WO2020168454A1 - 行为推荐方法、装置、存储介质及电子设备 - Google Patents

行为推荐方法、装置、存储介质及电子设备 Download PDF

Info

Publication number
WO2020168454A1
WO2020168454A1 PCT/CN2019/075367 CN2019075367W WO2020168454A1 WO 2020168454 A1 WO2020168454 A1 WO 2020168454A1 CN 2019075367 W CN2019075367 W CN 2019075367W WO 2020168454 A1 WO2020168454 A1 WO 2020168454A1
Authority
WO
WIPO (PCT)
Prior art keywords
behavior
user
electronic device
information
work
Prior art date
Application number
PCT/CN2019/075367
Other languages
English (en)
French (fr)
Inventor
戴堃
张寅祥
帅朝春
吴建文
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 CN201980080169.3A priority Critical patent/CN113168596A/zh
Priority to PCT/CN2019/075367 priority patent/WO2020168454A1/zh
Publication of WO2020168454A1 publication Critical patent/WO2020168454A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

Definitions

  • This application belongs to the field of computer technology, and in particular relates to a behavior recommendation method, device, storage medium, and electronic equipment.
  • Electronic devices such as smart phones and tablet computers appear in people's lives.
  • Electronic devices can install applications of different application types to provide users with different functions.
  • video applications can be installed to provide video playback functions
  • social service applications can be installed to provide social functions
  • game applications can be installed to provide games. Function, etc.
  • the embodiments of the present application provide a behavior recommendation method, device, storage medium, and electronic device, which can reduce the adverse effects on the user's body caused by using the electronic device.
  • an embodiment of the present application provides a behavior recommendation method applied to an electronic device, including:
  • an embodiment of the present application provides a behavior recommendation device applied to electronic equipment, including:
  • the first obtaining module is used to obtain usage information of the electronic device used by the user;
  • the second acquisition module is used to acquire work and rest behavior information that characterizes the user's work and rest behavior
  • the third obtaining module is configured to obtain behavior suggestions corresponding to the user according to the usage information, the work and rest behavior information, and a preset behavior recommendation model;
  • the suggestion display module is used to display the behavior suggestion to the user.
  • an embodiment of the present application provides a storage medium on which a computer program is stored, and when the computer program is executed on a computer, the computer is caused to execute the steps in the behavior recommendation method provided by the embodiment of the present application.
  • an embodiment of the present application provides an electronic device including a memory and a processor, and the processor is configured to execute the steps in the behavior recommendation method provided by the embodiment of the present application by calling a computer program stored in the memory .
  • the application embodiment it is possible to obtain the use information of the user using the electronic device, and obtain the work and rest behavior information that characterizes the user's work and rest behavior, and obtain the corresponding user's information according to the obtained use information, work and rest behavior information, and preset behavior recommendation model.
  • Behavior suggestions to show users the acquired behavior suggestions, so as to reduce the adverse effects on the user's body caused by the use of electronic devices that affect the normal work and rest.
  • FIG. 1 is a schematic flowchart of a behavior recommendation method provided by an embodiment of the present application.
  • Fig. 2 is a schematic diagram of obtaining behavior suggestions according to usage information, work and rest behavior information, and behavior recommendation models in an embodiment of the present application.
  • FIG. 3 is a schematic flowchart of another behavior recommendation method provided by an embodiment of the present application.
  • FIG. 4 is an example diagram of an electronic device acquiring work and rest behavior information in an embodiment of the present application.
  • Fig. 5 is an example diagram showing behavior suggestions on a screen in an embodiment of the present application.
  • Fig. 6 is another example diagram showing behavior suggestions on the screen in an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a behavior recommendation apparatus provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 9 is another schematic diagram of the structure of an electronic device provided by an embodiment of the present application.
  • FIG. 1 is a schematic flowchart of a behavior recommendation method provided by an embodiment of the present application.
  • the behavior recommendation method can be applied to electronic devices.
  • the process of the behavior recommendation method may include:
  • the usage information of the electronic device used by the user is acquired.
  • the electronic device can periodically obtain the user's electronic equipment 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.
  • Equipment usage information where usage information is used to describe how users use electronic devices, including but not limited to information describing where users use electronic devices, information describing when users use electronic devices, and information describing how users operate electronic devices One or more of the device information.
  • the electronic device when the electronic device reaches an information acquisition period, it acquires the usage information of the electronic device used by the user during the information acquisition period.
  • the work and rest behavior information characterizing the user's work and rest behavior is obtained.
  • the electronic device in addition to obtaining usage information of the user using the electronic device, the electronic device also obtains work and rest behavior information that characterizes the user's work and rest behavior.
  • the work and rest behavior information includes one or more of information used to describe when the user is resting (such as sleep, nap, etc.), information describing when the user is working, and information describing when the user is exercising.
  • 101 and 102 is not limited by the sequence number. 102 can be executed after 101, 102 can be executed before 101, or 101 and 102 can be executed in parallel.
  • a behavior recommendation corresponding to the user is acquired.
  • a behavior recommendation model is pre-stored in the electronic device. As shown in FIG. 2, the behavior recommendation model takes the use information of the user using the electronic device and the user's work, rest and behavior information as input, and the corresponding The behavior suggestion is output. Among them, behavior suggestions include but are not limited to sleep suggestions or exercise suggestions.
  • the electronic device after the electronic device obtains the use information of the user using the electronic device and the work and rest behavior information that characterizes the user's work and rest behavior, the electronic device inputs the obtained use information and work and rest behavior information into the preset behavior recommendation model, And obtain the corresponding user's behavior suggestions output by the behavior recommendation model.
  • the behavior recommendation model will output a sleep recommendation "please rest as soon as possible”.
  • the behavior suggestion can also be a work suggestion.
  • the usage information and the work rest and behavior information describe "the user is always using certain applications during the time period when the user is originally working”
  • the behavior recommendation model will output the work Suggest "please concentrate on work”.
  • the obtained behavior suggestions are shown to the user.
  • the behavior suggestions can be displayed to users through audio, and behavior suggestions can be displayed to users through text. Show users behavior suggestions through pictures.
  • FIG. 3 is a schematic flowchart of another behavior recommendation method provided by an embodiment of this application.
  • the behavior recommendation method can be applied to electronic devices.
  • the process of the behavior recommendation method may include:
  • the usage information of the electronic device used by the user is acquired.
  • the electronic device can periodically obtain the user's electronic 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.
  • Equipment usage information where usage information is used to describe how users use electronic devices, including but not limited to information describing where users use electronic devices, information describing when users use electronic devices, and information describing how users operate electronic devices One or more of the device information.
  • the electronic device when the electronic device reaches an information acquisition period, it acquires the usage information of the electronic device used by the user during the information acquisition period.
  • the electronic device in addition to obtaining usage information of the user using the electronic device, the electronic device also obtains work and rest behavior information that characterizes the user's work and rest behavior.
