WO2020192400A1

WO2020192400A1 - Playback terminal playback control method, apparatus, and device, and computer readable storage medium

Info

Publication number: WO2020192400A1
Application number: PCT/CN2020/078347
Authority: WO
Inventors: 宁秋梅
Original assignee: 深圳创维－Rgb电子有限公司
Priority date: 2019-03-27
Filing date: 2020-03-09
Publication date: 2020-10-01
Also published as: CN109889901A

Abstract

Disclosed are a playback terminal playback control method, apparatus, and device, and a computer readable storage medium. The method comprises: acquiring an image in a preset range in front of a playback terminal, implementing facial recognition on the basis of the image to acquire a facial recognition result and, in response to determining that the facial recognition result is the presence of a human face, acquiring facial features; on the basis of the facial features, determining a target viewing scene; determining a target viewing mode on the basis of the target viewing scene, and performing playback control on the basis of the target viewing mode.

Description

Play control method, device, equipment and computer readable storage medium of play terminal

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office with an application number of 201910236340.7 on March 27, 2019. The entire content of this application is incorporated into this application by reference.

Technical field

The present disclosure relates to image communication technology, for example, to a playback control method, device, device, and computer-readable storage medium of a playback terminal.

Background technique

With the development of technology, more and more users can play audio and video more conveniently through smart electronic devices such as smart TVs, smart phones and computers. However, users are more likely to be attracted by the output content and become immersed in it, leading to too long viewing time or too close viewing distance, resulting in visual impairment or mental fatigue of the user. In other words, when the smart electronic device in the related art plays audio and video or displays the operation interface of an application such as a game, there is a problem that the playback control is not smart enough.

Summary of the invention

Embodiments of the present invention provide a playback control method, device, device, and computer-readable storage medium of a playback terminal to realize intelligent playback control of different viewing scenes and improve the viewing scene discrimination and scene switching efficiency of the playback terminal device.

The embodiment of the present invention provides a playback control method of a playback terminal, including:

Acquire an image within a preset range in front of the playback terminal, perform face recognition based on the image to obtain a face recognition result, and obtain face features in response to determining that the face recognition result is a face;

Determining the target viewing scene according to the facial features;

A target viewing mode is determined according to the target viewing scene, and playback control is performed according to the target viewing mode.

The embodiment of the present invention also provides a playback control device of a playback terminal, which includes:

The facial feature acquisition module is configured to acquire an image within a preset range in front of the playback terminal, and perform face recognition according to the image to obtain a face recognition result, and in response to determining that the face recognition result is a face, obtain Facial features

The target viewing scene determination module is configured to determine the target viewing scene according to the facial features;

The target viewing mode determining module is configured to determine the target viewing mode according to the target viewing scene, and perform playback control according to the target viewing mode.

The embodiment of the present invention also provides a device, which includes:

One or more processors;

Storage device, set to store one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the playback control method of the playback terminal provided in any embodiment of the present application.

The embodiment of the present invention also provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, it implements the playback control method of the playback terminal provided in any embodiment of the present application.

Description of the drawings

Figure 1 is a schematic structural diagram of a playback terminal system in an embodiment of the present invention;

FIG. 2 is a flowchart of a playback control method of a playback terminal in Embodiment 1 of the present invention;

FIG. 3 is a flowchart of a playback control method of a playback terminal in Embodiment 2 of the present invention;

FIG. 4 is a flowchart of a playback control method of a playback terminal in Embodiment 3 of the present invention;

5 is a schematic structural diagram of a playback control device of a playback terminal in Embodiment 4 of the present invention;

Figure 6 is a schematic structural diagram of a device in Embodiment 5 of the present invention.

detailed description

The application will be further described in detail below with reference to the drawings and embodiments. It is understandable that the specific embodiments described here are only used to explain the application, but not to limit the application. In addition, it should be noted that, for ease of description, the drawings only show a part of the structure related to the present application instead of all of the structure.

