Wake-up processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a wake-up processing method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining a recommended wake-up mode for a target wake-up user through a wake-up large model when the target wake-up user is in a rest scene, and determining that the target wake-up user is in a wake-up triggering state; and performing rest wake-up processing on the target wake-up user based on the recommended wake-up mode. According to the method, the recommended wake-up mode adaptive to the target wake-up user is determined through the wake-up large model, a more humanized wake-up mode can be provided, and the wake-up efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of smart home device control technology, specifically to a wake-up processing method, device, storage medium, and electronic device. Background Technology

[0002] During kindergarten and primary school, children are in a critical period of growth and development, and sufficient sleep is essential for their physical and mental health. However, children in this age group generally have weaker biological clock regulation abilities, higher sleep needs, and insufficient morning wakefulness, leading parents to spend a lot of energy dealing with their children's difficulty getting up in the morning. Traditional methods of waking children up, such as suddenly shouting, forcibly pulling, or continuously ringing a bell, are not humane and can easily have negative psychological and physiological effects on children, resulting in low efficiency in waking them up. Summary of the Invention

[0003] This application provides a wake-up processing method, apparatus, storage medium, and electronic device, which can improve the efficiency of waking up users.

[0004] In a first aspect, embodiments of this application provide a wake-up processing method, including:

[0005] When the target wake-up user is in a resting scenario, obtain the recommended wake-up mode for the target wake-up user using the wake-up big model;

[0006] Once it is determined that the user is in a wake-up triggered state, a rest wake-up process is performed on the target wake-up user based on the recommended wake-up mode.

[0007] In some implementations, obtaining the recommended wake-up mode for the target wake-up user using a wake-up model includes:

[0008] Monitor the target wake-up elements for the target wake-up user;

[0009] Based on the wake-up model, a wake-up mode recommendation process is performed on the target wake-up user according to the target wake-up elements to obtain a recommended wake-up mode for the target wake-up user.

[0010] In some implementations, the step of performing wake-up pattern recommendation processing on the target wake-up user based on the target wake-up elements, to obtain a recommended wake-up pattern for the target wake-up user, includes:

[0011] Based on the wake-up model, environmental element information, user attribute information, and user sleep information are extracted from the target wake-up elements.

[0012] Based on the environmental element information, the user attribute information, and the user sleep information, a wake-up mode recommendation process is performed on the target wake-up user to generate the recommended wake-up mode.

[0013] In some implementations, the step of generating the recommended wake-up mode by performing wake-up mode recommendation processing on the target wake-up user based on the environmental element information, the user attribute information, and the user sleep information includes:

[0014] A comprehensive reference wake-up feature vector is obtained by fusing multi-dimensional features based on the environmental element information, user attribute information, and user sleep information using a wake-up model; and a user wake-up environment feature vector is obtained by parsing the user wake-up environment based on the comprehensive reference wake-up feature vector.

[0015] Based on the comprehensive reference wake-up feature vector and the user wake-up environment feature vector, wake-up strategy element reasoning is performed to obtain wake-up time window information, wake-up method information, wake-up intensity information, and context response information;

[0016] The recommended wake-up mode is obtained by comprehensively processing the wake-up mode based on the wake-up time window information, the wake-up method information, the wake-up intensity information, and the context response information.

[0017] In some implementations, the monitoring of target wake-up elements for a target wake-up user includes:

[0018] Collect environmental element information of the resting scene of the target awakened user, as well as user attribute information and user sleep information of the target awakened user;

[0019] The target wake-up element is determined based on the environmental element information, the user attribute information, and the user sleep information.

[0020] In some implementations, determining the target wake-up element based on the environmental element information, the user attribute information, and the user sleep information includes:

[0021] Based on the environmental element information, the user attribute information, and the user sleep information, a wake-up element completion questionnaire is generated for the target wake-up user, and the wake-up element completion questionnaire is provided to the target wake-up user.

[0022] The target wake-up element is determined by completing a questionnaire based on the wake-up element.

[0023] In some implementations, after performing rest-wake processing on the target wake-up user based on the recommended wake-up mode, the method further includes:

[0024] Push wake-up events to preset electronic devices;

[0025] The system receives a wake-up stop operation from the preset electronic device in response to the wake-up event, thereby stopping the wake-up process for the target wake-up user.

[0026] In some implementations, after performing rest-wake processing on the target wake-up user based on the recommended wake-up mode, the method further includes:

[0027] The system detects audio in the resting scenario. If the audio matches a preset audio for disabling wake-up function, the system disables wake-up processing for the target user.

[0028] In some implementations, after performing rest-wake processing on the target wake-up user based on the recommended wake-up mode, the method further includes:

[0029] Collect the behavioral state information of the target wake-up user. If the behavioral state information indicates that the target wake-up user is in a wake-up state, then disable the wake-up process for the target wake-up user.

[0030] In some embodiments, the wake-up processing method provided in this application further includes:

[0031] The system detects audio in the resting scenario. If the audio matches a preset audio for activating the wake-up function, it initiates wake-up processing for the target user.

[0032] In some embodiments, the wake-up processing method provided in this application further includes:

[0033] A wake-up setting event is pushed to a preset electronic device, and the wake-up start operation of the preset electronic device in response to the wake-up setting event is received to start the wake-up process for the target wake-up user.

[0034] Secondly, embodiments of this application also provide a wake-up processing device, including:

[0035] The acquisition module is used to acquire the recommended wake-up mode for the target wake-up user using the wake-up big model when the target wake-up user is in a resting scenario;

[0036] The wake-up module is used to determine that the user is in a wake-up triggered state and to perform rest wake-up processing on the target wake-up user based on the recommended wake-up mode.

[0037] Thirdly, embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, which, when run on a computer, causes the computer to perform a wake-up processing method as provided in any embodiment of this application.

[0038] Fourthly, embodiments of this application also provide an electronic device, including a processor and a memory, wherein the memory has a computer program, and the processor executes a wake-up processing method as provided in any embodiment of this application by calling the computer program.

[0039] The technical solution provided in this application, when the target wake-up user is in a resting scenario, obtains a recommended wake-up mode for the target wake-up user using a wake-up model, determines that the user is in a wake-up triggered state, and performs rest wake-up processing on the target wake-up user based on the recommended wake-up mode. This application, by determining the recommended wake-up mode suitable for the target wake-up user through a wake-up model, can provide a more user-friendly wake-up method and improve wake-up efficiency. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic flowchart of a wake-up processing method provided in an embodiment of this application.

[0042] Figure 2 This is a schematic diagram of the wake-up processing device provided in an embodiment of this application.