  • the work and rest behavior information includes one or more of information used to describe when the user is resting (such as sleep, nap, etc.), information describing when the user is working, and information describing when the user is exercising.
  • 201 and 202 are not limited by the sequence number. 202 can be executed after 201, 202 can be executed before 201, or 201 and 202 can be executed in parallel.
  • "acquiring work and rest behavior information that characterizes the user's work and rest behavior” may include:
  • 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 obtains the work and rest behavior information that characterizes the user's work and rest behavior, it can obtain the sensor data collected by its configured sensor, and then generate the work and rest behavior information that characterizes the user's work and rest behavior according to the acquired sensor data.
  • the electronic device determines that the user is asleep during this time period, and accordingly generates a description of the user being asleep during the time period Work and rest behavior information.
  • the electronic device determines that the user is in motion during this time period, and accordingly generates a description of the user in motion during the time period Work and rest behavior information.
  • "acquiring work and rest behavior information that characterizes the user's work and rest behavior” may include:
  • the data acquisition request is used to instruct the wearable device to return the user's work and rest behavior information collected by it;
  • the electronic device is associated with the user's wearable device (for example, a smart bracelet, smart watch, smart jewelry, etc.) according to the input operation received from the user in advance.
  • the wearable device for example, a smart bracelet, smart watch, smart jewelry, etc.
  • Bluetooth pairing can be performed based on Bluetooth technology, and an association relationship with the wearable device can be established after the pairing is successful.
  • wearable devices are usually worn by users, and wearable devices can more accurately collect user's work and rest behavior information.
  • the electronic device when the electronic device obtains the work and rest behavior information that characterizes the user's work and rest behavior, on the one hand, it can generate a data acquisition request in accordance with the agreed message format, and send the generated data acquisition request to the pre-associated wearable device , Through the data acquisition request instructs the wearable device to return the collected user’s work and activity information; on the other hand, after the wearable device receives the data acquisition request from the electronic device, according to the data acquisition request, the collected user’s The work and rest behavior information is returned to the electronic device.
  • a behavior recommendation corresponding to the user is acquired.
  • a behavior recommendation model is pre-stored in the electronic device. As shown in FIG. 2, the behavior recommendation model takes the use information of the user using the electronic device and the user's work, rest and behavior information as input, and the corresponding The behavior suggestion is output. Among them, behavior suggestions include but are not limited to sleep suggestions or exercise suggestions.
  • the electronic device after the electronic device obtains the use information of the user using the electronic device and the work and rest behavior information that characterizes the user's work and rest behavior, the electronic device inputs the obtained use information and work and rest behavior information into the preset behavior recommendation model, And obtain the corresponding user's behavior suggestions output by the behavior recommendation model.
  • the behavior recommendation model will output a sleep recommendation "please rest as soon as possible”.
  • the behavior suggestion can also be a work suggestion.
  • the usage information and the work rest and behavior information describe "the user is always using certain applications during the time period when the user is originally working”
  • the behavior recommendation model will output the work Suggest "please concentrate on work”.
  • the obtained behavior suggestions are displayed to the user through the screen of the electronic device.
  • the obtained behavior suggestion is displayed to the user through the audio output module of the electronic device.
  • the electronic device uses different methods to show the acquired behavior suggestions to the user according to whether the user is looking at its screen.
  • the electronic device first determines whether the user is gazing at the screen of the electronic device.
  • the electronic device can use eye tracking technology to track the gaze position of the user. If the gaze position of the user is on the screen, it can be determined that the user is gazing at the screen.
  • the electronic device displays the acquired behavior suggestions to the user in the form of text or pictures through the screen.
  • the electronic device shows the acquired behavior suggestions to the user through the audio output module of the electronic device.
  • the audio output module may be an audio output module built into the electronic device (such as a built-in speaker), or an audio output module external to the electronic device (such as an external speaker, earphone, etc.).
  • wearable devices are usually worn by users, and the location of the wearable device is the location of the user. Therefore, the electronic device can obtain the distance between it and the pre-associated wearable device, and use this distance as the distance between it and the user. For example, the electronic device can use positioning technology to obtain its first position, and at the same time instruct the pre-associated wearable device to use positioning technology to obtain its second position, and return to the electronic device. Thus, the electronic device The distance between it and the pre-associated wearable device can be calculated according to the first position and the second position.
  • the electronic device After the electronic device obtains the distance between it and the pre-associated wearable device, it further determines whether the distance between it and the pre-associated wearable device is less than or equal to the preset distance, wherein, if the result of the judgment is yes, then The electronic device determines that the user can hear the aforementioned behavior suggestion output by the audio output module. If the determination result is no, the electronic device determines that the user cannot hear the aforementioned behavior suggestion output by the audio output module.
  • the preset distance can be set by a person of ordinary skill in the art based on experience, and the embodiment of the present application does not specifically limit its value.
  • the electronic device determines whether the distance between it and the pre-associated wearable device is less than or equal to the preset distance, if the obtained judgment result is yes, then the user
  • the aforementioned behavior suggestion output by the audio output module can be heard, and at this time, the electronic device can output the aforementioned behavior suggestion in audio through its audio output module, and display the aforementioned behavior suggestion to the user.
  • the method further includes:
  • the acquired behavior suggestion is sent to the pre-associated wearable device, and the pre-associated wearable device is instructed to display the aforementioned behavior suggestion to the user.
  • the electronic device determines whether the distance between the electronic device and the pre-associated wearable device is less than or equal to the preset distance, if the obtained judgment result is no, then the user The aforementioned behavior suggestions output by the audio output module cannot be heard. At this time, the electronic device can send the acquired behavior suggestions to the pre-associated wearable device, and instruct the pre-associated wearable device to show the aforementioned behavior to the user Suggest.
  • the manner in which the aforementioned wearable device displays behavior suggestions to users is not specifically limited.
  • the behavior suggestions can be displayed to the user through audio, and the behavior suggestions can be displayed to the user through text. You can also show behavior suggestions to users through pictures.
  • "showing the acquired behavior suggestions to the user through the screen of the electronic device” may include:
  • a prompt box including behavior suggestions is generated, and the generated prompt box is displayed on the screen of the electronic device.
  • "showing the acquired behavior suggestions to the user through the screen of the electronic device” may include:
  • the electronic device when the electronic device displays the acquired behavior suggestions to the user through its screen, assuming that the acquired behavior suggestions are "please take eye protection exercises to relieve eyesight and rest as soon as possible", the electronic device can obtain The behavior suggestion is added to the scrolling display in the notification bar displayed on the screen.
  • "showing the acquired behavior suggestions to users” includes:
  • the behavior suggestions in the embodiments of this application are related to time, and there is a time difference between different time zones, and the time is also different.
