CN112667887A

CN112667887A - Content recommendation method and device, electronic equipment and server

Info

Publication number: CN112667887A
Application number: CN202011533640.0A
Authority: CN
Inventors: 王健
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-12-22
Filing date: 2020-12-22
Publication date: 2021-04-16
Anticipated expiration: 2040-12-22
Also published as: CN112667887B

Abstract

The disclosure relates to a content recommendation method and device, electronic equipment and a server. In one embodiment of the method, data acquired by the client may be analyzed and processed, where the data includes vital sign information acquired by the client through the wearable device. When the terminal account watches the video, the vital sign information can reflect the current emotional state of the terminal account more really, so that the server can determine the emotion of the terminal account when watching the playing content according to the vital sign information, can tag the watched playing content and mark the tagged playing content as a corresponding emotional identifier. Therefore, the server can search the recommended content with the same or similar emotion according to the current emotion identification and return the recommended content to the client, and the client can play the content which is more in line with the current emotion state of the terminal account, so that the accuracy of the recommended content is improved.

Description

Content recommendation method and device, electronic equipment and server

Technical Field

The present disclosure relates to the field of computer data processing technologies, and in particular, to a content recommendation method and apparatus, an electronic device, and a server.

Background

With the development of science and technology, the speed of mobile internet is increasing, and the short video application of the terminal is gradually popularized. The user may search for and view content of interest through the short video application.

A service providing video content sharing may recommend content that may be of interest to a user using some recommendation algorithm. For example, in some algorithms, videos may be recommended to a user based on recommendation factors such as the user's gender, age, region, network environment, etc. With the continuous increase of user demands, how to recommend more accurate content to a user has become a technical problem which needs to be solved urgently at present.

Disclosure of Invention

The disclosure provides a content recommendation method, a content recommendation device, electronic equipment and a server, which at least solve the problem that recommended content is not accurate enough. The technical scheme of the disclosure is as follows:

acquiring acquisition information of a client, wherein the acquisition information comprises information of client playing content and vital sign information acquired through wearable equipment;

determining emotion identification of the content played by the client according to the vital sign information;

searching for recommended content matched with the emotion identification;

and sending the searched recommended content to the client.

According to another aspect of the disclosed embodiment, in the method, the recommended content matched with the emotion identifier includes:

the shared content matched with the emotion mark,

alternatively, the first and second electrodes may be,

and the associated content of the target account matched with the emotion identification.

According to another aspect of the embodiment of the present disclosure, in the method, after sending the found recommended content to the client, the method further includes:

acquiring recommendation feedback information of a client, wherein the recommendation feedback information at least comprises one of playing duration information of the recommended content and terminal operation information during playing of the recommended content;

and when the recommendation result of the recommended content is determined to be successful according to the recommendation feedback information, pushing new recommended content, the matching degree of which with the emotion identification of the recommended content reaches the preset requirement, to the client.

According to another aspect of the embodiments of the present disclosure, in the method, when it is determined that the recommendation result of the recommended content is successful according to the recommendation feedback information, the method further includes:

keeping or improving the recommendation weight of the emotion identification of the recommended content to obtain the recommendation weight after the emotion identification is updated;

correspondingly, the pushing of the new recommended content to the client, the matching degree of which with the emotion identification of the recommended content reaches a preset requirement, includes: and selecting the first M emotion identifications with the highest recommendation weight, and pushing recommendation contents matched with the M emotion identifications to the client, wherein M is a non-zero natural number.

acquiring recommendation feedback information of a client, wherein the recommendation feedback information comprises acquired playing time length information of the recommended content and terminal operation information during playing of the recommended content;

when the recommendation result of the recommended content is determined to be failed according to the recommendation feedback information, reducing the recommendation weight of the emotion identification of the recommended content to obtain the recommendation weight of the historical emotion identification;

determining a new emotion identifier according to the acquired new acquired data;

and selecting the first N emotion identifications with the highest recommendation weight values from the historical emotion identifications and the new emotion identifications, and pushing recommendation contents matched with the N emotion identifications to the client, wherein N is a non-zero natural number.

According to an aspect of an embodiment of the present disclosure, there is provided a content recommendation method including:

acquiring vital sign information acquired by wearable equipment;

sending the playing content information and the vital sign information to a server;

receiving recommended content sent by a server, wherein the recommended content comprises recommended content which is searched by the server and matched with emotion identification of a played video, and the emotion identification is determined according to the vital sign information;

and playing the recommended content.

the shared content matched with the emotion mark,

alternatively, the first and second electrodes may be,

According to another aspect of the embodiments of the present disclosure, in the method, after playing the recommended content, the method further includes:

acquiring recommendation feedback information including playing duration information of the recommended content and terminal operation information when the recommended content is played;

and sending the recommendation feedback information to the server, wherein the recommendation feedback information is used for pushing new recommendation content of which the matching degree with the emotion identification of the recommendation content reaches a preset requirement to the client when the recommendation result of the recommendation content is determined to be successful according to the recommendation feedback information.

According to another aspect of the embodiments of the present disclosure, in the method, after the recommendation feedback information is sent to the server, a new recommended content sent by the server is also received, where the new recommended content is determined by:

when the server determines that the recommendation result of the recommended content is successful according to the recommendation feedback information, maintaining or improving the recommendation weight of the emotion identification of the recommended content to obtain the recommendation weight after the emotion identification is updated;

selecting the first M emotion identifiers with the highest recommendation weight, and taking the recommendation content matched with the M emotion identifiers as new recommendation content, wherein M is a non-zero natural number.

sending the recommendation feedback information to the server, wherein the recommendation feedback information is used for reducing the recommendation weight of the emotion identification of the recommended content to obtain the recommendation weight of the historical emotion identification when the recommendation result of the recommended content is determined to be failed according to the recommendation feedback information;

receiving new recommended content sent by a server, wherein the new recommended content is determined by adopting the following method:

the server selects the first N emotion identifications with the highest recommendation weight values from the new emotion identifications and the historical emotion identifications, takes the recommendation contents matched with the N emotion identifications as new recommendation contents, wherein N is a natural number, and the new emotion identifications are determined according to new acquisition data uploaded by the client.

According to another aspect of the embodiments of the present disclosure, there is also provided a content recommendation apparatus including:

the first receiving module is used for acquiring the acquisition information of the client, wherein the acquisition information comprises the information of the playing content of the client and the vital sign information acquired by the wearable equipment;

the emotion determining module is used for determining emotion identification of the content played by the client according to the vital sign information;

the content searching module is used for searching the recommended content matched with the emotion identification;

and the sending module is used for sending the searched recommended content to the client.

