Natural wake-up system for controlling acousto-optic time management based on off-line voice recognition

Abstract

The invention relates to the technical field of smart home control, and particularly discloses a natural wake-up system for controlling acousto-optic time management based on off-line voice recognition, which comprises an off-line voice recognition module for recognizing a user voice instruction in an off-line state; and the main control module calculates a first personalized influence factor of the smart home control parameters on a user wake-up process and a second personalized influence factor of a user specified wake-up moment according to the home control parameter matrix, the wake-up efficiency vector and the specified wake-up moment vector, and generates an acousto-optic time management strategy in combination with the AI and a user voice instruction. And the time management module is responsible for recording real-time time. And the RF communication module and the infrared signal transmitting module respectively transmit control signals to the smart home capable of receiving the RF signals and the infrared control signals in real time according to strategies. The audio playing module plays a built-in audio file through a loudspeaker according to a strategy, a more comfortable and intelligent awakening environment is created, and the awakening feeling of a user and the satisfaction degree of the user to the system are improved.

Description

Technical Field

[0001] The present invention relates to the field of smart home control technology, and in particular to a natural wake-up system based on offline voice recognition control and sound and light time management. Background Art

[0002] In the smart home sector, natural wakeup systems are crucial for enabling natural interaction between people and smart home devices. As people's pursuit of a higher quality of life increases, they desire more convenient and natural control of smart home devices, prompting the emergence of natural wakeup systems. These systems transform the traditional manual operation of smart homes, allowing users to easily control home devices through voice commands, significantly enhancing the user experience. The application of offline voice recognition technology has revitalized the natural wakeup system. Even in unstable or unavailable network conditions, offline voice recognition ensures the system continues to function, ensuring continuous and stable control of smart home devices. Furthermore, the sound and light time management feature further optimizes smart home usage scenarios. By incorporating time factors to control lighting, sound, and other devices, it can better meet users' needs at different times of day and create a comfortable and convenient home environment. This natural wakeup system, integrating offline voice recognition and sound and light time management, aligns with the intelligent and user-friendly trends in smart home development, possesses broad market prospects, and will propel the smart home industry into a new stage of development.

[0003] However, existing natural wake-up systems have numerous shortcomings. Voice recognition lacks offline capabilities, making it difficult to accurately recognize commands when the network is poor, limiting functionality. They also fail to fully consider user personalization, fail to generate relevant data based on natural wake-up records, and struggle to identify personalized influencing factors and develop precise sound and light timing management strategies. Furthermore, their interaction with various smart home devices is flawed, making it impossible to accurately control devices and create a wake-up atmosphere through corresponding modules based on strategies and timing. Consequently, their low level of intelligence and personalization makes it difficult to meet user needs.

[0004] Therefore, the present invention proposes a natural wake-up system based on offline speech recognition to control sound and light time management. Summary of the Invention

[0005] The present invention provides a natural wake-up system based on offline speech recognition and sound and light time management, comprising:

[0006] First, the offline voice recognition module recognizes user voice commands offline. This means users can conveniently interact with the system via voice even without an internet connection, unrestricted by network conditions. This significantly improves the system's flexibility and stability, ensuring users can issue commands at any time. Second, the main control module generates multiple key vectors and matrices based on the user's natural wake-up history and derives personalized impact factors. Combined with artificial intelligence and voice commands, it generates an audio-visual time management strategy. This strategy fully considers user habits and personalized needs, enabling customized wake-up and smart home control solutions for each user, enhancing the user experience while also strengthening the system's intelligence and targetedness. Furthermore, the time management module records real-time time, providing a precise time reference for the entire system. This allows the audio-visual time management strategy to be executed based on accurate time information, ensuring timely and accurate control and ensuring that appropriate audio-visual and smart home control operations are executed at the appropriate time. Furthermore, the RF communication module and infrared signal transmission module each send control signals to smart home devices that can receive different signals. This design is compatible with a wide range of smart home devices, expanding the system's applicability and allowing users to integrate various smart devices in their homes for unified and convenient control. Finally, the audio playback module plays built-in audio files according to the sound and light time management strategy and real-time time, providing users with a personalized wake-up audio experience. In conjunction with other control functions, it creates a more comfortable and intelligent wake-up environment, improving users' wake-up experience and satisfaction with the system.

[0007] The present invention provides a natural wake-up system based on offline speech recognition and sound and light time management, comprising:

[0008] An offline speech recognition module is used to recognize the user's voice commands received by the microphone in an offline state;

[0009] The main control module is used to obtain a first personalized impact factor of the smart home control parameters on the user's wake-up process and a second personalized impact factor of the user's specified wake-up time on the user's wake-up process based on the home control parameter matrix, wake-up efficiency vector, and specified wake-up time vector generated using the user's natural wake-up record, and to generate an acoustic and optical time management strategy by combining artificial intelligence and the user's voice command;

[0010] Time management module, used to record real-time time;

[0011] RF communication module, used to send control signals to smart home devices that can receive RF signals based on the sound and light time management strategy and real-time time;

[0012] An infrared signal transmitting module is used to send a control signal to a smart home that can receive infrared control signals based on the sound and light time management strategy, real-time time, and the smart home remote control code stored in the infrared remote control code library;

[0013] The audio playback module is used to play built-in audio files through the speaker based on the sound and light time management strategy and real time.

[0014] Preferably, it also includes:

[0015] Rechargeable battery, used to provide power for the microphone, offline voice recognition module, main control module, time management module, RF communication module, infrared remote control code library, infrared signal transmission module, audio playback module, speaker, power management module, and LED display module;

[0016] The power management module is used to send a reminder signal when the remaining capacity of the rechargeable battery is lower than a threshold value, and at the same time, adjust the working mode of the main control module to the power saving mode;

[0017] LED display module, used to display real-time time, remaining battery power, time information in the latest voice command, and the working status of all communicative smart devices;

[0018] The storage module is used to store all received voice commands, the continuous working status of all communicative smart devices, and all currently determined sound and light time management strategies.

[0019] Preferably, the smart home devices that can receive RF signals include LED lamps, smart curtains, and aromatherapy machines;

[0020] The LED lamp gradually lights up and changes color temperature based on the control signal received;

[0021] The smart curtains gradually open based on the control signal received;

[0022] The aroma diffuser starts working based on the received control signal.

[0023] Preferably, the smart home that can receive RF signals is an air conditioner, and the air conditioner gradually adjusts the temperature to a corresponding temperature based on the received control signal.

[0024] Preferably, the main control module includes:

[0025] A data processing submodule is used to generate a home control parameter matrix, a wake-up efficiency vector, and a prescribed wake-up time vector based on the user's natural wake-up records;

[0026] a correlation analysis submodule for generating a first personalized impact factor of the smart home control parameters on the user's wake-up process and a second personalized impact factor of the user-specified wake-up time on the user's wake-up process based on the correlation analysis results between the home control parameter matrix and the wake-up efficiency vector and the correlation analysis results between the specified wake-up time vector and the wake-up efficiency vector;

[0027] The sound and light time management strategy generation submodule is used to obtain the sound and light time management strategy based on the first personalized influence factor of the smart home control parameter on the user wake-up process, the second personalized influence factor of the user-specified wake-up time on the user wake-up process, the latest user-specified wake-up time represented by the latest received voice command, and the pre-built sound and light time management strategy generation model.