  • the electronic device first determines its current time zone (because the electronic device is carried by the user, the electronic device is currently in The time zone is the time zone where the user is currently located), and then it is judged whether the current time zone is the preset time zone (for example, it can be configured as the time zone where the electronic device is at the time of collection of the aforementioned usage information and work and rest behavior information), Among them, if the judgment result is yes, it can be determined that the time zone where the electronic device is located has not changed, otherwise, it can be determined that the time zone where the electronic device is located has changed.
  • the time zone in which the electronic device is located has not changed, it means that the previously obtained behavior suggestion matches the current time zone of the user, and the aforementioned behavior suggestion can be directly shown to the user.
  • the method further includes:
  • the device can obtain the time difference between its current time zone and the preset time zone, and then adjust the aforementioned behavior suggestions based on the time difference to obtain the adjusted behavior suggestions that match the user's current time zone, and then show it to the user Suggested behavior after adjustment.
  • the behavior suggestion initially obtained by the electronic device is "please rest at 22:00”
  • the time difference between the current time zone of the electronic device and the preset time zone is 2 hours, such as 2 hours late, you can The behavior suggestion to be adjusted, the adjusted behavior suggestion "please rest at 20:00”.
  • the electronic device uses the current time as As a benchmark, a two-hour delay is used as the display time of the aforementioned behavior suggestion, that is, the aforementioned behavior suggestion is displayed after a two-hour delay.
  • the behavior recommendation method provided in the embodiment of the present application further includes:
  • the user's pre-configured work and rest plan is adjusted.
  • schedule includes but is not limited to wake-up alarm clock, schedule, etc.
  • the electronic device in addition to providing corresponding behavior suggestions to the user, can also adjust the user's pre-configured work and rest plan according to the user's work and rest behavior information.
  • the electronic device can delay the ringing time of the wake-up alarm clock configured by the user.
  • the sleep prediction model is obtained through machine learning algorithm training in advance, and the machine learning algorithm can achieve various functions through continuous feature learning. For example, it can provide information based on the user’s historical work and rest behavior information and the use of electronic equipment. Suggest healthy behaviors.
  • 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. Of 1, 2, 3, 4, etc.
  • 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 can obtain usage information samples and work and rest behavior information samples, and randomly combine the use information samples and work and rest behavior information samples to obtain multiple use information-work and rest behavior information sample pairs. Then, professionals (such as health experts) can give corresponding behavior suggestions based on these information sample pairs. For example, if the pair describes that the user is always using certain applications during the period of sleep time, you can suggest The user takes a nap, eye protection exercise, restful sleep or other small activities to relieve fatigue.
  • a supervised learning algorithm is used to take multiple sample pairs of usage information-work and rest and behavior information as training input, and behavior suggestions corresponding to each sample pair as target output, and perform model training to obtain a behavior recommendation model.
  • a general behavior recommendation model can be pre-trained by the server, and the general behavior recommendation model is recorded as the initial behavior recommendation model.
  • the electronic device may obtain the initial behavior recommendation model trained by the server from the server. Then, the electronic device obtains the user's physical sign data (such as gender, age, height, weight, etc.), and updates the initial behavior recommendation model (in layman's terms, personalization) according to the user's physical sign data, and obtains the match with the user Behavior recommendation model.
  • the electronic device updating the initial behavior recommendation model does not change the configuration of the initial behavior recommendation model, but changes the parameters of the initial behavior recommendation model, so that the updated initial behavior recommendation model can be output to the user Suggested actions that match.
  • FIG. 7 is a schematic structural diagram of a behavior recommendation apparatus provided by an embodiment of the application.
  • the behavior recommendation device can be applied to electronic equipment.
  • the behavior recommendation apparatus may include: a first acquisition module 401, a second acquisition module 402, a third acquisition module 403, and a suggestion display module 404.
  • the first obtaining module 401 is configured to obtain usage information of the electronic device used by the user;
  • the second obtaining module 402 is used to obtain work and rest behavior information that characterizes the user's work and rest behavior;
  • the third obtaining module 403 is configured to obtain behavior suggestions corresponding to the user according to the obtained usage information, work and rest behavior information, and preset behavior recommendation models;
  • the suggestion display module 404 is used to display the acquired behavior suggestions to the user.
  • the aforementioned behavior advice includes sleep advice or exercise advice.
  • the suggestion display module 404 may be used to:
  • the suggestion display module 404 can be used to:
  • the display time of the aforementioned behavior suggestion is determined according to the obtained time difference, and the aforementioned behavior suggestion is displayed when the determined display time is reached.
  • the behavior recommendation device further includes an adjustment module for:
  • the behavior recommendation device further includes a first model training module, configured to:
  • a machine learning algorithm is used to train to obtain the behavior recommendation model.
  • the behavior recommendation device further includes a second model training module, configured to:
  • the first obtaining module 401 obtains the usage information of the user using the electronic device, obtain the initial behavior recommendation model trained by the server;
  • the suggestion display module 404 when showing behavior suggestions to users, can be used to:
  • the aforementioned behavior suggestion is shown to the user through the audio output module of the electronic device.
  • the suggestion display module 404 may be used to:
  • the suggestion display module 404 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 behavior recommendation 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 behavior recommendation method provided in the embodiment of the present application by calling a computer program stored in the memory.
  • FIG. 8 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.
  • Those of ordinary skill in the art can understand that the structure of the electronic device shown in FIG. 8 does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different component arrangement .
  • 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:
  • FIG. 9 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. 8 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 aforementioned behavior advice includes sleep advice or exercise advice.
  • the processor 602 may execute:
  • the processor 602 may execute:
  • the display time of the aforementioned behavior suggestion is determined according to the obtained time difference, and the aforementioned behavior suggestion is displayed when the determined display time is reached.
  • processor 602 may further execute:
  • the processor 602 may execute:
  • the behavior recommendation model is obtained by training with a machine learning algorithm.
  • the processor 602 may execute:
  • the processor 602 may execute:
  • the aforementioned behavior suggestion is shown to the user through the audio output module of the electronic device.
  • the processor 602 may execute:
  • the processor 602 may execute:
  • the behavior recommendation apparatus/electronic device provided in the embodiment of the application belongs to the same concept as the behavior recommendation method in the above embodiment. Any method provided in the behavior recommendation method embodiment can be run on the behavior recommendation apparatus/electronic device. For the implementation process, refer to the behavior recommendation method embodiment, 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 may include a process such as an embodiment of the behavior recommendation method during execution.
  • 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 behavior recommendation device of the embodiment of the present application its functional modules may be integrated into one processing chip, or each module may exist alone physically, or two or more modules may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software function 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.

