WO2024055931A1 - 运动推荐方法、睡眠推荐方法及其装置、电子设备及存储介质 - Google Patents

运动推荐方法、睡眠推荐方法及其装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2024055931A1
WO2024055931A1 PCT/CN2023/118017 CN2023118017W WO2024055931A1 WO 2024055931 A1 WO2024055931 A1 WO 2024055931A1 CN 2023118017 W CN2023118017 W CN 2023118017W WO 2024055931 A1 WO2024055931 A1 WO 2024055931A1
Authority
WO
WIPO (PCT)
Prior art keywords
sleep
target
exercise
data
historical
Prior art date
Application number
PCT/CN2023/118017
Other languages
English (en)
French (fr)
Inventor
史明澍
汪孔桥
汤猛帆
高屹
Original Assignee
安徽华米健康科技有限公司
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 安徽华米健康科技有限公司 filed Critical 安徽华米健康科技有限公司
Publication of WO2024055931A1 publication Critical patent/WO2024055931A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9538—Presentation of query results
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines

Definitions

  • the present application relates to the technical field of electronic equipment, and in particular to an exercise recommendation method, a sleep recommendation method and its device, electronic equipment and storage media.
  • This application provides an exercise recommendation method, a sleep recommendation method, a device, an electronic device and a storage medium.
  • the present application provides an exercise recommendation method, the method comprising: obtaining historical sleep data and historical exercise data of a target object through a terminal device, the historical sleep data including sleep data of at least one day before a target time period, and the historical exercise data including exercise data of at least one day before the target time period; obtaining a target exercise recommendation result for the target object in the target time period based on the historical sleep data and the historical exercise data, the target exercise recommendation result including at least one of a target recommended exercise time and a target recommended exercise amount; and outputting relevant information of the target exercise recommendation result.
  • the target exercise recommendation result of the target object in the target time period can be obtained based on the target object's historical sleep data and historical movement data, and the target exercise recommendation result can be recommended to the target object, thereby helping the target object to maintain scientific And regular exercise habits lay the foundation for the improvement of the target's exercise ability and the achievement of active health goals.
  • the historical sleep data of the target object can be data obtained by sleep monitoring of the target object, and can include all the sleep data of the target object monitored from a certain point in time, or can also include a part of the sleep data.
  • Data for example, sleep data of a specific length of time before the target time period, or sleep data that meets specific conditions before the target time period.
  • the historical motion data of the target object can be data obtained through motion monitoring of the target object, and can include all the motion data of the target object monitored from a certain point in time, or a part of the motion data, such as the target time. Movement data of a specific length of time before the segment, or movement data that meets specific conditions before the target time period.
  • Historical sleep data and historical exercise data may be data monitored in the same time period, or may be data monitored in different time periods. The different time periods may partially overlap, or the different time periods may not be the same. coincide.
  • the historical sleep data may include at least one of the following: sleep start time, sleep end time, sleep duration, sleep heart rate, sleep stage data, and sleep breathing data.
  • the historical exercise data may include at least one of the following: exercise start time, exercise end time, exercise duration, exercise intensity, exercise type, exercise heart rate, exercise impulse, and exercise energy consumption.
  • the time period uses one day as the time unit, for example, 1 natural day, or 24 hours starting from a certain point in time, etc.
  • the time when the method is executed is called the current day
  • the target exercise recommendation results of the target object in the target time period include the target exercise recommendation results of the target object in the next day, for example, the target exercise recommendation results of the current day, or tomorrow's target Exercise recommendation results.
  • a candidate exercise time set is determined based on at least part of the historical exercise time data included in the historical exercise data, and the candidate exercise time set includes at least one candidate exercise time; according to the historical sleep data, from the The target recommended exercise time is determined from the candidate exercise time set.
  • the set of candidate motion times may include one or more candidate motion times.
  • Historical motion data may include historical motion time data.
  • One or more candidate motion times may be determined based on part or all of the historical motion time data included in the historical motion data. For example, all exercise times included in historical exercise time data may be used as candidate exercise times.
  • the movement time that satisfies certain conditions among all the movement times included in the historical movement time data can also be used as the candidate movement time, for example, the movement time whose number of occurrences reaches a certain threshold in the historical movement time data can be used as the candidate movement time, etc. .
  • the candidate motion time is obtained by processing part or all of the historical motion time data.
  • historical exercise data is used to determine the target subject's exercise habits or preferences
  • historical sleep data is used to determine the target subject's sleeping habits or preferences.
  • Targeting can be performed in combination with the target subject's exercise habits or preferences and sleeping habits or preferences. Exercise recommendations for target objects.
  • the target recommended exercise time of the target object can be determined based on the target object's historical sleep data and historical movement data, and combined with the target object's movement and sleep habits or preferences, to help the target object maintain a scientific and regular schedule.
  • Exercise habits establish a foundation for improving the target's exercise ability and achieving active health goals.
  • the sleep type of the target object may be determined, and the target recommended exercise time may be determined from the set of candidate exercise times based on the sleep type of the target object and historical sleep data.
  • the sleep type of the target object is determined based on the historical sleep data of the target object. For example, a classification model is used to process the target object's historical sleep data to obtain the target object's sleep type.
  • the sleep type of the target subject is determined based on received user input information.
  • the sleep type of the target object may include one of the following: early bedtime type, late bedtime type, early riser type, late riser type, and sleep disorder type.
  • the historical sleep data includes historical sleep start time data
  • the target recommended exercise time can be determined from at least one candidate exercise time based on the historical sleep start time data.
  • the movement time offset corresponding to the sleep type of the target object can be determined from a plurality of preset movement time offsets; according to the corresponding movement time offset and the At least a portion of the historical sleep start time data included in the historical sleep data is used to determine the target recommended exercise time from the candidate exercise time set.
  • determine the exercise time requirement based on the historical sleep start time data included in the historical sleep data and the exercise time offset corresponding to the sleep type of the target object; and select the candidate exercise time set that satisfies all requirements. At least one candidate exercise time required for the exercise time is determined as the target recommended exercise time.
  • the exercise time requirement may be determined based on the target subject's historical sleep start time data for at least one day close to the target time period and the exercise time offset corresponding to the target subject's sleep type.
  • exercise time requirements may include: latest exercise time.
  • the latest exercise time may include the latest exercise start time, and/or the latest exercise end time.
  • multiple candidate recommended exercise times can be selected from a set of candidate exercise times based on historical sleep data, and then prompt information is output to prompt selection from the multiple candidate recommended exercise times based on the received user input. Information determines target recommended exercise times.
  • the target recommended exercise time can be selected from the candidate exercise time set based on historical sleep data and historical exercise data.
  • multiple candidate recommended exercise times may be selected from the candidate exercise time set based on the historical sleep data, and a target recommended exercise time may be selected from the multiple candidate recommended exercise times based on the historical exercise data.
  • the target recommended exercise time is determined from the plurality of candidate recommended exercise times.
  • the initial motion recommendation result of the target time period is determined based on the first historical motion data in the historical motion data, and the initial motion recommendation result of the target time period is adjusted based on at least part of the historical sleep data, Get the target motion recommendation results in the target time period.
  • exercise recommendation can be performed in units of one exercise recommendation period.
  • Each exercise recommendation cycle can include multiple days or time periods.
  • the length of time included in an exercise recommendation cycle can be preset, such as one week, or can also be specified by the user.
  • the first historical motion data includes motion data of at least one historical motion recommendation period before the current motion recommendation period to which the target time period belongs.
  • the first historical sports data includes the sports data of the previous N weeks before this week, N ⁇ 1.
  • the first historical motion data includes motion data of one or more time periods before the target time period.
  • the first historical movement data includes movement data of the previous N days before the current day.
  • At least a portion of the historical sleep data includes sleep data of at least one day close to the target time period.
  • at least part of the historical sleep data includes sleep data of the previous day or N days of the target time period, or sleep data of one or more days that have passed within the current exercise recommendation cycle.
  • the initial motion recommendation results for each of the multiple time periods included in the current motion recommendation cycle can be determined based on the same historical motion data, for example, based on at least one historical motion recommendation cycle before the current motion recommendation cycle.
  • Exercise data determines the initial exercise recommendation results for each time period included in the current exercise recommendation cycle.
  • initial exercise recommendation results for different time periods included in the current exercise recommendation cycle may be determined based on different historical exercise data.
  • the initial motion recommendation result for each time period is determined based on the motion data of at least one time period before each time period.
  • the determination of the initial motion recommendation result and the determination of the target motion recommendation result may not be performed at the same time.
  • the initial motion recommendation result of the target time period may be determined at the first time before the current motion recommendation period
  • the target exercise recommendation result of each time period in the current exercise recommendation cycle is determined when the time period arrives or at the second time before the arrival.
  • the initial exercise recommendation results for each day of the week are determined before the week, and the target exercise recommendation results for the current day or the next day are determined every day of the week.
  • the initial exercise recommendation result of the target time period is determined based on the health status of the target object at the first time and the first historical exercise data.
  • the exercise recommendation strategy for the target time period is determined based on the physiological data measurement results of the target object; the target time is determined based on the exercise recommendation strategy for the target time period and the first historical exercise data.
  • the initial motion recommendation results of the segment is determined based on the physiological data measurement results of the target object; the target time is determined based on the exercise recommendation strategy for the target time period and the first historical exercise data.
  • the physiological data measurement results of the target object can be obtained by measuring one or more physiological data of the target object, such as heart rate, blood pressure, psychological pressure, etc.
  • the current health status of the target object can be determined based on the physiological data measurement results, and the current exercise recommendation strategy can be determined based on the current health status.
  • the exercise recommendation result includes a recommended amount of exercise
  • the exercise recommendation strategy may include increasing the amount of exercise, maintaining the amount of exercise, and reducing the amount of exercise.
  • the sleep quality evaluation result of the target object on at least one day close to the target time period is obtained; based on the sleep quality of the target object on the at least one day Evaluate the results and adjust the initial motion recommendation results of the target time period to obtain the target motion recommendation results of the target time period.
  • the sleep quality assessment results of at least one day adjacent to the target time period may include the sleep quality assessment results of the previous day or the first N days of the target time period, for example, include the sleep quality assessment results of the previous two weeks, or,
  • the sleep quality assessment results of one or more days that have passed within the current exercise recommendation cycle may be included, for example, the sleep quality assessment results of at least one day that has passed this week may be included.
  • the initial motion recommendation result of the target time period is adjusted based on at least part of the historical sleep data and the second historical motion data in the historical motion data to obtain the target time The target motion recommendation result of the period, wherein the second historical motion data includes motion data within the current motion recommendation period and at least one day before the target time period.
  • the historical motion data includes second historical motion data
  • the second historical motion data includes motion data of the previous day or N days close to the target time period.
  • the second historical exercise data includes exercise data of one or more days that have passed within the current exercise recommendation cycle.
  • a movement assessment result of the target object for at least one day before the target time period is obtained, and based on the movement assessment result and at least part of the historical sleep data, an initial movement recommendation for the target time period is made. The results are adjusted and processed to obtain the target motion recommendation results in the target time period.
  • the sleep quality evaluation result of the target object at least one day before the target time period is obtained, and according to the second historical motion data, it is determined that the target object is in Based on the exercise evaluation results of at least one day before the target time period, based on the sleep quality evaluation results and the exercise evaluation results, the initial exercise recommendation results of the target time period are adjusted to obtain the results of the target time period.
  • Target exercise recommendation results are adjusted to obtain the results of the target time period.
  • an initial motion recommendation result of the target time period is determined, and the initial motion recommendation result of the target time period is performed based on at least a portion of the historical sleep data and the second historical motion data in the historical motion data. Adjust the processing to obtain the target motion recommendation results in the target time period.
  • the second historical motion data may include motion data of at least one day close to the target time period.
  • the initial motion recommendation result of the target time period may be obtained based on the historical motion data and/or historical sleep data of the target object, such as the various possible implementations described above.
  • the initial exercise recommendation results are obtained based on user input information.
  • the initial exercise recommendation results are obtained based on prior knowledge or expert knowledge.
  • the initial exercise recommendation result is based on at least one of the target object's first historical exercise data, the target object's physiological parameter measurement results, user input information, and exercise physiology prior information (or exercise physiology expert knowledge) owned.
  • a motion evaluation result of the target object is obtained based on the second historical motion data; and an initial motion of the target time period is obtained based on the motion evaluation result and at least part of the historical sleep data.
  • the recommendation results are adjusted to obtain the target motion recommendation results for the target time period.
  • a motion evaluation result of the target object is obtained according to the second historical motion data; a sleep quality evaluation result of the target object is obtained according to at least a part of the historical sleep data; and a sleep quality evaluation result of the target object is obtained according to the motion.
  • the initial exercise recommendation results of the target time period are adjusted to obtain the target exercise recommendation results of the target time period.
  • the above-mentioned exercise evaluation results may be used to indicate that the target object has achieved the target amount of exercise in at least one day close to the target time period.
  • the exercise evaluation result includes at least one of the frequency of reaching the target amount of exercise and the indication of the total amount of exercise reaching the target.
  • the indication of the total amount of exercise reaching the target can be used to indicate the target object's performance within at least one day close to the target time period.
  • the frequency of meeting the exercise amount can be used to indicate the frequency of reaching the target amount of exercise in at least one day, that is, the proportion of the number of days in which the amount of exercise reaches the target in the total number of days corresponding to the at least one day.
  • the frequency of meeting the exercise volume standard can indicate the proportion of days when the exercise volume reaches the standard in one or more days that have passed in the current exercise recommendation cycle
  • the total exercise volume compliance indicator can indicate whether the total amount of exercise in one or more days that has passed in the current exercise recommendation cycle has reached the standard. Set the total amount of exercise.
  • the actual amount of exercise for at least one day close to the target time period can be obtained based on the second historical exercise data.
  • the second historical exercise data includes the actual exercise amount of at least one day close to the target time period.
  • the second historical exercise data includes the actual exercise amount of each day in at least one day that has passed in the current exercise recommendation period. Actual amount of exercise.
  • the actual amount of exercise for at least one day close to the target time period can be obtained by processing at least a part of the second historical exercise data.
  • the exercise evaluation result is obtained based on the actual amount of exercise per day in at least one day close to the target time period and the recommended exercise information corresponding to the at least one day.
  • the recommended exercise information corresponding to the at least one day includes the recommended exercise amount for each day of the at least one day. In another example, the recommended exercise information corresponding to at least one day includes the recommended total amount of exercise for at least one day. In another example, the recommended exercise information corresponding to at least one day includes the total amount of recommended exercise in the current exercise recommendation period.
  • the actual total amount of exercise of the target object in the at least one day is determined based on the actual amount of exercise of the target object in at least one day close to the target time period. According to the actual amount of exercise corresponding to the at least one day The recommended total amount of exercise and the actual total amount of exercise for at least one day are used to determine whether the total amount of exercise for at least one day reaches the standard.
  • the target recommended amount of exercise in the target time period is obtained by comparing the exercise amount compliance indicator included in the exercise assessment result with the first preset threshold and/or comparing the sleep quality indicator included in the sleep quality assessment result with the second preset threshold.
  • the initial recommendation included in the initial exercise recommendation result is The amount of exercise is adjusted to the minimum amount of exercise of the target object.
  • the target recommended amount of exercise is the minimum amount of exercise of the target object.
  • the initial recommended exercise amount included in the initial exercise recommendation result is not adjusted.
  • the target recommended exercise amount is determined as the initial recommended exercise amount.
  • the initial recommended exercise amount included in the initial exercise recommendation result can be adjusted to 0 to obtain the target recommended exercise amount, At this time, the target recommended exercise amount is 0, that is, no exercise is recommended during the target time period.
  • the initial recommended exercise amount included in the initial exercise recommendation result may be adjusted to the minimum exercise amount of the target object, The target recommended exercise amount is obtained. At this time, the target recommended exercise amount is the minimum exercise amount of the target object.
  • the initial recommended amount of exercise in the target time period can be determined, and the initial recommended amount of exercise in the target time period can be dynamically adjusted based on the actual exercise situation and sleep conditions of one or more days close to the target time period, so that The target recommended amount of exercise is more in line with the current status of the target object, and the exercise recommendation is more effective.
  • the sleep quality assessment result includes a sleep recovery index.
  • sleep heart rate variability data of the target object is obtained based on at least part of the historical sleep data; sleep recovery indicators of the target object are obtained based on the sleep heart rate variability data of the target object.
  • the sleep heart rate variability data of the target subject includes at least one of the following: short-term sleep heart rate variability parameters of the target subject, long-term sleep heart rate variability parameters of the target subject, and the target subject's sleep heart rate variability data on the previous day. sleep heart rate variability parameters.
  • the short-term sleep heart rate variability parameter may indicate the characteristics of the target subject's heart rate variability during sleep within a short length of time adjacent to the target time period, which may be, for example, the week before the target time period, or the current exercise recommendation. The cycle's previous exercise recommended cycle.
  • the short-term sleep heart rate variability parameter may include baseline heart rate variability.
  • the long-term sleep heart rate variability parameter may indicate the characteristics of the target subject's heart rate variability during sleep within a longer period of time adjacent to the target time period, which may be, for example, the target time period or the first two weeks of the current exercise recommendation period. , one month or more before.
  • the long-term sleep heart rate variability parameters may include The normal range of fluctuations in heart rate variability.
  • the target object's sleep recommendation results can also be determined based on the target object's historical sleep data.
  • the present application provides a sleep recommendation method, which method includes: obtaining historical sleep data of a target object through a terminal device; and based on at least one of attribute information of the target object and expected sleep information of the target object.
  • method obtaining at least one target sleep parameter value of the target object; based on the at least one target sleep parameter value and the historical sleep data of the target object, obtaining the sleep recommendation result of the target object in the target time period,
  • the sleep recommendation result includes at least one of a recommended sleep time, a recommended wake-up time, and a recommended sleep duration; information related to the sleep recommendation result is output.
  • At least one target sleep parameter value can be obtained based on at least one of the target object's attribute information and expected sleep information, and the target sleep parameter value can be obtained based on at least one target sleep parameter value and the target object's historical sleep data.
  • the subject's sleep recommendation results during the target time period, thereby helping the target subject gradually develop scientific and regular sleep habits.
  • the target time period could be today, tomorrow, or next week.
  • the length of the target period can be preset or user-specified.
  • the historical sleep data of the target subject may include sleep data of one or more time periods before the target time period.
  • the target object's historical sleep data can be used to indicate the target object's recent sleep status.
  • the historical sleep data may include the day before the target time period, one or more days that have passed within the current sleep recommendation cycle to which the target time period belongs, or the sleep data of the previous sleep recommendation cycle.
  • historical sleep data may include sleep data from the day before the target time period, one or more days passed this week, or the previous week.
  • the target object's desired sleep information includes at least one desired sleep parameter value, that is, the desired value of at least one sleep parameter, such as desired sleep duration, desired wake-up time, desired fall asleep time, or one or more.
  • the desired sleep information may be obtained by receiving an input instruction from the target object, or may be obtained based on the sleep information of the group to which the target object belongs.
  • the attribute information of the target object includes basic personal information of the target object, such as one or any combination of age, gender, BMI, occupation, hobbies, sleeping habits, etc.
  • the validity of the desired sleep information may be determined before at least one target sleep parameter value is obtained.
  • At least one target sleep parameter value may be determined based on the desired sleep information.
  • At least one target sleep parameter value may be determined according to the attribute information of the target object.
  • the validity of each of the at least one desired sleep parameter value included in the desired sleep information may be determined. For example, it is determined whether a certain desired sleep parameter value is within a preset value range. If it is within the preset value range, it is valid. If it is not within the preset value range, it is invalid.
  • the desired sleep information includes multiple desired sleep parameter values, and some of the desired sleep parameter values are valid and some of the desired sleep parameter values are invalid, then at least one of the valid desired sleep parameter values and the attribute information can be used. to determine the target sleep parameter value corresponding to the invalid desired sleep parameter value.
  • the first desired sleep parameter value in response to the existence of a valid desired sleep parameter value corresponding to the first sleep parameter in the desired sleep information of the target object, is determined based on the corresponding valid desired sleep parameter value.
  • the target sleep parameter value corresponding to the sleep parameter For example, the effective desired sleep parameter value corresponding to the first sleep parameter is determined as the target sleep parameter value corresponding to the first sleep parameter.
  • the second sleep parameter in response to the fact that there is no valid expected sleep parameter value corresponding to the second sleep parameter in the expected sleep information of the target object, the second sleep parameter is determined according to the attribute information of the target object. The corresponding target sleep parameter value.
  • the group or sleep category to which the target object belongs can be determined based on the attribute information of the target object, and then at least one target sleep parameter value can be determined based on the group or sleep category to which the target object belongs.
  • a sleep adjustment strategy for the target object is determined based on the target object's historical sleep data and the at least one target sleep parameter value; and based on the sleep adjustment strategy, the target object is obtained at the target time according to the sleep adjustment strategy. segment’s sleep recommendation results.
  • the sleep adjustment strategy may include a gradual adjustment strategy or a direct adjustment strategy.
  • At least one current sleep parameter value of the target object can be obtained based on the target object's historical sleep data, and sleep recommendation results can be obtained based on at least one current sleep parameter value and at least one target sleep parameter value.
  • the at least one current sleep parameter value may include at least one of historical sleep time, historical wake-up time, and historical sleep duration.
  • At least one current sleep parameter value of the target object is obtained by processing historical sleep data of the target object.
  • the at least one current sleep parameter value is a statistical average of the sleep parameters within a specific time interval before the target time period.
  • the sleep recommendation result for the target time period can be obtained by comparing the difference between at least one current sleep parameter value and at least one target sleep parameter value.
  • the sleep adjustment strategy of the target subject in response to the difference between the current sleep parameter value and the target sleep parameter value exceeding a preset difference range, it is determined that the sleep adjustment strategy of the target subject is a progressive adjustment strategy.
  • the sleep adjustment strategy is determined to be a progressive adjustment strategy.
  • the sleep recommendation result for the target time period is obtained based on the adjustment step size and the current sleep parameter value.
  • the current sleep parameter value is adjusted with an adjustment step to obtain a sleep recommendation result for the target time period, so that the recommended sleep parameters included in the sleep recommendation result are closer to the target sleep parameter value from the current sleep parameter value.
  • the adjustment step size is determined based on the difference between the current sleep parameter value and the target sleep parameter value.
  • the adjustment step size is preset or determined based on user input information.
  • the sleep recommendation strategy in response to the difference between the current sleep parameter value and the target sleep parameter value being within the preset difference range, is determined to be a direct adjustment strategy.
  • sleep recommendation results are determined based on target sleep parameter values.
  • the recommended sleep parameter included in the sleep recommendation result of the target object is determined to be the target sleep parameter value.
  • the method further includes: obtaining the supplementary sleep recommendation result of the target object in the target time period based on the sleep data of the previous day of the target time period included in the target object's historical sleep data. .
  • the previous day's sleep data may include the previous day's regular sleep data and/or supplemental sleep data.
  • whether to recommend the target subject to supplement sleep during the target time period may be determined based on whether the target subject's regular sleep parameters on the day before the target time period reach a preset parameter range.
  • the supplementary sleep recommended duration included in the supplementary sleep recommendation result of the target object in the target time period is greater than zero. For a while. At this time, it is recommended to have a certain amount of supplementary sleep during the target time period.
  • the first duration may be a preset value, or may be determined based on at least part of the target subject's historical sleep data.
  • the target object's regular sleep duration reaching the preset sleep duration on the previous day it is determined that the supplementary sleep recommended duration included in the supplementary sleep recommendation result of the target object is zero. At this time, it is recommended not to perform supplementary sleep during the target period.
  • the method further includes: outputting a supplementary sleep duration reminder based on the historical sleep data of the target object.
  • a supplementary sleep duration reminder in response to the sleep data of the previous day of the target time period indicating that the target subject's supplementary sleep duration on the previous day exceeds the recommended duration range, a supplementary sleep duration reminder is output, and the supplementary sleep duration reminder is used to Prompt to control the supplementary sleep duration in the target time period within the recommended duration range.
  • the target object's supplementary sleep recommendation results can be obtained based on the target object's historical sleep data, thereby avoiding the target object's lack of energy due to poor regular sleep, and at the same time avoiding the negative impact of long supplementary sleep on health. adverse effects and establish a basis for the achievement of active health goals of target subjects.
  • the present application provides an exercise recommendation device, which includes: an acquisition module configured to acquire historical sleep data and historical motion data of a target object through a terminal device, where the historical sleep data includes data before the target time period. At least one day's sleep data, and the historical movement data includes at least one day's movement data before the target time period; a processing module configured to obtain the target object's time period based on the historical sleep data and the historical movement data.
  • the target exercise recommendation result of the target time period, the target exercise recommendation result includes at least one of the target recommended exercise time and the target recommended exercise amount; an output module is used to output relevant information of the target exercise recommendation result.
  • the exercise recommendation device includes a module or unit for performing the processes and/or steps of the first aspect or any possible implementation of the first aspect.
  • this application provides a sleep recommendation device, which includes: an acquisition module configured to acquire historical sleep data of a target object through a terminal device; a first processing module configured to obtain historical sleep data of a target object based on the attribute information of the target object and At least one target sleep parameter value of the target object is obtained from at least one of the desired sleep information of the target object; a second processing module is configured to obtain at least one target sleep parameter value of the target object based on at least one target sleep parameter value of the target object and the target The historical sleep data of the object is used to obtain the sleep recommendation result of the target object in the target time period.
  • the sleep recommendation result includes at least one of recommended sleep time, recommended wake-up time and recommended sleep duration; an output module is used to output Information related to the sleep recommendation results.
  • the sleep recommendation device includes a module or unit for performing the processes and/or steps of the second aspect or any implementation of the second aspect.
  • the present application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor. , the instructions are executed by the at least one processor, so that the at least one processor can execute the motion recommendation method as described in the first aspect or any possible implementation of the first aspect, or to enable the at least one
  • the processor is capable of executing the sleep recommendation method as described in the second aspect or any possible implementation of the second aspect.
  • the present application provides a computer-readable storage medium for storing instructions, wherein when the instructions are executed, the exercise recommendation method as described in the first aspect or any implementation of the first aspect is caused to be Implement, or cause, the sleep recommendation method as described in the second aspect or any implementation of the second aspect to be implemented.
  • the present application provides a computer program product, including a computer program that, when executed by a processor, implements the exercise recommendation method as described in the first aspect or any implementation of the first aspect, or implements The sleep recommendation method described in the second aspect or any implementation of the second aspect.
  • Figure 1 is an exemplary block diagram of a health guidance system provided by an embodiment of the present application.
  • Figure 2 is a schematic flowchart of an exercise recommendation method provided by an embodiment of the present application.
  • FIG. 3 is a schematic flowchart of another exercise recommendation method provided by an embodiment of the present application.
  • Figure 4 is a schematic flowchart of yet another exercise recommendation method provided by an embodiment of the present application.
  • Figure 5 is a schematic diagram of an exemplary exercise amount recommendation solution provided by an embodiment of the present application.
  • Figure 6 is a schematic diagram of an exemplary exercise recommendation solution provided by an embodiment of the present application.
  • Figure 7 is a schematic flowchart of a sleep recommendation method provided by an embodiment of the present application.
  • Figure 8 is a schematic diagram of an exemplary sleep recommendation solution provided by an embodiment of the present application.
  • Figure 9 is a schematic diagram of an exemplary supplementary sleep suggestion solution provided by an embodiment of the present application.
  • Figure 10 is a schematic diagram of an exemplary sleep recommendation solution provided by an embodiment of the present application.
  • Figure 11 is a schematic diagram of an exemplary health guidance system provided by an embodiment of the present application.
  • Figure 12 is a schematic diagram of an exercise recommendation device provided by an embodiment of the present application.
  • Figure 13 is a schematic diagram of a sleep recommendation device provided by an embodiment of the present application.
  • Figure 14 is a schematic diagram of another sleep recommendation device provided by an embodiment of the present application.
  • Figure 15 is a schematic block diagram of an electronic device provided by an embodiment of the present application.
  • Terminal devices such as wearable devices, smartphones, and personal digital assistants are increasingly used to monitor users’ movement and physiological information, such as heart rate, blood oxygen levels, etc., but no in-depth analysis of the detected user data is performed. and utilization to help users achieve proactive health goals.
  • the embodiment of the present application solves such problems by making exercise recommendations and sleep recommendations for users based on the sleep data and motion data collected by the terminal device.
  • the target object's historical sleep data and historical motion data are collected through the terminal device, and the target motion recommendation result of the target object is obtained based on the historical sleep data and historical motion data, and relevant information about the target motion recommendation result is output. Therefore, based on the target object's historical sleep data and historical exercise data, the target exercise recommendation results are determined and recommended to the target object, thereby helping the target object maintain scientific and regular exercise habits, improving the target object's exercise ability and achieving active health goals. Establish foundation.
  • FIG. 1 is an exemplary block diagram of a health guidance system 100 provided by an embodiment of the present application.
  • the system 100 includes a wearable device 102 , a server device 104 and an intermediate device 106 .
  • the intermediate device 106 is an intermediate connection device between the wearable device 102 and the server device 104 .
  • Wearable device 102 is a computing device configured to be worn by a user during operation.
  • the wearable device 102 may be implemented as a wrist-worn device worn on the user's wrist, or may be implemented as a band or loop worn on the user's arms, legs, or torso, or may be implemented as a wrist-worn device worn on the user's head or eyes.
  • wearable device 102 may include a housing, a wearable, a display, a communication element, a positioning element, one or more sensors, memory, and a processor.
  • wearable device 102 includes one or more sensors 108 .
  • the sensor 108 may include one or any combination of a photoplethysmography (PPG) sensor, a pulse wave sensor, an acceleration sensor, a blood pressure sensor, a sleep sensor, an electrocardiogram sensor, a body temperature sensor, a pressure sensor, an ultrasonic sensor, an infrared sensor, etc. .
  • PPG photoplethysmography
  • One or more of the sensors 108 may be used to measure physiological parameters of the user.
  • the physiological parameters may include one or more combinations of heart rate, heart rate variability, blood oxygen saturation, blood pressure, blood sugar, body temperature, respiration, etc. .
  • a program 110 is run on the wearable device 102 for processing user data collected based on the sensor 108 The measurement signal generated by the data.
  • Server device 104 is a computing device that runs server program 112 to process measurement signal data.
  • Server device 104 may be or include a hardware server (eg, a server device), a software server (eg, web server and/or virtual server), or both.
  • server device 104 may be a server device located in a rack.
  • the server program 112 is configured to use the measurement signal data to detect one or more of a health condition, an exercise condition, a sleep condition, or a combination thereof of the user of the wearable device 102 .
  • the server program 112 may receive measurement signal data from the intermediary device 106 and may then use the received measurement signal data to detect one or more of a health condition, exercise condition, sleep condition, or a combination thereof of the user of the wearable device 102 .
  • the server program 112 may use the measurement signal data to determine a user state or a change in a user state, and then detect a health condition, exercise condition, sleep condition, or condition of the user of the wearable device 102 based on the determined user state or change in the user state. one or more of its combinations.
  • Server program 112 may access database 114 in server device 104 to perform at least some functions of server program 112.
  • Database 114 is a database or other data store used to store, manage, or otherwise provide data used to deliver the functionality of server program 112 .
  • database 114 may store physiological signal data received by server device 104, information generated or otherwise determined by the physiological signal data.
  • database 114 may be a relational database management system, an object database, an XML database, a configuration management database, a management information base, one or more flat files, other suitable non-transitory storage mechanisms, or a combination thereof.
  • Intermediary device 106 is a device used to facilitate communication between wearable device 102 and server device 104 .
  • the intermediary device 106 receives data from the wearable device 102 and sends the received data to the server device 104, for example, for use by the server program 112.
  • the intermediary device 106 may be a computing device, such as a mobile device (eg, a smartphone, tablet, laptop, or other mobile device) or other computer (eg, a desktop computer or other non-mobile computer).
  • the intermediary device 106 may be or include network hardware, such as a router, a switch, a load balancer, another network device, or a combination thereof.
  • intermediary device 106 may be another network connection device.
  • the intermediary device 106 may be a networked power charger for the wearable device 102 .
  • the intermediary device 106 may run an application 118, which may be one or more application software installed on the intermediary device 106.
  • the application software may be used by the user of the intermediary device 106 (usually the same person as the user of the wearable device 102 , but in some cases may not be the same person as the user of the wearable device 102 ) in the middle of the purchase.
  • the device 106 is then installed on the intermediate device 106, or the manufacturer of the intermediate device 106 can pre-install it on the intermediate device 106 before the intermediate device 106 leaves the factory.
  • Application 118 is configured to send data to or receive data from wearable device 102 and/or to send data to or receive data from server device 104 .
  • Application 118 may receive commands from the user of intermediary device 106 .
  • Application 118 may receive commands from its users through application 118's user interface.
  • intermediary device 106 is a computing device with a touch screen display
  • a user of intermediary device 106 may receive commands by touching a portion of the display that corresponds to a user interface element in the application.
  • a command received by application 118 from a user of intermediary device 106 may be a command to transmit physiological signal data received at intermediary device 106 (eg, from wearable device 102 ) to server device 104 .
  • Intermediary device 106 sends physiological signal data to server device 104 in response to such commands.
  • the command received by the application 118 from the user of the intermediary device 106 may be a command to review information received from the server device 104 , for example, related to the detected health status, exercise status, Information related to one or more sleep conditions or a combination thereof.
  • client devices are granted access to server program 112 .
  • the client device may be a mobile device such as a smartphone, tablet, laptop, etc.
  • the client device may be a desktop computer or other non-mobile computer.
  • Client devices can run client applications to communicate with server program 112 .
  • a client application may be able to access some or all of the server program 112 mobile applications that contain certain functionality and/or data.
  • client devices may communicate with server device 104 over network 116 .
  • the client device may be the intermediary device 106.
  • server device 104 may be a virtual server.
  • a virtual server can be implemented using a virtual machine (eg, a Java virtual machine).
  • the implementation of a virtual machine can use one or more virtual software systems, such as HTTP servers, java servlet containers, hypervisors or other software systems.
  • the one or more virtual software systems used to implement the virtual servers may be implemented in hardware instead.
  • intermediary device 106 receives data from wearable device 102 using a short-range communication protocol.
  • a short range communication protocol could be Low energy, infrared, Z-wave, ZigBee, other protocols or combinations thereof.
  • Intermediary device 106 sends data received from wearable device 102 to server device 104 over network 116 .
  • network 116 may be a local area network, a wide area network, a machine-to-machine network, a virtual private network, or other public or private network.
  • Network 116 may use remote communication protocols.
  • the remote communication protocol may be Ethernet, TCP, IP, Power Line Communications, Wi-Fi, GPRS, GSM, CDMA, other protocols, or combinations thereof.
  • System 100 is used to continuously transmit physiological signal data from wearable device 102 to server device 104 .
  • Sensor 108 may continuously or otherwise frequently periodically collect measurement signal data of the user of wearable device 102 .
  • Implementations of system 100 may differ from those shown and described with respect to FIG. 1 .
  • intermediary device 106 may be omitted.
  • wearable device 102 may be configured to communicate directly with server device 104 over network 116 .
  • direct communication between wearable device 102 and server device 104 over network 116 may include the use of remote, low-power systems or other communication mechanisms.
  • both the intermediary device 106 and the server device 104 may be omitted.
  • wearable device 102 may be configured to perform the functions described above with respect to server device 104. In such implementations, wearable device 102 may process and store data independently of other computing devices.
  • the method provided by the embodiment of the present application can be executed by an electronic device, where the method can be executed by a wearable device or other devices.
  • the wearable device can send the collected data to the intermediate device, and the intermediate device executes the method; for another example, the wearable device can directly send the collected data to the server device, and the server device executes the method.
  • the wearable device can send the collected data to the intermediate device, the intermediate device sends the data to the server device, and the server device executes the method.
  • the method provided by the embodiment of the present application can be completed by multiple devices. For example, part of the operation is performed by a wearable device, and another part of the operation is performed by an intermediate device.
  • part of the operation is performed by a wearable device, and another part of the operation is performed by an intermediate device.
  • the server device performs the operation.
  • part of the operation is performed by the intermediate device, and another part of the operation is performed by the server device. This is not specifically limited in the embodiment of the present application.
  • the method can also be implemented through electronic devices such as smartphones, personal digital assistants, and tablet computers.
  • the smartphone collects the user's motion and/or sleep data and executes the method provided by the embodiments of the present disclosure.
  • Figure 2 is a schematic flow chart of an exercise recommendation method provided by an embodiment of the present application.
  • the exercise recommendation method may include but is not limited to S201 to S203.
  • the historical sleep data includes sleep data for at least one day before the target time period
  • the historical movement data includes movement data for at least one day before the target time period.
  • the historical sleep data includes sleep data in a first time period
  • the historical motion data includes motion data in a second time period.
  • Each time period in the embodiment of this application can be measured in days, and different time periods can have different time lengths.
  • a time period can include one day, three days, one week, three weeks, one month, or six months, etc.
  • the "day” here can refer to a natural day, or it can refer to 24 hours starting from a certain point in time.
  • the time when the method is executed is called the current day.
  • the first time period may include one or more days before the current day
  • the second time period may include one or more days before the current day.
  • the first time period and the second time period may be the same.
  • the first time period and the second time period both include one or more days before the current day, for example, one or more days that have passed this week. multiple days, the day before the current day, the current day The first 7 days, the first 14 days, the previous month or the first three months, etc. of the day, or the previous week, the first two weeks, the previous month, the first half year, etc. of the week where the day is located.
  • the second time period and the first time period have an inclusive relationship.
  • the time length included in the second time period is greater than or equal to the time length included in the first time period, that is, the second time period Contains the first time period, for example, the second time period includes the days before the current day, and the first time period includes the day before the current day.
  • the first time period includes the second time period.
  • the first time period and the second time period are temporally related. For example, the second time period is located in the first time period.
  • the second time period includes the previous week or weeks before this week, and the first time period includes one or more days before the current day within this week, that is, one or more days that have passed this week. Or, there is an intersection between the first time period and the second time period, that is, part of the time between the first time period and the second time period overlaps.
  • the target time period includes the next day, such as today or tomorrow. In other embodiments, the target time period includes the next week or weeks or a time period of a specific length. For ease of understanding, the following description takes the target time period as one day as an example, and the embodiments of the present application are not limited thereto.
  • the electronic device that performs the method may be a terminal device, such as the wearable device 102 shown in FIG. 1 .
  • the terminal device can collect the sleep data and/or movement data of the target object, and store the collected data in the local or remote memory directly or after one or more processes, and then, in S201, obtain Historical sleep data and/or historical exercise data stored in local or remote storage.
  • the electronic device that performs the method is another device different from the terminal device, for example, the intermediate device 106 or the server device 104 shown in FIG. 1 .
  • the terminal device can collect the sleep data and/or movement data of the target object, and send the collected data to the electronic device directly or after one or more processes.
  • the electronic device receives the terminal historical sleep data and/or historical movement data sent by the device, or the electronic device obtains historical sleep data and/or historical movement data stored in local or remote memory, or the electronic device performs a processing on the received data sent by the terminal device. After one or more processes, historical sleep data and/or historical movement data are obtained.
  • the historical sleep data of the target object may include one or more types of sleep-related data.
  • the target object's historical sleep data may include sleep-related physiological data collected through sensors, such as one or any combination of the target object's body movement data, breathing data, heart rate data, etc. collected during sleep.
  • sleep data may be obtained at least in part based on sleep-related physiological data collected through sensors. For example, one or more types of processing, such as feature extraction, etc., may be performed on the sleep-related physiological data to obtain the target The object's sleep data.
  • the sleep data includes sleep time (ST), sleep latency, sleep duration (total sleep time, TST), wake-up time, deep sleep duration, deep sleep ratio, sleep stage data, wake-up times (WN), wake-up time To accumulate time (WT), fall asleep time regularity (STR), sleep duration regularity (TSTR), etc. one or any combination.
  • the historical motion data of the target object may include one or more types of motion-related data.
  • the historical motion data of the target object includes acceleration data and/or motion-related physiological data collected during the motion, where the acceleration data may be collected by an accelerometer, a gyroscope or other types of acceleration sensors, Exercise-related physiological data may include one or any combination of heart rate, respiration rate, skin sweat data, etc.
  • the motion data may be obtained at least in part based on the collected acceleration data and/or motion-related physiological data.
  • the collected acceleration data and/or motion-related physiological data may be subjected to one or Various processes are used to obtain the motion data of the target object.
  • the exercise data includes one or more of exercise type, exercise start time, exercise end time, exercise duration, exercise impulse, exercise energy consumption, exercise intensity, etc.
  • the target exercise recommendation result includes at least one of the target recommended exercise time and the target recommended exercise amount.
  • the target recommended exercise time may be at least one of exercise start time and exercise end time
  • the target recommended exercise amount may be target exercise impulse, target exercise intensity, or exercise at a specific exercise intensity.
  • At least one of time, total target exercise time, target energy consumption, or target recommended exercise time and target recommended exercise amount may also include other information, which is not limited in the embodiments of the present application.
  • the target motion recommendation results may also include motion types or other motion parameters.
  • the sleep type of the target object is determined, and the target recommended exercise time of the target time period is obtained based on the target object's sleep type, historical exercise data, and historical sleep data.
  • the sleep type of the target object may be obtained at least in part by analyzing the user's personal information, or the sleep type of the target object may be determined based on user input information, for example, the target object inputs its own sleep type.
  • the sleep type of the target object is obtained based on the historical sleep data of the target object. For example, the historical sleep data of the target object over a period of time is input into the machine learning model for processing, and the sleep type of the target object is obtained.
  • the sleep type of the target object is determined based on the historical sleep data of the target object
  • at least one historical exercise time of the target object is determined based on the historical exercise data of the target object
  • the target recommended exercise time for the target time period is obtained based on the sleep type of the target object and the at least one historical exercise time of the target object.
  • a sleep type of the target object is determined based on historical sleep data of the target object
  • at least one candidate movement time of the target object is determined based on historical movement data of the target object
  • at least one candidate movement time is determined.
  • the target recommended exercise time is determined among the candidate exercise times.
  • an initial motion recommendation result of the target object in the target time period is determined based on the target object's historical motion data, and the initial motion recommendation result of the target time period is adjusted based at least in part on the target object's historical sleep data. Process to obtain the target motion recommendation results in the target time period.
  • determining the initial exercise recommendation result of the target time period based on the first historical exercise data in the historical exercise data, and adjusting the initial exercise recommendation result based on at least a part of the historical sleep data Get target exercise recommendation results.
  • the first historical motion data includes motion data of at least one time period before the target time period.
  • exercise recommendation may be performed in units of exercise recommendation periods including multiple time periods.
  • the first historical motion data includes motion data of at least one time period before the current motion recommendation period to which the target time period belongs, for example, motion data of at least one historical motion recommendation period before the current motion recommendation period.
  • a sports recommendation period is one week, and the first historical sports data includes the sports data of one or more weeks close to this week, such as the previous week, the previous three weeks, or the previous month.
  • At least a portion of the historical sleep data may include sleep data for one or more days adjacent to the target time period.
  • at least part of the historical sleep data may include sleep data of the previous day or the previous N days of the target time period.
  • at least part of the historical sleep data may include sleep data for one or more days within the current exercise recommendation cycle.
  • at least part of the historical sleep data may include sleep data of one or more days that have passed within the current exercise recommendation cycle.
  • an initial exercise recommendation result for each time period included in the current exercise recommendation period to which the target time period belongs is determined, such as an initial recommended exercise time and/or an initial recommended exercise amount.
  • expert knowledge or exercise physiology knowledge, or exercise strategy information determined based on exercise physiology knowledge, and the first historical exercise data of the target object can be combined to obtain initial exercise recommendation results for each time period in multiple time periods.
  • initial exercise recommendations may be determined before the week, and target exercise recommendations for the current or next day may be determined each day of the week.
  • the initial exercise recommendation result of the target time period is determined at the first time, which is before the current exercise recommendation period to which the target time period belongs; based on at least part of the historical sleep data , the initial motion recommendation result of the target time period is adjusted at the second time to obtain the target motion recommendation result of the target time period, and the second time is within the current motion recommendation period and within the target time period.
  • the second time is the day before or today of the target time period.
  • a sleep quality assessment result of the target subject for at least one day close to the target time period is obtained, and based at least in part on the sleep quality assessment result, the target time is determined.
  • the initial motion recommendation results of the target time period are adjusted to obtain the target motion recommendation results of the target time period.
  • the sleep quality assessment results can be used to evaluate the user's sleep situation.
  • the sleep quality assessment results can include one or more sleep assessment indicators such as sleep recovery, sleep quality score, and deep sleep duration.
  • the initial recommended exercise amount in the initial exercise recommendation result can be adjusted based on the sleep quality assessment result. For example, if the sleep quality assessment result indicates that the target subject's recent or current sleep assessment index is poor, such as the sleep assessment index is lower than a preset threshold, the initial recommended exercise amount can be reduced to obtain the target recommended exercise amount. For another example, if the sleep quality assessment result indicates that the target subject's recent or current sleep assessment index is good, and if the sleep assessment indicator reaches a preset threshold, the initial recommended exercise amount can be increased or maintained to obtain the target recommended exercise amount.
  • the initial exercise recommendation result of the target time period may be adjusted according to at least one of the second historical exercise data and at least a part of the historical sleep data included in the historical exercise data to obtain the target time Segment target motion recommendation results.
  • the second historical motion data may include motion data for one or more days before the target time period.
  • the second historical motion data may be part of the first historical motion data.
  • the second historical exercise data includes one or more days of exercise data close to the target time period.
  • the second historical exercise data includes one or more days of exercise data within the current exercise recommendation period.
  • the current exercise recommendation Movement data for one or more days that have passed within the cycle.
  • a motion evaluation result of the target object is obtained according to the second historical motion data, wherein the motion evaluation result indicates that the amount of motion reaches the standard for at least one day close to the target time period, and based at least in part on the motion evaluation result of the target object, the motion evaluation result of the target object is obtained.
