WO2020015657A1

WO2020015657A1 - Mobile terminal, and method and apparatus for pushing video

Info

Publication number: WO2020015657A1
Application number: PCT/CN2019/096212
Authority: WO
Inventors: 高杰
Original assignee: 奇酷互联网络科技（深圳）有限公司
Priority date: 2018-07-17
Filing date: 2019-07-16
Publication date: 2020-01-23
Also published as: CN108989887A

Abstract

Disclosed are a mobile terminal, and a method and apparatus for pushing a video, wherein the method and apparatus are applied to the mobile terminal, and the method comprises the following steps: acquiring facial feature data when the screen of a mobile terminal is unlocked; according to the facial feature data, analyzing the current mood of a user; determining whether the mood state is a pre-set unhappy mood; and if so, pushing a specific video to the user according to a pre-set rule, so as to adjust the mood of the user. According to the present application, in the process of unlocking a screen through facial recognition, the recognized facial feature data is brought into a mood analysis model for analysis to obtain the mood of the current user; and when it is determined that the current mood of the user is an unhappy state, a corresponding video is pushed to help the user adjust their mood. In the present application, the grading of videos to be pushed is also carried out, so that a video that better conforms to requirements of the user is pushed, so as to achieve the purpose of rapidly and effectively adjusting the mood of the user, and enabling a mobile phone to more intelligently accompany the user.

Description

Mobile terminal and method and device for pushing video

[Technical Field]

The present invention relates to the field of computers, and in particular, to a mobile terminal and a method and device for pushing video.

【Background technique】

Existing mobile phones not only have the functions of making calls and making calls, but also have the functions of wallets, entertainment functions such as playing games and watching movies, etc. The mobile phones have become increasingly inseparable daily necessities, such as users' good friends accompanying the users, but the existing mobile phones are still The user's current mood state cannot be identified, and a suitable accompany method cannot be given according to the user's mood state. For example, when the user is in a bad mood, he cannot help the user to adjust his mood. The accompany mode of the mobile phone is still not intelligent enough, and needs to be improved.

[Summary of the Invention]

The main purpose of the present invention is to provide a method for pushing video, which aims to solve the problem that the existing mobile phone cannot identify the user's mood state and cannot help the user to adjust the mood.

In order to achieve the above-mentioned object of the present invention, the present invention proposes a method for pushing video, which is applied to a mobile terminal and includes steps:

Acquiring facial feature data when the screen of the mobile terminal is unlocked;

Analyze the current mood state of the user according to the facial feature data;

Determining whether the mood state is a preset unhappy mood state;

If so, the specified video is pushed to the user according to a preset rule to adjust the user's mood.

Further, the step of analyzing the current mood state of the user according to the facial feature data includes:

Sending the facial feature data to a server;

The receiving server inputs the facial feature data into a mood state recognition model, and obtains mood analysis data, where the mood analysis data includes a mood state and a preset level corresponding to the mood state.

Further, the mood state recognition model is obtained by inputting the collected expression data into a training model as a training sample.

Further, the step of determining whether the mood state is a preset unhappy mood state includes:

Inputting the preset unhappy mood state into the mood recognition model to obtain a first vector;

Inputting the facial feature data into a mood state recognition model to obtain a second vector;

Performing Euclidean distance calculation on the second vector and the first vector;

If the Euclidean distance is less than a preset value, it is determined that the mood state is a preset unhappy mood state.

Further, the step of pushing a specified video to a user according to a preset rule includes:

Obtain the level corresponding to the current unhappy mood state of the user;

According to the level corresponding to the unhappy mood state, a video with a preset amusement level is selected by the user.

Further, the preset amusement level is related to the comedy index of the video.

Further, after the step of selecting a video corresponding to the amusement level according to the level corresponding to the unhappy mood state, the method includes:

Collect real-time facial feature change data during user watching video and send it to the server;

Receive in real time the analysis of the facial feature change data sent by the server to obtain the mood state change data;

Judging whether the pushed video is appropriate according to the change trend of the mood state change data;

If not, re-screen the higher-rated videos pushed by the server.

