Recording control method, device, display equipment and storage medium
By acquiring human body detection data from the playback device and combining it with user status and preset recording rules, recording control commands are generated, solving the problems of content omission and invalid recording in existing recording methods, and realizing automatic and accurate recording control.
Patent Information
- Application Number
- CN202611241531.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-14
- Publication Date
- 2026-11-17
AI Technical Summary
The recording methods of existing playback devices are prone to content omissions and invalid recordings due to manual operation or fixed time control, making it difficult to accurately control the recording of target content based on the user's actual viewing situation.
By acquiring human detection data within the target area, the user's status is determined, and combined with the user's historical behavior and preset recording rules, recording control instructions are generated to automatically control the recording and processing of the target content.
It enables automatic and accurate control of the recording of target content based on the user's actual viewing situation, reducing content omissions and invalid recordings.
Smart Images

Figure CN123123527A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of display device control technology, and in particular to a recording control method, apparatus, display device, and storage medium. Background Technology
[0002] With the increasing intelligence of playback devices such as smart TVs, set-top boxes, and conference tablets, users' demand for recording playback content is constantly growing. Existing playback devices are usually equipped with a Personal Video Recorder (PVR) function to store currently playing live programs or other audio and video content on local storage or external storage devices for easy viewing later.
[0003] Existing recording methods mainly include manual recording and scheduled recording. Manual recording requires the user to actively issue a record or stop command, which is prone to failure to start or stop recording in a timely manner due to user negligence or temporary absence. Scheduled recording usually starts or stops recording only according to a pre-set time, making it difficult to comprehensively judge the recording needs based on whether the user is actually watching the playback device, whether the current playback content matches the user's preferences, and whether the current time period matches the user's viewing habits. Therefore, it is possible that the content that needs to be recorded is not recorded, or that recording continues even when there is no actual recording need.
[0004] Therefore, the recording methods of existing display devices are prone to content omissions and invalid recordings due to manual operation or fixed time control. How to accurately control the recording of target content according to the user's actual viewing situation has become a technical problem that needs to be solved. Summary of the Invention
[0005] In view of this, in order to solve the above-mentioned technical problems or some of the technical problems, the present invention provides a recording control method, apparatus, display device and storage medium.
[0006] In a first aspect, embodiments of the present invention provide a recording control method, comprising: Based on human detection data obtained within the target area, the user status within the target area is determined, and the user status is used to characterize whether the user is viewing the target device; The target recording status is determined based on the user status, the target content currently being played on the target device, the current time period, and the preset recording rules. The target recording status indicates whether recording is being performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of the user status, the target content, and the current time period and the target recording status. Based on the current recording status of the target content and the target recording status, a recording control instruction is generated, and the target content is recorded according to the recording control instruction.
[0007] In one possible implementation, the human detection data includes image data, and determining the user status within the target area based on the human detection data acquired within the target area includes: Determine whether a user exists within the target area based on the image data; When there are one or more users in the target area, for each user, the user's position and line of sight are determined based on the continuously collected image data, and the duration of continuous eye closure is counted. When at least one of the users is located within a preset viewing area, the user's line of sight is pointing towards the display area of the target device, and the duration of continuous eye closure is less than or equal to a threshold for the duration of eye closure, the user state is determined to indicate that the user is viewing the target device. The user state is determined to indicate that the user is not watching the target device when at least one of the following conditions exists: there is no user in the preset viewing area, or the user's gaze direction in the preset viewing area is not pointing to the display area, or the continuous eye-closing duration of each user in the preset viewing area is greater than the eye-closing duration threshold.
[0008] In one possible implementation, the human body detection data further includes radar echo data acquired by millimeter-wave radar, and determining the user status within the target area includes: For each user, the location of the first user is determined based on the image data, and the location of the second user is determined based on the radar echo data; When the distance between the first user location and the second user location is less than the location association threshold, it is determined that the first user location and the second user location correspond to the same user; The reliability of the first user location and the second user location are determined based on the clarity of the image data and the signal quality of the radar echo data, respectively. The first user location and the second user location are weighted and fused according to the credibility to obtain the fused user location, and the user state is determined according to the fused user location, the user's gaze direction and the duration of continuous eye closure.
[0009] In one possible implementation, the method for determining the preset recording rules includes: Obtain at least one of the user's historical behavior and the user's preset plan, wherein the user's historical behavior includes at least one of historical viewing behavior and historical recording behavior; When the user's historical behavior is obtained, user preference information is determined based on the user's historical behavior. The user preference information includes at least one of preferred viewing time period, preferred channel, and preferred content type. When the user's preset plan is obtained, the planned recording content and planned recording time period are extracted from the user's preset plan; Based on at least one of the user preference information and the user preset plan, determine the recording content range and recording time range corresponding to different user states, and generate the preset recording rules based on the recording content range and the recording time range.
[0010] In one possible implementation, determining the target recording status based on the user status, the target content currently being played on the target device, the current time period, and preset recording rules includes: When the user status indicates that the user is watching the target device, the corresponding recording content range and recording time range are determined according to the preset recording rules; When the target content falls within the scope of the recording content and the current time period is within the scope of the recording time period, the target recording status is determined and recording is performed. When the user status indicates that the user is not viewing the target device, or the target content is not within the scope of the recording content, or the current time period is not within the scope of the recording time period, it is determined that the target recording status indicates that no recording will be performed.
[0011] In one possible implementation, the current recording state includes an unrecorded state, a recording in progress state, and a paused recording state. The step of generating recording control instructions based on the current recording state of the target content and the target recording state includes: When the target recording state indicates that recording is in progress, and the current recording state is the non-recording state, a start recording command is generated; When the target recording state indicates that recording is in progress, and the current recording state is the paused recording state, a resume recording command is generated; When the target recording state indicates that recording is not in progress, and the current recording state is the recording state, a pause recording command is generated; When the target recording state continuously indicates that no recording has been performed for a preset stop time, and the current recording state is the paused recording state, a stop recording command is generated.
[0012] In one possible implementation, before generating the recording control commands, the method further includes: When the target recording state determined this time is different from the target recording state determined in the previous time, the duration of the target recording state determined this time is counted, and the target content is stored cyclically to a temporary buffer. The temporary buffer is used to store the target content within a preset buffer duration. When the duration is less than the preset confirmation duration, the current recording state is maintained; When the duration reaches the preset confirmation duration, a recording control command corresponding to the target recording state determined this time is generated. When the recording control command is the start recording command or the resume recording command, the target content in the temporary buffer and the target content recorded after executing the recording control command are written into the same recording file.