[0043] Figure 3 This is a schematic diagram of a first structure of an electronic device provided in an embodiment of this application.

[0044] Figure 4 This is a schematic diagram of a second structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the protection scope of this application.

[0046] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0047] During kindergarten and primary school, children are in a critical period of growth and development, and sufficient sleep is essential for their physical and mental health. However, children in this age group generally have weaker biological clock regulation abilities, higher sleep needs, and insufficient morning wakefulness, leading parents to spend a lot of energy dealing with their children's difficulty getting up in the morning. Traditional methods of waking children up, such as suddenly shouting, forcibly pulling, or continuously ringing a bell, are not humane and can easily have negative psychological and physiological effects on children, resulting in low efficiency in waking them up.

[0048] To address the aforementioned technical problems, embodiments of this application provide a wake-up processing method. The execution entity of this wake-up processing method can be the wake-up processing device provided in these embodiments, or an electronic device integrating the wake-up processing device. The wake-up processing device can be implemented in hardware or software. The electronic device can be a smart home device, such as a smart camera, smart speaker, smart robot, smart TV, or smart door lock. The electronic device can also be a terminal device, such as a smartphone, tablet computer, PDA, laptop computer, or desktop computer.

[0049] Please see Figure 1 , Figure 1 This is a schematic flowchart of a wake-up processing method provided in an embodiment of this application. The specific flow of the wake-up processing method provided in this embodiment of the application can be as follows:

[0050] S110. When the target wake-up user is in a resting scenario, obtain the recommended wake-up mode for the target wake-up user using the wake-up big model.

[0051] In this context, a target arousal user refers to an individual who needs to be awakened at a specific time or in a specific situation. For example, in a scenario where children in kindergarten and primary school typically need to get up early for school, the target arousal user could be a child in kindergarten or primary school.

[0052] Among them, rest scenarios refer to scenarios where users are in a relaxed, sleeping, or low-activity state. For example, a user taking a nap at a table, resting with their eyes closed on a sofa, or sleeping.

[0053] Among them, the wake-up big model refers to an artificial intelligence model based on deep learning that generates personalized wake-up strategies for target users through multimodal data fusion and dynamic reasoning.

[0054] The recommended wake-up mode refers to a combination of wake-up strategies generated by a wake-up model, tailored to the target user in a specific resting scenario. For example, this recommended wake-up mode could be voice wake-up or a combination of voice and light wake-up. Furthermore, in this recommended wake-up mode, when using voice or light wake-up, the sound type, volume, light parameters (including light frequency and color), and the timing of the sound and light combination are all personalized based on the target user.

[0055] In this embodiment, the wake-up model provides the most suitable wake-up method for the user based on the target user's current resting scenario, and serves as the recommended wake-up mode.

[0056] For example, the recommended wake-up mode could wake the user by using gradually increasing, gentle music, mild voice prompts, or simulated changes in natural light, rather than by suddenly blasting a loud alarm clock that might startle the user. For instance, the recommended wake-up mode could involve lights gradually brightening at a rate of 10% per minute to simulate sunrise; simultaneously, soft birdsong could be played, starting at 30 decibels and increasing by 5 decibels per minute until reaching 50 decibels.

[0057] In this embodiment, a large wake-up model can be used to provide personalized and suitable wake-up solutions for target wake-up users in specific rest scenarios, thereby improving the user experience.

[0058] In some implementations, prior to step S110, user information can be collected via sensors to determine whether the user is in a resting state. For example, accelerometers and gyroscopes in smartwatches, mobile phones, or smart home devices can monitor the user's activity level. If the user is detected to remain still or move slowly for an extended period, it can be determined that the user is in a resting state. Another example is monitoring the user's heart rate changes via wearable devices. During rest or sleep, the heart rate is typically low and stable; monitoring the user's heart rate via wearable devices can help determine whether the user is in a resting state. Yet another example is capturing user images via a smart home camera; if the user is detected to remain still for an extended period with their eyes closed, it can be determined that the user is in a resting state.

[0059] S120. Determine that the user is in a wake-up triggered state, and perform rest wake-up processing on the target wake-up user based on the recommended wake-up mode.

[0060] The wake-up trigger state refers to the state where the wake-up trigger conditions are met, requiring preparation or initiation of wake-up processing. These trigger conditions may be a preset time point (such as a set alarm time), the triggering of an external event (such as receiving an emergency message), or monitoring of the user's state (such as detecting a suitable wake-up phase in the user's sleep cycle). Wake-up processing is only required when these trigger conditions are met.

[0061] In this embodiment, after obtaining the recommended wake-up mode for the target wake-up user and determining that the user is in a wake-up triggered state, the wake-up process will be performed on the target wake-up user according to the recommended wake-up mode.

[0062] In practice, this application is not limited by the execution order of the described steps. Without causing conflicts, some steps may be performed in other orders or simultaneously.

[0063] As can be seen from the above, the wake-up processing method provided in this application, when the target wake-up user is in a resting scenario, obtains the recommended wake-up mode for the target wake-up user using a wake-up big model, determines that the user is in a wake-up triggered state, and performs rest wake-up processing on the target wake-up user based on the recommended wake-up mode. In this application, determining the recommended wake-up mode suitable for the target wake-up user through a wake-up big model can provide a more user-friendly wake-up method and improve wake-up efficiency.

[0064] In some implementations, when obtaining the recommended wake-up mode for the target wake-up user using the wake-up big model, the target wake-up elements for the target wake-up user can be monitored, and based on the wake-up big model, the wake-up mode recommendation process can be performed on the target wake-up user according to the target wake-up elements to obtain the recommended wake-up mode for the target wake-up user.

[0065] Target wake-up factors refer to various factors that directly influence the wake-up effect and experience of the user. These factors cover multiple aspects, including the user's resting environment, the user's own attributes, and the user's sleep state. Together, they constitute a set of key information that determines how to wake the user in the most appropriate way. By monitoring these factors, suitable wake-up modes can be recommended to users more accurately.

[0066] In this embodiment, when obtaining the recommended wake-up mode, it is necessary to monitor and collect the relevant characteristics or conditions of the target wake-up user to summarize the target wake-up elements. The target wake-up elements are the key factors affecting the selection of the wake-up mode. Based on the target wake-up elements, the user's current real state and needs information can be obtained. Then, the monitored target wake-up elements are used as input and passed to the wake-up big model. The wake-up big model uses its internal knowledge and algorithms to analyze and process these elements, thereby deriving a recommended wake-up mode that meets the characteristics and needs of the target wake-up user. This recommended wake-up mode can be used as the basis for subsequent wake-up operations.

