CN111460850A - Data processing method and device, electronic equipment and storage medium - Google Patents

Data processing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN111460850A
CN111460850A CN201910002765.1A CN201910002765A CN111460850A CN 111460850 A CN111460850 A CN 111460850A CN 201910002765 A CN201910002765 A CN 201910002765A CN 111460850 A CN111460850 A CN 111460850A
Authority
CN
China
Prior art keywords
data
sleep
target user
model
state
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN201910002765.1A
Other languages
Chinese (zh)
Other versions
CN111460850B (en
Inventor
郑智民
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
China Mobile Communications Ltd Research Institute
Original Assignee
China Mobile Communications Group Co Ltd
China Mobile Communications Ltd Research Institute
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 China Mobile Communications Group Co Ltd, China Mobile Communications Ltd Research Institute filed Critical China Mobile Communications Group Co Ltd
Priority to CN201910002765.1A priority Critical patent/CN111460850B/en
Priority to PCT/CN2019/130837 priority patent/WO2020140913A1/en
Publication of CN111460850A publication Critical patent/CN111460850A/en
Application granted granted Critical
Publication of CN111460850B publication Critical patent/CN111460850B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
    • A61M21/02—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis for inducing sleep or relaxation, e.g. by direct nerve stimulation, hypnosis, analgesia
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
    • H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
    • H05B47/10—Controlling the light source
    • H05B47/105—Controlling the light source in response to determined parameters
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
    • A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
    • A61M2021/0044—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the sight sense
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2205/00—General characteristics of the apparatus
    • A61M2205/33—Controlling, regulating or measuring
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2230/00—Measuring parameters of the user
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection

Abstract

The embodiment of the invention discloses a data processing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring environmental data; acquiring current state data and characteristic data of a target user; selecting a regular sleep model or an irregular sleep model as a target model according to the current state data; inputting the environmental data and the characteristic data into a selected target model to obtain light control parameters; controlling light emission of a light emitting device using the light control parameter, wherein the controlling light emission of the light emitting device comprises: controlling the light emitting device to emit light that promotes sleep of the target user, or controlling the light emitting device to emit light that inhibits sleep of the target user.

Description

Data processing method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of information technologies, and in particular, to a data processing method and apparatus, an electronic device, and a storage medium.
Background
The biological effects of light on humans can be divided into visual effects and non-visual effects. The visual effect is mainly composed of the cone cells of the retina, perceiving luminosity and color; the non-visual effect is mainly composed of rod-shaped cells of the pineal body, senses luminosity, generates bioelectricity, influences sympathetic nerves, and governs the pineal body cells to release melatonin into flowing blood, so that hormone secretion is reduced, metabolism is slowed down, and natural sleep is induced.
Some technical schemes for adjusting sleep through light appear at present, but the adjustment effect is found to be not good, and especially the adjustment effect is worse for users who have irregular sleep.
Disclosure of Invention
In view of this, embodiments of the present invention are intended to provide a data processing method and apparatus, an electronic device, and a storage medium. The technical scheme of the invention is realized as follows:
a method of data processing, comprising:
acquiring environmental data;
acquiring current state data and characteristic data of a target user;
selecting a regular sleep model or an irregular sleep model as a target model according to the current state data;
inputting the environmental data and the characteristic data into a selected target model to obtain light control parameters;
controlling light emission of a light emitting device using the light control parameter, wherein the controlling light emission of the light emitting device comprises: controlling the light emitting device to emit light that promotes sleep of the target user, or controlling the light emitting device to emit light that inhibits sleep of the target user.
Based on the above scheme, the selecting a regular sleep model or an irregular sleep model as a target model according to the current sleep state of the target user includes at least one of the following:
if the current state data indicate that the current sleep state of the target user does not accord with the sleep rule corresponding to the regular sleep model, selecting the irregular sleep model as the target model;
and if the current state data indicate that the current sleep state of the target user accords with the sleep rule corresponding to the regular sleep model, selecting the regular sleep model as the target model.