Abstract

一种行为推荐方法,应用于电子设备,可以获取用户使用电子设备的使用信息(101),以及获取表征用户的作息行为的作息行为信息(102),并根据获取到的使用信息、作息行为信息以及预设的行为推荐模型,获取对应用户的行为建议(103),向用户展示行为建议(104),帮助用户规律作息,从而减少因使用电子设备而影响正常作息给用户身体造成的不良影响。

Description

行为推荐方法、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,尤其涉及一种行为推荐方法、装置、存储介质及电子设备。
背景技术
目前,随着计算机技术的广泛应用和发展,如智能手机和平板电脑等电子设备出现在人们的生活中。电子设备可以安装不同应用类型的应用来向用户提供不同的功能,比如,可以安装视频类应用以提供视频播放功能,可以安装社交服务类应用以提供社交功能,还可以安装游戏类应用以提供游戏功能,等等。然而,正是由于电子设备提供的这些功能,使得用户因使用电子设备,而影响正常作息,对用户的身体健康造成不良影响。
发明内容
本申请实施例提供一种行为推荐方法、装置、存储介质及电子设备,可以降低因使用电子设备而对用户身体造成的不良影响。
第一方面,本申请实施例提供一种行为推荐方法,应用于电子设备,包括:
获取用户使用所述电子设备的使用信息;
获取表征用户的作息行为的作息行为信息;
根据所述使用信息、所述作息行为信息以及预设的行为推荐模型,获取对应所述用户的行为建议;
向所述用户展示所述行为建议。
第二方面,本申请实施例提供一种行为推荐装置,应用于电子设备,包括:
第一获取模块,用于获取用户使用所述电子设备的使用信息;
第二获取模块,用于获取表征用户的作息行为的作息行为信息;
第三获取模块,用于根据所述使用信息、所述作息行为信息以及预设的行为推荐模型,获取对应所述用户的行为建议;
建议展示模块,用于向所述用户展示所述行为建议。
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,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行为推荐方法中的步骤。
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行为推荐方法中的步骤。
申请实施例中,可以获取用户使用电子设备的使用信息,以及获取表征用户的作息行为的作息行为信息,并根据获取到的使用信息、作息行为信息以及预设的行为推荐模型,获取对应用户的行为建议,向用户展示获取到的行为建议,从而减少因使用电子设备而影响正常作息给用户身体造成的不良影响。
附图说明
下面结合附图,通过对本申请的具体实施方式详细描述,将使本申请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行为推荐方法的一流程示意图。
图2是本申请实施例中根据使用信息、作息行为信息以及行为推荐模型获取行为建议的示意图。
图3是本申请实施例提供的行为推荐方法的另一流程示意图。
图4是本申请实施例中电子设备获取作息行为信息的示例图。
图5是本申请实施例中通过屏幕展示行为建议的一示例图。
图6是本申请实施例中通过屏幕展示行为建议的另一示例图。
图7是本申请实施例提供的行为推荐装置的结构示意图。
图8是本申请实施例提供的电子设备的一结构示意图。
图9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,本申请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申请具体实施例,其不应被视为限制本申请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行为推荐方法的一流程示意图。该行为推荐方法可以应用于电子设备。该行为推荐方法的流程可以包括:
在101中,获取用户使用电子设备的使用信息。
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), 周期性的获取用户使用电子设备的使用信息,其中,使用信息用于描述用户如何使用电子设备,包括但不限于描述用户在何地使用电子设备的信息、描述用户在何时使用电子设备的信息以及描述用户具体如何操作电子设备的信息中的一种或多种。
比如,电子设备在到达一信息获取周期时,获取用户在该信息获取周期内使用电子设备的使用信息。
在102中,获取表征用户的作息行为的作息行为信息。
本申请实施例中,电子设备除了获取用户使用电子设备的使用信息之外,还获取表征用户的作息行为的作息行为信息。其中,作息行为信息包括用于描述用户在何时休息(如睡眠、小憩等)的信息、描述用户在何时工作的信息以及描述用户在何时运动的信息中的一种或多种。
应当说明的是,101和102的执行顺序并不受序号限定,可以在101之后执行102,也可以在101之前执行102,还可以并行执行101和102。
在103中,根据获取到的使用信息、作息行为信息以及预设的行为推荐模型,获取对应用户的行为建议。
需要说明的是,本申请实施例中在电子设备预先存储有行为推荐模型,如图2所示,该行为推荐模型以用户使用电子设备的使用信息以及用户的作息行为信息为输入,以对应的行为建议为输出。其中,行为建议包括但不限于睡眠建议或运动建议等。
本申请实施例中,电子设备在获取到用户使用电子设备的使用信息以及获取到表征用户的作息行为的作息行为信息之后,将获取到的使用信息和作息行为信息输入预设的行为推荐模型,并获取到行为推荐模型输出的对应用户的行为建议。
比如,假设使用信息和作息行为信息描述了“用户在本来是睡眠时间的时间段内始终在使用某些应用”,则行为推荐模型将输出睡眠建议“请尽早休息”。
又比如,假设使用信息和作息行为信息描述了“用户在非睡眠时间段内始终在使用某些应用”,则行为推荐模型将输出运动建议“请运动放松一下”
在其他实施例中,行为建议还可以为工作建议,比如,假设使用信息和作息行为信息描述了“用户在本来是工作的时间段内始终在使用某些应用”,则行为推荐模型将输出工作建议“请专心工作”。
在104中,向用户展示获取到的行为建议。
应当说明的是,本申请实施例中对于电子设备如何向用户展示行为建议的方式不做具体限定,可以通过音频的方式向用户展示行为建议,可以通过文字的方式向用户展示行为建议,还可以通过图片的方式向用户展示行为建议等。
由上可知,本申请实施例中,可以获取用户使用电子设备的使用信息,以及获取表征用户的作息行为的作息行为信息,并根据获取到的使用信息、作息行为信息以及预设的行为推荐模型,获取对应用户的行为建议,向用户展示获取到的行为建议,帮助用户规律作息,从而减少因使用电子设备而影响正常作息给用户身体造成的不良影响。
请参照图3,图3为本申请实施例提供的行为推荐方法的另一流程示意图。该行为推荐方法可以应用于电子设备。该行为推荐方法的流程可以包括:
在201中,获取用户使用电子设备的使用信息。
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),周期性的获取用户使用电子设备的使用信息,其中,使用信息用于描述用户如何使用电子设备,包括但不限于描述用户在何地使用电子设备的信息、描述用户在何时使用电子设备的信息以及描述用户具体如何操作电子设备的信息中的一种或多种。
比如,电子设备在到达一信息获取周期时,获取用户在该信息获取周期内使用电子设备的使用信息。
在202中,获取表征用户的作息行为的作息行为信息。
本申请实施例中,电子设备除了获取用户使用电子设备的使用信息之外,还获取表征用户的作息行为的作息行为信息。其中,作息行为信息包括用于描述用户在何时休息(如睡眠、小憩等)的信息、描述用户在何时工作的信息以及描述用户在何时运动的信息中的一种或多种。
应当说明的是,201和202的执行顺序并不受序号限定,可以在201之后执行202,也可以在201之前执行202,还可以并行执行201和202。
作为一种可选的实施方式,“获取表征用户的作息行为的作息行为信息”可以包括:
(1)获取电子设备中传感器采集的传感器数据;
(2)根据获取到的传感器数据生成表征用户的作息行为的作息行为信息。
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。
电子设备在获取表征用户的作息行为的作息行为信息时,可以获取其配置的传感器所采集到的传感器数据,再根据获取到的传感器数据生成表征用户的作息行为的作息行为信息。
比如,在一时间段内,若定位传感器采集到的位置数据描述电子设备处于用户“家中”、声音传感器采集到的声音数据描述电子设备处于“安静环境”、光线传感器采集到的光线数据描述电子设备处于“暗光环境”且重力传感器和加速度传感器采集到的相应传感器数据未发生变化,则电子设备判定用户在该时间段内处于睡眠状态,相应生成描述用户在该时间段内处于睡眠状态的作息行为信息。