  • the initial motion recommendation results are adjusted to obtain the target motion recommendation results.
  • the amount of exercise reaching the target may include the frequency of reaching the target amount of exercise and/or the indication of the total amount of exercise reaching the target.
  • the indication of the total amount of exercise reaching the target may be used to indicate whether the total amount of exercise in at least one day approaching the target time period has reached the target.
  • the frequency of reaching the target may be used to indicate the frequency of reaching the target for exercise volume within at least one day, that is, the proportion of the number of days on which the target amount of exercise is achieved in the total number of days corresponding to the at least one day.
  • the frequency of meeting the exercise volume standard can indicate the proportion of days when the exercise volume reaches the standard in one or more days that have passed in the current exercise recommendation cycle
  • the total exercise volume compliance indicator can indicate whether the total amount of exercise in one or more days that has passed in the current exercise recommendation cycle has reached the standard.
  • Set the total amount of exercise The set total amount of exercise may be the sum of the recommended exercise amounts for one or more days that have passed, or may be the total recommended exercise amount for the current exercise recommendation cycle.
  • other indicators may be used to characterize the amount of exercise reaching the target, which is not limited in the embodiments of the present application.
  • the initial recommended exercise amount can be kept unchanged or the initial recommended exercise amount can be increased.
  • the exercise amount attainment condition includes a good exercise amount attainment index, such as the exercise amount attainment index reaches a preset threshold, the initial recommended exercise amount can be kept unchanged or the initial recommended exercise amount can be reduced.
  • the initial exercise recommendation result for the target time period may be determined, and the initial exercise recommendation for the target time period may be determined based on at least a portion of the historical sleep data and the second historical exercise data in the historical exercise data. The results are adjusted and processed to obtain the target motion recommendation results in the target time period.
  • At least part of the historical sleep data includes sleep data of at least one day close to the target time period, for example, sleep data of the day before or N days before the target time period, or the time interval between the target time period and the target time period is less than a set time period.
  • the second historical motion data includes motion data of at least one day close to the target time period, for example, motion data of the day before or N days before the target time period, or the time interval between the target time period and the target time period is less than the set time period.
  • at least a part of the second historical exercise data and the historical sleep data correspond to the same time period, such as a time period within the current exercise recommendation period and before the target time period.
  • the historical sleep data of the target object can be quantitatively evaluated to obtain the sleep quality evaluation result of the target object. Based on the second historical motion data, the motion evaluation result is obtained, and based on the sleep quality evaluation result and the motion evaluation result, The initial motion recommendation results are adjusted to obtain the target motion recommendation results.
  • the electronic device may push information related to the target exercise recommendation results in any suitable manner.
  • the electronic device may display relevant information on the target exercise recommendation result on the display, or output relevant information on the target exercise recommendation result to the target object through notification, voice, vibration or other tactile output methods.
  • the electronic device may send the relevant information of the target exercise recommendation result to the terminal device, so that the terminal device outputs the relevant information of the target exercise recommendation result to the target object.
  • the information related to the target exercise recommendation result may include the target exercise recommendation result itself, for example, include at least one of the target recommended exercise time and the target recommended exercise amount.
  • the information related to the target exercise recommendation result may include reminder information generated according to the target exercise recommendation result, for example, reminder information to remind you to exercise at the target recommended exercise time, and reminder information generated before exercise to remind you to complete the target recommended exercise amount.
  • Reminder information, reminder information generated during exercise to remind you that a specific amount of exercise needs to be completed, etc., is not limited in this embodiment of the present application.
  • the target exercise recommendation result of the target object can be obtained based on the target object's historical sleep data and historical movement data, and relevant information of the target exercise recommendation result can be output, thereby helping the target object maintain scientific and regular exercise. habits to establish a foundation for the improvement of the target's exercise ability and the achievement of active health goals.
  • the following will illustrate how to obtain the target subject's sleep quality assessment results based on at least part of the historical sleep data with specific examples.
  • the historical sleep data includes at least one of the following sleep parameters: sleep time (ST), sleep duration (total sleep time, TST), wake-up time, deep sleep duration, deep sleep ratio, sleep stage, wake-up Number of times (WN), cumulative wake-up time (WT), sleep time regularity (STR), and sleep duration regularity (TSTR).
  • sleep time ST
  • sleep duration total sleep time, TST
  • wake-up time deep sleep duration
  • deep sleep ratio sleep stage
  • sleep stage wake-up Number of times
  • WT cumulative wake-up time
  • STR sleep time regularity
  • TSTR sleep duration regularity
  • the sleep quality assessment result of the target subject may be determined based on one or more sleep parameters included in the historical sleep data.
  • feature extraction processing can be performed on sleep-related physiological data included in historical sleep data to obtain sleep feature data, and based on the sleep feature data, a sleep quality evaluation result can be obtained.
  • one or more items in the historical sleep data, or one or more items in the sleep characteristic data obtained based on the sleep data can be preprocessed to obtain the input data, and then the input data can be input to the pre-processed data.
  • the trained sleep quality assessment model is used to obtain the sleep quality assessment results of the target object.
  • z-score can be used to preprocess one or more items of data in the sleep characteristic data.
  • the preprocessing can be performed by the following formula: deal with:
  • z i is the standard score of the i-th feature data in a certain sleep feature data
  • x ⁇ x 1 , x 2 ... x n ⁇
  • n is the set of the sleep feature data
  • x i is the i-th feature data in the set of sleep feature data
  • i is an integer, 1 ⁇ i ⁇ n
  • u is the average value of the sleep feature data
  • s is the sleep feature data The standard deviation of the feature data.
  • sleep quality assessment can be performed through the Pittsburgh Sleep Quality Assessment Model.
  • This sleep quality assessment model can be implemented through a deep learning network.
  • PSQI Pantsburgh Sleep Quality Index, Pittsburgh Sleep Quality Index
  • DNN is the deep neural network
  • TST, ST, DR, STR, TSTR, WN, WT are the inputs of the sleep quality assessment model; where , TST represents the sleep duration, ST represents the time to fall asleep, DR represents the proportion of deep sleep, STR represents the regularity of falling asleep time, TSTR represents the regularity of sleep duration, WN represents the number of wake-ups, and WT represents the cumulative wake-up time.
  • the above multiple sleep parameters or sleep characteristic data may have the same weight.
  • corresponding weight values may be set for the above-mentioned sleep parameters or sleep characteristic data based on the PSQI questionnaire in sleep medicine.
  • the above deep neural network can be trained in any suitable way, for example, in a supervised or unsupervised way, which is not limited in the embodiments of the present application.
  • Figure 3 is a schematic flowchart of another exercise recommendation method provided by an embodiment of the present application.
  • the target exercise recommendation result includes the target recommended exercise time.
  • the method may include but is not limited to S301 to S304.
  • S301 can be implemented in any manner among the embodiments of this application, and will not be described again here.
  • a set of candidate exercise time is determined based on at least part of the historical exercise time data included in the historical exercise data.
  • the historical sleep data includes sleep data of the previous day or the previous time period of the target time period.
  • Historical movement data includes movement data of multiple days before the target time period, for example, one month, three months, etc.
  • historical exercise data is used to determine the target subject's exercise habits or preferences
  • historical sleep data is used to determine the target subject's sleeping habits or preferences.
  • Targeting can be performed in combination with the target subject's exercise habits or preferences and sleeping habits or preferences. Recommend exercise time for the target object.
  • the set of candidate motion times may include multiple candidate motion times.
  • all historical movement times included in the historical movement time data may be used as candidate movement times.
  • the movement time that satisfies certain conditions among all historical movement times included in the historical movement time data can also be used as a candidate movement time.
  • a historical movement time whose number of occurrences reaches a certain threshold in the historical movement time data can be used as a candidate movement time.
  • the candidate motion time is obtained by processing multiple historical motion times in the historical motion time data.
  • multiple candidate motions are obtained by statistically analyzing the multiple historical motion times included in the historical motion time data. time.
  • Ext_1, Ext_2,...Ext_n are the time periods to which the historical movement time included in the historical movement data of the target object belongs (for example, one hour is the interval), and n is a positive integer, 0 ⁇ n ⁇ 24.
  • the target recommended exercise time is determined from the candidate exercise time set based on historical sleep data.
  • a target recommended exercise time suitable for the target object's sleep condition is determined from the candidate exercise time set.
  • the sleep type of the target object may be determined, and the target recommended exercise time may be determined from the candidate exercise time set based on the sleep type of the target object.
  • the sleep type is used to characterize the sleep habits of the target subject.
  • the sleep type may include an early-rising type, a late-rising type, and a sleep disorder type, wherein the early-rising type represents that the target subject has a habit of getting up early; the late-rising type represents that the target subject has a habit of getting up late; and the sleep disorder type represents that the target subject has a habit of getting up late.
  • the sleep type may also include other types, for example, early bed type, late bed type, difficulty falling asleep type, dreamy type, frequent waking type in the middle of the night, sleep less type, sleep more type, etc. any one or Any combination is possible, and the embodiments of this application do not limit this.
  • the sleep type can be obtained based on instructions input by the target subject or information input by the user. For example, prompt information prompts the target subject to enter his/her sleep habit information, such as sleep time, whether there are sleep disorders, sleep type, etc. information, and then the sleep type of the target object can be obtained based on the user input information.
  • the sleep type corresponding to the sleep type information included in the user input information can be directly used as the sleep type of the target object, or the user input information can be processed, for example.
  • Use user input information as input parameters of the sleep classification model, or use user input information and preset mapping rules to determine the sleep type of the target object.
  • the sleep type is obtained through sleep monitoring of the target subject.
  • the historical sleep data of the target object within a period of time is used to obtain the sleep type of the target object.
  • the target object's historical sleep data during this period of time is input into the sleep classification model directly or after one or more types of processing to obtain the target object's sleep type.
  • the period of time may be a longer period of time, for example, the period of time may be one month, three months, half a year, etc., which is not limited here.
  • a wearable device worn by the target subject can be used to monitor the sleep of the target subject, or other types of terminal devices can be used to monitor the sleep of the target subject.
  • the historical sleep data can be a wearable device or other All sleep data of the target object monitored by a type of terminal device can also be part of all sleep data of the target object monitored by a wearable device or other types of terminal devices, such as meeting specific conditions or being within a certain time period from the target. Sleep data within the time interval is not limited here.
  • the target object's historical sleep data determine one or more data such as the target object's sleep latency, fall asleep time, sleep end time, number of wake-ups, cumulative wake-up time, deep sleep duration, light sleep duration, etc. And through statistical analysis of the obtained data, the sleep type of the target object is obtained.
  • the target object's sleep type is determined to be an early-rising type; if the target object's sleep end time is generally later than the preset time (for example, 9 o'clock) ), the target object's sleep type is determined to be a late-rising type; when the target object's sleep latency is greater than the preset duration, or the number of wake-ups during sleep is greater than the preset number, or the cumulative wake-up duration during sleep is greater than the preset duration If the duration threshold is determined (for example, 1 hour), the sleep type of the target object is determined to be a sleep disorder type.
  • the sleep type is determined in other ways, for example, the sleep type of the target object is determined based on user portrait information such as personal information of the target object, which is not limited in the embodiments of the present application.
  • an exercise time that matches the sleep type can be selected from the candidate exercise time set as the target recommended exercise time.
  • the movement time offset corresponding to the sleep type of the target object is determined from a plurality of preset movement time offsets, and the movement time offset is determined from the candidate movement time set according to the corresponding movement time offset.
  • Target recommended exercise time For example, the mapping relationship between the sleep type and the preset movement time offset can be set in advance, and the movement time offset corresponding to the sleep type of the target object can be determined by searching and comparing.
  • a model for determining the movement time offset can be constructed, and the pre-built model can be used to process the sleep type of the target object to obtain the corresponding movement time offset, or the corresponding movement time offset can be determined through other methods.
  • the amount is not limited in the embodiments of this application.
  • the target recommended exercise time is determined from the candidate exercise time set based on the target subject's sleep type and historical sleep data.
  • the target object's reference sleep start time is determined based on the target object's historical sleep data and/or sleep type; based on the above corresponding motion time offset and the reference sleep start time, a candidate motion time set is selected.
  • Target recommended exercise time is determined based on the target object's historical sleep data and/or sleep type; based on the above corresponding motion time offset and the reference sleep start time.
  • the reference sleep start time of the target subject is determined based on historical sleep start time data included in the historical sleep data.
  • the target object's historical sleep start time on the previous day is used as the target object's reference sleep start time.
  • the reference sleep start time of the target object is obtained by statistically analyzing the historical sleep start time of the target object in the previous week or the first few days of this week.
  • the group sleep start time corresponding to the sleep type of the target object is used as the reference sleep start time of the target object.
  • the group sleep start time may be obtained by performing sleep analysis on a user group belonging to the same sleep type as the target object.
  • the exercise time requirement is determined based on the target object's reference sleep start time and exercise time offset, and the target recommended exercise time is determined from the candidate exercise time set based on the exercise time requirement.
  • the exercise time requirement is determined based on the historical sleep start time data and exercise time offset included in the historical sleep data; at least one candidate exercise time in the candidate exercise time set that meets the exercise time requirement is determined as the target recommended exercise time.
  • the latest movement time of the target object can be determined based on the movement time offset and the reference sleep start time, and then one or more candidate movements located before the latest movement time in the candidate movement time set can be determined.
  • ExtSleepRule represents the time period that meets the exercise time requirements
  • ST t-1 represents the sleep start time of the target object on the previous day or week, that is, the sleep start time of the previous time period or the previous exercise recommendation cycle
  • C2, C3 and C4 respectively represents the movement time offset corresponding to early-rising type, late-rising type, and sleep disorder type.
  • ExtCandidate represents the candidate recommended exercise time set, which includes one or more selected candidate recommended exercise times
  • ExtHistory represents the candidate exercise time set
  • ExtSleepRule represents the exercise time set that meets the exercise time requirements. At least one candidate recommended exercise time in the set of candidate recommended exercise times may be determined as the target recommended exercise time.
  • the candidate recommended exercise time can be determined as the target recommended exercise time.
  • multiple candidate recommended exercise times can be selected from the set of candidate exercise times, and then prompt information is output to prompt the target object to select from the multiple candidate recommended exercise times, and the target is determined based on the received target object input information.
  • Recommended exercise time In this way, the selected target recommended exercise time can be made to better meet the needs or preferences of the target subject, so as to improve the target subject's exercise enthusiasm.
  • the final target recommended exercise time can be determined from multiple candidate recommended exercise times by combining the historical movement frequency of the target object in each candidate recommended exercise time. For example, based on at least part of the historical movement time data of the target object, determine the movement frequency of the target object in each candidate recommended movement time among the plurality of candidate recommended movement times, and determine the movement frequency of the target object in each candidate recommended movement time in the plurality of candidate recommended movement times.
  • the exercise frequency of the exercise time determines the target recommended exercise time from multiple candidate recommended exercise times.
  • the target recommended movement time can be determined from multiple candidate movement times by combining the historical movement frequency of the target object in each candidate movement time included in the candidate movement time set. For example, based on at least part of the historical movement time data of the target object, determine the movement frequency of the target object in each candidate movement time among the plurality of candidate movement times, and determine the movement frequency of the target object in each candidate movement time among the plurality of candidate movement times. Frequency, determine the target recommended exercise time from multiple candidate exercise times.
  • the movement frequency can be obtained from all historical movement time data, or it can be obtained from historical movement time data of a specific time interval, or it can be obtained from historical movement time data that meets specific conditions. There is no limitation here. .
  • the candidate movement time with the highest movement frequency of the target object can be determined from multiple candidate movement times as the target recommended movement time.
  • ExtCandidate represents the multiple candidate recommended movement times of the target object
  • Frequency() is the movement frequency statistical function
  • Ext recommend (t) represents the target recommended movement time
  • Argmax represents the collection of functions.
  • the target recommended exercise time of the target object can be determined based on at least part of the historical exercise time data of the target object's historical sleep data and historical exercise data, and combined with the target object's exercise and sleep habits or preferences, to help the target
  • the subject maintains scientific and regular exercise habits, which lays a foundation for the improvement of the target subject's exercise ability and the achievement of active health goals.
  • the initial exercise recommendation result of the target time period is determined based on the first historical exercise data in the historical exercise data; the initial exercise recommendation result is adjusted based on at least part of the historical sleep data. , get the target motion recommendation results.
  • Figure 4 is a schematic flow chart of another exercise recommendation method provided by an embodiment of the present application. As shown in Figure 4, the method may include but is not limited to S401 to S404.
  • the initial motion recommendation result of the target time period is determined based on the first historical motion data in the historical motion data.
  • the first historical motion data includes motion data for one or more time periods before the target time period.
  • the interval between one or more time periods corresponding to the motion data included in the first historical motion data and the target time period is within a certain numerical range, that is, the interval between the one or more time periods and the target time period The interval is smaller to better reflect the recent movement of the target object.
  • the exercise recommendation strategy for the target time period is determined based on the physiological data measurement results of the target object, and the initial exercise recommendation result for the target time period is determined based on the exercise recommendation strategy for the target time period and the first historical exercise data.
  • the current physiological state of the target object can be determined based on the physiological data measurement results of the target object, and the initial exercise recommendation results for the target time period can be determined based on the current physiological state of the target object.
  • the current physiological state may refer to the physiological state when or before the initial exercise recommendation result is determined.
  • the physiological data measurement results may include one or more types of heart rate data, pressure data, health data, etc., which are not limited in the embodiments of the present application.
  • the target exercise recommendation result includes the target recommended exercise amount.
  • the exercise recommendation strategy may include one of the following: increasing the amount of exercise, reducing the amount of exercise, or maintaining the amount of exercise.
  • the exercise recommendation strategy can be further refined into increasing the amount of exercise of a specific amplitude, decreasing the amount of exercise of a specific amplitude, and so on.
  • the physiological state of the target object is determined based on the physiological data measurement results obtained before determining the initial exercise recommendation result, and the exercise recommendation strategy is determined based on the physiological state of the target object.
  • the exercise recommendation strategy may be an exercise recommendation strategy for the target time period, or may be an exercise recommendation strategy for the current exercise recommendation period (such as this week) to which the target time period belongs.
  • the historical motion data of the target object can be determined based on the first historical motion data of the target object, and then the initial motion recommendation result can be determined based on the historical motion data and the motion recommendation strategy.
  • the amount of movement of each movement of the target object within a specific time interval can be determined based on the first historical movement data of the target object collected by the terminal device, and then based on the amount of movement of each movement of the target object within a specific length of time and the amount of movement of the target object within a specific time interval.
  • the frequency of exercise in a specific time interval is used to obtain the average amount of exercise of the target object.
  • the initial exercise recommendation result of the target time period is determined.
  • the specific time interval may be, for example, the previous week, the previous 21 days, the previous month, etc.
  • the recommended total amount of exercise for the current exercise recommendation cycle can be determined based on the target object's first historical exercise data and the exercise recommendation strategy, and then combined with the recommended total amount of exercise and exercise expert/physiological knowledge and the target object's exercise preferences. At least one of the information/setting information determines the target recommended exercise amount in the target time period.
  • the first historical motion data includes motion data of at least one historical motion recommendation period before the current motion recommendation period.
  • An exercise recommendation cycle can correspond to one week, two weeks, or a specific length of time. For example, if an exercise recommendation period is one week, the total amount of recommended exercise for this week can be determined by the following formula:
  • TRIMP(w) represents the total amount of recommended exercise this week
  • CTL t-1 represents the average amount of exercise of the target object in the previous week
  • R and C1 represent the climbing rate and offset coefficient respectively, which can be obtained from the prior knowledge of sleep.
  • Decrease load represents the movement
  • the exercise recommendation strategy indicates that the amount of exercise needs to be reduced
  • Increase load indicates that the exercise recommendation strategy requires increasing the amount of exercise
  • Maintain load indicates that the exercise recommendation strategy requires maintaining the amount of exercise.
  • the initial exercise recommendation results for each day of the week are determined.
  • the historical motion data may include acceleration data and heart rate data.
  • the acceleration data and heart rate data within a certain time interval included in the first historical motion data the average amount of motion of the target object within the time interval can be obtained.
  • a preset heart rate threshold for example: 110 beats/minute
  • the duration of the movement state and the heart rate data in the movement state are used to obtain the amount of movement of the target object each time it moves.
  • the amount of movement can also be the movement impulse, but the embodiment of the present application does not limit this.
  • the initial exercise recommendation result is adjusted based on at least part of the historical sleep data to obtain the target exercise recommendation result.
  • At least a part of the historical sleep data may refer to all historical sleep data, or a part of the historical sleep data, for example, historical sleep data of a specific time interval.
  • the initial exercise recommendation results can be adjusted based on the sleep data of one or more time periods that are close to the target time period and the time interval between the target time period and the target time period is less than the set value, for example, the sleep of the previous day Data, or sleep data for the previous week, or sleep data for days that have passed this week, etc.
  • the initial exercise recommendation results can be adjusted based on the previous day's sleep data.
  • the initial exercise recommendation result may be adjusted based on the sleep data of the elapsed time interval in the current exercise recommendation cycle.
  • the initial exercise recommendation result may be adjusted based on the sleep data of at least one historical exercise recommendation period before the current exercise recommendation period.
  • the initial exercise recommendation results may be adjusted based on sleep data at a specific time interval from the target time period.
  • the sleep quality evaluation result of the target object is obtained based on at least part of the historical sleep data; the initial exercise recommendation result is adjusted based on the sleep quality evaluation result of the target object to obtain the target exercise recommendation result.
  • the target subject's sleep quality at least one day before the target time period is evaluated to obtain a sleep quality evaluation result, and based on the sleep quality evaluation result, the initial exercise recommendation result is adjusted. , get the target motion recommendation results.
  • the sleep quality assessment result may include a sleep quality score, or may include a sleep quality evaluation grade, such as excellent, good, passing, failing, etc., or may also include parameters used to indicate whether the sleep quality meets the standard, such as meeting the standard or failing. Meet the target, or it can also include indicators indicating the degree of restorative sleep, etc.
  • the reference standard for the sleep quality evaluation result may be for all users, such as a preset fixed standard, or for a group of sleep types of the target subject, for example, the sleep of the target subject is within the group of the sleep type.
  • the embodiment of the present application does not limit the implementation method of sleep quality assessment.
  • the initial exercise recommendation results can be adjusted based on the sleep quality assessment results of the last day or multiple days. For example, if the target subject's sleep quality assessment result indicates that the target subject's sleep quality in the last day or days is relatively high, the recommended amount of exercise included in the initial exercise recommendation result can be kept unchanged, or the amount included in the initial exercise recommendation result can be appropriately increased. recommended amount of exercise. For another example, if the target subject's sleep quality assessment result indicates that the target subject has poor sleep quality in the last day or days, the recommended amount of exercise included in the initial exercise recommendation result can be appropriately reduced to avoid the target subject's physical damage due to excessive exercise. Discomfort.
  • the initial motion recommendation result is adjusted based on at least part of the historical sleep data and the second historical motion data in the historical motion data to obtain the target motion recommendation result.
  • the second historical motion data includes motion data of one or more time periods adjacent to the target time period. The interval between one or more time periods corresponding to the second historical motion data and the target time period is relatively small and may be within a certain interval range.
  • the second historical motion data includes motion data of the previous or previous N time periods of the target time period, such as the motion data of the previous day or the previous N days.
  • the second historical motion data includes motion data of one or more time periods within the current motion recommendation cycle to which the target time period belongs, for example, motion data of at least one day that has passed within the current motion recommendation cycle.
  • the initial exercise recommendation result may be adjusted based on the sleep data and exercise data in one or more time periods within the current exercise recommendation period and before the target time period, to obtain the target exercise recommendation result.
  • the second historical motion data and the historical sleep data used in the process of adjusting the initial motion recommendation results may both correspond to the time interval that has elapsed in the current motion recommendation cycle, such as this week. one or more days.
  • the second historical motion data utilized in the process of adjusting the initial motion recommendation results may correspond to the time interval that has elapsed within the current motion recommendation period, and the historical sleep data utilized may correspond to the target time period. the previous time period, such as the previous day.
  • the movement and sleep status of the target object in the recent period can be integrated, the initial movement recommendation results can be adjusted, and the target movement recommendation results can be obtained, so that the target movement recommendation results are more in line with the target subject's recent physiological state and actual needs.
  • the movement evaluation result of the target object can be obtained based on the second historical movement data, and the movement evaluation result is used to indicate that the target object's movement amount reaches the target; based on at least part of the historical sleep data, the target subject's movement before the target time period can be obtained. At least one day's sleep quality assessment results; based on the exercise assessment results and sleep quality assessment results, the initial exercise recommendation results are adjusted to obtain the target exercise recommendation results.
  • the actual amount of exercise per day in at least one day close to the target time period can be obtained based on the second historical exercise data, and the exercise evaluation result can be obtained based on the actual amount of exercise.
  • the exercise evaluation result can be obtained based on the actual amount of exercise per day in at least one day close to the target time period and the recommended exercise information corresponding to the day.
  • the actual amount of exercise per day of the target object in at least one day that has passed in the current exercise recommendation cycle can be compared with the target object's daily recommended exercise amount is compared to determine whether the target object's daily exercise amount reaches the standard; based on whether the target object's daily exercise amount reaches the standard in at least one day that has passed within the current exercise recommendation cycle, it is determined whether the target object's daily exercise amount reaches the standard.
  • the exercise evaluation results of at least one day that have passed within the current exercise recommendation period can be compared with the target object's daily recommended exercise amount.
  • the exercise evaluation result may include the total amount of exercise meeting the target and/or the frequency of meeting the exercise amount.
  • the total amount of exercise reaching the standard may indicate whether the total amount of exercise in at least one day close to the target time period has reached the standard. For example, the actual total amount of exercise in at least one day that has passed in the current exercise recommendation period reaches the target in at least one day or in the current exercise recommendation period. Recommended total amount of exercise.
  • the frequency of meeting the exercise volume standard may indicate the proportion of the number of days in which the exercise volume reaches the target on at least one day near the target time period to the total number of days corresponding to the at least one day.
  • the actual total amount of exercise of the target object in at least one day can be determined based on the actual amount of exercise of the target object in at least one day close to the target time period, and the total amount of recommended exercise corresponding to the at least one day and the total amount of exercise can be determined.
  • the actual total amount of exercise for at least one day is determined to determine whether the target object's total amount of exercise for at least one day reaches the standard.
  • the recommended total amount of exercise for at least one day may be the target recommended total amount of exercise that has been adjusted according to the embodiment of the present application. In other embodiments, the recommended total amount of exercise for at least one day may also be unadjusted.
  • the initial recommended total amount of exercise is not limited here.
  • the total amount of actual exercise for at least one day close to the target time period may refer to the sum of the actual exercise amount for one or more days that have passed within the current exercise recommendation cycle, and the total amount of recommended exercise corresponding to at least one day close to the target time period may include The total amount of recommended exercise in the current exercise recommendation cycle, or the sum of the recommended exercise amounts in one or more days that have passed in the current exercise recommendation cycle.
  • the target object's daily exercise amount can be determined based on the target object's actual daily exercise amount and the daily recommended exercise amount in at least one day close to the target time period, and the daily exercise amount compliance status of the at least one day can be determined.
  • the amount of exercise should meet the target frequency for at least one day.
  • the target object's amount of exercise on that day has reached the standard. Assuming that the actual amount of exercise on a certain day is less than the recommended amount of exercise on that day, it is determined that the target object's amount of exercise on that day has not reached the standard. Among them, the determination of the amount of exercise reaching the standard can be expressed as follows:
  • TRIMP'(t) represents the actual amount of exercise of the target object on a certain day
  • TRIMP(t) represents the recommended amount of exercise of the target object on this day
  • Achieve(t) represents the amount of exercise reaching the target.
  • the following formula can be used to determine the number of days the target object has reached the target amount of exercise in at least one day close to the target time period:
  • Achieve_count(t) is the number of days when the target object reaches the target amount of exercise in at least one day close to the target time period
  • t is the total number of days corresponding to the at least one day close to the target time period.
  • the number of days when the amount of exercise reaches the target can be divided by the total number of days corresponding to the at least one day to obtain the frequency of reaching the target amount of exercise.
  • the number of days when the amount of exercise reaches the standard can be compared with a preset day threshold. If the number of days when the amount of exercise reaches the standard is greater than the preset threshold, it is determined that the frequency of reaching the standard for exercise meets the requirements. Otherwise, it is determined that the frequency of reaching the standard for exercise does not meet the requirements.
  • the initial recommended exercise amount is adjusted according to at least one of the exercise assessment results and the sleep assessment results to obtain the target recommended exercise amount, wherein the exercise assessment result indicates whether the total amount of exercise reaches the standard and/or the frequency of the exercise amount reaching the standard. Whether the preset threshold is reached.
  • the initial recommended exercise amount included in the initial exercise recommendation result may be adjusted to the target object
  • the minimum amount of exercise is used to obtain the target recommended amount of exercise.
  • the target recommended exercise amount is the minimum exercise amount of the target object.
  • the initial exercise recommendation result can be included. Included are initial recommended levels of exercise adjusted to the target subject's minimum level of exercise.
  • the initial recommended exercise amount included in the initial exercise recommendation result is not adjusted, and the target recommended exercise amount is This is the initial recommended amount of exercise.
  • the initial exercise recommendation result may not be included. Adjust the initial recommended amount of exercise.
  • the initial recommended exercise amount included in the initial exercise recommendation result can be adjusted to 0, and the target recommended exercise amount is 0. .
  • the target recommended exercise amount can be adjusted to 0. That is, the target object is not recommended to exercise during the target time period.
  • the initial recommended exercise amount included in the initial exercise recommendation result may be adjusted to the minimum exercise amount of the target object, and the target The recommended amount of exercise is the minimum amount of exercise for the target object. That is to say, when the exercise assessment result indicates that the total amount of exercise reaches the standard and the frequency of reaching the standard is lower than the preset frequency threshold, regardless of whether the sleep quality indicated by the sleep quality assessment result reaches the preset quality threshold, the initial exercise recommendation result can be included in the result. Included are initial recommended levels of exercise adjusted to the target subject's minimum level of exercise.
  • the initial recommended exercise amount included in the initial exercise recommendation result is not adjusted, and at this time the target recommended exercise amount is Recommended amount of exercise for the initial period.
  • the initial recommended exercise amount included in the initial exercise recommendation result may be adjusted to the minimum exercise amount of the target object, where , the target recommended amount of exercise is the minimum amount of exercise for the target object.
  • the initial recommended exercise amount included in the initial exercise recommendation result can be adjusted to 0.
  • the target recommended exercise amount That is 0.
  • the initial recommended exercise amount included in the initial exercise recommendation result is adjusted to the minimum exercise amount of the target subject , get the target recommended amount of exercise.
  • the initial recommended exercise amount is determined as the target recommended exercise amount.
  • the sleep quality assessment results include sleep recovery degree or sleep recovery index, or the sleep quality assessment results include other parameters.
  • the sleep heart rate variability (Heart Rate Variability, HRV) data of the target object is obtained based on at least part of the historical sleep data; the sleep recovery index of the target object is obtained based on the sleep HRV data of the target object.
  • HRV Heart Rate Variability
  • the specific value of the sleep recovery indicator of the target object can be determined.
  • a quantitative representation of the target subject's sleep recovery index can also be determined to reduce algorithm complexity. For example, it can be determined whether the target object's sleep recovery degree meets the standard. For another example, the level of the target object's sleep recovery degree can be determined, such as good, medium, poor, etc. The embodiments of this application do not implement the sleep recovery index specifically. limited.
  • the historical sleep data may include heart rate data obtained during sleep monitoring, and the sleep HRV data of the target object may be obtained by processing the heart rate data included in the historical sleep data.
  • Sleep HRV data may include sleep-related HRV data for shorter time intervals and/or longer time intervals.
  • the target subject's sleep HRV data may include the target subject's sleep HRV data on the previous day or several days, or at a specific time interval.
  • the sleep HRV data of the target subject may include data obtained by processing the sleep HRV data of the target subject on the previous day or several days, or at a specific time interval.
  • the sleep HRV data of the target subject may also include sleep HRV data of multiple different time intervals.
  • the sleep HRV data of the target subject includes at least one of the following: short-term sleep HRV parameters, long-term sleep HRV parameters, and sleep HRV parameters of the day before the target time period.
  • the short-term sleep HRV parameters may be used to characterize the sleep HRV characteristics of the target subject within a short time interval, such as the previous week, the previous two weeks, or consecutive days within this week.
  • the short-term sleep HRV parameters may include, for example, baseline HRV.
  • the short-term sleep HRV parameter may be obtained by processing sleep heart rate data or sleep HRV data within the first specific time interval.
  • Long-term sleep HRV parameters can be used to characterize the target subject's sleep HRV characteristics over a longer time interval, such as the previous three weeks, the previous month, or longer.
  • the long-term sleep HRV parameter may include, for example, a normal fluctuation range of HRV.
  • the long-term sleep HRV parameter can be obtained by processing sleep heart rate data or sleep HRV data within a second specific time interval, wherein the time length of the second specific time interval can be greater than the time length of the first specific time interval, and The time length of the first specific time interval may be greater than the time length of the target time period.
  • the short-term sleep HRV parameters can be obtained by processing the sleep HRV data of the target subject within a preset short time window, for example, by averaging.
  • the target subject's baseline HRV on that day can be obtained by the following formula:
  • Baseline(t) is the baseline HRV of the target subject on the day or the current time
  • T1 is the preset short-term evaluation time window
  • HRV(i) is the sleep HRV of the i-th day.
  • the short-term sleep HRV parameters may only include the current baseline HRV, or the short-term sleep HRV parameters may also include at least two days of baseline HRV, such as the baseline HRV of the current day and the baseline of the previous day. HRV, the embodiment of this application does not limit this.
  • long-term sleep HRV parameters can be obtained by processing the sleep HRV data of the target subject within a preset longer time window.
  • the normal fluctuation range of the target subject's HRV on the day or at the current time can be obtained by the following formula:
  • N_range(t) is the normal fluctuation range of HRV on the day
  • T2 is the preset long-term evaluation time window
  • ⁇ is the standard deviation within the T2 interval
  • 0.75 is the fitting parameter, which can be adjusted according to the actual situation.
  • the long-term sleep HRV parameter can be used as a reference, combined with at least one of the target subject's short-term sleep HRV parameter and the sleep HRV of the previous day, to determine the sleep recovery index of the target subject.
  • the sleep recovery index of the target subject may be obtained by comparing at least one of the target subject's sleep HRV of the previous day and the target subject's short-term sleep HRV parameter of the current day with the long-term sleep HRV parameter. For example, if the target subject's sleep HRV of the previous day and the baseline HRV of the current day are both within the normal fluctuation range, it can be determined that the target subject's sleep recovery index is the first value, or it can be determined that the sleep recovery degree reaches the standard.
  • the target subject's sleep HRV of the previous day is not within the normal fluctuation range, it is determined that the target subject's sleep recovery index is a second value smaller than the first value, or it is determined that the sleep recovery index does not meet the standard.
  • the target subject's baseline HRV on that day exceeds the upper limit of the normal fluctuation range, it is determined that the target subject's sleep recovery index is the first value, or it is determined that the sleep recovery degree reaches the standard.
  • the baseline HRV of the target subject that day is less than the lower limit of the normal fluctuation range, it is determined that the target subject's sleep recovery index is the second value, or it is determined that the sleep recovery degree is not up to standard.
  • the target subject's sleep recovery index may be determined by analyzing changes in short-term sleep HRV parameters of the target subject, such as changes in baseline HRV for at least two days. For example, if the target subject's baseline HRV on that day is greater than or equal to the target subject's baseline HRV on the previous day, it is determined that the value of the target subject's sleep recovery index is the first value, or it is determined that the sleep recovery degree reaches the standard.
  • the target subject's sleep HRV of the previous day is not within the normal fluctuation range, but the baseline HRV of the current day exceeds the upper limit of the normal fluctuation range, then the target subject's sleep recovery index is determined to be the first value, or the sleep recovery degree is determined to be up to standard.
  • the target subject's sleep HRV of the previous day is not within the normal fluctuation range but the baseline HRV of the current day is greater than the baseline HRV of the previous day, then determine the target subject's sleep recovery index as the first value, or determine that the sleep recovery degree reaches the standard, etc.
  • the embodiments of the present application do not limit the implementation method of determining the sleep recovery index of the target object.
  • At least one of the target subject's sleep recovery index and exercise assessment results may be used to determine the target recommended exercise amount. For example, if the total amount of exercise performed by the target object this week has not reached the target, for example, the total amount of actual exercise performed this week is less than the total amount of recommended exercise this week, and the sleep recovery index indicates that sleep recovery is good, for example, the sleep recovery index is the first value, the initial recommended amount of exercise is adjusted to the lowest amount of exercise of the target object, wherein the lowest amount of exercise of the target object can be determined based on at least one of the target object's attribute information, historical exercise data, and exercise preference information.
  • the initial recommended amount of exercise will not be adjusted.
  • the target object's total amount of exercise this week has reached the target, but the frequency of reaching the target amount of exercise is low, for example, the frequency of reaching the target amount of exercise has not reached the preset frequency threshold, the recommended amount of exercise can be adjusted to the target object's minimum amount of exercise.
  • the recommended amount of exercise can be adjusted to 0 or other preset values, such as preset by the target object. numerical value.
  • only the target recommended amount of exercise may be output.
  • the information of the initial recommended exercise amount and the target recommended exercise amount can also be output simultaneously, and indicate whether the user agrees to the adjustment of the recommended exercise amount, or instruct the user to adjust the initial recommended exercise amount and the target recommended exercise amount. Head Choose from the recommended amount of exercise, which is not limited in the embodiments of this application.
  • the initial exercise recommendation result of the target time period may be determined, and the initial exercise recommendation result may be adjusted based on at least part of the historical sleep data and the second historical exercise data in the historical exercise data, Get target exercise recommendation results.
  • the initial motion recommendation result of the target time period can be determined based on the first historical motion data.
  • the initial motion recommendation result of the target time period can be obtained based on the first historical motion data of the time period corresponding to the target time period within at least one historical motion recommendation period.
  • the actual exercise time and the actual exercise amount included in the first historical exercise data of the corresponding time period are respectively used as the initial recommended exercise time and the initial recommended exercise amount.
  • the initial motion recommendation result of the target time period may be determined based on the first historical motion data and the physiological data measurement results of the target object.
  • the current physiological state of the target object can be obtained based on the physiological data measurement results of the target object, and the initial recommended exercise amount and/or the initial recommended exercise time of the target time period can be determined based on the current physiological state of the target object.
  • the initial motion recommendation results for the target time period can be determined based on user input information. For example, the user inputs an exercise plan for a certain day or a certain week. At this time, the initial exercise recommendation results for the target time period can be determined based on the exercise plan input by the user.
  • the initial motion recommendation result of the target time period may be determined based on historical motion recommendation information of the previous time period, several previous time periods, or at least one historical motion recommendation period and other time intervals. For example, determining the initial exercise recommendation for the target time period based on the recommended exercise time and/or recommended exercise amount of the time period (such as the day of the week) corresponding to the target time period in at least one historical exercise recommendation period (such as the previous week or weeks) result.
  • the recommended exercise time of the corresponding time period can be used as the initial recommended exercise time of the target time period, and the recommended exercise amount of the corresponding time period can be used as the initial recommended exercise amount of the target time period, or the recommended exercise amount in the corresponding time period
  • a certain amount of adjustment is made on the basis of, for example, a certain amount of adjustment is made to the recommended amount of exercise in the corresponding time period based on the current physiological state of the target object to obtain the initial recommended amount of exercise in the target time period.
  • historical exercise recommendation information and first historical exercise data can be combined to obtain an initial exercise recommendation result for the target time period. For example, based on the first historical movement data, the historical movement recommendation information is adjusted to obtain an initial movement recommendation result for the target time period.
  • the initial exercise recommendation result can be obtained based on one or more information such as the attribute information of the target object, such as basic information, the user group to which the target object belongs, the sleep type of the target object, the sleep group to which the target object belongs, etc. .
  • the initial exercise recommendation results are obtained for a certain day or for each day of a certain week.
  • any two or more implementation methods in the above possible implementation examples can be combined to obtain the initial motion recommendation result in the target time period.
  • the initial exercise recommendation result can be adjusted based on at least one day's sleep data adjacent to the target time period and at least one day's exercise data adjacent to the target time period, to obtain the target exercise recommendation result.
  • the initial exercise recommendation result can be adjusted based on at least one day's exercise data within the current exercise recommendation period and the sleep data of the previous day in the target time period to obtain the target exercise recommendation result.
  • the location of the target object in multiple locations can be obtained based on at least one of attribute information of the target object, motion preference information of the target object, motion prior information, historical motion data of the target object, and physiological data measurement results of the target object.
  • the first exercise recommendation for different exercise recommendation cycles can be the same, or change with a certain step size, etc.
  • the first exercise recommendation of each exercise recommendation period may include the first exercise recommendation results of multiple time periods included in the exercise recommendation period, or may only include the total exercise recommendation of the exercise recommendation period without dividing each time period.
  • a first adjustment process may be performed on the first exercise recommendation.
  • the historical exercise data of at least one historical exercise recommendation period before the exercise recommendation period may be used.
  • the first exercise recommendation of the exercise recommendation cycle is carried out Adjustment processing, or adjustment processing of the first exercise recommendation result of at least one time period in the exercise recommendation cycle, to obtain the second exercise recommendation of the exercise recommendation cycle.
  • the second exercise recommendation may include second exercise recommendation results for multiple time periods included in the exercise recommendation cycle.
  • a second adjustment process may be performed on the second exercise recommendation.
  • each time period of the exercise recommendation cycle Before or when each time period of the exercise recommendation cycle arrives, it may be based on at least one historical time period in the exercise recommendation cycle ( That is, the historical motion data and/or historical sleep data of at least one time period that has passed) are adjusted to the second motion recommendation result of the time period to obtain the third motion recommendation result of the time period. Finally, the user is provided with the third exercise recommendation result in the time period.
  • the first exercise recommendation result in a certain time period may be the initial exercise recommendation result in the time period
  • the second exercise recommendation result may be the target exercise recommendation result in the time period.
  • the second exercise recommendation result of a certain time period may be the initial exercise recommendation result of the time period
  • the third exercise recommendation result may be the target exercise recommendation result of the time period.
  • the first exercise recommendation result of a certain time period may be the initial exercise recommendation result of the time period
  • the third exercise recommendation result of the time period may be the target exercise recommendation result of the time period.
  • FIG. 5 is a schematic diagram of an exemplary exercise amount recommendation solution provided by an embodiment of the present application.
  • motion monitoring of the target object can be performed to obtain motion data of the target object.
  • the movement of the target object can be monitored through one or more sensors of a wearable device or other types of terminal equipment, and the movement data of the target object can be obtained, such as heart rate data, acceleration data, location, exercise type, exercise intensity, exercise start time, One or more types such as the end time of exercise.
  • sleep monitoring of the target object can be performed to obtain sleep data of the target object.
  • the sleep data of the target subject can be obtained through one or more sensors of a wearable device or other types of terminal equipment, or through a sleep monitor set on the bed, and the sleep data can include sleep data.
  • the sleep data can include sleep data.
  • the motion recommendation model can be used to obtain the initial recommended motion amount of the target object based on the motion data of the target object.
  • the target object's daily recommended amount of exercise in the current motion recommendation period (such as one week or other lengths of time) is obtained.
  • the frequency of reaching the standard of movement amount can be detected based on the movement data of the target object, and the frequency of reaching the standard of movement amount of the target object can be obtained.
  • the target object's motion data in the current exercise recommendation period is used to obtain the target object's current frequency of reaching the target amount of exercise.
  • the sleep recovery evaluation model can be used to obtain the target object's current sleep recovery index.
  • the target subject's current sleep recovery index can be obtained based on the target subject's sleep data in a previous period of time (such as the previous day, the previous week, or a specific length of time).
  • a dynamic adjustment strategy is used to adjust the initial recommended exercise amount in the target time period to obtain the target recommended exercise amount in the target time period.
  • whether to adjust the initial recommended amount of exercise can be determined based on sleep recovery indicators. For example, if the sleep recovery index reaches the preset index threshold, the initial recommended exercise amount will not be adjusted, that is, the target recommended exercise amount will be the initial recommended exercise amount. For another example, if the sleep recovery index does not reach the preset index threshold, it is determined to adjust the initial recommended exercise amount. At this time, the initial recommended exercise amount can be directly adjusted to the minimum exercise amount or 0, or the target recommended exercise amount can be determined based on the frequency of reaching the standard amount of exercise. For example, if the frequency of reaching the standard amount of exercise reaches the preset frequency threshold, the initial recommended amount of exercise is adjusted to 0. For another example, if the frequency of reaching the standard amount of exercise does not reach the preset frequency threshold, the initial recommended amount of exercise is adjusted to the minimum amount of exercise.
  • the initial recommended exercise amount of the target object can be determined, and the initial recommended exercise amount can be dynamically adjusted according to at least one of the target object's current exercise and sleep conditions, thereby helping the target object maintain scientific and regular exercise habits.
  • the exercise recommendation method of the present application can provide appropriate exercise suggestions to the target object, help the target object to perform scientific exercise to produce a sleep aid effect, thereby improving the quality of night sleep; at the same time, good night sleep Quality can also increase the target's willingness to move during the day, making the target more receptive to exercise recommendations.
  • good night sleep Quality can also increase the target's willingness to move during the day, making the target more receptive to exercise recommendations.
  • Figure 6 is a schematic diagram of an exemplary exercise recommendation solution provided by an embodiment of the present application.
  • this exercise recommendation solution is based on the two-way influence between exercise and sleep.
  • the movement of the target object is monitored through a terminal device such as a wearable device to obtain the movement data of the target object.
  • sleep monitoring of the target object is performed through a terminal device such as a wearable device to obtain sleep data of the target object.
  • the candidate movement amount and candidate movement time of the target object may be determined respectively based on the movement data of the target object.
  • the candidate motion amount of the target object can be obtained based on the motion data of the target object in the previous time interval of a first specific length
  • the candidate motion amount of the target object can be obtained based on the motion data of the target object in the previous time interval of a second specific length.
  • candidate motion time wherein the motion data relied upon when determining the candidate motion amount and the candidate motion time may be at the same time interval or at different time intervals, for example, the first specific length may be shorter than the second specific length,
  • the embodiments of the present application are not limited to this.
  • the sleep start time and sleep recovery index of the target object can be determined respectively based on the sleep data of the target object.