Further, after the step of pushing the specified video to the user according to a preset rule, the method includes:

Count the user's rating data for each recommended video;

The one-to-one correspondence between each recommended video is updated to the video level folder corresponding to each of the rating data according to the rating data.

This application also provides a device for pushing video, which is integrated in a mobile terminal and includes:

An obtaining module, configured to obtain facial feature data when the screen of the mobile terminal is unlocked;

An analysis module, configured to analyze a user's current mood state according to the facial feature data;

A judging module, configured to judge whether the mood state is a preset unhappy mood state;

A push module is configured to push a specified video to a user according to a preset rule to adjust the user's mood if it is a preset unhappy mood state.

Further, the analysis module includes:

A sending unit, configured to send the facial feature data to a server;

A first receiving unit is configured to receive mood analysis data obtained by the server after inputting the facial feature data into a mood state recognition model, where the mood analysis data includes a mood state and a preset level corresponding to the mood state.

Further, the first receiving unit is further configured to:

Receiving a first vector obtained by inputting the preset unhappy mood state into the mood recognition model;

Receiving a second vector obtained by inputting the facial feature data into a mood state recognition model;

The judgment module is further configured to:

Further, the push module includes:

An obtaining unit, configured to obtain a level corresponding to the current unhappy mood state of the user;

The selecting unit is configured to select a video with a preset amusement level by the user according to the level corresponding to the unhappy mood state.

Further, the push module further includes:

An acquisition unit, which is used to collect real-time facial feature change data during a user watching a video and send the data to a server;

A second receiving unit, configured to receive, in real time, the mood state change data obtained by analyzing the facial feature change data sent by the server;

A judging unit, configured to judge whether the pushed video is appropriate according to a change trend of the mood state change data;

The filtering unit is configured to re-screen videos with higher ratings pushed by the server if the videos pushed are not suitable.

Further, the device for pushing video further includes:

A statistics module, which is used to collect statistics on user ratings of each recommended video;

An update module is configured to update each of the recommended videos in a one-to-one correspondence to the video rating folder corresponding to each of the rating data according to the rating data.

This application also provides a mobile terminal, including a processor and a memory,

The memory is configured to store a program for the device for pushing a video to execute any one of the methods for pushing a video;

The processor is configured to execute a program stored in the memory.

In this application, during the process of face recognition and descreening, the identified facial feature data is brought into a mood state analysis model to analyze and obtain the current user's mood state. When it is determined that the current mood used is unhappy state Time, then push the corresponding video to help users adjust their mood. This application also classifies the videos that are pushed in order to push videos that better meet user needs, to achieve the purpose of quickly and effectively adjusting the user's mood, and to make the way that mobile phones accompany users more intelligent.

[Brief Description of the Drawings]

1 is a schematic flowchart of a method for pushing a video according to an embodiment of the present application;

FIG. 2 is a schematic block diagram of a structure of a device for pushing video according to an embodiment of the present application; FIG.

FIG. 3 is a schematic block diagram of a mobile terminal according to an embodiment of the present application.

The realization of the purpose, functional characteristics and advantages of the present invention will be further explained with reference to the embodiments and the drawings.

【detailed description】

It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

Referring to FIG. 1, an embodiment of the present application provides a method for pushing a video, which is applied to a mobile terminal and includes steps:

S1: Obtain facial feature data when the screen of the mobile terminal is unlocked.

The mobile terminal in this embodiment includes, but is not limited to, a mobile phone. The facial feature data in this embodiment is facial feature data obtained when face unlocking is performed through face recognition. The same data serves two functions, namely, for unlocking and For mood recognition, convenient and quick.

S2: Analyze the current mood state of the user according to the facial feature data.

This embodiment obtains a user's current mood state through a mood recognition model based on face feature data. The mood recognition model of this embodiment is obtained by collecting mood facial expression data of a large number of people, and using the collected expression data as a training sample and inputting it into a training model such as CNN.