[0067] In one implementation, the wake-up model can be trained using the following steps:

[0068] (1) Obtain the basic large language model and create an initial large wake-up model for the rest wake-up scenario based on the basic large language model;

[0069] Among them, basic large language models include, but are not limited to, large models in the field of natural language processing (NLP), such as GPT-3, GPT-4, ChatGPT, BERT, and RoBERTa.

[0070] This fundamental large language model can understand the semantic information of various target wakefulness elements in the input, such as the specific contexts and needs represented by words like "early morning," "child," and "gentle music." Simultaneously, it can generate natural and fluent text for outputting detailed descriptions of recommended wakefulness patterns.

[0071] For example, when recommending wake-up patterns based on target wake-up elements, this basic large language model can understand the specific needs expressed by the target wake-up elements input by the user. For instance, if a user inputs "My child always has trouble getting up in the morning, likes to listen to soft music, and wants the bedroom lights to gradually brighten," the basic large language model can understand these elements and transform them into feature information that can be used for subsequent processing. When generating recommended wake-up patterns, the model can describe the recommended wake-up patterns in natural language, such as "It is recommended to start at 7 a.m. with soft piano music as the wake-up sound, while the bedroom lights gradually brighten over 10 minutes."

[0072] Furthermore, the basic large language model has accumulated rich knowledge during its learning process, covering multiple fields including sleep science, child psychology, and music styles. This knowledge can provide theoretical support and reference for wake-up pattern recommendations. Moreover, the basic large language model possesses a certain degree of knowledge transfer capability, enabling it to apply knowledge learned in one task to another related task. When recommending wake-up patterns, the basic large language model can utilize its knowledge reserves, combined with target wake-up elements, to provide users with scientifically sound suggestions. For example, based on sleep science knowledge, the model knows that suddenly waking a child during deep sleep can affect their mood and mental state throughout the day; therefore, it will consider a gradual awakening approach when recommending wake-up patterns. Simultaneously, the model can recommend suitable music types and lighting changes based on the psychological characteristics of children of different age groups, achieving effective knowledge transfer.

[0073] (2) Obtain the target wake-up elements of the sample and label the target wake-up elements with recommended wake-up mode tags;

[0074] (3) Use the sample target wake-up elements to train the initial wake-up model for at least one round;

[0075] (4) During the model forward propagation training process, the prediction and recommendation wake-up mode is determined based on the sample target wake-up elements by the initial wake-up large model;

[0076] (5) During the backpropagation training of the model, the recommended wake-up mode generation loss is determined based on the predicted recommended wake-up mode and the recommended wake-up mode label. The recommended wake-up mode generation loss is used to adjust the model parameters of the initial wake-up model until the initial wake-up model finishes training and the wake-up model is obtained.

[0077] Specifically, the recommended wake-up mode generation loss is calculated using a preset model loss formula based on the predicted recommended wake-up mode and the recommended wake-up mode label. This preset model loss formula can be one or more of the following fitting techniques: contrastive loss, cross-entropy loss, hinge loss, etc.

[0078] Optionally, the initial wake-up conditions for terminating training on the large model may include conditions such as the loss function value being less than or equal to a preset loss function threshold, or the number of iterations reaching a preset threshold. Specific training termination conditions can be determined based on actual circumstances and are not specifically limited here.

[0079] The wake-up model can be trained based on the basic large language model. By leveraging the language understanding and generation capabilities, knowledge reserves and transfer capabilities, and personalized recommendation potential of the basic large language model, combined with appropriate training methods and precautions, it can provide users with accurate and personalized recommendation wake-up modes.

[0080] The above-mentioned method generates a corresponding recommended wake-up mode based on the target wake-up elements input by the user. This method can match the recommended wake-up mode with the characteristics and needs of the target wake-up user, making the provided wake-up method more user-friendly and thus improving wake-up efficiency.

[0081] In some implementations, when performing wake-up mode recommendation processing on the target wake-up user based on the wake-up big model and target wake-up elements to obtain a recommended wake-up mode for the target wake-up user, environmental element information, user attribute information, and user sleep information can be extracted from the target wake-up elements based on the wake-up big model, and a recommended wake-up mode can be generated based on the environmental element information, user attribute information, and user sleep information.

[0082] Among them, environmental element information refers to various types of information related to the external environment in which the target user is awakened, such as lighting conditions, sound environment, temperature, and humidity.

[0083] User attribute information refers to information about the characteristics of the target user, which helps the model better understand individual differences and thus provide more personalized wake-up pattern recommendations. This includes information such as age, gender, occupation, and personal preferences.

[0084] Among these, user sleep information reflects the sleep state and quality of the target user, and is crucial for determining the appropriate wake-up mode. This includes information such as sleep stage, sleep duration, and sleep quality.

[0085] In this embodiment, the target wake-up elements include various types of wake-up-related information, but this information may be complex and unclassified. The wake-up big data model accurately extracts environmental element information, user attribute information, and user sleep information from these elements. That is, the wake-up big data model filters and organizes the raw data, classifying different types of information to enable more targeted analysis and processing later. After extracting the environmental element information, user attribute information, and user sleep information, the wake-up big data model comprehensively considers the interrelationships and influences between these information, using its internal learning mechanism and algorithms to recommend wake-up modes for the target wake-up user. This process is similar to selecting one or more wake-up modes most suitable for the target wake-up user from numerous wake-up modes based on different combinations of conditions. After recommendation processing, the wake-up big data model generates recommended wake-up modes for the target wake-up user. These recommended wake-up modes are usually presented in a specific and operable form, such as detailed wake-up time arrangements, the type of wake-up device used, the volume and rhythm of the wake-up sound, and the brightness and color changes of the lights, facilitating implementation by electronic devices or related systems.

[0086] In some implementations, when generating recommended wake-up modes for target wake-up users based on environmental element information, user attribute information, and user sleep information, a comprehensive reference wake-up feature vector can be obtained by multi-dimensional feature fusion based on environmental element information, user attribute information, and user sleep information using a large wake-up model. Based on this comprehensive reference wake-up feature vector, user wake-up environment feature vector is obtained through user wake-up environment analysis. Based on the comprehensive reference wake-up feature vector and the user wake-up environment feature vector, wake-up strategy element reasoning is performed to obtain wake-up time window information, wake-up method information, wake-up intensity information, and contextual response information. Finally, based on the wake-up time window information, wake-up method information, wake-up intensity information, and contextual response information, a comprehensive wake-up mode processing is performed to obtain the recommended wake-up mode.

