WO2020168448A1 - 睡眠预测方法、装置、存储介质及电子设备 - Google Patents

睡眠预测方法、装置、存储介质及电子设备 Download PDF

Info

Publication number
WO2020168448A1
WO2020168448A1 PCT/CN2019/075356 CN2019075356W WO2020168448A1 WO 2020168448 A1 WO2020168448 A1 WO 2020168448A1 CN 2019075356 W CN2019075356 W CN 2019075356W WO 2020168448 A1 WO2020168448 A1 WO 2020168448A1
Authority
WO
WIPO (PCT)
Prior art keywords
state information
sleep
current
electronic device
sleep prediction
Prior art date
Application number
PCT/CN2019/075356
Other languages
English (en)
French (fr)
Inventor
戴堃
张寅祥
吴建文
帅朝春
陆天洋
Original Assignee
深圳市欢太科技有限公司
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市欢太科技有限公司, Oppo广东移动通信有限公司 filed Critical 深圳市欢太科技有限公司
Priority to PCT/CN2019/075356 priority Critical patent/WO2020168448A1/zh
Priority to CN201980080279.XA priority patent/CN113164056A/zh
Publication of WO2020168448A1 publication Critical patent/WO2020168448A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons

Definitions

  • This application belongs to the field of computer technology, and in particular relates to a sleep prediction method, device, storage medium, and electronic equipment.
  • electronic devices such as tablet computers and mobile phones are configured to perform system updates while the user is sleeping, and other operations that affect the user's use or take a long time to avoid affecting the user's use.
  • the related technology achieves the foregoing purpose by predicting the user's sleep, such as predicting the user's sleep interval, etc.
  • the accuracy of the related technology for predicting the user's sleep is low.
  • the embodiments of the present application provide a sleep prediction method, device, storage medium, and electronic device, which can enable the electronic device to accurately predict the user's sleep.
  • an embodiment of the present application provides a sleep prediction method applied to an electronic device, including:
  • the pre-trained sleep prediction model corresponding to the current use scene perform sleep prediction on the user to obtain the prediction result.
  • an embodiment of the present application provides a sleep prediction device applied to an electronic device, including:
  • An obtaining module used to obtain current state information of the electronic device
  • a determining module configured to determine the current usage scenario of the electronic device according to the current state information
  • the prediction module is used to predict the user's sleep according to the pre-trained sleep prediction model corresponding to the current use scene, and obtain the prediction result.
  • an embodiment of the present application provides a storage medium on which a computer program is stored.
  • the computer program is executed on a computer, the computer is caused to execute the sleep prediction method provided in the embodiment of the present application. step.
  • an embodiment of the present application provides an electronic device including a memory and a processor, and the processor is used to execute the steps in the sleep prediction method provided in the embodiment of the present application by calling a computer program stored in the memory .
  • the electronic device can obtain its current state information, and determine its current use scene according to its current state information, and then use the sleep prediction model corresponding to its current use scene to predict the user's sleep, which can improve the user's sleep The accuracy of the forecast.
  • FIG. 1 is a schematic flowchart of a sleep prediction method provided by an embodiment of the present application.
  • Fig. 2 is a schematic diagram of selecting a target sleep prediction model from a set of sleep prediction models in an embodiment of the present application.
  • FIG. 3 is another schematic flow chart of the sleep prediction method provided by an embodiment of the present application.
  • Fig. 4 is a schematic diagram of an operation configuration interface provided in an embodiment of the present application.
  • Fig. 5 is a schematic structural diagram of a sleep prediction device provided by an embodiment of the present application.
  • Fig. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 7 is another schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 1 is a schematic flowchart of a sleep prediction method provided by an embodiment of the present application.
  • the sleep prediction method can be applied to electronic devices.
  • the process of the sleep prediction method may include:
  • the current state information of the electronic device is acquired.
  • the electronic device may periodically obtain its status information after being turned on, where the status information includes but is not limited to related information used to describe the current use status, location status, and environmental status of the electronic device.
  • the current is not used to specifically refer to a certain moment, but is used to refer to the moment when the electronic device performs the operation of obtaining status information. Therefore, in the embodiment of the present application, each time the electronic device executes the "current moment" of acquiring the status information, the corresponding acquired status information is recorded as the "current status information".
  • the current usage scenario of the electronic device is determined according to the aforementioned current state information.
  • the electronic device after the electronic device obtains its current state information, it further determines its current usage scenario based on the obtained current state information.
  • the usage scenario is used to describe the scenario in which the user uses the electronic device, including but not Limited to home vacation scenes, travel scenes, work trip scenes, daily work scenes, etc.
  • the electronic device determines that its current use scene is a home scene according to the acquired current state information.
  • a sleep prediction is performed on the user to obtain a prediction result.
  • a set of sleep prediction models is pre-stored in the electronic device, and the set of sleep prediction models includes a plurality of sleep prediction models, which are respectively suitable for predicting a user's sleep interval in different usage scenarios, where ,
  • the user’s sleep interval includes at least the moment when the user enters sleep and the moment when the user wakes up.
  • the electronic device determines its current use scene according to its current state information, it further selects a sleep prediction model corresponding to its current use scene from the set of sleep prediction models (or in other words, it is suitable for checking the current use scene).
  • the sleep prediction model that predicts the user's sleep interval is used as the target sleep prediction model currently used to predict the user's sleep interval.
  • the sleep prediction model set includes four sleep prediction models, namely A sleep prediction model suitable for sleep prediction in the home vacation scene, and B sleep prediction model suitable for sleep prediction in the travel scene , C sleep prediction model suitable for sleep prediction in work travel scenarios and D sleep prediction model suitable for sleep prediction in daily work scenarios.
  • the electronic device determines that its current use scene is a home vacation scene, select sleep prediction model A from the set of sleep prediction models as the target sleep prediction model; if the electronic device determines that its current use scene is a travel scene, set the sleep prediction model Select B sleep prediction model as the target sleep prediction model; if the electronic device determines that its current use scene is a work trip scenario, select C sleep prediction model from the set of sleep prediction models as the target sleep prediction model; if the electronic device determines its current use If the scene is a daily work scene, the D sleep prediction model is selected from the sleep prediction model as the target sleep prediction model.
  • the sleep prediction model is obtained through machine learning algorithm training in advance, and the machine learning algorithm can realize various functions through continuous feature learning. For example, it can predict the user's sleep interval based on the user's historical work and rest behavior.
  • machine learning algorithms may include: decision tree models, logistic regression models, Bayes models, neural network models, clustering models, and so on.
  • machine learning algorithms can be divided according to various situations. For example, machine learning algorithms can be divided into supervised learning algorithms, non-supervised learning algorithms, semi-supervised learning algorithms, reinforcement learning algorithms, etc. based on learning methods.
  • supervised learning Under supervised learning, the input data is called “training data”, and each set of training data has a clear identification or result, such as “spam” and “non-spam” in the anti-spam system, and recognition of handwritten digits. "1", “2", “3”, “4" and so on.
  • supervised learning establishes a learning process that compares the scene type information with the actual results of the "training data”, and continuously adjusts the recognition model until the model's scene type information reaches an expected accuracy rate.
  • Common application scenarios for supervised learning are classification problems and regression problems.
  • Common algorithms include Logistic Regression and Back Propagation Neural Network.
  • the data is not specially identified, and the recognition model is to infer some internal structure of the data.
  • Common application scenarios include the learning of association rules and clustering.
  • Common algorithms include Apriori algorithm and k-Means algorithm.
  • Semi-supervised learning algorithm In this learning mode, the input data is partially identified.
  • This learning model can be used for type recognition, but the model first needs to learn the internal structure of the data in order to organize the data reasonably for prediction.
  • Application scenarios include classification and regression.
  • Algorithms include some extensions to commonly used supervised learning algorithms. These algorithms first try to model unidentified data, and then predict the identified data on this basis.
  • Graph inference algorithm Graph Inference
  • Laplacian SVM Laplacian SVM
  • Reinforcement learning algorithm In this learning mode, the input data is used as feedback to the model. Unlike the supervised model, the input data is only used as a way to check whether the model is right or wrong. Under reinforcement learning, the input data is directly fed back to the model. The model must be adjusted for this immediately.
  • Common application scenarios include dynamic systems and robot control.
  • Common algorithms include Q-Learning and Temporal difference learning.
  • machine learning algorithms can also be divided into:
  • Regression algorithm common regression algorithms include: Ordinary Least Square, Logistic Regression, Stepwise Regression, Multivariate Adaptive Regression Splines and Local Scatter Smoothing Estimate (Locally Estimated Scatterplot Smoothing).
  • Example-based algorithms include k-Nearest Neighbor (KNN), Learning Vector Quantization (LVQ), and Self-Organizing Map (SOM).
  • KNN k-Nearest Neighbor
  • LVQ Learning Vector Quantization
  • SOM Self-Organizing Map
  • Regularization methods common algorithms include: Ridge Regression, Least Absolute Shrinkage and Selection Operator (LASSO), and Elastic Net (Elastic Net).
  • LASSO Least Absolute Shrinkage and Selection Operator
  • Elastic Net Elastic Net
  • Decision tree algorithm common algorithms include: Classification and Regression Tree (CART), ID3 (Iterative Dichotomiser 3), C4.5, Chi-squared Automatic Interaction Detection (CHAID), Decision Stump, Random Forest (Random Forest), Multiple Adaptive Regression Spline (MARS) and Gradient Boosting Machine (GBM).
  • CART Classification and Regression Tree
  • ID3 Iterative Dichotomiser 3
  • C4.5 Chi-squared Automatic Interaction Detection
  • CHAI Chi-squared Automatic Interaction Detection
  • Decision Stump Random Forest
  • Random Forest Random Forest
  • MERS Multiple Adaptive Regression Spline
  • GBM Gradient Boosting Machine
  • Bayesian method algorithms include: Naive Bayes algorithm, Averaged One-Dependence Estimators (AODE), and Bayesian Belief Network (BBN).
  • AODE Averaged One-Dependence Estimators
  • BBN Bayesian Belief Network
  • the electronic device After the electronic device selects the target sleep prediction model (that is, the sleep prediction model corresponding to the current use scene of the electronic device) from the set of sleep prediction models, it can predict the user's sleep according to the target sleep prediction model to obtain the prediction result .
  • the sleep prediction for the user includes but is not limited to the time of entering sleep, the time of ending sleep, and the sleep interval composed of the time of entering sleep and the time of ending sleep, etc.
  • the user's sleep prediction is performed according to the target sleep prediction model, and the user's sleep interval is obtained from 23:30 on the current day to 06:60 on the next day.
  • the electronic device can obtain its current state information, determine its current use scenario according to its current state information, and then select the target sleep prediction model corresponding to its current use scenario from the set of sleep prediction models. Using the target sleep prediction model to predict the user's sleep can improve the accuracy of the user's sleep prediction.
  • FIG. 3 is a schematic diagram of another flow of the sleep prediction method provided by an embodiment of the application.
  • the sleep prediction method can be applied to electronic devices.
  • the process of the sleep prediction method may include:
  • the electronic device obtains sensor data collected by the sensor.
  • the electronic device In 202, the electronic device generates its current state information based on sensor data.