The playback control method of the playback terminal provided by the embodiments of the present invention can be applied to smart devices (ie playback terminal devices) capable of processing audio and video signals and display output, such as smart set-top boxes, smart TVs, smart phones, handheld computers, and smart learning Computer, laptop or desktop computer, etc. Since the image in front of the playback terminal device needs to be used in the embodiment of the present invention, a camera needs to be set. The camera may be integrated in the playback terminal device, that is, a built-in camera of the playback terminal device, or an external camera that can be connected to the playback terminal device.

Referring to FIG. 1, the playback terminal system 100 formed by the external camera 110 and the smart TV 120 in the embodiment of the present invention will be described as an example. The external camera 110 includes an image sensor 111, a digital signal processing chip 112, and a main processing chip 113 connected in communication. The smart TV 120 includes a smart processing module 121 and a display module 122 that are communicatively connected. The external camera 110 and the smart TV 120 are respectively connected through a Universal Serial Bus (USB) interface provided thereon, and the connection may be the smart processing module 121 in the smart TV 120 and the main engine in the external camera 110. Processing chip 113. The image sensor 111 mainly projects an image in front of the smart TV 120 onto its surface through a lens, converts it into an electrical signal, and then converts it into a digital image signal through an analog-to-digital (A/D). After the digital signal processing chip 112 obtains the digital image signal, it processes it, and sends the processed digital image signal to the main processing chip 113. The main processing chip 113 performs processing again, and finally obtains the digital image in front of the smart TV 120 and sends it to the smart processing module 121 in the smart TV 120. The intelligent processing module 121 performs face recognition, scene judgment, and viewing mode selection on the received digital image. The display module 122 controls and displays the interface in the corresponding viewing mode according to the instructions of the intelligent processing module.

Example one

The playback control method of the playback terminal provided in this embodiment is applicable to the situation where the playback terminal device plays audio and video. The method can be executed by a playback control device of a playback terminal, which can be implemented by software and/or hardware. The device can be integrated in an audio and video playback terminal device, such as a user terminal device, such as a smart set-top box, Smart TV, smart phone, handheld computer, smart learning machine, laptop or desktop computer, etc. In the embodiment of the present invention, a smart TV is taken as an example for description. Referring to Fig. 2, the method of this embodiment specifically includes the following steps.

S110: Acquire an image within a preset range in front of the playback terminal, and perform face recognition according to the image to obtain a face recognition result, and in response to determining that the face recognition result is a face, obtain a face feature.

Watching scenes that are often encountered in the process of playing programs on smart TVs are: (1) When children watch TV, they will always feel that they have moved from a position farther from the TV screen to a position closer to the TV screen, although The parents will correct it, but the children still have the above situation repeatedly. (2) Once children start to watch TV programs, they will be immersed in it and hard to extricate themselves. No matter how parents persuade them to protect their eyesight, there will always be situations where children do not listen to discipline. (3) When the elderly watch TV, they always like to adjust the sound loudly and always feel that the TV picture is not clear. As the elderly grow older, multiple tissue structures and organ functions in the body of the elderly gradually decline, especially the gradual appearance of visual and hearing impairments, which affect the information reception of the surrounding environment. Therefore, when the elderly watch TV, the clarity of the images they see and the sound effects they hear will be greatly reduced. (4) In the process of watching TV, it often happens that you leave because of accidents or fall asleep because of fatigue. At this time, although no one is watching, TV programs are always playing. (5) During TV playback, users are often required to verify their identity. Traditional identity verification methods (for example, mobile phone number, QQ, or WeChat, etc.) require manual operations by users, which are not convenient enough.

If the smart TV is to make the playback control of the above multiple viewing scenes more intelligent and user-friendly, it is necessary to identify different types of viewers and different viewing states. With the development of Artificial Intelligence (AI) technology and face recognition technology, it is feasible to determine the target viewer type and viewing state through face recognition. For example, a large amount of face data can be used to train a face recognition model based on the IA algorithm to obtain a face recognition model that can accurately and quickly recognize faces from images and obtain facial features.

In one embodiment, an image in a certain range in front of the smart TV can be collected through a built-in camera or an external camera of the smart TV. Then input the image into a face recognition model to obtain facial features. The facial features may include age, gender, race, facial expressions, and so on. Age can be used to determine the target viewer type, and facial expressions can be used to determine whether the viewer is asleep.

S120: Determine a target viewing scene according to the facial features.