[0087] The comprehensive reference wake-up feature vector is obtained by fusing environmental element information, user attribute information, and user sleep information into a multi-dimensional feature. Multi-dimensional feature fusion refers to integrating and encoding different types and dimensions of information (such as ambient light, sound, and temperature; user's age, gender, and occupation; and user's sleep stage, duration, and quality) to form a vector containing multiple key pieces of information. This vector forms the basis for subsequent processing, comprehensively reflecting various factors influencing wake-up mode selection. It provides a comprehensive reference for subsequent user wake-up environment analysis and wake-up strategy element inference. Through the analysis of this vector, the model can comprehensively consider various factors, avoiding the bias caused by single pieces of information, and thus more accurately determine the appropriate wake-up mode for the user.

[0088] User wake-up environment parsing refers to extracting feature information related to the specific environment in which the user wakes up from the comprehensive reference wake-up feature vector and encoding this information into a new vector. This vector mainly focuses on the physical environment at the time of user wake-up, such as ambient light intensity, sound type and volume, temperature, and humidity. The user wake-up environment feature vector is used to further refine the description of the user's wake-up environment, providing more specific environmental information for wake-up strategy element inference. Different wake-up environments require different wake-up strategies. For example, in a noisy environment, it may be necessary to increase the volume of the wake-up sound, while in a dimly lit environment, it may be necessary to increase the brightness of the lights. This vector helps the model formulate appropriate wake-up strategies based on the specific environment.

[0089] The wake-up time window refers to a suitable time range within which waking the user maximizes the effectiveness and comfort of the wake-up process. It considers factors such as the user's sleep cycle, sleep habits, and environmental factors. For example, based on the user's sleep stage, the model can determine the wake-up time window as the period near the light sleep stage or REM sleep stage, while also adjusting for factors such as the user's daily wake-up time and changes in ambient light. Wake-up time window information is a crucial component of recommended wake-up patterns, ensuring that users are woken up at the appropriate time and avoiding discomfort and fatigue caused by sudden awakening during deep sleep. An accurate wake-up time window helps improve a user's mental state and work efficiency throughout the day.

[0090] The wake-up method information refers to the specific method or means used to wake the user. Common wake-up methods include sound wake-up (such as alarm clock ringtones, music, and voice prompts), light wake-up (such as gradually brightening lights), and vibration wake-up (such as the vibration of a smart bracelet). The model selects the most suitable wake-up method based on the user's personal preferences, sleep state, and environmental factors. For example, for users who like music, specific music may be recommended as a wake-up sound; for users who are light sleepers, light wake-up may be recommended. A suitable wake-up method can improve the user's wake-up experience and reduce discomfort during the wake-up process. Different users have different levels of acceptance of wake-up methods, so selecting an appropriate wake-up method based on individual user differences is crucial.

[0091] The arousal intensity information indicates the strength of the stimulus used during the wake-up process. Examples include the volume of sound for wake-up, the rate and amplitude of brightness change for light for wake-up, and the frequency and intensity of vibration for wake-up. Determining the arousal intensity requires considering factors such as the user's sleep state, ambient noise level, and individual sensitivity to stimuli. For example, in a noisy environment, the volume of sound may need to be increased; for users in deep sleep, the amplitude of brightness change for light may need to be increased. Appropriate arousal intensity ensures that the user can be effectively awakened while avoiding problems caused by excessively strong or weak stimuli. Excessively strong stimuli may startle the user, affecting their mood and health; insufficiently strong stimuli may fail to awaken the user, causing them to miss important appointments.

[0092] Contextual response information refers to the adjustments and feedback made based on the specific context of the user's wake-up (such as the day's schedule, weather conditions, and the user's emotional state). For example, if the user has an important meeting that day, the model may adjust the wake-up time in advance and provide some encouraging voice prompts to help the user better cope with the day's tasks; if the weather forecast indicates heavy rain, the model may remind the user to bring rain gear upon wake-up. Contextual response information makes the recommended wake-up mode more intelligent and personalized, providing more considerate services based on the user's actual needs and environmental changes. It takes into account the user's specific needs in different situations, improving the practicality and adaptability of the wake-up mode.

[0093] In this embodiment, the wake-up model first fuses environmental element information, user attribute information, and user sleep information into a comprehensive reference wake-up feature vector. This step integrates various relevant information, providing a comprehensive foundation for subsequent processing. Based on the comprehensive reference wake-up feature vector, the model analyzes the user's wake-up environment to obtain a user wake-up environment feature vector. This step further refines the description of the user's wake-up environment, providing more specific environmental information for wake-up strategy element inference. The model then infers wake-up strategy elements based on the comprehensive reference wake-up feature vector and the user wake-up environment feature vector, obtaining wake-up time window information, wake-up method information, wake-up intensity information, and contextual response information. This step comprehensively considers various factors and determines the wake-up strategy elements suitable for the user. Finally, the model performs comprehensive wake-up mode processing based on the wake-up time window information, wake-up method information, wake-up intensity information, and contextual response information to obtain a recommended wake-up mode. This step integrates various wake-up strategy elements to form a complete recommended wake-up mode suitable for the target user. Through the above process, the wake-up model can provide users with personalized and scientifically reasonable recommended wake-up modes based on environmental element information, user attribute information, and user sleep information, improving the user's wake-up experience and quality of life, and increasing wake-up efficiency.

[0094] In some implementations, when monitoring target wake-up elements for a target wake-up user, environmental element information of the resting scene in which the target wake-up user is located, as well as user attribute information and user sleep information of the target wake-up user, can be collected, and target wake-up elements can be determined based on environmental element information, user attribute information, and user sleep information.

[0095] For example, environmental element information can include lighting conditions, sound environment, temperature, and humidity. For instance, a light sensor can be used to collect information such as light intensity and color in the resting environment. For example, during the day, the intensity and color of natural light change over time, while at night, indoor lighting settings can affect a user's sleep and wakefulness. By collecting this information, the lighting environment during rest can be understood, providing a basis for determining suitable wake-up lighting conditions. For instance, a sound sensor can be used to monitor the noise level and sound type in the resting environment. For example, if a user lives near a noisy street, external noise may affect their sleep quality, requiring consideration of using stronger sound stimulation or noise reduction measures during wake-up. For instance, temperature and humidity sensors can be used to obtain temperature and humidity data for the resting environment. Suitable temperature and humidity help improve a user's sleep quality, and the impact of these factors on the user during wake-up also needs to be considered. For example, in a hot and humid environment, the wake-up method may need to be adjusted to avoid user discomfort.

