Method, device and equipment for adaptively regulating and controlling film watching environment and storage medium
By obtaining user physiological indicators and behaviors, combining film and television content, and using deep learning models to generate environmental regulation solutions, the problem that the existing technology cannot adjust the viewing environment in real time is solved, and the immersive viewing experience is improved.
Patent Information
- Application Number
- CN202411116143.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-26
AI Technical Summary
The existing home theater's viewing environment control methods lack understanding of users' emotional status and behavioral patterns, and cannot adjust the environment in real time, resulting in an inability to provide an immersive viewing experience, affecting the user's experience.
By obtaining the physiological indicators, user behavior and viewing environment parameters of the movie viewing user, combining the current film and television content, using preset deep learning models to generate the best adaptation solution to the current environment, and controlling the linkage operation of environmental regulation equipment to create immersion A movie viewing environment.
It realizes real-time understanding of the user's emotional status and behavioral patterns, dynamically adjusts the viewing environment, and improves the user's immersive viewing experience and viewing experience.
Smart Images

Figure CN119024909A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of smart cinema technology, and in particular to a method, device, equipment and storage medium for adaptively controlling a viewing environment. Background Art
[0003] Currently, most home theaters basically rely on the user's manual control and simple mode selection to change the viewing environment. They cannot adjust the environment in real time according to the user's viewing emotions and behavior patterns. This method lacks understanding of the user's emotional state and behavior patterns, resulting in a failure to provide users with an immersive viewing environment and a low user experience.
[0004] Therefore, there is an urgent need for a method that can adaptively control the viewing environment so that users can have an immersive viewing experience and improve the viewing experience. Summary of the invention
[0005] Based on this, it is necessary to provide a method, device, equipment and storage medium that can adaptively control the viewing environment in response to the above-mentioned technical problems, aiming to solve the problem that the existing methods of controlling the viewing environment lack understanding of the user's emotional state and behavior patterns, and cannot automatically control an immersive viewing environment for the user, thus affecting the viewing experience.
[0006] A method for adaptively controlling a viewing environment, the method comprising:
[0007] Obtain the physiological indicators, user behaviors and viewing environment parameters of the viewing users;
[0008] According to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, the best adaptation solution adapted to the current viewing environment is generated through a preset deep learning model;
[0009] The optimal adaptation scheme is used to control the coordinated operation of environmental control equipment to create an immersive viewing environment.
[0010] In one embodiment, obtaining the physiological indicators, user behavior and viewing environment parameters of the viewing user specifically includes:
[0011] Collecting physiological indicators of the user when watching a movie through a wearable device and / or a first sensor device, wherein the physiological indicators include any one or any combination of heart rate, pressure, respiratory rate, blood oxygen saturation, body temperature and sound;
[0012] Acquire user behavior through a camera, wherein the user behavior includes any one or any combination of facial expressions, body postures, and sitting postures;
[0013] The viewing environment parameters are acquired through the second sensing device, and the viewing environment parameters include any one or any combination of temperature, humidity and brightness.
[0014] In one embodiment, the environment control device includes any one or any combination of a heater, a fan, an air conditioner, a humidifier, a light, an audio system, and a flavor generator, and the controlling the environment control devices to operate in conjunction with each other using the optimal adaptation scheme to create an immersive viewing environment includes:
[0015] Generate a real-time environment control plan according to the best adaptation plan, wherein the environment control plan includes any one or any combination of environment parameter values, the environment control equipment to be called, control speed and control mode;
[0016] Generate a predicted environment control plan in advance according to the environment control plan, combined with the power of the environment control equipment, the size of the viewing venue and the content of the film and television;
[0017] The environment control devices are dynamically controlled to operate in conjunction with each other in real time using a real-time environment control scheme and / or a predicted environment control scheme to create an immersive viewing environment.
[0018] In one embodiment, after controlling the environment control devices to operate in conjunction with each other using the optimal adaptation scheme to create an immersive viewing environment, the method further includes:
[0019] The control performance of the viewing environment is monitored in real time, and the control performance includes control speed, stability and accuracy. If problems are found in the control performance or users feedback that the current control effect is not good, the environment control equipment is controlled to operate in conjunction according to the predetermined best adaptation plan.