[0028] Preferably, the data processing submodule includes:

[0029] A wake-up efficiency value analysis unit is used to analyze the wake-up efficiency value of each natural wake-up process based on the continuous control execution time of each smart home in the sound and light time management strategy executed in each natural wake-up process in the user's natural wake-up record and the corresponding time required for the user to fully wake up;

[0030] A home control parameter matrix generation unit is used to generate a home control parameter matrix based on the continuous control parameter threads of all smart homes in the sound and light time management strategy executed in all natural wake-up processes in the natural wake-up record;

[0031] a wake-up efficiency vector generating unit, configured to generate a wake-up efficiency vector based on the wake-up efficiency values ​​of all natural wake-up processes in the natural wake-up record;

[0032] The wake-up time vector generating unit is configured to generate a specified wake-up time vector based on the user-specified wake-up time of all natural wake-up processes in the natural wake-up record.

[0033] Preferably, the wake-up efficiency value analysis unit includes:

[0034] a single wake-up efficiency value determining subunit, configured to use the ratio of the continuous control execution time of each smart home in each natural wake-up process to the time required for the user to fully wake up in the corresponding natural wake-up process as the single wake-up efficiency value of each smart home in the corresponding natural wake-up process;

[0035] The single wake-up efficiency value aggregation subunit is used to perform weighted summation of the single wake-up efficiency values ​​of all smart homes in a single natural wake-up process based on the wake-up weights of all smart homes to obtain the wake-up efficiency value of each natural wake-up process.

[0036] Preferably, the correlation analysis submodule includes:

[0037] A matrix dimensionality reduction and derivation unit is used to perform dimensionality reduction processing on the home control parameter matrix to obtain a home control parameter dimensionality reduction matrix, generate a control parameter dimensionality reduction function for each smart home based on the control parameter dimensionality reduction value sequence of each smart home in the home control parameter dimensionality reduction matrix, and generate a home control parameter dimensionality reduction first-order derivative matrix based on the first-order derivative values ​​of the control parameter dimensionality reduction functions of all smart homes at all times;

[0038] a first influencing factor calculation unit, configured to analyze at least one common eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension, and obtain a first influencing factor of the smart home control parameters on the user wake-up process based on the cosine similarity between the common eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension and the eigenvector of the wake-up efficiency vector in the time dimension;

[0039] A second impact factor calculation unit is used to obtain a second impact factor of the user-specified wake-up time on the user's wake-up process based on a correlation analysis result between the specified wake-up time vector and the wake-up efficiency vector;

[0040] a wake-up difficulty assessment unit, configured to assess the user's wake-up difficulty based on the user's natural wake-up record;

[0041] The personalized influence factor calibration unit is used to determine the first personalized influence factor of the smart home control parameters on the user wake-up process and the second personalized influence factor of the user-specified wake-up time on the user wake-up process based on the first influence factor of the smart home control parameters on the user wake-up process and the second personalized influence factor of the user-specified wake-up time on the user wake-up process and the user's wake-up difficulty.

[0042] Preferably, the first impact factor calculation unit includes:

[0043] A first eigenvalue decomposition subunit is configured to determine a covariance matrix of a reduced-dimensional first-order derivative matrix of home control parameters, perform eigenvalue decomposition on the covariance matrix of the reduced-dimensional first-order derivative matrix of home control parameters, obtain at least one eigenvalue and a corresponding eigenvector, and use each eigenvector as a common eigenvector of the reduced-dimensional first-order derivative matrix of home control parameters in a time dimension;

[0044] A vector time dimension expansion subunit is used to construct a lag feature matrix of the wake-up efficiency vector based on a sliding window method, perform mean zeroing and variance normalization on the lag feature matrix of the wake-up efficiency vector, and obtain a standardized lag feature matrix;

[0045] A second eigenvalue decomposition subunit is used to perform eigenvalue decomposition on the covariance matrix of the standardized lag feature matrix to obtain all eigenvalues ​​and corresponding eigenvectors of the covariance matrix of the standardized lag feature matrix, and use the eigenvector corresponding to the maximum eigenvalue among all eigenvalues ​​and corresponding eigenvectors of the covariance matrix of the standardized lag feature matrix as the eigenvector of the wake-up efficiency vector in the time dimension;

[0046] A cosine similarity calculation subunit, configured to calculate the cosine similarity of the feature vectors of each common feature vector whose corresponding feature value is greater than a threshold and the wake-up efficiency vector in the time dimension;

[0047] The correlation synthesis subunit is used to calculate the weight value of each common eigenvector whose corresponding eigenvalue is greater than the threshold based on all eigenvalues ​​greater than the threshold, and based on the weight values ​​of all common eigenvectors whose corresponding eigenvalue is greater than the threshold, perform weighted summation of the cosine similarities of the eigenvectors of each common eigenvector whose corresponding eigenvalue is greater than the threshold and the wake-up efficiency vector in the time dimension, to obtain the first influencing factor of the smart home control parameter on the user wake-up process.

[0048] Preferably, the personalized impact factor calibration unit includes:

[0049] an adjustment coefficient determination subunit, configured to determine an average wake-up time based on the user's natural wake-up records, determine a first adjustment coefficient based on the average wake-up time and the user's wake-up difficulty, and determine a second adjustment coefficient based on the user's wake-up difficulty and difficulty sensitivity coefficient;

[0050] A first influencing factor personalized calibration subunit is configured to use the product of the first influencing factor of the smart home control parameter on the user wake-up process, the first adjustment coefficient, and the control parameter importance weight as the first personalized influencing factor of the smart home control parameter on the user wake-up process;

[0051] The second influencing factor personalized calibration subunit is used to take the product of the second personalized influencing factor of the user-specified wake-up time on the user wake-up process and the second adjustment coefficient and the time window adjustment coefficient as the second personalized influencing factor of the user-specified wake-up time on the user wake-up process.

[0052] The present invention has the following beneficial effects compared to the prior art: First, the offline voice recognition module recognizes user voice commands in an offline state. This means that even without a network connection, users can still conveniently interact with the system through voice, unrestricted by the network environment. This greatly improves the flexibility and stability of the system and ensures that users can issue commands at any time. Second, the main control module generates multiple key vectors and matrices based on the user's natural wake-up records and obtains personalized influence factors. Then, combined with artificial intelligence and voice commands, it generates an audio-visual time management strategy. This fully considers the user's usage habits and personalized needs, and can customize exclusive wake-up and smart home control solutions for different users, improving the user experience while enhancing the intelligence and targetedness of the system. Furthermore, the time management module records real-time time, providing an accurate time reference for the entire system. This enables the audio-visual time management strategy to be executed based on accurate time information, ensuring the timeliness and accuracy of control and ensuring that the corresponding audio-visual and smart home control operations are performed at the appropriate time. In addition, the RF communication module and the infrared signal transmission module respectively send control signals to smart homes that can receive different signals. This design is compatible with multiple types of smart home devices, expanding the scope of application of the system and facilitating the integration of various smart devices in the home for unified and convenient control. Finally, the audio playback module plays built-in audio files according to the sound and light time management strategy and real-time time, providing users with a personalized wake-up audio experience. In conjunction with other control functions, it creates a more comfortable and intelligent wake-up environment, improving users' wake-up experience and satisfaction with the system.