[0096] For example, user attribute information may include basic information and personal preference information. Basic information can be obtained by collecting and analyzing user images to determine basic details such as age and gender. Alternatively, it can be collected through user registration information or questionnaires. Users of different ages and genders may have different sensitivities and preferences regarding wake-up, and occupational characteristics can also influence users' sleep schedules and needs. Personal preference information may include understanding users' preferences for wake-up sound types (such as pop music, classical music, natural sounds, etc.), the appearance and function of wake-up devices, and the fun of wake-up methods. For example, some users prefer to wake up to soft birdsong, while others prefer the mechanical sound of an alarm clock. In scenarios involving waking up children in kindergarten and primary school, the aforementioned user attribute information can be entered by parents into the electronic device to configure the wake-up function.

[0097] For example, user sleep information can be detected through sleep monitoring devices, such as smart bracelets, smartwatches, and sleep monitoring pads, to monitor sleep stages, sleep duration, number of times the user turns over, and breathing rate in real time. This data can reflect the user's sleep quality and state, helping to determine the appropriate wake-up time. For instance, waking the user during their light sleep or REM sleep stage can reduce fatigue and discomfort. Furthermore, user feedback can also be used to obtain sleep information, such as whether it was easy to fall asleep, whether the user had many dreams, and whether they felt refreshed after waking up. This feedback can supplement the collection of user sleep data, helping to provide a more comprehensive understanding of the user's sleep patterns.

[0098] In this embodiment, the collected environmental element information, user attribute information, and user sleep information are comprehensively analyzed and integrated. For example, based on the user's sleep stage and the lighting conditions of the resting environment, a suitable wake-up light change method is determined; considering the user's personal preferences and sleep quality, the most suitable wake-up sound and volume are selected; and based on the user's occupation and daily routine, a reasonable wake-up time window is determined. Through this comprehensive analysis, the wake-up elements that can best meet the user's needs, i.e., the target wake-up elements, are determined.

[0099] In some implementations, when determining the target wake-up elements based on environmental element information, user attribute information, and user sleep information, a wake-up element completion questionnaire for the target wake-up user can be generated based on the environmental element information, user attribute information, and user sleep information. The wake-up element completion questionnaire is then provided to the target wake-up user, and the target wake-up elements are determined based on the wake-up element completion questionnaire.

[0100] In one example, environmental element information is collected by installing various sensors (such as light sensors, sound sensors, temperature and humidity sensors) in the resting environment where the target user is located, to obtain real-time data on ambient light intensity, sound decibels, temperature, humidity, etc. For example, installing a light sensor in the bedroom can record changes in light levels at different times of the day.

[0101] In one example, user attribute information is collected through methods such as users actively filling out questionnaires, registering information, or obtaining data from third-party sources. This includes collecting basic information such as age, gender, occupation, lifestyle habits, and personal preferences. For example, understanding whether a user is an office worker or a student, whether they regularly exercise, and what types of music they like.

[0102] In one example, user sleep information is collected by using devices such as smart bracelets, smartwatches, and sleep monitoring pads to monitor and record the user's sleep stages (light sleep, deep sleep, REM sleep), sleep duration, number of times the user turns over, and respiratory rate. These devices can analyze the user's physical activity through built-in sensors to determine their sleep state.

[0103] In this embodiment, the scope of wake-up elements is initially determined based on environmental element information, user attribute information, and user sleep information. This clarifies the information that the questionnaire needs to collect. The questionnaire further gathers direct user feedback on wake-up elements, supplementing the information obtained through data collection and analysis, and verifying the accuracy of the preliminary conclusions drawn from data analysis. It also uncovers potential user needs and preferences that may not be obtained through simple data collection and analysis. For example, a user might mention in the questionnaire that they want a specific voice prompt upon wake-up, a need that was not previously considered. Combining user subjective feedback with objective data allows for a more comprehensive and accurate determination of target wake-up elements, improving the effectiveness of the wake-up solution and user satisfaction. Specifically, when generating a wake-up element questionnaire, environmental element information, user attribute information, and user sleep information can be provided to the questionnaire platform. The platform's rich questionnaire template library determines a questionnaire template related to the above information, and a questionnaire is created based on this template as the wake-up element questionnaire.

[0104] For example, the questionnaire questions can be designed as follows:

[0105] Closed-ended questions: Design questions with fixed options to facilitate quick user responses and result analysis. For example, "Which of the following wake-up methods do you prefer? (A. Alarm ringtone; B. Soft music; C. Gradually increasing light; D. Vibration)".

[0106] Open-ended questions: Include some open-ended questions to allow users to freely express their thoughts and needs. For example, "Under what circumstances would you feel most comfortable being woken up?"

[0107] Rating scale questions: Use a scale to measure a user's attitude or feelings toward certain arousal elements. For example, "Please select from the following options (1-very weak, 2-weak, 3-moderate, 4-strong, 5-very strong) based on your tolerance for the intensity of sound arousal."

[0108] In some implementations, after performing rest wake-up processing on the target wake-up user based on the recommended wake-up mode, a wake-up event can be pushed to a preset electronic device, and a wake-up stop operation can be received from the preset electronic device in response to the wake-up event to stop the wake-up processing on the target wake-up user.

[0109] In this context, the pre-set electronic device refers to a specific electronic device that is pre-configured in the target user's wake-up scenario to receive, process, and interact with wake-up-related information. As a terminal for information interaction, it undertakes important functions such as receiving wake-up commands and providing feedback on operational information, enabling users or relevant personnel to control it and thus influence the target user's wake-up process.

[0110] Among them, a wake-up event refers to an event that performs wake-up processing on the target wake-up user.

[0111] In this embodiment, after completing the rest-to-wake process for the target user based on the recommended wake-up mode, a wake-up event can be pushed to a preset electronic device. If a stop operation command is received from the preset electronic device in response to the wake-up event, the wake-up process for the target user will be stopped.

[0112] Taking the wake-up scenario for children in kindergarten and primary school as an example, the default electronic device is usually a smartphone used by the child's parents. Parents can receive wake-up event information pushed by the system through specific applications or functional modules on their phones and perform actions on these events, such as turning off wake-up notifications, thus achieving remote control over the child's wake-up process. This allows parents to conveniently manage wake-up events anytime, anywhere. In other scenarios, the default electronic device may also be a smartwatch, tablet, or other electronic device with communication and interactive functions; the specific choice depends on the usage scenario and user needs.

[0113] In some implementations, after performing rest wake-up processing on the target wake-up user based on the recommended wake-up mode, audio in the rest scenario can also be detected. If the audio matches the preset audio for disabling the wake-up function, then the wake-up processing on the target wake-up user is turned off.