[0013] In a second aspect, embodiments of the present invention provide a recording control device, comprising: The first determining module is used to determine the user status within the target area based on human body detection data obtained within the target area, wherein the user status is used to characterize whether the user is viewing the target device; The second determining module is used to determine the target recording status based on the user status, the target content currently being played on the target device, the current time period, and the preset recording rules. The target recording status indicates whether recording is being performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of the user status, the target content, and the current time period and the target recording status. The generation module is used to generate recording control instructions based on the current recording status of the target content and the target recording status, and to perform recording processing on the target content according to the recording control instructions.
[0014] Thirdly, embodiments of the present invention provide a display device, including: a processor and a memory, wherein the processor is configured to execute a recording control program stored in the memory to implement the recording control method described in any one of the first aspects above.
[0015] Fourthly, embodiments of the present invention provide a storage medium storing one or more programs, which can be executed by one or more processors to implement the recording control method described in any one of the first aspects.
[0016] The recording control scheme provided in this invention determines the user status within the target area based on human detection data acquired within that area. The user status indicates whether the user is currently viewing the target device. A target recording status is determined based on the user status, the target content currently playing on the target device, the current time period, and preset recording rules. The target recording status indicates whether recording is to be performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of user status, target content, and current time period and the target recording status. Recording control instructions are generated based on the current recording status of the target content and the target recording status, and the target content is recorded according to these instructions. Therefore, by combining user status, target content, and current time period to determine the target recording status and controlling the recording process accordingly, the recording of the target content can be automatically and accurately controlled based on the user's actual viewing situation, reducing content omissions and invalid recordings. Attached Figure Description
[0017] Figure 1 A flowchart illustrating a recording control method provided in this application embodiment; Figure 2 A flowchart illustrating another recording control method provided in this application embodiment; Figure 3 A flowchart illustrating another recording control method provided in this application embodiment; Figure 4 A structural diagram of a recording control device provided in an embodiment of this application; Figure 5 This is a structural diagram of a display device provided in an embodiment of this application. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0019] To facilitate understanding of the embodiments of the present invention, further explanations and descriptions will be provided below with reference to the accompanying drawings and specific embodiments. These embodiments do not constitute a limitation on the embodiments of the present invention.
[0020] Figure 1 This is a flowchart illustrating a recording control method provided in an embodiment of this application. Figure 1 As shown, the specific implementation steps of the recording control method are as follows: Step S101: Based on the human body detection data obtained in the target area, determine the user status in the target area. The user status is used to characterize whether the user is watching the target device.
[0021] This application embodiment identifies the viewing status of users within the target area through human body detection data, and combines the identified user status with the target content currently being played on the target device, the current time period, and preset recording rules to determine whether recording is required; after obtaining the target recording status, it generates corresponding recording control instructions based on the current recording status of the target content, thereby forming a closed-loop control process from human perception, recording decision to recording execution.
[0022] The target area can be a space where the target device is installed and users can view it, such as a family living room, bedroom, conference room, or exhibition area; the target device can be a display device such as a TV, set-top box, or conference tablet with content playback and recording capabilities; human body detection data can be data generated by a human body detection device continuously or periodically detecting the target area, representing human body position, line of sight, and whether the target device is being viewed; user status can be status information used to represent whether there is a user in the target area who is viewing the target device.
[0023] In this embodiment, the application is applied to scenarios such as watching live home programs and saving meeting content. The execution entity for each step can be a controller or a recording control module in the target device. The following description uses the recording control module in the target device as the execution entity. The recording control module can receive human detection data output by one or more human detection devices, such as cameras, millimeter-wave radar, and infrared sensors, within the target area. It performs format conversion, time synchronization, and abnormal data filtering on the human detection data, and determines whether there is a user watching the target device within the target area based on the processed human detection data, thus obtaining a user status indicating whether they are watching or not.
[0024] For example, the target device is a television set up in the living room, and the human body detection device continuously collects human body detection data in the living room. The recording control module can update the user status according to a preset detection cycle so as to trigger subsequent recording decisions in a timely manner when the user enters, leaves, or stops watching. It should be noted that this embodiment corresponding to the independent claim only provides a general description of the process of determining the user status; the specific data types of human body detection and the viewing status determination methods can be referred to in subsequent embodiments.
[0025] Step S102: Determine the target recording status based on the user status, the target content currently being played on the target device, the current time period, and the preset recording rules. The target recording status indicates whether recording is to be performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of the user status, the target content, and the current time period and the target recording status.
[0026] The target content can be a live broadcast, conference footage, or other continuous media content currently playing on the target device; the current time period can be determined by the current system time and the playback time of the target content; user history behavior can include the user's past viewing and recording behavior; the user's preset plan can be the content to be recorded and its recording time period set in advance by the user; the preset recording rules can be the recording decision rules that have been established and stored in advance; the target recording status can include the status indicating that recording is in progress and the status indicating that recording is not in progress.
[0027] In this embodiment, the recording control module can obtain at least one of the following content information from the target device: channel identifier, program name, content type, start time, and end time, and read the current system time to form the current time period. Subsequently, the user status, target content, and current time period are used as rule inputs and matched with the correspondence recorded in the preset recording rules. The matched status is then used as the target recording status.
[0028] For example, preset recording rules can be generated based on the news channels and corresponding viewing times that users frequently watch, or they can be generated based on the user's pre-set recording plan for a gala. When the user's status, the currently playing program, and the current time period match the correspondence in the preset recording rules, the target recording status can be determined and recording can begin; when they do not match, the target recording status can be determined and recording can be stopped.
[0029] Step S103: Generate recording control instructions based on the current recording status of the target content and the target recording status, and perform recording processing on the target content according to the recording control instructions.
[0030] The current recording state can be the current operating state of the recording module of the target device for the target content; the recording control command can be the control information used to control the recording module to change or maintain the current recording state; and the recording processing can be the process of acquiring, encoding, encapsulating and storing the data stream of the target content.
[0031] In this embodiment, the recording control module can read the current recording state corresponding to the target content, combine the current recording state with the target recording state to generate a recording control command corresponding to the state transition relationship between the two, and send the recording control command to the personal video recording module of the target device. After receiving the recording control command, the personal video recording module performs the corresponding processing of starting, maintaining, pausing, resuming or stopping recording of the target content, and stores the resulting recording file in the local storage space of the target device or the storage space communicatively connected to the target device.
[0032] For example, when the target content is not currently being recorded, but the target recording status indicates that recording is required, the recording control module can control the personal video recording module to start receiving the data stream of the target content and create a recording file; when the current recording status is consistent with the target recording status, the current recording process can be maintained, thereby avoiding the repeated sending of invalid control commands.