Based on the above scheme, the method further comprises:
if the target model is a non-sleep regular model, acquiring non-regular sleep data of the target user;
the step of inputting the environment data and the feature data into a selected target model to obtain light control parameters comprises the following steps:
and inputting the environment data, the feature data and the irregular sleep-comforting data into the irregular sleep model to obtain the light control parameters.
Based on the scheme, the irregular sleep data comprises at least one of the following data:
sleep time deviation data for going to sleep;
time zone deviation data of the time zone in which the target user is located;
continuous state data of the irregular sleep;
frequency of occurrence of irregular sleep.
Based on the above scheme, the acquiring the environmental data includes at least one of:
acquiring current season data;
acquiring illumination data of a space where a current target user is located;
acquiring temperature data of a space where a current target user is located;
and/or the presence of a gas in the gas,
the acquiring of the feature data of the target user comprises:
acquiring static characteristic data of the user;
and acquiring the dynamic characteristic data of the user.
Based on the above scheme, the acquiring of the dynamic feature data of the user includes at least one of the following:
acquiring current action characteristic data of the target user;
and acquiring current physical sign characteristic data of the target user.
Based on the above scheme, the method further comprises:
performing first denoising processing on the characteristic data, removing first noise data outside a preset frequency range and obtaining first characteristic data;
performing correlation analysis filtering on the first characteristic data, removing second noise data located in the preset frequency range and obtaining second characteristic data;
analyzing the second characteristic data to obtain third characteristic data representing the state of the target user;
the step of inputting the environment data and the feature data into a selected target model to obtain light control parameters comprises the following steps:
and inputting the third characteristic data and the environment data into a target model of the target user to obtain the light control parameter.
Based on the above scheme, the analyzing the second feature data to obtain third feature data representing the state of the target user includes:
analyzing the second feature data, and extracting time domain feature data of the target user from the second feature data, wherein the time domain feature data comprises: peak data and/or trough data of a characteristic curve corresponding to the second characteristic data in the time domain;
peak data and/or trough data of the action curve or the physical sign change curve of the target user;
and/or the presence of a gas in the gas,
analyzing the second characteristic data, and extracting frequency domain characteristic data of the target user from the second characteristic data; wherein the frequency domain feature data comprises: and peak data and/or trough data of the characteristic curve corresponding to the second characteristic data in the frequency domain.
Based on the above scheme, the first noise data includes: acquiring jitter data of which the jitter frequency is outside the preset frequency range, electromagnetic interference data of which the electromagnetic frequency is outside the preset frequency range and magnetic field noise of which the electromagnetic frequency is outside the preset range of the equipment;
and/or the presence of a gas in the gas,
the second noise data includes: and acquiring jitter data of which the jitter frequency is within the preset frequency range.
Based on the above scheme, the inputting the environmental data and the feature data into the selected target model to obtain the light control parameters includes:
performing dimensionality reduction processing on the third characteristic data and the environmental data according to a dimensionality reduction processing strategy to obtain input data with preset dimensionality;
and inputting input data of a preset dimension into the target model to obtain the light control parameters.
Based on the above scheme, performing dimensionality reduction processing on the third feature data and the environmental data according to a dimensionality reduction processing strategy to obtain input data of a preset dimensionality includes:
determining whether the target user is in an overall static state or not based on a first preset condition and the action characteristic data of the target user;
if the target user is in an action state, determining whether the target user is in a first type of local static state according to the action characteristic data;
if the target user is not in the first type of local static state, determining whether the target user is in a second type of local static state according to the action characteristic data;
and if the target user is in an action state, sampling the action characteristic data of the target user according to the current action state of the target user to obtain sampling characteristic data serving as the input data.
Based on the above scheme, according to the dimensionality reduction processing strategy, performing dimensionality reduction processing on the third feature data and the environmental data to obtain input data of a preset dimensionality, further comprising:
if the target user is in the overall static state, stopping determining whether the target user is in the first type of local static state and the second type of local static state;
and/or the presence of a gas in the gas,
and if the target user is in the first type of local static state, stopping the determination of whether the target user is in the second type of local static state.