[0020] In one embodiment, the method further comprises:
[0021] Training the preset deep learning model, wherein the training the preset deep learning model comprises:
[0022] Collect historical viewing environment data, historical user behavior, and historical physiological data;
[0023] The collected historical viewing environment data, historical user behavior, and historical physiological data are preliminarily screened through preprocessing algorithms to remove outliers and duplicate values, and missing values are inferred through probability calculations;
[0024] Normalizing the pre-processed historical movie-watching environment data, historical user behavior, and historical physiological data;
[0025] According to the purpose of achieving the best viewing environment effect, features with a high correlation with the target variable are selected from the normalized historical viewing environment data, historical user behavior, and historical physiological data for reinforcement learning, wherein the target variable includes any one or any combination of ambient light intensity, viewing distance, and viewing emotion fluctuations;
[0026] Classify and encode the features and convert the features into numerical features, wherein the features include set user preferences;
[0027] Transforming the features to improve the distribution of the features and the performance of the model, wherein the transformation includes one or any combination of logarithmic transformation and square root transformation;
[0028] Performing feature dimensionality reduction on the historical viewing environment data, historical user behavior, and historical physiological data by using dimensionality reduction technology to reduce the number of features, wherein the dimensionality reduction technology includes principal component analysis (PCA) and latent Dirichlet allocation (LDA);
[0029] The preset deep learning model is generated by training the preset regression model through the historical viewing environment data, historical user behavior, and historical physiological data after dimensionality reduction.
[0030] In one embodiment, the training of the preset deep learning model further includes:
[0031] Evaluate the preset deep learning model using a test data set, wherein the evaluation indicators include mean square error (MSE), root mean square error (RMSE), R square, or any combination thereof;
[0032] The preset deep learning model is optimized and iterated according to the evaluation results, and the optimization includes model parameter optimization and model structure optimization.
[0033] In one embodiment, the method further comprises:
[0034] Collect actual feedback from users, optimize and iterate the preset deep learning model. A device for adaptively controlling a viewing environment, comprising:
[0035] A parameter acquisition module is used to obtain physiological indicators, user behaviors and viewing environment parameters of the viewing user;
[0036] A control generation module is used to generate the best adaptation scheme adapted to the current viewing environment through a preset deep learning model according to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content;
[0037] The control execution module is used to control the coordinated operation of the environmental control equipment according to the optimal adaptation solution to create an immersive viewing environment.
[0038] A control device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0039] Obtain the physiological indicators, user behaviors and viewing environment parameters of the viewing users;
[0040] According to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, the best adaptation solution adapted to the current viewing environment is generated through a preset deep learning model;
[0041] The optimal adaptation scheme is used to control the coordinated operation of environmental control equipment to create an immersive viewing environment.
[0042] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:
[0043] Obtain the physiological indicators, user behaviors and viewing environment parameters of the viewing users;
[0044] According to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, the best adaptation solution adapted to the current viewing environment is generated through a preset deep learning model;
[0045] The optimal adaptation scheme is used to control the coordinated operation of environmental control equipment to create an immersive viewing environment.
[0046] The above-mentioned method, device, equipment and storage medium for adaptively controlling the viewing environment obtain the physiological indicators, user behavior and viewing environment parameters of the viewing user; based on the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, generate the best adaptation plan that adapts to the current viewing environment through a preset deep learning model; use the best adaptation plan to control the linkage operation of the environmental control equipment to create an immersive viewing environment, combine the user behavior, viewing environment and film and television content, judge the user's emotional state and behavior pattern, realize adaptive control of the viewing environment, so that users have an immersive viewing experience and improve the viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 A schematic diagram of a flow chart of a method for adaptively controlling a movie viewing environment in one embodiment;
[0048] Figure 2 is a structural block diagram of a device for adaptively controlling a movie viewing environment in one embodiment;
[0049] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0051] In one embodiment, Figure 1 As shown, a method for adaptively controlling a viewing environment is provided. The method is described by taking an intelligent control terminal for household use as an example. The intelligent control terminal is wirelessly or wiredly connected to a wearable device, a camera, and a sensor, and includes the following steps:
[0052] Step S101, obtaining the physiological indicators, user behavior and viewing environment parameters of the viewing user.