According to another aspect of the disclosed embodiment, in the apparatus, the recommended content matching the emotion identifier may include:

the shared content matched with the emotion mark,

alternatively, the first and second electrodes may be,

According to another aspect of the embodiments of the present disclosure, in the apparatus, the apparatus further includes:

the second receiving module is used for acquiring recommendation feedback information of the client after the searched recommendation content is sent to the client, wherein the recommendation feedback information at least comprises one of playing duration information of the recommendation content and terminal operation information during the playing of the recommendation content;

and the first pushing module is used for pushing new recommended content, the matching degree of which with the emotion identification of the recommended content reaches a preset requirement, to the client when the recommendation result of the recommended content is determined to be successful according to the recommendation feedback information.

the first weight value adjusting module is used for keeping or improving the recommendation weight value of the emotion identifier of the recommended content when the recommendation result of the recommended content is determined to be successful according to the recommendation feedback information, and obtaining the recommendation weight value after the emotion identifier is updated;

correspondingly, the pushing, by the first pushing module, the new recommended content to the client, the matching degree of the emotion identification of the recommended content of which the matching degree reaches the preset requirement includes: and selecting the first M emotion identifications with the highest recommendation weight, and pushing recommendation contents matched with the M emotion identifications to the client, wherein M is a non-zero natural number.

the second receiving module is used for acquiring the acquisition information of the client, wherein the acquisition information comprises the information of the playing content of the client and the vital sign information acquired by the wearable equipment;

the second weight value adjusting module is used for reducing the recommendation weight value of the emotion identification of the recommended content to obtain the recommendation weight value of the historical emotion identification when the recommendation result of the recommended content is determined to be failed according to the recommendation feedback information;

the new emotion determining module is used for determining a new emotion identifier according to the acquired new acquired data;

and the second pushing module is used for selecting the first N emotion identifications with the highest recommendation weight values from the historical emotion identifications and the new emotion identifications, and pushing recommendation contents matched with the N emotion identifications to the client, wherein N is a non-zero natural number.

According to another aspect of the embodiments of the present disclosure, there is also provided a content recommendation apparatus, the apparatus including:

the vital sign acquisition module is used for acquiring vital sign information acquired by the wearable equipment;

the information uploading module is used for sending the playing content information and the vital sign information to a server;

the recommendation content receiving module is used for receiving recommendation content sent by a server, wherein the recommendation content comprises recommendation content which is searched by the server and matched with emotion identification of a played video, and the emotion identification is determined according to the vital sign information;

and the playing module is used for playing the recommended content.

the shared content matched with the emotion mark,

alternatively, the first and second electrodes may be,

the feedback acquisition module is used for acquiring recommendation feedback information comprising the playing duration information of the recommended content and the terminal operation information during the playing of the recommended content when the recommended content is played;

and the first feedback module is used for sending the recommendation feedback information to the server, and the recommendation feedback information is used for pushing new recommended content to the client when the recommendation result of the recommended content is determined to be successful according to the recommendation feedback information, wherein the matching degree of the new recommended content and the emotion identification of the recommended content reaches a preset requirement.

a first new receiving module, configured to receive new recommended content sent by the server after sending the recommendation feedback information to the server, where the new recommended content is determined in the following manner:

the second feedback module is used for sending the recommendation feedback information to the server, and the recommendation feedback information is used for reducing the recommendation weight of the emotion identification of the recommended content to obtain the recommendation weight of the historical emotion identification when the recommendation result of the recommended content is determined to be failed according to the recommendation feedback information;

a second new receiving module, configured to receive new recommended content sent by the server, where the new recommended content is determined in the following manner:

According to another aspect of the embodiments of the present disclosure, there is also provided an electronic device, including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of any embodiment of the present disclosure implemented on a client.

According to another aspect of the embodiments of the present disclosure, there is also provided a storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the method according to any one of the embodiments of the present disclosure implemented in a client.

According to another aspect of the embodiments of the present disclosure, there is also provided a server, including:

at least one processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of any embodiment of the present disclosure implemented in a server.

According to another aspect of the embodiments of the present disclosure, there is also provided a storage medium, wherein instructions in the storage medium, when executed by a processor of a server, enable the server to perform the method of any one of the present disclosure implemented in the server.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

the server can analyze and process data acquired by the client, wherein the data comprises vital sign information acquired by the client through the wearable device. When the terminal account watches the video, the vital sign information can reflect the current emotional state of the terminal account more really, so that the server can determine the emotion of the terminal account when watching the playing content according to the vital sign information, can tag the watched playing content and mark the tagged playing content as a corresponding emotional identifier. Therefore, the server can search the recommended content with the same or similar emotion according to the current emotion identification and return the recommended content to the client, and the client can play the content which is more in line with the current emotion state of the terminal account, so that the accuracy of the recommended content is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

Fig. 1 is a diagram illustrating an application environment of a content recommendation method according to an exemplary embodiment.

Fig. 2 is a diagram illustrating an application environment of a content recommendation method according to an exemplary embodiment.

FIG. 3 is a flow diagram illustrating a method of content recommendation, according to an example embodiment.

FIG. 4 is a flow diagram illustrating a method of content recommendation, according to an example embodiment.

FIG. 5 is a flow diagram illustrating a method of content recommendation, according to an example embodiment.

FIG. 6 is a flow diagram illustrating a method of content recommendation, according to an example embodiment.

FIG. 7 is a flow diagram illustrating a method of content recommendation, according to an example embodiment.

FIG. 8 is a flow diagram illustrating a method of content recommendation, according to an example embodiment.

Fig. 9 is a flow chart illustrating a method of content recommendation according to an example embodiment.

Fig. 10 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 11 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 12 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 13 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 14 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 15 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 16 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 17 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 18 is a block diagram illustrating a content recommendation device according to an example embodiment.

Fig. 19 is an internal structural diagram of an electronic device shown in accordance with an example embodiment.

Fig. 20 is an internal block diagram of a server according to an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. For example, the terms first, second, etc. may be used to denote names, but not to denote any particular order.