[0033] As can be seen from the above, this embodiment forms a closed-loop recording control through human body detection, rule decision-making, and recording execution. This allows the recording behavior to be automatically adjusted according to the user's actual viewing situation, playback content, and playback time, reducing manual operation by the user and improving the accuracy and timeliness of recording control.
[0034] In one embodiment, a specific implementation process for determining a user's state based on image data is described. The specific implementation steps are as follows: Step S201: Determine whether there is a user in the target area based on the image data.
[0035] The image data can be a sequence of image frames or video frames continuously captured by the camera for the target area; the user can be a detection object with human contours or key points in the image data.
[0036] In this embodiment, the image data can first undergo brightness adjustment, noise filtering, and size normalization, and then a human detection model can be used to identify human regions in the image data. When the recognition confidence of at least one human region reaches the human detection threshold, it is determined that one or more users exist within the target area; when no human region has a recognition confidence that reaches the human detection threshold, it is determined that no user exists within the target area. For continuous image data, human regions that are close in location and have similar human features in adjacent image frames can be associated with the same user to enable continuous detection of the same user.
[0037] Step S202: When there are one or more users in the target area, for each user, determine the user's position and line of sight based on the continuously collected image data, and count the duration of continuous eye closure.
[0038] The user's position can be the user's location in the target area coordinate system or the center of the user's body area in the image coordinate system; the user's gaze direction can be the gaze direction determined by the user's eye key points, head posture, or facial orientation; the continuous eye-closing duration can be the length of time that the same user's eyes remain in a closed state.
[0039] In this embodiment, for each detected user, the human body center point, facial key points, and eye key points can be extracted from consecutive image frames, and the human body center point can be converted into the user's position within the target area according to the camera calibration parameters. The user's gaze direction is determined based on the eye key points and head posture, and the continuous eye-closing time is accumulated based on the eye opening and closing results in consecutive image frames; when the user is detected to have reopened their eyes, the continuous eye-closing time for that user is reset to zero and the statistics are recalculated.
[0040] For example, a brief blink can yield a shorter duration of continuous eye closure; while sleep or prolonged eye closure can yield a duration of continuous eye closure that reaches or exceeds a threshold. Therefore, the presence of a human body, its location, whether it is facing the display area, and whether it is in a prolonged eye-closed state can be combined to determine whether the user is actually viewing the target device.
[0041] Step S203: When at least one user's position is within the preset viewing area, the user's line of sight is pointing towards the display area of the target device, and the duration of continuous eye closure is less than or equal to the eye closure duration threshold, the user's state is determined to indicate that the user is viewing the target device.
[0042] The preset viewing area can be a spatial area determined based on the target device's setting location, display direction, and preset viewing distance; the display area can be the screen area of the target device used to display the target content; and the eye-closing duration threshold can be a time threshold used to distinguish between brief blinks and continuous eye-closing.
[0043] In this embodiment, for each user, it is determined whether the user's position, the user's gaze direction, and the duration of continuous eye closure simultaneously meet the viewing conditions. When any user is located within a preset viewing area, and the angle between their gaze direction and the direction from their position to the target device's display area is less than a gaze angle threshold, and the duration of continuous eye closure is less than or equal to a duration of eye closure threshold, it can be determined that at least one user is viewing the target device, and the user state is set to indicate that the user is viewing the target device.
[0044] For example, if the target area is the living room, the space within a certain distance and angle range directly in front of the TV can be set as the preset viewing area. When the user is sitting on the sofa facing the TV, their position and line of sight meet the viewing conditions; when the user blinks normally, since the continuous duration of eye closure does not exceed the eye closure duration threshold, it is still determined that the user is watching the target device, avoiding frequent changes in the user's state due to brief blinks.
[0045] Step S204: When at least one of the following conditions exists, determine the user status indicating that the user is not watching the target device: there is no user in the preset viewing area, or the user's gaze direction in the preset viewing area is not pointing to the display area, or the continuous closed-eye duration of each user in the preset viewing area is greater than the closed-eye duration threshold.
[0046] In this context, "not watching" can mean that there is no user in the target area, or that although there are users, none of them simultaneously meet the three viewing conditions: user location, user gaze direction, and continuous eye-closing duration. In this embodiment, when there are no users in the preset viewing area, it is directly determined that the user is not watching the target device; when there are users in the preset viewing area, but none of them are facing the display area, it is determined that the user is not watching the target device; when the continuous eye-closing duration of each user is greater than a threshold, it is determined that each user is in a prolonged eye-closing state, and it is determined that the user is not watching the target device. For multi-user scenarios, as long as there is no user who simultaneously meets all viewing conditions, the user status can be determined as indicating that the user is not watching the target device.
[0047] For example, if there are two users in the preset viewing area, user A is facing the display area but has their eyes closed for a duration exceeding the eye-closed duration threshold, while user B has their eyes open but their gaze is not directed towards the display area. In this case, neither user meets all the viewing conditions at the same time, and it can be determined that the user is not viewing the target device.
[0048] As can be seen from the above, by simultaneously using the user's location, the user's gaze direction, and the duration of continuous eye closure to determine whether the user is watching, it is possible to rule out situations where the user is merely within the target area but not paying attention to the displayed content or is in a sleeping state, thereby improving the accuracy of user status judgment.
[0049] In one embodiment, a specific implementation process for determining user status by fusing image data and radar echo data is described. The specific implementation steps are as follows: Step S301: For each user, determine the location of the first user based on the image data, and determine the location of the second user based on the radar echo data.
[0050] The radar echo data can be data generated by a millimeter-wave radar emitting electromagnetic waves towards a target area and receiving the reflected echoes from the human body. The first user position can be a user position determined based on image data; the second user position can be a user position determined based on radar echo data. In this embodiment, the center position of the human body in the image data can be transformed to the target area coordinate system according to camera calibration parameters to obtain the first user position; simultaneously, the radar echo data is processed for range, azimuth, and target clustering to obtain one or more second user positions detected by the radar. The camera and millimeter-wave radar can be pre-calibrated together relative to a reference point in the target area, so that the first user position and the second user position are in the same target area coordinate system, thereby enabling position comparison and fusion.
[0051] Step S302: When the distance between the first user location and the second user location is less than the location association threshold, determine that the first user location and the second user location correspond to the same user.
[0052] The location association threshold can be the maximum allowable location difference used to determine whether an image-detected target and a radar-detected target belong to the same user.