Based on the above scheme, after the controlling the light emission of the light emitting device by using the light control parameter, the method further includes:
obtaining effect data for light control, wherein the effect data comprises: at least one of sleep effect data, sleep activity data, and non-sleep activity data of the target user;
and optimizing the regular sleep model and/or the irregular sleep model according to the effect data.
A data processing apparatus comprising:
the first acquisition module is used for acquiring environmental data;
the second acquisition module is used for acquiring the current state data and the characteristic data of the target user;
a selection module for selecting a regular sleep model or an irregular sleep model as a target model according to the current state data
The third acquisition module is used for inputting the environmental data and the characteristic data into the selected target model to obtain light control parameters;
a control module for controlling light emission of the light emitting device using the light control parameter, wherein the controlling light emission of the light emitting device includes: controlling the light emitting device to emit light that promotes sleep of the target user, or controlling the light emitting device to emit light that inhibits sleep of the target user. Regular sleep model and irregular sleep model
An electronic device, comprising:
a memory;
and the processor is connected with the memory and used for realizing the data processing method provided by one or more of the technical schemes by executing the computer executable instructions on the memory.
A computer storage medium having stored thereon computer-executable instructions; the computer-executable instructions, when executed, enable a data processing method provided by one or more of the foregoing technical solutions.
According to the technical scheme provided by the embodiment of the invention, the environmental data, the current state data and the characteristic data of the target user are obtained, and the light control parameters are formed by firstly determining whether the regular sleep model or the irregular sleep model is used as the target model according to the current state data, so that the light can be controlled according to whether the user is regularly or irregularly sleeping at present, and better light control beneficial to inhibiting or promoting sleep is provided, therefore, the accurate light control can be realized no matter the sleep of the target user is regular or irregular at present, the light for promoting sleep is emitted when the target user needs to promote sleep, and the light for inhibiting sleep is emitted when the target user needs to inhibit sleep, so that the sleep of the target user can be accurately adjusted by using the light.
Drawings
Fig. 1 is a schematic flow chart of a first data processing method according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a second data processing method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a third data processing method according to an embodiment of the present invention;
FIG. 5 is a flow chart illustrating a method for sleep conditioning for irregular sleep according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an irregular sleep model controlling a lighting device to emit light according to an embodiment of the present invention.
Detailed Description
The technical solution of the present invention is further described in detail with reference to the drawings and the specific embodiments of the specification.
The study finds that people with a reversed time difference, people falling down from three shifts in a factory, medical personnel, and the like are most likely to cause chronic biological clock imbalance due to the reversal of time difference, and are likely to cause stomach discomfort such as ulcer and heart disease, and the like, the excitability of sympathetic nerves is related to the light color and the illumination intensity reaching the pineal body, some manufacturers propose blue light irradiation to improve irregular sleep conditions, the generation of melatonin in the body is increased by proper illumination of a sleep-aid lamp (N1 light sleep stage (1200 + 7000L ux, N4 before automatic wake-up, REM stage receives 2500 + 10000lux), the melatonin (with circadian rhythm and midnight secretion reaching the peak) contributes to deepening sleep depth (the specific gravity of REM and N + 4), the sleep-wake-rhythm is changed, the physiological clock is adjusted, the sleep quality is adjusted.
In view of the above, in consideration of the fact that the light demand required by the user to promote or suppress sleep is inconsistent between regular sleep and irregular sleep, a data processing method as shown in fig. 1 is proposed, which includes:
step S110: acquiring environmental data;
step S120: acquiring current state data and characteristic data of a target user;
step S130: selecting a regular sleep model or an irregular sleep model as a target model according to the current state data;
step S140: inputting the environment data and the feature data into a selected target model, and acquiring light control parameters by a regular sleep model and an irregular sleep model;
step S150: controlling light emission of a light emitting device using the light control parameter, wherein the controlling light emission of the light emitting device comprises: controlling the light emitting device to emit light that promotes sleep of the target user, or controlling the light emitting device to emit light that inhibits sleep of the target user.