[0053] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0054] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0056] Figure 1 Schematic diagram of a natural wake-up system based on offline speech recognition and sound-light time management in an embodiment of the present invention;

[0057] Figure 2 Schematic diagram of controlling various smart home appliances based on offline voice recognition in an embodiment of the present invention;

[0058] Figure 3 Schematic diagram of the execution logic of the main control module in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0060] Example 1:

[0061] The present invention provides a natural wake-up system based on offline speech recognition control and sound and light time management. Each module works together to achieve the natural wake-up function. Figure 1 Offline voice recognition to control the alarm clock, including:

[0062] Offline Voice Recognition Module: This module enables the system to recognize user voice commands collected through the microphone even when the system is offline and without a network connection. This feature eliminates network dependency and allows users to easily communicate commands to the system regardless of their network environment. For example, a user can say a command such as "Set wake-up mode for 7 AM tomorrow" in an environment without Wi-Fi or mobile data. The offline voice recognition module will accurately recognize the command and initiate the wake-up setup process, meeting the user's need for natural wake-up system control in different scenarios.

[0063] Main control module: It uses the user's natural wake-up records to generate a home control parameter matrix, a wake-up efficiency vector, and a prescribed wake-up time vector. By analyzing and processing these data, the first personalized impact factor of the smart home control parameters (such as light brightness, color temperature, sound volume, type, etc.) on the user's wake-up process, and the second personalized impact factor of the user-specified wake-up time on the wake-up process are obtained. For example, by analyzing the user's multiple natural wake-up records, it was found that the user's wake-up efficiency is higher in warm light of a specific color temperature and soft bird sounds, thereby determining the impact factors of these parameters on the wake-up process. Then, the main control module combines artificial intelligence technology and the user's voice commands to generate a sound and light time management strategy suitable for the user. This strategy fully takes into account the user's personalized needs and habits to ensure that the most suitable natural wake-up environment is created for the user.

[0064] Time Management Module: This module is responsible for accurately recording real-time time, providing an accurate time reference for the entire natural wake-up system. System operations, such as executing wake-up tasks according to set times and adjusting the rhythm of environmental factors such as lighting and sound based on real-time time, rely on the time information recorded by the time management module. For example, if a user sets a wake-up time of 7:00 AM, the time management module accurately timed the time and triggered a series of wake-up actions at that time, ensuring the accuracy and timeliness of the wake-up process.

[0065] RF Communication Module: Based on the sound and light time management strategy generated by the main control module and the real-time recorded by the time management module, the RF communication module sends control signals to smart home devices that can receive RF signals. This enables the system to interact with RF-enabled smart devices and remotely control them. For example, before the set wake-up time, the RF communication module sends a signal to the smart curtains according to the strategy, causing them to slowly open, simulating the gradual increase in natural light and creating an atmosphere similar to a natural wake-up.

[0066] Infrared Signal Transmission Module: Based on the sound and light time management strategy, real-time clock information, and the smart home remote control codes stored in the infrared remote control code library, this module sends control signals to smart home devices that can receive infrared control signals. For traditional smart home devices that rely on infrared signals for control, such as some air conditioner models, the infrared signal transmission module plays a key role. For example, during the wake-up process, the module sends infrared signals to the air conditioner at the appropriate time according to the strategy, adjusting the indoor temperature and creating a comfortable wake-up environment for the user.

[0067] Audio playback module: Based on the sound and light time management strategy and real-time time, the built-in audio files are played through the speaker. During the natural awakening process, the audio playback module plays an important role in creating an atmosphere. For example, as the wake-up time approaches, the audio playback strategy starts softly and gradually increases the volume of natural bird calls or other natural sounds, simulating the sound changes in the natural environment in the early morning. This helps the user gradually transition from deep sleep to light sleep, ultimately waking up naturally and achieving a healthy awakening.

[0068] Example 2:

[0069] On the basis of Example 1, the natural wake-up system based on offline speech recognition control sound and light time management is further improved. Each new module plays an important role in the entire natural wake-up system. Combined with the overall technical solution: Figure 1 , also includes:

[0070] Rechargeable battery: It acts as an energy hub in the entire natural wake-up system, powering many key components such as the microphone, offline voice recognition module, and main control module. This design is closely centered around the system's offline usage requirements. Even when there is no network and the external mains power is interrupted, the system can still operate normally thanks to the rechargeable battery, continuing its function of simulating natural wake-up. For example, in the event of a sudden power outage, the system can still create a natural wake-up environment for users by controlling LED lamps, smart curtains and other devices according to preset programs, ensuring the reliability and stability of the system and meeting the user's need to "sleep until naturally awake." At the same time, it also conforms to the system's characteristics of working without an Internet connection and protecting user privacy and security.

[0071] Power management module: It has the dual functions of power monitoring and mode adjustment. When the remaining capacity of the rechargeable battery is lower than the threshold, a reminder signal is issued. This function is designed to promptly inform the user of the power status so that the user can charge in time to avoid the system being unable to perform the wake-up task normally due to power exhaustion. At the same time, the main control module is adjusted to power saving mode. This operation ensures the continuous operation of key system functions by reducing the power consumption of the main control module when the power is limited. For example, when the power is low, although the main control module enters power saving mode, it can still control various smart devices based on the natural wake-up strategy previously set by the user to maintain the basic wake-up function of the system. This can meet user needs while making the most of limited power, reflecting the humanization and intelligence of the system design.

[0072] LED display module: As a window for information interaction, its display function is closely related to the system's time management and device status monitoring. It displays real-time time, corresponding to the time recorded by the time management module, providing users with an accurate time reference, allowing them to understand the current moment and arrange subsequent activities appropriately. It displays the remaining battery life, allowing users to have an idea of ​​the power reserves of the rechargeable battery. Combined with reminders from the power management module, this helps them better plan charging times. Displaying the time information in the latest voice command helps users confirm key command content such as the wake-up time, ensuring that the natural wake-up settings are accurate. Displaying the working status of all communicative smart devices allows users to intuitively understand whether devices such as LED lamps, smart curtains, aromatherapy machines, and air conditioners are operating according to preset strategies, such as the brightness and color temperature of LED lamps and the degree of opening and closing of smart curtains, thereby effectively monitoring and managing the entire natural wake-up environment.

[0073] The storage module serves as the foundation for system data recording and analysis. Storing all received voice commands helps the system conduct in-depth analysis of users' wake-up needs and operating habits. For example, by analyzing user voice commands across different time periods and scenarios, the system can further optimize offline voice recognition, improving recognition accuracy and natural language understanding, allowing users to express their needs more easily and naturally. The system also stores the ongoing operating status of all communicative smart devices, providing data support for analyzing device usage patterns and optimizing control strategies. For example, it can understand the opening speed and travel requirements of smart curtains in different seasons and at different wake-up times, thereby more accurately simulating natural wake-up scenarios. It also stores all currently determined sound and light time management strategies, facilitating their reuse and adjustment in subsequent operations. Based on the user's long-term usage habits and environmental changes, the system continuously optimizes the natural wake-up mode to achieve better wake-up results and achieve the healthy "sleep until waking naturally" wake-up goal. This also provides data support for continuous system improvement and functionality expansion.