The content recommendation method provided by the present disclosure can be applied to the application environment shown in fig. 1. Wherein the terminal 110 may interact with the server 120 through a network connection. The server 120 may transmit video data to the terminal 110, and the terminal 110 may generate and play a video locally after receiving the video data. The video may be played when a video playing Application (APP) is opened on the terminal 110 side, or may be played when the video playing window is activated by switching from another APP to the video playing application. The terminal account may be worn with a wearable device 130, such as the smart watch shown in fig. 1, and the wearable device 130 may collect vital sign information of the user, such as heart rate, body temperature, and the like. These vital sign information may be transmitted to the terminal 110. For example, the wearable device 130 may pair with the terminal 110 through bluetooth, and then the terminal account sends the collected vital sign information to the terminal 110 in real time or periodically. When the terminal 110 plays the video, the currently played video content and the collected vital sign information may be reported to the server 120. The server 120 can determine the emotion when the terminal account watches the video content according to the analysis of the vital sign information, and can mark a corresponding emotion identifier for the video. The server 120 may look up the video or target account for the same emotion and return it to the client. The client side can play the recommended content according to the videos with the same emotion marks or the target account.

The wearable devices described in the embodiments of the present disclosure may generally include a portable device that is worn directly on a person, or integrated into a person's clothing or accessory. If the human body can be directly worn on an intelligent watch, an intelligent shoe and the like of a sambucus quadrifilatus, the intelligent watch, the intelligent shoe and the like can be worn on the head, and the intelligent glasses, the intelligent helmet and the like can be indirectly contacted with the human body or used for human body function assistance or decoration equipment, such as an intelligent coat, an intelligent schoolbag, an intelligent crutch, an intelligent accessory and the like. Generally, the wearable device may be provided with one or more sensors, such as an environmental sensor, an optical heart rate sensor, a temperature sensor, etc. The wearable device may have certain data processing and communication capabilities, such as receiving signals from the sensor device, converting analog signals to digital signals or performing data counting, etc., transmitting collected data to another device, etc. The terminal 110 described in the embodiments of the present disclosure may include, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, vehicle-mounted devices, medical devices, and the like. The servers 120 described in the embodiments of the present disclosure may include, but are not limited to, independent servers, server clusters, distributed processing servers, blockchain servers, cloud computing platforms, and the like, and combinations thereof. The server 120 may be understood as one or more servers on the side opposite to the client 110, such as a server that may analyze and process the vital sign information to determine the emotion identifier, a server that matches the recommended content according to the emotion identifier, and the like. It should be noted that the wearable device and the client may be different devices without mechanical connection, as shown in fig. 1. In another application scenario, a wearable device may be integrated into one device of the client, or the client integrates a sensor device for collecting the vital sign information, or the wearable device has a content recommended by the play server (for example, the wearable device can obtain the vital sign information and also play a video, and can communicate with the server), as shown in fig. 2, the client 110 may integrate a heart rate sensor 140, and the collected information uploaded to the server at this time may still be considered as the vital sign information collected by the client through the wearable device.

For convenience of description, in some embodiments of the present disclosure, an object that views playback content and performs a manipulation behavior at the terminal 110 may be referred to as a terminal account, such as the terminal account C _ user1 that is viewing the video playback application APP _ 1. An account that the server 120 finds to match (same or similar to) the emotion of the terminal account is called a target account, such as the target account S _ user1 that publishes or uploads videos on the content sharing platform, and the server finds the target account S _ user2 that belongs to the emotion identifier "Happy" with the terminal account C _ user 1. The following describes an exemplary implementation scenario in which recommended content is sent to a terminal account according to vital sign information of the terminal account collected by a client. Of course, the following description of the embodiments does not limit other scalable solutions obtained based on the embodiments of the present disclosure. For example, the content played by the client and the recommended content sent to the client may be video, audio, pictures, or texts, or a combination thereof.

Fig. 3 is a flow chart illustrating a content recommendation method according to an exemplary embodiment, which may be used in the server 120 as shown in fig. 3, and may include the following steps.

In step S302, the collected information of the client may be obtained, where the collected information includes information of content played by the client and vital sign information collected by the wearable device.

The vital sign information may include characteristic parameters directly reflecting the vital body of the terminal account, such as heart rate, temperature, blood pressure, and the like, and may also include collected characteristic parameters related to the environment where the vital body of the terminal account is located, such as altitude related to a location, a GPS location (GPS, Global Positioning System), brightness information related to light, acceleration related to a motion state, and the like. The client can establish connection with the wearable device to realize data transmission. In this way, the wearable device can send the acquired vital sign information of the terminal account to the client. For example, the wearable device may establish a connection with the client through near field communication, such as bluetooth, infrared, and the like. The wearable device may send a data packet to the client via near field communication. The data structure of the data packet may be set as a combination of the message type and the message body. The message type can be set to different types of vital signs, such as heart rate, body temperature, altitude, etc., and the message body can be specific data.

The wearable device can periodically or real-timely collect the vital sign information and can periodically or real-timely send the vital sign information to the client. Or the client may also actively acquire the vital sign information of the wearable device before reporting the acquired information or issue an instruction to request the wearable device to send the vital sign information to the client based on the requirement of reporting the acquired information to the server. Or the client can report the acquisition information or other information to the server and receive the vital sign information sent by the wearable device.

The information that the client plays the content may include a category label of the video that the client is playing or has recently played. Generally, a video sharing platform may classify video contents in advance and mark corresponding tags on the video contents, such as a series of drama clips, a national cartoon, a chinese song, a monitoring snapshot, and the like. In some implementations, the classification of the video may include a multi-level classification, may include a parent classification, a child classification, etc., or a primary classification, a secondary classification, etc. For example, the classification label of a certain video can be "make a fun", and can also be "fault collection" of sub-classification under "make a fun". Thus, the client can obtain information including the category label of the playing video. The client can send the classification label of the played video and the vital sign information to a server during or after the video is played. Of course, the collected information may also include other information content, such as a timestamp, an account identifier, publisher information of a video played by the client, and the like, which is not limited in this disclosure.

In step S304, an emotion identifier of the client playing content is determined according to the vital sign information.

The emotion identification may include an identifier indicating the type or degree of emotion that the terminal account is in. For example, the emotion mark "Happy" may be used to indicate a Happy emotion, the "sad" may be used to indicate an impaired emotion, and the expression strength of the expressed emotion may also be used, the "Happy _ 1" may indicate that the degree of the Happy emotion is more drastic, the "Happy _ 2" may indicate that the degree of the Happy emotion is normal, and the "Happy _ 3" may indicate that the terminal account has a little Happy emotion, and the degree of the Happy emotion is lower. After the vital sign information is obtained, some algorithms or models can be adopted to analyze and process the vital sign information, and emotion identification corresponding to the vital sign information is output. The vital sign information can be acquired when the client plays the video or recently, and can reflect the emotional characteristics of the terminal account when the terminal account watches the video, so that the terminal account, the vital sign information, the playing content and the emotional identification can have corresponding relations. For example, the vital sign information collected when the terminal account C _ user1 plays the video Vid _1 is Date _1, and the emotion determined by the server based on the vital sign information Date _1 is identified as "Happy _ 1". Therefore, the emotion flag "Happy _ 1" may be used as an emotion flag to be determined based on the vital sign information Date _1, or as an emotion flag of the played video Vid _1 corresponding to the vital sign information Date _1, or as an emotion flag of the terminal account C _ user1 when viewing the played video Vid _ 1. The emotion mark can be associated with corresponding terminal account, vital sign information, playing content and other information, for example, an emotion label is used as a kind of label for playing video.