The target viewing scene refers to a viewing scene adapted to the current viewer. In order to increase the speed of determining the target viewing scene, multiple viewing scenes (ie, preset viewing scenes) can be preset, such as children viewing scenes, elderly viewing scenes, sleeping viewing scenes, and unattended viewing scenes. In addition, the judgment conditions corresponding to each preset viewing scene can be set. For example, age can be used as the judgment condition for children viewing scenes and elderly viewing scenes, facial expressions can be used as judgment conditions for sleep viewing scenes, and whether there are people in unattended scenes. Face features are used as judgment conditions and so on.

In an embodiment, the facial features obtained above can be compared with the judgment conditions corresponding to each preset viewing scene to determine the target viewing scene.

S130: Determine a target viewing mode according to the target viewing scene, and perform playback control according to the target viewing mode.

The target viewing mode refers to the viewing mode corresponding to the target viewing scene. In order to be able to respond quickly, as with viewing scenes, the embodiment of the present invention also sets a corresponding preset viewing mode for each preset viewing scene, for example, children viewing scenes correspond to children mode, elderly viewing scenes correspond to elderly mode, and sleep viewing scenes Corresponding to the sleep mode, the unattended scene corresponds to the unattended mode, etc. This correspondence relationship can be called the mapping relationship between scenes and modes. In addition, it is also necessary to define the output mode and output content of each preset viewing mode.

In an embodiment, the target viewing mode is determined according to the determined target viewing scene and the mapping relationship between the scene and the mode. After that, the screen is displayed according to the output mode and output content of the target viewing mode.

It should be noted that both viewing scenes and viewing modes can be customized according to actual application scenarios, and the foregoing multiple preset viewing scenes and preset viewing modes are all examples of embodiments of the present invention.

The technical solution of this embodiment obtains a face recognition result by acquiring an image within a preset range in front of the playback terminal and performing face recognition based on the image, and in response to determining that the face recognition result is a human face, the face is obtained Features: Determine the target viewing scene according to the facial features; determine the target viewing mode according to the target viewing scene, and perform playback control according to the target viewing mode. It realizes the automatic determination of the target viewing mode suitable for the viewer according to the facial features of the viewer, makes the playback control of different viewing scenes more intelligent and humanized, and improves the viewing scene discrimination and scene switching efficiency of the playback terminal device.

On the basis of the above technical solution, S120 includes: judging whether the viewer is in a sleep state according to facial expressions in facial features; if the viewer is in a sleep state, determining that the target viewing scene is a sleep viewing scene; accordingly, S130 includes : Monitor the sleep duration of the viewer in the sleep state; if the sleep duration is greater than the second duration threshold, determine that the target viewing mode is the sleep mode.

In one embodiment, it can be judged whether the viewer is awake or asleep according to the facial expression in the facial features. If it is awake, then no processing is performed. If it is asleep, it is determined that the viewer is in a sleep state, and the target viewing scene is determined to be a sleep viewing scene. Afterwards, considering that there may be situations in which the viewer closes his eyes for a short time to rest, takes a nap, or the face recognition result is wrong, this embodiment does not immediately switch the target viewing mode to the sleep mode when it is determined to be a sleep viewing scene, but It will continuously monitor whether the user is in a sleep state, and record the time the user is in the sleep state to obtain the sleep duration. If it is determined that the sleep duration is greater than the preset duration (ie, the second duration threshold), the target viewing mode is switched to the sleep mode. The second duration threshold here may be the default duration, or may be preset by the viewer. The output mode and output content of the sleep mode can also be set by the viewer. In this embodiment, the sleep mode is set to standby. The advantage of this setting is to reduce system power consumption and save power.

On the basis of the above technical solution, after performing face recognition based on the image, it may also include: if the result of face recognition is that there is no face, then determining when the playback duration of no one is greater than or equal to the third duration threshold The target viewing mode is the unattended mode.

If there is no person in the image obtained in S110, the face recognition model cannot obtain the face features. Therefore, it can be judged whether there is a face currently by whether the face recognition model outputs facial features. If there is no human face, it means that there is no viewer at present, and the same is true for the sleep mode switch. At this time, continue to monitor whether there are viewers and record the duration of unattended playback. If it is determined that the playback duration is greater than or equal to the preset duration (that is, the third duration threshold), the target viewing mode is switched to the unattended mode. The third duration threshold and the unattended mode can also be set by the viewer. In this embodiment, the unattended mode is set to standby. The advantage of this setting is to reduce system power consumption and save power.