  • the target subject's current sleep recovery indicator may be determined based on the target subject's sleep data within a previous interval of a specific length, which may be the same as the length of the time interval used to determine the candidate amount of exercise or the candidate exercise time, It can also be different.
  • the target subject's sleep start time (such as the time to fall asleep or the time to go to bed) is determined based on the target subject's sleep data of the previous day or the previous few days or weeks.
  • the target amount of exercise in the target time period may be determined based on the candidate exercise amount of the target object and the current sleep recovery index.
  • At least one candidate amount of exercise may be selected from multiple candidate amounts of exercise as the target amount of exercise based on the current sleep recovery index of the target object.
  • the candidate exercise amount can be adjusted based on the current sleep recovery index to obtain the target exercise amount.
  • the target movement time of the target object may be determined based on the candidate movement time of the target object and the sleep start time.
  • At least one candidate movement time may be selected from a plurality of candidate movement times based on the sleep start time of the target object as the target movement time.
  • the candidate movement time can be adjusted based on the sleep start time of the target object to obtain the target movement time, where the adjustment process can be limiting, deleting, increasing or shifting, etc.
  • exercise suggestions for the target time period may be output, and the exercise suggestions may indicate the target exercise time and target exercise amount of the target object in the target time period.
  • relevant information of the exercise suggestions may be sent to the wearable device, or the exercise advice may be sent to the wearable device.
  • the relevant information of the exercise suggestion may be directly output to the user, or the relevant information of the exercise suggestion may be sent to other devices, which is not limited in the embodiments of the present application.
  • sleep recommendations can also be provided for the target object based on the target object's sleep data and combined with the target object's expected sleep information.
  • FIG. 7 is a schematic flowchart of a sleep recommendation method provided by an embodiment of the present application. As shown in Figure 7, the method may include but is not limited to S701 to S704.
  • the historical sleep data of the target object can be collected through the terminal device.
  • the terminal device can collect the sleep data through at least one of a motion sensor and a physiological sensor.
  • the motion sensor includes, for example, an acceleration sensor, One or more sensors such as a gyroscope, and physiological sensors may include, for example, one or more heart rate sensors, respiration sensors, body temperature sensors, blood pressure sensors, etc.
  • the historical sleep data may include sleep data for one or more time periods before the target time period.
  • historical sleep data may include sleep data for one or more days prior to the target time period.
  • the historical sleep data includes the sleep data of the previous day.
  • the historical sleep data includes sleep data for one or more days of the current sleep recommendation cycle, for example, includes sleep data for one or more days within this week and before the current day.
  • the historical sleep data includes sleep data of at least one historical sleep recommendation period, for example, includes sleep data of multiple days in the previous week.
  • the historical sleep data may be the historical sleep data in the embodiments described above, which is not limited in the embodiments of the present application.
  • Historical sleep data may include one of sleep start time (i.e., time to fall asleep), sleep end time (i.e., wake-up time), sleep duration, number of wake-ups, cumulative wake-up time, sleep breathing data, sleep heart rate data, sleep latency, etc. species or any variety. For specific implementation, reference may be made to the above embodiments, which will not be described again here.
  • At least one target sleep parameter value of the target object is obtained according to at least one of the attribute information of the target object and the desired sleep information of the target object.
  • the attribute information of the target object includes basic personal information of the target object, such as one or any combination of age, gender, BMI, occupation, hobbies, sleeping habits, geographical location, etc.
  • the attribute information of the target object may include other information, such as one or more of the user group to which the target object belongs, the sleep group to which the target object belongs, or the sleep type of the target object.
  • the target object's desired sleep information includes at least one desired sleep parameter value, that is, the desired value of at least one sleep parameter, for example, desired sleep duration, desired waking time, desired falling asleep time, or one or more, Alternatively, expected values for other sleep parameters may also be included.
  • the desired sleep information may be obtained by receiving user input information, or may be obtained based on the sleep information of the group to which the target object belongs, and so on.
  • the desired sleep information may include the direction of sleep improvement of the target subject, for example, the sleep duration becomes longer, or the proportion of deep sleep increases, or the sleep latency becomes shorter, etc.
  • the at least one target sleep parameter value of the target object may include a target value of at least one sleep parameter, for example, one or more of target sleep time, target wake-up time, target sleep duration, etc.
  • At least one target sleep parameter value of the target object is obtained according to the attribute information of the target object.
  • at least one target sleep parameter value of the target object is obtained according to the user group and/or sleep group to which the target object belongs.
  • At least one target sleep parameter value of the target object is obtained according to the desired sleep information of the target object.
  • at least one desired sleep parameter value included in the desired sleep information is determined as at least one target sleep parameter value.
  • at least one target sleep parameter value is obtained by performing arithmetic processing on at least one desired sleep parameter included in the desired sleep information.
  • At least one target sleep parameter value of the target object is obtained according to the desired sleep information of the target object and the attribute information of the target object. For example, a part of the target sleep parameter value is determined as the expected sleep parameter value in the expected sleep information, and another part of the target sleep is obtained by using at least one expected sleep parameter value included in the expected sleep information or the determined target sleep parameter value and attribute information. parameter value.
  • the weights of the desired sleep information and the attribute information can be set, and the target sleep parameter value can be obtained based on the desired sleep information, the attribute information and their corresponding weights.
  • the sleep improvement model can be used to process the desired sleep information and attribute information to obtain the target sleep parameter value.
  • other methods may be used to obtain the target sleep parameter value.
  • the desired sleep information is considered as a priority factor. If the desired sleep information is available, the desired sleep information is used to obtain the target sleep parameter value. If there is no desired sleep information available, the attribute information is used to obtain the target sleep parameter value. For another example, attribute information is considered as a priority factor. If attribute information is available, the initial sleep parameter value is obtained using the attribute information, and the period is used to obtain the initial sleep parameter value. The initial sleep parameter value is adjusted based on the desired sleep information to obtain the target sleep parameter value.
  • the validity of each of some or all of the desired sleep parameter values included in the desired sleep information may be determined. For example, it may be determined whether the value of each desired sleep parameter value in the at least one desired sleep parameter value is within a corresponding preset value range, wherein different desired sleep parameter values may be set to different preset value ranges. If a certain desired sleep parameter value is within a preset value range, the desired sleep parameter value is determined to be valid; otherwise, the desired sleep parameter value is determined to be invalid.
  • the preset numerical range can be determined based on prior knowledge of sleep, or the preset numerical range can be determined based on attribute information of the target object, for example, based on the group to which the target object belongs. Alternatively, the preset numerical range is determined by other methods, which is not limited here.
  • the expected sleep parameter value in response to the existence of a valid expected value for a certain sleep parameter, that is, the expected sleep information includes a valid expected sleep parameter value corresponding to the sleep parameter, then the expected sleep parameter value can be used to determine the sleep state.
  • the target value of the parameter is the target sleep parameter value corresponding to the sleep parameter.
  • a valid desired sleep parameter value is determined as a target sleep parameter value corresponding to the sleep parameter.
  • the corresponding target sleep parameter value is obtained by processing the valid desired sleep parameter value.
  • the expected sleep information in response to a certain sleep parameter not having a valid expected value, that is, the expected sleep information does not contain a valid expected sleep parameter value corresponding to the sleep parameter, for example, the expected sleep information does not include a valid expected sleep parameter value corresponding to the sleep parameter. If the expected sleep parameter value, or the expected sleep parameter value corresponding to the included sleep parameter, is not within the preset value range, the attribute information of the target object, the effective expected sleep parameter value or the corresponding target sleep parameter value, and sleep physiology can be used At least one of the knowledge is used to determine the target sleep parameter value corresponding to the sleep parameter.
  • the desired sleep information validity judgment result may include: the desired sleep information is valid or the desired sleep information is invalid. For example, it can be determined whether at least one desired sleep parameter value included in the desired sleep information is valid to determine whether the desired sleep information is valid. As an example, if all desired sleep parameter values included in the desired sleep information are invalid, or the number or proportion of invalid desired sleep parameter values included exceeds a certain threshold, the desired sleep information is determined to be invalid. For another example, determine whether the expected sleep information contains an expected value of a specific sleep parameter, or whether the expected value of a specific sleep parameter contained in the expected sleep information is valid, to determine whether the expected sleep information is valid.
  • the desired sleep information includes multiple desired sleep parameter values
  • the implementation method of judging the validity of the desired sleep information is not limited.
  • At least one target sleep parameter value may be determined based on a validity determination result of at least one desired sleep parameter value. As some implementation methods, it can be determined whether the expected sleep information includes a valid expected sleep parameter value corresponding to a certain sleep parameter. If a valid expected sleep parameter value corresponding to the sleep parameter is included, the target sleep parameter value corresponding to the sleep parameter can be obtained by using the valid expected sleep parameter value. If the effective expected sleep parameter value corresponding to the sleep parameter is not included, the target sleep parameter value corresponding to the sleep parameter can be determined using the attribute information of the target object and/or sleep prior knowledge.
  • target sleep parameter values include target sleep duration.
  • the target sleep duration for the target subject is determined as the valid desired sleep duration. If a valid desired sleep duration is not included, e.g. If the desired sleep duration is invalid, or the included desired sleep duration is invalid, the target sleep duration is determined based on the attribute information of the target object. For example, the target sleep duration of the target subject is determined based on at least one of the target subject's gender, age, and BMI, as well as sleep prior knowledge and/or preset mapping rules.
  • the group to which the target object belongs (such as a user group and/or a sleep group) is determined based on the attribute information of the target object, and the target sleep duration of the target object is determined based on the information of the group to which the target object belongs.
  • the target sleep duration can be obtained by the following formula:
  • TargetTST represents the target sleep duration
  • TargetTST rule represents the recommended sleep duration of the group to which the target object belongs
  • TargetTST user represents the expected sleep duration included in the target object's expected sleep information.
  • the target sleep duration is determined as the desired sleep duration. If the desired sleep duration is invalid, the target sleep duration is determined as the recommended sleep duration for the group to which the target object belongs.
  • target sleep parameter values corresponding to other sleep parameters and/or other sleep parameters included in the desired sleep information can be used.
  • the corresponding effective expected sleep parameter value is used to determine the target sleep parameter value corresponding to the sleep parameter.
  • a part of the plurality of target sleep parameter values may be determined based on at least one of the attribute information of the target object and the desired sleep information, and based on the determined part of the parameter values and the desired sleep information of the target object. At least one method is to determine another part of the target sleep parameter values.
  • the target desired parameter value includes a target sleep duration and a target fall asleep time (or a target sleep start time) and/or a target wake-up time (or a target sleep end time), which may be based on the target sleep duration and/or the target sleep information included in the desired sleep information.
  • Effective desired wake time to determine target sleep time may be determined based on the target sleep duration and/or a valid expected sleep time included in the expected sleep information.
  • the target sleep time can be determined by:
  • TargetST is the target sleep time
  • TargetST rule is the sleep time determined based on the target object's attribute information and/or sleep prior knowledge
  • TargetST user is the target object's expected sleep time
  • TargetWT user is the target object's expected wake time
  • TargetTST is the target sleep duration.
  • the target sleep time is determined as the desired sleep time. If the expected sleep information includes an expected wake-up time, or includes a valid expected wake-up time, the target sleep time can be determined based on the expected wake-up time and the target sleep duration. If the expected sleep information does not include the expected sleep time or valid expected sleep time, nor the expected wake time or valid expected wake time, then the target sleep time is determined based on the attribute information of the target object and/or sleep prior knowledge. Time, for example, determine the target bedtime of the target object as the recommended bedtime of the group to which the target object belongs.
  • the above formulas can be used to determine the target sleep duration and the target fall asleep time respectively, and the target wake-up time of the target object can be determined based on the target sleep duration and the target fall asleep time.
  • the target wake-up time can be determined by the following formula:
  • TargetST rule is the sleep time determined based on the target object's attribute information and/or sleep prior knowledge
  • TargetTST is the target sleep duration
  • TargetST user is the target object's expected sleep time
  • TargetWT user is the expected wake-up time of the target subject.
  • the target wake-up time is determined as the desired wake-up time. If the expected sleep information includes the expected sleep time or a valid expected sleep time, the target wake-up time is obtained based on the expected sleep time and the target sleep duration. If the target object's expected sleep information does not include the expected sleep time or valid expected sleep time, nor the expected wake time or valid expected wake time, then based on the target object's attribute information and/or sleep prior knowledge Determine the target sleep time and target sleep duration to determine the target wake-up time.
  • a sleep recommendation result of the target object in the target time period is obtained.
  • the sleep recommendation result includes at least one recommended sleep parameter value.
  • the sleep recommendation result includes at least one of recommended sleep time, recommended wake-up time, and recommended sleep duration.
  • the historical sleep data may include sleep data for one or more time periods before the target time period.
  • the historical sleep data may be used to indicate the recent sleep status of the target subject.
  • the historical sleep data may include sleep data of the previous week, the previous month, or other time intervals, which is not limited here.
  • the current sleep parameter value of the target object is obtained, and based on at least one target sleep parameter value of the target object, the current sleep parameter value of the target object is adjusted according to a preset sleep adjustment strategy. Adjust to obtain at least one recommended sleep parameter value included in the sleep recommendation result of the target object.
  • the preset sleep adjustment strategy may include a progressive adjustment strategy (or a step-by-step adjustment strategy) and a direct adjustment strategy (or a single-level adjustment strategy or a one-step adjustment strategy), wherein, In the gradual adjustment strategy, the current sleep parameter value can be used as the starting point and gradually approaches the target sleep parameter value as time goes by. In the direct adjustment strategy, the current sleep parameter value can be directly adjusted to the target sleep parameter value.
  • the preset sleep adjustment strategy can also be implemented in other ways, which is not limited here.
  • the sleep recommendation results of the target time period may include sleep recommendation results for the current day, tomorrow, next week, or a certain time interval set by the target object.
  • S701 and S702 can be executed in any order or at the same time.
  • S702 may be performed in advance and the target sleep parameter value may be stored, and then S701 may be performed. That is, the historical sleep data of the target object is collected through the terminal device, and the stored target sleep parameter values are obtained. Finally, the sleep recommendation results for the target time period are obtained based on the historical sleep data and target sleep parameter values.
  • S701 may be performed first, that is, the historical sleep data of the target object is collected through the terminal device and stored, and then S702 is performed to obtain at least one target sleep parameter value of the target object, which is not limited here.
  • At least one target sleep parameter value of the target object can be obtained based on at least one of the target object's attribute information and desired sleep information, and based on at least one target sleep parameter value and historical sleep data of the target object, Obtain the sleep recommendation results of the target object, thereby helping the target object gradually develop scientific and regular sleep habits.
  • Figure 8 is a schematic diagram of an exemplary sleep recommendation solution provided by an embodiment of the present application.
  • the attribute information of the target object can be obtained.
  • the attribute information of the target object includes basic information, such as one or more of age, gender, BMI and other information.
  • the reference sleep duration of the group to which the target object belongs can be determined based on the attribute information of the target object.
  • the group to which the target object belongs can be determined based on the attribute information of the target object, and the reference sleep duration can be determined based on the group to which the target object belongs, such as group attribute information, sleep information of other objects in the group, etc.
  • the subjective expectation information of the target object can be obtained, for example, the target object can be obtained through user interaction operation.
  • Subjective expectation information input by the subject for example, the expected value of one or any number of sleep parameters such as the expected time to fall asleep, the expected sleep duration, the expected wake-up time, etc.
  • the subjective expectation information may be the desired sleep information in the above embodiment.
  • the sleep target of the target subject may be determined based on at least one of the target subject's subjective expectation information and the reference sleep duration of the group to which the target subject belongs.
  • the sleep target may include target values of one or any plurality of sleep parameters such as target sleep time, target wake-up time, and target sleep duration.
  • S802 may not be executed, and this is not limited in the embodiments of the present application.
  • sleep monitoring of the target object can be performed to obtain historical sleep data of the target object within a preset time interval.
  • the historical sleep data may include one or any combination of sleep start time, sleep end time, sleep stage data, sleep breathing data, sleep quality data, etc.
  • the preset time interval may be the previous week, but the embodiment of the present application does not limit this.
  • a step-by-step adjustment strategy can be used to obtain the target object's sleep recommendations in the target time period (S807).
  • the sleep recommendations include Recommended values for one or any number of sleep parameters including recommended sleep time, recommended sleep duration, and recommended wake-up time to help target subjects gradually develop regular sleep habits.
  • the target object's sleep adjustment strategy is determined based on the target object's historical sleep data and at least one target sleep parameter value, and the target object's sleep recommendation results are obtained based on the sleep adjustment strategy.
  • the sleep adjustment strategy may include a gradual adjustment strategy or a direct adjustment strategy.
  • the incremental adjustment strategy is to make smaller, stepwise adjustments to the sleep parameters of the target subject.
  • the direct adjustment strategy is to adjust the sleep parameters of the target object to the target sleep parameter value at one time.
  • the target subject's sleep adjustment strategy may be determined based on a difference between at least one current sleep parameter value and at least one target sleep parameter value indicated by historical sleep data.
  • a direct adjustment strategy can be adopted.
  • a progressive adjustment strategy can be adopted to allow the target subject to sleep parameters to achieve sleep goals step by step.
  • the historical sleep data of the target object can be processed, such as statistical processing, to obtain at least one current sleep parameter value of the target object.
  • the target object's historical sleep data within a certain time interval can be processed to obtain the target object's average sleep duration within the time interval.
  • the average sleep duration can be obtained by processing multiple days of sleep within the time interval. It is obtained by averaging the sleep duration, for example, the average of the sleep duration of multiple days, or it is obtained by averaging after filtering out the maximum value, minimum value or abnormal value of the sleep duration of multiple days, or it is obtained by averaging the occurrence frequency of more than
  • the sleep duration of a certain threshold is obtained through statistical processing, etc., and the embodiments of the present application do not limit this.
  • the sleep recommendation results of the target object in response to the difference between the at least one current sleep parameter value and the at least one target sleep parameter value indicated by the target subject's historical sleep data exceeding the preset difference range, based on the adjustment step size and the at least one current sleep parameter value, Obtain the sleep recommendation results of the target object.
  • the current sleep parameter value is adjusted with an adjustment step to obtain the recommended sleep parameter value included in the sleep recommendation result, so that the recommended sleep parameter value included in the sleep recommendation result gradually approaches the target sleep parameter value as time goes by.
  • a progressive adjustment strategy can be used to adjust the current sleep parameter values.
  • the adjustment step size may be preset. Alternatively, the adjustment step size can be obtained based on attribute information of the target object, for example, based on the group to which the target object belongs. Alternatively, the adjustment step size may be obtained based on the difference between the current sleep parameter value and the target sleep parameter value. For example, the adjustment step size may be obtained based on the difference and a preset time interval for achieving the sleep target. Or, the adjustment step size is determined based on user input information, etc. The implementation method of the adjustment step size is not limited here.
  • determining the target subject's sleep are target sleep parameter values.
  • a direct adjustment strategy can be used to adjust the current sleep parameter values.
  • the difference between the at least one current sleep parameter value and the at least one target sleep parameter value may include a difference value between each of the at least one current sleep parameter value and the corresponding target sleep parameter value.
  • the difference between the at least one current sleep parameter value and the at least one target sleep parameter value is within the preset difference range, which may mean that each difference value is within the corresponding preset difference range, or means that it is within the corresponding preset difference range. Assume that the proportion of difference values within the difference range exceeds a certain value, or that the statistical value of the difference values is within the preset difference range, etc.
  • the difference between the at least one current sleep parameter value and the at least one target sleep parameter value includes a difference value between a certain current sleep parameter value and the corresponding target sleep parameter value.
  • the difference between the at least one current sleep parameter value and the at least one target sleep parameter value includes statistical information of at least one difference value between the at least one current sleep parameter value and the at least one target sleep parameter value, such as a maximum difference, a minimum Difference or average difference, etc. There is no limit to the specific implementation method here.
  • the recommended sleep duration this week can be obtained by the following formula:
  • TST recommend (W) is the recommended sleep duration for this week
  • C5 is the preset difference range corresponding to the sleep duration
  • ⁇ TST is the adjustment step corresponding to the sleep duration, for example: twenty minutes
  • TST (w-1) is the target The subject's average sleep duration over the past week.
  • the target subject's average sleep duration in the previous week is used as the target subject's current sleep duration. If the difference between the target object's average sleep duration in the previous week and the target sleep duration is less than or equal to C5, a direct adjustment strategy is adopted to directly determine this week's recommended sleep duration as the target sleep duration. If the difference between the target object's average sleep duration in the previous week and the target sleep duration is greater than C5, a progressive adjustment strategy will be adopted to determine the recommended sleep duration for this week as the average sleep duration in the previous week increased by ⁇ TST or reduce.
  • the adjustment step size ⁇ TST may be a preset fixed value, or may be determined based on expectations of the target object, or may be determined based on attribute information of the target object, and so on.
  • the adjustment step size ⁇ TST corresponding to the sleep duration may be equal to the preset difference range C5 corresponding to the sleep duration.
  • the adjustment step size ⁇ TST corresponding to the sleep duration can also be set to a value different from the preset difference range C5 corresponding to the sleep duration, which is not limited in the embodiments of the present application.
  • the recommended bedtime for this week can be obtained by:
  • ST recommend (w) is the recommended sleep time for this week
  • ST(w-1) is the average sleep time of the target object in the previous week
  • ⁇ ST is the adjustment step corresponding to the sleep time
  • C6 is the preset corresponding to the sleep time. range of differences.
  • the target subject's current bedtime is determined to be the target subject's average bedtime over the previous week. If the difference between the target subject's average sleep time in the previous week and the target sleep time is less than or equal to C6, a direct adjustment strategy is adopted to directly determine this week's recommended sleep time as the target sleep time. And if the difference between the target object's average sleep time in the previous week and the target sleep time is greater than C6, a gradual adjustment strategy will be adopted to determine the recommended sleep time this week as the average sleep time in the previous week increased by ⁇ ST or reduce.
  • the adjustment step size ⁇ ST may be a preset fixed value, or may be determined based on expectations of the target object, or may be determined based on attribute information of the target object, and so on.
  • the adjustment step ⁇ ST corresponding to the falling asleep time may be equal to the preset difference range C6 corresponding to the falling asleep time.
  • the adjustment step ⁇ ST corresponding to the falling asleep time can also be set to a value different from the preset difference range C6 corresponding to the falling asleep time, which is not limited in the embodiment of the present application.
  • the target subject may also be guided to supplement sleep.
  • the supplementary sleep recommendation results of the target object in the target time period can be obtained.
  • the supplementary sleep recommendation result may include recommending that the target object perform supplementary sleep or not, or include Including the recommended duration for the target subject to supplement sleep, the longest sleep duration, the latest wake-up time or the latest sleep time, etc., the embodiments of the present application do not limit this.
  • Regular sleep here may refer to longer periods of sleep that the subject engages in, such as nighttime sleep, while supplemental sleep may refer to shorter periods of sleep that the subject engages in, such as daytime naps or naps.
  • the supplementary sleep recommendation results for the target time period can be obtained based on the sleep data of the previous day, or based on the sleep data of one or more days that have passed this week.
  • the target subject's regular sleep data of the previous day can be obtained by measuring the target subject's physiological data and body movement data during regular sleep, such as regular sleep duration, regular sleep quality assessment, regular sleep staging data, etc., and Based on the regular sleep data, the supplementary sleep recommendation results of the target object in the target time period are obtained.
  • the regular sleep duration of the previous day is less than the preset duration threshold, the target subject may be recommended to supplement sleep during the target time period.
  • the supplementary sleep recommendation result may include a first indicator for recommending supplementary sleep, Or the recommended supplementary sleep duration included in the supplementary sleep recommendation result is the first duration greater than zero.
  • the target subject may be recommended not to perform supplementary sleep during the target period.
  • the supplementary sleep recommendation result may include recommending not to perform supplementary sleep.
  • the second indicator, or the supplementary sleep recommendation result includes a supplementary sleep recommended duration of zero.
  • the previous day's regular sleep duration is equal to or greater than the preset duration threshold, it may be determined whether to recommend supplementary sleep in the target time period based on historical supplementary sleep data included in the target subject's historical sleep data.
  • the target subject may be recommended to supplement sleep during the target time period, and if the target subject's historical supplementary sleep data indicates that the target subject does not have the habit of supplementing sleep, Then it can be recommended that the target object does not perform supplementary sleep during the target time period.
  • the preset duration threshold may be a preset fixed value, such as 8 hours, or may be determined based on the target subject's historical sleep data, such as the target subject's regular sleep average duration, or may be determined based on the target subject's expected sleep information or sleep goal. , no limitation is made here.
  • whether to recommend supplementary sleep in the target time period can be determined based on the target subject's routine sleep quality assessment results on the previous day. For example, whether to recommend supplementary sleep in the target time period can be determined based on the target subject's sleep recovery index. Supplementary sleep, or use other types of historical sleep data to determine whether to recommend supplementary sleep during the target time period, which is not limited here.
  • a recommended duration of supplemental sleep may also be determined.
  • the recommended duration of supplementary sleep may be preset, such as 30 minutes or no more than 1 hour.
  • the recommended supplementary sleep duration may be determined by combining the target subject's subjective expectation information and the previous day's regular sleep duration.
  • the recommended supplementary sleep duration may be determined based on historical supplementary sleep data included in the target subject's historical sleep data, such as the average duration of supplementary sleep in the previous week.
  • the recommended supplementary sleep duration can be determined based on attribute information of the target object, and so on.
  • the recommended length of supplementary sleep for a target time period can be determined by:
  • Nap recommend (t) is the recommended supplementary sleep duration in the target time period
  • TST (t-1) is the regular sleep duration of the target object on the previous day
  • TST threshold is the sleep duration threshold
  • C7 is the first duration, which can be the pre-
  • the fixed value of the setting is either obtained based on the attribute information of the target object or based on the historical sleep data of the target object.
  • the supplementary sleep recommendation result of the target object is obtained based on at least one of the target object's regular sleep data of the previous day and the supplementary sleep data of the previous day.
  • the supplementary sleep recommendation result may also include a supplementary sleep duration reminder, for example, do not supplement sleep for too long, or please set an alarm before supplementing sleep. etc., to prevent the target subject from supplementing sleep for too long and affecting subsequent regular sleep or daytime mental state.
  • the target subject's supplementary sleep duration reminder can be obtained based on the target subject's historical sleep data. For example, it may be determined whether to generate a supplementary sleep duration reminder based on the historical supplementary sleep data in the historical sleep data. For example, in response to the historical supplementary sleep data indicating that the target subject's supplementary sleep duration exceeded the recommended duration on the previous day, a supplementary sleep duration reminder is generated to remind the target subject that the supplementary sleep duration during the target time period does not exceed the recommended duration.
  • Nap recommend is the recommended supplementary sleep duration
  • Nap'(t) is the target object's time on the previous day. of supplementary sleep duration.
  • a supplementary sleep duration reminder is output to remind the target subject to appropriately adjust the supplementary sleep duration; otherwise, the supplementary sleep duration is not output. remind.
  • FIG. 9 is a schematic diagram of an exemplary supplementary sleep suggestion solution provided by an embodiment of the present application.
  • the historical motion data of the target object can be obtained, for example, the activity data of the previous day.
  • historical supplementary sleep data of the target object can be obtained, for example, daytime nap data of the previous day.
  • the historical regular sleep data of the target object can be obtained, for example, the night sleep data of the previous day.
  • the data obtained in the above steps can be combined to obtain supplementary sleep suggestions for the target object.
  • the target subject's supplementary sleep duration on the previous day can be monitored. If the supplementary sleep duration on the previous day is greater than the preset duration threshold, or greater than the recommended supplementary sleep duration, a supplementary sleep duration reminder can also be provided in the supplementary sleep recommendation to Prevent the target from sleeping too long during the target period.
  • the target object's supplementary sleep recommendation results can be obtained based on the target object's historical sleep data, thereby avoiding the target object's lack of energy during the day due to poor night sleep, and at the same time avoiding the negative impact of long supplementary sleep on health. adverse effects and establish a foundation for the target to achieve their active health goals.
  • the sleep health of the target subject can be further improved by providing the target subject with appropriate sleep cognitive information.
  • the sleep cognitive knowledge corresponding to the target object can be obtained from the CBT-I (Cognitive Behavioral Therapy for Insomnia) sleep cognitive knowledge base based on the attribute information of the target object.
  • CBT-I Cognitive Behavioral Therapy for Insomnia
  • sleep environment suggestions for the target object are obtained based on the acquired sleep cognitive knowledge.
  • the sleep cognitive information may include at least one of dietary advice, sleep environment advice, and physical and mental relaxation advice.
  • dietary advice may include, for example: if you are sensitive to stimulant drinks such as coffee/tea, avoid drinking these drinks after 2 pm.
  • sleeping environment suggestions may include: a suitable temperature can help people fall asleep faster, and the bedroom temperature should generally be on the low side, controlled at around 21 to 24 degrees.
  • sleeping environment suggestions may include: the most suitable bed temperature is 1 to 2 degrees higher than the human body surface temperature.
  • Suggestions for physical and mental relaxation may include, for example: doing something quiet and relaxing before going to bed, such as meditating, reading, etc.
  • This sleep recognition information can be universal, or can be determined based on the characteristics of the target object, such as based on attribute information of the target object, such as age, gender, hobbies, lifestyle habits, etc., or based on one or more of the target object.
  • Current health status such as sleep type, exercise habit type, disease information, etc. one or more, or basic Regarding the historical monitoring information of the target object, for example, coffee intake beyond the preset time, sleep environment temperature is too high, stress before going to bed, etc., one or more, the embodiments of the present application do not limit this.
  • sleep cognitive information can be provided for the target subject to further help the target subject improve sleep quality, thereby helping the target subject develop healthy sleep habits.
  • the electronic device can simultaneously perform exercise recommendations and sleep recommendations based on the target object's historical sleep data and historical motion data.
  • FIG 11 is a schematic diagram of an exemplary health guidance system provided by an embodiment of the present application.
  • the health guidance system mainly includes three modules: a sleep assessment module 1101, a data measurement module 1102 and a sleep improvement module 1103.
  • the sleep evaluation module 1101 can evaluate the sleep quality of the target object. For example, according to the sleep data measured by the data measurement module 1102, the sleep quality evaluation result of the target object and/or at least one current sleep parameter value can be obtained to indicate the target object. current sleep status.
  • the data measurement module 1102 can measure and process data of the target object. For example, the target subject's sleep (such as regular sleep and/or supplementary sleep), movement, physiological parameters and other data are collected and processed through the terminal device.
  • the target subject's sleep such as regular sleep and/or supplementary sleep
  • movement, physiological parameters and other data are collected and processed through the terminal device.
  • the sleep improvement module 1103 can calculate a path to achieve the sleep goal and obtain sleep improvement suggestions based on the target subject's current physiological or sleep status and current existing sleep problems or sleep problems that are expected to be improved.
  • the sleep improvement suggestions may include one or more of exercise suggestions, regular sleep suggestions, supplementary sleep suggestions, and sleep cognitive suggestions.
  • the sleep improvement suggestions may include the target exercise recommendation results described in the above embodiment.
  • the sleep improvement suggestions may include the sleep recommendation results described in the above embodiments.
  • the sleep improvement recommendations may include target exercise recommendation results and sleep recommendation results.
  • this application combines exercise and sleep to form a closed loop of active health guidance. Based on the target object's historical movement and sleep data, combined with prior knowledge in the sleep field, we can achieve better health goals for the target object and provide operational improvement plans.
  • the device 1200 includes: an acquisition module 1201, configured to acquire the historical sleep data and historical movement data of the target object through the terminal device.
  • the historical sleep data includes sleep data of at least one day before the target time period, and the historical movement data.
  • the data includes movement data for at least one day before the target time period;
  • the processing module 1202 is used to obtain the target movement recommendation result of the target object in the target time period based on the historical sleep data and historical movement data, and the target movement recommendation result includes the target recommended movement At least one of time and target recommended exercise amount;
  • the output module 1203 is used to output information related to the target exercise recommendation result.
  • the time when the processing is performed is called the day
  • the target motion recommendation results of the target object in the target time period include the target motion recommendation results of the target object in the next day, for example, the target motion recommendation results of the current day, Or tomorrow’s target exercise recommendation results.
  • the processing module 1202 is configured to: determine a candidate exercise time set according to at least a part of the historical exercise time data contained in the historical exercise data, where the candidate exercise time set includes at least one candidate exercise time; according to the historical sleep data, The target recommended motion time is determined from the set of candidate motion times.
  • the set of candidate motion times may include one or more candidate motion times.
  • One or more candidate motion times may be determined based on part or all of the historical motion time data included in the historical motion data. For example, all exercise times included in historical exercise time data may be used as candidate exercise times.
  • the movement time that satisfies certain conditions among all the movement times included in the historical movement time data can also be used as the candidate movement time, for example, the movement time whose number of occurrences reaches a certain threshold in the historical movement time data can be used as the candidate movement time, etc. .
  • the candidate motion time is obtained by processing part or all of the historical motion time data.
  • the processing module 1202 is configured to: determine the sleep type of the target subject; determine the movement time offset corresponding to the sleep type of the target subject from a plurality of preset movement time offsets; according to the corresponding of The target recommended exercise time is determined from the candidate exercise time set using the exercise time offset and at least a portion of the historical sleep start time data included in the historical sleep data.
  • the sleep type of the target object may include one of the following: early sleeping type, late sleeping type, early rising type, late rising type, and sleep disorder type.
  • the processing module 1202 is configured to: determine exercise time requirements based on at least a portion of historical sleep start time data included in the historical sleep data and an exercise time offset corresponding to the sleep type of the target subject; and combine the candidate exercise time At least one candidate exercise time in the set that meets the exercise time requirement is determined as the target recommended exercise time.
  • the processing module 1202 is configured to: select multiple candidate recommended exercise times from a set of candidate exercise times based on historical sleep data, and then output prompt information to prompt selection from the multiple candidate recommended exercise times, and based on The received user input information determines the target recommended exercise time.
  • the processing module 1202 is configured to: select a plurality of candidate recommended exercise times from a set of candidate exercise times based on historical sleep data; determine the target object's position in each of the multiple candidate recommended exercise times based on the historical exercise data. The exercise frequency of the recommended exercise time; according to the exercise frequency of the target object in each candidate recommended exercise time among the multiple candidate recommended exercise times, determine the target recommended exercise time from the multiple candidate recommended exercise times.
  • the processing module 1202 is configured to: determine an initial exercise recommendation result for the target time period based on the first historical exercise data in the historical exercise data, and adjust the initial exercise recommendation result based on at least a part of the historical sleep data. Process to obtain the target motion recommendation results in the target time period.
  • the processing module 1202 is configured to: determine an exercise recommendation strategy for the target time period based on the physiological data measurement results of the target object; determine an exercise recommendation strategy for the target time period based on the exercise recommendation strategy for the target time period and the first historical exercise data. Initial exercise recommendation results.
  • the processing module 1202 is configured to: obtain the sleep quality assessment results of the target subject for at least one day close to the target time period based on at least a part of the historical sleep data; and adjust the initial exercise recommendation results based on the sleep quality assessment results. Process to obtain target motion recommendation results.
  • the processing module 1202 is further configured to: adjust the initial motion recommendation result based on at least a portion of the target object's historical sleep data and the second historical motion data in the historical motion data to obtain the target motion recommendation result, wherein, the second historical motion data includes motion data within the current motion recommendation period and at least one day before the target time period.
  • the processing module 1202 is further configured to: obtain the sleep quality evaluation result of the target object for at least one day before the target time period based on at least part of the target object's historical sleep data, and obtain the sleep quality evaluation result of the target object according to the sleep quality evaluation result and the second history.
  • the motion data is used to adjust the initial motion recommendation results to obtain the target motion recommendation results.
  • the processing module 1202 is further configured to: obtain a motion evaluation result of the target object based on the second historical motion data, where the motion evaluation result is used to indicate that the target object's motion amount reaches the standard for at least one day close to the target time period; according to Based on the exercise assessment results and sleep quality assessment results, the initial exercise recommendation results are adjusted to obtain the target exercise recommendation results.
  • the exercise assessment result includes at least one of frequency of reaching the target amount of exercise and indication of total amount of exercise reaching the standard.
  • the indication of the total amount of exercise reaching the standard can be used to indicate whether the total amount of exercise of the target object reaches the target in at least one day close to the target time period.
  • the frequency of reaching the standard of exercise amount can be It is used to indicate the frequency with which the exercise amount reaches the target in the at least one day, for example, the proportion of the number of days in which the exercise amount reaches the target in the total number of days corresponding to the at least one day.
  • the second historical exercise data includes the actual amount of exercise per day in at least one day close to the target time period.
  • the results of the exercise assessment are used to indicate whether the amount of exercise has reached the target.
  • the processing module 1202 is further configured to obtain a motion evaluation result based on the actual amount of exercise per day in at least one day close to the target time period and the recommended exercise information corresponding to the at least one day.
  • the sleep quality assessment results include sleep recovery indicators; the processing module 1202 is configured to: obtain the sleep heart rate variability data of the target object based on at least part of the historical sleep data; based on the target object The sleep heart rate variability data is used to obtain the sleep recovery index of the target object.
  • the exercise recommendation device provided by the embodiments of the present application includes modules for implementing the steps and/or processes in the above exercise recommendation method embodiments. For the sake of brevity, they will not be described again here.
  • the target exercise recommendation result of the target object in the target time period can be obtained based on the target object's historical sleep data and historical exercise data, and the target exercise recommendation result can be recommended to the target object, thereby helping the target The subject maintains scientific and regular exercise habits, which lays a foundation for the improvement of the target subject's exercise ability and the achievement of active health goals.
  • the device 1300 includes: an acquisition module 1301, used to obtain the historical sleep data of the target object through the terminal device; a first processing module 1302, used to obtain the target object's desired sleep information based on the attribute information of the target object. At least one of, obtain at least one target sleep parameter value of the target object; the second processing module 1303 is configured to obtain the target object's sleep parameter value in the target time period based on at least one target sleep parameter value of the target object and the historical sleep data of the target object.
  • Sleep recommendation results include at least one of recommended sleep time, recommended wake-up time, and recommended sleep duration; the first output module 1304 is used to output information related to the sleep recommendation results.
  • the first processing module 1302 is further configured to: before obtaining at least one target sleep parameter value, determine the validity of at least one desired sleep parameter value included in the desired sleep information. For example, it is determined whether at least one desired sleep parameter value is within a preset value range.
  • the first processing module 1302 is configured to: in response to the existence of a valid desired sleep parameter value corresponding to the first sleep parameter in the desired sleep information of the target object, determine the valid desired sleep parameter value as the said The target sleep parameter value corresponding to the first sleep parameter.
  • the first processing module 1302 is configured to: in response to the fact that there is no valid expected sleep parameter value corresponding to the second sleep parameter in the expected sleep information of the target object, determine the second sleep parameter value according to the attribute information of the target object.
  • the target sleep parameter value corresponding to the sleep parameter is configured to: in response to the fact that there is no valid expected sleep parameter value corresponding to the second sleep parameter in the expected sleep information of the target object, determine the second sleep parameter value according to the attribute information of the target object. The target sleep parameter value corresponding to the sleep parameter.
  • the second processing module 1303 is used to: determine the target object's sleep adjustment strategy based on the target object's historical sleep data and at least one target sleep parameter value; and obtain the target object's sleep adjustment strategy in the target time period based on the sleep adjustment strategy. Sleep recommendation results.
  • the sleep adjustment strategy may include a gradual adjustment strategy or a direct adjustment strategy.
  • the second processing module 1303 is also configured to: obtain at least one current sleep parameter value of the target object based on the target object's historical sleep data, and obtain at least one current sleep parameter value and at least one target sleep parameter value based on the target object's historical sleep data. Get sleep recommendation results.
  • the at least one current sleep parameter value may include at least one of historical sleep time, historical wake-up time, and historical sleep duration.
  • the second processing module 1303 is configured to: in response to the difference between the current sleep parameter value and the target sleep parameter value exceed a preset difference range, determine that the sleep adjustment strategy of the target subject is a progressive adjustment strategy.
  • the second processing module 1303 is configured to: in response to the difference between the current sleep parameter value and the target sleep parameter value being within the preset difference range, determine the sleep recommendation strategy to be a direct adjustment strategy.
  • the apparatus further includes a third processing module 1405.
  • a third processing module 1405. is a schematic structural diagram of another sleep recommendation device 1400 provided by an embodiment of the present application.
  • the device 1400 also includes a third processing module 1405 and a second output module 1406.
  • the third processing module 1405 is configured to obtain the supplementary sleep recommendation result of the target object in the target time period based at least in part on the regular sleep data of the previous day of the target time period included in the target object's historical sleep data.
  • modules 1401 to 1404 in Figure 14 have the same structure and function as modules 1301 to 1304 in Figure 13 .
  • the third processing module 1405 is also used to determine whether to recommend the target subject to perform supplementary sleep in the target time period based on whether the target subject's regular sleep parameters on the day before the target time period reach the preset parameter range.
  • the apparatus 1400 further includes a second output module 1406 for: based at least in part on The target object's supplementary sleep data on the day before the target time period is output, and a supplementary sleep duration reminder is output.
  • the second output module 1406 is also configured to: in response to the sleep data of the previous day of the target time period indicating that the target subject's supplementary sleep duration on the previous day exceeds the recommended duration range, output a supplementary sleep duration reminder for prompting Control the length of supplementary sleep during the target time period within the recommended length range.
  • the sleep recommendation device provided by the embodiments of the present application includes modules for implementing the steps and/or processes in the above sleep recommendation method embodiments. For the sake of brevity, they will not be described again here.
  • At least one target sleep parameter value of the target object can be obtained based on at least one of the target object's attribute information and desired sleep information, and based on at least one target sleep parameter value of the target object and
  • the target object's historical sleep data is used to obtain the target object's sleep recommendation results in the target time period, thereby helping the target object gradually develop scientific and regular sleep habits.
  • the target object's supplementary sleep recommendation results can be obtained based on the target object's historical sleep data, thereby avoiding the target object's lack of energy due to poor regular sleep, and at the same time avoiding the adverse effects of long supplementary sleep on health. Establish the basis for the achievement of the subject's active health goals.
  • the present application also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, The instructions are executed by at least one processor to enable at least one processor to perform the exercise recommendation method of any of the foregoing embodiments, or to enable at least one processor to perform the sleep recommendation method of any of the foregoing embodiments.
  • the present application also provides a computer-readable storage medium, in which the computer instructions are used to cause the computer to execute the exercise recommendation method according to any of the foregoing embodiments provided by the embodiments of the present application, or to execute the method according to The embodiments of this application provide the sleep recommendation method of any of the aforementioned embodiments.
  • FIG. 15 is a schematic block diagram of an example electronic device that can be used to implement embodiments of the present application.
  • Electronic devices are intended to refer to various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.
  • the components shown herein, their connections and relationships, and their functions are examples only and are not intended to limit the implementation of the present application as described and/or claimed herein.
  • the electronic device 1500 includes a computing unit 1501, which can be loaded into a random access memory (Random Access Memory) according to a computer program stored in a read-only memory (Read-Only Memory, ROM) 1502 or from a storage unit 1508.
  • Computer program in RAM) 1503 to perform various appropriate actions and processes.
  • RAM 1503 various programs and data required for the operation of the electronic device 1500 can also be stored.
  • Computing unit 1501, ROM 1502 and RAM 1503 are connected to each other via bus 1504.
  • An input/output (I/O) interface 1505 is also connected to bus 1504.
  • the I/O interface 1505 includes: input unit 1506, such as keyboard, mouse, etc.; output unit 1507, such as various types of displays, speakers, etc.; storage unit 1508, such as magnetic disk, optical disk etc.; and communication unit 1509, such as network card, modem, wireless communication transceiver, etc.
  • the communication unit 1509 allows the electronic device 1500 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunications networks.
  • Computing unit 1501 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 1501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, and various running machine learning models. The calculation unit of the algorithm, a digital signal processor (Digital Signal Process, DSP), and any appropriate processor, controller, microcontroller, etc.
  • the computing unit 1501 performs various methods and processes described above, such as an exercise recommendation method or a sleep recommendation method. For example, in some embodiments, exercise recommendations
  • the method or sleep recommendation method may be implemented as a computer software program, which is tangibly embodied in a machine-readable medium, such as storage unit 1508.
  • part or all of the computer program may be loaded and/or installed onto electronic device 1500 via ROM 1502 and/or communication unit 1509 .
  • the computer program When the computer program is loaded into the RAM 1503 and executed by the computing unit 1501, one or more steps of the above-described exercise recommendation method or sleep recommendation method may be performed.
  • the computing unit 1501 may be configured to perform the exercise recommendation method or the sleep recommendation method in any other suitable manner (eg, by means of firmware).
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSP Application Specific Standard Parts
  • SOC System On Chip
  • CPLD Complex Programmable Logic Device
  • These various embodiments may include implementation in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor
  • the processor which may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • An output device may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • An output device may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • Program code for implementing the methods of the present application may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions specified in the flowcharts and/or block diagrams/ The operation is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory ((Erasable Programmable Read-Only Memory, EPROM) or flash memory), optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or the above any suitable combination.
  • RAM random access memory
  • ROM read only memory
  • EPROM erasable programmable read only memory
  • flash memory flash memory
  • optical fiber Portable compact disk read-only memory
  • CD-ROM Compact Disc Read-Only Memory
  • optical storage device magnetic storage device, or the above any suitable combination.
  • the systems and techniques described herein may be implemented on a computer having a display device (e.g., a cathode ray tube (CRT) or LCD) for displaying information to the user.
  • a display device e.g., a cathode ray tube (CRT) or LCD
  • Crystal Display liquid crystal display
  • keyboard and pointing device such as a mouse or trackball
  • Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be provided in any form, including acoustic input, voice input, or tactile input) to receive input from the user.
  • the systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., A user's computer having a graphical user interface or web browser through which the user can interact with implementations of the systems and technologies described herein), or including such backend components, middleware components, or any combination of front-end components in a computing system.
  • the components of the system may be interconnected by any form or medium of digital data communication (eg, a communications network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), the Internet, and blockchain networks.
  • Computer systems may include clients and servers. Clients and servers are generally remote from each other and typically interact over a communications network. The relationship of client and server is created by computer programs running on corresponding computers and having a client-server relationship with each other.
  • the server can be a cloud server, also known as a cloud computing server or cloud host. It is a host product in the cloud computing service system and solves the management problems that exist in traditional physical hosts and VPS (Virtual Private Server) services. It has the disadvantages of high difficulty and weak business scalability.
  • the server can also be a distributed system server or a server combined with a blockchain.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Biophysics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Pathology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Molecular Biology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