The data processing method provided by the embodiment can be applied to various electronic devices, for example, can be applied to user equipment or a home gateway. The user equipment may be: the mobile phone, the tablet computer or the wearable device of the user. After obtaining the light control parameters, the devices control the light emitting devices to emit light or control the devices to emit light.
The light emitting device may be various devices capable of emitting light, and may be the user device itself, or may be a light emitting device at a location where a target user is located, such as a bedroom or a living room.
In this embodiment, the electronic device may first obtain environment data, where the environment data represents an environmental condition of a space where the target user is currently located. For example, environmental data is collected by environmental sensors.
Different environments have different effects on both the user's sleep activity and non-sleep activity. For example, in either case of being too bright or too dark, the target user's sleep is not utilized. In this embodiment, it is desirable to assist sleeping or non-sleeping activities by means of lights. In this embodiment, the feature data of the target user is obtained, and the feature data may constitute an individual static image of the target user, an individual dynamic image of the target user, a physical sign image of the target user, an emotion image of the target user, and the like.
The user characteristic data may include: the feature data acquired by the acquisition is also included in dynamic acquisition, for example, dynamically acquired by a physiological sensor, and includes but is not limited to: heartbeat data of a target user, electroencephalogram data of the target user, pulse data of the target user and the like.
The current state parameter may at least characterize whether the target user is currently in a sleep state or a non-sleep state.
In some embodiments, the current state parameter may also be used to characterize a sleep stage or a sleep depth of the target user in a sleep state; the current state parameter can also be used for representing parameters such as the wakefulness degree of the target user in a non-sleep state.
In this embodiment, one target user corresponds to two models, namely a regular sleep model and an irregular sleep model.
The regular sleep model can be used for forming the light control parameter when the current sleep state of the target user is regular sleep; the irregular sleep model may be used to form the light control parameter when the current sleep state of the target user is irregular sleep.
In this way, in step S140, a corresponding light control parameter may be formed according to whether the current sleep state of the target user is a regular sleep state, so as to implement accurate control of light.
Because the color of the light and/or the brightness of the light have certain promoting or inhibiting effects on human emotions and physical signs, in this embodiment, the environmental data and the characteristic data are used as the input of the target model, and the target model can obtain the light control parameters for controlling the light emission of the light-emitting device.
For example, the light control parameter includes at least one of:
color control parameters of the light for controlling the color of the light, for example, the color control parameters may include: the light emitting wavelength, different wavelengths correspond to different colors of light;
the brightness control parameter of the lamp light is used for controlling the brightness of the light emitting device, and may include: the light value.
The color change of the light controls the parameters,
the brightness variation of the light controls the parameters, and in some cases, the brightness of the light varies to promote or inhibit sleep of the user. For example, the lights may be brighter and brighter at the beginning of the morning; when falling asleep at night, the brightness of the lamplight is required to be darker and darker; when the target user needs to be awakened, the color of the light may need to be gradually switched from the light with warm tone to the light with cold tone; while it may be necessary to gradually switch from cool to warm light before falling asleep.
The lighting angle control parameter of the light is used for controlling the lighting angle of the light; the light control parameters also include an irradiation angle control parameter, since the light irradiation directly to the visual field of the target user may inhibit sleep and the light irradiation from the side may contribute to the sleep of the user.
In summary, in this embodiment, the environment data and the feature data are input by a regular sleep model and an irregular sleep model that are self-set by the target user, and thus, the light control parameters of the target user are obtained; therefore, the lighting control parameters provided by target users with different ages, sleeping habits and sexes are distinguished, so that lighting control is performed for each user, and the requirement for individual lighting control of the user is ensured.
The step S130 may include at least one of:
if the current state data indicate that the current sleep state of the target user does not accord with the sleep rule corresponding to the regular sleep model, selecting the irregular sleep model as the target model;
and if the current state data indicate that the current sleep state of the target user accords with the sleep rule corresponding to the regular sleep model, selecting the regular sleep model as the target model.