  • the electronic device can periodically obtain its status information according to a preset information acquisition cycle (appropriate value can be selected by a person of ordinary skill in the art based on experience, for example, it can be set to a natural day) after being turned on ,
  • the status information includes, but is not limited to, relevant information used to describe the use status, location status, and environmental status of the electronic device.
  • the current is not used to specifically refer to a certain moment, but is used to refer to the moment when the electronic device performs the operation of obtaining status information. Therefore, in the embodiment of the present application, each time the electronic device executes the "current moment" of acquiring the status information, the corresponding acquired status information is recorded as the "current status information".
  • the electronic device may use its own configured sensor to obtain current state information.
  • the sensors configured by the electronic device include, but are not limited to, gravity sensors, acceleration sensors, positioning sensors (such as satellite positioning sensors, base station positioning sensors, etc.), sound sensors, and light sensors.
  • the electronic device When the electronic device performs the operation of acquiring status information at the "current moment”, it first acquires the sensor data collected by its configured sensor in the current information acquisition period corresponding to the "current moment”, and then generates current information based on these sensor data. status information.
  • the electronic device generates state information describing its use state based on the cleaned gravity sensor data and acceleration sensor data, generates state information describing its location based on the positioning sensor data, and generates state information based on the sound sensor and light sensor. State information describing the state of its environment, etc.
  • the electronic device determines its current usage scenario according to its current state information.
  • the electronic device after the electronic device obtains its current state information, it further determines its current usage scenario based on the obtained current state information.
  • the usage scenario is used to describe the scenario in which the user uses the electronic device, including but not Limited to home vacation scenes, travel scenes, work trip scenes, daily work scenes, etc.
  • the electronic device determines that its current use scene is a home scene according to the acquired current state information.
  • the electronic device predicts the user's sleep according to the pre-trained sleep prediction model corresponding to the current usage scenario, and obtains the user's sleep interval.
  • a set of sleep prediction models is pre-stored in the electronic device, and the set of sleep prediction models includes a plurality of sleep prediction models, which are respectively suitable for predicting a user's sleep interval in different usage scenarios, where ,
  • the user’s sleep interval includes at least the moment when the user enters sleep and the moment when the user wakes up.
  • the electronic device determines its current use scene according to its current state information, it further selects a sleep prediction model corresponding to its current use scene from the set of sleep prediction models (or in other words, it is suitable for checking the current use scene).
  • the sleep prediction model that predicts the user's sleep interval is used as the target sleep prediction model currently used to predict the user's sleep interval.
  • the sleep prediction model set includes four sleep prediction models, namely A sleep prediction model suitable for sleep prediction in the home vacation scene, and B sleep prediction model suitable for sleep prediction in the travel scene , C sleep prediction model suitable for sleep prediction in work travel scenarios and D sleep prediction model suitable for sleep prediction in daily work scenarios.
  • the electronic device determines that its current use scene is a home vacation scene, select sleep prediction model A from the set of sleep prediction models as the target sleep prediction model; if the electronic device determines that its current use scene is a travel scene, set the sleep prediction model Select B sleep prediction model as the target sleep prediction model; if the electronic device determines that its current use scene is a work trip scenario, select C sleep prediction model from the set of sleep prediction models as the target sleep prediction model; if the electronic device determines its current use If the scene is a daily work scene, the D sleep prediction model is selected from the sleep prediction model as the target sleep prediction model.
  • the electronic device selects the target sleep prediction model from the sleep prediction model set, it can perform sleep prediction on the user according to the target sleep prediction model to obtain the user's sleep interval. For example, it is predicted that the user's sleep interval is 23:30 on the current day to 06:60 the next day.
  • the electronic device performs a preset operation.
  • the electronic device when the electronic device reaches the predicted sleep interval, it detects the duration of turning off the screen, so as to determine whether the user enters sleep according to the duration. Wherein, the electronic device may determine that the user enters sleep when the duration of the off-screen duration reaches the preset duration. When it is determined that the user enters sleep, the electronic device performs a preset operation configured in advance and executed in the sleep interval.
  • the value of the preset duration in the embodiment of the present application can be determined by a person of ordinary skill in the art according to actual needs, for example, it can be set to 5 minutes.
  • the embodiment of the present application does not limit the configuration of the preset operation. It can be manually configured by the user, or the electronic device can be configured by default.
  • the electronic device can configure the system update operation as a preset operation, thereby predicting The system update operation is performed in the sleep interval to update the system to the latest version; the electronic device can also configure the application update operation as a preset operation, so as to perform the application update operation in the predicted sleep interval and update the installed application to The latest version, etc.; the electronic device can configure the power consumption control operation as a preset operation, thereby applying a preset power consumption control strategy for reducing power consumption in the predicted sleep interval, reducing the power consumption of the electronic device, and so on.
  • the electronic device provides a preset operation configuration interface.
  • the preset operation configuration interface includes the prompt message "Please select the operation performed during sleep", operation selection box, drop-down button, drop-down Menu, OK button, and Cancel button.
  • the drop-down menu is called out according to the user's click operation on the drop-down button.
  • the drop-down menu provides various operations that the electronic device can perform during the user's sleep interval, as shown in the system update in Figure 4 Operation, application update operations, etc., the user can select the operation performed by the electronic device in the user's sleep interval according to actual needs, and after selecting the operation that needs to be performed by the electronic device in the user's sleep interval, click the OK button to instruct the electronic device to The operation selected by the user is the aforementioned preset operation. Or, if the user finds that there is no need for an operation performed by the electronic device during the user's sleep interval, he can click the cancel button to instruct the electronic device to perform a preset operation of the default configuration.
  • the electronic device when the electronic device determines its current usage scenario according to its current state information, it can execute:
  • the electronic device determines from the multiple usage scenarios the usage scenario whose status information matches its current status information according to the prestored status information of multiple usage scenarios;
  • the electronic device regards the use scene whose state information matches its current state information as its current use scene.
  • the electronic device locally pre-stores the status information of multiple different usage scenarios (or, using multiple different status information to respectively describe multiple different usage scenarios), such as the status information of the home vacation scenario and the status of the outing travel scenario Information, status information of work travel scenes, and status information of daily work scenes.
  • an electronic device determines its current usage scenario based on its current status information, it can determine the usage scenario whose status information matches its current status information from the multiple usage scenarios based on its pre-stored status information of multiple usage scenarios, and The usage scenario where the status information matches its current status information is taken as its current usage scenario.
  • the electronic device determines from the multiple usage scenarios a usage scenario whose status information matches its current status information based on the prestored status information of multiple usage scenarios, including:
  • the electronic device obtains the similarity between the status information of each usage scene and its current status information
  • the electronic device determines a usage scenario whose similarity reaches a preset similarity as a usage scenario whose state information matches its current state information.
  • the electronic device can determine whether the two status information matches according to the similarity between the two status information. In this way, when the electronic device determines the usage scenario in which the status information matches its current status information, it can obtain each status information separately.
  • the similarity between the state information of the use scene and its current state information, and the use scene whose similarity reaches a preset similarity is determined as the use scene whose state information matches the current state information.
  • the electronic device prestores state information of a home vacation scene, state information of a travel scene, state information of a work trip scene, and state information of a daily work scene, and the preset similarity is configured to be 85%. If the electronic device obtains that the status information of the home vacation scene is similar to its current status information at 40%, the status information of the outing travel scene is similar to its current status information at 45%, and the status information of the work trip scene is similar to its current status information. The similarity is 70%, and the similarity between the status information of the daily work scene and its current status information is 86%. It can be seen that the similarity between the status information of the daily work scene and the current status information of the electronic device reaches the preset similarity (85 %), the electronic device determines the daily work scene as the use scene whose status information matches its current status information.
  • the electronic device when acquiring the similarity between the status information of each usage scene and its current status information, the electronic device may execute:
  • the electronic device separately obtains the word vector sets of the status information of each usage scenario, and obtains multiple first word vector sets;
  • the electronic device obtains the word vector set of its current state information, and obtains the second word vector set;
  • the electronic device separately calculates the distance between each first word vector set and the second word vector set
  • the electronic device uses the calculated distances as the similarity between the status information of each usage scene and its current status information.
  • the electronic device when the electronic device obtains the similarity between the status information of each usage scene and its current status information, the electronic device characterizes any status information among the status information of multiple usage scenes stored in advance. Extract, obtain the word vector set of the state information of each use scene, and record the word vector set of the state information of each use scene as the first word vector set. In addition, the electronic device also performs feature extraction on its current state information, and obtains the word vector set of its current state information, which is recorded as the second word vector set.
  • the electronic device After the electronic device obtains the first word vector set of the state information of each usage scene and the second word vector set of its current state information, it calculates the difference between each first word vector set and the second word vector set. The distance is calculated as the similarity between the status information of each usage scene and its current status information.
  • the cosine distance between the first word vector set and the second word vector set can be obtained by referring to the following formula:
  • e represents the cosine distance between the first word vector set and the second word vector set
  • f represents the first word vector set
  • N represents the dimensions of the first word vector set and the second word vector set (the dimensions of the two word vector sets Same)
  • f i represents the word vector of the i-th dimension in the first word vector set (the state information of a usage scenario includes state information of multiple dimensions, such as use state information, location state information, environmental state information, etc.
  • the dimension word vector is the word vector of the state information of the i-th dimension