[0074] Example 3:

[0075] Based on Example 1, Figure 2 ,Smart homes that can receive RF signals include LED lamps, smart curtains, and aromatherapy machines;

[0076] Smart homes that can receive RF signals: This type of smart home includes LED lamps, smart curtains, and aromatherapy machines. These devices are important components of the natural wake-up system to achieve environmental simulation.

[0077] LED lamps: When LED lamps receive control signals from the RF communication module, they gradually illuminate according to the settings, gradually changing their color temperature as they illuminate. For example, at the beginning of the wake-up process, LED lamps may slowly illuminate at a lower brightness and a warmer color temperature, simulating the gradual increase in natural light and the transition from warm to bright in the early morning. This helps users gradually adapt to the light changes and transition from deep sleep to light sleep, meeting the requirements of the natural wake-up system to simulate the changes in natural ambient light.

[0078] Smart curtains: Based on control signals from the RF communication module, the smart curtains gradually open. For example, as wake-up time approaches, the smart curtains slowly open, allowing more natural light to filter into the room, further enhancing the light effect. Combined with LED lighting, they create a more realistic natural wake-up lighting environment, making the wake-up process more natural.

[0079] Aromatherapy Diffuser: Once it receives a control signal, the aromatherapy diffuser activates. In a natural wake-up system, the aromatherapy diffuser releases a specific fragrance that helps create a comfortable wake-up atmosphere. For example, it releases a refreshing fragrance to help users wake up more easily from sleep, enhancing the natural wake-up experience through olfactory perception.

[0080] Example 4:

[0081] Based on Example 1, Figure 2 The smart home appliance that can receive RF signals is an air conditioner. Based on the received control signal, the air conditioner gradually adjusts the temperature to a specific temperature. This section specifically describes a smart home appliance that can receive RF signals, focusing on the air conditioner and its response to the control signal. Here, the smart home appliance that can receive RF signals is an air conditioner. Upon receiving the control signal sent by the RF communication module based on the acoustic and optical time management strategy and real-time clock, the air conditioner gradually adjusts the temperature to a specific temperature.

[0082] For example, in a natural awakening scenario, to create a comfortable awakening environment for the user, the system sends a control signal to the air conditioner via the RF communication module before the wake-up time approaches, based on a preset sound and light time management strategy. The air conditioner then gradually adjusts the temperature. For example, if the set wake-up temperature is 25°C, it will gradually adjust from the current temperature towards 25°C, avoiding sudden temperature changes that may cause discomfort to the user. This is in line with the natural awakening system's goal of fully simulating a natural and comfortable environment, allowing the user to smoothly transition from deep sleep to light sleep and finally awaken naturally.

[0083] Example 5:

[0084] Based on Example 1, Figure 3 , main control module, including:

[0085] The data processing submodule is responsible for generating a home control parameter matrix, a wake-up efficiency vector, and a prescribed wake-up time vector based on the user's natural wake-up records. This submodule operates based on the user's natural wake-up records. Natural wake-up records refer to detailed information collected by the system regarding each natural wake-up by the user, such as the brightness and color temperature settings of LED lamps, the degree of opening of smart curtains, the type of scent released by the aromatherapy device, the content and volume of audio playback, and the corresponding wake-up time. The data processing submodule organizes and analyzes these records to generate a home control parameter matrix, a wake-up efficiency vector, and a prescribed wake-up time vector.

[0086] The home control parameter matrix is ​​a data structure that arranges various home control parameters in a matrix format. It clearly displays the combinations of different home control parameters in different wake-up scenarios. For example, the rows of the matrix can represent different wake-up events, and the columns represent different home control parameters, such as the first column for LED light brightness, the second for color temperature, and the third for the smart curtain opening ratio. This allows users to intuitively see the values ​​of each home control parameter at each wake-up.

[0087] The wakeup efficiency vector is a data representation used to measure the efficiency of the user's transition from deep sleep to light sleep and ultimately waking up naturally during each wakeup process. Simply put, each element in the vector corresponds to a wakeup event, and the element's value can be quantified using a numerical value, such as a range of 0-100, with higher values ​​indicating higher wakeup efficiency. This value can be derived based on, for example, an assessment of the user's state after wakeup.

[0088] Among them, the specified wake-up time vector records the wake-up time set by the user each time. Each element in the vector is a specific time value, such as "7:00 am" and "8:30 am", which makes it convenient for the system to analyze the relationship between the user-set wake-up time and the wake-up efficiency.

[0089] The correlation analysis submodule is used to generate a first personalized impact factor of the smart home control parameters on the user's wake-up process and a second personalized impact factor of the user-specified wake-up time on the user's wake-up process based on the correlation analysis results between the home control parameter matrix and the wake-up efficiency vector and the correlation analysis results between the specified wake-up time vector and the wake-up efficiency vector. Specifically, it includes:

[0090] Analysis based on the home control parameter matrix and the wake-up efficiency vector: The home control parameter matrix contains the combinations of various smart home control parameters during each natural wake-up process. Parameters such as LED lighting brightness and color temperature, and the degree of smart curtain opening, are recorded in different wake-up scenarios. The wake-up efficiency vector quantifies the efficiency of the user's transition from deep sleep to light sleep and ultimately to natural awakening during each wake-up process. By analyzing the relationship between these two parameters, such as the correlation between specific lighting settings of brightness and color temperature and wake-up efficiency, the home control parameter combinations that have the greatest impact on wake-up efficiency are identified, thereby determining the first personalized impact factor of the smart home control parameters on the user's wake-up process. Based on these correlation analysis results, the generated first personalized impact factor reflects the unique impact of the smart home control parameters on the user's wake-up process. For example, if a specific combination of parameters such as light brightness, color temperature, and the degree of smart curtain opening is found to be closely correlated with higher wake-up efficiency, then these parameters will have a larger weight in the first personalized impact factor, indicating that they have a more critical impact on the user's wake-up process.

[0091] Based on the analysis of the prescribed wake-up time vector and the wake-up efficiency vector: The prescribed wake-up time vector records the wake-up time set by the user each time. By performing a correlation analysis with the wake-up efficiency vector, we can understand the impact of different wake-up times on the wake-up efficiency. For example, the analysis found that when the user sets the wake-up time between 7:00-7:30 in the morning, the wake-up efficiency is higher. Then, when generating the second personalized influence factor, the weight corresponding to this time period will be higher, so as to reflect the degree of influence of the user-prescribed wake-up time on the user's wake-up process. Through the correlation analysis of these two aspects, the generated first personalized influence factor and second personalized influence factor can accurately reflect the role of smart home control parameters and prescribed wake-up time on each user's unique wake-up process.