[0053] In this embodiment, the spatial distance between each first user location and each second user location can be calculated, and first user locations and second user locations with a distance less than the location association threshold can be associated. When a first user location corresponds to multiple second user locations that meet the conditions, the second user location with the smallest spatial distance can be selected; when there are multiple users, they can be associated one-to-one in order of increasing spatial distance to avoid the same radar-detected target being repeatedly associated with multiple image detection targets.
[0054] Step S303: Determine the reliability of the first user location and the second user location based on the clarity of the image data and the signal quality of the radar echo data, respectively.
[0055] The image data clarity can be determined based on at least one of image brightness, blur level, human body occlusion ratio, and human body detection confidence; the radar echo data signal quality can be determined based on at least one of echo signal strength, signal-to-noise ratio, and target clustering stability; and the confidence level can be a normalized value used to characterize the reliability of the corresponding user location.
[0056] In this embodiment, the reliability of the first user location is obtained by normalizing and weighting the various indicators corresponding to image clarity; the reliability of the second user location is obtained by normalizing and weighting the various indicators corresponding to the signal quality of the radar echo data. The reliability of the first user location is increased when the image is clear and there are no obstructions from the human body; the reliability of the first user location is decreased when the ambient light is insufficient or the human body is obstructed. The reliability of the second user location is increased when the radar echo is stable and the signal-to-noise ratio is high.
[0057] Step S304: The first user's position and the second user's position are weighted and fused according to the credibility to obtain the fused user position, and the user's status is determined according to the fused user position, the user's gaze direction and the duration of continuous eye closure.
[0058] The merged user location can be a location obtained by weighting the first user location and the second user location according to their respective credibility.
[0059] In this embodiment, the product of the first user location and its credibility, and the product of the second user location and its credibility, can be added together and then divided by the sum of the two credibility values to obtain the fused user location. Subsequently, the fused user location replaces the user location determined solely based on image data, and the user's gaze direction and continuous eye-closing duration obtained from the image data are combined to determine the user state according to the viewing conditions described in steps S203 and S204.
[0060] For example, in a dimly lit living room, the image data has low clarity while the radar echo data has high signal quality. A larger fusion weight can be assigned to the second user's location to make the fused user's location closer to the second user's location. When the radar is interfered with by other moving objects but the image data is clear, the fusion weight of the first user's location can be increased.
[0061] As can be seen from the above, by associating image location and radar location and dynamically determining fusion weights according to data quality, the impact of low light, occlusion, or radar interference on user location judgment can be reduced, and the stability of user status detection can be improved.
[0062] In one embodiment, a specific implementation process for determining preset recording rules is described. The specific implementation steps are as follows: Step S401: Obtain at least one of user historical behavior and user preset plan, wherein user historical behavior includes at least one of historical viewing behavior and historical recording behavior.
[0063] Among them, historical viewing behavior can be behavioral data formed by the user watching target content in the past, recorded by the target device, including at least one of the following: viewing date, viewing time period, channel, content name, content type, and viewing duration; historical recording behavior can be behavioral data formed by the user starting recording, pausing recording, resuming recording, or stopping recording in the past; and user preset plan can be a recording arrangement preset by the user through the target device.
[0064] In this embodiment, the target device can read user historical behavior within a preset historical period from local behavior logs and read user preset plans that have not yet been executed or are currently being executed from the recording plan list. To protect user privacy, user historical behavior can be statistically analyzed locally on the target device, without having to upload original records containing user identity or viewed content.
[0065] Step S402: When obtaining user historical behavior, determine user preference information based on user historical behavior. User preference information includes at least one of preferred viewing time period, preferred channel, and preferred content type.
[0066] Among them, the preferred viewing time period can be the time range in which the user's viewing frequency or cumulative viewing time reaches the preferred time period threshold; the preferred channel can be the channel whose viewing frequency or cumulative viewing time reaches the preferred channel threshold; and the preferred content type can be the content category in which the user's historical viewing or recording times reach a preset threshold.
[0067] In this embodiment, user history behavior can be grouped and statistically analyzed according to viewing date, time period, channel and content type. The degree of preference is calculated based on the number of views, cumulative viewing time and recording time corresponding to each group. Time periods, channels or content types with the degree of preference reaching the preset preference threshold are written into user preference information.
[0068] For example, if a user consistently watches news channels during evening hours on multiple weekdays and has repeatedly recorded similar news programs, that evening hour can be identified as the preferred viewing time, the news channel as the preferred channel, and news content as the preferred content type.
[0069] Step S403: When the user's preset plan is obtained, extract the planned recording content and the planned recording time period from the user's preset plan.
[0070] The planned recording content can be represented by at least one of the following: program name, channel identifier, content type, or program unique identifier; the planned recording time period can include the planned start time and the planned end time.
[0071] In this embodiment, the user can select a program to be recorded or enter a recording time period on the target device's recording plan page, and the target device will generate a user-preset plan accordingly. The recording control module can parse the content and time fields in the user-preset plan to obtain the planned recording content and planned recording time period; when the user-preset plan only contains a program's unique identifier, the corresponding channel, start time, and end time of the program can be queried according to the Electronic Program Guide (EPG).
[0072] Step S404: Based on at least one of user preference information and user preset plans, determine the recording content range and recording time range corresponding to different user states, and generate preset recording rules based on the recording content range and recording time range.
[0073] The recording content range can be a set of channels, programs, or content types that are allowed to trigger recording; the recording time range can be one or more time intervals that are allowed to trigger recording; the recording content range and recording time range corresponding to different user states can be content and time constraints set separately for users who are watching and users who are not watching.
[0074] In this embodiment, when user preference information is obtained, the preferred channel and preferred content type can be added to the recording content range, and the preferred viewing time period can be added to the recording time period range. When the user's preset plan is obtained, the planned recording content can be added to the recording content range, and the planned recording time period can be added to the recording time period range. Subsequently, the user status, whether the target content belongs to the recording content range, whether the current time period is within the recording time period range, and the corresponding target recording status are associated and stored to form preset recording rules.
[0075] When both user preference information and user-preset plans exist, the user-preset plans can be set as the rule source above the user preference information, giving priority to user-defined plans. Alternatively, the two can be combined so that the target content and current time period satisfy the corresponding rule conditions when matched with either source. For example, if user preference information indicates that the user usually watches news channels in the evening, while the user-preset plans indicate that a specific evening event needs to be recorded on the weekend, then time period rules for news content and plan rules for the specific evening event can be formed separately.