For example, according to a sleep rule of regular sleep, the target user should be in a sleep state at the current time, but the target user is still in a non-sleep state according to the current state data, which indicates that the light control parameter is currently suitable for being formed by adopting a non-regular sleep model.
For another example, according to the sleep rule of regular sleep, the current time is the sleep time of the user but the time zone in which the target user is located is changed, which may also be considered as being not in accordance with the sleep rule corresponding to the regular sleep model, and a non-sleep rule needs to be selected as the target model.
In a word, if any one of the sleep time and the sleep time zone (the time zone where the target user is located) does not meet the sleep rule corresponding to the regular sleep model, the irregular sleep model is selected as the target model, otherwise, the regular sleep model is selected as the target model.
In other embodiments, the method further comprises:
if the target model is a non-sleep regular model, acquiring non-regular sleep data of the target user;
the step S140 may include: and inputting the environment data, the feature data and the irregular sleep-comforting data into the irregular sleep model to obtain the light control parameters.
The irregular sleep data may include: various differential data characterizing the irregular sleep state and the regular sleep state, etc. As such, the irregular sleep model may determine whether sleep suppression or sleep promotion is needed in conjunction with the irregular sleep data. At the same time, the irregular sleep model may combine the environmental data and the characteristic data to determine specific light control parameters needed to promote sleep or inhibit sleep.
In some embodiments, as shown in fig. 7, the irregular sleep data includes at least one of:
sleep time deviation data for going to sleep, e.g., target user 10: 00 falling asleep, the current time is already 1:15 of the next day, the target user does not fall asleep, and the time difference between the two is 2:15, which can be used as one of the time deviation data;
time zone deviation data of the time zone in which the target user is located; for example, the target user flies from beijing to london, and due to the difference between the time zone of beijing and the time zone of london, the time zone deviation data may also be used as the irregular sleep data in china;
continuous state data of the irregular sleep; for example, the persistent state data may include at least one of: the time length of the target user continuously sleeping irregularly, the time length of the target user keeping in the irregular non-sleeping state irregularly and the time length of the target user keeping in the irregular sleeping state irregularly;
frequency data of irregular sleep; for example, the frequency of occurrence data of irregular sleep may include at least one of: the number and/or frequency of irregular sleep occurrences in a preset period, such as the last half month or one month.
After the irregular sleep data is input into the irregular sleep model, the irregular sleep model is convenient to determine whether to promote the sleep or inhibit the sleep. In addition, the non-sleep data may also be used with environmental data and feature data to facilitate the generation of light control parameters for sleep promotion or sleep suppression.
As can be seen from fig. 7, in fig. 7, many irregular sleep data (or irregular sleep factors, for example, sleep time deviation data of entering sleep, time zone deviation data of the time zone in which the target user is located, occurrence frequency data of irregular sleep, and one or more of the continuous state data of this irregular sleep) are introduced into the irregular sleep model.
In some embodiments, the step S110 may include at least one of:
acquiring current season data;
acquiring illumination data of a space where a current target user is located;
and acquiring the temperature data of the space where the current target user is located.
Different seasons, different temperatures, different sunshine, different sleep duration and/or different deep and light sleep required by the target user.
In some embodiments, the environmental data may further include: humidity data, different humidities have different effects on the sleep of the target user.
And/or the presence of a gas in the gas,
the step S120 may include:
acquiring static characteristic data of the user;
and acquiring the dynamic characteristic data of the user.
The static feature data may include: data corresponding to a static personal representation of the user, such as age, gender, and/or personal sleep characteristics of the target user.
The dynamic profile data includes, but is not limited to, at least one of:
limb motion data of the target user;
heart rate data of the target user;
heart Rate Variability (HRV) data of the target user, etc. The HRV characterizes the degree of activity of the sympathetic and parasympathetic applications of the target user, the more active the sympathetic is, the more excited the mood of the user and the less suitable it is for sleep.