On the basis of the above technical solution, after S110, it may further include: performing viewer identity verification according to the facial features. For current user identity verification scenarios in scenarios such as login or permission acquisition appearing in the playback terminal device, although the user can manually input verification information to achieve user identity verification, it is more convenient and safer to implement identity verification through face recognition. Therefore, in this embodiment, the acquired facial features of the viewer can be matched with the facial feature information of the user stored in the device, or the facial feature information of the current device stored in the cloud, so as to achieve viewer identity verification.

Example two

In this embodiment, on the basis of the first embodiment above, "determine the target viewing scene according to the facial features" is described. On this basis, "determine the target viewing mode according to the target viewing scene" can also be described. The explanation of the terms that are the same as or corresponding to the above-mentioned embodiment will not be repeated here. Referring to FIG. 3, the playback control method of the playback terminal provided in this embodiment includes the following steps.

S201. Acquire an image within a preset range in front of the playback terminal, and perform face recognition according to the image to obtain a face recognition result, and in response to determining that the face recognition result is a face, obtain a face feature.

S202: Determine the target viewer type according to the age information in the facial features and the preset age segment information.

The preset age group information refers to information about multiple preset age groups (ie, preset age groups) and corresponding viewer types. For example, setting 0-14 years old as the first age group corresponds to children; setting 15-60 years old as the second age group corresponds to adults; setting 60 years old and above as the third age group corresponds to the elderly.

In an embodiment, age information can be extracted from the facial features, and the age information can be matched with a plurality of preset age segments in the preset age segment information. If the age information falls within a certain preset age range (referred to as a target preset age range), it can be determined that the target viewer type is the viewer type corresponding to the target preset age range. For example, if the age information is 10 years old, then it falls into the first age group, and the target viewer type is determined to be children.

It should be noted that the number of currently existing viewers can be identified from the facial features. If the number is multiple, the target viewer type corresponding to each viewer can be determined in this operation. For example, if there are currently 3 viewers, then 3 target viewer types can be determined.

S203: If the target viewer type includes children, it is determined that the target viewing scene is a child viewing scene.

If it is determined in S202 that the number of viewers is one and the target viewer type is a child, then the target viewing scene can be directly determined as a child viewing scene.

If it is determined in S202 that there are multiple viewers, as long as the multiple target viewer types include children, the target viewing scene is set as a child viewing scene.

Then execute S205 and/or S207, that is to say, in the children's viewing scene, only the viewing distance can be obtained and judged, or only the viewing time can be obtained and judged, and the viewing distance can be obtained and judged as well as watching Time acquisition and judgment.

S204: If the target viewer type includes the elderly and does not include children, it is determined that the target viewing scene is the elderly viewing scene.

If it is determined in S202 that the number of viewers is one, and the target viewer type is an elderly person, then the target viewing scene can be directly determined as the elderly viewing scene.

If it is determined in S202 that the number of viewers is multiple, when the multiple target viewer types do not include children and include the elderly, that is, all the multiple target viewer types are elderly, or the multiple target viewer types are elderly And adults, set the target viewing scene as the elderly viewing scene. S209 is then executed.

S205. Obtain the viewing distance.

The distance between the smart TV and the child viewer is obtained through the distance detection device in the smart TV.

S206: If the viewing distance is less than or equal to the preset distance threshold, it is determined that the target viewing mode is the first child mode.

The preset distance threshold is a pre-set minimum allowable distance value between the TV and the viewer. The preset distance threshold can be set by parents according to the actual situation in their own home, or the TV default setting value, such as 1.8 meters, can be used. The first child mode is a viewing mode set for the viewing distance, which can set the output mode and output content when the distance is too close to remind the child to increase the distance between it and the TV. Exemplarily, the first child mode is set to pause the current playing screen, and pop up a prompt audio and video interface and reduce the current screen brightness. That is, set the output mode of the first child mode to pause the current playback screen, and pop up a new preset playback screen, while appropriately reducing the playback brightness; and the output content is set to prompt audio and video, for example, the little fox voice animation prompts "Children, Don’t be too close to the TV, you can protect your eyes if you stay away.” etc.