本申请提出一种运动推荐方法、睡眠推荐方法及其装置、电子设备及存储介质。运动推荐方法包括：通过终端设备获取目标对象的历史睡眠数据和历史运动数据（S201）；根据历史睡眠数据和历史运动数据，得到目标对象在目标时间段的目标运动推荐结果（S202）；输出目标运动推荐结果的相关信息（S203）。

Description

运动推荐方法、睡眠推荐方法及其装置、电子设备及存储介质 技术领域
本申请涉及电子设备技术领域，尤其涉及运动推荐方法、睡眠推荐方法及其装置、电子设备及存储介质。
背景技术
随着电子设备技术的发展，其被越来越多地用于进行用户健康生活的监督和管理，例如运动监测、睡眠监测、久坐提醒等。在医学上，将拥有高质量生活体验的时间描述为“健康寿命”。而把追逐“健康寿命”的这一过程，称作为“主动健康”。想要达成“主动健康”的目的，需要对用户的状态进行实时评估，并通过类似于控制论系统中的反馈回路，给予用户适合的健康指导，从而达到用户预设的健康目标。
相关技术的局限性在于虽然可以基于电子设备获取用户的多项数据，但是并未对上述数据进行更深层次的分析与利用，以帮助用户实现主动健康目标。
发明内容
本申请提供了一种运动推荐方法、睡眠推荐方法、装置、电子设备及存储介质。
第一方面，本申请提供一种运动推荐方法，所述方法包括：通过终端设备获取目标对象的历史睡眠数据和历史运动数据，所述历史睡眠数据包括在目标时间段之前的至少一天的睡眠数据，所述历史运动数据包括在所述目标时间段之前的至少一天的运动数据；根据所述历史睡眠数据和所述历史运动数据，得到所述目标对象在目标时间段的目标运动推荐结果，所述目标运动推荐结果包括目标推荐运动时间和目标推荐运动量中的至少一种；输出所述目标运动推荐结果的相关信息。
根据本申请的技术方案，可以基于目标对象的历史睡眠数据和历史运动数据，获取目标对象在目标时间段的目标运动推荐结果，并向目标对象推荐该目标运动推荐结果，从而帮助目标对象保持科学且规律的运动习惯，为目标对象运动能力的提升以及主动健康目标的达成建立基础。
在一些实现方式中，目标对象的历史睡眠数据可以是通过对目标对象进行睡眠监测得到的数据，可以包括从某一时间点开始监测到的目标对象的所有睡眠数据，也可以包括其中的一部分睡眠数据，例如，目标时间段之前的特定时间长度的睡眠数据，或者目标时间段之前的满足特定条件的睡眠数据。目标对象的历史运动数据可以是通过对目标对象进行运动监测得到的数据，可以包括从某一时间点开始监测到的目标对象的所有运动数据，也可以包括其中的一部分运动数据，例如，目标时间段之前的特定时间长度的运动数据，或者目标时间段之前的满足特定条件的运动数据。历史睡眠数据和历史运动数据可以为在相同的时间段监测到的数据，也可以为在不同的时间段监测到的数据，该不同的时间段可以有部分重合，或者该不同的时间段可以不重合。
在一些实现方式中，历史睡眠数据可以包括下列中的至少一项：睡眠开始时间、睡眠结束时间、睡眠持续时间、睡眠心率、睡眠分期数据、睡眠呼吸数据。
在一些实现方式中，历史运动数据可以包括下列中的至少一项：运动开始时间、运动结束时间、运动持续时间、运动强度、运动类型、运动心率、运动冲量、运动消耗能量。
在一些实现方式中，时间段以一天作为时间单位，例如，1个自然日，或者从某个时间点起算的24小时，等等。
例如，将执行该方法的时间称为当天，目标对象在目标时间段的目标运动推荐结果包括目标对象在接下来的一天的目标运动推荐结果，例如，当天的目标运动推荐结果，或者明天的目标运动推荐结果。
在一些实现方式中，根据所述历史运动数据中包含的至少一部分历史运动时间数据，确定候选运动时间集合，所述候选运动时间集合包括至少一个候选运动时间；根据所述历史睡眠数据，从所述候选运动时间集合中确定所述目标推荐运动时间。
该候选运动时间集合可以包括一个或多个候选运动时间。历史运动数据可以包括历史运动时间数据。可以根据历史运动数据中包括的部分或全部历史运动时间数据来确定一个或多个候选运动时间。例如，可以将历史运动时间数据中包括的所有运动时间作为候选运动时间。或者，也可以将历史运动时间数据中包括的所有运动时间中满足一定条件的运动时间作为候选运动时间，例如将历史运动时间数据中出现的次数达到一定阈值的运动时间作为候选运动时间，等等。或者，候选运动时间是通过对部分或全部历史运动时间数据进行处理后得到的。
在一个例子中，历史运动数据用于确定目标对象的运动习惯或喜好，历史睡眠数据用于确定目标对象的睡眠习惯或喜好，可以结合目标对象的运动习惯或喜好以及睡眠习惯或喜好来进行针对目标对象的运动推荐。
根据本申请的技术方案，可以根据所述目标对象的历史睡眠数据和历史运动数据，确定目标对象的目标推荐运动时间，结合目标对象的运动和睡眠习惯或喜好，帮助目标对象保持科学且规律的运动习惯，为目标对象运动能力的提升以及主动健康目标的达成建立基础。
在一些实现方式中，可以确定所述目标对象的睡眠类型，并根据目标对象的睡眠类型和历史睡眠数据，从所述候选运动时间集合中确定所述目标推荐运动时间。
作为一个例子，根据所述目标对象的历史睡眠数据，确定所述目标对象的睡眠类型。例如，利用分类模型对目标对象的历史睡眠数据进行处理，得到目标对象的睡眠类型。
作为另一个例子，根据接收到的用户输入信息，确定所述目标对象的睡眠类型。
在一种实现方式中，目标对象的睡眠类型可以包括以下中的一种：早睡型、晚睡型、早起型、晚起型、睡眠障碍型。
在一种实现方式中，历史睡眠数据包括历史睡眠开始时间数据，可以根据历史睡眠开始时间数据，从至少一个候选运动时间中确定目标推荐运动时间。
在一个例子中，可以从多个预设的运动时间偏移量中，确定出与所述目标对象的睡眠类型对应的运动时间偏移量；根据所述对应的运动时间偏移量和所述历史睡眠数据中包括的至少一部分历史睡眠开始时间数据，从所述候选运动时间集合中确定所述目标推荐运动时间。
作为一个例子，根据所述历史睡眠数据中包括的历史睡眠开始时间数据以及与所述目标对象的睡眠类型对应的运动时间偏移量，确定运动时间要求；将所述候选运动时间集合中满足所述运动时间要求的至少一个候选运动时间确定为所述目标推荐运动时间。
作为另一个例子，可以基于目标对象在临近目标时间段的至少一天的历史睡眠开始时间数据以及目标对象的睡眠类型对应的运动时间偏移量，确定运动时间要求。
作为一个例子，运动时间要求可以包括：最晚运动时间。该最晚运动时间可以包括最晚运动开始时间，和/或最晚运动结束时间。
在一些实现方式中，可以根据历史睡眠数据，从候选运动时间集合中选择多个候选推荐运动时间，然后输出提示信息，以提示从多个候选推荐运动时间中选择，并基于接收到的用户输入信息确定目标推荐运动时间。
在一些实现方式中，可以根据历史睡眠数据和历史运动数据，从候选运动时间集合中选择目标推荐运动时间。
作为一个例子，可以根据所述历史睡眠数据，从所述候选运动时间集合中选择多个候选推荐运动时间，并根据历史运动数据，从多个候选推荐运动时间中选择目标推荐运动时间。
例如，根据所述历史运动数据，确定所述目标对象在所述多个候选推荐运动时间中每个候选推荐运动时间的运动频次；根据所述目标对象在所述多个候选推荐运动时间中每个候选推荐运动时间的运动频次，从所述多个候选推荐运动时间中确定所述目标推荐运动时间。
在一些实现方式中，根据历史运动数据中的第一历史运动数据，确定目标时间段的初始运动推荐结果，并根据历史睡眠数据的至少一部分，对目标时间段的初始运动推荐结果进行调整处理，得到目标时间段的目标运动推荐结果。
作为一个例子，可以以一个运动推荐周期作为单位进行运动推荐。每个运动推荐周期可以包括多天或多个时间段。例如，一个运动推荐周期包括的时间长度可以预先设定，例如一个星期，或者也可以由用户指定。
作为一个例子，所述第一历史运动数据包括在所述目标时间段所属的当前运动推荐周期之前的至少一个历史运动推荐周期的运动数据。例如，第一历史运动数据包括本周之前的前N周的运动数据，N≥1。
作为另一个例子，所述第一历史运动数据包括在所述目标时间段之前的一个或多个时间段的运动数据。例如，第一历史运动数据包括当天之前的前N天的运动数据。
作为一个例子，所述历史睡眠数据的至少一部分包括临近所述目标时间段的至少一天的睡眠数据。例如，所述历史睡眠数据的至少一部分包括目标时间段的前一天或前N天的睡眠数据，或者当前运动推荐周期内已经经过的一天或多天的睡眠数据。
作为一个例子，可以根据相同的历史运动数据，确定当前运动推荐周期包括的多个时间段中每个时间段的初始运动推荐结果，例如，根据当前运动推荐周期之前的至少一个历史运动推荐周期的运动数据，确定当前运动推荐周期包括的每个时间段的初始运动推荐结果。
作为另一个例子，可以根据不同的历史运动数据，确定当前运动推荐周期包括的不同时间段的初始运动推荐结果。例如，根据每个时间段之前的至少一个时间段的运动数据，确定该时间段的初始运动推荐结果。
在一些实现方式中，初始运动推荐结果的确定与目标运动推荐结果的确定可以不在同一时间执行，作为一个例子，可以在当前运动推荐周期之前的第一时间确定目标时间段的初始运动推荐结果，而在当前运动推荐周期内的每个时间段到来时或到来前的第二时间确定该时间段的目标运动推荐结果。例如，在本周之前确定本周每一天的初始运动推荐结果，而在本周的每一天确定当天或下一天的目标运动推荐结果。
在一些实现方式中，根据目标对象在第一时间的健康状态以及第一历史运动数据，确定目标时间段的初始运动推荐结果。
作为一个例子，根据所述目标对象的生理数据测量结果，确定所述目标时间段的运动推荐策略；基于所述目标时间段的运动推荐策略以及所述第一历史运动数据，确定所述目标时间段的初始运动推荐结果。
目标对象的生理数据测量结果可以是通过对目标对象进行一种或多种生理数据测量得到的，例如心率、血压、心理压力等。可以根据生理数据测量结果确定目标对象当前的健康状态，并基于当前的健康状态来确定当前的运动推荐策略。
作为一个例子，运动推荐结果包括推荐运动量，相应地，运动推荐策略可以包括增加运动量、保持运动量和减小运动量。
在一些实现方式中，根据所述历史睡眠数据的至少一部分，得到所述目标对象在临近所述目标时间段的至少一天的睡眠质量评估结果；基于所述目标对象在所述至少一天的睡眠质量评估结果，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果。
作为一个例子，临近所述目标时间段的至少一天的睡眠质量评估结果可以包括目标时间段的前一天或前N天的睡眠质量评估结果，例如，包括前两周的睡眠质量评估结果，或者，可以包括当前运动推荐周期内已经经过的一天或多天的睡眠质量评估结果，例如，包括本周已经经过的至少一天的睡眠质量评估结果。
在一些实现方式中，根据历史睡眠数据的至少一部分以及所述历史运动数据中的第二历史运动数据，对所述目标时间段的初始运动推荐结果进行调整处理，得到目标时间 段的目标运动推荐结果，其中，所述第二历史运动数据包括当前运动推荐周期内且在所述目标时间段之前的至少一天的运动数据。
作为一个例子，历史运动数据包括第二历史运动数据，第二历史运动数据包括临近目标时间段的前一天或前N天的运动数据。作为另一个例子，第二历史运动数据包括当前运动推荐周期内已经经过的一天或多天的运动数据。
在一些实现方式中，根据第二历史运动数据，得到目标对象在目标时间段之前的至少一天的运动评估结果，并根据运动评估结果以及历史睡眠数据的至少一部分，对目标时间段的初始运动推荐结果进行调整处理，得到目标时间段的目标运动推荐结果。
作为一个例子，根据所述历史睡眠数据的至少一部分，得到所述目标对象在所述目标时间段之前的至少一天的睡眠质量评估结果，根据所述第二历史运动数据，确定所述目标对象在所述目标时间段之前的至少一天的运动评估结果，根据所述睡眠质量评估结果以及所述运动评估结果，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果。
在一些实现方式中，确定目标时间段的初始运动推荐结果，并根据所述历史睡眠数据的至少一部分和所述历史运动数据中的第二历史运动数据，对目标时间段的初始运动推荐结果进行调整处理，得到目标时间段的目标运动推荐结果。
第二历史运动数据可以包括临近所述目标时间段的至少一天的运动数据。
目标时间段的初始运动推荐结果可以是根据目标对象的历史运动数据和/或历史睡眠数据得到的，例如上文描述的各种可能的实现方式。或者，初始运动推荐结果是根据用户输入信息得到的。或者，初始运动推荐结果是根据先验知识或者专家知识得到的。作为一个例子，初始运动推荐结果是根据目标对象的第一历史运动数据、目标对象的生理参数测量结果、用户输入信息以及运动生理学先验信息(或称为运动生理学专家知识)中的至少一种得到的。
在一些实现方式中，根据所述第二历史运动数据，得到所述目标对象的运动评估结果；根据所述运动评估结果和所述历史睡眠数据的至少一部分，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果。
在一些实现方式中，根据所述第二历史运动数据，得到所述目标对象的运动评估结果；根据所述历史睡眠数据的至少一部分，得到所述目标对象的睡眠质量评估结果；根据所述运动评估结果和睡眠质量评估结果，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果。
上文所述的运动评估结果可以用于指示所述目标对象在临近所述目标时间段的至少一天的运动量达标情况。
作为一个例子，所述运动评估结果包括运动量达标频次和运动总量达标指示中的至少一项，运动总量达标指示可以用于指示所述目标对象在临近所述目标时间段的至少一天内的运动总量是否达标，运动量达标频次可以用于指示所述至少一天内运动量达标的频次，即，运动量达标的天数在所述至少一天对应的总天数中所占的比例。例如，运动量达标频次可以指示当前运动推荐周期内已经经过的一天或多天内运动量达标的天数比例，运动总量达标指示可以指示当前运动推荐周期内已经经过的一天或多天的运动总量是否达到设定运动总量。
在一些实现方式中，可以根据第二历史运动数据，得到临近目标时间段的至少一天的实际运动量。作为一个例子，所述第二历史运动数据包括临近所述目标时间段的至少一天的实际运动量，例如，所述第二历史运动数据包括所述当前运动推荐周期中已经经过的至少一天中每天的实际运动量。作为另一个例子，可以通过对第二历史运动数据中的至少一部分进行处理，得到临近目标时间段的至少一天的实际运动量。
在一些实现方式中，根据临近所述目标时间段的至少一天中每天的实际运动量以及所述至少一天对应的推荐运动信息，得到所述运动评估结果。
在一个例子中，所述至少一天对应的推荐运动信息包括所述至少一天中每天的推荐运动量。在另一个例子中，所述至少一天对应的推荐运动信息包括所述至少一天的推荐运动总量。在另一个例子中，所述至少一天对应的推荐运动信息包括当前运动推荐周期的推荐运动总量。
在一个例子中，将所述目标对象在临近所述目标时间段的至少一天中每天的实际运动量与所述每天的推荐运动量进行比较，以确定所述目标对象在所述每天的运动量是否达标；根据所述目标对象在临近所述目标时间段的至少一天中每天的运动量是否达标，确定所述目标对象在所述至少一天的运动量达标频次。
在另一个例子中，根据所述目标对象在临近所述目标时间段的至少一天中每天的实际运动量，确定所述目标对象在所述至少一天的实际运动总量，根据所述至少一天对应的推荐运动总量和所述至少一天的实际运动总量，确定所述至少一天的运动总量是否达标。
在一些实现方式中，通过比较运动评估结果包括的运动量达标指标与第一预设阈值和/或比较睡眠质量评估结果包括的睡眠质量指标与第二预设阈值，得到目标时间段的目标推荐运动量。
在一个例子中，响应于所述运动评估结果指示运动总量未达标，且所述睡眠质量评估结果指示的睡眠质量指标低于预设质量阈值，将所述初始运动推荐结果中包括的初始推荐运动量调整至所述目标对象的最低运动量，此时，所述目标推荐运动量即为目标对象的最低运动量。
在一个例子中，响应于所述运动评估结果指示运动总量未达标，且所述睡眠质量评估结果指示的睡眠质量指标达到预设质量阈值，不对初始运动推荐结果中包括的初始推荐运动量进行调整，此时，将所述目标推荐运动量确定为所述初始推荐运动量。
在一个例子中，响应于所述运动评估结果指示运动总量达标、且运动量达标频次达到预设频次阈值，则可以将初始运动推荐结果中包括的初始推荐运动量调整为0，得到目标推荐运动量，此时，目标推荐运动量为0，即在目标时间段不推荐进行运动。
在一个例子中，响应于所述运动评估结果指示运动总量达标、且运动量达标频次低于预设频次阈值，则可以将初始运动推荐结果中包括的初始推荐运动量调整为目标对象的最低运动量，得到目标推荐运动量，此时，所述目标推荐运动量即为目标对象的最低运动量。
根据本申请的技术方案，可以确定目标时间段的初始推荐运动量，并根据临近所述目标时间段的一天或多天的实际运动情况以及睡眠情况对目标时间段的初始推荐运动量进行动态调整，使得目标推荐运动量更符合目标对象当前的状态，运动推荐更加有效。
在一些实现方式中，所述睡眠质量评估结果包括睡眠恢复指标。
在一些实现方式中，根据所述历史睡眠数据的至少一部分，得到所述目标对象的睡眠心率变异性数据；基于所述目标对象的睡眠心率变异性数据，得到所述目标对象的睡眠恢复指标。
在一个例子中，目标对象的睡眠心率变异性数据包括下列中的至少一种：目标对象的短期睡眠心率变异性参数、所述目标对象的长期睡眠心率变异性参数以及所述目标对象在前一天的睡眠心率变异性参数。
短期睡眠心率变异性参数可以指示目标对象在临近目标时间段的较短时间长度内的睡眠期间的心率变异性的特性，该较短时间长度例如可以为目标时间段的前一周，或者当前运动推荐周期的前一运动推荐周期。作为一个例子，该短期睡眠心率变异性参数可以包括基线心率变异性。
长期睡眠心率变异性参数可以指示目标对象在临近目标时间段的较长时间长度内的睡眠期间的心率变异性的特性，该较长周期例如可以为目标时间段或当前运动推荐周期的前两周、前一个月或更长时间。作为一个例子，该长期睡眠心率变异性参数可以包括 心率变异性的正常波动范围。
在一些实现方式中，还可以根据目标对象的历史睡眠数据，确定目标对象的睡眠推荐结果。具体实现可以参见第二方面任意可能实现方式。
第二方面，本申请提供一种睡眠推荐方法，所述方法包括：通过终端设备获取目标对象的历史睡眠数据；根据所述目标对象的属性信息和所述目标对象的期望睡眠信息中的至少一种，得到所述目标对象的至少一个目标睡眠参数值；基于所述至少一个目标睡眠参数值以及所述目标对象的历史睡眠数据，得到所述目标对象在目标时间段的睡眠推荐结果，所述睡眠推荐结果包括推荐入睡时间、推荐醒来时间和推荐睡眠时长中的至少一种；输出所述睡眠推荐结果的相关信息。
根据本申请的技术方案，可以根据目标对象的属性信息和期望睡眠信息中的至少一种，得到至少一个目标睡眠参数值，并基于至少一个目标睡眠参数值以及目标对象的历史睡眠数据，得到目标对象在目标时间段的睡眠推荐结果，从而帮助目标对象循序渐进的养成科学且规律的睡眠习惯。
在一个例子中，目标时间段可以是当天、明天或下一周。目标时间段的时间长度可以是预先设置的，或者是用户指定的。
在一个例子中，目标对象的历史睡眠数据可以包括目标时间段之前的一个或多个时间段的睡眠数据。目标对象的历史睡眠数据可以用于指示目标对象近期的睡眠情况。历史睡眠数据可以包括目标时间段的前一天、目标时间段所属的当前睡眠推荐周期内已经经过的一天或多天、或上一睡眠推荐周期的睡眠数据。例如，历史睡眠数据可以包括目标时间段的前一天、本周经过的一天或多天、或上一周的睡眠数据。
作为一个例子，所述目标对象的期望睡眠信息包括至少一个期望睡眠参数值，即至少一个睡眠参数的期望值，例如，期望睡眠时长、期望醒来时间、期望入睡时间等一种或任意多种。该期望睡眠信息可以是通过接收目标对象输入指令得到的，或者是根据目标对象所属群体的睡眠信息得到的。
作为一个例子，所述目标对象的属性信息包括目标对象的个人基本信息，例如年龄、性别、BMI、职业、兴趣爱好、睡眠习惯等一项或任意多项。
在一些实现方式中，可以在得到至少一个目标睡眠参数值之前，确定期望睡眠信息的有效性。
在一个例子中，如果确定期望睡眠信息有效，则可以根据期望睡眠信息来确定至少一个目标睡眠参数值。
在另一个例子中，如果确定期望睡眠信息无效，则可以根据目标对象的属性信息来确定至少一个目标睡眠参数值。
在一些实现方式中，可以在得到至少一个目标睡眠参数值之前，确定期望睡眠信息中包括的至少一个期望睡眠参数值中每个期望睡眠参数值的有效性。例如，确定某个期望睡眠参数值是否在预设数值范围内，如在预设数值范围内，则有效，如不在预设数值范围内，则无效。
在另一个例子中，如果期望睡眠信息中包括多个期望睡眠参数值，且部分期望睡眠参数值有效，部分期望睡眠参数值无效，则可以使用有效的期望睡眠参数值以及属性信息中的至少一种来确定无效的期望睡眠参数值对应的目标睡眠参数值。
在一些实现方式中，响应于所述目标对象的期望睡眠信息中存在与第一睡眠参数对应的有效的期望睡眠参数值，则根据所述对应的有效的期望睡眠参数值，确定所述第一睡眠参数对应的目标睡眠参数值。例如，将第一睡眠参数对应的有效的期望睡眠参数值确定为所述第一睡眠参数对应的目标睡眠参数值。
在一些实现方式中，响应于所述目标对象的期望睡眠信息中不存在与第二睡眠参数对应的有效的期望睡眠参数值，则根据所述目标对象的属性信息，确定所述第二睡眠参数对应的目标睡眠参数值。
作为一个例子，可以基于目标对象的属性信息，确定目标对象所属的群体或睡眠类别，然后，基于目标对象所属的群体或睡眠类别，确定至少一个目标睡眠参数值。
在一些实现方式中，根据所述目标对象的历史睡眠数据以及所述至少一个目标睡眠参数值，确定所述目标对象的睡眠调整策略；根据所述睡眠调整策略，得到所述目标对象在目标时间段的睡眠推荐结果。
该睡眠调整策略可以包括渐进式调整策略或者直接调整策略。
在一些实现方式中，可以根据目标对象的历史睡眠数据，得到目标对象的至少一个当前睡眠参数值，并根据至少一个当前睡眠参数值和至少一个目标睡眠参数值来得到睡眠推荐结果。
作为一个例子，该至少一个当前睡眠参数值可以包括历史入睡时间、历史醒来时间、历史睡眠时长中的至少一种。
作为一个例子，通过对所述目标对象的历史睡眠数据进行处理，得到所述目标对象的至少一个当前睡眠参数值。例如，该至少一个当前睡眠参数值为对目标时间段之前的特定时间间隔内的睡眠参数的统计平均。
在一个例子中，可以通过比较至少一个当前睡眠参数值和至少一个目标睡眠参数值之间的差异，得到目标时间段的睡眠推荐结果。
在一些实现方式中，响应于所述当前睡眠参数值与所述目标睡眠参数值之间的差异超过预设差异范围，确定所述目标对象的睡眠调整策略为渐进式调整策略。
作为一个例子，响应于所述目标对象的历史睡眠数据指示的当前睡眠参数值与所述目标睡眠参数值之间的差异超过预设差异范围，则确定睡眠调整策略为渐进式调整策略。
在一些实现方式中，在渐进式调整策略中，基于调整步长和所述当前睡眠参数值，得到所述目标时间段的睡眠推荐结果。
例如，以调整步长对当前睡眠参数值进行调整，得到目标时间段的睡眠推荐结果，以使得睡眠推荐结果包括的推荐睡眠参数从当前睡眠参数值向目标睡眠参数值靠近。
作为一个例子，基于当前睡眠参数值和目标睡眠参数值之间的差异，确定调整步长。
作为另一个例子，调整步长是预先设置的，或者根据用户输入信息确定的。
在一些实现方式中，响应于所述当前睡眠参数值与目标睡眠参数值之间的差异在所述预设差异范围内，则确定睡眠推荐策略为直接调整策略。
作为一个例子，在直接调整策略中，基于目标睡眠参数值确定睡眠推荐结果。
作为一个例子，在直接调整策略中，确定所述目标对象的睡眠推荐结果包括的推荐睡眠参数为所述目标睡眠参数值。
在一些实现方式中，所述方法还包括：根据所述目标对象的历史睡眠数据中包括的所述目标时间段的前一天的睡眠数据，得到所述目标对象在目标时间段的补充睡眠推荐结果。
作为一个例子，前一天的睡眠数据可以包括前一天的常规睡眠数据和/或补充睡眠数据。
在一些实现方式中，可以根据目标对象在目标时间段的前一天的常规睡眠参数是否达到预设参数范围，来确定是否推荐目标对象在目标时间段进行补充睡眠。
作为一个例子，响应于所述目标对象在前一天的常规睡眠时长未达到预设睡眠时长，则确定所述目标对象在目标时间段的补充睡眠推荐结果包括的补充睡眠推荐时长为大于零的第一时长。此时，推荐在目标时间段进行一定时长的补充睡眠。
该第一时长可以是预设数值，或者是根据目标对象的历史睡眠数据的至少一部分确定的。
作为另一个例子，响应于所述目标对象在前一天的常规睡眠时长达到预设睡眠时长，则确定所述目标对象的补充睡眠推荐结果包括的补充睡眠推荐时长为零。此时，推荐在目标时间段不进行补充睡眠。
在一些实现方式中，所述方法还包括：基于所述目标对象的历史睡眠数据，输出补充睡眠时长提醒。
在一些实现方式中，响应于所述目标时间段的前一天的睡眠数据指示所述目标对象在前一天的补充睡眠时长超过推荐时长范围，输出补充睡眠时长提醒，所述补充睡眠时长提醒用于提示将所述目标时间段的补充睡眠时长控制在所述推荐时长范围内。
通过本申请的技术方案，可以基于目标对象的历史睡眠数据，得到目标对象的补充睡眠推荐结果，从而避免目标对象由于常规睡眠不佳而造成精力不济，同时避免较长的补充睡眠对健康产生的不利影响，为目标对象的主动健康目标的达成建立基础。
第三方面，本申请提供一种运动推荐装置，所述装置包括：获取模块，用于通过终端设备获取目标对象的历史睡眠数据和历史运动数据，所述历史睡眠数据包括在目标时间段之前的至少一天的睡眠数据，所述历史运动数据包括在所述目标时间段之前的至少一天的运动数据；处理模块，用于根据所述历史睡眠数据和所述历史运动数据，得到所述目标对象在所述目标时间段的目标运动推荐结果，所述目标运动推荐结果包括目标推荐运动时间和目标推荐运动量中的至少一种；输出模块，用于输出所述目标运动推荐结果的相关信息。
在一些实现方式中，运动推荐装置包括用于执行第一方面或第一方面的任意可能实现方式中的流程和/或步骤的模块或单元。
第四方面，本申请提供一种睡眠推荐装置，所述装置包括：获取模块，用于通过终端设备获取目标对象的历史睡眠数据；第一处理模块，用于根据所述目标对象的属性信息和所述目标对象的期望睡眠信息中的至少一种，得到所述目标对象的至少一个目标睡眠参数值；第二处理模块，用于基于所述目标对象的至少一个目标睡眠参数值以及所述目标对象的历史睡眠数据，得到所述目标对象在目标时间段的睡眠推荐结果，所述睡眠推荐结果包括推荐入睡时间、推荐醒来时间和推荐睡眠时长中的至少一种；输出模块，用于输出所述睡眠推荐结果的相关信息。
在一些实现方式中，睡眠推荐装置包括用于执行第二方面或第二方面的任意实现方式中的流程和/或步骤的模块或单元。
第五方面，本申请提供一种电子设备，包括：至少一个处理器；以及与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如第一方面或第一方面的任意可能实现方式所述的运动推荐方法，或者，使所述至少一个处理器能够执行如第二方面或第二方面的任意可能实现方式所述的睡眠推荐方法。
第六方面，本申请提供一种计算机可读存储介质，用于存储有指令，其中，当所述指令被执行时，使如第一方面或第一方面任意实现方式所述的运动推荐方法被实现，或者，使如第二方面或第二方面的任意实现方式中所述的睡眠推荐方法被实现。
第七方面，本申请提供一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现如第一方面或第一方面的任意实现方式所述的运动推荐方法，或者，实现如第二方面或第二方面的任意实现方式所述的睡眠推荐方法。
应当理解，本部分所描述的内容并非旨在标识本申请的实施例的关键或重要特征，也不用于限制本申请的范围。本申请的其它特征将通过以下的说明而变得容易理解。
附图说明
附图用于更好地理解本申请，不构成对本申请的限定。
图1是本申请实施例提供的健康指导系统的示例性框图。
图2是本申请实施例提供的一种运动推荐方法的流程示意图。
图3是本申请实施例提供的另一种运动推荐方法的流程示意图。
图4是本申请实施例提供的又一种运动推荐方法的流程示意图。
图5是本申请实施例提供的一种示例性运动量推荐方案的示意图。
图6是本申请实施例提供的一种示例性运动建议方案的示意图。
图7是本申请实施例提供的一种睡眠推荐方法的流程示意图。
图8是本申请实施例提供的一种示例性睡眠建议方案的示意图。
图9是本申请实施例提供的一种示例性补充睡眠建议方案的示意图。
图10是本申请实施例提供的一种示例性睡眠建议方案的示意图。
图11是本申请实施例提供的一种示例性健康指导系统的示意图。
图12是本申请实施例提供的一种运动推荐装置的示意图。
图13是本申请实施例提供的一种睡眠推荐装置的示意图。
图14是本申请实施例提供的另一种睡眠推荐装置的示意图。
图15为本申请实施例提供的一种电子设备的示意性框图。
具体实施方式
以下结合附图对本申请的示范性实施例做出说明，其中包括本申请实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本申请的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
在本申请的描述中，除非另有说明，“/”表示或的意思，例如，A/B可以表示A或B。本文中的“和/或”仅仅是描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。本申请中涉及的第一、第二等各种数字编号仅为描述方便进行的区分，并不用来限制本申请实施例的范围，也不表示先后顺序。
可穿戴设备、智能手机、个人数字助理等终端设备越来越多地用于监测用户的运动和生理信息，例如心率、血氧水平等，但是并未对检测到的用户数据进行深层次的分析与利用，以帮助用户实现主动健康目标。
本申请实施例基于终端设备采集的睡眠数据和运动数据为用户进行运动推荐和睡眠推荐来解决此类问题。通过终端设备采集目标对象的历史睡眠数据和历史运动数据，根据历史睡眠数据和历史运动数据，得到目标对象的目标运动推荐结果，并输出目标运动推荐结果的相关信息。从而，基于目标对象的历史睡眠数据和历史运动数据，确定并向目标对象推荐目标运动推荐结果，从而帮助目标对象保持科学且规律的运动习惯，为目标对象运动能力的提升以及主动健康目标的达成建立基础。
图1是本申请实施例提供的健康指导系统100的示例性框图。参考图1，该系统100包括可穿戴设备102、服务器设备104和中间设备106，中间设备106是可穿戴设备102和服务器设备104的中间连接设备。
可穿戴设备102是一种计算设备，被配置为在操作期间由用户佩戴。可穿戴设备102可以实现为佩戴在用户手腕上的腕戴式设备，或者也可以实现为佩戴在用户手臂、腿或躯干上的带或环，或者，也可以实现为佩戴在用户头部或眼部的头戴式设备，佩戴在用户耳部的耳戴式设备，或佩戴在用户服饰或配饰中的穿戴式设备，或者，也可以实现为佩戴在用户腰部、腿部或足部的穿戴式设备，等等。
一般地，可穿戴设备102可以包括壳体、佩戴件、显示器、通信元件、定位元件、一个或多个传感器、存储器以及处理器。
在图1所示的例子中，可穿戴设备102包括一个或多个传感器108。传感器108可以包括光容积图(photoplethysmography，PPG)传感器、脉搏波传感器、加速度传感器、血压传感器、睡眠传感器、心电图传感器、体温传感器、压力传感器、超声波传感器、红外传感器等组合中的一个或任意多个。传感器108中的一个或多个可以用于测量用户的生理参数，例如，生理参数可以包括心率、心率变异性、血氧饱和度、血压、血糖、体温、呼吸等组合中的一个或任意多个。
此外，可穿戴设备102上运行有程序110，用于处理基于传感器108采集到的用户 数据而产生的测量信号。
服务器设备104是运行服务器程序112以处理测量信号数据的计算设备。服务器设备104可以是或包括硬件服务器(例如，服务器设备)、软件服务器(例如，web服务器和/或虚拟服务器)或两者。例如，在服务器设备104是或包括硬件服务器的情况下，服务器设备104可以是位于机架中的服务器设备。
服务器程序112用于使用测量信号数据来检测可穿戴设备102的用户的健康状况、运动状况、睡眠状况或其组合中的一个或多个。例如，服务器程序112可以从中间设备106接收测量信号数据，然后可以使用接收的测量信号数据来检测可穿戴设备102的用户的健康状况、运动状况、睡眠状况或其组合中的一个或多个。例如，服务器程序112可以使用测量信号数据来确定用户状态或用户状态的变化，然后基于所确定的用户状态或用户状态的变化来检测可穿戴设备102的用户的健康状况、运动状况、睡眠状况或其组合中的一个或多个。
服务器程序112可以访问服务器设备104中的数据库114，以执行服务器程序112的至少一些功能。数据库114是用于存储、管理或以其他方式提供用于交付服务器程序112的功能的数据的数据库或其他数据存储。例如，数据库114可以存储服务器设备104接收的生理信号数据、通过生理信号数据而产生或以其他方式确定的信息。例如，数据库114可以是关系数据库管理系统、对象数据库、XML数据库、配置管理数据库、管理信息库、一个或多个平面文件、其他合适的非瞬态存储机制或其组合。
中间设备106是用于促进可穿戴设备102和服务器设备104之间的通信的设备。具体而言，中间设备106从可穿戴设备102接收数据，并将接收到的数据发送到服务器设备104，例如供服务器程序112使用。中间设备106可以是计算设备，例如移动设备(例如，智能手机、平板电脑、笔记本电脑或其他移动设备)或其他计算机(例如，台式计算机或其他非移动计算机)。或者，中间设备106可以是或包括网络硬件，例如路由器、交换机、负载平衡器、另一网络设备或其组合。作为另一备选方案，中间设备106可以是另一个网络连接设备。例如，中间设备106可以是可穿戴设备102的联网电源充电器。
例如，根据中间设备106的特定实现，中间设备106可以运行应用程序118，应用程序118可以是安装在中间设备106上的一个或多个应用软件。在一些实现中，应用软件可以是中间设备106的用户(通常是与可穿戴设备102的用户相同的人，但在某些情况下可能不是与可穿戴设备102的用户相同的人)在购买中间设备106后安装在中间设备106上，也可以是中间设备106的制造商在中间设备106出厂前预装在中间设备106上。应用程序118配置为向可穿戴设备102发送数据或从可穿戴设备102接收数据，和/或，向服务器设备104发送数据或从服务器设备104接收数据。应用程序118可以从中间设备106的用户接收命令。应用程序118可以通过应用程序118的用户界面接收来自其用户的命令。例如，在中间设备106是具有触摸屏显示器的计算设备的情况下，中间设备106的用户可以通过触摸与应用程序中的用户界面元素相对应的显示器的一部分来接收命令。
例如，应用程序118从中间设备106的用户接收的命令可以是将在中间设备106接收(例如，从可穿戴设备102接收)的生理信号数据传送到服务器设备104的命令。中间设备106响应于这样的命令将生理信号数据发送到服务器设备104。在另一示例中，应用程序118从中间设备106的用户接收的命令可以是审查从服务器设备104接收的信息的命令，例如，与检测出的可穿戴设备102的用户的健康状况、运动状况、睡眠状况或其组合中的一个或多个有关的信息。
在一些实现中，客户端设备被赋予访问服务器程序112的权限。例如，客户端设备可以是移动设备，例如智能手机、平板电脑、笔记本电脑等。在另一示例中，客户端设备可以是台式计算机或其它非移动计算机。客户端设备可以运行客户端应用程序以与服务器程序112通信。例如，客户端应用程序可以是能够访问服务器程序112的部分或全 部功能和/或数据的移动应用。例如，客户端设备可以通过网络116与服务器设备104通信。在一些这样的实现中，客户端设备可以是中间设备106。
在一些实现中，服务器设备104可以是虚拟服务器。例如，可以使用虚拟机(例如，Java虚拟机)实现虚拟服务器。虚拟机的实现可以使用一个或多个虚拟软件系统，例如，HTTP服务器、java servlet容器、hypervisor或其他软件系统。在一些这样的实现中，用于实现虚拟服务器的一个或多个虚拟软件系统可以改为在硬件中实现。