In this embodiment, the emotion identifier may be generated by processing data of the vital sign information using one or more algorithms, or may be determined by combining one or more machine learning models. The Machine learning model may employ supervised Machine learning models such as Logistic Regression (LR) and Support Vector Machine (SVM), for example. Or a emotion recognition model is constructed in advance based on a Convolutional Neural Network (CNN) and the like, and the emotion recognition model is trained by using the vital sign samples. The server can input the emotion recognition model after acquiring the vital sign information, and the emotion recognition model can output corresponding emotion classification (emotion identification).

In step S306, the recommended content matching the emotion identification is searched.

The matching may include that the searched emotion identifier of the recommended content and the emotion identifier of the content played by the client meet a preset matching requirement. For example, the emotion identifier "Happy _ 1" of a certain video Vid _1 searched by the server side is the same as the emotion identifier "Happy _ 1" of the content played by the client, it may be determined that the emotion identifier of the video Vid _1 matches the emotion identifier, and then the video Vid _1 may be used as the recommended content matching the emotion identifier "Happy _ 1".

In other embodiments, the matching may also include that the similarity or the association degree of the emotion identifiers meets a preset matching requirement. For example, the found emotion identifier of a certain video Vid _1 is "Happy _ 1", the determined emotion identifier of the content played by the client is "Happy", the processing unit judges that the similarity between "Happy _ 1" and "Happy" meets the matching requirement and both belong to Happy emotion categories, or judges that "Happy _ 1" belongs to a sub-category of a "Happy" parent category, and the association degree meets the matching requirement, and can determine that the emotion identifier "Happy _ 1" of the video Vid _1 is matched with the emotion identifier "Happy", so that the video Vid _1 can be used as recommended content matched with the emotion identifier "Happy".

The server can search in a local or special storage unit for storing the shared content such as the video and the like in the server according to the emotion identifier, and search for the content matched with the emotion identifier. The searched content matched with the emotion identifier can be wholly or partially used as recommended content pushed to the terminal account. As described above, the found recommended content may be content of the same media type as the content played by the client, such as video content, or other types of recommended content, such as audio or images matched with the emotion identifier.

In step S308, the found recommended content is sent to the client.

The server can send all or part of the searched content matched with the emotion identifier to the client as recommended content pushed to the terminal account. When a plurality of matched contents are found, a pre-designed algorithm can be adopted to further screen out recommended contents which are finally sent to the client. For example, when the server finds videos of multiple fun categories according to the emotion identifier "happy", one video with the highest matching degree can be further screened out according to attributes such as age and gender of the terminal account and sent to the client as recommended content.

The content recommendation method provided by the disclosure can analyze and process data acquired by the client, wherein the data comprises vital sign information acquired by the client through wearable equipment. When the terminal account watches the video, the vital sign information can reflect the current emotional state of the terminal account more really, so that the server can determine the emotion of the terminal account when watching the playing content according to the vital sign information, can tag the watched playing content and mark the tagged playing content as a corresponding emotional identifier. Therefore, the server can search the recommended content with the same or similar emotion according to the current emotion identification and return the recommended content to the client, and the client can play the content which is more in line with the current emotion state of the terminal account, so that the accuracy of the recommended content is improved.

In another exemplary embodiment of the present disclosure, the emotion identifier may be used not only as an identifier of the video and other shared content, but also as an emotion identifier of the target account. For example, the emotion identifier of the terminal account C _ user1 watching a short video at the video playing application APP _1 is "Happy", the server 120 may look up the target account S _ user1, which emotion identifier is also "Happy", for a certain period of time (e.g. within the last 3 minutes of the current time). The associated information of the target account S _ user1 may then be used as the recommended content. The content associated with the target account may include information related to the target account, such as an account number, a direct broadcast number, a video introduction of the target account, and the like, and may also include broadcast content belonging to the target account, such as a video belonging to the target account S _ user 1. Therefore, in another exemplary embodiment of the present disclosure, the recommended content matched with the emotion identification may include:

the shared content matched with the emotion mark,

alternatively, the first and second electrodes may be,

The shared content generally refers to specific media information, such as video data, audio data, pictures, and the like that can be played at the client. For example, the shared content involved in short video applications may include video data. After the emotion of the terminal account is recognized, the sharing content matched with the emotion can be pushed to the client, the target account matched with the emotion can be found, then the related information of the target account or the sharing content of the target account is pushed to the terminal account, the terminal account can quickly acquire the related content of the target account with the same emotion, the accuracy of recommended content is further improved, the recommended content and the recommendation mode are more diversified, and the terminal account interaction experience is enriched and improved.

Fig. 4 is a flowchart illustrating a content recommendation method according to an exemplary embodiment, and as shown in fig. 4, in another exemplary embodiment of the present disclosure, after sending the found recommended content to the client, the method may further include:

s402: acquiring recommendation feedback information of a client, wherein the recommendation feedback information at least comprises one of playing duration information of the recommended content and terminal operation information during playing of the recommended content;

s404: and when the recommendation result of the recommended content is determined to be successful according to the recommendation feedback information, pushing new recommended content, the matching degree of which with the emotion identification of the recommended content reaches the preset requirement, to the client.

The recommendation feedback information may include information about a playing condition of the recommended content acquired and obtained by the client at the client, and may also include an operation behavior (which may be terminal operation information) performed on the client when the terminal account views the recommended content. For example, the client may collect the play duration information of the recommended content, and may also collect terminal operation information such as approval, collection, sharing, and the like of a terminal account when the recommended content is played. The playing time length information may be an absolute value of the playing time length, or may be a relative value of the playing time length compared with the complete playing time length of the recommended content. For example, when the recommended content is a short video of 10 seconds, if the client detects that the short video is played for only 5 seconds, the playing time length information may be 5 seconds. Or, the client may determine that the playing time information is 50% based on that the complete playing time of the short video is 10 seconds and the actual playing time is 5 seconds. In another example, if the full playing time length of the short video is 10 seconds, and the short video is actually played for 10 seconds, the playing time length information may be determined to be 100%, or it may be determined that the short video is completely played.