If it is determined that the obtained viewing distance is less than or equal to the preset distance threshold, it means that the child is too close to the TV at this time, and the target viewing mode is switched to the first child mode. Then S210 is executed.

If after the execution of the first child mode, it is detected that the viewing distance is greater than the preset distance threshold, the first child mode is switched to the original viewing mode, that is, the current playback picture that was paused before continues to be played. Of course, it is also possible to encourage children to stay away from the TV through audio and video methods before playing the currently playing screen, increase children's favorability, and help children establish good viewing habits.

It should be noted that, considering that some parents do not customize the preset distance threshold, and the actual distance for watching TV in the family is less than the default preset distance threshold, the distance detection and processing method is set in the embodiment of the present invention It is to remind 3 times within half an hour. If the number of reminders reaches 3, then the reminder will be reminded 3 hours apart, or you can set whether to continue to pop up the setting method of distance detection reminder, so that parents can turn off this function, which can avoid watching The viewer’s viewing troubles. The above half hour, 3 times and 3 hours are examples and can be modified to other values.

S207. Obtain the viewing time.

When it is determined that the viewer type is a child, the system time is recorded, and the viewing time is compared with the first time threshold according to the set frequency. Here, the first time threshold is a preset maximum allowable viewing time. The first time threshold can be set by the parents themselves, or a default value can be set.

S208: If the viewing duration is greater than or equal to the first duration threshold, determine that the target viewing mode is the second child mode.

The second child mode refers to a viewing mode set for the viewing time, and the second child mode can set the output mode and output content when the viewing time is too long, so as to encourage children to rest. Exemplarily, the second child mode is set to pause the current playing screen and pop up the unlock interface. That is, the output mode of the second child mode is set to pause the current playing screen and a new alternative screen pops up; and the output content, that is, the alternative screen is set as an unlock screen, such as a login interface or an answer interface that requires parental intervention.

If it is determined that the obtained viewing time length is greater than or equal to the first time length threshold, it means that the child watches TV for a long time at this time and needs to prompt him to rest. At this time, the target viewing mode is set to the second child mode. Then S210 is executed.

S209. Determine that the target viewing mode is the elderly mode.

Exemplarily, the elderly mode is set to increase the image clarity and amplify the gain of the high frequency part of the sound. If subtitles or other displayed text can be controlled separately, the elderly mode can also include increasing font size. After that, S210 is executed.

S210: Play according to the target viewing mode.

In the technical solution of this embodiment, the target viewer type is determined based on the age information in the facial features and the preset age segment information; if the target viewer type includes children, the target viewing scene is determined to be the children viewing scene; The viewer type includes the elderly and does not include children, and the target viewing scene is determined to be the viewing scene of the elderly. It realizes the more accurate determination of the target viewing scene, and improves the intelligence of different scene playback control. If the target viewing scene is a child viewing scene, by detecting the viewing distance and/or viewing time, the current imitation mode is intelligently switched to the first child mode and/or the second child mode, making the viewing mode of the playback terminal more suitable for children Watching saves parents' worry and effort and improves user experience.

Example three

On the basis of the first and second embodiments above, this embodiment combines multiple target viewing scene judgments and target viewing mode determination processes, and provides a complete process example of a playback control method of a playback terminal. Explanations of terms that are the same as or corresponding to those in the above multiple embodiments will not be repeated here. Referring to FIG. 4, the playback control method of the playback terminal provided in this embodiment includes the following steps.

S301: Acquire an image within a preset range in front of the playback terminal, and perform face recognition according to the image to obtain a face recognition result.

S302: If the face recognition result is that there is no face, when the unattended playback duration is greater than or equal to the third duration threshold, it is determined that the target viewing mode is the unattended mode. Then S318 is executed.

S303: If the face recognition result is that there is a face, obtain the face feature. Then S304 is executed.

S304: Determine whether the viewer is in a sleep state according to facial expressions in the facial features. If the viewer is in the sleep state, S305 is executed; if the viewer is not in the sleep state, S308 is executed.