[0053] Specifically, the physiological indicators of the user when watching a movie are collected through a wearable device and / or a first sensor device, and the physiological indicators include any one or any combination of heart rate, pressure, breathing rate, blood oxygen saturation, body temperature and sound; the user behavior is obtained through a camera, and the user behavior includes any one or any combination of facial expressions, body shape and sitting posture; the viewing environment parameters are obtained through a second sensor device, and the viewing environment parameters include any one or any combination of temperature, humidity and brightness. Among them, the wearable device is used to collect the user's physiological parameters, and the wearable device includes any one or any combination of smart bracelets, smart watches, and VR glasses. The intelligent control terminal obtains the physiological indicators, user behavior and viewing environment parameters of the viewing user in real time. The first sensor device and the second sensor device are used to obtain multi-dimensional perception information, such as sound, temperature, humidity and brightness. The camera is used to obtain real-time user behavior and film and television content.
[0054] Step S102, based on the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, generate the best adaptation plan that adapts to the current viewing environment through a preset deep learning model.
[0055] In this embodiment, the best adaptation scheme is the best adaptation scheme obtained by the preset deep learning model according to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content. Compare and correct according to the characteristics of the environmental control equipment with the current physiological indicators, user behavior and viewing environment parameters, and generate the corresponding environmental adaptation scheme in time according to the viewing venue to replicate the scenes of the film and television content and help the audience integrate into the work faster. The intelligent control terminal generates the best adaptation scheme that adapts to the current viewing environment through the preset deep learning model based on the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content.
[0056] Step S103, controlling the environment control equipment to operate in conjunction with each other using the optimal adaptation solution to create an immersive viewing environment.
[0057] In this embodiment, the environment control equipment includes any one or any combination of a heater, a fan, an air conditioner, a humidifier, a light, an audio system, and a flavor generator. Controlling the environment control equipment to operate in conjunction with each other to create an immersive viewing environment using the optimal adaptation scheme includes:
[0058] Generate a real-time environment control plan according to the best adaptation plan, wherein the environment control plan includes any one or any combination of environment parameter values, the environment control equipment to be called, control speed and control mode;
[0059] Generate a predicted environment control plan in advance according to the environment control plan, combined with the power of the environment control equipment, the size of the viewing venue and the content of the film and television;
[0060] The environment control devices are controlled to operate in a coordinated manner in real time and dynamically using a real-time environment control scheme and / or a predicted environment control scheme to create an immersive viewing environment.
[0061] Among them, the real-time environment control scheme is an environment control scheme adapted to the current film and television content, and the predicted environment control scheme is an environment control scheme generated in advance according to the film and television content. Since the environmental parameters are affected by the power of the environmental control equipment and the size of the viewing venue, the environmental parameters change with the curve, so the predicted environment control scheme is more adapted to the film and television content. If the current film and television content is a very warm scene, then in the best adaptation scheme, the lighting of the viewing environment is adjusted to dark warm yellow, and the temperature and humidity are adjusted to a comfortable level, that is, 18°C to 25°C, and the relative humidity is between 40% and 70%. This scheme will make the human body feel most comfortable. Within this temperature range, the physiological and psychological state of the human body is relatively stable.
[0062] Preferably, after step S103, the method further includes:
[0063] The control performance of the viewing environment is monitored in real time, and the control performance includes control speed, stability and accuracy. If problems are found in the control performance or the user feedback shows that the current control effect is not good, the environment control equipment is controlled to operate in conjunction according to a predetermined optimal adaptation scheme, wherein the stability is judged by the detection result of the third sensor device, and the accuracy is judged by the physiological characteristic data obtained by the user's wearable device.
[0064] Preferably, after step S103, the method further includes:
[0065] Collect actual feedback from users and optimize and iterate the preset deep learning model.
[0066] In this embodiment, the actual feedback is obtained through the user interaction module to obtain the user's feedback on the actual viewing experience. The user interaction module displays the current environmental parameter settings and other information to the user, and the actual viewing experience can also be evaluated and fed back. In order to simplify the user's feedback path, a variety of data collection methods are provided, such as asking whether the current system is accurate, so that users can quickly and accurately feedback their actual feelings and their own needs. According to the actual feedback results of the user, the preset deep learning model and the generated best adaptation plan are optimized in real time to improve the generated best adaptation plan to better meet the actual needs of customers. Because of individual differences, fine-tuning can be performed according to the actual feelings of the user. At this time, the system will collect the audience's physiological indicators and compare them with the current picture content to determine whether the audience has reached a relaxed state. If the user's emotions are still relatively tense, the next best adaptation plan will focus more on the time it takes for the user to reach the expected emotions as the main parameter.