[0092] The second personalized impact factor reflects the unique impact of the user's specified wake-up time on the wake-up process. For example, if analysis shows that the user's wake-up efficiency is higher when the wake-up time is set between 6:30 and 7:30 in the morning, then the weight corresponding to this time period in the second personalized impact factor will be greater, indicating that this time period has a greater impact on the user's wake-up process.

[0093] The sound and light time management strategy generation submodule is used to obtain the sound and light time management strategy based on the first personalized influence factor of the smart home control parameter on the user wake-up process, the second personalized influence factor of the user-specified wake-up time on the user wake-up process, the latest user-specified wake-up time represented by the latest received voice command, and the pre-built sound and light time management strategy generation model.

[0094] This submodule uses as key inputs the first personalized impact factor of the smart home control parameters on the user's wake-up process, generated by the correlation analysis submodule, and the second personalized impact factor of the user-specified wake-up time on the user's wake-up process. These two factors reflect the user's personalized wake-up characteristics. Furthermore, the latest user-specified wake-up time, as indicated by the most recently received voice command, is also crucial information, clarifying the user's desired wake-up time. For example, if a user says "Set wake-up time at 7:15 AM tomorrow," "7:15 AM" here refers to the latest user-specified wake-up time.

[0095] Furthermore, the pre-built sound and light time management strategy generation model is based on a large amount of data and algorithms. It can output a sound and light time management strategy that is suitable for the user based on various input parameters. This model was obtained through deep learning of many excellent wake-up examples from users (including the first personalized influence factor of smart home control parameters on the user wake-up process, the second personalized influence factor of the user-specified wake-up time on the user wake-up process, the latest user-specified wake-up time represented by the most recently received voice command, and the sound and light time management strategy adopted when the user is awakened under this premise and gives a good wake-up evaluation).

[0096] By inputting the first personalized impact factor of smart home control parameters on the user's wake-up process, the second personalized impact factor of the user-specified wake-up time on the user's wake-up process, and the latest user-specified wake-up time indicated by the most recently received voice command into a pre-built sound and light time management strategy generation model, a sound and light time management strategy tailored to the user can be generated. If the model finds that a user prefers a softer light gradient and gentle running water sounds when awakened, and sets an early wake-up time, it will generate a sound and light time management strategy that starts at an earlier time and gradually increases the light brightness and volume at a slower rate. For example, at 6:45 a.m., the LED lights will slowly light up at a lower brightness and warm colors, while the gentle sound of running water begins to play. As the time approaches 7:15, the brightness and volume will gradually increase, creating a comfortable wake-up environment.

[0097] Example 6:

[0098] Based on Example 5, the data processing submodule includes:

[0099] A wake-up efficiency value analysis unit is used to analyze the wake-up efficiency value of each natural wake-up process based on the continuous control execution time of each smart home in the sound and light time management strategy executed in each natural wake-up process in the user's natural wake-up record and the corresponding time required for the user to fully wake up;

[0100] The wake-up efficiency value analysis unit works based on the sound and light time management strategy executed in each natural wake-up process in the user's natural wake-up record. The sound and light time management strategy here involves the continuous control execution time of each smart home. For example, in a natural wake-up process, the duration from the LED lamp gradually brightening to reaching a certain brightness, or the time taken for the smart curtains to be fully opened from the beginning, these are the continuous control execution time of the smart home. The corresponding time required for the user to fully wake up refers to the time from the start of the natural wake-up process to the time when the user is truly fully awake. This time can be obtained by rotating the knob or other input methods (such as key input) when the user feels fully awake during the wake-up process, and then statistically inputting it into the wake-up device. The unit analyzes the relationship between these two times to obtain the wake-up efficiency value of each natural wake-up process.

[0101] The home control parameter matrix generation unit is used to generate a home control parameter matrix for all smart home continuous control parameter threads in the sound and light time management strategy executed for all natural wake-up processes in the natural wake-up record. Each smart home has a series of related control parameters, such as the brightness and color temperature of LED lamps, the opening speed and travel of smart curtains, etc. The sequence formed by these parameters changing over time is the continuous control parameter thread. For example, during multiple natural wake-up processes, the sequence of values ​​of the brightness and color temperature of each LED lamp at different time points, as well as the numerical sequence of the opening speed and travel of smart curtains at each stage, etc., all of these smart home continuous control parameter threads are integrated to form the home control parameter matrix. This matrix can comprehensively display the changes in various smart home control parameters during different natural wake-up processes.

[0102] The wake-up efficiency vector generation unit is used to generate a wake-up efficiency vector based on the wake-up efficiency values ​​of all natural wake-up processes in the natural wake-up record. Just as the wake-up efficiency value analysis unit calculates the wake-up efficiency values ​​for each natural wake-up process, these values ​​are arranged in the order of the natural wake-up processes to form the wake-up efficiency vector. For example, the wake-up efficiency value of the first natural wake-up process is 70, the second is 80, the third is 75, and so on. This vector of values ​​can intuitively reflect the changes in wake-up efficiency over different natural wake-up processes.

[0103] The wake-up time vector generation unit is used to generate a specified wake-up time vector based on the user-specified wake-up times of all natural wake-up events in the natural wake-up record. Each user-specified wake-up time, such as "7:00 AM" or "9:30 AM," is arranged in the order of natural wake-up events to form a specified wake-up time vector. This vector can be used to analyze the patterns of user-specified wake-up times and their relationship with other data, such as wake-up efficiency.

[0104] Example 7:

[0105] Based on Example 6, the wake-up efficiency value analysis unit includes:

[0106] a single wake-up efficiency value determining subunit, configured to use the ratio of the continuous control execution time of each smart home in each natural wake-up process to the time required for the user to fully wake up in the corresponding natural wake-up process as the single wake-up efficiency value of each smart home in the corresponding natural wake-up process;

[0107] This subunit is responsible for calculating the single wake-up efficiency value of each smart home in the corresponding natural wake-up process. The specific approach is to compare the total time required for the user to fully wake up during each natural wake-up process with the continuous control execution time of each smart home in the natural wake-up process. For example, in a certain natural wake-up process, it took a total of 20 minutes for the user to fully wake up, and the LED lamp took 15 minutes from the beginning of adjusting the brightness to reaching the set brightness. Then the single wake-up efficiency value of the LED lamp in this natural wake-up process is 15÷20=0.75 (here it is assumed that the ratio is the calculation method of the single wake-up efficiency value). Similarly, for other smart home devices such as smart curtains and aromatherapy machines, their single wake-up efficiency values ​​in this natural wake-up process are calculated separately in this way. In this way, we can understand the individual contribution of each smart home device to the user's wake-up process.

[0108] The single wake-up efficiency value aggregation subunit is used to perform weighted summation of the single wake-up efficiency values ​​of all smart homes in a single natural wake-up process based on the wake-up weights of all smart homes to obtain the wake-up efficiency value of each natural wake-up process.