  • g i represents the word vector of the i-th dimension in the second word vector set.
  • the electronic device when the electronic device obtains the word vector set of its current state information and obtains the second word vector set, it can execute:
  • the electronic device inputs its current state information into the encoder neural network
  • the electronic device uses the word vector set of the current state information output by the encoder neural network as the second word vector set.
  • the current state information may be segmented into the encoder neural network and processed by the encoder neural network. Then output the word vector vector corresponding to the aforementioned current state information, and correspondingly, the electronic device uses the word vector set of the aforementioned current state information output by the encoder neural network as the second word vector set.
  • a single-layer recurrent neural network can be used for training to obtain the encoder neural network, or a multi-layer recurrent neural network can be used.
  • the encoder neural network obtained by training may also be trained using a convolutional neural network, or its variants, or a neural network of other network structures to obtain an encoder neural network.
  • the electronic device when the electronic device separately obtains the word vector sets of the status information of each usage scenario to obtain multiple first word vector sets, it may execute:
  • the electronic device respectively inputs the state information of each use scene into the encoder neural network, and uses the word vector set of the state information of each use scene output by the encoder neural network as the first word vector set.
  • the electronic device when the electronic device determines its current usage scenario according to its current state information, it can execute:
  • the electronic device recognizes the use scene corresponding to its current state information according to its current state information and the use scene recognition model as its current use scene.
  • a usage scene recognition model for usage scene recognition can be pre-trained, and the usage scene recognition model can be configured locally in the electronic device.
  • the electronic device determines its current usage scenario based on its current status information, it can input its current status information into the configured usage scenario recognition model, and the usage scenario recognition model can identify the usage scenario corresponding to the aforementioned current status information, and Output.
  • the electronic device uses the use scene corresponding to the aforementioned current state information output by the use scene recognition model as its current use scene.
  • the electronic device when the electronic device predicts the user's sleep according to the pre-trained sleep prediction model corresponding to the current usage scenario, and obtains the prediction result, it can execute:
  • the obtained work and rest behavior parameters and usage parameters are input into the sleep prediction model for sleep prediction, and the prediction result output by the sleep prediction model is obtained.
  • the electronic device first obtains the target sleep prediction model (that is, the sleep prediction model corresponding to the current use scene) for the feature parameters required for sleep prediction, and the feature parameters include the user's work and rest behavior parameters and the user's operating parameters of the electronic device. Then, the obtained characteristic parameters are input to the target sleep prediction model, and the target sleep prediction model predicts the user and outputs the prediction result.
  • the target sleep prediction model that is, the sleep prediction model corresponding to the current use scene
  • the feature parameters include the user's work and rest behavior parameters and the user's operating parameters of the electronic device.
  • FIG. 5 is a schematic structural diagram of a sleep prediction device provided by an embodiment of the application.
  • the sleep prediction device can be applied to electronic equipment.
  • the sleep prediction device may include: an acquisition module 401, a determination module 402, a selection module 403, and a prediction module 403.
  • the obtaining module 401 is used to obtain current state information of the electronic device
  • the determining module 402 is configured to determine the current usage scenario of the electronic device according to the aforementioned current state information
  • the prediction module 403 is configured to perform sleep prediction on the user according to the pre-trained sleep prediction model corresponding to the current use scene, and obtain the prediction result.
  • the determining module 402 when determining the current usage scenario of the electronic device according to the aforementioned current state information, the determining module 402 may be used to:
  • the pre-stored status information of multiple usage scenarios determine the usage scenario whose status information matches the aforementioned current status information from the multiple usage scenarios;
  • the use scene whose state information matches the aforementioned current state information is taken as the current use scene.
  • the determining module 402 when determining a usage scenario whose status information matches the foregoing current status information from the multiple usage scenarios according to the prestored status information of multiple usage scenarios, the determining module 402 may be used to:
  • the use scenario where the similarity reaches the preset similarity is determined as the use scenario where the state information matches the foregoing current state information.
  • the determining module 402 when acquiring the similarity between the status information of each usage scenario and the aforementioned current status information, the determining module 402 may be used to:
  • the calculated distances are taken as the similarity between the state information of each usage scene and the aforementioned current state information.
  • the determining module 402 when obtaining the word vector set of the aforementioned current state information to obtain the second word vector set, the determining module 402 may be used to:
  • the word vector set of the foregoing current state information output by the encoder neural network is used as the second word vector set.
  • the determining module 402 may be used to:
  • the state information of each use scene is input into the encoder neural network, and the word vector set of the state information of each use scene output by the encoder neural network is used as the first word vector set.
  • the determining module 402 when determining the current usage scenario of the electronic device according to the aforementioned current state information, the determining module 402 may be used to:
  • the usage scene corresponding to the aforementioned current status information is identified as the aforementioned current usage scene.
  • the prediction module 403 may be used to:
  • the obtained work and rest behavior parameters and usage parameters are input into the sleep prediction model for sleep prediction, and the prediction result output by the sleep prediction model is obtained.
  • the prediction result includes the user's sleep interval
  • the sleep prediction device further includes an execution module for:
  • a preset operation is performed, where the preset operation includes a system update operation, an application update operation, and/or a power consumption control operation.
  • the acquiring module 401 when acquiring the current state information of the electronic device, the acquiring module 401 may be used to:
  • the embodiment of the present application provides a computer-readable storage medium on which a computer program is stored.
  • the stored computer program is executed on a computer, the computer is caused to execute the steps in the sleep prediction method provided in the embodiment of the present application.
  • An embodiment of the present application further provides an electronic device including a memory and a processor, and the processor executes the steps in the sleep prediction method provided in the embodiment of the present application by calling a computer program stored in the memory.
  • FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the application.
  • the electronic device may include a memory 601 and a processor 602.
  • a person of ordinary skill in the art can understand that the structure of the electronic device shown in FIG. 6 does not constitute a limitation on the electronic device, and may include more or less components than those shown in the figure, or a combination of certain components, or different component arrangements. .
  • the memory 601 can be used to store application programs and data.
  • the application program stored in the memory 601 contains executable code.
  • Application programs can be composed of various functional modules.
  • the processor 602 executes various functional applications and data processing by running application programs stored in the memory 601.
  • the processor 602 is the control center of the electronic device. It uses various interfaces and lines to connect the various parts of the entire electronic device, and executes the electronic device by running or executing the application program stored in the memory 601 and calling the data stored in the memory 601
  • the various functions and processing data of the electronic device can be used to monitor the electronic equipment as a whole.
  • the processor 602 in the electronic device will load the executable code corresponding to the process of one or more audio processing programs into the memory 601 according to the following instructions, and the processor 602 will run and store the executable code
  • the application program in the memory 601 thus executes:
  • the user is predicted to sleep to obtain the prediction result.
  • FIG. 7 is another schematic structural diagram of the electronic device provided by an embodiment of the application. The difference from the electronic device shown in FIG. 6 is that the electronic device further includes components such as an input unit 603 and an output unit 604.
  • the input unit 603 can be used to receive inputted numbers, character information or user characteristic information (such as fingerprints), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
  • user characteristic information such as fingerprints
  • the output unit 604 may be used to output information input by the user or information provided to the user, such as a speaker.
  • the processor 602 in the electronic device will load the executable code corresponding to the process of one or more audio processing programs into the memory 601 according to the following instructions, and the processor 602 will run and store the executable code
  • the application program in the memory 601 thus executes:
  • the user is predicted to sleep to obtain the prediction result.
  • the processor 602 may execute:
  • the pre-stored status information of multiple usage scenarios determine the usage scenario whose status information matches the foregoing current status information from the multiple usage scenarios;
  • the use scene whose state information matches the aforementioned current state information is taken as the current use scene.
  • the processor 602 may execute:
  • the use scenario where the similarity reaches the preset similarity is determined as the use scenario where the state information matches the foregoing current state information.
  • the processor 602 may execute:
  • the calculated distances are taken as the similarity between the state information of each usage scene and the aforementioned current state information.
  • the processor 602 may execute:
  • the word vector set of the foregoing current state information output by the encoder neural network is used as the second word vector set.
  • the processor 602 may execute:
  • the state information of each use scene is input into the encoder neural network, and the word vector set of the state information of each use scene output by the encoder neural network is used as the first word vector set.
  • the processor 602 may execute:
  • the usage scene corresponding to the aforementioned current status information is identified as the aforementioned current usage scene.
  • the processor 602 may execute:
  • the obtained work and rest behavior parameters and usage parameters are input into the sleep prediction model for sleep prediction, and the prediction result output by the sleep prediction model is obtained.
  • the prediction result includes the user's sleep interval.
  • the processor 602 may execute:
  • a preset operation is performed, where the preset operation includes a system update operation, an application update operation, and/or a power consumption control operation.
  • the processor 602 may execute:
  • the sleep prediction device/electronic device provided by the embodiment of the application belongs to the same concept as the sleep prediction method in the above embodiment. Any method provided in the sleep prediction method embodiment can be run on the sleep prediction device/electronic device. For the implementation process, refer to the embodiment of the sleep prediction method, which will not be repeated here.
  • the program may be stored in a computer readable storage medium, such as stored in a memory, and executed by at least one processor, and the execution process may include a process such as an embodiment of the sleep prediction method.
  • the storage medium may be a magnetic disk, an optical disc, a read only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), etc.
  • the sleep prediction device of the embodiment of the present application its functional modules may be integrated in one processing chip, or each module may exist alone physically, or two or more modules may be integrated in one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium, such as a read-only memory, a magnetic disk, or an optical disk.