S3: Determine whether the mood state is a preset unhappy mood state.

The preset unhappy mood state in this embodiment is represented by a corresponding first vector output by a mood recognition model. After the user's current mood state passes the mood recognition model, a second vector is output, and the Euclidean distance calculation is performed between the second vector and the first vector. If the Euclidean distance is less than a preset value, indicating that the second vector is close to the first vector, the user is judged The current mood state is unhappy, otherwise it is happy.

S4: If yes, push the specified video to the user according to a preset rule to adjust the user's mood.

In this embodiment, after analyzing that the current mood state of the user is an unhappy state, a corresponding video may be pushed to the user to adjust the mood state of the user. The preset rules in this embodiment are a push method or a video selection method that can better adjust the user's mood, including pushing videos according to user preferences, or pushing high ratings based on a large number of user praise data in a large database, or according to Push preset videos at different mood status levels, or use them in combination with other push methods to push.

Further, step S2 in this embodiment includes:

S20: Send the facial feature data to a server.

The training process of the mood recognition model in this embodiment is completed on the server side. The training process of the mood recognition model requires a large amount of data and calculation processes, and is completed on the server side to reduce the operating load of the mobile phone. The mood recognition process of this embodiment is also completed on the server side to ensure the consistency of the mood recognition model after training. In this embodiment, the obtained facial feature data is sent to the server, and then input into the mood recognition model through the server. In order to complete the user's mood state recognition analysis.

S21: The mood analysis data obtained by the receiving server after inputting the facial feature data into a mood state recognition model, wherein the mood analysis data includes a mood state and a preset level corresponding to the mood state.

The data output by the mood recognition model in this embodiment carries a preset level corresponding to a mood state. For example, the unhappy mood state includes preset levels such as lost, relatively sad, very distressed, or distressed. In this embodiment, the unhappy mood state is refined to more accurately push videos suitable for the current mood state of the user. For example, when the unhappy mood state of this embodiment is a loss level, the facial expression of the face is expressed as melancholy, and the corners of the mouth are pulled down. After inputting the facial feature data with the representative characteristics of the loss level into the mood recognition model, the first The first classification vector in a vector; similarly sad face feature data is input to the mood recognition model, and the second classification vector in the first vector is output; very painful or distressed face feature data is input into the mood After identifying the model, the third classification vector in the first vector is output; the first vector corresponding to the preset unhappy mood state is subdivided into several small partitions in order to more accurately select the corresponding video push.

Further, step S4 in this embodiment includes:

S40: Acquire the level corresponding to the current unhappy mood state of the user.

In this embodiment, by inputting facial feature data corresponding to a user's current unhappy mood state into a mood recognition model, the first vector corresponding to a preset unhappy mood state is subdivided into several small Which one of the partitions is closer is to indicate which partition corresponds to the preset level.

S41: Select a video with a preset amusement level by the user according to the level corresponding to the unhappy mood state.

The preset amusement level video in this embodiment is related to the comedy index of the video, and includes a first level amusement video, a second level amusement video, and a third level amusement video, respectively corresponding to the first vector corresponding to the unhappy mood state. The first classification vector, the second classification vector, and the third classification vector. For example, the current facial expression is a tearful state with tears in the eyes, which is relatively sad. The second classification vector in the first vector is output. At this time, choosing to push the second-level amusement video can break the tears and laugh. When one is selected When level amusement video, it may not be able to adjust the mood, or the mood state cannot be adjusted quickly. However, when you choose to push a level three amusement video, it will be over-adjusted, which will make people feel frivolous. State adjustments are best for a peaceful mood.

Further, step S4 in this embodiment further includes:

S42: Collect real-time facial feature change data during the user watching the video and send it to the server.

In this embodiment, after the video is pushed, the user will collect facial feature change data in real time while watching the video. For example, by collecting facial feature data every fixed period of time, forming facial feature change data during the user watching the video. Then the facial feature change data is input into the mood recognition model in turn for analysis.