In some embodiments, the obtaining dynamic characteristic data of the user includes at least one of:
acquiring current action characteristic data of the target user; for example, hand motion data, foot motion data, head motion data, and/or torso movement data;
acquiring current physical sign characteristic data of the target user, such as heart rate data, blood oxygen content data and/or HRV data.
In some embodiments, as shown in fig. 2, the method further comprises:
step S101: performing first denoising processing on the characteristic data, removing first noise data outside a preset frequency range and obtaining first characteristic data;
step S102: performing correlation analysis filtering on the first characteristic data, removing second noise data located in the preset frequency range and obtaining second characteristic data;
step S103: analyzing the second characteristic data to obtain third characteristic data representing the state of the target user;
the step S130 may include: and inputting the third characteristic data and the environment data into a target model of the target user to obtain the light control parameter.
In order to reduce the influence of noise data input into the regular sleep model and the irregular sleep model on the accuracy of the light control parameters in this embodiment, the characteristic data is first denoised in this embodiment. In the present embodiment, in order to remove noise data in the feature data as much as possible, denoising processing is performed twice. For example, first noise data outside the preset frequency range in which the feature data is located may be removed by the first denoising process, and second noise data within the preset frequency range in which the feature data is located may be removed by the correlation analysis. The action features and/or physical signs of the user may exhibit a certain rule, but the second noise data may not exhibit such a rule, which may be a change rule in the time domain, and/or a change rule in the frequency domain, for example, the heartbeat data of the user is periodic, which is a change rule in the time domain, and the brain waves of the user may be switched between waves of different frequencies, but may all be between specific frequency points, which is a change rule in the frequency domain. The correlation analysis may be: and filtering second noise data which do not accord with the time and/or frequency domain change rule of the target user by judging whether each separated signal meets the time and/or frequency domain change rule of the target user. Of course, this is merely an example and the specific implementation is not limited thereto.
In some embodiments, the step S103 may include:
analyzing the second feature data, and extracting time domain feature data of the target user from the second feature data, wherein the time domain feature data comprises: peak data and/or trough data of a characteristic curve corresponding to the second characteristic data in the time domain;
peak data and/or trough data of the action curve or the physical sign change curve of the target user;
and/or the presence of a gas in the gas,
analyzing the second characteristic data, and extracting frequency domain characteristic data of the target user from the second characteristic data; wherein the frequency domain feature data comprises: and peak data and/or trough data of the characteristic curve corresponding to the second characteristic data in the frequency domain.
If the target user acts, an action curve can be drawn in a time domain or a frequency domain through the collected action characteristic data, and the wave peak value and/or the wave trough value of the action curve are very large data which possibly represent the action characteristics of the user. For example, parameters such as the motion amplitude, the motion intensity, the maximum motion amplitude and/or the motion intensity at each motion frequency, and the like at the time of the motion peak and trough are extracted from the second data.
The sign data of the user can also be used for drawing a corresponding sign curve in a time domain and/or a frequency domain, and peak data and/or trough data in the second characteristic parameter can be extracted for processing according to the sign curve.
In some embodiments, the first noise data comprises: acquiring jitter data of which the jitter frequency is outside the preset frequency range, electromagnetic interference data of which the electromagnetic frequency is outside the preset frequency range and magnetic field noise of which the electromagnetic frequency is outside the preset range of the equipment;
and/or the presence of a gas in the gas,
the second noise data includes: and acquiring jitter data of which the jitter frequency is within the preset frequency range.
The jitter of the device may affect the motion characteristic data of the user, and the electromagnetic interference noise and/or the magnetic field noise may affect the brain wave data of the user.
In some embodiments, the step S130 may include:
performing dimensionality reduction processing on the third characteristic data and the environmental data according to a dimensionality reduction processing strategy to obtain input data with preset dimensionality;
and inputting input data of a preset dimension into the target to obtain the light control parameter.