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种睡眠预测方法，应用于电子设备，使得电子设备可以获取其当前状态信息（101），并根据其当前状态信息确定其当前使用场景（102），进而利用对应其当前使用场景的睡眠预测模型对用户进行睡眠预测（103），能够提高对用户进行睡眠预测的准确度。

Description

睡眠预测方法、装置、存储介质及电子设备 技术领域
本申请属于计算机技术领域，尤其涉及一种睡眠预测方法、装置、存储介质及电子设备。
背景技术
目前，如平板电脑、手机等电子设备经过配置，可以在用户睡眠时进行系统更新等影响用户使用或者耗时较长的操作，以此来避免对用户的使用造成影响。为此，相关技术通过对用户进行睡眠预测，比如预测用户的睡眠区间等来达到前述目的，然而相关技术中对用户进行睡眠预测的准确度较低。
发明内容
本申请实施例提供一种睡眠预测方法、装置、存储介质及电子设备，可以使得电子设备能够准确的对用户进行睡眠预测。
第一方面，本申请实施例提供一种睡眠预测方法，应用于电子设备，包括：
获取所述电子设备的当前状态信息；
根据所述当前状态信息确定所述电子设备的当前使用场景；
根据预先训练的对应所述当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果。
第二方面，本申请实施例提供一种睡眠预测装置，应用于电子设备，包括：
获取模块，用于获取所述电子设备的当前状态信息；
确定模块，用于根据所述当前状态信息确定所述电子设备的当前使用场景；
预测模块，用于根据预先训练的对应所述当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果。
第三方面，本申请实施例提供一种存储介质，其上存储有计算机程序，其中，当所述计算机程序在计算机上执行时，使得所述计算机执行本申请实施例提供的睡眠预测方法中的步骤。
第四方面，本申请实施例提供一种电子设备，包括存储器，处理器，所述处理器通过调用所述存储器中存储的计算机程序，用于执行本申请实施例提供的睡眠预测方法中的步骤。
本申请实施例中，电子设备可以获取其当前状态信息，并根据其当前状态 信息确定其当前使用场景，进而利用对应其当前使用场景的睡眠预测模型对用户进行睡眠预测，能够提高对用户进行睡眠预测的准确度。
附图说明
下面结合附图，通过对本发明的具体实施方式详细描述，将使本发明的技术方案及其有益效果显而易见。
图1是本申请实施例提供的睡眠预测方法的一流程示意图。
图2是本申请实施例中从睡眠预测模型集合中选取目标睡眠预测模型的示意图。
图3是本申请实施例提供的睡眠预测方法的另一流程示意图。
图4是本申请实施例中提供的操作配置界面的示意图。
图5是本申请实施例提供的睡眠预测装置的结构示意图。
图6是本申请实施例提供的电子设备的一结构示意图。
图7是本申请实施例提供的电子设备的另一结构示意图。
具体实施方式
请参照图示，其中相同的组件符号代表相同的组件，本发明的原理是以实施在一适当的运算环境中来举例说明。以下的说明是基于所例示的本发明具体实施例，其不应被视为限制本发明未在此详述的其它具体实施例。
请参照图1，图1是本申请实施例提供的睡眠预测方法的一流程示意图。该睡眠预测方法可以应用于电子设备。该睡眠预测方法的流程可以包括：
在101中，获取电子设备的当前状态信息。
比如，电子设备可以在开机后，周期性的获取其状态信息，其中，状态信息包括但不限于用于描述电子设备当前的使用状态、位置状态以及环境状态等的相关信息。
应当说明的是，当前并不用于特指某时刻，而是用于代指电子设备执行获取状态信息这一操作的时刻。因此，本申请实施例中在电子设备每次执行获取状态信息的“当前时刻”，将对应获取到的状态信息记为“当前状态信息”。
在102中，根据前述当前状态信息确定电子设备的当前使用场景。
本申请实施例中，电子设备在获取到其当前状态信息之后，进一步根据获取到的当前状态信息确定其当前使用场景，其中，使用场景用于描述用户使用 电子设备所处的场景，包括但不限于居家休假场景、外出旅行场景、工作出差场景、日常工作场景等。
比如，电子设备根据获取到的当前状态信息确定其当前使用场景为居家场景。
在103中，根据预先训练的对应当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果。
需要说明的是，本申请实施例在电子设备预先存储有睡眠预测模型集合，该睡眠预测模型集合包括多个睡眠预测模型，分别适于在不同的使用场景下对用户的睡眠区间进行预测，其中，用户的睡眠区间至少包括用户进入睡眠的时刻以及用户醒来的时刻。
本申请实施例中，电子设备在根据其当前状态信息确定其当前使用场景后，进一步从睡眠预测模型集合中选取对应其当前使用场景的睡眠预测模型(或者说，适于在当前使用场景下对用户的睡眠区间进行预测的睡眠预测模型)，作为当前用于对用户的睡眠区间进行预测的目标睡眠预测模型。
比如，请参照图2，睡眠预测模型集合中包括四个睡眠预测模型，分别为适于在居家休假场景进行睡眠预测的A睡眠预测模型、适于在外出旅行场景进行睡眠预测的B睡眠预测模型、适于在工作出差场景进行睡眠预测的C睡眠预测模型以及适于在日常工作场景进行睡眠预测的D睡眠预测模型。若电子设备确定其当前使用场景为居家休假场景，则从睡眠预测模型集合中选取A睡眠预测模型作为目标睡眠预测模型；若电子设备确定其当前使用场景为外出旅行场景，则从睡眠预测模型集合中选取B睡眠预测模型作为目标睡眠预测模型；若电子设备确定其当前使用场景为工作出差场景，则从睡眠预测模型集合中选取C睡眠预测模型作为目标睡眠预测模型；若电子设备确定其当前使用场景为日常工作场景，则从睡眠预测模型中选取D睡眠预测模型作为目标睡眠预测模型。
应当说明的是，睡眠预测模型预先通过机器学习算法训练得到，机器学习算法可以通过不断的特征学习来实现各种功能，比如，可以根据用户的历史作息行为，对用户的睡眠区间进行预测。其中，机器学习算法可以包括：决策树模型、逻辑回归模型、贝叶斯模型、神经网络模型、聚类模型等等。
机器学习算法的算法类型可以根据各种情况划分，比如，可以基于学习方 式可以将机器学习算法划分成：监督式学习算法、非监控式学习算法、半监督式学习算法、强化学习算法等等。
在监督式学习下，输入数据被称为“训练数据”，每组训练数据有一个明确的标识或结果，如对防垃圾邮件系统中“垃圾邮件”“非垃圾邮件”，对手写数字识别中的“1“，”2“，”3“，”4“等。在建立识别模型的时候，监督式学习建立一个学习过程，将场景类型信息与“训练数据”的实际结果进行比较，不断的调整识别模型，直到模型的场景类型信息达到一个预期的准确率。监督式学习的常见应用场景如分类问题和回归问题。常见算法有逻辑回归(Logistic Regression)和反向传递神经网络(Back Propagation Neural Network)。
在非监督式学习中，数据并不被特别标识，识别模型是为了推断出数据的一些内在结构。常见的应用场景包括关联规则的学习以及聚类等。常见算法包括Apriori算法以及k-Means算法等。
半监督式学习算法，在此学习方式下，输入数据被部分标识，这种学习模型可以用来进行类型识别，但是模型首先需要学习数据的内在结构以便合理的组织数据来进行预测。应用场景包括分类和回归，算法包括一些对常用监督式学习算法的延伸，这些算法首先试图对未标识数据进行建模，在此基础上再对标识的数据进行预测。如图论推理算法(Graph Inference)或者拉普拉斯支持向量机(Laplacian SVM)等。
强化学习算法，在这种学习模式下，输入数据作为对模型的反馈，不像监督模型那样，输入数据仅仅是作为一个检查模型对错的方式，在强化学习下，输入数据直接反馈到模型，模型必须对此立刻作出调整。常见的应用场景包括动态系统以及机器人控制等。常见算法包括Q-Learning以及时间差学习(Temporal difference learning)。
此外，还可以基于根据算法的功能和形式的类似性将机器学习算法划分成：