S43: Receive the analysis of the facial feature change data sent by the server in real time to obtain the mood state change data.

The mood state change data in this embodiment may be formed according to an output vector value corresponding to the facial feature change data. The value of the output vector value fluctuates, which constitutes the fluctuation of the mood state change data.

S44: Determine whether the pushed video is appropriate according to a change trend of the mood state change data.

In this embodiment, the change trend of the mood state change data is the best, and the mood state becomes better in the gentle change trend, and this is used to determine whether the pushed video is suitable. It is appropriate to meet the above mentioned gentle change trend. Otherwise it is inappropriate.

S45: If it is not suitable, re-screen the videos with higher ratings pushed by the server.

This embodiment is not suitable, which means that pushing the video does not have the effect of improving the mood state. Push higher rated videos. The videos with higher ratings in this embodiment include videos with higher ratings in user historical data, as well as videos with higher ratings in large databases.

Further, after step S4 in another embodiment of the present application, the method includes:

S5: Count the user's rating data for each recommended video.

The push video in this embodiment can be exited after the user gives a corresponding score after watching, in order to collect and count the user's rating data for each recommended video, so as to form the user's own database according to the above rating data, so as to push targeted video.

S6: Update each of the recommended videos to the video level folder corresponding to each of the rating data according to the rating data.

In this embodiment, each video is stored in a different folder correspondingly according to different ratings of the video by the user, so that the historical browsing video of the user is classified according to the folder during the storage process. For example, the total score is 10 points, a rating of 0 to 5 corresponds to a negative review video, a rating of 6 to 8 corresponds to a positive review video, and a rating of 9 to 10 corresponds to a highly rated video. In order to push the video to the user, it is preferable to select from the positive video and the highly rated video Priority push. Both the positive video and the particularly positive video in this embodiment include videos with different amusement levels.

The method for pushing video screens in the present application uses the identified facial feature data into a mood state analysis model in the process of face recognition and screen resolution, and analyzes to obtain the mood state of the current user. When the current mood is unhappy, the user can adjust the mood by pushing the corresponding video. This application also classifies the videos that are pushed in order to push videos that are more in line with user needs, to quickly and effectively adjust the user ’s mood, and to make the way that mobile phones accompany users more intelligent.

Referring to FIG. 2, an embodiment of the present application further provides a device for pushing video, which is integrated in a mobile terminal and includes:

The obtaining module 1 is configured to obtain facial feature data when the screen of the mobile terminal is unlocked.

The mobile terminal in this embodiment includes, but is not limited to, a mobile phone. The facial feature data in this embodiment is facial feature data obtained when face unlocking is performed through face recognition. The same data serves two functions, that is, for unlocking, and For mood recognition, convenient and quick.

The analysis module 2 is configured to analyze a current mood state of the user according to the facial feature data.

The determining module 3 is configured to determine whether the mood state is a preset unhappy mood state.

The pushing module 4 is configured to push a specified video to the user according to a preset rule to adjust the user's mood if it is a preset unhappy mood state.

Further, the analysis module 2 includes:

A sending unit, configured to send the facial feature data to a server.

The first receiving unit is configured to receive mood analysis data obtained by the server after inputting the facial feature data into a mood state recognition model, where the mood analysis data includes a mood state and a preset level corresponding to the mood state.

Further, the push module 4 includes:

The obtaining unit is configured to obtain a level corresponding to the current unhappy mood state of the user.

The preset amusement level video in this embodiment is related to the comedy index of the video, and includes a first level amusement video, a second level amusement video, and a third level amusement video, respectively corresponding to the first vector corresponding to the unhappy mood state. The first classification vector, the second classification vector, and the third classification vector. For example, the current facial expression is a tearful state with tears in the eyes, which is relatively sad. The second classification vector in the first vector is output. At this time, choosing to push the second-level amusement video can break the tears and laugh. When one is selected, When level amusement video, it may not be able to adjust the mood, or the mood state cannot be adjusted quickly. However, when you choose to push a level three amusement video, it will be over-adjusted, which will make people feel frivolous. In this embodiment, the unhappy mood State adjustments are best for a peaceful mood.