又比如,在一时间段内,若定位传感器采集到的位置数据描述电子设备处于“户外”、声音传感器采集到的声音数据描述电子设备处于“嘈杂环境”、光线传感器采集到的光线数据描述电子设备处于“亮光环境”且重力传感器和加速度传感器采集到的相应传感器数据未发生频繁变化,则电子设备判定用户在该时间段内处于运动状态,相应生成描述用户在该时间段内处于运动状态的作息行为信息。
作为另一种可选的实施方式,“获取表征用户的作息行为的作息行为信息”可以包括:
(1)发送数据获取请求至预关联的可穿戴设备,数据获取请求用于指示可穿戴设备返回其采集的用户的作息行为信息;
(2)接收可穿戴设备返回的作息行为信息。
应当说明的是,在本申请实施例中,电子设备预先根据接收到用户的输入操作,与用户的可穿戴设备(比如,可以是智能手环、智能手表、智能首饰等)进行关联。比如,可以基于蓝牙技术进行蓝牙配对,并在配对成功后建立与可穿戴设备的关联关系。
容易理解的是,可穿戴设备通常由用户随身穿戴,可穿戴设备能够更为准 确的采集到用户的作息行为信息。请参照图4,电子设备在获取表征用户的作息行为的作息行为信息时,一方面,可以按照约定的报文格式生成数据获取请求,并将生成的数据获取请求发送至预关联的可穿戴设备,通过该数据获取请求指示可穿戴设备返回其采集的用户的作息行为信息;另一方面,可穿戴设备在接收到来自电子设备的数据获取请求之后,根据该数据获取请求,将采集的用户的作息行为信息返回至电子设备。
在203中,根据获取到的使用信息、作息行为信息以及预设的行为推荐模型,获取对应用户的行为建议。
需要说明的是,本申请实施例中在电子设备预先存储有行为推荐模型,如图2所示,该行为推荐模型以用户使用电子设备的使用信息以及用户的作息行为信息为输入,以对应的行为建议为输出。其中,行为建议包括但不限于睡眠建议或运动建议等。
本申请实施例中,电子设备在获取到用户使用电子设备的使用信息以及获取到表征用户的作息行为的作息行为信息之后,将获取到的使用信息和作息行为信息输入预设的行为推荐模型,并获取到行为推荐模型输出的对应用户的行为建议。
比如,假设使用信息和作息行为信息描述了“用户在本来是睡眠时间的时间段内始终在使用某些应用”,则行为推荐模型将输出睡眠建议“请尽早休息”。
又比如,假设使用信息和作息行为信息描述了“用户在非睡眠时间段内始终在使用某些应用”,则行为推荐模型将输出运动建议“请运动放松一下”
在其他实施例中,行为建议还可以为工作建议,比如,假设使用信息和作息行为信息描述了“用户在本来是工作的时间段内始终在使用某些应用”,则行为推荐模型将输出工作建议“请专心工作”。
在204中,判断用户是否注视于电子设备的屏幕,是则转入205,否则转入206。
在205中,通过电子设备的屏幕向用户展示获取到的行为建议。
在206中,通过电子设备的音频输出模组向用户展示获取到的行为建议。
在本申请实施例中,电子设备根据用户是否注视于其屏幕,采用不同的方式向用户展示获取到的行为建议。其中,电子设备首先判断用户是否注视于电子设备的屏幕,比如,电子设备可以采用眼球追踪技术追踪用户的注视位置, 若用户的注视位置位于屏幕之上,即可判定用户注视于其屏幕。
若判定用户注视于电子设备的屏幕,则电子设备通过其屏幕以文字或图片等方式向用户展示获取到的行为建议。
若判定用户未注视于电子设备的屏幕,则电子设备通过电子设备的音频输出模组向用户展示获取到的行为建议。其中,音频输出模组可以是电子设备内置的音频输出模组(比如内置扬声器),也可以是电子设备外接的音频输出模组(比如外置扬声器、耳机等)。
在一实施方式中,在“通过电子设备的音频输出模组向用户展示获取到的行为建议”之前,还包括:
(1)获取电子设备与预关联的可穿戴设备之间的距离;
(2)判断电子设备与预关联的可穿戴设备之间的距离是否小于或等于预设距离;
(3)若是,则通过电子设备的音频输出模组向用户展示获取到的行为建议。
应当说明的是,可穿戴设备通常由用户随身穿戴,可穿戴设备的位置即为用户的位置。因此,电子设备可以获取其与预关联的可穿戴设备之间的距离,将该距离作为其与用户之间的距离。比如,电子设备可以采用定位技术获取到其所处的第一位置,同时指示预关联的可穿戴设备采用定位技术获取到其所处的第二位置,并返回至电子设备,由此,电子设备可以根据该第一位置以及第二位置计算出其与预关联的可穿戴设备之间的距离。
电子设备在获取到其与预关联的可穿戴设备之间的距离之后,进一步判断其与预关联的可穿戴设备之间的距离是否小于或等于预设距离,其中,若判断结果为是,则电子设备判定用户能够听到其通过音频输出模组所输出的前述行为建议,若判断结果为否,则电子设备判定用户无法听到其通过音频输出模组所输出的前述行为建议。其中,预设距离可以由本领域普通技术人员根据经验进行设置,本申请实施例对其取值不做具体限定。
根据以上描述,本领域普通技术人员可以理解的是,在电子设备判断其与预关联的可穿戴设备之间的距离是否小于或等于预设距离之后,若得到的判断结果为是,则说明用户能够听到其通过音频输出模组所输出的前述行为建议,此时,电子设备即可通过其音频输出模组以音频的方式输出前述行为建议,将 前述行为建议展示给用户。
在一实施方式中,在“判断电子设备与预关联的可穿戴设备之间是否小于或等于预设距离”之后,还包括:
若否,则将获取到的行为建议发送至预关联的可穿戴设备,并指示预关联的可穿戴设备向用户展示前述行为建议。
根据以上描述,本领域普通技术人员可以理解的是,在电子设备判断其与预关联的可穿戴设备之间的距离是否小于或等于预设距离之后,若得到的判断结果为否,则说明用户无法听到其通过音频输出模组所输出的前述行为建议,此时,电子设备可以将获取到的行为建议发送至预关联的可穿戴设备,并指示预关联的可穿戴设备向用户展示前述行为建议。
应当说明的是,本申请实施例中对于前述可穿戴设备如何向用户展示行为建议的方式不做具体限定,可以通过音频的方式向用户展示行为建议,可以通过文字的方式向用户展示行为建议,还可以通过图片的方式向用户展示行为建议等。
在一实施方式中,“通过电子设备的屏幕向用户展示获取到的行为建议”可以包括:
生成包括行为建议的提示框,并在电子设备的屏幕中显示生成的提示框。
比如,请参照图5,电子设备在通过其屏幕向用户展示获取到的行为建议时,假设获取到的行为建议为“请做眼保运动缓解视力疲劳后尽早休息”,电子设备生成包括前述行为建议的提示框,并其屏幕中显示包括前述行为建议的提示框。
在一实施方式中,“通过电子设备的屏幕向用户展示获取到的行为建议”可以包括:
在电子设备的屏幕显示的通知栏中添加获取到的行为建议。
比如,请参照图6,电子设备在通过其屏幕向用户展示获取到的行为建议时,假设获取到的行为建议为“请做眼保运动缓解视力疲劳后尽早休息”,电子设备可以将获取到的行为建议添加至屏幕显示的通知栏中滚动显示。
在一实施方式中,“向用户展示获取到的行为建议”,包括:
(1)确定电子设备当前所处的时区,并判断电子设备当前所处的时区是否为预设时区;
(2)若是,则直接向用户展示前述行为建议。
应当说明的是,本申请实施例中的行为建议是与时间相关的,不同的时区之间存在时差,其时间也是不同的。为了确保向用户展示的行为建议是与用户所处时区所匹配的,在本申请实施例中,电子设备首先确定其当前所处的时区(由于电子设备由用户随身携带,电子设备当前所处的时区也即是用户当前所处的时区),然后判断其当前所处的时区是否为预设时区(比如,可以配置为电子设备在前述使用信息、作息行为信息的采集时刻所处的时区),其中,若判断结果为是,则可判定电子设备所处的时区未发生变化,否则判定电子设备所处的时区发生了变化。
基于以上描述,若电子设备所处的时区未发生变化,则说明前述获取到的行为建议是与用户当前所处的时区所匹配的,即可直接向用户展示前述行为建议。
在一实施方式中,“判断电子设备当前所处的时区是否为预设时区”之后,还包括:
(1)若否,则获取电子设备当前所处的时区与预设时区的时差;
(2)根据获取到的时差对前述行为建议进行调整,并向用户展示调整后的行为建议;或者,
(3)根据获取到的时差确定前述行为建议的展示时刻,并在到达确定的展示时刻时展示前述行为建议。
基于以上相关描述,本领域普通技术人员可以理解的是,若电子设备所处的时区发生了变化,则说明前述获取到的行为建议是与用户当前所处的时区所不匹配的,此时电子设备可以获取到其当前所处的时区与预设时区的时差,然后根据该时差对前述行为建议进行调整,得到调整后的、与用户当前所处的时区所匹配的行为建议,再向用户展示调整后的行为建议。
比如,假设电子设备初始获取到的行为建议为“请在22:00休息”,若电子设备当前所处的时区与预设时区的时差为2小时,比如晚2小时,则可以对初始获取到的行为建议进行调整,得到调整后的行为建议“请在20:00休息”。
又比如,假设电子设备初始获取到的行为建议为“到时间休息了”,若电子设备当前所处的时区与预设时区的时差为2小时,比如早2小时,则电子设备以当前时刻为基准,延后两小时作为前述行为建议的展示时刻,即延后2 小时再展示前述行为建议。
在一实施方式中,本申请实施例提供的行为推荐方法还包括:
根据前述作息行为信息对用户预先配置的作息计划进行调整。