S305. Determine that the target viewing scene is a sleep viewing scene. Then S306 is executed.

S306. Monitor the sleep duration of the viewer in a sleep state.

S307: If the sleep duration is greater than the second duration threshold, determine that the target viewing mode is the sleep mode. Then S318 is executed.

S308: Determine the target viewer type according to the age information in the facial features and the preset age segment information.

S309: If the target viewer type includes children, it is determined that the target viewing scene is a child viewing scene. Then execute S313.

S310: If the target viewer type includes the elderly and does not include children, it is determined that the target viewing scene is an elderly viewing scene. S317 is then executed.

S311: If the target viewer type is an adult, it is determined that the target viewing scene is an adult viewing scene.

If all target viewer types are adults, the target viewing scene is determined to be an adult viewing scene. Since there is no special restriction on the adult viewing scene, there is no need to perform any processing on the current viewing mode, that is, perform S312.

S312: Use the current viewing mode as the target viewing mode. Then S318 is executed.

S313. Obtain the viewing distance, and determine whether the viewing distance is greater than a preset distance threshold. If the viewing distance is greater than the preset distance threshold, S312 is executed; if the viewing distance is less than or equal to the preset distance threshold, S314 is executed.

S314. Determine that the target viewing mode is the first child mode. Then S318 is executed.

S315. Obtain the viewing duration, and determine whether the viewing duration is less than a first duration threshold. If yes, execute S312; if not, execute S316.

S316. Determine that the target viewing mode is the second child mode. Then S318 is executed.

S317. Determine that the target viewing mode is the elderly mode. Then S318 is executed.

S318: Perform playback control according to the target viewing mode.

The technical solution of this embodiment first determines whether someone is watching, and when no one is watching, it directly switches to the unmanned mode; when someone is watching, it determines whether the viewer is in a sleep state, and if so, switches to the sleep mode; Whether the viewer type is children, adults or the elderly, and switching the corresponding target viewing mode for each viewer type can improve the playback process, improve playback intelligence and playback efficiency, and save system power consumption to a certain extent.

The following is an embodiment of a playback control device for a playback terminal provided by an embodiment of the present invention. This device belongs to the same inventive concept as the playback control methods of a playback terminal in the foregoing multiple embodiments. In the embodiment of the playback control device for a playback terminal For details that are not described in detail, please refer to the foregoing embodiment of the playback control method of the playback terminal.

Example four

This embodiment provides a playback control device for a playback terminal. Referring to FIG. 5, the device includes a facial feature acquisition module 510, a target viewing scene determination module 520, and a target viewing mode determination module 530.

The facial feature acquisition module 510 is configured to acquire an image within a preset range in front of the playback terminal, and perform face recognition according to the image to obtain a face recognition result, and in response to determining that the face recognition result is a human face, obtain a human face Face features.

The target viewing scene determination module 520 is configured to determine the target viewing scene according to the facial features.

The target viewing mode determining module 530 is configured to determine the target viewing mode according to the target viewing scene, and perform playback control according to the target viewing mode.

In an embodiment, the target viewing scene determination module 520 is set to:

Determine the target viewer type based on the age information in the facial features and the preset age segment information;

If the target viewer type includes children, it is determined that the target viewing scene is a child viewing scene;

If the target viewer type includes the elderly and does not include children, the target viewing scene is determined to be the elderly viewing scene.

In an embodiment, the target viewing mode determination module 530 is set to:

If the target viewing scene is a child viewing scene, the viewing distance is obtained;

If the viewing distance is less than or equal to the preset distance threshold, it is determined that the target viewing mode is the first child mode.

In an embodiment, the target viewing mode determination module 530 is set to:

If the target viewing scene is a child viewing scene, the viewing time is obtained;

If the viewing duration is greater than or equal to the first duration threshold, it is determined that the target viewing mode is the second child mode.

In an embodiment, the target viewing mode determination module 530 is set to:

If the target viewing scene is an elderly viewing scene, it is determined that the target viewing mode is an elderly mode.