Further, the push module 4 further includes:

An acquisition unit is configured to collect real-time facial feature change data during a user watching a video and send the data to a server.

The second receiving unit is configured to receive, in real time, the mood state change data obtained by analyzing the facial feature change data sent by the server.

The judging unit is configured to judge whether the pushed video is appropriate according to a change trend of the mood state change data.

Further, the device for pushing video further includes:

The statistics module is used to collect statistics on user ratings of each recommended video.

The device for pushing a video screen of the present application brings the identified facial feature data into a mood state analysis model during the process of face recognition and screen resolution, and analyzes to obtain the current user's mood state. When the current mood is unhappy, the user can adjust the mood by pushing the corresponding video. This application also classifies the videos that are pushed in order to push videos that better meet user needs, to achieve the purpose of quickly and effectively adjusting the user's mood, and to make the way that mobile phones accompany users more intelligent.

Referring to FIG. 3, an embodiment of the present invention further provides a mobile terminal including a processor 1080 and a memory 1020, where the memory 1020 is configured to store a program for a device that pushes a video to execute the foregoing method for pushing a video; the processor 1080 is And configured to execute a program stored in the memory.

For ease of description, only the parts related to the embodiment of the present invention are shown, and specific technical details are not disclosed, please refer to the method part of the embodiment of the present invention. The mobile terminal may be any terminal device including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), and a vehicle-mounted computer. Taking the mobile terminal as a mobile phone as an example:

FIG. 3 is a block diagram showing a partial structure of a mobile phone related to a mobile terminal according to an embodiment of the present invention. Referring to FIG. 3, the mobile phone includes: a radio frequency (RF) circuit 1010, a memory 1020, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a wireless fidelity (WiFi) module 1070, and a processor 1080 , And power supply 1090 and other components. Those skilled in the art can understand that the structure of the mobile phone shown in FIG. 3 does not constitute a limitation on the mobile phone, and may include more or fewer parts than those shown in the figure, or combine certain parts, or arrange different parts.

The following describes each component of the mobile phone in detail with reference to FIG. 3:

The RF circuit 1010 can be used for receiving and transmitting signals during information transmission and reception or during a call. In particular, the downlink information of the base station is received and processed by the processor 1080; in addition, the uplink data of the design is transmitted to the base station. Generally, the RF circuit 1010 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, the RF circuit 1010 can also communicate with a network and other devices through wireless communication. The above wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division Multiple Access) Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), E-mail, Short Messaging Service (SMS), etc.

The memory 1020 may be used to store software programs and modules. The processor 1080 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 1020. The memory 1020 may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, at least one function required application program (such as a sound playback function, an image playback function, etc.), etc .; the storage data area may store data according to Data (such as audio data, phone book, etc.) created by the use of mobile phones. In addition, the memory 1020 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

The input unit 1030 can be used to receive inputted numeric or character information, and generate key signal inputs related to user settings and function control of the mobile phone. Specifically, the input unit 1030 may include a touch panel 1031 and other input devices 1032. Touch panel 1031, also known as touch screen, can collect user's touch operations on or near it (such as the user using a finger, stylus, etc. any suitable object or accessory on touch panel 1031 or near touch panel 1031 Operation), and drive the corresponding connection device according to a preset program. Optionally, the touch panel 1031 may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch position, and detects the signal caused by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into contact coordinates, and sends it To the processor 1080, and can receive the commands sent by the processor 1080 and execute them. In addition, various types such as resistive, capacitive, infrared, and surface acoustic wave can be used to implement the touch panel 1031. In addition to the touch panel 1031, the input unit 1030 may include other input devices 1032. Specifically, other input devices 1032 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, an operation lever, and the like.