应当说明的是,作息计划包括但不限于起床闹钟、事程安排等。
本申请实施例中,电子设备除了向用户提供对应的行为建议之外,还可以根据用户的作息行为信息对用户预先配置的作息计划进行调整。
比如,电子设备根据前述作息行为信息识别出用户加班到较晚的时间,则可延迟用户配置的起床闹钟的响铃时刻。
在一实施方式中,“获取用户使用电子设备的使用信息”之前,还包括:
采用机器学习算法训练得到行为推荐模型。
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信息以及使用电子设备的使用信息,给出健康的行为建议。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)。
在本申请实施例中,电子设备可以获取使用信息样本和作息行为信息样本,并将使用信息样本和作息行为信息样本进行随机组合,得到多个使用信息-作息行为信息样本对。然后,可由专业人员(比如健康专家)根据这些信息样本对给出对应的行为建议,比如,假设一样本对描述了用户在本来是睡眠时间的 时间段内始终在使用某些应用,则可以建议用户小憩、眼保运动、补觉或者其他小活动来缓解疲劳。
然后,采用监督学习算法,将多个使用信息-作息行为信息样本对作为训练输入、将各样本对对应的行为建议作为目标输出,进行模型训练得到行为推荐模型。
在一实施方式中,“获取用户使用电子设备的使用信息”之前,还包括:
(1)获取服务器训练的初始行为推荐模型;
(2)获取用户的体征数据,根据用户的体征数据对初始行为推荐模型进行更新,得到前述行为推荐模型。
其中,可由服务器预先训练一个通用的行为推荐模型,将该通用的行为推荐模型记为初始行为推荐模型。在本申请实施例中,电子设备可以从服务器获取到的服务器所训练的初始行为推荐模型。然后,电子设备获取用户的体征数据(比如性别、年龄、身高、体重等),并根据用户的体征数据对初始行为推荐模型进行更新(通俗的说,即个性化),得到与用户所匹配的行为推荐模型。
应当说明的是,电子设备对初始行为推荐模型进行更新并不对初始行为推荐模型的构型进行改动,而是对初始行为推荐模型的参数进行改动,使得更新后的初始行为推荐模型能够输出与用户所匹配的行为建议。
请参照图7,图7为本申请实施例提供的行为推荐装置的结构示意图。该行为推荐装置可以应用于电子设备。行为推荐装置可以包括:第一获取模块401、第二获取模块402、第三获取模块403以及建议展示模块404。
第一获取模块401,用于获取用户使用电子设备的使用信息;
第二获取模块402,用于获取表征用户的作息行为的作息行为信息;
第三获取模块403,用于根据获取到的使用信息、作息行为信息以及预设的行为推荐模型,获取对应用户的行为建议;
建议展示模块404,用于向用户展示获取到的行为建议。
在一实施方式中,前述行为建议包括睡眠建议或运动建议。
在一实施方式中,在向用户展示行为建议之前,建议展示模块404可以用于:
确定电子设备当前所处的时区,并判断电子设备当前所处的时区是否为预 设时区;
若是,则直接向用户展示前述行为建议。
在一实施方式中,在判断电子设备当前所处的时区是否为预设时区之后,建议展示模块404可以用于:
若否,则获取电子设备当前所处的时区与预设时区的时差;
根据获取到的时差对前述行为建议进行调整,并向用户展示调整后的行为建议;或者,
根据获取到的时差确定前述行为建议的展示时刻,并在到达确定的展示时刻时展示前述行为建议。
在一实施方式中,行为推荐装置还包括调整模块,用于:
根据作息行为信息对用户预先配置的作息计划进行调整。
在一实施方式中,行为推荐装置还包括第一模型训练模块,用于:
在第一获取模块401获取用户使用电子设备的使用信息之前,采用机器学习算法训练得到所述行为推荐模型。
在一实施方式中,行为推荐装置还包括第二模型训练模块,用于:
在第一获取模块401获取用户使用电子设备的使用信息之前,获取服务器训练的初始行为推荐模型;
获取用户的体征数据,根据获取到的体征数据对初始行为推荐模型进行更新,得到行为推荐模型。
在一实施方式中,在向用户展示行为建议时,建议展示模块404可以用于:
判断用户是否注视于电子设备的屏幕;
若是,则通过电子设备的屏幕向用户展示前述行为建议;
若否,则通过电子设备的音频输出模组向用户展示前述行为建议。
在一实施方式中,在通过电子设备的屏幕向用户展示前述行为建议时,建议展示模块404可以用于:
生成包括前述行为建议的提示框,并在屏幕中显示生成的提示框。
在一实施方式中,在通过电子设备的屏幕向用户展示前述行为建议时,建议展示模块404可以用于:
在屏幕显示的通知栏中添加前述行为建议。
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行为推荐方法中的步骤。
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行为推荐方法中的步骤。
请参照图8,图8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8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:
获取用户使用电子设备的使用信息;
获取表征用户的作息行为的作息行为信息;
根据获取到的使用信息、作息行为信息以及预设的行为推荐模型,获取对应用户的行为建议;
向用户展示获取到的行为建议。
请参照图9,图9为本申请实施例提供的电子设备的另一结构示意图,与图8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:
获取用户使用电子设备的使用信息;
获取表征用户的作息行为的作息行为信息;
根据获取到的使用信息、作息行为信息以及预设的行为推荐模型,获取对应用户的行为建议;
向用户展示获取到的行为建议。
在一实施方式中,前述行为建议包括睡眠建议或运动建议。
在一实施方式中,在向用户展示行为建议之前,处理器602可以执行:
确定电子设备当前所处的时区,并判断电子设备当前所处的时区是否为预设时区;
若是,则直接向用户展示前述行为建议。
在一实施方式中,在判断电子设备当前所处的时区是否为预设时区之后,处理器602可以执行:
若否,则获取电子设备当前所处的时区与预设时区的时差;
根据获取到的时差对前述行为建议进行调整,并向用户展示调整后的行为建议;或者,
根据获取到的时差确定前述行为建议的展示时刻,并在到达确定的展示时刻时展示前述行为建议。
在一实施方式中,处理器602还可以执行:
根据作息行为信息对用户预先配置的作息计划进行调整。
在一实施方式中,在获取用户使用电子设备的使用信息之前,处理器602可以执行:
采用机器学习算法训练得到所述行为推荐模型。
在一实施方式中,在获取用户使用电子设备的使用信息之前,处理器602 可以执行:
获取服务器训练的初始行为推荐模型;
获取用户的体征数据,根据获取到的体征数据对初始行为推荐模型进行更新,得到行为推荐模型。
在一实施方式中,在向用户展示行为建议时,处理器602可以执行:
判断用户是否注视于电子设备的屏幕;
若是,则通过电子设备的屏幕向用户展示前述行为建议;
若否,则通过电子设备的音频输出模组向用户展示前述行为建议。
在一实施方式中,在通过电子设备的屏幕向用户展示前述行为建议时,处理器602可以执行:
生成包括前述行为建议的提示框,并在屏幕中显示生成的提示框。
在一实施方式中,在通过电子设备的屏幕向用户展示前述行为建议时,处理器602可以执行:
在屏幕显示的通知栏中添加前述行为建议。
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,可以参见上文针对行为推荐方法的详细描述,此处不再赘述。
本申请实施例提供的行为推荐装置/电子设备与上文实施例中的行为推荐方法属于同一构思,在行为推荐装置/电子设备上可以运行行为推荐方法实施例中提供的任一方法,其具体实现过程详见行为推荐方法实施例,此处不再赘述。
需要说明的是,对本申请实施例行为推荐方法而言,本领域普通技术人员可以理解实现本申请实施例行为推荐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行为推荐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。
对本申请实施例的行为推荐装置而言,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行为推荐方法、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申请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申请的方法及其核心思想;同时,对于本领域的技术人员,依据本申请的思想,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申请的限制。