在一些实现中，中间设备106使用短距离通信协议从可穿戴设备102接收数据。例如，短距离通信协议可以是低能、红外、Z波、ZigBee、其他协议或其组合。中间设备106通过网络116将从可穿戴设备102接收的数据发送到服务器设备104。例如，网络116可以是局域网、广域网、机器对机器网络、虚拟专用网络或其它公共或专用网络。网络116可以使用远程通信协议。例如，远程通信协议可以是以太网、TCP、IP、电力线通信、Wi-Fi、GPRS、GSM、CDMA、其他协议或其组合。
系统100用于将生理信号数据从可穿戴设备102连续传输到服务器设备104。传感器108可以连续地或以其他方式频繁地周期性地采集可穿戴设备102的用户的测量信号数据。
系统100的实现可能不同于关于图1所示和描述的。在一些实现中，可以省略中间设备106。例如，可穿戴设备102可以被配置为通过网络116直接与服务器设备104通信。例如，可穿戴设备102和服务器设备104之间通过网络116的直接通信可以包括使用远程、低功率系统或其它通信机制。在一些实现中，中间设备106和服务器设备104都可以省略。例如，可穿戴设备102可以被配置为执行如上所述的关于服务器设备104的功能。在这样的实现中，可穿戴设备102可以独立于其他计算设备来处理和存储数据。
本申请实施例提供的方法可以由电子设备执行，其中，该方法可以由可穿戴设备执行，也可以由其它设备执行。例如，可穿戴设备可以将采集到的数据发送给中间设备，由该中间设备来执行该方法；又例如，可穿戴设备可以将采集到的数据直接发送给服务器设备，由该服务器设备来执行该方法；又例如，可穿戴设备可以将采集到的数据发送至中间设备，由中间设备将数据发送至服务器设备，由服务器设备来执行该方法。或者，本申请实施例提供的方法可以由多个设备共同完成，例如，一部分操作由可穿戴设备执行，另一部分操作由中间设备执行，再例如，一部分操作由可穿戴设备执行，另一部分操作由服务器设备执行，再例如，一部分操作由中间设备执行，另一部分操作由服务器设备执行，本申请实施例对此不做具体限定。
在一些实施例中，该方法也可以通过智能手机、个人数字助理、平板电脑等电子设备来实现。例如，智能手机采集用户的运动和/或睡眠数据，并执行本公开实施例提供的方法。
请参见图2，图2是本申请实施例提供的一种运动推荐方法的流程示意图。该运动推荐方法可以包括但不限于S201至S203。
在S201中，通过终端设备获取目标对象的历史睡眠数据和历史运动数据。
具体地，所述历史睡眠数据包括在目标时间段之前的至少一天的睡眠数据，所述历史运动数据包括在所述目标时间段之前的至少一天的运动数据。作为一个例子，所述历史睡眠数据包括第一时间段的睡眠数据，所述历史运动数据包括第二时间段的运动数据。
本申请实施例中的各个时间段，可以以天为单位，且不同的时间段可以具有不同的时间长度。例如，某个时间段可以包括一天、三天、一周、三周、一个月或半年等。这里的“天”可以指自然日，也可以指从某一时间点开始的24小时。
在本申请实施例中，为了便于描述，将执行该方法的时间称为当天。第一时间段可以包括当天之前的一天或多天，第二时间段可以包括当天之前的一天或多天。其中，在一些实施例中，第一时间段和第二时间段可以相同，例如，第一时间段和第二时间段均包括当天之前的一天或多天，例如，本星期已经经过的一天或多天、当天的前一天、当 天的前7天、前14天、前一个月或前三个月等等，或者当天所在星期的前一周、前两周、前一个月、前半年等等。在另一些实施例中，第二时间段和第一时间段为包含关系，作为一个例子，第二时间段包括的时间长度大于或等于第一时间段包含的时间长度，也即第二时间段包含第一时间段，例如，第二时间段包括当天之前的多天，第一时间段包括当天的前一天。作为另一个例子，第一时间段包含第二时间段。在另一些实施例中，第一时间段和第二时间段之间无交集，作为一个例子，第一时间段和第二时间段为时间前后关系，例如，第二时间段位于第一时间段之前，第二时间段包括本周之前的前一周或前几周，第一时间段包括本周内在当天之前的一天或多天，即本周已经经过的一天或多天。或者，第一时间段和第二时间段存在交集，也即第一时间段和第二时间段的部分时间重叠。
在一些实施例中，目标时间段包括接下来的一天，例如，当天或者明天。在另一些实施例中，目标时间段包括接下来的一周或多周或特定长度的时间段。为了便于理解，下文以目标时间段为一天为例进行描述，本申请实施例不限于此。
在一些实施例中，执行该方法的电子设备可以为终端设备，例如图1所示的可穿戴设备102。此时，终端设备可以采集目标对象的睡眠数据和/或运动数据，并将采集到的数据直接或进行一种或多种处理后存储在本地或远端存储器内，然后，在S201中，获取本地或远端存储器内存储的历史睡眠数据和/或历史运动数据。在另一些实施例中，执行该方法的电子设备为不同于终端设备的其它设备，例如，图1所示的中间设备106或服务器设备104。此时，终端设备可以采集目标对象的睡眠数据和/或运动数据，并将采集到的数据直接或进行一种或多种处理后发送给电子设备，相应地，在S201中，电子设备接收终端设备发送的历史睡眠数据和/或历史运动数据，或者，电子设备获取本地或远端存储器存储的历史睡眠数据和/或历史运动数据，或者，电子设备对接收到的终端设备发送的数据进行一种或多种处理后，得到历史睡眠数据和/或历史运动数据。
目标对象的历史睡眠数据可以包括睡眠相关的一种或多种类型的数据。在一些实施例中，目标对象的历史睡眠数据可以包括通过传感器采集到的睡眠相关生理数据，例如在睡眠期间采集到的目标对象的体动数据、呼吸数据、心率数据等一种或任意多种。在另一些实施例中，睡眠数据可以是至少部分地根据通过传感器采集到的睡眠相关生理数据得到的，例如，可以对睡眠相关生理数据进行一种或多种处理，如特征提取等，得到目标对象的睡眠数据。作为一个例子，该睡眠数据包括入睡时间(ST)、入睡潜伏期、睡眠时长(total sleep time，TST)、苏醒时间、深睡时长、深睡比例、睡眠分期数据、醒来次数(WN)、醒来累计时长(WT)、入睡时间规律性(STR)、睡眠时长规律性(TSTR)等一种或任意多种。
目标对象的历史运动数据可以包括运动相关的一种或多种类型的数据。在一些实施例中，目标对象的历史运动数据包括加速度数据和/或运动期间采集到的运动相关生理数据，其中，加速度数据可以是通过加速度计、陀螺仪或其它类型的加速度传感器采集到的，运动相关生理数据可以包括心率、呼吸率、皮肤汗液数据等一种或任意多种。在另一些实施例中，运动数据可以是至少部分地根据采集到的加速度数据和/或运动相关生理数据得到的，例如，可以对采集到的加速度数据和/或运动相关生理数据进行一种或多种处理，得到目标对象的运动数据。作为一个例子，该运动数据包括运动类型、运动开始时间、运动结束时间、运动持续时间、运动冲量、运动消耗能量、运动强度等一种或任意多种。
在S202中，根据历史睡眠数据和历史运动数据，得到目标对象在目标时间段的目标运动推荐结果。
在本申请实施例中，目标运动推荐结果包括目标推荐运动时间和目标推荐运动量中的至少一种。其中，该目标推荐运动时间可以是运动开始时间和运动结束时间中的至少一种，该目标推荐运动量可以是目标运动冲量、目标运动强度、特定运动强度下的运动 时间、目标运动总时间、目标消耗能量中的至少一种，或者目标推荐运动时间和目标推荐运动量也可以包括其它信息，本申请实施例对此不做限定。在一些实施例中，目标运动推荐结果还可以包括运动类型或其它运动参数。
在一些实施例中，确定目标对象的睡眠类型，并根据目标对象的睡眠类型、历史运动数据和历史睡眠数据，得到目标时间段的目标推荐运动时间。其中，目标对象的睡眠类型可以是至少部分地通过对用户个人信息进行分析得到的，或者，目标对象的睡眠类型是根据用户输入信息确定的，例如目标对象输入自己的睡眠类型。或者，目标对象的睡眠类型是根据目标对象的历史睡眠数据得到的，例如，将目标对象在一段时间的历史睡眠数据输入到机器学习模型进行处理，得到目标对象的睡眠类型。
在另一些实施例中，根据目标对象的历史睡眠数据确定目标对象的睡眠类型，根据目标对象的历史运动数据确定目标对象的至少一个历史运动时间，并根据目标对象的睡眠类型和目标对象的至少一个历史运动时间，得到目标时间段的目标推荐运动时间。
作为又一种示例，根据目标对象的历史睡眠数据，确定目标对象的睡眠类型，根据目标对象的历史运动数据，确定目标对象的至少一个候选运动时间，并至少部分地根据睡眠类型，从至少一个候选运动时间中确定目标推荐运动时间。
在一些实施例中，根据目标对象的历史运动数据，确定目标对象在目标时间段的初始运动推荐结果，并至少部分地根据目标对象的历史睡眠数据，对目标时间段的初始运动推荐结果进行调整处理，得到目标时间段的目标运动推荐结果。
作为一个例子，根据历史运动数据中的第一历史运动数据，确定所述目标时间段的初始运动推荐结果，并根据所述历史睡眠数据的至少一部分，对所述初始运动推荐结果进行调整处理，得到目标运动推荐结果。
第一历史运动数据包括目标时间段之前的至少一个时间段的运动数据。在一些实施例中，可以以包括多个时间段的运动推荐周期作为单位进行运动推荐。此时，第一历史运动数据包括在目标时间段所属的当前运动推荐周期之前的至少一个时间段的运动数据，例如，当前运动推荐周期之前的至少一个历史运动推荐周期的运动数据。作为一个例子，一个运动推荐周期为一周，第一历史运动数据包括前一周、前三周或前一个月等临近本周的一周或多周的运动数据。
历史睡眠数据的至少一部分可以包括临近目标时间段的一天或多天的睡眠数据。例如，历史睡眠数据的至少一部分可以包括目标时间段的前一天或前N天的睡眠数据。再例如，历史睡眠数据的至少一部分可以包括当前运动推荐周期内的一天或多天的睡眠数据。再例如，历史睡眠数据的至少一部分可以包括当前运动推荐周期内已经经过的一天或多天的睡眠数据。
在一个例子中，根据第一历史运动数据，确定目标时间段所属的当前运动推荐周期包括的多个时间段中每个时间段的初始运动推荐结果，例如初始推荐运动时间和/或初始推荐运动量。此时，可以结合专家知识或者运动生理学知识或者根据运动生理学知识确定的运动策略信息，以及目标对象的第一历史运动数据，得到多个时间段中每个时间段的初始运动推荐结果。
初始运动推荐结果的确定与目标运动推荐结果的确定可以不在同一时间执行。作为一个例子，可以在本周之前确定初始运动推荐结果，而在本周的每一天确定当天或下一天的目标运动推荐结果。此时，根据第一历史运动数据，在第一时间确定目标时间段的初始运动推荐结果，所述第一时间在所述目标时间段所属的当前运动推荐周期之前；根据历史睡眠数据的至少一部分，在第二时间对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果，所述第二时间在所述当前运动推荐周期内且在所述目标时间段之前，例如，第二时间为目标时间段的前一天或当天。
在一些实施例中，根据历史睡眠数据的至少一部分，得到目标对象在临近目标时间段的至少一天的睡眠质量评估结果，并至少部分地根据睡眠质量评估结果，对目标时间 段的初始运动推荐结果进行调整处理，得到目标时间段的目标运动推荐结果。
该睡眠质量评估结果可以用于评价用户的睡眠情况，例如，睡眠质量评估结果可以包括睡眠恢复度、睡眠质量评分、深度睡眠时长等一种或多种睡眠评估指标。
作为一个例子，可以根据睡眠质量评估结果，对初始运动推荐结果中的初始推荐运动量进行调整处理。例如，如果睡眠质量评估结果指示目标对象最近或当前的睡眠评估指标较差，如睡眠评估指标低于一预设阈值，则可以降低初始推荐运动量，得到目标推荐运动量。再例如，如果睡眠质量评估结果指示目标对象最近或当前的睡眠评估指标较好，如睡眠评估指标达到一预设阈值，则可以提高初始推荐运动量或保持初始推荐运动量，得到目标推荐运动量。
在另一些实施例中，可以根据历史运动数据中包括的第二历史运动数据和历史睡眠数据中的至少一部分中的至少一种，对目标时间段的初始运动推荐结果进行调整处理，得到目标时间段的目标运动推荐结果。
第二历史运动数据可以包括目标时间段之前的一天或多天的运动数据。其中，第二历史运动数据可以为第一历史运动数据的一部分。或者，第二历史运动数据包括临近目标时间段的一天或多天的运动数据，作为一个例子，第二历史运动数据包括当前运动推荐周期内的一天或多天的运动数据，例如，当前运动推荐周期内已经经过的一天或多天的运动数据。
作为一个例子，根据第二历史运动数据，得到目标对象的运动评估结果，其中，运动评估结果指示临近目标时间段的至少一天的运动量达标情况，并至少部分地根据目标对象的运动评估结果，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
在一个例子中，该运动量达标情况可以包括运动量达标频次和/或运动总量达标指示，运动总量达标指示可以用于指示临近目标时间段的所述至少一天内的运动总量是否达标，运动量达标频次可以用于指示所述至少一天内运动量达标的频次，即，运动量达标的天数在所述至少一天对应的总天数中所占的比例。例如，运动量达标频次可以指示当前运动推荐周期内已经经过的一天或多天内运动量达标的天数比例，运动总量达标指示可以指示当前运动推荐周期内已经经过的一天或多天的运动总量是否达到设定运动总量。该设定运动总量可以为已经经过的一天或多天的推荐运动量之和，或者可以为当前运动推荐周期的推荐运动总量。在另一个例子中，可以通过其它指标来表征运动量达标情况，本申请实施例对此不做限定。
在一个例子中，如果运动量达标情况包括的运动量达标指标较差，如运动量达标指标低于一预设阈值，则可以保持初始推荐运动量不变或增加初始推荐运动量。在另一个例子中，如果运动量达标情况包括的运动量达标指标较好，如运动量达标指标达到一预设阈值，则可以保持初始推荐运动量不变或降低初始推荐运动量。
在另一些实施例中，可以确定目标时间段的初始运动推荐结果，并根据所述历史睡眠数据的至少一部分和所述历史运动数据中的第二历史运动数据，对目标时间段的初始运动推荐结果进行调整处理，得到目标时间段的目标运动推荐结果。
所述历史睡眠数据的至少一部分包括临近所述目标时间段的至少一天的睡眠数据，例如，目标时间段的前一天或前N天的睡眠数据，或与目标时间段之间的时间间隔小于设定数值的一个或多个时间段的睡眠数据，或某一设定时间点到目标时间段之间的一个或多个时间段的睡眠数据，或当前运动推荐周期内已经经过的一天或多天的睡眠数据。所述第二历史运动数据包括临近所述目标时间段的至少一天的运动数据，例如，目标时间段的前一天或前N天的运动数据，或与目标时间段之间的时间间隔小于设定数值的一个或多个时间段的运动数据，或某一设定时间点到目标时间段之间的一个或多个时间段的运动数据，或当前运动推荐周期内已经经过的一天或多天的运动数据。在一个例子中，所述第二历史运动数据和所述历史睡眠数据的至少一部分对应相同的时间段，例如在当前运动推荐周期内且在目标时间段之前的时间段。
在一些实现方式中，可以对目标对象的历史睡眠数据进行量化评估，得到目标对象的睡眠质量评估结果，基于第二历史运动数据，得到运动评估结果，并基于睡眠质量评估结果和运动评估结果，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
在S203中，输出目标运动推荐结果的相关信息。
在一些实现例中，电子设备可以以任何合适的方式推送所述目标运动推荐结果的相关信息。例如，电子设备可以在显示器上显示目标运动推荐结果的相关信息，或者，通过通知、语音、振动或其它触觉输出的方式向目标对象输出目标运动推荐结果的相关信息。
在另一些实施例中，电子设备可以向终端设备发送该目标运动推荐结果的相关信息，以使得终端设备向目标对象输出目标运动推荐结果的相关信息。
目标运动推荐结果的相关信息可以包括目标运动推荐结果本身，例如，包括目标推荐运动时间和目标推荐运动量中的至少一种。或者，目标运动推荐结果的相关信息可以包括根据目标运动推荐结果生成的提醒信息，例如，用于提醒在目标推荐运动时间进行运动的提醒信息，在运动前生成的用于提醒完成目标推荐运动量的提醒信息，在运动过程中生成的用于提醒还需要完成特定运动量的提醒信息，等等，本申请实施例对此不做限定。
通过实施本申请实施例，可以基于目标对象的历史睡眠数据和历史运动数据，得到目标对象的目标运动推荐结果，并输出该目标运动推荐结果的相关信息，从而帮助目标对象保持科学且规律的运动习惯，为目标对象运动能力的提升以及主动健康目标的达成建立基础。
下面将结合具体例子，说明如何根据历史睡眠数据的至少一部分，得到目标对象的睡眠质量评估结果。
在一个例子中，历史睡眠数据包括下列睡眠参数中的至少一种：入睡时间(ST)、睡眠时长(total sleep time，TST)、苏醒时间、深睡时长、深睡比例、睡眠阶段、醒来次数(WN)、醒来累计时长(WT)、入睡时间规律性(STR)、睡眠时长规律性(TSTR)。
可以基于历史睡眠数据中包括的一项或多项睡眠参数，来确定目标对象的睡眠质量评估结果。作为一个例子，可以对历史睡眠数据中包括的睡眠相关生理数据进行特征提取处理，得到睡眠特征数据，并基于该睡眠特征数据，得到睡眠质量评估结果。作为另一个例子，可以对历史睡眠数据中的一项或多项，或根据睡眠数据得到的睡眠特征数据中的一项或多项，进行预处理得到输入数据，然后将该输入数据输入至预先训练的睡眠质量评估模型，以得到目标对象的睡眠质量评估结果。
在一个例子中，以对睡眠特征数据进行预处理为例，可以使用z分数(z-score)对睡眠特征数据中的一项或多项数据进行预处理，例如，可通过以下式子进行预处理：
其中，zi是某项睡眠特征数据中第i个特征数据的标准分数，x＝{x1,x2...xn}，代表该睡眠特征数据的集合，n为该睡眠特征数据的集合中包含的特征数据的个数，xi是该睡眠特征数据的集合中第i个特征数据，i为整数，1≤i≤n，u是该睡眠特征数据的平均值，s是该睡眠特征数据的标准差。
在一个例子中，可以通过匹兹堡睡眠质量评估模型进行睡眠质量评估。该睡眠质量评估模型可以通过深度学习网络来实现。例如，睡眠质量评估模型可表示如下：
PSQI＝DNN(TST,ST,DR,STR,TSTR,WN,WT)
其中，PSQI(Pittsburgh Sleep Quality Index，匹兹堡睡眠质量指数)为睡眠质量评估模型的输出，DNN为深度神经网络，TST,ST,DR,STR,TSTR,WN,WT为睡眠质量评估模型的输入；其中，TST表示睡眠时长，ST表示入睡时间，DR表示深睡比例，STR表示入睡时间规律性，TSTR表示睡眠时长规律性，WN表示醒来次数，WT表示醒来累计时长。
在一些实施例中，以上多项睡眠参数或睡眠特征数据可以具有相同的权重。在另一些实施例中，可以基于睡眠医学中的PSQI问卷为上述睡眠参数或睡眠特征数据分别设置对应的权重值。以上深度神经网络可以通过任意合适的方式进行训练，例如，通过监督或无监督的方式，本申请实施例对此不做限定。
请参见图3，图3是本申请实施例提供的另一种运动推荐方法的流程示意图，其中，在该例子中，目标运动推荐结果包括目标推荐运动时间。如图3所示，该方法可以包括但不限于S301至S304。
在S301中，通过终端设备获取目标对象的历史睡眠数据和历史运动数据。
S301可通过本申请的各实施例中的任一种方式实现，这里不再赘述。
在S302中，根据历史运动数据中包含的至少一部分历史运动时间数据，确定候选运动时间集合。
在一个例子中，历史睡眠数据包括目标时间段的前一天或前一时间段的睡眠数据。历史运动数据包括目标时间段之前的多天的运动数据，例如，一个月、三个月等等。
在一个例子中，历史运动数据用于确定目标对象的运动习惯或喜好，历史睡眠数据用于确定目标对象的睡眠习惯或喜好，可以结合目标对象的运动习惯或喜好以及睡眠习惯或喜好来进行针对目标对象的运动时间推荐。
在一个例子中，该候选运动时间集合可以包括多个候选运动时间。例如，可以将历史运动时间数据中包括的所有历史运动时间作为候选运动时间。或者，也可以将历史运动时间数据中包括的所有历史运动时间中满足一定条件的运动时间作为候选运动时间，例如将历史运动时间数据中出现的次数达到一定阈值的历史运动时间作为候选运动时间，等等。或者，候选运动时间是通过对历史运动时间数据中的多个历史运动时间进行处理后得到的，例如，通过对历史运动时间数据中包括的多个历史运动时间进行统计分析，得到多个候选运动时间。
举例而言，确定历史运动数据中的部分或全部历史运动时间所属的多个时间段，并将确定的多个时间段作为候选运动时间集合，可表示如下：
ExtHistory＝{Ext_1,Ext_2,...Ext_n}
其中，Ext_1,Ext_2,...Ext_n为目标对象的历史运动数据之中包含的历史运动时间所属的时间段(例如以1小时为间隔)，n为正整数，0≤n≤24。
在S303中，根据历史睡眠数据，从候选运动时间集合中确定目标推荐运动时间。
举例而言，根据目标对象的历史睡眠数据以及睡眠先验知识，从候选运动时间集合中确定出适合目标对象的睡眠情况的目标推荐运动时间。
在一些实现方式中，可以确定目标对象的睡眠类型，并根据目标对象的睡眠类型，从候选运动时间集合中确定目标推荐运动时间。
该睡眠类型用于表征目标对象的睡眠习惯。在一个例子中，睡眠类型可以包括早起类型、晚起类型和睡眠障碍类型，其中，早起类型代表目标对象具有早起的习惯；晚起类型代表目标对象具有晚起的习惯；睡眠障碍类型代表目标对象有疑似失眠症状。在其它例子中，该睡眠类型也可以包括其它类型，例如，早睡类型、晚睡类型、入睡困难类型、多梦类型、半夜频醒类型、少睡类型、多睡类型等等任意一种或任意组合，本申请实施例对此不做限定。
在一个例子中，该睡眠类型可以是根据目标对象输入的指令或用户输入信息得到的，例如，通过提示信息提示目标对象输入自己的睡眠习惯信息，例如睡眠时间、是否有睡眠障碍、睡眠类型等信息，然后可以根据用户输入信息，得到目标对象的睡眠类型，例如，直接将用户输入信息中包括的睡眠类型信息所对应的睡眠类型作为目标对象的睡眠类型，或者对用户输入信息进行处理，例如将用户输入信息作为睡眠分类模型的输入参数，或者，利用用户输入信息和预设映射规则，确定目标对象的睡眠类型。
在另一个例子中，该睡眠类型是通过对目标对象进行睡眠监测得到的。例如，根据 目标对象在一段时间内的历史睡眠数据，得到目标对象的睡眠类型。例如，将目标对象在该段时间内的历史睡眠数据直接或经过一种或多种处理后输入到睡眠分类模型中进行处理，得到目标对象的睡眠类型。其中，该段时间可以是较长的时间段，例如，该段时间可以是一个月、三个月、半年等，这里不做限定。在一些实现方式中，可以利用目标对象佩戴的可穿戴设备对目标对象进行睡眠监测，或者利用其它类型的终端设备对目标对象进行睡眠监测，此时，该历史睡眠数据可以是可穿戴设备或其它类型的终端设备监测到的目标对象的所有睡眠数据，也可以是可穿戴设备或其它类型的终端设备监测到的目标对象的所有睡眠数据中的一部分，例如满足特定条件或距离目标时间段在一定时间间隔内的睡眠数据，这里不做限定。
举例而言，根据目标对象的历史睡眠数据，确定目标对象的睡眠潜伏期、入睡时间、睡眠结束时间、醒来次数、醒来累计时长、深睡时长、浅睡时长等一项或多项数据，并通过对得到的数据进行统计分析，得到目标对象的睡眠类型。假如，目标对象的睡眠结束时间一般早于或者等于预设时间(例如7点)，则确定目标对象的睡眠类型为早起类型；假如目标对象的睡眠结束时间一般晚于预设时间(例如9点)，则确定目标对象的睡眠类型为晚起类型；当目标对象的睡眠潜伏期大于预设时长，或者在睡眠期间的醒来次数大于预设次数，或者在睡眠期间的醒来累计时长大于预设时长阈值(例如，1小时)，则确定目标对象的睡眠类型为睡眠障碍类型。
在另一个例子中，该睡眠类型是通过其它方式确定的，例如，根据目标对象的个人信息等用户画像信息，确定目标对象的睡眠类型，本申请实施例对此不做限定。
在一些实现方式中，可以根据目标对象的睡眠类型，从候选运动时间集合中选择符合该睡眠类型的运动时间，作为目标推荐运动时间。作为一个例子，从多个预设的运动时间偏移量中，确定出与目标对象的睡眠类型对应的运动时间偏移量，并根据对应的运动时间偏移量，从候选运动时间集合中确定目标推荐运动时间。例如，可以预先设置睡眠类型与预设的运动时间偏移量之间的映射关系，并通过查找比对的方式，确定目标对象的睡眠类型对应的运动时间偏移量。再例如，可以构建运动时间偏移量的确定模型，并利用预先构建的模型对目标对象的睡眠类型进行处理，得到对应的运动时间偏移量，或者可以通过其它方式确定对应的运动时间偏移量，本申请实施例对此不做限定。
在一些实现方式中，根据目标对象的睡眠类型和历史睡眠数据，从候选运动时间集合中确定目标推荐运动时间。
在一些实现方式中，根据目标对象的历史睡眠数据和/或睡眠类型，确定目标对象的参考睡眠开始时间；根据上述对应的运动时间偏移量和参考睡眠开始时间，从候选运动时间集合中选择目标推荐运动时间。
在一个例子中，根据历史睡眠数据中包括的历史睡眠开始时间数据，确定目标对象的参考睡眠开始时间。例如，将目标对象在前一天的历史睡眠开始时间，作为目标对象的参考睡眠开始时间。再例如，通过对目标对象在前一周或本周的前几天的历史睡眠开始时间进行统计分析，得到目标对象的参考睡眠开始时间。
在另一个例子中，将目标对象的睡眠类型所对应的群体睡眠开始时间，作为目标对象的参考睡眠开始时间。该群体睡眠开始时间可以是通过对与目标对象属于同一睡眠类型的用户群体进行睡眠分析得到的。
在一些实现方式中，根据目标对象的参考睡眠开始时间和运动时间偏移量，确定运动时间要求，并根据运动时间要求从候选运动时间集合中确定目标推荐运动时间。
在一个例子中，根据历史睡眠数据中包括的历史睡眠开始时间数据与运动时间偏移量，确定运动时间要求；将候选运动时间集合中满足运动时间要求的至少一个候选运动时间确定为目标推荐运动时间。
作为一种示例，可以根据运动时间偏移量和参考睡眠开始时间，确定目标对象的最晚运动时间，然后将候选运动时间集合中位于该最晚运动时间之前的一个或多个候选运 动时间，作为目标推荐运动时间。
例如，根据以下式子来确定目标对象的运动时间要求：
其中，ExtSleepRule表示满足运动时间要求的时间段，STt-1表示目标对象在前一天或前一周的睡眠开始时间，即前一时间段或前一运动推荐周期的睡眠开始时间，C2、C3及C4分别表示早起类型、晚起类型、睡眠障碍类型对应的运动时间偏移量。将候选运动时间集合中的时间段和满足运动时间要求的时间段求交集，得到候选推荐运动时间，也即：
ExtCandidate＝ExtHistory∩ExtSleepRule
其中，ExtCandidate表示候选推荐运动时间集合，其中包括选出的一个或多个候选推荐运动时间，ExtHistory表示候选运动时间集合，ExtSleepRule表示满足运动时间要求的运动时间集合。可以将候选推荐运动时间集合中的至少一个候选推荐运动时间确定为目标推荐运动时间。
在一些实现方式中，候选推荐运动时间集合中包括的候选推荐运动时间仅有一个，此时，可以将该候选推荐运动时间确定为目标推荐运动时间。在另一些实现方式中，候选推荐运动时间集合中包括的候选推荐运动时间可以有多个，此时，可以从候选推荐运动时间集合中的多个候选推荐运动时间中进行二次筛选，以得到最终的目标推荐运动时间。
在一个例子中，可以从候选运动时间集合中选择多个候选推荐运动时间，然后输出提示信息，以提示目标对象从多个候选推荐运动时间中选择，并基于接收到的目标对象输入信息确定目标推荐运动时间。这样，可以使得选择的目标推荐运动时间更满足目标对象的需求或喜好，以提高目标对象的运动积极性。
在另一个例子中，可以结合目标对象在各个候选推荐运动时间的历史运动频次，从多个候选推荐运动时间中确定最终的目标推荐运动时间。例如，根据目标对象的至少一部分历史运动时间数据，确定目标对象在多个候选推荐运动时间中每个候选推荐运动时间的运动频次，并根据目标对象在多个候选推荐运动时间中每个候选推荐运动时间的运动频次，从多个候选推荐运动时间中确定目标推荐运动时间。
在另一些实现方式中，可以结合目标对象在候选运动时间集合包括的各个候选运动时间的历史运动频次，从多个候选运动时间中确定目标推荐运动时间。例如，根据目标对象的至少一部分历史运动时间数据，确定目标对象在多个候选运动时间中每个候选运动时间的运动频次，并根据目标对象在多个候选运动时间中每个候选运动时间的运动频次，从多个候选运动时间中确定目标推荐运动时间。其中，该运动频次可以是从所有历史运动时间数据得到的，也可以是从特定时间间隔的历史运动时间数据得到的，也可以是从满足特定条件的历史运动时间数据得到的，这里不做限定。
举例而言，可以从多个候选运动时间中确定目标对象运动频次最高的候选运动时间，作为目标推荐运动时间。作为一种示例，目标推荐运动时间可通过以下式子确定：
Extrecommend(t)＝Argmax(Frequency(ExtCandidate))
其中，ExtCandidate表示目标对象的多个候选推荐运动时间，Frequency()为运动频次统计函数，Extrecommend(t)表示目标推荐运动时间，Argmax表示对函数求集合。
在S304中，输出目标运动推荐结果的相关信息。
通过实施本申请实施例，可以根据目标对象的历史睡眠数据和历史运动数据中的至少一部分历史运动时间数据，确定目标对象的目标推荐运动时间，结合目标对象的运动和睡眠习惯或喜好，帮助目标对象保持科学且规律的运动习惯，为目标对象运动能力的提升以及主动健康目标的达成建立基础。
在本申请实施例的一种实现方式中，根据历史运动数据中的第一历史运动数据，确定目标时间段的初始运动推荐结果；根据历史睡眠数据的至少一部分，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
请参见图4，图4是本申请实施例提供的另一种运动推荐方法的流程示意图。如图4所示，该方法可以包括但不限于S401至S404。
在S401中，通过终端设备获取目标对象的历史睡眠数据和历史运动数据。
在S402中，根据历史运动数据中的第一历史运动数据，确定目标时间段的初始运动推荐结果。
第一历史运动数据包括在目标时间段之前的一个或多个时间段的运动数据。作为一个例子，第一历史运动数据包括的运动数据所对应的一个或多个时间段与目标时间段之间的间隔在一定数值范围内，即该一个或多个时间段与目标时间段之间的间隔较小，以更能反映目标对象最近的运动情况。
在一些实现方式中，根据目标对象的生理数据测量结果，确定目标时间段的运动推荐策略，并基于目标时间段的运动推荐策略以及第一历史运动数据，确定目标时间段的初始运动推荐结果。
在一些例子中，可以根据目标对象的生理数据测量结果，确定目标对象当前的生理状态，并基于目标对象当前的生理状态，确定目标时间段的初始运动推荐结果。其中，当前的生理状态可以指在确定初始运动推荐结果时或之前的生理状态。该生理数据测量结果可以包括心率数据、压力数据、健康数据等一种或多种，本申请实施例对此不做限定。
在一些例子中，目标运动推荐结果包括目标推荐运动量，相应地，运动推荐策略可以包括下列中的一种：增加运动量、降低运动量、维持运动量。或者，运动推荐策略也可以进一步细化为增加特定幅度的运动量、降低特定幅度的运动量，等等。例如，根据在确定初始运动推荐结果前获取到的生理数据测量结果，确定目标对象的生理状态，并根据目标对象的生理状态，来确定运动推荐策略。该运动推荐策略可以为目标时间段的运动推荐策略，也可以为目标时间段所属的当前运动推荐周期(如本周)的运动推荐策略。
在一些例子中，可以根据目标对象的第一历史运动数据，确定目标对象的历史运动量数据，然后根据历史运动量数据和运动推荐策略，来确定初始运动推荐结果。例如，可以根据终端设备采集到的目标对象的第一历史运动数据，确定目标对象在特定时间间隔内每次运动的运动量，然后基于目标对象在特定时间长度内每次运动的运动量以及目标对象在特定时间间隔内的运动频次，得到目标对象的平均运动量，最后，基于目标对象的平均运动量和运动推荐策略，来确定目标时间段的初始运动推荐结果。该特定时间间隔例如可以为前一周、前21天、前一个月等等。
在一些例子中，可以根据目标对象的第一历史运动数据和运动推荐策略，确定当前运动推荐周期的推荐运动总量，然后结合该推荐运动总量以及运动专家/生理学知识和目标对象的运动偏好信息/设置信息中的至少一种，确定目标时间段的目标推荐运动量。
作为一种示例，第一历史运动数据包括当前运动推荐周期之前的至少一个历史运动推荐周期的运动数据。一个运动推荐周期可以对应一周、两周或特定时间长度。例如，一个运动推荐周期为一周，可以通过以下公式来确定本周的推荐运动总量：
其中，TRIMP(w)表示本周的推荐运动总量，CTLt-1表示目标对象在上一周的平均运动量，R和C1分别表示爬升率和偏移系数，可从睡眠先验知识中获取，或者根据目标对象的属性信息、历史运动数据或生理数据中的至少一项得到，Decrease load代表运 动推荐策略为需要降低运动量，Increase load代表运动推荐策略为需要增加运动量，Maintain load代表运动推荐策略为需要维持运动量。
然后，基于目标对象在本周的初始推荐运动时间和推荐运动总量，确定本周内每天的初始运动推荐结果。
在一个例子中，历史运动数据可以包括加速度数据和心率数据，可以根据第一历史运动数据中包括的一定时间间隔内的加速度数据和心率数据，得到目标对象在该时间间隔内的平均运动量。例如，响应于目标对象的心率数据指示当前心率值大于预设的心率阈值(例如：110次/分钟)且加速度数据大于预设的加速度阈值，则确定目标对象当前处于运动状态，根据目标对象处于运动状态的持续时长和处于运动状态的心率数据，得到目标对象每次运动时的运动量，该运动量也可以为运动冲量，但本申请实施例对此不做限定。
在S403中，根据历史睡眠数据的至少一部分，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
历史睡眠数据的至少一部分可以指所有历史睡眠数据，或者历史睡眠数据中的一部分，例如，特定时间间隔的历史睡眠数据。作为一个例子，可以根据临近目标时间段且与目标时间段之间的时间间隔小于设定值的一个或多个时间段的睡眠数据，对初始运动推荐结果进行调整处理，例如，前一天的睡眠数据，或者上一周的睡眠数据，或本周已经经过的日子的睡眠数据，等等。例如，可以根据前一天的睡眠数据，对初始运动推荐结果进行调整处理。再例如，可以根据当前运动推荐周期内已经经过的时间间隔的睡眠数据，对初始运动推荐结果进行调整处理。再例如，可以根据当前运动推荐周期之前的至少一个历史运动推荐周期的睡眠数据，对初始运动推荐结果进行调整处理。再例如，可以根据与目标时间段间隔特定时间长度的时间间隔的睡眠数据，对初始运动推荐结果进行调整处理。
在一些实施例中，根据历史睡眠数据的至少一部分，得到目标对象的睡眠质量评估结果；基于目标对象的睡眠质量评估结果，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
举例而言，根据历史睡眠数据的至少一部分，对目标对象在目标时间段之前的至少一天的睡眠质量进行评估，得到睡眠质量评估结果，并基于睡眠质量评估结果，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
该睡眠质量评估结果可以包括睡眠质量分数，也可以包括睡眠质量评价等级，例如，优、良、及格、不及格等，或者也可以包括用于指示睡眠质量是否达标的参数，例如，达标或未达标，或者也可以包括用于指示睡眠恢复度的指标，等等。该睡眠质量评估结果的参考标准可以是针对所有用户的，例如预先设定的固定标准，或者是针对目标对象的睡眠类型的群体的，例如，目标对象的睡眠在该睡眠类型的群体中而言的质量评估结果，或者是针对目标对象本身的，例如，针对自身的历史睡眠情况而言的质量评估结果，等等，本申请实施例对睡眠质量评估的实现方式不做限定。
可以基于最近一天或多天的睡眠质量评估结果，对初始运动推荐结果进行调整处理。例如，如果目标对象的睡眠质量评估结果指示目标对象在最近一天或几天的睡眠质量相对较高，则可以保持初始运动推荐结果中包括的推荐运动量不变，或者适当增加初始运动推荐结果中包括的推荐运动量。再例如，如果目标对象的睡眠质量评估结果指示目标对象在最近一天或几天的睡眠质量较差，则可以适当降低初始运动推荐结果中包括的推荐运动量，以避免目标对象由于运动过量而导致身体不适。