回归算法，常见的回归算法包括：最小二乘法(Ordinary Least Square)，逻辑回归(Logistic Regression)，逐步式回归(Stepwise Regression)，多元自适应回归样条(Multivariate Adaptive Regression Splines)以及本地散点平滑估计(Locally Estimated Scatterplot Smoothing)。
基于实例的算法，包括k-Nearest Neighbor(KNN),学习矢量量化(Learning Vector Quantization，LVQ)，以及自组织映射算法(Self-Organizing Map， SOM)。
正则化方法，常见的算法包括：Ridge Regression，Least Absolute Shrinkage and Selection Operator(LASSO)，以及弹性网络(Elastic Net)。
决策树算法，常见的算法包括：分类及回归树(Classification And Regression Tree，CART)，ID3(Iterative Dichotomiser 3)，C4.5，Chi-squared Automatic Interaction Detection(CHAID),Decision Stump,随机森林(Random Forest)，多元自适应回归样条(MARS)以及梯度推进机(Gradient Boosting Machine，GBM)。
贝叶斯方法算法，包括：朴素贝叶斯算法，平均单依赖估计(Averaged One-Dependence Estimators，AODE)，以及Bayesian Belief Network(BBN)。
电子设备在从睡眠预测模型集合中选取出目标睡眠预测模型(也即是对应电子设备的当前使用场景的睡眠预测模型)之后，即可根据该目标睡眠预测模型对用户进行睡眠预测，得到预测结果。应当说明的是，对用户的睡眠预测包括但不限于进入睡眠的时刻、结束睡眠的时刻以及进入睡眠的时刻和结束睡眠的时刻所组成的睡眠区间等。比如，根据目标睡眠预测模型对用户进行睡眠预测，得到用户的的睡眠区间为当日23:30-次日06:60。
由上可知，本申请实施例中，电子设备可以获取其当前状态信息，并根据其当前状态信息确定其当前使用场景，进而从睡眠预测模型集合中选取对应其当前使用场景的目标睡眠预测模型，利用该目标睡眠预测模型对用户进行睡眠预测，能够提高对用户进行睡眠预测的准确度。
请参照图3，图3为本申请实施例提供的睡眠预测方法的另一流程示意图。该睡眠预测方法可以应用于电子设备。该睡眠预测方法的流程可以包括：
在201中，电子设备获取传感器采集的传感器数据。
在202中，电子设备根据传感器数据生成其当前状态信息。
本申请实施例中，电子设备可以在开机后，按照预设的信息获取周期(可由本领域普通技术人员根据经验取合适值，比如，可以设置为一个自然日)，周期性的获取其状态信息，其中，状态信息包括但不限于用于描述电子设备的使用状态、位置状态以及环境状态等的相关信息。
应当说明的是，当前并不用于特指某时刻，而是用于代指电子设备执行获 取状态信息这一操作的时刻。因此，本申请实施例中在电子设备每次执行获取状态信息的“当前时刻”，将对应获取到的状态信息记为“当前状态信息”。
本申请实施例中，电子设备可以利用自身配置的传感器来获取当前状态信息。其中，电子设备配置的传感器包括但不限于重力传感器、加速度传感器、定位传感器(如卫星定位传感器、基站定位传感器等)、声音传感器以及光线传感器等。
电子设备在“当前时刻”执行获取状态信息这一操作时，首先获取到其配置的传感器在“当前时刻”对应的当前信息获取周期内所采集的传感器数据，然后再根据这些传感器数据来生成当前状态信息。
比如，电子设备根据清洗出的重力传感器数据和加速度传感器数据生成用于描述其使用状态的状态信息，根据定位传感器数据生成用于描述其位置状态的状态信息，根据声音传感器和光线传感器生成用于描述其环境状态的状态信息等。
在203中，电子设备根据其当前状态信息确定其当前使用场景。
本申请实施例中，电子设备在获取到其当前状态信息之后，进一步根据获取到的当前状态信息确定其当前使用场景，其中，使用场景用于描述用户使用电子设备所处的场景，包括但不限于居家休假场景、外出旅行场景、工作出差场景、日常工作场景等。
比如，电子设备根据获取到的当前状态信息确定其当前使用场景为居家场景。
在204中，电子设备根据预先训练的对应当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到用户的睡眠区间。
需要说明的是，本申请实施例在电子设备预先存储有睡眠预测模型集合，该睡眠预测模型集合包括多个睡眠预测模型，分别适于在不同的使用场景下对用户的睡眠区间进行预测，其中，用户的睡眠区间至少包括用户进入睡眠的时刻以及用户醒来的时刻。
本申请实施例中，电子设备在根据其当前状态信息确定其当前使用场景后，进一步从睡眠预测模型集合中选取对应其当前使用场景的睡眠预测模型(或者说，适于在当前使用场景下对用户的睡眠区间进行预测的睡眠预测模型)，作为当前用于对用户的睡眠区间进行预测的目标睡眠预测模型。
比如，请参照图2，睡眠预测模型集合中包括四个睡眠预测模型，分别为适于在居家休假场景进行睡眠预测的A睡眠预测模型、适于在外出旅行场景进行睡眠预测的B睡眠预测模型、适于在工作出差场景进行睡眠预测的C睡眠预测模型以及适于在日常工作场景进行睡眠预测的D睡眠预测模型。若电子设备确定其当前使用场景为居家休假场景，则从睡眠预测模型集合中选取A睡眠预测模型作为目标睡眠预测模型；若电子设备确定其当前使用场景为外出旅行场景，则从睡眠预测模型集合中选取B睡眠预测模型作为目标睡眠预测模型；若电子设备确定其当前使用场景为工作出差场景，则从睡眠预测模型集合中选取C睡眠预测模型作为目标睡眠预测模型；若电子设备确定其当前使用场景为日常工作场景，则从睡眠预测模型中选取D睡眠预测模型作为目标睡眠预测模型。
其中，电子设备在从睡眠预测模型集合中选取出目标睡眠预测模型之后，即可根据该目标睡眠预测模型对用户进行睡眠预测，得到用户的睡眠区间。比如，预测得到用户的睡眠区间为当日23:30-次日06:60。
在205中，若到达预测的睡眠区间，且熄屏的持续时长达到预设时长，则电子设备执行预设操作。
本申请实施例中，电子设备在到达预测的睡眠区间时，侦测其熄屏的持续时长，从而根据该持续时长判断用户是否进入睡眠。其中，电子设备可以在其熄屏的持续时长达到预设时长时，判定用户进入睡眠。当判定用户进入睡眠时，电子设备执行预先配置的、在睡眠区间执行的预设操作。
应当说明的是，本申请实施例中对于预设时长的取值不做具体限定，可由本领域普通技术人员根据实际需要进行取值，比如，可以设置为5分钟。
此外，本申请实施例中对于预设操作的配置也不做限定，可以由用户手动配置，也可由电子设备缺省配置，比如，电子设备可以将系统更新操作配置为预设操作，从而在预测的睡眠区间内执行系统更新操作，将系统更新到最新版本；电子设备也可以将应用更新操作配置为预设操作，从而在预测的睡眠区间内执行应用更新操作，将已安装的应用程序更新到最新版本等；电子设备可以将功耗控制操作配置为预设操作，从而在预测的睡眠区间应用预设的用于降低功耗的功耗控制策略，降低电子设备的功耗等等。
又比如，请参照图4，电子设备提供有预设操作配置界面，如图4所示， 预设操作配置界面包括提示信息“请选择睡眠期间执行的操作”，操作选择框、下拉按钮、下拉菜单、确定按钮以及取消按钮，其中，下拉菜单根据用户对下拉按钮的点击操作呼出，下拉菜单中提供有电子设备可以在用户睡眠区间内执行的多种操作，如图4中示出的系统更新操作、应用更新操作等，用户可以根据实际需要选择电子设备在用户睡眠区间内执行的操作，并在选定需要由电子设备在用户睡眠区间内执行的操作后，点击确定按钮，指示电子设备将用户选择的操作作为前述预设操作。或者，若用户发现无需要电子设备在用户睡眠区间执行的操作，则可以点击取消按钮，指示电子设备执行缺省配置的预设操作。
在一实施方式中，电子设备在根据其当前状态信息确定其当前使用场景时，可以执行：
电子设备根据预存的多个使用场景的状态信息，从多个使用场景中确定出状态信息与其当前状态信息匹配的使用场景；