[0109] Different smart home devices may play different roles in the overall wake-up process, so a wake-up weight is assigned to each smart home device. For example, suppose the wake-up weight of the LED lamp is 0.4, the wake-up weight of the smart curtain is 0.3, the wake-up weight of the aromatherapy device is 0.2, and the total weight of all other devices is 0.1 (these weights are for example purposes only). During a natural wake-up process, the individual wake-up efficiency values ​​of the LED lamp are 0.2, the individual wake-up efficiency values ​​of the smart curtain are 0.5, the individual wake-up efficiency values ​​of the aromatherapy device are 0.8, and the combined individual wake-up efficiency values ​​of all other devices are 0.3. The wake-up efficiency value for this natural wake-up process is 0.2 × 0.4 + 0.5 × 0.3 + 0.8 × 0.2 + 0.3 × 0.1 = 0.42. This weighted summation comprehensively considers the different roles of each smart home device in the wake-up process, resulting in a wake-up efficiency value that more accurately reflects the overall wake-up effect.

[0110] Example 8:

[0111] Based on Example 5, the correlation analysis submodule includes:

[0112] A matrix dimensionality reduction and derivation unit is used to perform dimensionality reduction processing on the home control parameter matrix to obtain a home control parameter dimensionality reduction matrix, generate a control parameter dimensionality reduction function for each smart home based on the control parameter dimensionality reduction value sequence of each smart home in the home control parameter dimensionality reduction matrix, and generate a home control parameter dimensionality reduction first-order derivative matrix based on the first-order derivative values ​​of the control parameter dimensionality reduction functions of all smart homes at all times;

[0113] Because the original home control parameter matrix may contain data with multiple dimensions, dimensionality reduction is necessary to more easily analyze its relationship with the wake-up efficiency vector (for example, by merging the values ​​of the same control parameter at adjacent moments to reduce the amount of data in the matrix's time dimension). This results in a reduced-dimensional home control parameter matrix. For example, the original matrix may contain multiple parameter dimensions for various smart home devices. After dimensionality reduction, some dimensions that have less impact on the analysis are removed, making the data more concise while retaining key information.

[0114] Based on the home control parameter reduction matrix, the reduced-dimensionality values ​​of each smart home device at different times form a sequence, which is used to generate a control parameter reduction function for each smart home device. For example, the sequence of reduced-dimensionality values ​​of the brightness of an LED lamp over time can be fitted with a function to describe the change pattern of the reduced-dimensionality values ​​over time.

[0115] Next, the first-order derivatives of the dimensionality reduction functions for all smart home control parameters are calculated at all times. These first-order derivatives reflect the rate of change of the function. These first-order derivatives are used to generate a dimensionality reduction matrix of home control parameters. This matrix shows the rate of change of each smart home device's control parameters at different times, providing an important basis for subsequent analysis.

[0116] a first influencing factor calculation unit, configured to analyze at least one common eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension, and obtain a first influencing factor of the smart home control parameters on the user wake-up process based on the cosine similarity between the common eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension and the eigenvector of the wake-up efficiency vector in the time dimension;

[0117] These shared feature vectors can reflect the common change characteristics of home control parameters in the time dimension. For example, there may be a feature vector that reflects that the control parameters of multiple smart home devices show similar trends in a certain time period.

[0118] At the same time, the eigenvector of the wake-up efficiency vector in the time dimension is determined. By calculating the cosine similarity between the shared eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension and the eigenvector of the wake-up efficiency vector in the time dimension, the first influencing factor of the smart home control parameters on the user wake-up process is obtained. Cosine similarity measures the degree of similarity between two vectors. A higher similarity indicates a closer correlation between changes in home control parameters and wake-up efficiency, and a larger first influencing factor, indicating a more significant impact of the smart home control parameters on the user wake-up process.

[0119] The second impact factor calculation unit is configured to obtain a second impact factor of the user-specified wake-up time on the user's wake-up process based on the correlation analysis results between the specified wake-up time vector and the wake-up efficiency vector. The second impact factor of the user-specified wake-up time on the user's wake-up process is determined by a specific analysis method, such as calculating the correlation coefficient (or cosine similarity) between the two. If there is a strong correlation between the specified wake-up time and the wake-up efficiency, for example, if the wake-up efficiency is higher at certain specific times, the corresponding second impact factor will be larger, indicating that the specified wake-up time has a greater impact on the wake-up process.

[0120] The wake-up difficulty assessment unit is used to assess the user's wake-up difficulty based on the user's natural wake-up history. For example, the wake-up difficulty level can be determined by analyzing the wake-up time required by the user during multiple natural wake-up processes. If a user frequently takes a long time to fully wake up, the user's wake-up difficulty level can be considered high.

[0121] The personalized impact factor calibration unit is used to determine the first personalized impact factor of the smart home control parameters on the user's wake-up process and the second personalized impact factor of the user-specified wake-up time on the user's wake-up process based on the first impact factor of the smart home control parameters on the user's wake-up process, the second personalized impact factor of the user-specified wake-up time on the user's wake-up process, and the user's wake-up difficulty. For example, if the user's wake-up difficulty is high, the first impact factor and the second impact factor may be appropriately adjusted to make the impact of the smart home control parameters and the specified wake-up time on the wake-up process more consistent with the user's actual situation, thereby determining the first personalized impact factor of the smart home control parameters on the user's wake-up process and the second personalized impact factor of the user-specified wake-up time on the user's wake-up process, providing more accurate data support for the subsequent generation of an audio-visual time management strategy that better meets user needs.

[0122] Example 9:

[0123] Based on Example 8, the first impact factor calculation unit includes:

[0124] The first eigenvalue decomposition subunit is used to determine the covariance matrix of the reduced-dimensional first-order derivative matrix of the home control parameters. Eigenvalue decomposition is performed on the covariance matrix of the reduced-dimensional first-order derivative matrix of the home control parameters to obtain at least one eigenvalue and a corresponding eigenvector. Each eigenvector is then treated as a shared eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension. For example, if changes in the control parameters of the LED lamps are related to changes in the control parameters of the smart curtains in some way, the covariance matrix can reflect this relationship. Eigenvalue decomposition is then performed on the covariance matrix to obtain at least one eigenvalue and a corresponding eigenvector. These eigenvectors can reflect the shared characteristics of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension, so each eigenvector is treated as a shared eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension. For example, a certain eigenvector may reflect the changing trend of multiple smart home control parameters within a specific time period.

[0125] The vector time dimension expansion subunit constructs a lagged feature matrix of the wake-up efficiency vector using a sliding window method. This matrix is ​​mean-normalized and variance-normalized to obtain a standardized lagged feature matrix. The sliding window acts like a box that moves across the wake-up efficiency vector, each time enclosing a certain number of elements. A new matrix, the lagged feature matrix, is constructed based on these elements. For example, if the window size is 3, it moves across the wake-up efficiency vector sequentially, each time taking three consecutive elements to construct a new row vector. All these row vectors form the lagged feature matrix. This lagged feature matrix is ​​then mean-normalized and variance-normalized to bring the data to a consistent scale for ease of subsequent analysis. This process results in a standardized lagged feature matrix that more accurately reflects the characteristics of the wake-up efficiency vector along the time dimension.