The actually obtained environment data and the feature data are combined according to a predetermined combination mode to form a vector and/or a matrix with a high latitude, but some of the data may not contribute much to obtaining the light control parameters, or some data may not influence the light control parameters until the combination of the data. In order to reduce the data processing amount, in this embodiment, a dimension reduction processing strategy is used to perform dimension reduction processing on the data, for example, dimension reduction processing on environmental parameters and feature data is performed, and only M pieces of data are obtained as input data of the human sleep image model; and M can be a value of 6, 9 or 12, and the specific value can be dynamically set according to requirements.
In some embodiments, the performing, according to the dimension reduction processing policy, dimension reduction processing on the third feature data and the environment data to obtain input data of a preset dimension includes:
determining whether the target user is in an overall static state or not based on a first preset condition and the action characteristic data of the target user;
if the target user is in an action state, determining whether the target user is in a first type of local static state according to the action characteristic data;
if the target user is not in the first type of local static state, determining whether the target user is in a second type of local static state according to the action characteristic data;
and if the target user is in an action state, sampling the action characteristic data of the target user according to the current action state of the target user to obtain sampling characteristic data serving as the input data.
For example, the body posture data in the motion characteristic data may be used as a determination of whether the whole body is in a static state, and if the whole body is in a static state, it may indicate that the target user is currently in a sleep state or a sleep-entering state.
For another example, whether the target user is in the overall still state is integrally judged according to the motion feature data of each part in the motion feature data, for example, whether the target user is in the overall still state is integrally judged according to the hand motion data and the foot motion data of the user, for example, the hand motion data of the user represents that the hand motion of the target user is slight, the foot motion data represents that the foot motion is slight, the target user can be considered to be in the overall still state, and otherwise, the target user can be considered to be in the motion state. If the target user is in the action state, it needs to be further determined whether the target user is in the local action state, for example, if the target user may lie down or sit down but still plays a mobile phone, the target user is in the hand action state, not the hand still state. In this embodiment, it is also determined whether the user is in a local static state, and if a certain local part of the target user is in a static state, the local action state data may be removed and not used as input data; or, as data. In this embodiment, the first type of local still state and the second type of local still state are different still states, and the difference may be represented by at least one of the following:
for example, different types of local stationary states, e.g., local translational stationary states and local rotational stationary states;
for another example, the local corresponding to the first local still state is larger than the local corresponding to the second type local still state. For example, the part corresponding to the first local static state may be the entire upper limb; the part corresponding to the second type of local static state may be a finger.
In order to reduce unnecessary data processing, the performing, according to a dimensionality reduction processing strategy, dimensionality reduction processing on the third feature data and the environmental data to obtain input data of a preset dimensionality further includes:
if the target user is in the overall static state, stopping determining whether the target user is in the first type of local static state and the second type of local static state;
and/or the presence of a gas in the gas,
and if the target user is in the first type of local static state, stopping the determination of whether the target user is in the second type of local static state.
By stopping the judgment of different static states in time, the required calculation amount can be reduced, and the processing speed is improved.
In some embodiments, the method further comprises:
obtaining effect data for light control, wherein the effect data comprises: sleep effect data and/or non-sleep activity data of the target user;
and optimizing the regular sleep model or the irregular sleep model according to the effect data.
In this embodiment, the regular sleep model may be trained using regular sleep data and regular sleep effect data of the regular sleep model.
The training data for the irregular sleep model may include:
regular sleep data, light control data and regular sleep effect data;
irregular sleep data, light control data, and irregular sleep effect data.
The details of the irregular sleep data can be found in the foregoing embodiments, and will not be discussed herein.
Regular sleep data, light control data and regular sleep effect data are introduced into the training of the irregular sleep model, so that the model training can be carried out according to the regular sleep data, the light control data and the irregular sleep effect data, and the accuracy of the light control parameters of the irregular sleep model is further improved. After the light-emitting device is controlled to emit light, sleep effect data of the user is collected, for example, the sleep effect data can represent the promoting effect and/or the inhibiting effect of the light after controlled adjustment on the sleep of the user, and in this embodiment, the effect after the current light adjustment can be known through obtaining the effect data. Whether the effect reaches the expected effect or not and the corresponding light control parameters can be used as sample data for further optimization training of the regular sleep model and the irregular sleep model, and the regular sleep model and the irregular sleep model are deeply optimized, so that the personal characteristics of a target user can be represented more when the regular sleep model and the irregular sleep model are used more, and the light control parameters meeting the personal characteristics of the target user can be output to adjust light; so as to further promote the light control of the carriage light to the sleep stage and/or the non-sleep stage of the user.