[0076] As can be seen from the above, by forming personalized preferences based on users' historical behavior and generating preset recording rules in combination with the recording plans actively set by users, the recording decision can adapt to both users' long-term viewing habits and temporary recording needs.
[0077] In one embodiment, a specific implementation process for determining the target recording state according to preset recording rules is described. The specific implementation steps are as follows: Step S501: When the user status indicates that the user is watching the target device, determine the corresponding recording content range and recording time range according to the preset recording rules.
[0078] The corresponding recording content range and recording time range can be the set of content and time interval associated with the user's current viewing state in the preset recording rules.
[0079] In this embodiment, the recording control module can query preset recording rules based on the user's status to obtain one or more recording content ranges and recording time ranges corresponding to the user's current viewing state. When the preset recording rules include rules formed based on user preference information and rules formed based on the user's preset plan, the recording content range and recording time range corresponding to each rule can be read respectively.
[0080] Step S502: When the target content is within the recording content range and the current time period is within the recording time period range, determine the target recording status representation and start recording.
[0081] Among them, the target content falls within the scope of the recorded content, which can be the channel identifier, program identifier, or content type of the target content that matches the information recorded in the scope of the recorded content; the current time period is within the scope of the recorded time period, which can be the current system time being no earlier than the start time and no later than the end time of the recorded time period.
[0082] In this embodiment, the content information of the target content can be compared with the recording content range first, and then the current time period can be compared with the recording time period range; when the content comparison result and the time period comparison result are both matched, the target recording status representation is determined and recording is performed.
[0083] For example, the recording content range includes news channels, and the recording time range includes the user's preferred evening viewing times. When the target device is playing a news channel during that evening time and the user is watching on the target device, the target recording status can be determined and recording can be initiated.
[0084] Step S503: When the user status indicates that the user is not watching the target device, or the target content is not within the scope of the recording content, or the current time period is not within the recording time period, determine that the target recording status indicates that no recording will be performed.
[0085] Not recording can mean not starting a new recording process, or changing the ongoing recording process to a paused or stopped state.
[0086] In this embodiment, the recording control module can sequentially determine the user status, target content, and current time period. When the user is not viewing the target device, the target recording status can be directly determined so that recording will not be performed; when the user is viewing the target device, but either the target content or the current time period does not meet the preset recording rules, the target recording status can also be determined so that recording will not be performed.
[0087] As can be seen from the above, by simultaneously verifying the user status, target content, and current time period, the target recording status can be kept consistent with the actual viewing situation and the personalized recording range, thereby reducing recording content that does not conform to the rules.
[0088] In one embodiment, a specific implementation process for generating recording control instructions based on the current recording state and the target recording state is described. The specific implementation steps are as follows: Step S601: When the target recording status indicates that recording is in progress, and the current recording status is not recording, generate a start recording command.
[0089] The "not recording" state can be a state where the personal video recording module has not yet created a recording task and a recording file for the target content; the "start recording" command can be an instruction used to instruct the personal video recording module to create a recording task and start writing the target content.
[0090] In this embodiment, when the recording control module determines that recording is required but the target content is not currently being recorded, it can generate a start recording command containing at least one of the following: target content identifier, recording start time, and storage location. The personal video recording module then obtains the data stream of the target content based on the start recording command, creates a recording file, and begins writing.
[0091] Step S602: When the target recording status indicates that recording is in progress, and the current recording status is paused, a resume recording command is generated.
[0092] The pause recording state can temporarily stop writing target content to the current recording file, but retain the state of the recording task, the recording file, and the recording context; the resume recording command can be used to instruct the personal video recording module to continue executing the original recording task.
[0093] In this embodiment, the recording control module can locate the recording task that is in a paused recording state based on the target content identifier, and generate a resume recording instruction, so that the personal video recording module can continue to obtain data from the current data position of the target content and write the resumed content into the recording file corresponding to the one before the pause.
[0094] Step S603: When the target recording status indicates that recording is not in progress, and the current recording status is in progress, generate a pause recording command.
[0095] The "recording in progress" state can refer to the state in which the personal video recording module is continuously receiving and storing the target content; the "pause recording" command can be an instruction to temporarily stop the personal video recording module from writing but retain the conditions for recovery.
[0096] In this embodiment, when the recording control module determines that recording does not need to continue, it can generate a pause recording command. After receiving the pause recording command, the personal video recording module stops writing new target content to the recording file, and saves the current writing position, target content identifier, and recording time information so that recording can continue when a resume recording command is generated later.
[0097] Step S604: When the target recording state continuously indicates that no recording has been performed for a period of time that reaches the preset stop time, and the current recording state is paused recording, a stop recording command is generated.
[0098] The preset stop duration can be the longest time during which the recording task can remain in a paused state; the stop recording command can be an instruction used to instruct the personal video recording module to end the recording task and close the recording file.
[0099] In this embodiment, timing begins when the target recording state first changes to indicate that recording is not in progress. When this state continues for a preset stop duration and the recording task is still in a paused recording state, a stop recording command is generated. The personal video recording module closes the recording file according to the stop recording command, releases the cache and processing resources occupied by the recording task, and saves file information such as the name of the recording file, the recording period, and the content identifier.
[0100] As can be seen from the above, selecting the start, resume, pause, or stop recording command based on the current recording status and the target recording status can avoid repeatedly creating recording tasks, and by distinguishing between pause and stop, it can preserve the ability to recover from short-term status changes, while also preventing recording tasks from occupying system resources for a long time.
[0101] In one embodiment, a specific implementation process for performing status verification and content buffering before generating recording control commands is described. The specific implementation steps are as follows: Step S701: When the target recording state determined this time is different from the target recording state determined in the previous time, the duration of the target recording state determined this time is counted, and the target content is stored in a loop to a temporary buffer. The temporary buffer is used to store the target content within a preset buffer duration.
[0102] Among them, the previously determined target recording state can be the target recording state obtained and saved in the previous detection cycle; the duration can be the length of time that the target recording state remains unchanged in the continuous detection cycle; the temporary buffer can be the cache space in the target device memory used to cyclically store the target content in chronological order; the preset buffer duration can be the duration that the temporary buffer can retain the most recent segment of target content.
[0103] In this embodiment, the recording control module compares the current target recording status with the previous target recording status in each detection cycle. When they differ, the duration is set to zero and the timing restarts. Simultaneously, the target content is written to a temporary buffer according to its timestamp. When the temporary buffer reaches its capacity limit, the earliest recorded target content is overwritten, ensuring that the temporary buffer always stores target content within the most recent preset buffer duration.
[0104] Step S702: When the duration is less than the preset confirmation duration, maintain the current recording state.