The server may analyze the recommendation feedback information to determine whether the recommendation result of the recommended content sent to the client is successful. The decision of whether the recommendation is successful may include one or more information. For example, in one implementation manner, it may be set that if the recommendation content is completely played by the client, the recommendation result of the recommended content may be determined to be successful, or if the recommendation feedback information includes that the terminal account acquired by the client performs a praise operation on the recommended content, the recommendation result of the recommended content may be determined to be successful. Of course, the two recommendation feedback information may also be set comprehensively, for example, when the playing time length information is not less than 10 seconds and at least one of the terminal operation information of praise, analysis, comment and repeat playing is included, the recommendation result of the recommended content is determined to be successful.

The recommendation result of the recommended content may be identified using field information or an identifier. For example, the field "Result" may be used to indicate that the recommendation Result is successful, and the value "Result" is "true" indicates that the recommendation Result is failed. The server can determine the value of Result according to the recommendation feedback information, and further determine whether the recommendation Result is successful or identification. Of course, this disclosure does not exclude that other ways of indicating whether the recommendation result is successful or recognized may be used, such as determining that the recommendation result is successful directly according to whether the recommendation content is played completely and the like is performed.

If the server determines that the recommendation result of the recommended content is successful according to the recommendation feedback information, which may indicate that the recommended content meets the current emotional requirement of the terminal account, in some embodiments of the present disclosure, the recommended content with the same or similar emotional identifier as the recommended content may be further pushed to the client. And specifically acquiring new recommended content of which the matching degree with the emotion identification of the recommended content reaches a preset requirement. For example, the recommended content may be searched again according to the emotion identifier or the previously searched matched recommended content may be used as the new recommended content. The embodiment in which the matching degree meets the preset requirement may also refer to the embodiment of "matching" in step S306. Of course, the matching requirement set in the process of determining the new recommended content may be the same as or different from the matching requirement set in the process of determining the recommended content.

Fig. 5 is a flowchart illustrating a content recommendation method according to an exemplary embodiment, and as shown in fig. 5, in another exemplary embodiment of the present disclosure, when it is determined that the recommendation result of the recommended content is successful according to the recommendation feedback information, the method further includes:

s502: keeping or improving the recommendation weight of the emotion identification of the recommended content to obtain the recommendation weight after the emotion identification is updated;

The different emotion identifications may be identified by corresponding recommendation weights. The recommendation weight value may represent an emotion identifier corresponding to the recommended content as a weight of the recommended content. Generally, the higher the recommendation weight (the larger the value) of a certain emotion identifier, the content corresponding to the emotion identifier may be pushed preferentially. The recommendation weight of the emotion recognition may be varied or adjusted. For example, if the emotion identifier of the terminal account when watching the video Vid _1 is determined to be "Happy _ 3" according to the vital sign information, it indicates that the emotion of the terminal account is more Happy at this time. And then sending a video Vid _2 of 'Happy _ 3' to the client, wherein the video Vid _2 is the matched recommended content found according to the emotion identification. According to the recommendation feedback information of the recommended content Vid _2 fed back by the client, the terminal account finishes watching the video Vid _2 and likes the video Vid _2, and the terminal account likes the recommended content Vid _2, so that the recommended content meets the content watching requirement of the current emotional state of the terminal account. At this time, the recommendation weight of the emotion identifier "Happy _ 3" may be increased from the last recommendation weight of 0.8 to 0.85. If the recommendation result of the recommended content is successful, the recommendation weight of the emotion mark can be updated, and the updated recommendation weight is obtained. Of course, the recommendation weight may also remain unchanged, and in the embodiment of the present disclosure, the recommendation weight that remains unchanged still belongs to one of the embodiments of the updated recommendation weight.

Since the recommendation weight is added to the emotion identifier in the embodiment of the present disclosure, accordingly, when the server recommends new content (new recommended content) to the client, in an embodiment, the recommended content corresponding to the emotion identifier with a high recommendation weight may be preferentially used as new recommended content, and the new recommended content may be sent to the client. For example, the emotion identifier with the highest recommendation weight (i.e., M ═ 1) may be selected as the emotion state that is most matched with the terminal account currently, and then the recommended content that matches the emotion identifier with the highest recommendation weight may be pushed to the client. And selecting the recommended values of the top M emotion identifications, wherein the recommended values can comprise the recommended weight values updated from the emotion identifications, and can also comprise the recommended weight values of newly generated or previous emotion identifications. For the matching, the specific implementation manner may refer to the related description of the matching in the foregoing related embodiments, and is not described herein again.

And when the recommended content or the new recommended content is selected, if the determined emotion identification exists, selecting the recommended content with one or more emotion identifications and pushing the recommended content to the user. The minimum requirement for the recommendation weight may also be set in some embodiments. For example, if the recommendation weight is lower than 0.3, it may indicate that the recommended content may not conform to the current emotional state of the terminal account, and may be set as a normal recommendation policy according to age, gender, and the like.

Therefore, whether the terminal account likes the recommended content or not can be identified according to the playing time information of the recommended content and the terminal operation information of the terminal account, if yes, the weight of the emotion mark corresponding to the recommended content can be improved, the emotion type content can be continuously pushed subsequently, the emotion state of the terminal account for watching the recommended content is met, the accuracy of the recommended content is improved, and the experience of the terminal account for watching and sharing the content is also improved.

Fig. 6 is a flowchart illustrating a content recommendation method according to an exemplary embodiment, and as shown in fig. 6, in another exemplary embodiment of the present disclosure, after sending the found recommended content to the client, the method may further include:

s602: acquiring recommendation feedback information of a client, wherein the recommendation feedback information at least comprises one of playing duration information of the recommended content and terminal operation information during playing of the recommended content;

s604: when the recommendation result of the recommended content is determined to be failed according to the recommendation feedback information, reducing the recommendation weight of the emotion identification of the recommended content to obtain the recommendation weight of the historical emotion identification;

s606: determining a new emotion identifier according to the acquired new acquired data;

s608: and selecting the first N emotion identifications with the highest recommendation weight values from the historical emotion identifications and the new emotion identifications, and pushing recommendation contents matched with the N emotion identifications to the client, wherein N is a natural number.

The step S602 may refer to the step S402, which is not described herein.