In an embodiment, the target viewing scene determination module 520 is set to:

According to facial expressions in facial features, judge whether the viewer is asleep;

If the viewer is in a sleep state, it is determined that the target viewing scene is a sleep viewing scene;

Correspondingly, the target viewing mode determination module 530 is set to:

Monitor the length of sleep when the viewer is asleep;

If the sleep duration is greater than the second duration threshold, it is determined that the target viewing mode is the sleep mode.

In an embodiment, based on the above device, the device may further include an unattended mode determination module. The unattended viewing mode determination module is set to: after performing face recognition based on the image, if the face recognition result is that there is no face, the target viewing mode is determined when the unattended playback time is greater than or equal to the third duration threshold It is unmanned mode.

Through a playback control device of a playback terminal according to the fourth embodiment of the present invention, it is realized that the target viewing mode suitable for the viewer is automatically determined according to the facial features of the viewer, making the playback control of different viewing scenes more intelligent and humane , Improve the viewing scene discrimination and scene switching efficiency of the playback terminal device.

The play control device of the play terminal provided in the embodiment of the present invention can execute the play control method of the play terminal provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

It is worth noting that in the above embodiment of the playback control device of the playback terminal, the multiple units and modules included are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized. ; In addition, the specific names of multiple functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of this application.

Example five

Referring to FIG. 6, this embodiment provides a device 600, including: one or more processors 620; a storage device 610, configured to store one or more programs, when one or more programs are used by one or more processors 620 is executed so that one or more processors 620 implement the playback control method of the playback terminal provided in the embodiment of the present invention, and the method includes the following steps.

Acquire an image within a preset range in front of the playback terminal, and perform face recognition according to the image to obtain a face recognition result, and in response to determining that the face recognition result is a human face, a face feature is obtained.

Determine the target viewing scene based on the facial features.

The target viewing mode is determined according to the target viewing scene, and the playback control is performed according to the target viewing mode.

Of course, those skilled in the art can understand that the processor 620 may also implement the technical solution of the playback control method of the playback terminal provided in any embodiment of the present application.

The device 600 shown in FIG. 6 is only an example, and should not bring any limitation to the function and application scope of the embodiment of the present invention. It should be noted that the device provided in this embodiment may also include a camera for collecting images.

As shown in FIG. 6, the device 600 includes a processor 620, a storage device 610, an input device 630, and an output device 640; the number of processors 620 in the device can be one or more. In FIG. 6, one processor 620 is taken as an example. The processor 620, the storage device 610, the input device 630, and the output device 640 in the device may be connected by a bus or other means. In FIG. 6, the connection by the bus 650 is taken as an example.

The storage device 610, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the playback control method of the playback terminal in the embodiment of the present invention (for example, the playback terminal The facial feature acquisition module 510, the target viewing scene determination module 520, and the target viewing mode determination module 530 in the playback control device).

The storage device 610 may mainly include a storage program area and a storage data area. The storage program area may store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the terminal, etc. In addition, the storage device 610 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 non-volatile solid-state storage devices. In some examples, the storage device 610 may further include a memory remotely provided with respect to the processor 620, and these remote memories may be connected to the device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 630 may be used to receive input digital, image, or character information, and generate key signal input related to user settings and function control of the device. The output device 640 may include a display device such as a display screen.

Through a device of the fifth embodiment of the present invention, it is realized that the target viewing mode suitable for the viewer is automatically determined according to the facial features of the viewer, which makes the playback control of different viewing scenes more intelligent and user-friendly, and improves the playback terminal The device's viewing scene discrimination and scene switching efficiency.

Example Six

This embodiment provides a storage medium containing computer-executable instructions. The computer-executable instructions are used to execute a playback control method of a playback terminal when executed by a computer processor. The method includes the following steps.

Determine the target viewing scene based on the facial features.

Of course, a storage medium containing computer-executable instructions provided by an embodiment of the present invention is not limited to the above method operations, and can also execute the playback control method of a playback terminal provided in any embodiment of the present application. Related operations in.

Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be realized by software and necessary general-purpose hardware, of course, it can also be realized by hardware, but in many cases the former is the preferred embodiment. . Based on this understanding, the technical solution of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk. , Read-Only Memory (ROM), Random Access Memory (RAM), Flash memory (FLASH), hard disk or optical disk, etc., including several instructions to make a device (such as smart set-top box, smart A television, a smart phone, a palmtop computer, an intelligent learning machine, a notebook computer or a desktop computer, etc.) execute the playback control method of the playback terminal provided by the various embodiments of the present invention.