[0126] The second eigenvalue decomposition subunit is used to perform eigenvalue decomposition on the covariance matrix of the standardized lagged feature matrix to obtain all eigenvalues ​​and corresponding eigenvectors of the covariance matrix of the standardized lagged feature matrix, and use the eigenvector corresponding to the maximum eigenvalue among all the eigenvalues ​​and corresponding eigenvectors of the covariance matrix of the standardized lagged feature matrix as the eigenvector of the wake-up efficiency vector in the time dimension; this is because the eigenvector corresponding to the maximum eigenvalue contains the most important change information in the standardized lagged feature matrix and can represent the key features of the wake-up efficiency vector in the time dimension.

[0127] The cosine similarity calculation subunit calculates the cosine similarity of the time dimension of each shared eigenvector with a corresponding eigenvalue greater than a threshold and the wake-up efficiency vector. The threshold is set to filter out shared eigenvectors that significantly influence the results. Cosine similarity measures the degree of directional similarity between two vectors, with values ​​ranging from -1 to 1, where values ​​closer to 1 indicate greater similarity. By calculating cosine similarity, we can understand the degree of similarity between the shared features of the reduced first-order derivative matrix of home control parameters and the features of the wake-up efficiency vector.

[0128] The correlation synthesis subunit is used to calculate the weight value of each shared eigenvector whose corresponding eigenvalue is greater than the threshold based on all eigenvalues ​​greater than the threshold, that is: the ratio of a single eigenvalue greater than the threshold to the sum of all eigenvalues ​​greater than the threshold is used as the weight value of a single shared eigenvector whose corresponding eigenvalue is greater than the threshold; the larger the eigenvalue, the higher the weight of the corresponding shared eigenvector because it contains more important information.

[0129] Based on the weights of all shared eigenvectors whose corresponding eigenvalues ​​are greater than a threshold, the cosine similarity of the eigenvectors of each shared eigenvector with the wake-up efficiency vector in the time dimension is weighted summed to obtain the first impact factor of the smart home control parameters on the user wake-up process. This first impact factor comprehensively considers the similarity between the home control parameters and the wake-up efficiency vector in the time dimension and the importance of each shared eigenvector, and can more accurately reflect the impact of smart home control parameters on the user wake-up process.

[0130] Example 10:

[0131] Based on Example 8, the personalized impact factor calibration unit includes:

[0132] The adjustment coefficient determination subunit is used to determine the average wake-up time based on the user's natural wake-up records. This requires counting the time it takes for the user to wake up naturally from the beginning to the end, and then calculating the average of these times. For example, after counting multiple natural wake-up processes, the average wake-up time is 15 minutes.

[0133] The first adjustment coefficient is determined based on the average wake-up time and the user's wake-up difficulty, which is:

[0134] First adjustment coefficient = 1 + (user's wake-up difficulty - average wake-up time) × positive calibration factor;

[0135] The positive calibration factor has a value range of [0, 2], and a value of 0.5 is recommended here. The unit of the user's wake-up difficulty is minutes.

[0136] The second adjustment coefficient is determined based on the user's wake-up difficulty and difficulty sensitivity coefficient, namely:

[0137] The second adjustment coefficient=1-difficulty sensitivity coefficient (1-user's wake-up difficulty).

[0138] The difficulty sensitivity coefficient is a pre-set value between 0 and 1, with a recommended value of 0.3. It measures the impact of wakeup difficulty on the adjustment coefficient. For example, if the user wakes up with a high difficulty and a high difficulty sensitivity coefficient, the second adjustment coefficient will also increase accordingly.

[0139] The first impact factor personalized calibration subunit is used to calculate the product of the first impact factor of the smart home control parameter on the user's wake-up process, the first adjustment coefficient, and the control parameter importance weight as the first personalized impact factor of the smart home control parameter on the user's wake-up process. By multiplying these three factors, the first impact factor can be calibrated based on the user's average wake-up time, wake-up difficulty, and the importance of the control parameter itself to better suit the user's individual situation. For example, if the first impact factor is 0.6, the first adjustment coefficient is 1.2, and the control parameter importance weight is 0.8, then the first personalized impact factor is 0.6 × 1.2 × 0.8 = 0.576.

[0140] The second influencing factor personalized calibration subunit is used to take the product of the second personalized influencing factor of the user-specified wake-up time on the user wake-up process and the second adjustment coefficient and the time window adjustment coefficient as the second personalized influencing factor of the user-specified wake-up time on the user wake-up process.

[0141] The time window adjustment coefficient is related to the time range of the user-set wake-up time. For example, within the time period of 6-8 am, the impact of different times on the wake-up effect may be different. The time window adjustment coefficient is used to reflect this difference.

[0142] In this way, the second personalized impact factor is calibrated by comprehensively considering the user's wake-up difficulty, difficulty sensitivity coefficient, and time window factors. For example, if the second personalized impact factor is 0.7, the second adjustment coefficient is 1.3, and the time window adjustment coefficient is 0.9, then the calibrated value of the second personalized impact factor is 0.7 × 1.3 × 0.9 = 0.819. The two personalized impact factors obtained in this way can more accurately reflect the user's personalized characteristics in terms of smart home control parameters and prescribed wake-up times, providing a basis for generating more optimized sound and light time management strategies.

[0143] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalents, the present invention is intended to include these modifications and variations.

Claims

1. A natural wake-up system based on offline speech recognition and sound and light time management, characterized by: include: An offline speech recognition module is used to recognize the user's voice commands received by the microphone in an offline state; The main control module is used to obtain a first personalized impact factor of the smart home control parameters on the user's wake-up process and a second personalized impact factor of the user's specified wake-up time on the user's wake-up process based on the home control parameter matrix, wake-up efficiency vector, and specified wake-up time vector generated using the user's natural wake-up record, and to generate an acoustic and optical time management strategy by combining artificial intelligence and the user's voice command; Time management module, used to record real-time time; RF communication module, used to send control signals to smart home devices that can receive RF signals based on the sound and light time management strategy and real-time time; An infrared signal transmitting module is used to send a control signal to a smart home that can receive infrared control signals based on the sound and light time management strategy, real-time time, and the smart home remote control code stored in the infrared remote control code library; The audio playback module is used to play built-in audio files through the speaker based on the sound and light time management strategy and real time.

2. The natural wake-up system based on offline speech recognition and sound and light time management according to claim 1 is characterized in that: Also includes: Rechargeable battery, used to provide power for the microphone, offline voice recognition module, main control module, time management module, RF communication module, infrared remote control code library, infrared signal transmission module, audio playback module, speaker, power management module, and LED display module; The power management module is used to send a reminder signal when the remaining capacity of the rechargeable battery is lower than a threshold value, and at the same time, adjust the working mode of the main control module to the power saving mode; LED display module, used to display real-time time, remaining battery power, time information in the latest voice command, and the working status of all communicative smart devices; The storage module is used to store all received voice commands, the continuous working status of all communicative smart devices, and all currently determined sound and light time management strategies.

3. The natural wake-up system based on offline speech recognition and sound and light time management according to claim 1 is characterized in that: Smart home appliances that can receive RF signals include LED lamps, smart curtains, and aromatherapy machines; The LED lamp gradually lights up and changes color temperature based on the control signal received; The smart curtains gradually open based on the control signal received; The aroma diffuser starts working based on the received control signal.