In step 604, if it is determined that the recommendation result of the recommended content is failed according to the recommendation feedback information, the recommendation weight of the emotion identifier of the recommended content may be correspondingly reduced. For example, in the foregoing example, if it is determined from the vital sign information that the emotion of the terminal account is marked as "Happy _ 3" when the terminal account watches the video Vid _1, it indicates that the emotion of the terminal account is more Happy at this time. And then sending a video Vid _3 of 'Happy _ 3' to the client, wherein the video Vid _3 is the matched recommended content which is found according to the emotion identification. According to the recommendation feedback information of the recommended content Vid _3 fed back by the client, the terminal account does not see the video Vid _3 completely, the video is quickly slipped away, the fact that the terminal account does not like the recommended content Vid _3 can be shown, and the fact that the recommended content meets the content watching requirement which does not meet the current emotional state of the terminal account is shown. At this time, the emotion label "Happy _ 3" recommendation weight may be reduced from the last recommendation weight of 0.85 to 0.75. For convenience of description and distinction, the emotion identifier after the recommendation weight is adjusted (including decreasing, increasing, and maintaining) may be referred to as a historical emotion identifier.

In step S606, new collected data of the client may be obtained, and the emotion identifier (which may be referred to as a new emotion identifier) of the terminal account is determined again according to the vital sign information in the new collected data, or by combining the play duration information of the recommended content, the terminal operation information, and the like.

After the new emotion mark is determined again in the same way as the successful recommendation result of the recommended content, if there are multiple emotion marks, for example, the method may include the emotion mark F1 determined according to the previous collected data (the new collected data obtained last time is used as the collected data in the implementation process of the present embodiment), the historical emotion mark F2 after the emotion mark is raised or lowered, and the new emotion mark F3 determined according to the obtained new collected data. And selecting the recommended content matched with the first N emotion identifiers with the highest recommended weight value and pushing the recommended content to the client. For example, in an implementation example where N is 1, the recommendation weight values of the historical emotion identifications are 0.92 and 0.80, respectively, and the recommendation weight value of the new emotion identification is 0.85, at this time, although it is determined that the recommendation weight value of the current latest emotion identification of the terminal account is 0.85 according to the latest collected data, the current latest emotion identification of the terminal account still cannot become the optimal emotion identification of the recommended content, for example, the terminal account may only be a temporary emotion change, or the terminal account may handle a slow decline stage of the emotion change, but is not suitable for immediately changing the emotion identification of the recommended content (the emotion change usually does not change the content a lot of times in a period of time). Therefore, the recommended content of the emotion mark represented by 0.92 with the highest recommendation weight can still be selected and sent to the client. Of course, if the recommendation weight of the new emotion identifier obtained according to the algorithm or the model of the emotion identifier is 0.95, the recommendation content matched with the new emotion identifier can be pushed to the client.

As previously mentioned, the minimum requirement for the recommendation weight may also be set in some embodiments. For example, if the recommendation weight is lower than 0.3, it may be indicated that the recommended content may not conform to the current emotional state of the terminal account, and the value of N may be set to 0, that is, the content may not be recommended according to the emotion tag any more, and the recommended content may be selected by using a normal recommendation policy according to age, gender, and the like.

Therefore, according to the embodiment, whether the terminal account likes the recommended content or not can be identified according to the recommended content playing time length information and the terminal operation information of the terminal account. If the user does not like the user, the weight of the emotion mark corresponding to the recommended content can be reduced, a new emotion label can be determined again according to the vital sign information collected by the wearable device, and then the first N emotion marks with the highest recommended weight are screened out. Therefore, the emotion identification and the corresponding recommendation weight value can be continuously updated according to the continuously acquired vital sign information, the emotion state change of the terminal user is tracked, the recommendation content is enabled to be more consistent with the emotion state of the terminal account for watching the recommendation content, the accuracy of the recommendation content is improved, and the experience of the terminal account for watching and sharing the content is also improved.

The present disclosure also provides a content recommendation method that can be used on the client 110 side, described with reference to an embodiment of the method that can be used on the server S120 side. In a specific example embodiment, as shown in fig. 7, the method may include:

s702: acquiring vital sign information acquired by wearable equipment;

s704: sending the playing content information and the vital sign information to a server;

s706: receiving recommended content sent by a server, wherein the recommended content comprises recommended content which is searched by the server and matched with emotion identification of a played video, and the emotion identification is determined according to the vital sign information;

s708: and playing the recommended content.

In another exemplary embodiment of the content recommendation method of the present disclosure, the recommending content matched with the emotion identification may include:

the shared content matched with the emotion mark,

alternatively, the first and second electrodes may be,

Fig. 8 is a flowchart illustrating a content recommendation method according to an exemplary embodiment, and as shown in fig. 8, in another exemplary embodiment of the present disclosure, after playing the recommended content, the method further includes:

s802: acquiring recommendation feedback information including playing duration information of the recommended content and terminal operation information when the recommended content is played;

s804: and sending the recommendation feedback information to the server, wherein the recommendation feedback information can be used for pushing new recommended content of which the matching degree with the emotion identification of the recommended content reaches a preset requirement to the client when the recommendation result of the recommended content is determined to be successful according to the recommendation feedback information.

Fig. 9 is a flowchart illustrating a content recommendation method according to an exemplary embodiment, and as shown in fig. 9, in another exemplary embodiment of the present disclosure, after sending the recommendation feedback information to the server, the method may further include:

s902: and receiving the new recommended content sent by the server. Wherein the new recommended content is determined in the following manner:

Fig. 10 is a flowchart illustrating a content recommendation method according to an exemplary embodiment, and as shown in fig. 10, in another exemplary embodiment of the present disclosure, after playing the recommended content, the method further includes:

s1002: acquiring recommendation feedback information including playing duration information of the recommended content and terminal operation information when the recommended content is played;

s1004: sending the recommendation feedback information to the server, wherein the recommendation feedback information is used for reducing the recommendation weight of the emotion identification of the recommended content to obtain the recommendation weight of the historical emotion identification when the recommendation result of the recommended content is determined to be failed according to the recommendation feedback information;

s1006: receiving new recommended content sent by a server, wherein the new recommended content is determined by adopting the following method:

The dashed lines in fig. 9, 10 may indicate steps that may be repeatedly performed. For example, the client plays the recommended content, and sends one or more of recommended feedback information, vital sign information, played content information, and the like to the server. And the server continuously acquires new recommended content according to the information and then sends the new recommended content to the client. And when playing the new recommended content, the client continuously collects the vital sign information, sends new recommended feedback information and new collected information to the server, and the server analyzes the information to determine the new recommended content and then sends the new recommended content to the client for processing.