Claims

A playback control method of a playback terminal includes:

Acquire an image within a preset range in front of the playback terminal, perform face recognition based on the image to obtain a face recognition result, and obtain face features in response to determining that the face recognition result is a face;

Determining the target viewing scene according to the facial features;

A target viewing mode is determined according to the target viewing scene, and playback control is performed according to the target viewing mode.
The method according to claim 1, wherein the determining the target viewing scene according to the facial features comprises:

Determine the target viewer type according to the age information in the facial features and the preset age segment information;

In response to determining that the target viewer type includes children, determining that the target viewing scene is a child viewing scene;

In response to determining that the target viewer type includes the elderly and does not include children, it is determined that the target viewing scene is an elderly viewing scene.
The method according to claim 2, wherein the determining a target viewing mode according to the target viewing scene comprises:

In response to determining that the target viewing scene is the child viewing scene, acquiring a viewing distance;

In response to determining that the viewing distance is less than or equal to a preset distance threshold, it is determined that the target viewing mode is the first child mode.
The method according to claim 2, wherein the determining a target viewing mode according to the target viewing scene comprises:

In response to determining that the target viewing scene is the child viewing scene, acquiring the viewing time;

In response to determining that the viewing duration is greater than or equal to a first duration threshold, determining that the target viewing mode is a second child mode.
The method according to claim 2, wherein the determining the target viewing mode according to the target viewing scene, the formula comprises:

In response to determining that the target viewing scene is the elderly viewing scene, it is determined that the target viewing mode is the elderly mode.
The method according to claim 1, wherein the determining the target viewing scene according to the facial features comprises:

Judging whether the viewer is in a sleep state according to the facial expressions in the facial features;

In response to determining that the viewer is in the sleep state, determining that the target viewing scene is a sleep viewing scene;

The determining the target viewing mode according to the target viewing scene includes:

Monitoring the sleep duration of the viewer in the sleep state;

In response to determining that the sleep duration is greater than a second duration threshold, determining that the target viewing mode is a sleep mode.
The method according to claim 1, wherein after said performing face recognition according to said image, further comprising:

In response to determining that the human face recognition result is that there is no human face, in a case where the unattended playback duration is greater than or equal to a third duration threshold, it is determined that the target viewing mode is an unattended mode.
The method according to claim 3, wherein the first child mode is set to pause the current playing screen, pop up a prompt audio and video interface and reduce the current screen brightness.
The method according to claim 4, wherein the second child mode is set to pause the current playing screen and pop up an unlock interface.
The method according to claim 5, wherein the elderly mode is set to increase the image definition and amplify the gain of the high frequency part of the sound.
A playback control device of a playback terminal includes:

The facial feature acquisition module is configured to acquire an image within a preset range in front of the playback terminal, and perform face recognition according to the image to obtain a face recognition result, and in response to determining that the face recognition result is a face, obtain Facial features

The target viewing scene determination module is configured to determine the target viewing scene according to the facial features;

The target viewing mode determination module is configured to determine the target viewing mode according to the target viewing scene, and perform playback control according to the target viewing mode.
The apparatus according to claim 11, wherein the target viewing scene determination module is configured to:

Determine the target viewer type according to the age information in the facial features and the preset age segment information;

In response to determining that the target viewer type includes children, determining that the target viewing scene is a child viewing scene;

In response to determining that the target viewer type includes the elderly and does not include children, it is determined that the target viewing scene is an elderly viewing scene.
The apparatus according to claim 11, wherein the target viewing mode determining module is set to:

In response to determining that the target viewing scene is the child viewing scene, acquiring a viewing distance;

In response to determining that the viewing distance is less than or equal to a preset distance threshold, it is determined that the target viewing mode is the first child mode.
A device that includes:

One or more processors;

Storage device, set to store one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors implement the playback control method of the playback terminal according to any one of claims 1-10.
A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the playback control method of a playback terminal according to any one of claims 1-10.