The display unit 1040 may be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 1040 may include a display panel 1041, and optionally, the display panel 1041 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Further, the touch panel 1031 may cover the display panel 1041. When the touch panel 1031 detects a touch operation on or near the touch panel 1031, the touch panel 1031 transmits the touch operation to the processor 1080 to determine the type of the touch event. The type provides corresponding visual output on the display panel 1041. Although in FIG. 3, the touch panel 1031 and the display panel 1041 are implemented as two independent components to implement the input and input functions of the mobile phone, in some embodiments, the touch panel 1031 and the display panel 1041 can be integrated and Realize the input and output functions of the mobile phone.

The mobile phone may further include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor may adjust the brightness of the display panel 1041 according to the brightness of the ambient light. The proximity sensor may close the display panel 1041 and / Or backlight. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in various directions (usually three axes), and can detect the magnitude and direction of gravity when it is stationary. It can be used for applications that recognize the attitude of mobile phones (such as horizontal and vertical screen switching, related Games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tap), etc .; as for the mobile phone can also be equipped with gyroscope, barometer, hygrometer, thermometer, infrared sensor and other sensors, no longer here To repeat.

The audio circuit 1060, the speaker 1061, and the microphone 1062 can provide an audio interface between the user and the mobile phone. The audio circuit 1060 can transmit the received electrical data converted electrical signal to the speaker 1061, and the speaker 1061 converts the sound signal to an audio signal output. On the other hand, the microphone 1062 converts the collected sound signal into an electrical signal, and the audio circuit 1060 After receiving, it is converted into audio data, and then the audio data is output to the processor 1080 for processing, and then sent to, for example, another mobile phone via the RF circuit 1010, or the audio data is output to the memory 1020 for further processing.

WiFi is a short-range wireless transmission technology. The mobile phone can help users send and receive emails, browse web pages, and access streaming media through the WiFi module 1070. It provides users with wireless broadband Internet access. Although FIG. 3 shows the WiFi module 1070, it can be understood that it does not belong to the necessary configuration of the mobile phone, and can be omitted as needed without changing the essence of the invention.

The processor 1080 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. The processor 1080 runs or executes software programs and / or modules stored in the memory 1020, and calls data stored in the memory 1020 to execute. Various functions and processing data of the mobile phone, so as to monitor the mobile phone as a whole. Optionally, the processor 1080 may include one or more processing units; preferably, the processor 1080 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and an application program, etc. The modem processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 1080.

The mobile phone also includes a power supply 1090 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 1080 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system.

Although not shown, the mobile phone may further include a camera, a Bluetooth module, and the like, and details are not described herein again.

Referring to FIG. 3, in an embodiment of the present invention, the processor 1080 included in the mobile terminal also has the following functions:

Determining whether the mood state is a preset unhappy mood state;

Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and are not repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, which may be electrical, mechanical or other forms.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional unit.

A person of ordinary skill in the art may understand that all or part of the steps in the method of the foregoing embodiment may be implemented by a program instructing related hardware. The program may be stored in a computer-readable storage medium. The medium may be a read-only memory, a magnetic disk, or an optical disk.

The above is only a preferred embodiment of the present invention, and thus does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the description and drawings of the present invention, or directly or indirectly used in other related The technical field is included in the patent protection scope of the present invention.

Claims

A method for pushing video, which is applied to a mobile terminal and includes the steps:

Acquiring facial feature data when the screen of the mobile terminal is unlocked;

Analyze the current mood state of the user according to the facial feature data;

Determining whether the mood state is a preset unhappy mood state;

If so, the specified video is pushed to the user according to a preset rule to adjust the user's mood.
The method for pushing video according to claim 1, wherein the step of analyzing a user's current mood state based on the facial feature data comprises:

Sending the facial feature data to a server;

The receiving server inputs the facial feature data into a mood state recognition model, and obtains mood analysis data, where the mood analysis data includes a mood state and a preset level corresponding to the mood state.
The method for pushing video according to claim 2, wherein the mood state recognition model is obtained by inputting the collected expression data into a training model as a training sample.
The method for pushing video according to claim 2, wherein the step of determining whether the mood state is a preset unhappy mood state comprises:

Inputting the preset unhappy mood state into the mood recognition model to obtain a first vector;

Inputting the facial feature data into a mood state recognition model to obtain a second vector;

Performing Euclidean distance calculation on the second vector and the first vector;

If the Euclidean distance is less than a preset value, it is determined that the mood state is a preset unhappy mood state.
The method for pushing a video according to claim 2, wherein the step of pushing a specified video to a user according to a preset rule comprises:

Obtain the level corresponding to the current unhappy mood state of the user;

According to the level corresponding to the unhappy mood state, a video with a preset amusement level is selected by the user.
The method for pushing a video according to claim 5, wherein the preset amusement level is related to a comedy index of the video.
The method for pushing a video according to claim 5, wherein after the step of selecting a video corresponding to an amused level according to the level corresponding to the unhappy mood state, comprising:

Collect real-time facial feature change data during user watching video and send it to the server;

Receive in real time the analysis of the facial feature change data sent by the server to obtain the mood state change data;

Judging whether the pushed video is appropriate according to the change trend of the mood state change data;

If not, re-screen the higher-rated videos pushed by the server.
The method for pushing a video according to any one of claims 5-7, wherein after the step of pushing a specified video to a user according to a preset rule, comprises:

Count the user's rating data for each recommended video;

The one-to-one correspondence between each recommended video is updated to the video level folder corresponding to each of the rating data according to the rating data.
A device for pushing video, including:

An obtaining module, configured to obtain facial feature data when the screen of the mobile terminal is unlocked;

An analysis module, configured to analyze a user's current mood state according to the facial feature data;

A judging module, configured to judge whether the mood state is a preset unhappy mood state;

A push module is configured to push a specified video to a user according to a preset rule to adjust the user's mood if it is a preset unhappy mood state.
The device for pushing video according to claim 9, wherein the analysis module comprises:

A sending unit, configured to send the facial feature data to a server;

The first receiving unit is configured to receive mood analysis data obtained by the server after inputting the facial feature data into a mood state recognition model, where the mood analysis data includes a mood state and a preset level corresponding to the mood state.
The device for pushing video according to claim 10, wherein the mood state recognition model is obtained by inputting the collected expression data into a training model as a training sample.
The device for pushing video according to claim 10, wherein the first receiving unit is further configured to:

Receiving a first vector obtained by inputting the preset unhappy mood state into the mood recognition model;

Receiving a second vector obtained by inputting the facial feature data into a mood state recognition model;

The judgment module is further configured to:

Performing Euclidean distance calculation on the second vector and the first vector;

If the Euclidean distance is less than a preset value, it is determined that the mood state is a preset unhappy mood state.
The apparatus for pushing video according to claim 9, wherein the pushing module comprises:

An obtaining unit, configured to obtain a level corresponding to the current unhappy mood state of the user;

The selecting unit is configured to select a video with a preset amusement level by the user according to the level corresponding to the unhappy mood state.
The device for pushing video according to claim 13, wherein the preset amusement level is related to a comedy index of the video.
The device for pushing video according to claim 10, wherein the pushing module further comprises:

An acquisition unit, which is used to collect real-time facial feature change data during a user watching a video and send the data to a server;

A second receiving unit, configured to receive, in real time, the mood state change data obtained by analyzing the facial feature change data sent by the server;

A judging unit, configured to judge whether the pushed video is appropriate according to a change trend of the mood state change data;

The filtering unit is configured to re-screen videos with higher ratings pushed by the server if the videos pushed are not suitable.
The device for pushing video according to claim 10, wherein the device for pushing video further comprises:

A statistics module, which is used to collect statistics on user ratings of each recommended video;

An update module is configured to update each of the recommended videos in a one-to-one correspondence to the video rating folder corresponding to each of the rating data according to the rating data.
A mobile terminal including a processor and a memory,

The memory is configured to store a program for a device that pushes a video to execute the method for pushing a video according to any one of claims 1 to 8;

The processor is configured to execute a program stored in the memory.