电子设备将状态信息与其当前状态信息匹配的使用场景作为其当前使用场景。
其中，电子设备本地预存有多个不同使用场景的状态信息(或者说，使用多个不同的状态信息分别描述了多个不同的使用场景)，比如居家休假场景的状态信息、外出旅行场景的状态信息、工作出差场景的状态信息以及日常工作场景的状态信息等。
电子设备在根据其当前状态信息确定其当前使用场景时，即可根据其预存的多个使用场景的状态信息，从多个使用场景中确定出状态信息与其当前状态信息匹配的使用场景，并将该状态信息与其当前状态信息匹配的使用场景作为其当前使用场景。
在一实施方式中，电子设备在根据预存的多个使用场景的状态信息，从多个使用场景中确定出状态信息与其当前状态信息匹配的使用场景，包括：
电子设备获取各使用场景的状态信息与其当前状态信息之间的相似度；
电子设备将相似度达到预设相似度的使用场景确定为状态信息与其当前状态信息匹配的使用场景。
本申请实施例中，电子设备可以根据两个状态信息之间的相似度来判断两个状态信息是否匹配，这样，电子设备在确定状态信息与其当前状态信息匹配的使用场景时，可以分别获取各使用场景的状态信息与其当前状态信息之间的 相似度，并将相似度达到预设相似度的使用场景确定为状态信息与其当前状态信息所匹配的使用场景。
应当说明的是，本申请实施例中对于预设相似度的取值不做具体限制，可由本领域普通技术人员根据实际需要取合适值。
比如，假设电子设备预存有居家休假场景的状态信息、外出旅行场景的状态信息、工作出差场景的状态信息以及日常工作场景的状态信息，且预设相似度被配置为85％。若电子设备获取到居家休假场景的状态信息与其当前状态信息的相似度为40％、外出旅行场景的状态信息与其当前状态信息的相似度为45％、工作出差场景的状态信息与其当前状态信息的相似度为70％、日常工作场景的状态信息与其当前状态信息的相似度为86％，可以看出，日常工作场景的状态信息与电子设备的当前状态信息的相似度达到预设相似度(85％)，电子设备将日常工作场景确定为状态信息与其当前状态信息所匹配的使用场景。
在一实施方式中，电子设备在获取各使用场景的状态信息与其当前状态信息之间的相似度时，可以执行：
电子设备分别获取各使用场景的状态信息的词向量集合，得到多个第一词向量集合；
电子设备获取其当前状态信息的词向量集合，得到第二词向量集合；
电子设备分别计算各第一词向量集合与第二词向量集合之间的距离；
电子设备将计算得到的各距离作为各使用场景的状态信息与其当前状态信息之间的相似度。
本申请实施例中，电子设备在获取各使用场景的状态信息与其当前状态信息之间的相似度时，对于预存的多个使用场景的状态信息中的任一状态信息，电子设备对其进行特征提取，获取到各使用场景的状态信息的词向量集合，并将各使用场景的状态信息的词向量集合记为第一词向量集合。此外，电子设备还对其当前状态信息进行特征提取，获取到其当前状态信息的词向量集合，记为第二词向量集合。
电子设备在获取到各使用场景的状态信息的第一词向量集合以及获取到的其当前状态信息的第二词向量集合之后，分别计算各第一词向量集合与第二词向量集合之间的距离，并将计算得到各距离作为各使用场景的状态信息与其当前状态信息之间的相似度。
其中，可由本领域普通技术人员根据实际需要选取任意一种特征距离(比如欧氏距离、曼哈顿距离、切比雪夫距离以及余弦距离等)来衡量两个词向量集合之间的距离。
比如，可以获取第一词向量集合和第二词向量集合的余弦距离，具体参照以下公式：
Figure PCTCN2019075356-appb-000001
其中，e表示第一词向量集合和第二词向量集合的余弦距离，f表示第一词向量集合，N表示第一词向量集合和第二词向量集合的维度(两个词向量集合的维度相同)，f i表示第一词向量集合中第i维度的词向量(一种使用场景的状态信息包括多种维度的状态信息，比如使用状态信息、位置状态信息、环境状态信息等，第i维度的词向量即第i维度的状态信息的词向量)，g i表示第二词向量集合中第i维度的词向量。
在一实施方式中，电子设备在获取其当前状态信息的词向量集合，得到第二词向量集合时，可以执行：
电子设备将其当前状态信息输入编码器神经网络；
电子设备将编码器神经网络输出的前述当前状态信息的词向量集合作为第二词向量集合。
本申请实施例中，电子设备在获取其当前状态信息的词向量集合，得到第二词向量集合时，可以对其当前状态信息进行分词操作后输入编码器神经网络，由编码器神经网络进行处理后输出对应前述当前状态信息的词向量向量，相应的，电子设备将编码器神经网络输出的前述当前状态信息的词向量集合作为第二词向量集合。
应当说明的是，本申请实施例并不限定编码器神经网络的具体模型和拓扑结构，比如，可以采用单层的递归神经网络进行训练得到编码器神经网络，也可以采用多层的递归神经网络进行训练得到编码器神经网络还可以采用卷积神经网络、或者其变种、或者其他网络结构的神经网络进行训练，得到编码器神经网络。
在一实施方式中，电子设备在分别获取各使用场景的状态信息的词向量集合，得到多个第一词向量集合时，可以执行：
电子设备分别将各使用场景的状态信息输入编码器神经网络，并将编码器神经网络输出的各使用场景的状态信息的词向量集合作为第一词向量集合。
在一实施方式中，电子设备在根据其当前状态信息确定其当前使用场景时，可以执行：
电子设备根据其当前状态信息以及使用场景识别模型，识别其当前状态信息对应的使用场景，作为其当前使用场景。
其中，可以预先训练用于使用场景识别的使用场景识别模型，并将该使用场景识别模型配置在电子设备本地。这样，电子设备在根据其当前状态信息确定其当前使用场景时，可以将其当前状态信息输入到配置的使用场景识别模型，由使用场景识别模型识别出前述当前状态信息所对应的使用场景，并输出。相应的，电子设备将使用场景识别模型输出的前述当前状态信息所对应的使用场景作为其当前使用场景。
在一实施方式中，电子设备在根据预先训练的对应当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果时，可以执行：
获取用户的作息行为参数以及对电子设备的使用参数；
将获取到的作息行为参数以及使用参数输入到前述睡眠预测模型进行睡眠预测，得到前述睡眠预测模型输出的预测结果。
其中，电子设备首先获取目标睡眠预测模型(也即是对应当前使用场景的睡眠预测模型)进行睡眠预测所需的特征参数，该特征参数包括用户的作息行为参数以及用户对电子设备的操作参数，然后将获取到的特征参数输入到目标睡眠预测模型，由目标睡眠预测模型对用户进行预测，并输出预测结果。
请参照图5，图5为本申请实施例提供的睡眠预测装置的结构示意图。该睡眠预测装置可以应用于电子设备。睡眠预测装置可以包括：获取模块401、确定模块402、选取模块403以及预测模块403。
获取模块401，用于获取电子设备的当前状态信息；
确定模块402，用于根据前述当前状态信息确定电子设备的当前使用场景；
预测模块403，用于根据预先训练的对应当前使用场景的睡眠预测模型， 对用户进行睡眠预测，得到预测结果。
在一实施方式中，在根据前述当前状态信息确定电子设备的当前使用场景时，确定模块402可以用于：
根据预存的多个使用场景的状态信息，从多个使用场景中确定出状态信息与前述当前状态信息匹配的使用场景；
将状态信息与前述当前状态信息匹配的使用场景作为当前使用场景。
在一实施方式中，在根据预存的多个使用场景的状态信息，从多个使用场景中确定出状态信息与前述当前状态信息匹配的使用场景时，确定模块402可以用于：
获取各使用场景的状态信息与前述当前状态信息之间的相似度；
将相似度达到预设相似度的使用场景确定为状态信息与前述当前状态信息匹配的使用场景。
在一实施方式中，在获取各使用场景的状态信息与前述当前状态信息之间的相似度时，确定模块402可以用于：
分别获取各使用场景的状态信息的词向量集合，得到多个第一词向量集合；
获取前述当前状态信息的词向量集合，得到第二词向量集合；
分别计算各第一词向量集合与第二词向量集合之间的距离；
将计算得到的各距离作为各使用场景的状态信息与前述当前状态信息之间的相似度。
在一实施方式中，在获取前述当前状态信息的词向量集合，得到第二词向量集合时，确定模块402可以用于：
将前述当前状态信息输入编码器神经网络；