The above embodiments of the method that can be used on the client side may refer to the description of the foregoing embodiments on the server side. According to the method embodiment which can be implemented on one side of the client, the client can obtain the vital sign information of the wearable device, the emotion of the terminal account can be predicted according to the vital sign information, the recommended content which is the same as or similar to the emotion of the terminal account can be displayed on the client, the content recommendation accuracy of the client is improved, the consumption time of the terminal account on terminal content sharing application (such as short video application) is prolonged, and the viscosity and the use/interaction experience of the terminal account are improved.

It is understood that the embodiments of the client-side or server-side method described above are described in a progressive manner, and the same/similar parts of the embodiments may be referred to each other, and each embodiment focuses on differences from the other embodiments. Reference may be made to the description of other method embodiments for relevant points.

It should be understood that, although the steps in the flowcharts in fig. 2 to 10 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-10 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the steps or stages of other steps.

Based on the description of the content recommendation method embodiment, the present disclosure also provides a content recommendation device. The apparatus may include a system (including a distributed system), software (applications), modules, components, servers, logic function circuits, clients, etc. that use the methods described in embodiments of the present specification in conjunction with hardware as necessary to implement the apparatus. Based on the same innovative concept, the embodiments of the present disclosure provide an apparatus in one or more embodiments as described in the following embodiments. Since the implementation scheme of the apparatus for solving the problem is similar to that of the method, the specific implementation of the apparatus in the embodiment of the present specification may refer to the implementation of the foregoing method, and repeated details are not repeated. As used in this disclosure, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 11 is a block diagram illustrating a content recommendation device according to an example embodiment. The device may be a server, such as the server 120 described above. Referring specifically to fig. 11, the apparatus 200 may include:

the first receiving module 1102 may be configured to obtain acquisition information of a client, where the acquisition information includes information of content played by the client and vital sign information acquired by a wearable device;

the emotion determining module 1104 can be configured to determine an emotion identifier of the content played by the client according to the vital sign information;

a content search module 1106, which can be configured to search for recommended content matching the emotion identifier;

a sending module 1108, configured to send the found recommended content to the client.

In an exemplary embodiment, the recommended content matching the emotion identification may include:

the shared content matched with the emotion mark,

alternatively, the first and second electrodes may be,

An exemplary embodiment is shown in fig. 12, and fig. 12 is a block diagram of another content recommendation device according to an exemplary embodiment. Referring to fig. 12, the apparatus 200 may further include:

the second receiving module 1202 may be configured to obtain recommendation feedback information of the client after sending the found recommended content to the client, where the recommendation feedback information at least includes one of the playing duration information of the recommended content and the terminal operation information when the recommended content is played;

the first pushing module 1204 may be configured to, when it is determined that the recommendation result of the recommended content is successful according to the recommendation feedback information, push new recommended content to the client, where a matching degree of the emotion identifier of the recommended content meets a preset requirement.

An exemplary embodiment is shown in fig. 13, and fig. 13 is a block diagram of a content recommendation device according to an exemplary embodiment. Referring to fig. 13, the apparatus 200 may further include:

a first weight value adjusting module 1302, configured to keep or promote a recommendation weight value of the emotion identifier of the recommended content when it is determined that the recommendation result of the recommended content is successful according to the recommendation feedback information, so as to obtain a recommendation weight value after the emotion identifier is updated;

correspondingly, the pushing, by the first pushing module 1204, the new recommended content to the client, the matching degree of the emotion identifier of the recommended content of which the matching degree reaches the preset requirement includes: and selecting the first M emotion identifications with the highest recommendation weight, and pushing recommendation contents matched with the M emotion identifications to the client, wherein M is a non-zero natural number.

An exemplary embodiment is shown in fig. 14, and fig. 14 is a block diagram of a content recommendation device according to an exemplary embodiment. Referring to fig. 14, the apparatus 200 may further include:

the second receiving module 1202 may be configured to obtain acquisition information of the client, where the acquisition information includes information of content played by the client and vital sign information acquired by the wearable device;

the second weight value adjusting module 1404 may be configured to, when it is determined that the recommendation result of the recommended content is a failure according to the recommendation feedback information, reduce the recommendation weight value of the emotion identifier of the recommended content to obtain a recommendation weight value of a historical emotion identifier;

a new emotion determination module 1406, which may be configured to determine a new emotion identifier according to the obtained new collected data;

the second pushing module 1408 may be configured to select the top N emotion identifiers with the highest recommendation weight values from the historical emotion identifiers and the new emotion identifiers, and push the recommendation content matched with the N emotion identifiers to the client, where N is a non-zero natural number.

Based on the foregoing description of the method embodiments that can be implemented on the client side, the present disclosure also provides a content recommendation device. Fig. 15 is a block diagram illustrating a content recommendation device according to an example embodiment. The apparatus may be a client 110, and specifically, referring to fig. 15, the apparatus 100 may include:

a vital sign acquisition module 1502, which can be used to acquire vital sign information acquired by the wearable device;

the information uploading module 1504 may be configured to send the playing content information and the vital sign information to a server;

a recommended content receiving module 1506, configured to receive recommended content sent by a server, where the recommended content includes recommended content that is found by the server and matched with an emotion identifier of a playing video, where the emotion identifier is determined according to the vital sign information;

a playing module 1508, which may be configured to play the recommended content.

the shared content matched with the emotion mark,

alternatively, the first and second electrodes may be,

An exemplary embodiment is shown in fig. 16, and fig. 16 is a block diagram of a content recommendation device according to an exemplary embodiment. Referring to fig. 16, the apparatus 100 may further include:

a feedback collection module 1602, configured to collect recommendation feedback information including play duration information of the recommended content and terminal operation information when the recommended content is played;

the first feedback module 1604 may be configured to send the recommendation feedback information to the server, where the recommendation feedback information is used to push new recommended content to the client when it is determined that the recommendation result of the recommended content is successful according to the recommendation feedback information, where the matching degree of the emotion identification of the recommended content meets a preset requirement.