[0067] In the above-mentioned method for adaptively controlling the viewing environment, the physiological indicators, user behavior and viewing environment parameters of the viewing user are obtained; based on the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, the best adaptation plan that adapts to the current viewing environment is generated through a preset deep learning model; the environmental control equipment is controlled to operate in conjunction with the best adaptation plan to create an immersive viewing environment, and the user's emotional state and behavior pattern are judged in combination with the user behavior, viewing environment and film and television content, thereby realizing adaptive control of the viewing environment, allowing users to have an immersive viewing experience and improving the viewing experience.
[0068] In another embodiment, a method for adaptively controlling a viewing environment is provided, wherein the method further comprises:
[0069] The preset deep learning model is trained, wherein the preset deep learning model is a convolutional neural network.
[0070] Specifically, the training preset deep learning model includes:
[0071] Collect historical viewing environment data, historical user behavior, and historical physiological data; the historical viewing environment data, historical user behavior, and historical physiological data are all viewing environment data, user behavior, and physiological data of previous users of the viewing venue.
[0072] The collected historical viewing environment data, historical user behavior, and historical physiological data are preliminarily screened to remove outliers and duplicate values, and missing values are inferred through probability calculation.
[0073] The preprocessed historical movie-watching environment data, historical user behavior, and historical physiological data are normalized so that each feature has a similar scale, which is also a necessary operation for convolutional neural network training.
[0074] According to the purpose of achieving the best viewing environment effect, features with a high correlation with the target variable are selected from the normalized historical viewing environment data, historical user behavior, and historical physiological data for reinforcement learning, wherein the target variable includes any one or any combination of ambient light intensity, viewing distance, and viewing emotion fluctuations;
[0075] Classify and encode the features and convert the features into numerical features, wherein the features include set user preferences;
[0076] Transforming the features to improve the distribution of the features and the performance of the model, wherein the transformation includes one or any combination of logarithmic transformation and square root transformation;
[0077] Performing feature dimensionality reduction on the historical viewing environment data, historical user behavior, and historical physiological data through dimensionality reduction technology to reduce the number of features, reduce model complexity, and thus speed up the model's operation speed and resource usage. The dimensionality reduction technology includes principal components analysis (PCA) and latent Dirichlet Allocation (LDA);
[0078] The preset deep learning model is generated by training the preset regression model with the historical viewing environment data, historical user behavior, and historical physiological data after dimensionality reduction. The model is trained using the historical viewing environment data, historical user behavior, and historical physiological data that have been manually labeled, with the aim of training a model of standard data, which will be continuously iterated based on the model in the future. During the training process, the performance of the model is evaluated periodically through cross-validation, and appropriate model parameters are selected. At the same time, regularization, early stopping and other techniques are used to prevent overfitting.
[0079] Preferably, the training of the preset deep learning model further includes:
[0080] Evaluate the preset deep learning model using a test data set, wherein the evaluation indicators include mean square error (MSE), root mean square error (RMSE), R square, or any combination thereof;
[0081] The preset deep learning model is optimized and iterated according to the evaluation results, and the optimization includes model parameter optimization and model structure optimization.
[0082] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.
[0083] In one embodiment, Figure 2 As shown, a device for adaptively controlling a viewing environment is provided, comprising: a parameter acquisition module 21, a control generation module 22 and a control execution module 23, wherein:
[0084] The parameter acquisition module 21 is used to acquire the physiological indicators, user behavior and viewing environment parameters of the viewing user;
[0085] A control generation module 22 is used to generate an optimal adaptation scheme adapted to the current viewing environment through a preset deep learning model according to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content;
[0086] The control execution module 23 is used to control the environment control equipment to operate in conjunction with each other according to the optimal adaptation solution to create an immersive viewing environment.
[0087] Furthermore, the parameter acquisition module 21 is specifically used to collect physiological indicators of the user when watching a movie through a wearable device and / or a first sensing device, the physiological indicators including any one or any combination of heart rate, pressure, breathing rate, blood oxygen saturation, body temperature and sound; obtain user behavior through a camera, the user behavior including any one or any combination of facial expressions, body shape and sitting posture; obtain viewing environment parameters through a second sensing device, the viewing environment parameters including any one or any combination of temperature, humidity and brightness.