将编码器神经网络输出的前述当前状态信息的词向量集合作为第二词向量集合。
在一实施方式中，在分别获取各使用场景的状态信息的词向量集合，得到多个第一词向量集合时，确定模块402可以用于：
分别将各使用场景的状态信息输入编码器神经网络，并将编码器神经网络输出的各使用场景的状态信息的词向量集合作为第一词向量集合。
在一实施方式中，在根据前述当前状态信息确定电子设备的当前使用场景时，确定模块402可以用于：
根据前述当前状态信息以及使用场景识别模型，识别前述当前状态信息对应的使用场景，作为前述当前使用场景。
在一实施方式中，在根据预先训练的对应当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果时，预测模块403可以用于：
获取用户的作息行为参数以及对电子设备的使用参数；
将获取到的作息行为参数以及使用参数输入到前述睡眠预测模型进行睡眠预测，得到前述睡眠预测模型输出的预测结果。
在一实施方式中，预测结果包括用户的睡眠区间，睡眠预测装置还包括执行模块，用于:
若到达预测的睡眠区间，且电子设备熄屏的持续时长达到预设时长，则执行预设操作，其中，预设操作包括系统更新操作、应用更新操作和/或功耗控制操作。
在一实施方式中，在获取电子设备的当前状态信息时，获取模块401可以用于：
获取电子设备的传感器采集的传感器数据；
根据获取到的传感器数据生成前述当前状态信息。
本申请实施例提供一种计算机可读的存储介质，其上存储有计算机程序，当其存储的计算机程序在计算机上执行时，使得计算机执行如本申请实施例提供的睡眠预测方法中的步骤。
本申请实施例还提供一种电子设备，包括存储器，处理器，处理器通过调用存储器中存储的计算机程序，执行本申请实施例提供的睡眠预测方法中的步骤。
请参照图6，图6为本申请实施例提供的电子设备的结构示意图。该电子设备可以包括存储器601以及处理器602。本领域普通技术人员可以理解，图6中示出的电子设备结构并不构成对电子设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
存储器601可用于存储应用程序和数据。存储器601存储的应用程序中包含有可执行代码。应用程序可以组成各种功能模块。处理器602通过运行存储在存储器601的应用程序，从而执行各种功能应用以及数据处理。
处理器602是电子设备的控制中心，利用各种接口和线路连接整个电子设备的各个部分，通过运行或执行存储在存储器601内的应用程序，以及调用存储在存储器601内的数据，执行电子设备的各种功能和处理数据，从而对电子设备进行整体监控。
在本申请实施例中，电子设备中的处理器602会按照如下的指令，将一个或一个以上的音频处理程序的进程对应的可执行代码加载到存储器601中，并由处理器602来运行存储在存储器601中的应用程序，从而执行：
获取电子设备的当前状态信息；
根据前述当前状态信息确定电子设备的当前使用场景；
根据预先训练的对应当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果。
请参照图7，图7为本申请实施例提供的电子设备的另一结构示意图，与图6所示电子设备的区别在于，电子设备还包括输入单元603和输出单元604等组件。
其中，输入单元603可用于接收输入的数字、字符信息或用户特征信息(比如指纹)，以及产生与用户设置以及功能控制有关的键盘、鼠标、操作杆、光学或者轨迹球信号输入等。
输出单元604可用于输出由用户输入的信息或提供给用户的信息，如扬声器等。
在本申请实施例中，电子设备中的处理器602会按照如下的指令，将一个或一个以上的音频处理程序的进程对应的可执行代码加载到存储器601中，并由处理器602来运行存储在存储器601中的应用程序，从而执行：
获取电子设备的当前状态信息；
根据前述当前状态信息确定电子设备的当前使用场景；
根据预先训练的对应当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果。
在一实施方式中，在根据前述当前状态信息确定电子设备的当前使用场景时，处理器602可以执行：
根据预存的多个使用场景的状态信息，从多个使用场景中确定出状态信息 与前述当前状态信息匹配的使用场景；
将状态信息与前述当前状态信息匹配的使用场景作为当前使用场景。
在一实施方式中，在根据预存的多个使用场景的状态信息，从多个使用场景中确定出状态信息与前述当前状态信息匹配的使用场景时，处理器602可以执行：
获取各使用场景的状态信息与前述当前状态信息之间的相似度；
将相似度达到预设相似度的使用场景确定为状态信息与前述当前状态信息匹配的使用场景。
在一实施方式中，在获取各使用场景的状态信息与前述当前状态信息之间的相似度时，处理器602可以执行：
分别获取各使用场景的状态信息的词向量集合，得到多个第一词向量集合；
获取前述当前状态信息的词向量集合，得到第二词向量集合；
分别计算各第一词向量集合与第二词向量集合之间的距离；
将计算得到的各距离作为各使用场景的状态信息与前述当前状态信息之间的相似度。
在一实施方式中，在获取前述当前状态信息的词向量集合，得到第二词向量集合时，处理器602可以执行：
将前述当前状态信息输入编码器神经网络；
将编码器神经网络输出的前述当前状态信息的词向量集合作为第二词向量集合。
在一实施方式中，在分别获取各使用场景的状态信息的词向量集合，得到多个第一词向量集合时，处理器602可以执行：
分别将各使用场景的状态信息输入编码器神经网络，并将编码器神经网络输出的各使用场景的状态信息的词向量集合作为第一词向量集合。
在一实施方式中，在根据前述当前状态信息确定电子设备的当前使用场景时，处理器602可以执行：
根据前述当前状态信息以及使用场景识别模型，识别前述当前状态信息对应的使用场景，作为前述当前使用场景。
在一实施方式中，在根据预先训练的对应当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果时，处理器602可以执行：
获取用户的作息行为参数以及对电子设备的使用参数；
将获取到的作息行为参数以及使用参数输入到前述睡眠预测模型进行睡眠预测，得到前述睡眠预测模型输出的预测结果。
在一实施方式中，预测结果包括用户的睡眠区间，在根据目标睡眠预测模型进行睡眠预测，得到预测结果之后，处理器602可以执行：
若到达预测的睡眠区间，且电子设备熄屏的持续时长达到预设时长，则执行预设操作，其中，预设操作包括系统更新操作、应用更新操作和/或功耗控制操作。
在一实施方式中，在获取电子设备的当前状态信息时，处理器602可以执行：
获取电子设备的传感器采集的传感器数据；
根据获取到的传感器数据生成前述当前状态信息。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见上文针对睡眠预测方法的详细描述，此处不再赘述。
本申请实施例提供的睡眠预测装置/电子设备与上文实施例中的睡眠预测方法属于同一构思，在睡眠预测装置/电子设备上可以运行睡眠预测方法实施例中提供的任一方法，其具体实现过程详见睡眠预测方法实施例，此处不再赘述。
需要说明的是，对本申请实施例睡眠预测方法而言，本领域普通技术人员可以理解实现本申请实施例睡眠预测方法的全部或部分流程，是可以通过计算机程序来控制相关的硬件来完成，计算机程序可存储于一计算机可读取存储介质中，如存储在存储器中，并被至少一个处理器执行，在执行过程中可包括如睡眠预测方法的实施例的流程。其中，的存储介质可为磁碟、光盘、只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)等。
对本申请实施例的睡眠预测装置而言，其各功能模块可以集成在一个处理芯片中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中，存储介质譬 如为只读存储器，磁盘或光盘等。
以上对本申请实施例所提供的一种睡眠预测方法、装置、存储介质以及电子设备进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上，本说明书内容不应理解为对本发明的限制。