An exemplary embodiment is shown in fig. 17, and fig. 17 is a block diagram of a content recommendation device according to an exemplary embodiment. Referring to fig. 17, the apparatus 100 may further include:

a first new receiving module 1702, configured to receive, after sending the recommendation feedback information to the server, new recommended content sent by the server, where the new recommended content is determined in the following manner:

An exemplary embodiment is shown in fig. 18, and fig. 18 is a block diagram of a content recommendation device according to an exemplary embodiment. Referring to fig. 18, the apparatus 100 may further include:

a second feedback module 1804, configured to send the recommendation feedback information to the server, where the recommendation feedback information is used to reduce a recommendation weight of an emotion identifier of the recommended content when it is determined that the recommendation result of the recommended content is a failure according to the recommendation feedback information, so as to obtain a recommendation weight of a historical emotion identifier;

a second new receiving module 1802, configured to receive a new recommended content sent by a server, where the new recommended content is determined by:

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.

It should be noted that, the descriptions of the above-mentioned apparatuses, devices, servers, and the like according to the method embodiments may also include other embodiments, and specific implementations may refer to the descriptions of the related method embodiments. Meanwhile, the new embodiment formed by the mutual combination of the features of the methods, the devices, the equipment and the server embodiments still belongs to the implementation range covered by the present disclosure, and the details are not repeated herein.

For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, when implementing one or more of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, etc. The above-described apparatus embodiments are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another module apparatus/system, or some features may be omitted or not executed. In addition, the coupling, communication connection, etc. between the devices or units shown or described may be realized by direct and/or indirect coupling/connection, and may be realized by some standard or customized interfaces, protocols, etc., in an electrical, mechanical or other form.

Fig. 19 is a block diagram illustrating a processing device Z00 for content recommendation according to an example embodiment. The device Z00 may be an electronic device on the video viewing account side, for example, device Z00 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, or the like.

Referring to fig. 19, device Z00 may include one or more of the following components: a processing component Z02, a memory Z04, a power component Z06, a multimedia component Z08, an audio component Z10, an interface for input/output (I/O) Z12, a sensor component Z14 and a communication component Z16.

The processing component Z02 generally controls the overall operation of the device Z00, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component Z02 may include one or more processors Z20 to execute instructions to perform all or part of the steps of the method described above. Further, the processing component Z02 may include one or more modules that facilitate interaction between the processing component Z02 and other components. For example, the processing component Z02 may include a multimedia module to facilitate interaction between the multimedia component Z08 and the processing component Z02.

The memory Z04 is configured to store various types of data to support operations at device Z00. Examples of such data include instructions for any application or method operating on device Z00, contact data, phonebook data, messages, pictures, videos, etc. The memory Z04 may be implemented by any type or combination of volatile or non-volatile storage devices, such as static random access memory (12RAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component Z06 provides power to the various components of the device Z00. The power component Z06 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device Z00.

The multimedia component Z08 comprises a screen between the device Z00 and the object providing an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from an object. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component Z08 includes a front facing camera and/or a rear facing camera. When device Z00 is in an operating mode, such as a capture mode or a video mode, the front-facing camera and/or the rear-facing camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component Z10 is configured to output and/or input an audio signal. For example, the audio component Z10 includes a Microphone (MIC) configured to receive external audio signals when the device Z00 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory Z04 or transmitted via the communication component Z16. In some embodiments, the audio component Z10 further includes a speaker for outputting audio signals.

The I/O interface Z12 provides an interface between the processing component Z02 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly Z14 includes one or more sensors for providing status assessment of various aspects to the device Z00. For example, sensor assembly Z14 may detect the open/closed state of device Z00, the relative positioning of the components, such as the display and keypad of device Z00, sensor assembly Z14 may also detect a change in the position of one component of device Z00 or device Z00, the presence or absence of an object in contact with device Z00, the orientation or acceleration/deceleration of device Z00, and a change in the temperature of device Z00. The sensor assembly Z14 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly Z14 may also include a light sensor, such as a CMO12 or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly Z14 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component Z16 is configured to facilitate wired or wireless communication between device Z00 and other devices. Device Z00 may access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component Z16 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component Z16 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the device Z00 may be implemented by one or more application specific integrated circuits (a12IC), digital signal processors (D12P), digital signal processing devices (D12PD), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described content recommendation method, which may be implemented on the client side.

It should be noted that the device Z00 may be an exemplary description of an electronic device on the side of playing shared content, such as a mobile phone. In some end products it may not be necessary to include all of the above components or all of the functional units under a component.

In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium, such as a memory Z04, comprising instructions executable by the processor Z20 of the device Z00 to perform the above-described content recommendation method that may be implemented on the client side. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Fig. 20 is a block diagram illustrating a content recommendation device S00 according to an example embodiment. For example, the device S00 may be a combination of one or more servers, such as a server that analyzes and processes the vital sign information and determines the emotion label, a server that searches for matching recommended content according to the emotion identifier, a server that adjusts the recommendation weight of the emotion identifier, and the like, as well as combinations thereof. Referring to FIG. 20, device S00 includes a processing component S20 that further includes one or more processors and memory resources represented by memory S22 for storing instructions, e.g., applications, that are executable by processing component S20. The application program stored in the memory S22 may include one or more modules each corresponding to a set of instructions. Further, the processing component S20 is configured to execute instructions to perform the content recommendation method described above, which may be implemented on a server.

The device S00 may also include a power supply component S24 configured to perform power management of the device S00, a wired or wireless network interface S26 configured to connect the device S00 to a network, and an input-output (I/O) interface S28. The device S00 may operate based on an operating system stored in memory S22, such as Window 1212 erver, Mac O12X, Unix, Linux, FreeB12D, or the like.

In an exemplary embodiment, there is also provided a storage medium, such as the memory S22, including instructions executable by the processor of the device S00 to perform the above-described content recommendation method that may be implemented on the server side. The storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like. And other implementations of a readable storage medium, such as quantum storage, graphene storage, and so forth.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A content recommendation method, comprising:

searching for recommended content matched with the emotion identification;

and sending the searched recommended content to the client.

2. The method according to claim 1, wherein after sending the found recommended content to the client, the method further comprises:

3. The method according to claim 2, wherein when it is determined that the recommendation result of the recommended content is successful according to the recommendation feedback information, further comprising:

4. A content recommendation method, comprising:

acquiring vital sign information acquired by wearable equipment;

and playing the recommended content.

5. A content recommendation apparatus characterized by comprising:

6. A content recommendation apparatus, characterized in that the apparatus comprises:

and the playing module is used for playing the recommended content.

7. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of claim 4.

8. A storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the method of claim 4.

9. A server, comprising:

at least one processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of any one of claims 1 to 3.

10. A storage medium, wherein instructions in the storage medium, when executed by a processor of a server, enable the server to perform the method of any one of claims 1 to 3.