4. The natural wake-up system based on offline speech recognition and sound and light time management according to claim 1 is characterized in that: The smart home that can receive RF signals is an air conditioner, which gradually adjusts the temperature to a corresponding temperature based on the received control signal.

5. The natural wake-up system based on offline voice recognition and sound and light time management according to claim 1 is characterized in that: Main control module, including: A data processing submodule is used to generate a home control parameter matrix, a wake-up efficiency vector, and a prescribed wake-up time vector based on the user's natural wake-up records; a correlation analysis submodule for generating a first personalized impact factor of the smart home control parameters on the user's wake-up process and a second personalized impact factor of the user-specified wake-up time on the user's wake-up process based on the correlation analysis results between the home control parameter matrix and the wake-up efficiency vector and the correlation analysis results between the specified wake-up time vector and the wake-up efficiency vector; The sound and light time management strategy generation submodule is used to obtain the sound and light time management strategy based on the first personalized influence factor of the smart home control parameter on the user wake-up process, the second personalized influence factor of the user-specified wake-up time on the user wake-up process, the latest user-specified wake-up time represented by the latest received voice command, and the pre-built sound and light time management strategy generation model.

6. The natural wake-up system based on offline voice recognition and sound and light time management according to claim 5 is characterized in that: Data processing submodule, including: A wake-up efficiency value analysis unit is used to analyze the wake-up efficiency value of each natural wake-up process based on the continuous control execution time of each smart home in the sound and light time management strategy executed in each natural wake-up process in the user's natural wake-up record and the corresponding time required for the user to fully wake up; A home control parameter matrix generation unit is used to generate a home control parameter matrix based on the continuous control parameter threads of all smart homes in the sound and light time management strategy executed in all natural wake-up processes in the natural wake-up record; a wake-up efficiency vector generating unit, configured to generate a wake-up efficiency vector based on the wake-up efficiency values ​​of all natural wake-up processes in the natural wake-up record; The wake-up time vector generating unit is configured to generate a specified wake-up time vector based on the user-specified wake-up time of all natural wake-up processes in the natural wake-up record.

7. The natural wake-up system based on offline voice recognition and sound and light time management according to claim 6, characterized in that: Wake-up efficiency value analysis unit, including: a single wake-up efficiency value determining subunit, configured to use the ratio of the continuous control execution time of each smart home in each natural wake-up process to the time required for the user to fully wake up in the corresponding natural wake-up process as the single wake-up efficiency value of each smart home in the corresponding natural wake-up process; The single wake-up efficiency value aggregation subunit is used to perform weighted summation of the single wake-up efficiency values ​​of all smart homes in a single natural wake-up process based on the wake-up weights of all smart homes to obtain the wake-up efficiency value of each natural wake-up process.

8. The natural wake-up system based on offline voice recognition and sound and light time management according to claim 5, characterized in that: Correlation analysis submodule, including: A matrix dimensionality reduction and derivation unit is used to perform dimensionality reduction processing on the home control parameter matrix to obtain a home control parameter dimensionality reduction matrix, generate a control parameter dimensionality reduction function for each smart home based on the control parameter dimensionality reduction value sequence of each smart home in the home control parameter dimensionality reduction matrix, and generate a home control parameter dimensionality reduction first-order derivative matrix based on the first-order derivative values ​​of the control parameter dimensionality reduction functions of all smart homes at all times; a first influencing factor calculation unit, configured to analyze at least one common eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension, and obtain a first influencing factor of the smart home control parameters on the user wake-up process based on the cosine similarity between the common eigenvector of the reduced-dimensional first-order derivative matrix of the home control parameters in the time dimension and the eigenvector of the wake-up efficiency vector in the time dimension; A second impact factor calculation unit is used to obtain a second impact factor of the user-specified wake-up time on the user's wake-up process based on a correlation analysis result between the specified wake-up time vector and the wake-up efficiency vector; a wake-up difficulty assessment unit, configured to assess the user's wake-up difficulty based on the user's natural wake-up record; The personalized influence factor calibration unit is used to determine the first personalized influence factor of the smart home control parameters on the user wake-up process and the second personalized influence factor of the user-specified wake-up time on the user wake-up process based on the first influence factor of the smart home control parameters on the user wake-up process and the second personalized influence factor of the user-specified wake-up time on the user wake-up process and the user's wake-up difficulty.

9. The natural wake-up system based on offline voice recognition and sound and light time management according to claim 8, characterized in that: The first impact factor calculation unit includes: A first eigenvalue decomposition subunit is configured to determine a covariance matrix of a reduced-dimensional first-order derivative matrix of home control parameters, perform eigenvalue decomposition on the covariance matrix of the reduced-dimensional first-order derivative matrix of home control parameters, obtain at least one eigenvalue and a corresponding eigenvector, and use each eigenvector as a common eigenvector of the reduced-dimensional first-order derivative matrix of home control parameters in a time dimension; A vector time dimension expansion subunit is used to construct a lag feature matrix of the wake-up efficiency vector based on a sliding window method, perform mean zeroing and variance normalization on the lag feature matrix of the wake-up efficiency vector, and obtain a standardized lag feature matrix; A second eigenvalue decomposition subunit is used to perform eigenvalue decomposition on the covariance matrix of the standardized lag feature matrix to obtain all eigenvalues ​​and corresponding eigenvectors of the covariance matrix of the standardized lag feature matrix, and use the eigenvector corresponding to the maximum eigenvalue among all eigenvalues ​​and corresponding eigenvectors of the covariance matrix of the standardized lag feature matrix as the eigenvector of the wake-up efficiency vector in the time dimension; A cosine similarity calculation subunit, configured to calculate the cosine similarity of the feature vectors of each common feature vector whose corresponding feature value is greater than a threshold and the wake-up efficiency vector in the time dimension; The correlation synthesis subunit is used to calculate the weight value of each common eigenvector whose corresponding eigenvalue is greater than the threshold based on all eigenvalues ​​greater than the threshold, and based on the weight values ​​of all common eigenvectors whose corresponding eigenvalue is greater than the threshold, perform weighted summation of the cosine similarities of the eigenvectors of each common eigenvector whose corresponding eigenvalue is greater than the threshold and the wake-up efficiency vector in the time dimension, to obtain the first influencing factor of the smart home control parameter on the user wake-up process.

10. The natural wake-up system based on offline voice recognition and sound and light time management according to claim 8, characterized in that: Personalized impact factor calibration unit, including: an adjustment coefficient determination subunit, configured to determine an average wake-up time based on the user's natural wake-up records, determine a first adjustment coefficient based on the average wake-up time and the user's wake-up difficulty, and determine a second adjustment coefficient based on the user's wake-up difficulty and difficulty sensitivity coefficient; A first influencing factor personalized calibration subunit is configured to use the product of the first influencing factor of the smart home control parameter on the user wake-up process, the first adjustment coefficient, and the control parameter importance weight as the first personalized influencing factor of the smart home control parameter on the user wake-up process; The second influencing factor personalized calibration subunit is used to take the product of the second personalized influencing factor of the user-specified wake-up time on the user wake-up process and the second adjustment coefficient and the time window adjustment coefficient as the second personalized influencing factor of the user-specified wake-up time on the user wake-up process.

Images