在另一些实施例中，根据历史睡眠数据的至少一部分以及历史运动数据中的第二历史运动数据，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。第二历史运动数据包括临近目标时间段的一个或多个时间段的运动数据。该第二历史运动数据所对应的一个或多个时间段与目标时间段之间的间隔较小，可以在一定间隔范围内。作为一 个例子，第二历史运动数据包括目标时间段的前一个或前N个时间段的运动数据，例如前一天或前N天的运动数据。作为另一个例子，第二历史运动数据包括目标时间段所属的当前运动推荐周期内的一个或多个时间段的运动数据，例如，当前运动推荐周期内已经经过的至少一天的运动数据。
在一些例子中，可以根据在当前运动推荐周期内且在目标时间段之前的一个或多个时间段的睡眠数据和运动数据，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。此时，作为一个例子，对初始运动推荐结果进行调整处理的过程中所利用的第二历史运动数据和历史睡眠数据可以均对应于当前运动推荐周期内已经经过的时间间隔，如本周已经经过的一天或多天。作为另一个例子，对初始运动推荐结果进行调整处理的过程中所利用的第二历史运动数据可以对应于当前运动推荐周期内已经经过的时间间隔，而利用的历史睡眠数据可以对应于目标时间段的前一时间段，例如前一天。
这样，可以综合最近一段时间目标对象的运动情况和睡眠情况，对初始运动推荐结果进行调整处理，得到目标运动推荐结果，使得目标运动推荐结果更符合目标对象最近的生理状态和实际需求。
举例而言，可以根据第二历史运动数据，得到目标对象的运动评估结果，运动评估结果用于指示目标对象的运动量达标情况；根据历史睡眠数据的至少一部分，得到目标对象在目标时间段之前的至少一天的睡眠质量评估结果；根据运动评估结果和睡眠质量评估结果，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
在一些实现方式中，可以根据第二历史运动数据，得到临近目标时间段的至少一天中每天的实际运动量，并根据该实际运动量，得到运动评估结果。作为一个例子，可以根据临近目标时间段的至少一天中每天的实际运动量以及该每天对应的推荐运动信息，得到运动评估结果。
举例而言，假设第二历史运动数据对应于当前运动推荐周期内已经经过的至少一天，可以将所述目标对象在所述当前运动推荐周期内已经经过的至少一天中每天的实际运动量与所述目标对象每天的推荐运动量进行比较，以确定所述目标对象每天的运动量是否达标；根据所述目标对象在当前运动推荐周期内已经经过的至少一天中每天的运动量是否达标，确定所述目标对象在所述当前运动推荐周期内已经经过的至少一天的运动评估结果。
作为一个例子，该运动评估结果可以包括运动总量达标情况和/或运动量达标频次。其中，运动总量达标情况可以指示临近目标时间段的至少一天的运动总量是否达标，例如，当前运动推荐周期内已经经过的至少一天的实际运动总量达到该至少一天或当前运动推荐周期的推荐运动总量。运动量达标频次可以指示临近目标时间段的该至少一天的运动量达标的天数占该至少一天所对应的总天数的比例。
例如，可以根据所述目标对象在临近目标时间段的至少一天中每天的实际运动量，确定所述目标对象在该至少一天的实际运动总量，根据所述至少一天对应的推荐运动总量和所述至少一天的实际运动总量，确定目标对象在该至少一天的运动总量是否达标。其中，该至少一天的推荐运动总量可以是根据本申请实施例进行了调整处理的目标推荐运动总量，在其他实施例中，该至少一天的推荐运动总量也可以是未经调整处理的初始推荐运动总量，这里不做限定。
其中，临近目标时间段的至少一天的实际运动总量可以指当前运动推荐周期内已经经过的一天或多天的实际运动量之和，该临近目标时间段的至少一天对应的推荐运动总量可以包括当前运动推荐周期的推荐运动总量，或者当前运动推荐周期内已经经过的一天或多天的推荐运动量之和。
再例如，可以根据所述目标对象在临近目标时间段的至少一天中每天的实际运动量和每天的推荐运动量，确定每天的运动量达标情况，根据该至少一天中每天的运动量达标情况，确定目标对象在该至少一天的运动量达标频次。
作为一个例子，假设某一天的实际运动量大于或等于这一天的推荐运动量，则判定目标对象在这一天的运动量达标。假设某一天的实际运动量小于这一天的推荐运动量，则判定目标对象在这一天的运动量未达标。其中，运动量达标情况的确定可表示如下：
其中，TRIMP′(t)表示目标对象在某一天的实际运动量，TRIMP(t)表示目标对象在这一天的推荐运动量，Achieve(t)表示运动量达标情况，其中，在上式所示的例子中，Achieve(t)＝1代表运动量已达标，Achieve(t)＝0代表运动量未达标。
作为另一个例子，可以通过以下公式确定目标对象在临近目标时间段的至少一天中的运动量达标天数：
其中，Achieve_count(t)为目标对象在临近目标时间段的至少一天中的运动量达标天数，t为临近目标时间段的该至少一天所对应的总天数。
可以将该运动量达标天数除以该至少一天所对应的总天数，得到运动量达标频次。或者，可以将该运动量达标天数与预设天数阈值进行比较，如果该运动量达标天数大于预设天数阈值，则确定运动量达标频次满足要求，反之，则确定运动量达标频次不满足要求。
在一些实现方式中，根据运动评估结果和睡眠评估结果中的至少一种，对初始推荐运动量进行调整处理，得到目标推荐运动量，其中，运动评估结果指示运动总量是否达标和/或运动量达标频次是否达到预设阈值。
作为一种示例，响应于运动评估结果指示运动总量未达标，且睡眠质量评估结果指示的睡眠质量低于预设质量阈值，则可以将初始运动推荐结果中包括的初始推荐运动量调整至目标对象的最低运动量，得到目标推荐运动量。此时，目标推荐运动量即为目标对象的最低运动量。此时，在运动评估结果指示运动总量未达标，且睡眠质量评估结果指示的睡眠质量低于预设质量阈值时，不管运动量达标频次是否达到预设频次阈值，都可以将初始运动推荐结果中包括的初始推荐运动量调整至目标对象的最低运动量。
作为另一种示例，响应于运动评估结果指示运动总量未达标，且睡眠质量评估结果指示的睡眠质量达到预设质量阈值，不对初始运动推荐结果中包括的初始推荐运动量进行调整，目标推荐运动量即为初始推荐运动量。此时，在运动评估结果指示运动总量未达标，且睡眠质量评估结果指示的睡眠质量达到预设质量阈值时，不管运动量达标频次是否达到预设频次阈值，都可以不对初始运动推荐结果中包括的初始推荐运动量进行调整。
作为另一种示例，响应于运动评估结果指示运动总量达标，且运动量达标频次达到预设频次阈值，则可以将初始运动推荐结果中包括的初始推荐运动量调整为0，目标推荐运动量即为0。此时，在运动评估结果指示运动总量达标，且运动量达标频次达到预设频次阈值时，不管睡眠质量评估结果指示的睡眠质量是否达到预设质量阈值，都可以将目标推荐运动量调整为0，即不推荐目标对象在目标时间段进行运动。
作为又一种示例，响应于运动评估结果指示运动总量达标，且运动量达标频次低于预设频次阈值，则可以将初始运动推荐结果中包括的初始推荐运动量调整至目标对象的最低运动量，目标推荐运动量即为目标对象的最低运动量。也就是说，在运动评估结果指示运动总量达标，且运动量达标频次低于预设频次阈值时，不管睡眠质量评估结果指示的睡眠质量是否达到预设质量阈值，都可以将初始运动推荐结果中包括的初始推荐运动量调整至目标对象的最低运动量。
作为又一种示例，响应于运动评估结果指示运动总量未达标，且运动量达标频次低于预设频次阈值，则不对初始运动推荐结果中包括的初始推荐运动量进行调整，此时目标推荐运动量即为初始推荐运动量。
作为又一种示例，响应于运动评估结果指示运动总量达标，且运动量达标频次低于预设频次阈值，则可以将初始运动推荐结果中包括的初始推荐运动量调整至目标对象的最低运动量，此时，目标推荐运动量即为目标对象的最低运动量。
作为又一种示例，响应于运动评估结果指示运动总量达标，且运动量达标频次达到预设频次阈值，则可以将初始运动推荐结果中包括的初始推荐运动量调整为0，此时，目标推荐运动量即为0。
在一些实施例中，响应于运动评估结果指示运动量未达标，且睡眠质量评估结果指示的睡眠质量低于预设质量阈值，将初始运动推荐结果中包括的初始推荐运动量调整至目标对象的最低运动量，得到目标推荐运动量。
在一些实施例中，响应于运动评估结果指示运动量未达标，且睡眠质量评估结果指示的睡眠质量达到预设质量阈值，则将初始推荐运动量确定为目标推荐运动量。
在一些实施例中，睡眠质量评估结果包括睡眠恢复度或睡眠恢复指标，或者，睡眠质量评估结果包括其它参数。
在一些实现方式中，根据历史睡眠数据的至少一部分，得到目标对象的睡眠心率变异性(Heart Rate Variability，HRV)数据；基于目标对象的睡眠HRV数据，得到目标对象的睡眠恢复指标。
在一些实现方式中，可以确定目标对象的睡眠恢复指标的具体数值。或者，也可以确定目标对象的睡眠恢复指标的量化表征，以降低算法复杂度。例如，可以确定目标对象的睡眠恢复度是否达标，再例如，可以确定目标对象的睡眠恢复度的等级，例如好、中、差，等等，本申请实施例对睡眠恢复指标的具体实现不做限定。
历史睡眠数据可以包括睡眠监测过程中得到的心率数据，目标对象的睡眠HRV数据可以是通过对历史睡眠数据中包括的心率数据进行处理得到的。睡眠HRV数据可以包含较短时间间隔和/或较长时间间隔的睡眠相关HRV数据。例如，目标对象的睡眠HRV数据可以包括目标对象在前一天或前几天或特定时间间隔的睡眠HRV数据。再例如，目标对象的睡眠HRV数据可以包括通过对目标对象在前一天或前几天或特定时间间隔的睡眠HRV数据进行处理得到的数据。或者，目标对象的睡眠HRV数据也可以包括多种不同时间间隔的睡眠HRV数据。
在一个例子中，目标对象的睡眠HRV数据包括下列中的至少一种：短期睡眠HRV参数、长期睡眠HRV参数、在目标时间段的前一天的睡眠HRV参数。
其中，短期睡眠HRV参数可以用于表征目标对象在较短时间间隔内的睡眠HRV的特性，例如前一周、前两周或本周内的连续几天，该短期睡眠HRV参数例如可以包括基线HRV，该短期睡眠HRV参数可以是通过对第一特定时间间隔内的睡眠心率数据或睡眠HRV数据进行处理得到的。长期睡眠HRV参数可以用于表征目标对象在更长时间间隔内的睡眠HRV的特性，例如前三周、前一个月或更长时间。该长期睡眠HRV参数例如可以包括HRV的正常波动范围。该长期睡眠HRV参数可以通过对第二特定时间间隔内的睡眠心率数据或睡眠HRV数据进行处理得到的，其中，该第二特定时间间隔的时间长度可以大于第一特定时间间隔的时间长度，且该第一特定时间间隔的时间长度可以大于目标时间段的时间长度。
在一些实现方式中，短期睡眠HRV参数可以通过对目标对象在预设的较短时间窗口内的睡眠HRV数据进行处理得到，例如，通过进行平均处理得到。作为一个例子，目标对象在当天的基线HRV可通过以下式子得到：
其中，Baseline(t)为目标对象在当天或当前时间的基线HRV，T1为预设的短期评估时间窗口，HRV(i)为第i天的睡眠HRV。
在一些例子中，短期睡眠HRV参数可以仅包括当前的基线HRV，或者短期睡眠HRV参数也可以包括至少两天的基线HRV，例如当天的基线HRV以及前一天的基线 HRV，本申请实施例对此不做限定。
在一些实现方式中，长期睡眠HRV参数可以通过对目标对象在预设的较长时间窗口内的睡眠HRV数据进行处理得到。作为一个例子，目标对象在当天或当前时间的HRV的正常波动范围可以通过以下式子得到：
其中，N_range(t)为当天的HRV的正常波动范围，T2为预设的长期评估时间窗口，σ为T2区间内的标准差，0.75为拟合参数，可以根据实际情况来调整。
在一些实现方式中，可以以长期睡眠HRV参数作为参照，结合目标对象的短期睡眠HRV参数以及前一天的睡眠HRV中的至少一种，来确定目标对象的睡眠恢复指标。
作为一个例子，可以通过将目标对象前一天的睡眠HRV以及目标对象当天的短期睡眠HRV参数中的至少一项与长期睡眠HRV参数进行比较，来得到目标对象的睡眠恢复指标。例如，如果目标对象前一天的睡眠HRV以及当天的基线HRV均在正常波动范围内，则可以确定目标对象的睡眠恢复指标为第一数值，或者确定睡眠恢复度达标。再例如，如果目标对象前一天的睡眠HRV不在正常波动范围内，则确定目标对象的睡眠恢复指标为小于第一数值的第二数值，或者确定睡眠恢复指标不达标。再例如，如果目标对象当天的基线HRV超过正常波动范围的上限，则确定目标对象的睡眠恢复指标为第一数值，或确定睡眠恢复度达标。再例如，如果目标对象当天的基线HRV小于正常波动范围的下限，则确定目标对象的睡眠恢复指标为第二数值，或者确定睡眠恢复度不达标。
作为另一个例子，可以通过分析目标对象的短期睡眠HRV参数的变化，例如至少两天的基线HRV的变化，来确定目标对象的睡眠恢复指标。例如，如果目标对象当天的基线HRV大于或等于目标对象前一天的基线HRV，则确定目标对象的睡眠恢复指标的数值为第一数值，或者确定睡眠恢复度达标。
作为另一个例子，可以结合以上实现方式中的至少两种来得到目标对象的睡眠恢复指标。例如，如果目标对象前一天的睡眠HRV不在正常波动范围，但当天的基线HRV超过正常波动范围的上限，则确定目标对象的睡眠恢复指标为第一数值，或确定睡眠恢复度达标。再例如，如果目标对象前一天的睡眠HRV不在正常波动范围但当天的基线HRV大于前一天的基线HRV，则确定目标对象的睡眠恢复指标为第一数值，或确定睡眠恢复度达标，等等，本申请实施例对确定目标对象的睡眠恢复指标的实现方式不做限定。
在一些实施例中，可以利用目标对象的睡眠恢复指标和运动评估结果中的至少一项来确定目标推荐运动量。例如，如果目标对象本周的运动总量未达标，例如，本周已经进行的实际运动总量小于本周的推荐运动总量，且睡眠恢复指标指示睡眠恢复度较好，例如，睡眠恢复指标为第一数值，则将初始推荐运动量调整至目标对象的最低运动量，其中，该目标对象的最低运动量可以基于目标对象的属性信息、历史运动数据和运动偏好信息中的至少一种来确定。再例如，如果目标对象本周的运动总量未达标，且睡眠恢复指标指示睡眠恢复度较差，例如睡眠恢复指标为第二数值，则不对初始推荐运动量进行调整。再例如，如果目标对象本周的运动总量已达标，但运动量达标频次较低，例如运动量达标频次未达到预设频次阈值，则可以将推荐运动量调整至目标对象的最低运动量。再例如，如果目标对象的运动总量已达标，且运动量达标频次较高，例如运动量达标频次达到预设频次阈值，则可以将推荐运动量调整为0或其它预设数值，例如目标对象预先设置的数值。
在S404中，输出目标运动推荐结果的相关信息。
在一些实施例中，可以仅输出该目标推荐运动量。在一个例子中，如初始推荐运动量不同于目标推荐运动量，也可以同时输出初始推荐运动量的信息和目标推荐运动量的信息，并指示用户是否同意对推荐运动量的调整，或者指示用户在初始推荐运动量和目 标推荐运动量中进行选择，本申请实施例对此不做限定。
在本申请的另一些实现方式中，可以确定目标时间段的初始运动推荐结果，并根据历史睡眠数据的至少一部分和历史运动数据中的第二历史运动数据，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
在一些例子中，可以参照上文实施例，根据第一历史运动数据，确定目标时间段的初始运动推荐结果。作为一个例子，可以根据至少一个历史运动推荐周期内与所述目标时间段对应的时间段的第一历史运动数据，得到目标时间段的初始运动推荐结果。例如，将对应时间段的第一历史运动数据中包括的实际运动时间和实际运动量分别作为初始推荐运动时间和初始推荐运动量。
在另一些例子中，可以根据第一历史运动数据以及目标对象的生理数据测量结果，确定目标时间段的初始运动推荐结果。例如，可以根据目标对象的生理数据测量结果，得到目标对象当前的生理状态，并根据目标对象当前的生理状态，确定目标时间段的初始推荐运动量和/或初始推荐运动时间。
在另一些例子中，可以根据用户输入信息，确定目标时间段的初始运动推荐结果。例如，用户输入某一天或某一周的运动计划，此时，可以根据用户输入的运动计划，确定目标时间段的初始运动推荐结果。
在另一些例子中，可以根据前一时间段、前几个时间段或至少一个历史运动推荐周期等时间间隔的历史运动推荐信息，确定目标时间段的初始运动推荐结果。例如，根据至少一个历史运动推荐周期(例如前一周或前几周)中与目标时间段对应的时间段(例如星期几)的推荐运动时间和/或推荐运动量，确定目标时间段的初始运动推荐结果。作为一个例子，可以将对应的时间段的推荐运动时间作为目标时间段的初始推荐运动时间，将对应的时间段的推荐运动量作为目标时间段的初始推荐运动量，或者在对应的时间段的推荐运动量的基础上进行一定量的调整，例如根据目标对象当前的生理状态对对应的时间段的推荐运动量进行一定量的调整，得到目标时间段的初始推荐运动量。作为另一个例子，可以结合历史运动推荐信息和第一历史运动数据，得到目标时间段的初始运动推荐结果。例如，根据第一历史运动数据，对历史运动推荐信息进行调整处理，得到目标时间段的初始运动推荐结果。
在另一些例子中，可以根据目标对象的属性信息，例如基本信息，目标对象所属的用户群体、目标对象的睡眠类型、目标对象所属的睡眠群体等一种或多种信息，得到初始运动推荐结果。例如，基于目标对象所属的睡眠群体或目标对象的睡眠类型以及运动生理学知识，得到某一天或某一周中每一天的初始运动推荐结果。
在另一些例子中，可以结合以上可能实现方式示例中的任意两种以上实现方式，得到目标时间段的初始运动推荐结果。
在目标时间段到来时或到来前，可以根据临近目标时间段的至少一天的睡眠数据和临近目标时间段的至少一天的运动数据，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。例如，可以根据当前运动推荐周期内的至少一天的运动数据和目标时间段的前一天的睡眠数据，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。其具体实现方式参照上文实施例，这里不再赘述。
在一些例子中，可以根据目标对象的属性信息、目标对象的运动偏好信息、运动先验信息、目标对象的历史运动数据以及目标对象的生理数据测量结果中的至少一种，得到目标对象在多个运动推荐周期的第一运动推荐，不同运动推荐周期的第一运动推荐可以相同，或者以一定步长变化等等。每个运动推荐周期的第一运动推荐可以包括该运动推荐周期包括的多个时间段的第一运动推荐结果，或者可以仅包含该运动推荐周期的总运动推荐而不进行各个时间段的划分。作为一个可选例子，可以对该第一运动推荐进行第一调整处理，在每个运动推荐周期到来前或到来时，可以根据在该运动推荐周期之前的至少一个历史运动推荐周期的历史运动数据，对该运动推荐周期的第一运动推荐进行 调整处理，或对该运动推荐周期中至少一个时间段的第一运动推荐结果进行调整处理，得到该运动推荐周期的第二运动推荐。该第二运动推荐可以包括运动推荐周期包括的多个时间段的第二运动推荐结果。作为另一个可选例子，可以对该第二运动推荐进行第二调整处理，在该运动推荐周期的每个时间段到来前或到来时，可以基于该运动推荐周期中的至少一个历史时间段(即已经经过的至少一个时间段)的历史运动数据和/或历史睡眠数据，对该时间段的第二运动推荐结果进行调整处理，得到该时间段的第三运动推荐结果。最后，向用户提供该时间段的第三运动推荐结果。作为一个例子，某个时间段的第一运动推荐结果可以为该时间段的初始运动推荐结果，第二运动推荐结果可以为该时间段的目标运动推荐结果。作为另一个例子，某个时间段的第二运动推荐结果可以为该时间段的初始运动推荐结果，第三运动推荐结果可以为该时间段的目标运动推荐结果。作为另一个例子，某个时间段的第一运动推荐结果可以为该时间段的初始运动推荐结果，该时间段的第三运动推荐结果可以为该时间段的目标运动推荐结果，本申请实施例对此不做限定。
请参见图5，图5是本申请实施例提供的一种示例性运动量推荐方案的示意图。
在S501中，可以对目标对象进行运动监测，得到目标对象的运动数据。
可以通过可穿戴设备或其它类型的终端设备的一个或多个传感器对目标对象进行运动监测，得到目标对象的运动数据，例如心率数据、加速度数据、位置、运动类型、运动强度、运动开始时间、运动结束时间等一种或多种。
在S502中，可以对目标对象进行睡眠监测，得到目标对象的睡眠数据。
例如，可以通过可穿戴设备或其它类型的终端设备的一个或多个传感器，或通过设置在床上的睡眠监测器，对目标对象进行睡眠监测，得到目标对象的睡眠数据，该睡眠数据可以包括睡眠开始时间、睡眠结束时间、睡眠分期数据、睡眠心率、睡眠呼吸数据等一种或任意多种。
在S503中，可以根据目标对象的运动数据，利用运动推荐模型得到目标对象的初始推荐运动量。
例如，基于目标对象在至少一个历史运动推荐周期(例如前几周或其它时间长度)的运动数据，得到目标对象在当前运动推荐周期(例如一周或其它时间长度)中每天的初始推荐运动量。
在S504中，可以根据目标对象的运动数据，进行运动量达标频次检测，得到目标对象的运动量达标频次。
例如，利用目标对象在当前运动推荐周期内的运动数据，得到目标对象当前的运动量达标频次。
在S505中，可以基于目标对象的睡眠数据，利用睡眠恢复评估模型得到目标对象当前的睡眠恢复指标。
例如，可以基于目标对象在前一段时间(例如前一天、前一周或特定时间长度)的睡眠数据，得到目标对象当前的睡眠恢复指标。
在S506中，基于目标对象当前的运动量达标频次和睡眠恢复指标中的至少一种，利用动态调整策略对目标时间段的初始推荐运动量进行调整处理，得到目标时间段的目标推荐运动量。
作为一个例子，可以根据睡眠恢复指标确定是否调整初始推荐运动量。例如，如果睡眠恢复指标达到预设指标阈值，则不对初始推荐运动量进行调整，即目标推荐运动量为初始推荐运动量。再例如，如果睡眠恢复指标未达到预设指标阈值，则确定调整初始推荐运动量，此时，可以直接将初始推荐运动量调整为最低运动量或0，或者结合运动量达标频次确定目标推荐运动量。例如，如果运动量达标频次达到预设频次阈值，则将初始推荐运动量调整为0。再例如，如果运动量达标频次未达到预设频次阈值，则将初始推荐运动量调整为最低运动量。
通过本申请实施例，可以确定目标对象的初始推荐运动量，并根据目标对象当前的运动和睡眠情况中的至少一项对初始推荐运动量进行动态调整，从而帮助目标对象保持科学且规律的运动习惯，为目标对象运动能力的提升以及主动健康目标的达成建立基础。
通过以上实施例可以看出，本申请的运动推荐方法，可以向目标对象提供适宜的运动建议，帮助目标对象进行科学的运动以产生助眠作用，从而提升夜间睡眠质量；同时，良好的夜间睡眠质量也能够增加目标对象白天的活动意愿，从而使目标对象更容易接受运动建议。最终，当目标对象的夜间睡眠质量能够维持较高水平时，目标对象的主动健康目标也将更容易达成。
请参见图6，图6是本申请实施例提供的一种示例性运动建议方案的示意图。
如图6所示，该运动建议方案基于运动与睡眠之间的双向影响。在S601中，通过可穿戴设备等终端设备对目标对象进行运动监测，得到目标对象的运动数据。在S602中，通过可穿戴设备等终端设备对目标对象进行睡眠监测，得到目标对象的睡眠数据。
在S603和S606中，可以基于目标对象的运动数据，分别确定目标对象的候选运动量和候选运动时间。例如，可以基于目标对象在之前的第一特定长度的时间间隔内的运动数据，得到目标对象的候选运动量，并基于目标对象在之前的第二特定长度的时间间隔内的运动数据，得到目标对象的候选运动时间，其中，在确定候选运动量和候选运动时间时所依赖的运动数据可以是相同时间间隔的，也可以是不同时间间隔的，例如，第一特定长度可以短于第二特定长度，但本申请实施例不限于此。
在S604和S605中，可以基于目标对象的睡眠数据，分别确定目标对象的睡眠开始时间和睡眠恢复指标。例如，可以基于目标对象在之前的特定长度的一段时间间隔内的睡眠数据，确定目标对象当前的睡眠恢复指标，该特定长度可以与用于确定候选运动量或候选运动时间的时间间隔的长度相同，也可以不同。再例如，基于目标对象的前一天或前几天或前几周的睡眠数据，确定目标对象的睡眠开始时间(例如入睡时间或上床睡觉时间)。
在S607中，可以基于目标对象的候选运动量以及当前的睡眠恢复指标，确定目标时间段的目标运动量。
例如，可以基于目标对象当前的睡眠恢复指标从多个候选运动量中选择其中至少一个候选运动量作为目标运动量。再例如，可以基于当前的睡眠恢复指标对候选运动量进行调整处理，得到目标运动量。
在S608中，可以基于目标对象的候选运动时间以及睡眠开始时间，确定目标对象的目标运动时间。
例如，可以基于目标对象的睡眠开始时间从多个候选运动时间中选择其中至少一个候选运动时间，作为目标运动时间。再例如，可以基于目标对象的睡眠开始时间对候选运动时间进行调整处理，得到目标运动时间，其中，该调整处理可以是限缩、删减、增加或移位等。
在S609中，可以输出针对目标时间段的运动建议，该运动建议可以指示目标对象在目标时间段的目标运动时间和目标运动量，例如，可以向可穿戴设备发送该运动建议的相关信息，也可以直接向用户输出该运动建议的相关信息，也可以向其他设备发送该运动建议的相关信息，本申请实施例对此不做限定。
在本申请的一些实施例中，还可以基于目标对象的睡眠数据，并结合目标对象的期望睡眠信息，为目标对象提供睡眠推荐。
作为一种示例，请参见图7，图7是本申请实施例提供的一种睡眠推荐方法的流程示意图。如图7所示，该方法可以包括但不限于S701至S704。
在S701中，通过终端设备获取目标对象的历史睡眠数据。
可以通过终端设备采集目标对象的历史睡眠数据，其中，终端设备可以通过运动传感器和生理传感器中的至少一种来采集睡眠数据，运动传感器例如包括加速度传感器、 陀螺仪等一种或多种传感器，生理传感器可以例如包括心率传感器、呼吸传感器、体温传感器、血压传感器等一种或多种。
历史睡眠数据可以包括目标时间段之前的一个或多个时间段的睡眠数据。作为一个例子，历史睡眠数据可以包括目标时间段之前的一天或多天的睡眠数据。例如，该历史睡眠数据包括前一天的睡眠数据。作为另一个例子，历史睡眠数据包括当前睡眠推荐周期的一天或多天的睡眠数据，例如，包括本周内且在当天之前的一天或多天的睡眠数据。作为另一个例子，历史睡眠数据包括至少一个历史睡眠推荐周期的睡眠数据，例如，包括上一周的多天的睡眠数据。作为另一个例子，历史睡眠数据可以为上文所述实施例中的历史睡眠数据，本申请实施例对此不做限定。
历史睡眠数据可以包括睡眠开始时间(即入睡时间)、睡眠结束时间(即醒来时间)、睡眠时长、醒来次数、醒来累计时长、睡眠呼吸数据、睡眠心率数据、睡眠潜伏期等中的一种或任意多种。具体实现可以参照上文实施例，这里不再赘述。
在S702中，根据目标对象的属性信息和目标对象的期望睡眠信息中的至少一种，得到目标对象的至少一个目标睡眠参数值。
在一些例子中，目标对象的属性信息包括目标对象的个人基本信息，例如年龄、性别、BMI、职业、兴趣爱好、睡眠习惯、地理位置等一项或任意多项。在另一些例子中，目标对象的属性信息可以包括其它信息，例如目标对象所属的用户群体、目标对象所属的睡眠群体或目标对象的睡眠类型等一种或任意多种，本申请实施例对此不做限定。
在一些例子中，目标对象的期望睡眠信息中包括至少一个期望睡眠参数值，即至少一个睡眠参数的期望值，例如，期望睡眠时长、期望醒来时间、期望入睡时间等一种或任意多种，或者，也可以包括其它睡眠参数的期望值。该期望睡眠信息可以是通过接收用户输入信息得到的，或者是根据目标对象所属群体的睡眠信息得到的，等等。
在另一些例子中，期望睡眠信息可以包括目标对象的睡眠改善方向，例如，睡眠时长变长，或者深度睡眠比例提高，或者睡眠潜伏期变短，等等。
目标对象的至少一个目标睡眠参数值可以包括至少一个睡眠参数的目标值，例如，目标入睡时间、目标醒来时间、目标睡眠时长等一种或任意多种。
作为一个示例，根据目标对象的属性信息，得到目标对象的至少一个目标睡眠参数值。例如，根据目标对象所属的用户群体和/或睡眠群体，得到目标对象的至少一个目标睡眠参数值。
作为另一种示例，根据目标对象的期望睡眠信息，得到目标对象的至少一个目标睡眠参数值。例如，将期望睡眠信息中包括的至少一个期望睡眠参数值确定为至少一个目标睡眠参数值。再例如，通过对期望睡眠信息中包括的至少一个期望睡眠参数进行运算处理，得到至少一个目标睡眠参数值。
作为又一种示例，根据目标对象的期望睡眠信息和目标对象的属性信息，得到目标对象的至少一个目标睡眠参数值。例如，将一部分目标睡眠参数值确定为期望睡眠信息中的期望睡眠参数值，而利用期望睡眠信息中包括的至少一个期望睡眠参数值或确定的目标睡眠参数值以及属性信息，得到另一部分目标睡眠参数值。再例如，可以设置期望睡眠信息和属性信息的权重，并根据期望睡眠信息、属性信息以及各自对应的权重，得到目标睡眠参数值。再例如，可以利用睡眠改善模型对期望睡眠信息和属性信息进行处理，得到目标睡眠参数值。再例如，可以利用其它方式得到目标睡眠参数值。
作为又一种示例，假设目标对象的属性信息和目标对象的期望睡眠信息均被获取到或两者均可用，则将目标对象的属性信息和期望睡眠信息中的其中一者作为优先考量因素，得到目标对象的至少一个目标睡眠参数值。例如，将期望睡眠信息作为优先考量因素，如果有可用的期望睡眠信息，则利用期望睡眠信息得到目标睡眠参数值，如果没有可用的期望睡眠信息，则利用属性信息得到目标睡眠参数值。再例如，将属性信息作为优先考量因素，如有可用的属性信息，则利用属性信息得到初始睡眠参数值，并利用期 望睡眠信息对初始睡眠参数值进行调整处理，得到目标睡眠参数值。
在一些实现方式中，还可以先判断期望睡眠信息的有效性，并基于有效性判断结果，来确定得到目标睡眠参数值的方式。此时，可以基于期望睡眠信息的有效性判断结果以及期望睡眠信息和属性信息中的至少一种，确定至少一个目标睡眠参数值。
在一些例子中，可以判断期望睡眠信息中包括的部分或所有期望睡眠参数值中的每个期望睡眠参数值的有效性。例如，可以确定至少一个期望睡眠参数值中的每个期望睡眠参数值的数值是否在对应的预设数值范围内，其中，不同的期望睡眠参数值可以设置不同的预设数值范围。如果某个期望睡眠参数值在预设数值范围内，则确定该期望睡眠参数值有效，反之则确定该期望睡眠参数值无效。其中，该预设数值范围可以根据睡眠先验知识确定，或者，该预设数值范围可以根据该目标对象的属性信息来确定，例如根据目标对象所属群体来确定。或者，该预设数值范围通过其它方式确定，这里不做限定。
此时，作为一个可选例子，响应于某个睡眠参数存在有效的期望值，即期望睡眠信息中包括与该睡眠参数对应的有效的期望睡眠参数值，则可以利用该期望睡眠参数值确定该睡眠参数的目标值，即该睡眠参数对应的目标睡眠参数值。例如，将有效的期望睡眠参数值确定为该睡眠参数对应的目标睡眠参数值，再例如，通过对有效的期望睡眠参数值进行处理来得到对应的目标睡眠参数值。
作为另一个可选例子，响应于某个睡眠参数不存在有效的期望值，即期望睡眠信息中不包含与该睡眠参数对应的有效的期望睡眠参数值，例如期望睡眠信息不包含该睡眠参数对应的期望睡眠参数值，或包括的该睡眠参数对应的期望睡眠参数值不在预设数值范围内，则可以利用目标对象的属性信息、有效的期望睡眠参数值或对应的目标睡眠参数值、以及睡眠生理学知识中的至少一种，来确定该睡眠参数对应的目标睡眠参数值。
在另一些例子中，可以判断期望睡眠信息作为一个整体的有效性。此时，期望睡眠信息有效性判断结果可以包括：期望睡眠信息有效或期望睡眠信息无效。例如，可以判断期望睡眠信息中包括的至少一个期望睡眠参数值是否有效，来判断期望睡眠信息是否有效。作为一个例子，如果期望睡眠信息中包括的所有期望睡眠参数值均无效，或者包括的无效的期望睡眠参数值的个数或比例超过一定阈值，则确定期望睡眠信息无效。再例如，判断期望睡眠信息中是否包含某个特定睡眠参数的期望值，或者期望睡眠信息中包含的某个特定睡眠参数的期望值是否有效，来判断期望睡眠信息是否有效。再例如，如果期望睡眠信息中包括多个期望睡眠参数值，则可以判断由多个期望睡眠参数值运算得到的睡眠参数值(例如睡眠时长等)是否在合理范围内，来判断期望睡眠信息是否有效。再例如，可以判断多个期望睡眠参数值是否自洽，例如，期望睡眠开始时间和期望睡眠结束时间之间的时间间隔是否等于期望睡眠时长，来判断期望睡眠信息是否有效，等等，这里对判断期望睡眠信息有效性的实现方式不做限定。
此时，作为一个可选例子，响应于期望睡眠信息的有效性判断结果指示期望睡眠信息有效，则利用该期望睡眠信息中包括的至少一个期望睡眠参数值得到至少一个目标睡眠参数值。作为另一个可选例子，响应于有效性判断结果指示期望睡眠信息无效，则利用属性信息确定至少一个目标睡眠参数值。
在一些例子中，可以基于对至少一个期望睡眠参数值的有效性判断结果，来确定至少一个目标睡眠参数值。作为一些实现方式，可以判断期望睡眠信息中是否包括某个睡眠参数对应的有效的期望睡眠参数值。如果包括该睡眠参数对应的有效的期望睡眠参数值，则可以利用该有效的期望睡眠参数值得到该睡眠参数对应的目标睡眠参数值。而如果不包括该睡眠参数对应的有效的期望睡眠参数值，则可以利用目标对象的属性信息和/或睡眠先验知识，确定该睡眠参数对应的目标睡眠参数值。
作为一个例子，目标睡眠参数值包括目标睡眠时长。此时，可以判断期望睡眠信息中是否包括有效的期望睡眠时长。如果包括有效的期望睡眠时长，则将目标对象的目标睡眠时长确定为该有效的期望睡眠时长。如果不包括有效的期望睡眠时长，例如不包括 期望睡眠时长，或包括的期望睡眠时长无效，则基于目标对象的属性信息确定目标睡眠时长。例如，基于目标对象的性别、年龄、BMI中的至少一种以及睡眠先验知识和/或预设映射规则，确定目标对象的目标睡眠时长。再例如，基于目标对象的属性信息，确定目标对象所属群体(如用户群体和/或睡眠群体)，并基于目标对象所属群体的信息，确定目标对象的目标睡眠时长。
例如，目标睡眠时长可以通过以下式子得到：
其中，TargetTST表示目标睡眠时长，TargetTSTrule表示目标对象所属群体的推荐睡眠时长；TargetTSTuser表示目标对象的期望睡眠信息中包括的期望睡眠时长。
其中，在该示例中，如果目标对象的期望睡眠时长有效，则将目标睡眠时长确定为期望睡眠时长。而如果期望睡眠时长无效，则将目标睡眠时长确定为目标对象所属群体的推荐睡眠时长。
作为另一些实现方式，如果期望睡眠信息中不包含某个睡眠参数对应的有效的期望睡眠参数值，则可以利用其它睡眠参数对应的目标睡眠参数值和/或期望睡眠信息中包括的其它睡眠参数对应的有效的期望睡眠参数值，来确定该睡眠参数对应的目标睡眠参数值。例如，可以根据目标对象的属性信息和期望睡眠信息中的至少一项，来确定多个目标睡眠参数值中的一部分参数值，而基于确定的该部分参数值以及目标对象的期望睡眠信息中的至少一种，确定目标睡眠参数值中的另一部分参数值。例如，目标期望参数值包括目标睡眠时长以及目标入睡时间(或目标睡眠开始时间)和/或目标醒来时间(或目标睡眠结束时间)，可以基于目标睡眠时长和/或期望睡眠信息中包括的有效的期望醒来时间，来确定目标入睡时间。再例如，可以基于目标睡眠时长和/或期望睡眠信息中包括的有效的期望入睡时间，来确定目标醒来时间。
例如，目标入睡时间可通过以下式子来确定：
其中，TargetST为目标入睡时间，TargetSTrule为根据目标对象的属性信息和/或睡眠先验知识确定的入睡时间，TargetSTuser为目标对象的期望入睡时间，TargetWTuser为目标对象的期望醒来时间，TargetTST为目标睡眠时长。
其中，在该示例中，如果期望睡眠信息中包括期望入睡时间，或包括有效的期望入睡时间，则将目标入睡时间确定为期望入睡时间。如果期望睡眠信息中包括期望醒来时间，或包括有效的期望醒来时间，则可以根据期望醒来时间和目标睡眠时长来确定目标入睡时间。如果期望睡眠信息中既不包括期望入睡时间或有效的期望入睡时间，也不包括期望醒来时间或有效的期望醒来时间，则根据目标对象的属性信息和/或睡眠先验知识确定目标入睡时间，例如，将目标对象的目标入睡时间确定为该目标对象所属群体的推荐入睡时间。
在一些例子中，可以利用以上式子分别确定目标睡眠时长和目标入睡时间，目标对象的目标醒来时间可以根据目标睡眠时长和目标入睡时间确定。
再例如，目标醒来时间可以通过以下式子确定：
其中，TargetSTrule为根据目标对象的属性信息和/或睡眠先验知识确定的入睡时间，TargetTST为目标睡眠时长，TargetSTuser为目标对象的期望入睡时间，TargetWTuser 为目标对象的期望醒来时间。