[0105] The preset confirmation duration can be the shortest duration for confirming that the target recording status has stabilized; maintaining the current recording status can mean not sending a command to the personal video recording module to change the recording status before the target recording status has stabilized.
[0106] In this embodiment, when the duration is less than the preset confirmation duration, the recording control module continues to perform human detection and rule judgment, but maintains the current recording state of the personal video recording module. If the target recording state returns to the previous target recording state before the preset confirmation duration is reached, the current state change is canceled, the corresponding duration is reset to zero, and the judgment is restarted based on the subsequent target recording state.
[0107] Step S703: When the duration reaches the preset confirmation duration, generate a recording control command corresponding to the target recording state determined this time.
[0108] The recording control command corresponding to the target recording state can be determined according to the combination relationship between the current recording state and the target recording state as described in steps S601 to S604.
[0109] In this embodiment, if the target recording state remains continuously for the preset confirmation duration, it indicates that the state change was not caused by a brief blink, instantaneous head turn, or single-frame detection anomaly, and it can be confirmed that the target recording state has undergone a stable change. The recording control module reads the current recording state and generates a start recording command, resume recording command, pause recording command, or stop recording command according to the state transition relationship.
[0110] Step S704: When the recording control command is a start recording command or a resume recording command, write the target content in the temporary buffer and the target content recorded after executing the recording control command into the same recording file.
[0111] The same recording file can be a file created for the same target content and whose data is saved in chronological order according to the target content; the target content recorded after executing the recording control command can be the target content that the personal video recording module acquires in real time after starting or resuming recording.
[0112] In this embodiment, the personal video recording module can first read the target content in the temporary buffer that is located before the confirmation time, and then read the target content acquired in real time after the execution of the start recording command or resume recording command. It then sorts, deduplicates, and verifies the continuity of each part of the target content based on its timestamp, and subsequently writes it to the same recording file in chronological order. If the recording control command is a pause recording command or a stop recording command, the temporary buffer content that is no longer needed can be cleared after the state switch is completed.
[0113] For example, if a user's state changes briefly due to a turn of the head but recovers within a preset confirmation period, the current recording state is maintained without switching. When the user's state changes steadily and triggers the start of recording, the target content temporarily stored in the temporary buffer during the confirmation period is written to the recording file, thereby avoiding the loss of the starting content of the recording in order to suppress accidental switching.
[0114] As can be seen from the above, by setting a continuous confirmation process for the target recording status, state jitter caused by brief blinks, instantaneous head turns, and single detection anomalies can be filtered out; by cyclically buffering the target content during the confirmation period and rewriting it when starting or resuming recording, both recording control stability and content integrity can be taken into account.
[0115] In summary, the embodiments of this application can improve the automation level of recording control, detection stability, and the integrity of recorded content.
[0116] As an example Figure 2 A flowchart of another recording control method provided in the embodiments of this application is shown below. Figure 2As shown, for example, in a family living room scenario, the target device is a television. User A typically watches news channels from 7 PM to 9 PM daily. Based on User A's historical viewing behavior, the television determines news programs and the 7 PM to 9 PM timeframe as the recording content and time period, respectively, and generates preset recording rules accordingly. After the television is turned on, it uses multimodal sensors such as cameras and millimeter-wave radar to collect image data and radar echo data from the living room in real time. The edge computing module then fuses the collected data to determine User A's position, gaze direction, and duration of continuous eye closure. When User A is within the preset viewing area, their gaze is directed towards the television's display area, and the duration of continuous eye closure does not exceed a threshold, it is determined that User A is watching television. Figure 2 The user presence status shown in this scheme can be understood as the user viewing status determined after the above-mentioned human body detection.
[0117] When the television broadcasts a news program at 8 PM, the intelligent rule engine makes a decision based on user A's viewing status, the currently playing news program, the current time slot, and preset recording rules. Since the news program falls within the recording content scope, and 8 PM is within the recording time slot, the target recording state is determined to be recording. At this time, if the news program is not recording, a start recording command is generated; if the news program was previously paused, a resume recording command is generated. The television's Personal Video Recorder (PVR) module executes the start or resume recording command and writes the recorded news program data to memory.
[0118] During recording, if user A leaves the living room, or remains in the living room but their gaze is not directed at the TV display area, it is determined that user A is not watching TV, and the intelligent rule engine determines the target recording state as not recording. If a news program is currently being recorded, a pause recording command is generated; if user A's state of not watching TV continues for a preset stop time, such as 30 minutes, a stop recording command is generated through an exception handling process. If user A returns and resumes watching TV before the preset stop time is reached, a resume recording command is generated. To avoid frequent switching of recording states due to brief head turns by the user or momentary sensor fluctuations, a preset confirmation time can be allowed after a change in user state before executing the corresponding command, and a temporary buffer is used to save program data during the confirmation period.
[0119] Furthermore, if user A issues a recording request via a remote application while away from home, the exception handling process can generate a forced recording start command, allowing the personal video recording module to start recording regardless of the current user status. After recording is started, resumed, paused, or stopped, the television re-enters loop monitoring mode, continuing to collect human body detection data and update the user status.
[0120] Figure 3 A flowchart of another recording control method provided in the embodiments of this application is shown below. Figure 3 As shown, after the system is started, it uses multi-modal sensors such as cameras, millimeter-wave radar, and infrared sensors to collect human detection data in real time within the target area. Specifically, the cameras are used to identify the presence, number, and location of users within the target area; the millimeter-wave radar is used to detect subtle movements such as breathing and heartbeat, as well as user location; and the infrared sensors are used to make a preliminary judgment on the presence of users based on human thermal radiation information.
[0121] The edge computing unit fuses data collected by different sensors and outputs the user status within the target area, including information such as the presence of users, the number of users, user location, and user activity characteristics. In this solution, Figure 3 The phrase "user presence" is a simplified expression. It can be further determined whether the user is viewing the target device by combining the user's location, gaze direction, and duration of continuous eye closure.
[0122] The intelligent rules engine determines whether recording is necessary based on user status, a user habit database, and a time schedule database. The user habit database is built upon historical user behavior, including viewing times, channel preferences, and content type preferences. The time schedule database stores users' preset important programs and their corresponding recording times. Recording is determined to be necessary when the user is watching on the target device and the current content and time slot align with the user's habits or preset schedule; recording is not necessary when the user is not watching on the target device, or when the current content and time slot do not align with the user's habits or preset schedule.