Claims (13)

  1. 一种行为推荐方法,应用于电子设备,其中,所述行为推荐方法包括:
    获取用户使用所述电子设备的使用信息;
    获取表征用户的作息行为的作息行为信息;
    根据所述使用信息、所述作息行为信息以及预设的行为推荐模型,获取对应所述用户的行为建议;
    向所述用户展示所述行为建议。
  2. 根据权利要求1所述的行为推荐方法,其中,所述向所述用户展示所述行为建议,包括:
    确定所述电子设备当前所处的时区,并判断所述时区是否为预设时区;
    若是,则直接向所述用户展示所述行为建议。
  3. 根据权利要求2所述的行为推荐方法,其中,所述判断所述时区是否为预设时区之后,还包括:
    若否,则获取所述时区与所述预设时区的时差;
    根据所述时差对所述行为建议进行调整,并向用户展示调整后的行为建议;
    或者,根据所述时差确定所述行为建议的展示时刻,并在到达所述展示时刻时展示所述行为建议。
  4. 根据权利要求1所述的行为推荐方法,其中,所述行为推荐方法还包括:
    根据所述作息行为信息对所述用户预先配置的作息计划进行调整。
  5. 根据权利要求1所述的行为推荐方法,其中,所述获取用户使用所述电子设备的使用信息之前,还包括:
    采用机器学习算法训练得到所述行为推荐模型。
  6. 根据权利要求1所述的行为推荐方法,其中,所述获取用户使用所述电子设备的使用信息之前,还包括:
    获取服务器训练的初始行为推荐模型;
    获取用户的体征数据,根据所述体征数据对所述初始行为推荐模型进行更新,得到所述行为推荐模型。
  7. 根据权利要求1所述的行为推荐方法,其中,所述向所述用户展示所 述行为建议,包括:
    判断所述用户是否注视于所述电子设备的屏幕;
    若是,则通过所述屏幕向用户展示所述行为建议;
    若否,则通过所述电子设备的音频输出模组向用户展示所述行为建议。
  8. 根据权利要求7所述的行为推荐方法,其中,所述通过所述屏幕向用户展示所述行为建议,包括:
    生成包括所述行为建议的提示框,并在所述屏幕中显示所述提示框。
  9. 根据权利要求7所述的行为推荐方法,其中,所述通过所述屏幕向用户展示所述行为建议,包括:
    在所述屏幕显示的通知栏中添加所述行为建议。
  10. 根据权利要求1所述的行为推荐方法,其中,所述行为建议包括睡眠建议或运动建议。
  11. 一种行为推荐装置,应用于电子设备,其中,包括:
    第一获取模块,用于获取用户使用所述电子设备的使用信息;
    第二获取模块,用于获取表征用户的作息行为的作息行为信息;
    第三获取模块,用于根据所述使用信息、所述作息行为信息以及预设的行为推荐模型,获取对应所述用户的行为建议;
    建议展示模块,用于向所述用户展示所述行为建议。
  12. 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10中任一项所述的行为推荐方法。
  13. 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10中任一项所述的行为推荐方法。
PCT/CN2019/075367 2019-02-18 2019-02-18 行为推荐方法、装置、存储介质及电子设备 WO2020168454A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980080169.3A CN113168596A (zh) 2019-02-18 2019-02-18 行为推荐方法、装置、存储介质及电子设备
PCT/CN2019/075367 WO2020168454A1 (zh) 2019-02-18 2019-02-18 行为推荐方法、装置、存储介质及电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/075367 WO2020168454A1 (zh) 2019-02-18 2019-02-18 行为推荐方法、装置、存储介质及电子设备