[0114] In this embodiment, for example, the preset audio for disabling the wake-up function can be a combination of the voice assistant's wake-up phrase and the voice prompt to disable the wake-up event. For example, "Xiao An, Xiao An, please turn off the alarm." Here, "Xiao An, Xiao An" is the voice assistant's wake-up phrase, and "please turn off the alarm" is the voice prompt to disable the wake-up event. In this embodiment, if the audio in a resting scenario matches the preset audio for disabling the wake-up function, then the wake-up process for the target user is disabled.

[0115] In some implementations, after performing rest wake-up processing on the target wake-up user based on the recommended wake-up mode, the behavioral status information of the target wake-up user can also be collected. If the behavioral status information indicates that the target wake-up user is awake, then the wake-up processing on the target wake-up user is turned off.

[0116] Among them, behavioral state information refers to a set of data that reflects the various behavioral manifestations, activity characteristics, and physical reactions exhibited by a target individual within a specific time and space. In the scenario involved in this application, it specifically covers dynamic data on various aspects of a user's physical movements, physiological reactions, and sounds during the process from rest to wake-up. This data can intuitively present different states of the user, such as whether they are currently asleep, about to wake up, or fully awake.

[0117] In this embodiment, the electronic device first performs a rest-to-wake operation on the target user according to the recommended wake-up mode. During the wake-up process, it collects the target user's behavioral state information. Once this information indicates that the user is already awake, the system stops subsequent wake-up processing. This avoids unnecessary wake-up actions and improves the accuracy of wake-up and user experience.

[0118] For example, a camera can detect the image of the target waking the user, and image recognition technology can be used to analyze the user's actions and posture. For instance, the camera can identify whether the user has sat up or is active, thereby determining whether the user is in a woken state. If the target waking the user is detected to be in a woken state, the wake-up process for that target is turned off.

[0119] In some implementations, the wake-up processing method provided in this application can also detect audio in a resting scenario. If the audio is found to match a preset wake-up function audio, then wake-up processing for the target wake-up user is initiated.

[0120] In this embodiment, for example, the preset wake-up function activation audio can be a combination of the voice assistant's wake-up phrase and the voice prompt to deactivate the wake-up event, such as "Xiao An, Xiao An, please turn on the alarm." Here, "Xiao An, Xiao An" is the voice assistant's wake-up phrase, and "please turn on the alarm" is the voice prompt to deactivate the wake-up event. In this embodiment, if the audio in a resting scenario matches the preset wake-up function activation audio, then wake-up processing for the target user is initiated.

[0121] In some implementations, the wake-up processing method provided in this application can also push a wake-up setting event to a preset electronic device, receive a wake-up start operation from the preset electronic device in response to the wake-up setting event, and start wake-up processing for the target wake-up user.

[0122] Among them, the preset electronic device refers to a specific electronic device that is pre-configured in the target user wake-up scenario to receive, process and wake up related information.

[0123] The wake-up setting event refers to the set of detailed information related to the wake-up operation that the system pushes to preset electronic devices during the process of waking up a target user based on the recommended wake-up mode. It includes key parameters and settings for the wake-up operation and serves as an important basis for users or other relevant personnel to view, adjust, and control the wake-up process.

[0124] In this embodiment, a wake-up setting event can be pushed to a preset electronic device, so that the user of the preset electronic device can set the wake-up event based on the wake-up setting event, such as a wake-up start operation. Through the wake-up start operation, the wake-up process for the target wake-up user can be started.

[0125] Taking the wake-up scenario for children in kindergarten and primary school as an example, the default electronic device is usually a smartphone used by the child's parents. Parents can receive wake-up setting events pushed by the system through specific applications or functional modules on their phones. Based on the key parameters and wake-up settings provided in these events, they can perform actions such as enabling wake-up reminders, achieving remote control over the child's wake-up process. This allows parents to conveniently manage wake-up events anytime, anywhere. In other scenarios, the default electronic device may also be a smartwatch, tablet, or other electronic device with communication and interactive functions; the specific choice depends on the usage scenario and user needs.

[0126] In one embodiment, a wake-up processing device is also provided. See also... Figure 2 , Figure 2 This is a schematic diagram of the structure of a wake-up processing device 200 provided in an embodiment of this application. The wake-up processing device 200 is applied to an electronic device and includes an acquisition module 201 and a wake-up module 202, as follows:

[0127] The acquisition module 201 is used to acquire a recommended wake-up mode for the target wake-up user using a wake-up model when the target wake-up user is in a resting scenario.

[0128] The wake-up module 202 is used to determine that the user is in a wake-up triggered state and to perform rest wake-up processing on the target wake-up user based on the recommended wake-up mode.

[0129] In some implementations, the wake-up module 202 is specifically used for:

[0130] Monitor the target wake-up elements for the target wake-up user;

[0131] Based on the wake-up model, a wake-up mode recommendation process is performed on the target wake-up user according to the target wake-up elements to obtain a recommended wake-up mode for the target wake-up user.

[0132] In some implementations, the wake-up module 202 is specifically used for:

[0133] Based on the wake-up model, environmental element information, user attribute information, and user sleep information are extracted from the target wake-up elements.

[0134] Based on the environmental element information, the user attribute information, and the user sleep information, a wake-up mode recommendation process is performed on the target wake-up user to generate the recommended wake-up mode.

[0135] In some implementations, the wake-up module 202 is specifically used for:

[0136] A comprehensive reference wake-up feature vector is obtained by fusing multi-dimensional features based on the environmental element information, user attribute information, and user sleep information using a wake-up model; and a user wake-up environment feature vector is obtained by parsing the user wake-up environment based on the comprehensive reference wake-up feature vector.

[0137] Based on the comprehensive reference wake-up feature vector and the user wake-up environment feature vector, wake-up strategy element reasoning is performed to obtain wake-up time window information, wake-up method information, wake-up intensity information, and context response information;

[0138] The recommended wake-up mode is obtained by comprehensively processing the wake-up mode based on the wake-up time window information, the wake-up method information, the wake-up intensity information, and the context response information.

[0139] In some implementations, the wake-up module 202 is specifically used for:

[0140] Collect environmental element information of the resting scene of the target awakened user, as well as user attribute information and user sleep information of the target awakened user;

[0141] The target wake-up element is determined based on the environmental element information, the user attribute information, and the user sleep information.

[0142] In some implementations, the wake-up module 202 is specifically used for:

[0143] Based on the environmental element information, the user attribute information, and the user sleep information, a wake-up element completion questionnaire is generated for the target wake-up user, and the wake-up element completion questionnaire is provided to the target wake-up user.

[0144] The target wake-up element is determined by completing a questionnaire based on the wake-up element.

[0145] In some implementations, the wake-up module 202 is further configured to:

[0146] Push wake-up events to preset electronic devices;

[0147] The system receives a wake-up stop operation from the preset electronic device in response to the wake-up event, thereby stopping the wake-up process for the target wake-up user.