Claims (12)

  1. 一种睡眠预测方法，应用于电子设备，其中，包括：
    获取所述电子设备的当前状态信息；
    根据所述当前状态信息确定所述电子设备的当前使用场景；
    根据预先训练的对应所述当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果。
  2. 根据权利要求1所述的睡眠预测方法，其中，所述根据所述当前状态信息确定所述电子设备的当前使用场景，包括：
    根据预存的多个使用场景的状态信息，从所述多个使用场景中确定出状态信息与所述当前状态信息匹配的使用场景；
    将所述状态信息与所述当前状态信息匹配的使用场景作为所述当前使用场景。
  3. 根据权利要求2所述的睡眠预测方法，其中，所述根据预存的多个使用场景的状态信息，从所述多个使用场景中确定出状态信息与所述当前状态信息匹配的使用场景，包括：
    获取各所述使用场景的状态信息与所述当前状态信息之间的相似度；
    将所述相似度达到预设相似度的使用场景确定为所述状态信息与所述当前状态信息匹配的使用场景。
  4. 根据权利要求3所述的睡眠预测方法，其中，所述获取各所述使用场景的状态信息与所述当前状态信息之间的相似度，包括：
    分别获取各所述使用场景的状态信息的词向量集合，得到多个第一词向量集合；
    获取所述当前状态信息的词向量集合，得到第二词向量集合；
    分别计算各所述第一词向量集合与所述第二词向量集合之间的距离；
    将计算得到的各所述距离作为各所述相似度。
  5. 根据权利要求4所述的睡眠预测方法，其中，所述获取所述当前状态信息的词向量集合，得到第二词向量集合，包括：
    将所述当前状态信息输入编码器神经网络；
    将所述编码器神经网络输出的所述当前状态信息的词向量集合作为所述 第二词向量集合。
  6. 根据权利要求1所述的睡眠预测方法，其中，所述根据所述当前状态信息确定所述电子设备的当前使用场景，包括：
    根据所述当前状态信息以及使用场景识别模型，识别所述当前状态信息对应的使用场景，作为所述当前使用场景。
  7. 根据权利要求1所述的睡眠预测方法，其中，所述根据预先训练的对应所述当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果，包括：
    获取所述用户的作息行为参数以及对电子设备的使用参数；
    将所述作息行为参数以及所述使用参数输入到所述睡眠预测模型进行睡眠预测，得到所述睡眠预测模型输出的预测结果。
  8. 根据权利要求1所述的睡眠预测方法，其中，所述预测结果包括用户的睡眠区间，所述根据预先训练的对应所述当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果之后，还包括：
    若到达所述睡眠区间，且所述电子设备熄屏的持续时长达到预设时长，则执行预设操作，所述预设操作包括系统更新操作、应用更新操作和/或功耗控制操作。
  9. 根据权利要求1所述的睡眠预测方法，其中，所述当前状态信息包括描述所述电子设备当前的使用状态、位置状态以及环境状态的信息。
  10. 一种睡眠预测装置，应用于电子设备，其中，包括：
    获取模块，用于获取所述电子设备的当前状态信息；
    确定模块，用于根据所述当前状态信息确定所述电子设备的当前使用场景；
    预测模块，用于根据预先训练的对应所述当前使用场景的睡眠预测模型，对用户进行睡眠预测，得到预测结果。
  11. 一种存储介质，其上存储有计算机程序，其中，当所述计算机程序在计算机上执行时，使得所述计算机执行如权利要求1至9中任一项所述的睡眠预测方法。
  12. 一种电子设备，包括存储器，处理器，其中，所述处理器通过调用所述存储器中存储的计算机程序，用于执行如权利要求1至9中任一项所述的睡眠预测方法。
PCT/CN2019/075356 2019-02-18 2019-02-18 睡眠预测方法、装置、存储介质及电子设备 WO2020168448A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/075356 WO2020168448A1 (zh) 2019-02-18 2019-02-18 睡眠预测方法、装置、存储介质及电子设备
CN201980080279.XA CN113164056A (zh) 2019-02-18 2019-02-18 睡眠预测方法、装置、存储介质及电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/075356 WO2020168448A1 (zh) 2019-02-18 2019-02-18 睡眠预测方法、装置、存储介质及电子设备

Publications (1)

Publication Number Publication Date
WO2020168448A1 true WO2020168448A1 (zh) 2020-08-27

Family

ID=72143913

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/075356 WO2020168448A1 (zh) 2019-02-18 2019-02-18 睡眠预测方法、装置、存储介质及电子设备

Country Status (2)

Country Link
CN (1) CN113164056A (zh)
WO (1) WO2020168448A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111887830A (zh) * 2020-09-10 2020-11-06 贵州省人民医院 睡眠监测方法、装置、设备及可读存储介质
CN114027795A (zh) * 2021-11-11 2022-02-11 展讯半导体(南京)有限公司 婴儿睡眠状态监测方法、装置、终端设备及可读存储介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3712784A3 (en) * 2019-03-20 2020-11-04 Tata Consultancy Services Limited System and method for signal pre-processing based on data driven models and data dependent model transformation
CN113420740B (zh) * 2021-08-24 2021-12-03 深圳小小小科技有限公司 一种智能家居的控制方法、电子设备及计算机可读介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105323384A (zh) * 2015-11-25 2016-02-10 上海斐讯数据通信技术有限公司 一种多场景模式切换的方法及移动终端
CN107861605A (zh) * 2017-11-06 2018-03-30 北京小米移动软件有限公司 数据处理方法及装置
CN107943266A (zh) * 2017-11-20 2018-04-20 北京小米移动软件有限公司 功耗控制方法、装置和设备
CN107995676A (zh) * 2017-11-24 2018-05-04 北京小米移动软件有限公司 终端控制方法及装置
WO2018221750A1 (ja) * 2017-06-02 2018-12-06 学校法人慶應義塾 睡眠判定装置、睡眠判定方法、および、睡眠判定プログラム
CN108965605A (zh) * 2018-07-27 2018-12-07 南昌黑鲨科技有限公司 智能手机的控制方法及装置
WO2019018750A1 (en) * 2017-07-20 2019-01-24 Bose Corporation EARPHONES FOR MEASURING AND ENHANCING BREATHING

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102036372B1 (ko) * 2017-06-12 2019-10-25 을지대학교 산학협력단 수면 교육 시스템 및 방법
CN107567083B (zh) * 2017-10-16 2021-07-30 北京小米移动软件有限公司 进行省电优化处理的方法和装置
CN108536099A (zh) * 2018-02-26 2018-09-14 维沃移动通信有限公司 一种信息处理方法、装置及移动终端
CN108937861A (zh) * 2018-06-06 2018-12-07 姜涵予 一种评测睡眠状态的方法及装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105323384A (zh) * 2015-11-25 2016-02-10 上海斐讯数据通信技术有限公司 一种多场景模式切换的方法及移动终端
WO2018221750A1 (ja) * 2017-06-02 2018-12-06 学校法人慶應義塾 睡眠判定装置、睡眠判定方法、および、睡眠判定プログラム
WO2019018750A1 (en) * 2017-07-20 2019-01-24 Bose Corporation EARPHONES FOR MEASURING AND ENHANCING BREATHING
CN107861605A (zh) * 2017-11-06 2018-03-30 北京小米移动软件有限公司 数据处理方法及装置
CN107943266A (zh) * 2017-11-20 2018-04-20 北京小米移动软件有限公司 功耗控制方法、装置和设备
CN107995676A (zh) * 2017-11-24 2018-05-04 北京小米移动软件有限公司 终端控制方法及装置
CN108965605A (zh) * 2018-07-27 2018-12-07 南昌黑鲨科技有限公司 智能手机的控制方法及装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111887830A (zh) * 2020-09-10 2020-11-06 贵州省人民医院 睡眠监测方法、装置、设备及可读存储介质
CN111887830B (zh) * 2020-09-10 2023-03-10 贵州省人民医院 睡眠监测方法、装置、设备及可读存储介质
CN114027795A (zh) * 2021-11-11 2022-02-11 展讯半导体(南京)有限公司 婴儿睡眠状态监测方法、装置、终端设备及可读存储介质

Also Published As

Publication number Publication date
CN113164056A (zh) 2021-07-23

Similar Documents

Publication Publication Date Title
WO2020168448A1 (zh) 睡眠预测方法、装置、存储介质及电子设备
CN108764304B (zh) 场景识别方法、装置、存储介质及电子设备
EP3467723A1 (en) Machine learning based network model construction method and apparatus
US20190095794A1 (en) Methods and apparatus for training a neural network
WO2021089013A1 (zh) 空间图卷积网络的训练方法、电子设备及存储介质
CN111079833B (zh) 图像识别方法、装置以及计算机可读存储介质
CN111797078A (zh) 数据清洗方法、模型训练方法、装置、存储介质及设备
WO2021007985A1 (zh) 基于tsk模糊模型的粒子滤波方法、装置及存储介质
CN107943582B (zh) 特征处理方法、装置、存储介质及电子设备
WO2020168444A1 (zh) 睡眠预测方法、装置、存储介质及电子设备
KR20200020545A (ko) 전자 장치 및 그 제어 방법
CN109784133B (zh) 动作评量模型生成装置及其动作评量模型生成方法
WO2019062369A1 (zh) 应用管理方法、装置、存储介质及电子设备
CN110782043A (zh) 模型优化方法、装置、存储介质及服务器
CN111512299A (zh) 用于内容搜索的方法及其电子设备
WO2020168451A1 (zh) 睡眠预测方法、装置、存储介质及电子设备
CN108806699B (zh) 语音反馈方法、装置、存储介质及电子设备
WO2022057660A1 (en) Smart home bubble creation
CN107861769B (zh) 应用清理方法、装置、存储介质及电子设备
Jeon et al. Ontology-based user intention recognition for proactive planning of intelligent robot behavior
CN116415624A (zh) 模型训练方法及装置、内容推荐方法及装置
CN107766105B (zh) 应用清理方法、装置、存储介质及电子设备
KR20210144510A (ko) 뉴럴 네트워크를 이용하는 데이터 처리 방법 및 데이터 처리 장치
US20190236410A1 (en) Bootstrapping recommendation systems from passive data
CN114792256B (zh) 基于模型选择的人群扩量方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19916139

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 26-01-2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19916139

Country of ref document: EP

Kind code of ref document: A1