Publications (1)

Publication Number Publication Date
WO2020168454A1 true WO2020168454A1 (zh) 2020-08-27

Family

ID=72143966

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/075367 WO2020168454A1 (zh) 2019-02-18 2019-02-18 行为推荐方法、装置、存储介质及电子设备

Country Status (2)

Country Link
CN (1) CN113168596A (zh)
WO (1) WO2020168454A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104898834A (zh) * 2015-05-18 2015-09-09 百度在线网络技术(北京)有限公司 行为状态的调整方法及装置
CN106383450A (zh) * 2016-11-10 2017-02-08 北京工商大学 一种基于大数据的智能家居用户行为分析系统及方法
CN107609324A (zh) * 2017-10-11 2018-01-19 上海展扬通信技术有限公司 一种基于智能设备的用户作息的管理方法及管理装置
CN108876284A (zh) * 2018-05-14 2018-11-23 平安科技(深圳)有限公司 一种用户行为提示生成方法及终端设备

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105662394B (zh) * 2014-11-21 2019-02-05 中国移动通信集团公司 一种向用户提示信息的方法和装置
CN106210332A (zh) * 2016-07-21 2016-12-07 广东欧珀移动通信有限公司 控制方法及控制装置
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

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104898834A (zh) * 2015-05-18 2015-09-09 百度在线网络技术(北京)有限公司 行为状态的调整方法及装置
CN106383450A (zh) * 2016-11-10 2017-02-08 北京工商大学 一种基于大数据的智能家居用户行为分析系统及方法
CN107609324A (zh) * 2017-10-11 2018-01-19 上海展扬通信技术有限公司 一种基于智能设备的用户作息的管理方法及管理装置
CN108876284A (zh) * 2018-05-14 2018-11-23 平安科技(深圳)有限公司 一种用户行为提示生成方法及终端设备

Also Published As

Publication number Publication date
CN113168596A (zh) 2021-07-23

Similar Documents

Publication Publication Date Title
US11381450B1 (en) Altering digital therapeutics over time to achieve desired outcomes
CN107773214B (zh) 一种最佳唤醒策略的方法、计算机可读介质和系统
US9983775B2 (en) Dynamic user interfaces based on multiple data sources
US10978064B2 (en) Contextually relevant spoken device-to-device communication between IoT devices
CN107784357B (zh) 基于多模态深度神经网络的个性化智能唤醒系统及方法
KR102405405B1 (ko) 목표와 관련된 정보를 수신하도록 사용자를 허용하는 방법
US10108264B2 (en) System and method for embedded cognitive state metric system
US20180060500A1 (en) Smart health activity scheduling
US10559387B2 (en) Sleep monitoring from implicitly collected computer interactions
KR102585230B1 (ko) 통화 요청에 대한 알림 메시지를 제공하는 디바이스 및 방법
US11966317B2 (en) Electronic device and method for controlling same
CN111247782B (zh) 用于自动创建即时ad-hoc日历事件的方法和系统
US20150265211A1 (en) Device, method and application for establishing a current load level
WO2023040731A1 (zh) 用户姿势监测系统、方法及智能穿戴设备
Zhang et al. Multi-modal interactive fusion method for detecting teenagers’ psychological stress
WO2020168444A1 (zh) 睡眠预测方法、装置、存储介质及电子设备
US20220230753A1 (en) Techniques for executing transient care plans via an input/output device
WO2020168451A1 (zh) 睡眠预测方法、装置、存储介质及电子设备
WO2020168454A1 (zh) 行为推荐方法、装置、存储介质及电子设备
JPWO2019220745A1 (ja) 情報処理システム、情報処理方法、および記録媒体
US11393022B1 (en) Systems and methods for incentivizing saving
CN116802592A (zh) 使用自适应机制在iot环境中定制设备的方法和系统
US20240139629A1 (en) Effective multi-scale multi-granular targeting for game users
US20220351822A1 (en) Techniques for executing and modifying transient care plans via an input/output device
US11862034B1 (en) Variable content customization for coaching service

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: 19915656

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19915656

Country of ref document: EP

Kind code of ref document: A1