[0148] In some implementations, the wake-up module 202 is further configured to:

[0149] The system detects audio in the resting scenario. If the audio matches a preset audio for disabling wake-up function, the system disables wake-up processing for the target user.

[0150] In some implementations, the wake-up module 202 is further configured to:

[0151] Collect the behavioral state information of the target wake-up user. If the behavioral state information indicates that the target wake-up user is in a wake-up state, then disable the wake-up process for the target wake-up user.

[0152] In some implementations, the wake-up module 202 is further configured to:

[0153] The system detects audio in the resting scenario. If the audio matches a preset audio for activating the wake-up function, it initiates wake-up processing for the target user.

[0154] In some implementations, the wake-up module 202 is further configured to:

[0155] A wake-up setting event is pushed to a preset electronic device, and the wake-up start operation of the preset electronic device in response to the wake-up setting event is received to start the wake-up process for the target wake-up user.

[0156] It should be noted that the wake-up processing device provided in this application embodiment belongs to the same concept as the wake-up processing method in the above embodiment. Any of the methods provided in the wake-up processing method embodiment can be implemented through this wake-up processing device. For details of its implementation process, please refer to the wake-up processing method embodiment, which will not be repeated here.

[0157] This application embodiment also provides a computer program product, which stores at least one instruction, the at least one instruction being loaded and executed by the processor as described above. Figures 1-4 The wake-up processing method of the illustrated embodiment can be found in the following document for a detailed execution process. Figures 1-4 The specific details of the illustrated embodiments will not be elaborated here.

[0158] Furthermore, to better implement the wake-up processing method in the embodiments of this application, based on the wake-up processing method, this application also provides an electronic device. The electronic device can be a smart home device, such as a smart camera, smart speaker, smart robot, smart TV, smart door lock, etc. The electronic device can also be a terminal device, such as a smartphone, tablet computer, PDA, laptop computer, or desktop computer. Please refer to [link / reference]. Figure 3 , Figure 3 This is a schematic diagram of a first structure of an electronic device provided in an embodiment of this application. The electronic device 300 includes a processor 301 and a memory 302. The processor 301 and the memory 302 are electrically connected.

[0159] The processor 301 is the control center of the electronic device 300. It connects various parts of the electronic device via various interfaces and lines, and executes various functions and processes data by running or calling computer programs stored in the memory 302 and accessing data stored in the memory 302, thereby providing overall monitoring of the electronic device. The processor 301 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0160] The memory 302 can be used to store computer programs and data. The computer programs stored in the memory 302 contain instructions that can be executed in the processor. The computer programs can be composed of various functional modules. The processor 401 executes various functional applications and data processing by calling the computer programs stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 300 (such as audio data, video data, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0161] In this embodiment, the processor 301 in the electronic device 300 loads the instructions corresponding to the processes of one or more computer programs into the memory 302 according to the following steps, and the processor 401 runs the computer programs stored in the memory 302 to realize various functions:

[0162] When the target wake-up user is in a resting scenario, obtain the recommended wake-up mode for the target wake-up user using the wake-up big model;

[0163] Once it is determined that the user is in a wake-up triggered state, a rest wake-up process is performed on the target wake-up user based on the recommended wake-up mode.

[0164] In some implementations, please refer to Figure 4 , Figure 4 This is a second structural schematic diagram of the electronic device provided in an embodiment of this application. The electronic device 300 further includes: a radio frequency circuit 303, a display screen 304, a control circuit 305, an input unit 306, an audio circuit 307, a sensor 308, and a power supply 309. The processor 301 is electrically connected to the radio frequency circuit 303, the display screen 304, the control circuit 305, the input unit 306, the audio circuit 307, the sensor 308, and the power supply 309.

[0165] The radio frequency circuit 303 is used to transmit and receive radio frequency signals to communicate with network devices or other electronic devices via wireless communication.

[0166] The display screen 304 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of electronic devices, which can be composed of images, text, icons, videos, and any combination thereof.

[0167] The control circuit 305 is electrically connected to the display screen 304 and is used to control the display screen 304 to display information.

[0168] The input unit 306 can be used to receive input numeric or character information or user characteristic information (such as fingerprints), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. The input unit 306 may include a fingerprint recognition module.

[0169] The audio circuit 307 provides an audio interface between the user and the electronic device via a speaker and a microphone. The audio circuit 307 includes a microphone, which is electrically connected to the processor 301. The microphone is used to receive voice information input by the user.

[0170] Sensor 308 is used to collect information about the external environment. Sensor 308 may include one or more sensors such as an ambient light sensor, an accelerometer, and a gyroscope.

[0171] The power supply 309 is used to supply power to the various components of the electronic device 300. In some embodiments, the power supply 309 can be logically connected to the processor 301 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system.

[0172] Although not shown in the figure, electronic device 300 may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0173] In this embodiment, the processor 301 in the electronic device 300 loads the instructions corresponding to the processes of one or more computer programs into the memory 302 according to the following steps, and the processor 301 runs the computer programs stored in the memory 302 to realize various functions:

[0174] When the target wake-up user is in a resting scenario, obtain the recommended wake-up mode for the target wake-up user using the wake-up big model;

[0175] Once it is determined that the user is in a wake-up triggered state, a rest wake-up process is performed on the target wake-up user based on the recommended wake-up mode.

[0176] In some implementations, when processor 301 performs the step of obtaining the recommended wake-up mode for the target wake-up user using the wake-up model, it may perform the following:

[0177] Monitor the target wake-up elements for the target wake-up user;

[0178] Based on the wake-up model, a wake-up mode recommendation process is performed on the target wake-up user according to the target wake-up elements to obtain a recommended wake-up mode for the target wake-up user.

[0179] In some implementations, when processor 301 executes the wake-up model-based wake-up recommendation process to obtain a recommended wake-up mode for the target wake-up user, it may perform the following:

[0180] Based on the wake-up model, environmental element information, user attribute information, and user sleep information are extracted from the target wake-up elements.

[0181] Based on the environmental element information, the user attribute information, and the user sleep information, a wake-up mode recommendation process is performed on the target awakening user to generate the recommended wake-up mode.

[0182] In some implementations, when processor 301 performs the wake-up mode recommendation process based on the environmental element information, the user attribute information, and the user sleep information to generate the recommended wake-up mode for the target wake-up user, it may perform the following:

[0183] A comprehensive reference wake-up feature vector is obtained by fusing multi-dimensional features based on the environmental element information, user attribute information, and user sleep information using a wake-up model; and a user wake-up environment feature vector is obtained by parsing the user wake-up environment based on the comprehensive reference wake-up feature vector.