[0123] When recording is determined to be necessary, the system generates recording control commands based on the current recording status: a start recording command is generated if the system is not currently recording; a resume recording command is generated if the system is currently paused. When recording is determined not to be necessary, a pause or stop recording command is generated if the system is currently recording; otherwise, the system remains in standby mode. Furthermore, when a user is detected to be absent for more than a preset time, such as more than 30 minutes, an exception handling branch generates a stop recording command; when a recording request is received from a user via a remote application, an exception handling branch generates a start recording command.
[0124] The TV or PVR module executes the corresponding recording control commands and stores the recorded content to a portable storage device or internal hard drive. After completing this recording control, the system enters a loop monitoring state, re-collecting human body detection data and updating the user status, thereby continuously adjusting the recording process.
[0125] Figure 4A structural diagram of a recording control device provided in an embodiment of this application is shown below. Figure 4 As shown, The first determining module 41 is used to determine the user status within the target area based on the human body detection data obtained within the target area, wherein the user status is used to characterize whether the user is viewing the target device; The second determining module 42 is used to determine the target recording status based on the user status, the target content currently being played on the target device, the current time period, and the preset recording rules. The target recording status indicates whether recording is being performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of the user status, the target content, and the current time period and the target recording status. The generation module 43 is used to generate recording control instructions based on the current recording status of the target content and the target recording status, and to perform recording processing on the target content according to the recording control instructions.
[0126] In one possible implementation, the first determining module is specifically used to determine whether a user exists in the target area based on the image data; When there are one or more users in the target area, for each user, the user's position and line of sight are determined based on the continuously collected image data, and the duration of continuous eye closure is counted. When at least one of the users is located within a preset viewing area, the user's line of sight is pointing towards the display area of the target device, and the duration of continuous eye closure is less than or equal to a threshold for the duration of eye closure, the user state is determined to indicate that the user is viewing the target device. The user state is determined to indicate that the user is not watching the target device when at least one of the following conditions exists: there is no user in the preset viewing area, or the user's gaze direction in the preset viewing area is not pointing to the display area, or the continuous eye-closing duration of each user in the preset viewing area is greater than the eye-closing duration threshold.
[0127] In one possible implementation, the first determining module is further configured to determine the location of a first user based on the image data and the location of a second user based on the radar echo data for each user. When the distance between the first user location and the second user location is less than the location association threshold, it is determined that the first user location and the second user location correspond to the same user; The reliability of the first user location and the second user location are determined based on the clarity of the image data and the signal quality of the radar echo data, respectively. The first user location and the second user location are weighted and fused according to the credibility to obtain the fused user location, and the user state is determined according to the fused user location, the user's gaze direction and the duration of continuous eye closure.
[0128] In one possible implementation, the second determining module is further configured to obtain at least one of the user's historical behavior and the user's preset plan, wherein the user's historical behavior includes at least one of historical viewing behavior and historical recording behavior; When the user's historical behavior is obtained, user preference information is determined based on the user's historical behavior. The user preference information includes at least one of preferred viewing time period, preferred channel, and preferred content type. When the user's preset plan is obtained, the planned recording content and planned recording time period are extracted from the user's preset plan; Based on at least one of the user preference information and the user preset plan, determine the recording content range and recording time range corresponding to different user states, and generate the preset recording rules based on the recording content range and the recording time range.
[0129] In one possible implementation, the second determining module is specifically used to determine the corresponding recording content range and recording time range according to the preset recording rules when the user status indicates that the user is watching the target device. When the target content falls within the scope of the recording content and the current time period is within the scope of the recording time period, the target recording status is determined and recording is performed. When the user status indicates that the user is not viewing the target device, or the target content is not within the scope of the recording content, or the current time period is not within the scope of the recording time period, it is determined that the target recording status indicates that no recording will be performed.
[0130] In one possible implementation, the generation module is specifically used to generate a start recording command when the target recording state characterizes recording and the current recording state is the non-recording state; When the target recording state indicates that recording is in progress, and the current recording state is the paused recording state, a resume recording command is generated; When the target recording state indicates that recording is not in progress, and the current recording state is the recording state, a pause recording command is generated; When the target recording state continuously indicates that no recording has been performed for a preset stop time, and the current recording state is the paused recording state, a stop recording command is generated.
[0131] In one possible implementation, the second determining module is further configured to, when the target recording state determined this time is different from the target recording state determined in the previous time, count the duration of the target recording state determined this time, and cyclically store the target content to a temporary buffer, wherein the temporary buffer is used to store the target content within a preset buffer duration. When the duration is less than the preset confirmation duration, the current recording state is maintained; When the duration reaches the preset confirmation duration, a recording control command corresponding to the target recording state determined this time is generated. When the recording control command is the start recording command or the resume recording command, the target content in the temporary buffer and the target content recorded after executing the recording control command are written into the same recording file.
[0132] The recording control device provided in this embodiment can be as follows: Figure 4 The apparatus shown can perform, for example Figure 1-3 All steps of the method, thus achieving Figure 1-3 For details on the technical effects of the method shown, please refer to [link / reference]. Figure 1-3 The relevant descriptions are presented concisely and will not be elaborated upon here.
[0133] Figure 5 This is a schematic diagram of the structure of a display device provided in an embodiment of the present invention. Figure 5 The illustrated display device 500 includes at least one processor 501, a memory 502, at least one network interface 504, and other user interfaces 503. The various components in the display device 500 are coupled together via a bus system 505. It is understood that the bus system 505 is used to implement communication between these components. In addition to a data bus, the bus system 505 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 5 The general designated all buses as Bus System 505.
[0134] The user interface 503 may include a display, keyboard, or clicking device (e.g., mouse, trackball, touchpad, or touchscreen).
[0135] It is understood that the memory 502 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 502 described herein is intended to include, but is not limited to, these and any other suitable types of memory.
[0136] In some implementations, memory 502 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 5021 and application program 5022.
[0137] The operating system 5021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 5022 includes various applications, such as a media player and a browser, used to implement various application functions. The program implementing the method of this embodiment can be included in the application program 5022.
[0138] In this embodiment of the invention, by calling the program or instructions stored in memory 502, specifically the program or instructions stored in application program 5022, processor 501 executes the method steps provided in each method embodiment, including, for example: Based on human detection data obtained within the target area, the user status within the target area is determined, and the user status is used to characterize whether the user is viewing the target device; The target recording status is determined based on the user status, the target content currently being played on the target device, the current time period, and the preset recording rules. The target recording status indicates whether recording is being performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of the user status, the target content, and the current time period and the target recording status. Based on the current recording status of the target content and the target recording status, a recording control instruction is generated, and the target content is recorded according to the recording control instruction.