[0088] Furthermore, the environmental control equipment includes any one or any combination of heaters, fans, air conditioners, humidifiers, lights, speakers and flavor makers, and the control execution module 23 is specifically used to generate a real-time environmental control plan based on the best adaptation plan, and the environmental control plan includes any one or any combination of environmental parameter values, the environmental control equipment to be called, control speed and control method; according to the environmental control plan, combined with the power of the environmental control equipment, the size of the viewing venue and the film and television content, a predicted environmental control plan is generated in advance; the real-time environmental control plan and / or the predicted environmental control plan are used to dynamically control the linkage operation of the environmental control equipment in real time to create an immersive viewing environment.
[0089] Furthermore, the device also includes:
[0090] The control detection module is used to monitor the control performance of the viewing environment in real time. The control performance includes control speed, stability and accuracy. If problems are found in the control performance or users feedback that the current control effect is not good, the environmental control equipment is controlled to operate in conjunction according to the predetermined best adaptation plan.
[0091] Furthermore, the device also includes:
[0092] A model training module, used to train the preset deep learning model, wherein the model training module is specifically used to collect historical viewing environment data, historical user behavior, and historical physiological data;
[0093] The collected historical viewing environment data, historical user behavior, and historical physiological data are preliminarily screened through preprocessing algorithms to remove outliers and duplicate values, and missing values are inferred through probability calculations;
[0094] Normalizing the pre-processed historical movie-watching environment data, historical user behavior, and historical physiological data;
[0095] According to the purpose of achieving the best viewing environment effect, features with a high correlation with the target variable are selected from the normalized historical viewing environment data, historical user behavior, and historical physiological data for reinforcement learning, wherein the target variable includes any one or any combination of ambient light intensity, viewing distance, and viewing emotion fluctuations;
[0096] Classify and encode the features and convert the features into numerical features, wherein the features include set user preferences;
[0097] Transforming the features to improve the distribution of the features and the performance of the model, wherein the transformation includes one or any combination of logarithmic transformation and square root transformation;
[0098] Performing feature dimensionality reduction on the historical viewing environment data, historical user behavior, and historical physiological data by using dimensionality reduction technology to reduce the number of features, wherein the dimensionality reduction technology includes principal component analysis (PCA) and latent Dirichlet allocation (LDA);
[0099] The preset deep learning model is generated by training the preset regression model through the historical viewing environment data, historical user behavior, and historical physiological data after dimensionality reduction.
[0100] Furthermore, the model training module is specifically used to: use a test data set to evaluate the preset deep learning model, wherein the evaluation indicators include one or any combination of mean square error (MSE), root mean square error (RMSE), and R-squared; optimize and iterate the preset deep learning model according to the evaluation results, and the optimization includes model parameter optimization and model structure optimization.
[0101] Furthermore, the device also includes:
[0102] The model optimization module is used to collect actual feedback from users and optimize and iterate the preset deep learning model.
[0103] For the specific definition of the device for adaptively controlling the viewing environment, please refer to the definition of the method for adaptively controlling the viewing environment above, which will not be repeated here. Each module in the above-mentioned device for adaptively controlling the viewing environment can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0104] In one embodiment, a control device is provided. The control device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The control device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the control device is used to provide computing and control capabilities. The memory of the control device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the control device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for adaptively controlling the viewing environment is implemented. The display screen of the control device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the control device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0105] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the control device to which the scheme of the present application is applied. The specific control device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0106] In one embodiment, a control device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0107] Obtain the physiological indicators, user behaviors and viewing environment parameters of the viewing users;
[0108] According to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, the best adaptation solution adapted to the current viewing environment is generated through a preset deep learning model;
[0109] The optimal adaptation scheme is used to control the coordinated operation of environmental control equipment to create an immersive viewing environment.
[0110] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0111] Obtain the physiological indicators, user behaviors and viewing environment parameters of the viewing users;
[0112] According to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, the best adaptation solution adapted to the current viewing environment is generated through a preset deep learning model;
[0113] The optimal adaptation scheme is used to control the coordinated operation of environmental control equipment to create an immersive viewing environment.
[0114] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0115] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0116] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A method for adaptively controlling a viewing environment, characterized in that: The method comprises: Obtain the physiological indicators, user behaviors and viewing environment parameters of the viewing users; According to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content, the best adaptation solution adapted to the current viewing environment is generated through a preset deep learning model; The optimal adaptation scheme is used to control the coordinated operation of environmental control equipment to create an immersive viewing environment.