[0184] Based on the comprehensive reference wake-up feature vector and the user wake-up environment feature vector, wake-up strategy element reasoning is performed to obtain wake-up time window information, wake-up method information, wake-up intensity information, and context response information;

[0185] The recommended wake-up mode is obtained by comprehensively processing the wake-up mode based on the wake-up time window information, the wake-up method information, the wake-up intensity information, and the context response information.

[0186] In some implementations, when processor 301 performs the monitoring of target wake-up elements for the target wake-up user, it may perform the following:

[0187] Collect environmental element information of the resting scene of the target awakened user, as well as user attribute information and user sleep information of the target awakened user;

[0188] The target wake-up element is determined based on the environmental element information, the user attribute information, and the user sleep information.

[0189] In some implementations, when processor 301 executes the step of determining the target wake-up element based on the environmental element information, the user attribute information, and the user sleep information, it may perform the following:

[0190] Based on the environmental element information, the user attribute information, and the user sleep information, a wake-up element completion questionnaire is generated for the target wake-up user, and the wake-up element completion questionnaire is provided to the target wake-up user.

[0191] The target wake-up element is determined by completing a questionnaire based on the wake-up element.

[0192] In some implementations, after the processor 301 performs the rest-wake process for the target wake-up user based on the recommended wake-up mode, it may also perform:

[0193] Push wake-up events to preset electronic devices;

[0194] The system receives a wake-up stop operation from the preset electronic device in response to the wake-up event, thereby stopping the wake-up process for the target wake-up user.

[0195] In some implementations, after the processor 301 performs the rest-wake process for the target wake-up user based on the recommended wake-up mode, it may also perform:

[0196] The system detects audio in the resting scenario. If the audio matches a preset audio for disabling wake-up function, the system disables wake-up processing for the target user.

[0197] In some implementations, after the processor 301 performs the rest-wake process for the target wake-up user based on the recommended wake-up mode, it may also perform:

[0198] Collect the behavioral state information of the target wake-up user. If the behavioral state information indicates that the target wake-up user is in a wake-up state, then disable the wake-up process for the target wake-up user.

[0199] In some implementations, processor 301 may also perform:

[0200] The system detects audio in the resting scenario. If the audio matches a preset audio for activating the wake-up function, it initiates wake-up processing for the target user.

[0201] In some implementations, processor 301 may also perform:

[0202] A wake-up setting event is pushed to a preset electronic device, and the wake-up start operation of the preset electronic device in response to the wake-up setting event is received to start the wake-up process for the target wake-up user.

[0203] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run on a computer, the computer executes the wake-up processing method described in any of the above embodiments.

[0204] It should be noted that those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, which may include, but is not limited to, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0205] Furthermore, the terms "first," "second," and "third," etc., used in this application are used to distinguish different objects, not to describe a specific order. Additionally, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the listed steps or modules, but some embodiments may also include steps or modules not listed, or some embodiments may include other steps or modules inherent to these processes, methods, products, or devices.

[0206] The wake-up processing method, apparatus, storage medium, and electronic device provided in the embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this application; at the same time, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A wake-up processing method, characterized in that, include: When the target wake-up user is in a resting scenario, obtain the recommended wake-up mode for the target wake-up user using the wake-up big model; Once it is determined that the user is in a wake-up triggered state, a rest wake-up process is performed on the target wake-up user based on the recommended wake-up mode.

2. The method according to claim 1, characterized in that, The process of obtaining and using the wake-up model to recommend a wake-up mode for the target wake-up user includes: Monitor the target wake-up elements for the target wake-up user; Based on the wake-up model, a wake-up mode recommendation process is performed on the target wake-up user according to the target wake-up elements to obtain a recommended wake-up mode for the target wake-up user.

3. The method according to claim 2, characterized in that, The step of using a wake-up model to recommend wake-up modes for the target wake-up user based on the target wake-up elements includes: Based on the wake-up model, environmental element information, user attribute information, and user sleep information are extracted from the target wake-up elements. Based on the environmental element information, the user attribute information, and the user sleep information, a wake-up mode recommendation process is performed on the target wake-up user to generate the recommended wake-up mode.

4. The method according to claim 3, characterized in that, The step of generating the recommended wake-up mode by performing wake-up mode recommendation processing on the target wake-up user based on the environmental element information, the user attribute information, and the user sleep information includes: A comprehensive reference wake-up feature vector is obtained by fusing multi-dimensional features based on the environmental element information, user attribute information, and user sleep information using a wake-up model; and a user wake-up environment feature vector is obtained by parsing the user wake-up environment based on the comprehensive reference wake-up feature vector. Based on the comprehensive reference wake-up feature vector and the user wake-up environment feature vector, wake-up strategy element reasoning is performed to obtain wake-up time window information, wake-up method information, wake-up intensity information, and context response information; The recommended wake-up mode is obtained by comprehensively processing the wake-up mode based on the wake-up time window information, the wake-up method information, the wake-up intensity information, and the context response information.

5. The method according to claim 2, characterized in that, The monitoring targets the wake-up elements of the target wake-up user, including: Collect environmental element information of the resting scene of the target awakened user, as well as user attribute information and user sleep information of the target awakened user; The target wake-up element is determined based on the environmental element information, the user attribute information, and the user sleep information.

6. The method according to claim 5, characterized in that, The process of determining the target wake-up element based on the environmental element information, the user attribute information, and the user sleep information includes: Based on the environmental element information, the user attribute information, and the user sleep information, a wake-up element completion questionnaire is generated for the target wake-up user, and the wake-up element completion questionnaire is provided to the target wake-up user. The target wake-up element is determined by completing a questionnaire based on the wake-up element.

7. The method according to claim 1, characterized in that, After performing the rest-wake process on the target wake-up user based on the recommended wake-up mode, the method further includes: Push wake-up events to preset electronic devices; The system receives a wake-up stop operation from the preset electronic device in response to the wake-up event, thereby stopping the wake-up process for the target wake-up user.

8. A wake-up processing device, characterized in that, include: The acquisition module is used to acquire the recommended wake-up mode for the target wake-up user using the wake-up big model when the target wake-up user is in a resting scenario; The wake-up module is used to determine that the user is in a wake-up triggered state and to perform rest wake-up processing on the target wake-up user based on the recommended wake-up mode.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run on the computer, it causes the computer to perform the wake-up processing method as described in any one of claims 1 to 7.

10. An electronic device comprising a processor and a memory, the memory storing a computer program, characterized in that, The processor executes the wake-up processing method as described in any one of claims 1 to 7 by invoking the computer program.

Images