其中，在该示例中，如果期望睡眠信息中包括期望醒来时间或有效的期望醒来时间，则将目标醒来时间确定为期望醒来时间。如果期望睡眠信息中包括期望入睡时间或有效的期望入睡时间，则根据期望入睡时间和目标睡眠时长，得到目标醒来时间。如果目标对象的期望睡眠信息中既不包含期望入睡时间或有效的期望入睡时间，也不包括期望醒来时间或有效的期望醒来时间，则基于目标对象的属性信息和/或睡眠先验知识确定的目标入睡时间以及目标睡眠时长来确定目标醒来时间。
本领域技术人员可以理解，目标入睡时间和目标醒来时间的以上实现方式也可以互换，或通过其它方式确定，本申请实施例对此不做限定。
在S703中，基于目标对象的至少一个目标睡眠参数值以及目标对象的历史睡眠数据，得到目标对象在目标时间段的睡眠推荐结果。
在本申请的实施例中，睡眠推荐结果包括至少一个推荐睡眠参数值，例如睡眠推荐结果包括推荐入睡时间、推荐醒来时间和推荐睡眠时长中的至少一种。
该历史睡眠数据可以包括目标时间段之前的一个或多个时间段的睡眠数据，该历史睡眠数据可以用于指示目标对象近期的睡眠情况，其具体实现可以参照上文实施例。作为一个例子，该历史睡眠数据可以包括前一周、前一个月或其它时间间隔的睡眠数据，这里不做限定。
举例而言，基于目标对象的历史睡眠数据，得到目标对象的当前睡眠参数值，并基于目标对象的至少一个目标睡眠参数值，按照预设的睡眠调整策略，对目标对象的当前睡眠参数值进行调整，得到目标对象的睡眠推荐结果中包括的至少一个推荐睡眠参数值。在一个例子中，该预设的睡眠调整策略可以包括渐进式调整策略(或称为逐级调整策略)和直接调整策略(或称为单级调整策略或一步到位式调整策略)，其中，在渐进式调整策略中，可以以当前睡眠参数值作为出发点，随着时间的推移向目标睡眠参数值逐步靠近，而在直接调整策略中，可以直接将当前睡眠参数值调整为目标睡眠参数值。在另一个例子中，该预设的睡眠调整策略也可以通过其它方式实现，这里不做限定。
需要说明的是，目标时间段的具体实现可以参照上文实施例，该目标时间段的睡眠推荐结果可以包括当天、明天或下一周或目标对象设置的一定时间间隔的睡眠推荐结果。
在S704中，输出睡眠推荐结果的相关信息。
其中，S701和S702可以以任意先后顺序执行，或者同时执行。作为一个例子，可以预先执行S702并存储目标睡眠参数值，然后执行S701。即通过终端设备采集目标对象的历史睡眠数据，并获取存储的目标睡眠参数值，最后基于历史睡眠数据和目标睡眠参数值得到目标时间段的睡眠推荐结果。作为另一个例子，可以先执行S701，即通过终端设备采集目标对象的历史睡眠数据并进行存储，然后执行S702，得到目标对象的至少一个目标睡眠参数值，这里不做限定。
通过本申请实施例，可以根据目标对象的属性信息和期望睡眠信息中的至少一种，得到目标对象的至少一个目标睡眠参数值，并基于目标对象的至少一个目标睡眠参数值以及历史睡眠数据，得到目标对象的睡眠推荐结果，从而帮助目标对象循序渐进的养成科学且规律的睡眠习惯。
请参见图8，图8是本申请实施例提供的一种示例性睡眠建议方案的示意图。
在S801中，可以获取目标对象的属性信息，目标对象的属性信息包括基本信息，例如年龄、性别、BMI等信息中的一种或任意多种。
在S802中，可以基于目标对象的属性信息，确定目标对象所属群体的参考睡眠时长。
例如，可以基于目标对象的属性信息，确定目标对象所属群体，并根据目标对象所属群体，例如群体属性信息、群体中其它对象的睡眠信息等，确定参考睡眠时长。
在S803中，可以获取目标对象的主观期望信息，例如，通过用户交互操作获取目 标对象输入的主观期望信息，例如，期望入睡时间、期望睡眠时长、期望醒来时间等一项或任意多项睡眠参数的期望值。该主观期望信息可以为上文实施例中的期望睡眠信息。
在S804中，可以基于目标对象的主观期望信息和目标对象所属群体的参考睡眠时长中的至少一种，确定目标对象的睡眠目标。该睡眠目标可以包括目标入睡时间、目标醒来时间和目标睡眠时长等一项或任意多项睡眠参数的目标值。
在一些例子中，如确定主观期望信息中包含的期望睡眠时长有效，也可以不执行S802，本申请实施例对此不做限定。
在S805中，可以对目标对象进行睡眠监测，得到目标对象在预设时间间隔内的历史睡眠数据。该历史睡眠数据可以包括睡眠开始时间、睡眠结束时间、睡眠分期数据、睡眠呼吸数据、睡眠质量数据等一种或任意多种。在该示例中，该预设时间间隔可以为上一周，但本申请实施例对此不做限定。
在S806中，可以基于目标对象的睡眠目标以及目标对象在预设时间间隔内的历史睡眠数据，利用逐级调整策略，得到该目标对象在目标时间段的睡眠建议(S807)，该睡眠建议包括推荐入睡时间、推荐睡眠时长及推荐醒来时间中的一种或任意多种睡眠参数的推荐值，以帮助目标对象循序渐进的养成规律的睡眠习惯。
在一些实现方式中，根据目标对象的历史睡眠数据以及至少一个目标睡眠参数值，确定目标对象的睡眠调整策略，并根据睡眠调整策略，得到目标对象的睡眠推荐结果。
举例而言，该睡眠调整策略可以包括渐进式调整策略或直接调整策略。渐进式调整策略是对目标对象的睡眠参数进行较小幅度的逐步调整。而直接调整策略是一次性将目标对象的睡眠参数调整至目标睡眠参数值。
在一些例子中，可以基于历史睡眠数据指示的至少一个当前睡眠参数值与至少一个目标睡眠参数值之间的差异，确定目标对象的睡眠调整策略。作为一个例子，如历史睡眠数据指示的某个当前睡眠参数值与对应的目标睡眠参数值之间的差异较小，例如差异在预设差异范围内，则可以采取直接调整策略。作为另一个例子，如历史睡眠数据指示的某个当前睡眠参数值与对应的目标睡眠参数值之间的差异较大，例如差异超过预设差异范围，则可以采取渐进式调整策略，让目标对象的睡眠参数循序渐进地达到睡眠目标。
在一些实现方式中，可以对目标对象的历史睡眠数据进行处理，例如统计处理，得到目标对象的至少一个当前睡眠参数值。例如，可以通过对目标对象在一定时间间隔内的历史睡眠数据进行处理，得到目标对象在该时间间隔内的平均睡眠时长，其中，该平均睡眠时长可以是通过对该时间间隔内多天的睡眠时长进行平均处理得到的，例如，多天的睡眠时长的平均值，或者是滤除多天的睡眠时长中的最大值、最小值或异常值之后进行平均处理得到的，或者是对出现频率超过一定阈值的睡眠时长进行统计处理得到的，等等，本申请实施例对此不做限定。
作为一个例子，响应于目标对象的历史睡眠数据指示的至少一个当前睡眠参数值与至少一个目标睡眠参数值之间的差异超过预设差异范围，则基于调整步长和至少一个当前睡眠参数值，得到目标对象的睡眠推荐结果。
例如，以调整步长对当前睡眠参数值进行调整，得到睡眠推荐结果中包括的推荐睡眠参数值，以使得睡眠推荐结果中包括的推荐睡眠参数值随着时间推移逐步向目标睡眠参数值靠近。此时，可以采用渐进式调整策略对当前睡眠参数值进行调整。
该调整步长可以是预设的。或者，该调整步长可以根据目标对象的属性信息得到，例如，根据目标对象所属群体得到。或者，该调整步长可以根据当前睡眠参数值和目标睡眠参数值之间的差异得到，例如，基于该差异以及达成睡眠目标的预设时间间隔得到调整步长。或者，该调整步长是根据用户输入信息确定的，等等，这里对调整步长的实现方式不做限定。
作为另一个例子，响应于目标对象的历史睡眠数据指示的至少一个当前睡眠参数值与至少一个目标睡眠参数值之间的差异在所述预设差异范围内，则确定目标对象的睡眠 推荐结果中包括的推荐睡眠参数值为目标睡眠参数值。此时，可以采用直接调整策略对当前睡眠参数值进行调整。
在一个例子中，该至少一个当前睡眠参数值与至少一个目标睡眠参数值之间的差异可以包括至少一个当前睡眠参数值中每个当前睡眠参数值与对应的目标睡眠参数值之间的差异值，此时，该至少一个当前睡眠参数值与至少一个目标睡眠参数值之间的差异在预设差异范围内可以指每个差异值均在对应的预设差异范围内，或者指在对应的预设差异范围内的差异值的比例超过一定数值，或者指差异值的统计值在预设差异范围内，等等。或者，该至少一个当前睡眠参数值与至少一个目标睡眠参数值之间的差异包括某个当前睡眠参数值与对应的目标睡眠参数值之间的差异值。或者，该至少一个当前睡眠参数值与至少一个目标睡眠参数值之间的差异包括至少一个当前睡眠参数值与至少一个目标睡眠参数值之间的至少一个差异值的统计信息，例如最大差异、最小差异或平均差异等等，这里对具体实现方式不做限定。
在一个例子中，假设历史睡眠数据包括上一周的睡眠数据，且目标时间段的睡眠推荐结果包括本周的推荐入睡时间以及推荐睡眠时长，则本周的推荐睡眠时长可以通过以下式子得到：
其中，TSTrecommend(W)为本周的推荐睡眠时长，C5为睡眠时长对应的预设差异范围，ΔTST为睡眠时长对应的调整步长，例如：二十分钟，TST(w-1)为目标对象在上一周的平均睡眠时长。
在该示例中，将目标对象在上一周的平均睡眠时长作为目标对象的当前睡眠时长。如果目标对象在上一周的平均睡眠时长与目标睡眠时长之间的差异小于或等于C5，则采取直接调整策略，将本周的推荐睡眠时长直接确定为目标睡眠时长。而如果目标对象在上一周的平均睡眠时长与目标睡眠时长之间的差异大于C5，则采取渐进式调整策略，将本周的推荐睡眠时长确定为上一周的平均睡眠时长以ΔTST为单位增加或减少。调整步长ΔTST可以是预先设置的固定值，或者基于目标对象的期望确定，或者基于目标对象的属性信息确定，等等。在一个例子中，睡眠时长对应的调整步长ΔTST可以等于睡眠时长对应的预设差异范围C5。在其它例子中，睡眠时长对应的调整步长ΔTST也可以设置为不同于睡眠时长对应的预设差异范围C5的其它数值，本申请实施例对此不做限定。
在另一个例子中，本周的推荐入睡时间可以通过以下式子得到：
其中，STrecommend(w)为本周的推荐入睡时间，ST(w-1)为目标对象在上一周的平均入睡时间，ΔST为入睡时间对应的调整步长，C6为入睡时间对应的预设差异范围。
在该示例中，将目标对象的当前入睡时间确定为目标对象在上一周的平均入睡时间。如果目标对象在上一周的平均入睡时间与目标入睡时间之间的差异小于或等于C6，则采取直接调整策略，将本周的推荐入睡时间直接确定为目标入睡时间。而如果目标对象在上一周的平均入睡时间与目标入睡时间之间的差异大于C6，则采取渐进式调整策略，将本周的推荐入睡时间确定为上一周的平均入睡时间以ΔST为单位增加或减少。调整步长ΔST可以是预先设置的固定值，或者基于目标对象的期望确定，或者基于目标对象的属性信息确定，等等。在一个例子中，入睡时间对应的调整步长ΔST可以等于入睡时间对应的预设差异范围C6。在其它例子中，入睡时间对应的调整步长ΔST也可以设置为不同于入睡时间对应的预设差异范围C6的其它数值，本申请实施例对此不做限定。
在本申请实施例的一些实现方式中，还可以对目标对象的补充睡眠进行指导。可以基于终端设备采集的目标对象的历史睡眠数据，得到目标对象在目标时间段的补充睡眠推荐结果。该补充睡眠推荐结果可以包括推荐目标对象进行或不进行补充睡眠，或者包 括目标对象进行补充睡眠的推荐时长、最长睡眠时长、最晚醒来时间或最晚睡眠时间，等等，本申请实施例对此不做限定。
这里的常规睡眠可以指目标对象进行的较长时间的睡眠，例如夜间睡眠，而补充睡眠可以指目标对象进行的较短时间的睡眠，例如日间小睡或午睡。
在一些实现方式中，可以根据前一天的睡眠数据，或者根据本周已经经过的一天或多天的睡眠数据，得到目标时间段的补充睡眠推荐结果。
在一些例子中，可以通过测量目标对象在常规睡眠期间的生理数据及体动数据，得到目标对象在前一天的常规睡眠数据，例如常规睡眠时长、常规睡眠质量评估、常规睡眠分期数据等，并基于该常规睡眠数据，得到目标对象在目标时间段的补充睡眠推荐结果。作为一个例子，如果前一天的常规睡眠时长小于预设时长阈值，则可以推荐目标对象在目标时间段进行补充睡眠，此时，该补充睡眠推荐结果可以包括推荐进行补充睡眠的第一指示符，或者补充睡眠推荐结果包括的补充睡眠推荐时长为大于零的第一时长。作为另一个例子，如果前一天的常规睡眠时长等于或大于预设时长阈值，则可以推荐目标对象在目标时间段不进行补充睡眠，此时，该补充睡眠推荐结果可以包括推荐不进行补充睡眠的第二指示符，或者补充睡眠推荐结果包括的补充睡眠推荐时长为零。作为另一个例子，如果前一天的常规睡眠时长等于或大于预设时长阈值，则可以根据目标对象的历史睡眠数据中包括的历史补充睡眠数据，来确定是否推荐在目标时间段进行补充睡眠。例如，如果目标对象的历史补充睡眠数据指示目标对象有补充睡眠的习惯，则可以推荐目标对象在目标时间段进行补充睡眠，而如果目标对象的历史补充睡眠数据指示目标对象没有补充睡眠的习惯，则可以推荐目标对象在目标时间段不进行补充睡眠。
该预设时长阈值可以为预设的固定值，例如8小时，或者根据目标对象的历史睡眠数据来确定，例如目标对象的常规睡眠平均时长，或者根据目标对象的期望睡眠信息或睡眠目标来确定，这里不做限定。
在另一些例子中，可以根据目标对象在前一天的常规睡眠质量评估结果来确定是否推荐在目标时间段进行补充睡眠，例如，可以根据目标对象的睡眠恢复指标来确定是否推荐在目标时间段进行补充睡眠，或者通过其它类型的历史睡眠数据来确定是否推荐在目标时间段进行补充睡眠，这里不做限定。
在一些例子中，在推荐进行补充睡眠的情况下，还可以确定补充睡眠推荐时长。该补充睡眠推荐时长可以是预设的，如30分钟或不超过1个小时。或者，该补充睡眠推荐时长可以结合目标对象的主观期望信息以及前一天的常规睡眠时长来确定。或者，该补充睡眠推荐时长可以根据目标对象的历史睡眠数据中包括的历史补充睡眠数据来确定，例如上一周的补充睡眠平均时长。或者，该补充睡眠推荐时长可以根据目标对象的属性信息来确定，等等。
作为一个例子，目标时间段的补充睡眠推荐时长可以通过以下式子确定：
其中，Naprecommend(t)为目标时间段的补充睡眠推荐时长，TST(t-1)为目标对象在前一天的常规睡眠时长，TSTthreshold为睡眠时长阈值，C7为第一时长，可以为预先设置的固定值，或者根据目标对象的属性信息得到，或者根据目标对象的历史睡眠数据得到。
在另一些例子中，根据目标对象前一天的常规睡眠数据和前一天的补充睡眠数据中的至少一种，得到目标对象的补充睡眠推荐结果。
在另一些例子中，在推荐目标对象在目标时间段进行补充睡眠的情况下，补充睡眠推荐结果还可以包括补充睡眠时长提醒，例如不要补充睡眠过长时间，或者请在补充睡眠前设置闹钟，等等，以避免目标对象补充睡眠过长时间而影响接下来的常规睡眠或日间精神状态。
作为一个例子，可以基于目标对象的历史睡眠数据，得到目标对象的补充睡眠时长提醒。例如，可以基于历史睡眠数据中的历史补充睡眠数据，确定是否生成补充睡眠时长提醒。例如，响应于历史补充睡眠数据指示目标对象在前一天的补充睡眠时长超过推荐时长，生成补充睡眠时长提醒，以提醒目标对象在目标时间段的补充睡眠时长不要超过推荐时长。
例如，可以通过以下方式得到补充睡眠时长提醒。
其中，Nap Warning(t)＝True代表生成补充睡眠时长提醒，Nap Warning(t)＝False代表不生成补充睡眠时长提醒，Naprecommend为补充睡眠推荐时长，Nap′(t)为目标对象在前一天的补充睡眠时长。
在该示例中，响应于目标对象的历史补充睡眠数据指示目标对象在前一天的补充睡眠时长超过推荐时长，输出提醒目标对象适当调整补充睡眠时长的补充睡眠时长提醒；否则，不输出补充睡眠时长提醒。
请参见图9，图9是本申请实施例提供的一种示例性补充睡眠建议方案的示意图。
在S901中，可以获取目标对象的历史运动数据，例如，前一天的活动量数据。
在S902中，可以获取目标对象的历史补充睡眠数据，例如，前一天的日间小睡数据。
在S903中，可以获取目标对象的历史常规睡眠数据，例如，前一天的夜间睡眠数据。
在S904中，可以结合以上步骤中得到的数据，得到目标对象的补充睡眠建议。
作为一个例子，可以监测目标对象在前一天的补充睡眠时长，如果前一天的补充睡眠时长大于预设时长阈值，或者大于补充睡眠推荐时长，还可以在补充睡眠建议中进行补充睡眠时长提醒，以避免目标对象在目标时间段补充睡眠过长时间。
通过本申请实施例，可以基于目标对象的历史睡眠数据，得到目标对象的补充睡眠推荐结果，从而避免目标对象由于夜间睡眠不佳而造成日间精力不济，同时避免较长的补充睡眠对健康产生的不利影响，为目标对象的主动健康目标的达成建立基础。
在本申请的一些实施例中，还可以通过向目标对象提供合适的睡眠认知信息，进一步提升目标对象的睡眠健康。
请参见图10，图10是本申请实施例提供的一种示例性睡眠建议方案的示意图。其中，在S1001中，可以基于目标对象的属性信息从CBT-I(Cognitive Behavioral Therapy for Insomnia，认知行为治疗失眠疗法)睡眠认知知识库获取目标对象对应的睡眠认知知识。
在S1002中，根据获取到的睡眠认知知识，得到针对目标对象的饮食习惯建议。
在S1003中，根据获取到的睡眠认知知识，得到针对目标对象的睡眠环境建议。
在S1004中，根据获取到的睡眠认知知识，得到针对目标对象的身心放松建议。
在S1005中，将S1002-S1004中得到的至少一项建议推送给目标对象。
举例而言，睡眠认知信息可以包括饮食建议、睡眠环境建议和身心放松建议中的至少一种。其中，饮食建议例如可以包括：如果您对于咖啡/茶等兴奋性饮品比较敏感，要避免在下午两时后再饮用这些饮品。例如，睡眠环境建议可以包括：合适的温度能让人更快的入睡，卧室温度一般应该偏低，控制在21～24度左右。再例如，睡眠环境建议可以包括：最合适的被窝温度比人体体表温度高1～2度。身心放松建议例如可以包括：睡前可以做一些让自己安静放松的事情，比如冥想、读书等。
这些睡眠认识信息可以是通用性的，也可以是基于目标对象的特性确定的，例如基于目标对象的属性信息，例如年龄、性别、兴趣爱好、生活习惯等一种或多种，或基于目标对象的当前健康状态，如睡眠类型、运动习惯类型、疾病信息等一种或多种，或基 于对目标对象的历史监控信息，例如超过预设时间进行咖啡摄入、睡眠环境温度过高、临睡前的压力较大等一种或多种，本申请实施例对此不做限定。
通过实施本申请实施例，可以为目标对象提供睡眠认知信息，以进一步帮助目标对象提升睡眠质量，从而帮助目标对象养成健康的睡眠习惯。
在一些实施例中，电子设备可以基于目标对象的历史睡眠数据和历史运动数据，同时进行运动推荐和睡眠推荐。
请参见图11，图11是本申请实施例提供的一种示例性健康指导系统的示意图。如图11所示，该健康指导系统主要包括睡眠评估模块1101、数据测量模块1102和睡眠改善模块1103这三个模块。
睡眠评估模块1101可以对目标对象的睡眠质量进行评估，例如，可以根据数据测量模块1102测量得到的睡眠数据，得到目标对象的睡眠质量评估结果和/或至少一个当前睡眠参数值，以指示目标对象的当前睡眠情况。
数据测量模块1102可以对目标对象的数据进行测量和处理。例如，通过终端设备对目标对象的睡眠(如常规睡眠和/或补充睡眠)、运动、生理参数等数据进行收集和处理。
睡眠改善模块1103可以根据目标对象的当前生理或睡眠状态以及当前存在的睡眠问题或期望改善的睡眠问题，计算出达成睡眠目标的路径，并得到睡眠改善建议。
作为一个例子，该睡眠改善建议可以包括运动建议、常规睡眠建议、补充睡眠建议和睡眠认知建议中的一种或任意多种。
作为一个例子，该睡眠改善建议可以包括上文实施例中所述的目标运动推荐结果。
作为另一个例子，该睡眠改善建议可以包括上文实施例中所述的睡眠推荐结果。
作为另一个例子，该睡眠改善建议可以包括目标运动推荐结果和睡眠推荐结果。
由此可见，本申请在主动健康管理的架构下，将运动与睡眠一起形成一个主动健康指导的闭环。以目标对象的历史运动和睡眠数据作为基础，结合以睡眠领域中的先验知识，为目标对象达到更好的健康目标，提供具有操作性的改善方案。
请参见图12，图12是本申请实施例提供的一种运动推荐装置1200的示意图。如图12所示，该装置1200包括：获取模块1201，用于通过终端设备获取目标对象的历史睡眠数据和历史运动数据，历史睡眠数据包括在目标时间段之前的至少一天的睡眠数据，历史运动数据包括在目标时间段之前的至少一天的运动数据；处理模块1202，用于根据历史睡眠数据和历史运动数据，得到目标对象在目标时间段的目标运动推荐结果，目标运动推荐结果包括目标推荐运动时间和目标推荐运动量中的至少一种；输出模块1203，用于输出目标运动推荐结果的相关信息。
在一些实施例中，将执行该处理的时间称为当天，目标对象在目标时间段的目标运动推荐结果包括目标对象在接下来的一天的目标运动推荐结果，例如，当天的目标运动推荐结果，或者明天的目标运动推荐结果。
在一些实施例中，处理模块1202用于：根据历史运动数据中包含的至少一部分历史运动时间数据，确定候选运动时间集合，所述候选运动时间集合包括至少一个候选运动时间；根据历史睡眠数据，从候选运动时间集合中确定目标推荐运动时间。
该候选运动时间集合可以包括一个或多个候选运动时间。可以根据历史运动数据中包括的部分或全部历史运动时间数据来确定一个或多个候选运动时间。例如，可以将历史运动时间数据中包括的所有运动时间作为候选运动时间。或者，也可以将历史运动时间数据中包括的所有运动时间中满足一定条件的运动时间作为候选运动时间，例如将历史运动时间数据中出现的次数达到一定阈值的运动时间作为候选运动时间，等等。或者，候选运动时间是通过对部分或全部历史运动时间数据进行处理后得到的。
在一些实施例中，处理模块1202用于：确定目标对象的睡眠类型；从多个预设的运动时间偏移量中，确定出与目标对象的睡眠类型对应的运动时间偏移量；根据对应的 运动时间偏移量和历史睡眠数据中包括的至少一部分历史睡眠开始时间数据，从候选运动时间集合中确定目标推荐运动时间。
在一些实现方式中，目标对象的睡眠类型可以包括以下中的一种：早睡型、晚睡型、早起型、晚起型、睡眠障碍型。
在一些实施例中，处理模块1202用于：根据历史睡眠数据中包括的至少一部分历史睡眠开始时间数据以及与目标对象的睡眠类型对应的运动时间偏移量，确定运动时间要求；将候选运动时间集合中满足运动时间要求的至少一个候选运动时间确定为目标推荐运动时间。
在一些实施例中，处理模块1202用于：根据历史睡眠数据，从候选运动时间集合中选择多个候选推荐运动时间，然后输出提示信息，以提示从多个候选推荐运动时间中选择，并基于接收到的用户输入信息确定目标推荐运动时间。
在一些实施例中，处理模块1202用于：根据历史睡眠数据，从候选运动时间集合中选择多个候选推荐运动时间；根据历史运动数据，确定目标对象在多个候选推荐运动时间中每个候选推荐运动时间的运动频次；根据目标对象在多个候选推荐运动时间中每个候选推荐运动时间的运动频次，从多个候选推荐运动时间中确定目标推荐运动时间。
在一些实施例中，处理模块1202用于：根据历史运动数据中的第一历史运动数据，确定目标时间段的初始运动推荐结果，并根据历史睡眠数据的至少一部分，对初始运动推荐结果进行调整处理，得到目标时间段的目标运动推荐结果。
在一些实施例中，处理模块1202用于：根据目标对象的生理数据测量结果，确定目标时间段的运动推荐策略；基于目标时间段的运动推荐策略以及第一历史运动数据，确定目标时间段的初始运动推荐结果。
在一些实施例中，处理模块1202用于：根据历史睡眠数据的至少一部分，得到目标对象在临近目标时间段的至少一天的睡眠质量评估结果；基于睡眠质量评估结果，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
在一些实施例中，处理模块1202还用于：根据目标对象的历史睡眠数据的至少一部分以及历史运动数据中的第二历史运动数据，对初始运动推荐结果进行调整处理，得到目标运动推荐结果，其中，第二历史运动数据包括当前运动推荐周期内且在目标时间段之前的至少一天的运动数据。
在一些实施例中，处理模块1202还用于：根据目标对象的历史睡眠数据的至少一部分，得到目标对象在目标时间段之前的至少一天的睡眠质量评估结果，根据睡眠质量评估结果以及第二历史运动数据，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
在一些实现方式中，处理模块1202还用于：根据第二历史运动数据，得到目标对象的运动评估结果，运动评估结果用于指示目标对象在临近目标时间段的至少一天的运动量达标情况；根据运动评估结果和睡眠质量评估结果，对初始运动推荐结果进行调整处理，得到目标运动推荐结果。
运动评估结果包括运动量达标频次和运动总量达标指示中的至少一项，运动总量达标指示可以用于指示目标对象在临近目标时间段的至少一天内的运动总量是否达标，运动量达标频次可以用于指示所述至少一天内运动量达标的频次，例如，运动量达标的天数在所述至少一天对应的总天数中所占的比例。
在一些实现方式中，第二历史运动数据包括临近目标时间段的至少一天中每天的实际运动量。运动评估结果用于指示运动量达标情况。
在一些实现方式中，处理模块1202还用于：根据临近目标时间段的至少一天中每天的实际运动量以及所述至少一天对应的推荐运动信息，得到运动评估结果。
在一些实现方式中，睡眠质量评估结果包括睡眠恢复指标；处理模块1202用于：根据历史睡眠数据的至少一部分，得到目标对象的睡眠心率变异性数据；基于目标对象 的睡眠心率变异性数据，得到目标对象的睡眠恢复指标。
在一些实现方式中，本申请实施例提供的运动推荐装置包括用于实现以上运动推荐方法实施例中的步骤和/或流程的模块，为了简洁，这里不再赘述。
通过本申请实施例的运动推荐装置，可以基于目标对象的历史睡眠数据和历史运动数据，获取目标对象在目标时间段的目标运动推荐结果，并向目标对象推荐该目标运动推荐结果，从而帮助目标对象保持科学且规律的运动习惯，为目标对象运动能力的提升以及主动健康目标的达成建立基础。
请参见图13，图13是本申请实施例提供的一种睡眠推荐装置1300的示意图。如图13所示，该装置1300包括：获取模块1301，用于通过终端设备获取目标对象的历史睡眠数据；第一处理模块1302，用于根据目标对象的属性信息和目标对象的期望睡眠信息中的至少一种，得到目标对象的至少一个目标睡眠参数值；第二处理模块1303，用于基于目标对象的至少一个目标睡眠参数值以及目标对象的历史睡眠数据，得到目标对象在目标时间段的睡眠推荐结果，睡眠推荐结果包括推荐入睡时间、推荐醒来时间和推荐睡眠时长中的至少一种；第一输出模块1304，用于输出睡眠推荐结果的相关信息。
在一些实施例中，第一处理模块1302还用于：在得到至少一个目标睡眠参数值之前，确定期望睡眠信息中包括的至少一个期望睡眠参数值的有效性。例如，确定至少一个期望睡眠参数值是否在预设数值范围内。
在一些实施例中，第一处理模块1302用于：响应于目标对象的期望睡眠信息中存在与第一睡眠参数对应的有效的期望睡眠参数值，则将有效的期望睡眠参数值确定为所述第一睡眠参数对应的目标睡眠参数值。
在一些实施例中，第一处理模块1302用于：响应于目标对象的期望睡眠信息中不存在与第二睡眠参数对应的有效的期望睡眠参数值，则根据目标对象的属性信息，确定第二睡眠参数对应的目标睡眠参数值。
在一些实施例中，第二处理模块1303用于：根据目标对象的历史睡眠数据以及至少一个目标睡眠参数值，确定目标对象的睡眠调整策略；根据睡眠调整策略，得到目标对象在目标时间段的睡眠推荐结果。
该睡眠调整策略可以包括渐进式调整策略或者直接调整策略。
在一些实施例中，第二处理模块1303还用于：根据目标对象的历史睡眠数据，得到目标对象的至少一个当前睡眠参数值，并根据至少一个当前睡眠参数值和至少一个目标睡眠参数值来得到睡眠推荐结果。
该至少一个当前睡眠参数值可以包括历史入睡时间、历史醒来时间、历史睡眠时长中的至少一种。
在一些实施例中，第二处理模块1303用于：响应于当前睡眠参数值与目标睡眠参数值之间的差异超过预设差异范围，确定目标对象的睡眠调整策略为渐进式调整策略。
在另一些实施例中，第二处理模块1303用于：响应于当前睡眠参数值与目标睡眠参数值之间的差异在所述预设差异范围内，则确定睡眠推荐策略为直接调整策略。
在一些实施例中，装置还包括第三处理模块1405。作为一种示例，请参见图14，图14是本申请实施例提供的另一种睡眠推荐装置1400的结构示意图。如图14所示，该装置1400还包括第三处理模块1405和第二输出模块1406。第三处理模块1405用于至少部分地根据目标对象的历史睡眠数据中包括的目标时间段的前一天的常规睡眠数据，得到目标对象在目标时间段的补充睡眠推荐结果。其中，图14中的模块1401～1404与图13中的模块1301～1304具有相同的结构和功能。
在一些实施例中，第三处理模块1405还用于：根据目标对象在目标时间段的前一天的常规睡眠参数是否达到预设参数范围，来确定是否推荐目标对象在目标时间段进行补充睡眠。
在一些实现方式中，装置1400还包括第二输出模块1406，用于：至少部分地基于 目标对象在目标时间段的前一天的补充睡眠数据，输出补充睡眠时长提醒。
在一些实施例中，第二输出模块1406还用于：响应于目标时间段的前一天的睡眠数据指示目标对象在前一天的补充睡眠时长超过推荐时长范围，输出补充睡眠时长提醒，用于提示将目标时间段的补充睡眠时长控制在推荐时长范围内。
在一些实现方式中，本申请实施例提供的睡眠推荐装置包括用于实现以上睡眠推荐方法实施例中的步骤和/或流程的模块，为了简洁，这里不再赘述。
通过本申请实施例的睡眠推荐装置，可以根据目标对象的属性信息和期望睡眠信息中的至少一种，得到目标对象的至少一个目标睡眠参数值，并基于目标对象的至少一个目标睡眠参数值以及目标对象的历史睡眠数据，得到目标对象在目标时间段的睡眠推荐结果，从而帮助目标对象循序渐进的养成科学且规律的睡眠习惯。
此外，可以基于目标对象的历史睡眠数据，得到目标对象的补充睡眠推荐结果，从而避免目标对象由于常规睡眠不佳而造成精力不济，同时避免较长的补充睡眠对健康产生的不利影响，为目标对象的主动健康目标的达成建立基础。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
需要说明的是，本申请的技术方案中，所涉及的目标对象的相关信息的获取，存储和应用等，均符合相关法律法规的规定，且不违背公序良俗。
基于本申请的实施例，本申请还提供了一种电子设备，包括：至少一个处理器；以及与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行前述任一实施例的运动推荐方法，或者使至少一个处理器能够执行前述任一实施例的睡眠推荐方法。
基于本申请的实施例，本申请还提供了一种计算机可读存储介质，其中，计算机指令用于使计算机执行根据本申请实施例提供的前述任一实施例的运动推荐方法，或者，执行根据本申请实施例提供的前述任一实施例的睡眠推荐方法。
请参见图15，图15为可以用来实施本申请的实施例的示例电子设备的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本申请的实现。
如图15所示，电子设备1500包括计算单元1501，其可以根据存储在只读存储器(Read-Only Memory，ROM)1502中的计算机程序或者从存储单元1508加载到随机访问存储器(Random Access Memory，RAM)1503中的计算机程序，来执行各种适当的动作和处理。在RAM 1503中，还可存储电子设备1500操作所需的各种程序和数据。计算单元1501、ROM 1502以及RAM 1503通过总线1504彼此相连。输入/输出(Input/Output，I/O)接口1505也连接至总线1504。
电子设备1500中的多个部件连接至I/O接口1505，包括：输入单元1506，例如键盘、鼠标等；输出单元1507，例如各种类型的显示器、扬声器等；存储单元1508，例如磁盘、光盘等；以及通信单元1509，例如网卡、调制解调器、无线通信收发机等。通信单元1509允许电子设备1500通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
计算单元1501可以是具有处理和计算能力的各种通用和/或专用处理组件。计算单元1501的一些示例包括但不限于中央处理单元(Central Processing Unit，CPU)、图形处理单元(Graphics Processing Unit，GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(Digital Signal Process，DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元1501执行上文所描述的各个方法和处理，例如运动推荐方法或者睡眠推荐方法。例如，在一些实施例中，运动推荐 方法或者睡眠推荐方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元1508。在一些实施例中，计算机程序的部分或者全部可以经由ROM 1502和/或通信单元1509而被载入和/或安装到电子设备1500上。当计算机程序加载到RAM1503并由计算单元1501执行时，可以执行上文描述的运动推荐方法或者睡眠推荐方法的一个或多个步骤。备选地，在其他实施例中，计算单元1501可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行运动推荐方法或者睡眠推荐方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、芯片上系统的系统(System On Chip，SOC)、负载可编程逻辑设备(Complex Programmable Logic Device，CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本申请的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本申请的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读存储介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器((Erasable Programmable Read-Only Memory，EPROM)或快闪存储器)、光纤、便捷式紧凑盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、光学存储设备、磁存储设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，阴极射线管(Cathode Ray Tube，CRT)或者LCD(Liquid Crystal Display，液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入、或者触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(Local Area Network，LAN)、广域网(Wide Area Network，WAN)、互联网和区块链网络。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，又称为云计算服务器或云主机，是云计算服务体系中的一项主机产品，解决了传统物理主机与VPS(Virtual Private Server，虚拟专用服务器)服务中，存在的管理难度大，业务扩展性弱的缺陷。服务器也可以为分布式系统的服务器，或者是结合了区块链的服务器。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本申请中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本申请的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本申请保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本申请的精神和原则之内所作的修改、等同替换和改进等，均应包含在本申请保护范围之内。

