein.

[0126] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0127] Multiple components in the electronic device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0128] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 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 601 performs the various methods and processes described above, such as a recommendation method for multimedia content. For example, in some embodiments, the recommendation method for multimedia content may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the recommendation method for multimedia content described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the recommendation method for multimedia content in any other appropriate manner (e.g., by means of firmware).

[0129] Various implementations 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 products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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.

[0130] 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.

[0131] 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, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium 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.

[0132] 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 CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or 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).

[0133] The systems and techniques described herein may 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 may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0134] 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 between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0135] 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.

[0136] 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 method for recommending multimedia content, comprising: Determine label data of the target user; the label data includes behavior label data; Determining, for the target user, a content stream comprising at least two multimedia types according to the tag data; Aggregating multimedia contents in the content stream according to multimedia types to obtain content sets corresponding to each multimedia type; According to the degree of association between the content set and the tag data, the display order of each content set is determined, and the display order is determined as the external display order; wherein, for any content set, the degree of association between each multimedia content in the content set and the tag data is determined, and the determined degrees of association between each multimedia content and the tag data are added to obtain the degree of association between the content set and the tag data; For any content set, determine the internal display order between the multimedia contents in the content set according to the popularity, update time and the degree of association between the multimedia contents and the tag data; Displaying the multimedia content in each content set on the display interface of the display unit according to the display order; the display order includes an external display order and an internal display order; Among them, determining the behavior tag data of the target user includes: Determine the behavior tag data of the target user according to the historical usage behavior data of the target user on the auxiliary application and / or the auxiliary terminal, and the historical usage behavior data of the target user on the smart speaker; wherein the account information to which the auxiliary application and / or the auxiliary terminal and the smart speaker belong is the same; and the behavior tag data includes the type of multimedia of interest; Accordingly, according to the tag data, a content stream including at least two multimedia types is determined for the target user, including: Determine the first content to be recommended based on the association between the behavior tag data of the target user and the resources; and determine the second content to be recommended based on the historical usage behavior data of the smart speaker and the historical usage behavior data of auxiliary applications and / or auxiliary terminals by similar users of the target user; use the first content to be recommended and the second content to be recommended as the content stream of the target user; wherein the similar users of the target user are users other than the target user whose behavior tag data are similar to the behavior tag data of the target user.

2. The method according to claim 1, wherein: The step of displaying the multimedia contents in each content set on the display interface of the display unit in the display order includes: Allocating a display area for each content set on a display interface of the display unit according to the display order and the set direction; The multimedia content in the corresponding content set is displayed in the allocated display area.

3. The method according to claim 2, wherein: The displaying of the multimedia content in the corresponding content set in the allocated display area includes: Setting a content display frame and an identification attribute of a multimedia type of the content display frame in the allocated display area; The multimedia content in the content set is displayed in the content display frame, and a value is assigned to an identification attribute of the multimedia type of the content display frame according to the multimedia content corresponding to the content display frame.

4. The method according to claim 3, wherein: The identification attribute of the multimedia type includes at least one of the following: If the multimedia type is a TV series, the identification attribute is the updated episode number; If the multimedia type is movie, the identification attribute is rating; If the multimedia type is music, the identification attribute is the playback control; If the multimedia type is variety show, the identification attribute is the update issue number; If the multimedia type is news, the identification attribute is the update date.

5. The method according to claim 1, wherein: The label data includes basic label data; The step of determining the tag data of the target user includes: The basic label data of the target user is obtained from the configuration information of the smart speaker; wherein the basic label data includes age and family mode, and the family mode includes at least one of a child family, a preschool family, an elementary school family, a youth family and an elderly family.

6. A multimedia content recommendation device, comprising: A label data determination module, used to determine the label data of the target user; The label data includes behavior label data; a content stream determination module, configured to determine a content stream including at least two multimedia types for the target user according to the tag data; A content stream display module, used to display the content stream to the target user through a display unit of the smart speaker; The content stream display module includes: an aggregation unit, configured to aggregate multimedia contents in the content stream according to multimedia types to obtain a content set corresponding to each multimedia type; A display order determination unit, configured to determine the display order of each content set according to the degree of association between the content set and the tag data; and determine the display order as the external display order; wherein, for any content set, the degree of association between each multimedia content in the content set and the tag data is determined, and the determined degrees of association between each multimedia content and the tag data are added to obtain the degree of association between the content set and the tag data; For any content set, determine the internal display order between the multimedia contents in the content set according to the popularity, update time and the degree of association between the multimedia contents and the tag data; A display unit, configured to allocate a display area for each content set on a display interface of the display unit according to a display order; the display order includes an external display order and an internal display order; Wherein, the label data includes behavior label data; The tag data determination module is specifically used for: Determine the behavior tag data of the target user according to the historical usage behavior data of the target user for the auxiliary application and / or the auxiliary terminal, and the historical usage behavior data of the target user for the smart speaker; wherein the account information to which the auxiliary application and / or the auxiliary terminal and the smart speaker belong is the same, and the behavior tag data includes the type of multimedia of interest; Wherein, the content flow determination module is specifically used for: Determine the first content to be recommended based on the association between the behavior tag data of the target user and the resources; and determine the second content to be recommended based on the historical usage behavior data of the smart speaker and the historical usage behavior data of auxiliary applications and / or auxiliary terminals by similar users of the target user; use the first content to be recommended and the second content to be recommended as the content stream of the target user; wherein the similar users of the target user are users other than the target user whose behavior tag data are similar to the behavior tag data of the target user.

7. The device according to claim 6, wherein: The display unit comprises: A display area allocation subunit, configured to allocate a display area for each content set on the display interface of the display unit according to the display order and the set direction; The display subunit is used to display the multimedia content in the corresponding content set in the allocated display area.

8. The device according to claim 7, wherein: The display subunit is specifically used for: Setting a content display frame and an identification attribute of a multimedia type of the content display frame in the allocated display area; The multimedia content in the content set is displayed in the content display frame, and a value is assigned to an identification attribute of the multimedia type of the content display frame according to the multimedia content corresponding to the content display frame.

9. The device according to claim 8, wherein: The identification attribute of the multimedia type includes at least one of the following: If the multimedia type is a TV series, the identification attribute is the updated episode number; If the multimedia type is movie, the identification attribute is rating; If the multimedia type is music, the identification attribute is the playback control; If the multimedia type is variety show, the identification attribute is the update issue number; If the multimedia type is news, the identification attribute is the update date.

10. The device according to claim 6, wherein: The label data includes basic label data; The tag data determination module is specifically used for: The basic label data of the target user is obtained from the configuration information of the smart speaker; wherein the basic label data includes age and family mode, and the family mode includes at least one of a child family, a preschool family, an elementary school family, a youth family and an elderly family.

11. 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 multimedia content recommendation method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the multimedia content recommendation method according to any one of claims 1-5.

13. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for recommending multimedia content according to any one of claims 1 to 5.

Images