[0139] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 501. Processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 501 or by instructions in the form of software. The processor 501 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 502. Processor 501 reads the information in memory 502 and, in conjunction with its hardware, completes the steps of the above method.
[0140] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.
[0141] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.
[0142] The display device provided in this embodiment can be as follows: Figure 5 The device shown can perform, for example Figure 1-3 All steps of the method, thus achieving Figure 1-3 For details on the technical effects of the method shown, please refer to [link / reference]. Figure 1-3 The relevant descriptions are presented concisely and will not be elaborated upon here.
[0143] This invention also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; it may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; and it may also include combinations of the above types of memory.
[0144] One or more programs in the storage medium can be executed by one or more processors to implement the recording control method described above that is executed on the device side.
[0145] The processor is used to execute a recording control program stored in the memory to implement the following steps of the recording control method executed on the device side: Based on human detection data obtained within the target area, the user status within the target area is determined, and the user status is used to characterize whether the user is viewing the target device; The target recording status is determined based on the user status, the target content currently being played on the target device, the current time period, and the preset recording rules. The target recording status indicates whether recording is being performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of the user status, the target content, and the current time period and the target recording status. Based on the current recording status of the target content and the target recording status, a recording control instruction is generated, and the target content is recorded according to the recording control instruction.
[0146] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0147] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
[0148] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A recording control method, characterized in that, include: Based on human detection data obtained within the target area, the user status within the target area is determined, and the user status is used to characterize whether the user is viewing the target device; The target recording status is determined based on the user status, the target content currently being played on the target device, the current time period, and the preset recording rules. The target recording status indicates whether recording is being performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of the user status, the target content, and the current time period and the target recording status. Based on the current recording status of the target content and the target recording status, a recording control instruction is generated, and the target content is recorded according to the recording control instruction.
2. The method according to claim 1, characterized in that, The human detection data includes image data. Determining the user status within the target area based on the human detection data acquired within the target area includes: Determine whether a user exists within the target area based on the image data; When there are one or more users in the target area, for each user, the user's position and line of sight are determined based on the continuously collected image data, and the duration of continuous eye closure is counted. When at least one of the users is located within a preset viewing area, the user's line of sight is pointing towards the display area of the target device, and the duration of continuous eye closure is less than or equal to a threshold for the duration of eye closure, the user state is determined to indicate that the user is viewing the target device. The user state is determined to indicate that the user is not watching the target device when at least one of the following conditions exists: there is no user in the preset viewing area, or the user's gaze direction in the preset viewing area is not pointing to the display area, or the continuous eye-closing duration of each user in the preset viewing area is greater than the eye-closing duration threshold.
3. The method according to claim 2, characterized in that, The human body detection data also includes radar echo data collected by millimeter-wave radar, and determining the user status within the target area includes: For each user, the location of the first user is determined based on the image data, and the location of the second user is determined based on the radar echo data; When the distance between the first user location and the second user location is less than the location association threshold, it is determined that the first user location and the second user location correspond to the same user; The reliability of the first user location and the second user location are determined based on the clarity of the image data and the signal quality of the radar echo data, respectively. The first user location and the second user location are weighted and fused according to the credibility to obtain the fused user location, and the user state is determined according to the fused user location, the user's gaze direction and the duration of continuous eye closure.
4. The method according to claim 1, characterized in that, The methods for determining the preset recording rules include: Obtain at least one of the user's historical behavior and the user's preset plan, wherein the user's historical behavior includes at least one of historical viewing behavior and historical recording behavior; When the user's historical behavior is obtained, user preference information is determined based on the user's historical behavior. The user preference information includes at least one of preferred viewing time period, preferred channel, and preferred content type. When the user's preset plan is obtained, the planned recording content and planned recording time period are extracted from the user's preset plan; Based on at least one of the user preference information and the user preset plan, determine the recording content range and recording time range corresponding to different user states, and generate the preset recording rules based on the recording content range and the recording time range.
5. The method according to claim 4, characterized in that, The step of determining the target recording status based on the user status, the target content currently being played on the target device, the current time period, and preset recording rules includes: When the user status indicates that the user is watching the target device, the corresponding recording content range and recording time range are determined according to the preset recording rules; When the target content falls within the scope of the recording content and the current time period is within the scope of the recording time period, the target recording status is determined and recording is performed. When the user status indicates that the user is not viewing the target device, or the target content is not within the scope of the recording content, or the current time period is not within the scope of the recording time period, it is determined that the target recording status indicates that no recording will be performed.
6. The method according to claim 5, characterized in that, The current recording state includes an unrecorded state, a recording in progress state, and a paused recording state. Generating recording control instructions based on the current recording state of the target content and the target recording state includes: When the target recording state indicates that recording is in progress, and the current recording state is the non-recording state, a start recording command is generated; When the target recording state indicates that recording is in progress, and the current recording state is the paused recording state, a resume recording command is generated; When the target recording state indicates that recording is not in progress, and the current recording state is the recording state, a pause recording command is generated; When the target recording state continuously indicates that no recording has been performed for a preset stop time, and the current recording state is the paused recording state, a stop recording command is generated.
7. The method according to claim 6, characterized in that, Before generating the recording control command, the method further includes: When the target recording state determined this time is different from the target recording state determined in the previous time, the duration of the target recording state determined this time is counted, and the target content is stored cyclically to a temporary buffer. The temporary buffer is used to store the target content within a preset buffer duration. When the duration is less than the preset confirmation duration, the current recording state is maintained; When the duration reaches the preset confirmation duration, a recording control command corresponding to the target recording state determined this time is generated. When the recording control command is the start recording command or the resume recording command, the target content in the temporary buffer and the target content recorded after executing the recording control command are written into the same recording file.
8. A recording control device, characterized in that, include: The first determining module is used to determine the user status within the target area based on human body detection data obtained within the target area, wherein the user status is used to characterize whether the user is viewing the target device; The second determining module is used to determine the target recording status based on the user status, the target content currently being played on the target device, the current time period, and the preset recording rules. The target recording status indicates whether recording is being performed. The preset recording rules are determined based on at least one of the user's historical behavior and the user's preset plan, and represent the correspondence between the combination of the user status, the target content, and the current time period and the target recording status. The generation module is used to generate recording control instructions based on the current recording status of the target content and the target recording status, and to perform recording processing on the target content according to the recording control instructions.
9. A display device, characterized in that, include: A processor and a memory, the processor being configured to execute a recording control program stored in the memory to implement the recording control method according to any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the recording control method according to any one of claims 1 to 7.