Claims (30)

  1. 一种运动推荐方法，包括：
    通过终端设备获取目标对象的历史睡眠数据和历史运动数据，所述历史睡眠数据包括在目标时间段之前的至少一天的睡眠数据，所述历史运动数据包括在所述目标时间段之前的至少一天的运动数据；
    根据所述历史睡眠数据和所述历史运动数据，得到所述目标对象在所述目标时间段的目标运动推荐结果，所述目标运动推荐结果包括目标推荐运动时间和目标推荐运动量中的至少一种；
    输出所述目标运动推荐结果的相关信息。
  2. 如权利要求1所述的方法，其中，
    所述根据所述历史睡眠数据和所述历史运动数据，得到所述目标对象在所述目标时间段的目标运动推荐结果，包括：
    根据所述历史运动数据中包含的至少一部分历史运动时间数据，确定候选运动时间集合，所述候选运动时间集合包括至少一个候选运动时间；
    根据所述历史睡眠数据，从所述候选运动时间集合中确定所述目标推荐运动时间。
  3. 如权利要求2所述的方法，其中，所述根据所述历史睡眠数据，从所述候选运动时间集合中确定所述目标推荐运动时间，包括：
    根据所述目标对象的睡眠类型和所述历史睡眠数据，从所述候选运动时间集合中确定所述目标推荐运动时间。
  4. 如权利要求2或3所述的方法，其中，所述根据所述历史睡眠数据，从所述候选运动时间集合中确定所述目标推荐运动时间，包括：
    根据所述目标对象的睡眠类型，确定所述目标对象的睡眠类型对应的运动时间偏移量；
    根据所述对应的运动时间偏移量和所述历史睡眠数据中包括的至少一部分历史睡眠开始时间数据，确定运动时间要求，所述运动时间要求包括最晚运动时间；
    从所述候选运动时间集合中满足所述运动时间要求的至少一个候选运动时间中，确定所述目标推荐运动时间。
  5. 如权利要求3或4所述的方法，其中，所述睡眠类型包括下列中的至少一种：早起类型、晚起类型、早睡类型、晚睡类型和睡眠障碍类型。
  6. 如权利要求2至5中任一项所述的方法，其中，
    所述根据所述历史睡眠数据，从所述候选运动时间集合中确定所述目标推荐运动时间，包括：
    根据所述历史睡眠数据和所述至少一个候选运动时间对应的运动频次，从所述至少一个候选运动时间中确定所述目标推荐运动时间。
  7. 如权利要求1至6中任一项所述的方法，其中，所述根据所述历史睡眠数据和所述历史运动数据，得到所述目标对象在所述目标时间段的目标运动推荐结果，包括：
    根据所述历史运动数据中的第一历史运动数据，确定所述目标时间段的初始运动推荐结果；
    根据所述历史睡眠数据的至少一部分，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标对象在所述目标时间段的目标运动推荐结果。
  8. 如权利要求7所述的方法，其中，所述第一历史运动数据包括在所述目标时间段所属的当前运动推荐周期之前的至少一个历史运动推荐周期的运动数据；
    所述历史睡眠数据的至少一部分包括临近所述目标时间段的至少一天的睡眠数据。
  9. 如权利要求1至8中任一项所述的方法，其中，所述根据所述历史睡眠数据和所述历史运动数据，得到所述目标对象在所述目标时间段的目标运动推荐结果，包括：
    根据所述历史运动数据中的第一历史运动数据，在第一时间确定所述目标时间段的 初始运动推荐结果，所述第一时间在所述目标时间段所属的当前运动推荐周期之前；
    根据所述历史睡眠数据的至少一部分，在第二时间对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标对象在所述目标时间段的目标运动推荐结果，所述第二时间在所述当前运动推荐周期内且在所述目标时间段之前。
  10. 如权利要求7至9中任一项所述的方法，其中，所述根据所述历史运动数据中的第一历史运动数据，确定所述目标时间段的初始运动推荐结果，包括：
    根据所述目标对象的生理数据测量结果，确定所述目标时间段的运动推荐策略；
    基于所述目标时间段的运动推荐策略以及所述第一历史运动数据，确定所述目标时间段的初始运动推荐结果。
  11. 如权利要求10所述的方法，其中，所述初始运动推荐结果包括初始推荐运动量，所述运动推荐策略包括增加运动量、降低运动量或维持运动量。
  12. 如权利要求7至11中任一项所述的方法，其中，所述根据所述历史睡眠数据的至少一部分，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标对象在所述目标时间段的目标运动推荐结果，包括：
    根据所述历史睡眠数据的至少一部分，得到所述目标对象在临近所述目标时间段的至少一天的睡眠质量评估结果；
    基于所述至少一天的睡眠质量评估结果，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果。
  13. 如权利要求7至12中任一项所述的方法，其中，所述根据所述历史睡眠数据的至少一部分，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标对象在所述目标时间段的目标运动推荐结果，包括：
    根据所述历史睡眠数据的至少一部分以及所述历史运动数据中的第二历史运动数据，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果，其中，所述第二历史运动数据包括在所述目标时间段所属的当前运动推荐周期内且在所述目标时间段之前的至少一天的运动数据。
  14. 如权利要求1至6中任一项所述的方法，其中，
    所述根据所述历史睡眠数据和所述历史运动数据，得到所述目标对象在所述目标时间段的目标运动推荐结果，包括：
    确定所述目标时间段的初始运动推荐结果；
    根据所述历史睡眠数据的至少一部分以及所述历史运动数据中的第二历史运动数据，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果，其中，所述历史睡眠数据的至少一部分包括临近所述目标时间段的至少一天的睡眠数据，所述第二历史运动数据包括临近所述目标时间段的至少一天的运动数据。
  15. 如权利要求13或14所述的方法，其中，根据所述历史睡眠数据的至少一部分以及所述历史运动数据中的第二历史运动数据，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果，包括：
    根据所述第二历史运动数据，得到所述目标对象的运动评估结果，所述运动评估结果用于指示所述目标对象在临近所述目标时间段的至少一天的运动量达标情况；
    根据所述历史睡眠数据的至少一部分，得到所述目标对象的睡眠质量评估结果；
    根据所述运动评估结果和所述睡眠质量评估结果，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果。
  16. 如权利要求15所述的方法，其中，
    所述根据所述运动评估结果和所述睡眠质量评估结果，对所述目标时间段的初始运动推荐结果进行调整处理，得到所述目标时间段的目标运动推荐结果，包括：
    响应于所述运动评估结果指示运动量未达标，且所述睡眠质量评估结果指示的睡眠 质量指标低于预设质量指标阈值，将所述初始运动推荐结果中包括的初始推荐运动量调整至所述目标对象的最低运动量，得到所述目标推荐运动量；或者，
    响应于所述运动评估结果指示运动量未达标，且所述睡眠质量评估结果指示的睡眠质量指标达到所述预设质量指标阈值，则将所述目标推荐运动量确定为所述初始推荐运动量。
  17. 如权利要求15或16所述的方法，其中，所述睡眠质量评估结果包括睡眠恢复指标；
    所述根据所述历史睡眠数据的至少一部分，得到所述目标对象的睡眠质量评估结果，包括：
    根据所述历史睡眠数据的至少一部分，得到所述目标对象的睡眠心率变异性数据；
    基于所述目标对象的睡眠心率变异性数据，得到所述目标对象的睡眠恢复指标。
  18. 如权利要求17所述的方法，其中，所述目标对象的睡眠心率变异性数据包括下列中的至少一种：所述目标对象的短期睡眠心率变异性参数、所述目标对象的长期睡眠心率变异性参数以及所述目标对象在所述目标时间段的前一天的睡眠心率变异性参数。
  19. 一种睡眠推荐方法，包括：
    通过终端设备获取目标对象的历史睡眠数据；
    根据所述目标对象的属性信息和所述目标对象的期望睡眠信息中的至少一种，得到所述目标对象的至少一个目标睡眠参数值；
    基于所述至少一个目标睡眠参数值以及所述目标对象的历史睡眠数据，得到所述目标对象在目标时间段的睡眠推荐结果，所述睡眠推荐结果包括推荐入睡时间、推荐醒来时间和推荐睡眠时长中的至少一种；
    输出所述睡眠推荐结果的相关信息。
  20. 如权利要求19所述的方法，其中，所述目标对象的期望睡眠信息包括至少一个期望睡眠参数值；
    所述根据所述目标对象的属性信息和所述目标对象的期望睡眠信息中的至少一种，得到所述目标对象的至少一个目标睡眠参数值，包括：
    响应于所述目标对象的期望睡眠信息中存在与第一睡眠参数对应的有效的期望睡眠参数值，则将所述有效的期望睡眠参数值确定为所述第一睡眠参数对应的目标睡眠参数值；或者，
    响应于所述目标对象的期望睡眠信息中不存在与第二睡眠参数对应的有效的期望睡眠参数值，则根据所述目标对象的属性信息，确定所述第二睡眠参数对应的目标睡眠参数值。
  21. 如权利要求19或20所述的方法，其中，所述基于所述至少一个目标睡眠参数值以及所述目标对象的历史睡眠数据，得到所述目标对象在目标时间段的睡眠推荐结果，包括：
    根据所述目标对象的历史睡眠数据以及所述至少一个目标睡眠参数值，确定所述目标对象的睡眠调整策略；
    根据所述睡眠调整策略，得到所述目标对象在所述目标时间段的睡眠推荐结果。
  22. 如权利要求19至21中任一项所述的方法，其中，所述基于所述至少一个目标睡眠参数值以及所述目标对象的历史睡眠数据，得到所述目标对象在目标时间段的睡眠推荐结果，包括：
    对所述目标对象的历史睡眠数据进行处理，得到所述目标对象的至少一个当前睡眠参数值；
    响应于所述至少一个当前睡眠参数值与所述至少一个目标睡眠参数值之间的差异超过预设差异范围，利用渐进式调整策略，得到所述目标对象在所述目标时间段的睡眠 推荐结果。
  23. 如权利要求19至22中任一项所述的方法，其中，所述基于所述至少一个目标睡眠参数值以及所述目标对象的历史睡眠数据，得到所述目标对象在目标时间段的睡眠推荐结果，包括：
    响应于所述目标对象的历史睡眠数据指示的至少一个当前睡眠参数值与所述至少一个目标睡眠参数值之间的差异超过预设差异范围，则基于调整步长和所述当前睡眠参数值，得到所述目标对象在所述目标时间段的睡眠推荐结果；和/或
    响应于所述目标对象的历史睡眠数据指示的至少一个当前睡眠参数值与所述至少一个目标睡眠参数值之间的差异在所述预设差异范围内，则确定所述目标对象在所述目标时间段的睡眠推荐结果包括所述目标睡眠参数值。
  24. 如权利要求19至23中任一项所述的方法，还包括：
    至少部分地根据所述目标对象在所述目标时间段的前一天的常规睡眠数据，得到所述目标对象在所述目标时间段的补充睡眠推荐结果；和/或
    至少部分地基于所述目标对象在所述目标时间段的前一天的补充睡眠数据，输出补充睡眠时长提醒。
  25. 如权利要求24所述的方法，其中，所述至少部分地根据所述目标对象在所述目标时间段的前一天的常规睡眠数据，得到所述目标对象在所述目标时间段的补充睡眠推荐结果，包括：
    响应于所述目标对象在所述目标时间段的前一天的常规睡眠数据指示所述目标对象在所述前一天的常规睡眠时长未达到预设睡眠时长，则确定所述目标对象在所述目标时间段的补充睡眠推荐结果包括的补充睡眠推荐时长为大于零的第一时长；和/或
    响应于所述目标对象在所述目标时间段的前一天的常规睡眠数据指示所述目标对象在所述前一天的常规睡眠时长达到所述预设睡眠时长，则确定所述目标对象在所述目标时间段的补充睡眠推荐结果包括的补充睡眠推荐时长为零。
  26. 如权利要求24或25所述的方法，其中，所述至少部分地基于所述目标对象在所述目标时间段的前一天的补充睡眠数据，输出补充睡眠时长提醒，包括：
    响应于所述目标对象在所述目标时间段的前一天的补充睡眠数据指示所述目标对象在所述前一天的补充睡眠时长超过推荐时长范围，输出补充睡眠时长提醒，所述补充睡眠时长提醒用于提示将所述目标时间段的补充睡眠时长控制在所述推荐时长范围内。
  27. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；
    其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1至18中任一项所述的运动推荐方法，或者执行权利要求19至26中任一项所述的睡眠推荐方法。
  28. 一种计算机可读存储介质，用于存储有指令，其中，当所述指令被执行时，使如权利要求1至18中任一项所述的运动推荐方法被实现，或者使如权利要求19至26中任一项所述的睡眠推荐方法被实现。
  29. 一种运动推荐装置，包括用于执行权利要求1至18中任一项所述的运动推荐方法的至少一个模块。
  30. 一种睡眠推荐装置，包括用于执行权利要求19至26中任一项所述的睡眠推荐方法的至少一个模块。
PCT/CN2023/118017 2022-09-14 2023-09-11 运动推荐方法、睡眠推荐方法及其装置、电子设备及存储介质 WO2024055931A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211116627.4 2022-09-14
CN202211116627.4A CN115701877A (zh) 2022-09-14 2022-09-14 运动推荐方法、睡眠推荐方法及其装置

Publications (1)

Publication Number Publication Date
WO2024055931A1 true WO2024055931A1 (zh) 2024-03-21

Family

ID=85162762

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/118017 WO2024055931A1 (zh) 2022-09-14 2023-09-11 运动推荐方法、睡眠推荐方法及其装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN115701877A (zh)
WO (1) WO2024055931A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115701877A (zh) * 2022-09-14 2023-02-14 安徽华米健康科技有限公司 运动推荐方法、睡眠推荐方法及其装置
CN117809808A (zh) * 2024-02-26 2024-04-02 青岛杨辉大数据科技有限公司 一种个性化推荐运动计划的方法、系统、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109545321A (zh) * 2018-10-30 2019-03-29 维沃移动通信有限公司 一种策略推荐方法及装置
CN111568380A (zh) * 2020-05-19 2020-08-25 北京顺源开华科技有限公司 基于睡醒时间预测的闹钟设定方法、装置和设备
CN113870978A (zh) * 2021-09-27 2021-12-31 平安国际智慧城市科技股份有限公司 基于人工智能的运动推荐方法、装置、服务器及介质
US20220031233A1 (en) * 2020-07-31 2022-02-03 Samsung Electronics Co., Ltd. Electronic device for evaluating sleep quality and method for operation in the electronic device
CN114255848A (zh) * 2021-12-16 2022-03-29 珠海格力电器股份有限公司 一种姿势调整方法、装置、设备及存储介质
CN115701877A (zh) * 2022-09-14 2023-02-14 安徽华米健康科技有限公司 运动推荐方法、睡眠推荐方法及其装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109545321A (zh) * 2018-10-30 2019-03-29 维沃移动通信有限公司 一种策略推荐方法及装置
CN111568380A (zh) * 2020-05-19 2020-08-25 北京顺源开华科技有限公司 基于睡醒时间预测的闹钟设定方法、装置和设备
US20220031233A1 (en) * 2020-07-31 2022-02-03 Samsung Electronics Co., Ltd. Electronic device for evaluating sleep quality and method for operation in the electronic device
CN113870978A (zh) * 2021-09-27 2021-12-31 平安国际智慧城市科技股份有限公司 基于人工智能的运动推荐方法、装置、服务器及介质
CN114255848A (zh) * 2021-12-16 2022-03-29 珠海格力电器股份有限公司 一种姿势调整方法、装置、设备及存储介质
CN115701877A (zh) * 2022-09-14 2023-02-14 安徽华米健康科技有限公司 运动推荐方法、睡眠推荐方法及其装置

Also Published As

Publication number Publication date
CN115701877A (zh) 2023-02-14

Similar Documents

Publication Publication Date Title
WO2024055931A1 (zh) 运动推荐方法、睡眠推荐方法及其装置、电子设备及存储介质
US20220015695A1 (en) Sleep reactivity monitoring based sleep disorder prediction system and method
US20150182113A1 (en) Real-time fatigue, personal effectiveness, injury risk device(s)
US20150182130A1 (en) True resting heart rate
US20110230790A1 (en) Method and system for sleep monitoring, regulation and planning
US20180008191A1 (en) Pain management wearable device
JP2004254827A (ja) 睡眠状態判定装置
US20210407684A1 (en) Illness Detection Based on Temperature Data
US20200215299A1 (en) Method and apparatus for determining sleep need and sleep pressure based on physiological data
JP6134872B1 (ja) 対象の周期的な運動のサイクル数を計数するデバイス、方法及びシステム
JP2017000720A (ja) 生理学的老化レベルを評価する方法及び装置並びに老化特性を評価する装置
Grifantini How's My Sleep?: Personal sleep trackers are gaining in popularity, but their accuracy is still open to debate
US20210358628A1 (en) Digital companion for healthcare
US11793454B2 (en) Method and system for providing feedback to user for improving performance level management thereof
US11610663B2 (en) Method and system for remotely identifying and monitoring anomalies in the physical and/or psychological state of an application user using average physical activity data associated with a set of people other than the user
JP6304050B2 (ja) 生体状態推定装置
Kaneriya et al. Markov decision-based recommender system for sleep apnea patients
JP7250647B2 (ja) 仮眠補助システム、および、仮眠補助用プログラム
US11185260B1 (en) State-based methods and systems using continuous glucose monitors and accelerometers to regulate glucose levels
WO2021243240A1 (en) Method and system for remotely monitoring the physical and psychological state of an application user using altitude and/or motion data and one or more machine learning models
JP2023540660A (ja) ストレスの判定および管理技術
Liu et al. SmartCare: energy-efficient long-term physical activity tracking using smartphones
KR102382659B1 (ko) 당화혈색소 수치 추정을 위한 인공지능학습 모델의 학습 방법 및 그 시스템
WO2019210434A1 (en) Method and apparatus for determining the impact of behavior-influenced activities on the health level of a user
US20220409187A1 (en) Illness detection with menstrual cycle pattern analysis

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: 23864663

Country of ref document: EP

Kind code of ref document: A1