2. The method according to claim 1, characterized in that The acquisition of physiological indicators, user behaviors and viewing environment parameters of the viewing user specifically includes: Collecting physiological indicators of the user when watching a movie through a wearable device and / or a first sensor device, wherein the physiological indicators include any one or any combination of heart rate, pressure, respiratory rate, blood oxygen saturation, body temperature and sound; Acquire user behavior through a camera, wherein the user behavior includes any one or any combination of facial expressions, body postures, and sitting postures; The viewing environment parameters are acquired through the second sensing device, and the viewing environment parameters include any one or any combination of temperature, humidity and brightness.
3. The method according to claim 1, characterized in that The environment control equipment includes any one or any combination of heaters, fans, air conditioners, humidifiers, lights, audio equipment and flavor generators. The optimal adaptation scheme is used to control the environment control equipment to operate in conjunction to create an immersive viewing environment, including: Generate a real-time environment control plan according to the best adaptation plan, wherein the environment control plan includes any one or any combination of environment parameter values, the environment control equipment to be called, control speed and control mode; Generate a predicted environment control plan in advance according to the environment control plan, combined with the power of the environment control equipment, the size of the viewing venue and the content of the film and television; The environment control devices are controlled to operate in a coordinated manner in real time and dynamically using a real-time environment control scheme and / or a predicted environment control scheme to create an immersive viewing environment.
4. The method according to claim 1, characterized in that: After controlling the environment control equipment to operate in conjunction with each other using the optimal adaptation scheme to create an immersive viewing environment, the method further includes: The control performance of the viewing environment is monitored in real time, and the control performance includes control speed, stability and accuracy. If problems are found in the control performance or users feedback that the current control effect is not good, the environment control equipment is controlled to operate in conjunction according to the predetermined best adaptation plan.
5. The method according to claim 1, characterized in that The method further comprises: Training the preset deep learning model, wherein the training the preset deep learning model comprises: Collect historical viewing environment data, historical user behavior, and historical physiological data; The collected historical viewing environment data, historical user behavior, and historical physiological data are preliminarily screened through preprocessing algorithms to remove outliers and duplicate values, and missing values are inferred through probability calculations; Normalizing the pre-processed historical movie-watching environment data, historical user behavior, and historical physiological data; According to the purpose of achieving the best viewing environment effect, features with a high correlation with the target variable are selected from the normalized historical viewing environment data, historical user behavior, and historical physiological data for reinforcement learning, wherein the target variable includes any one or any combination of ambient light intensity, viewing distance, and viewing emotion fluctuations; Classify and encode the features and convert the features into numerical features, wherein the features include set user preferences; Transforming the features to improve the distribution of the features and the performance of the model, wherein the transformation includes one or any combination of logarithmic transformation and square root transformation; Performing feature dimensionality reduction on the historical viewing environment data, historical user behavior, and historical physiological data by using dimensionality reduction technology to reduce the number of features, wherein the dimensionality reduction technology includes principal components analysis (PCA) and latent Dirichlet Allocation (LDA); The preset deep learning model is generated by training the preset regression model through the historical viewing environment data, historical user behavior, and historical physiological data after dimensionality reduction.
6. The method according to claim 5, characterized in that The training preset deep learning model also includes: Evaluate the preset deep learning model using a test data set, wherein the evaluation indicators include mean square error (MSE), root mean square error (RMSE), R square, or any combination thereof; The preset deep learning model is optimized and iterated according to the evaluation results, and the optimization includes model parameter optimization and model structure optimization.
7. The method according to claim 1, characterized in that After controlling the environment control equipment to operate in conjunction with each other using the optimal adaptation scheme to create an immersive viewing environment, the method further includes: Collect actual feedback from users and optimize and iterate the preset deep learning model.
8. A device for adaptively controlling a viewing environment, characterized in that: The device comprises: A parameter acquisition module is used to obtain physiological indicators, user behaviors and viewing environment parameters of the viewing user; A control generation module is used to generate the best adaptation scheme adapted to the current viewing environment through a preset deep learning model according to the physiological indicators, user behavior and viewing environment parameters, combined with the current film and television content; The control execution module is used to control the coordinated operation of the environmental control equipment according to the optimal adaptation solution to create an immersive viewing environment.
9. A control device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