As shown in fig. 3, the present embodiment further provides a data processing apparatus, including:
a first obtaining module 110, configured to obtain environment data;
a second obtaining module 120, configured to obtain current state data and feature data of a target user;
a selecting module 130, configured to select a regular sleep model or an irregular sleep model as a target model according to the current state data;
a third obtaining module 140, configured to input the environment data and the feature data into the selected target model, so as to obtain a light control parameter;
a control module 150 for controlling the light emission of the light emitting device by using the light control parameter, wherein the controlling the light emission of the light emitting device comprises: controlling the light emitting device to emit light that promotes sleep of the target user, or controlling the light emitting device to emit light that inhibits sleep of the target user.
In some embodiments, the first obtaining module 110, the second obtaining module 120, the selecting module 130, the third obtaining module 140 and the control module 150 may be program modules, and the program modules, when executed by a processor, can achieve the obtaining of the aforementioned various data and the light emitting control of the light emitting device.
In some embodiments, the first obtaining module 110, the second obtaining module 120, the selecting module 130, the third obtaining module 140, and the control module 150 may be a hardware-software combination module, which may include: various programmable arrays, such as field programmable arrays or complex programmable arrays.
In still other embodiments, the first obtaining module 110, the second obtaining module 120, the selecting module 130, the third obtaining module 140, and the control module 150 may be pure hardware modules, which may include: an application specific integrated circuit.
In some embodiments, the selection module is specifically configured to perform at least one of: if the current state data indicate that the current sleep state of the target user does not accord with the sleep rule corresponding to the regular sleep model, selecting the irregular sleep model as the target model; and if the current state data indicate that the current sleep state of the target user accords with the sleep rule corresponding to the regular sleep model, selecting the regular sleep model as the target model.
In some embodiments, the apparatus further comprises:
the irregular sleep data module is used for acquiring irregular sleep data of the target user if the target model is an irregular sleep model;
the third obtaining module is specifically configured to input the environmental data, the feature data, and the irregular sleep-promoting data into the irregular sleep model to obtain the light control parameter.
In some embodiments, the irregular sleep data comprises at least one of:
sleep time deviation data for going to sleep;
time zone deviation data of the time zone in which the target user is located;
continuous state data of the irregular sleep;
frequency of occurrence of irregular sleep.
In some embodiments, the first obtaining module 110 is specifically configured to perform at least one of the following:
acquiring current season data;
acquiring illumination data of a space where a current target user is located;
acquiring temperature data of a space where a current target user is located;
and/or the presence of a gas in the gas,
in some embodiments, the second obtaining module 120 is specifically configured to obtain the static feature data of the user; and acquiring the dynamic characteristic data of the user.
In some embodiments, the second obtaining module 120 is specifically configured to perform at least one of the following:
acquiring current action characteristic data of the target user;
and acquiring current physical sign characteristic data of the target user.
In some embodiments, the apparatus further comprises:
the first denoising module is used for performing first denoising processing on the characteristic data, removing first noise data outside a preset frequency range and obtaining first characteristic data;
the second denoising module is used for carrying out correlation analysis filtering on the first characteristic data, removing second noise data located in the preset frequency range and obtaining second characteristic data;
the analysis module is used for analyzing the second characteristic data to obtain third characteristic data representing the state of the target user;
the third obtaining module is specifically configured to input the third feature data and the environment data to a regular sleep model and an irregular sleep model of the target user to obtain the light control parameter.
In some embodiments, the parsing module is specifically configured to parse the second feature data, and extract time-domain feature data of the target user from the second feature data, where the time-domain feature data includes: peak data and/or trough data of a characteristic curve corresponding to the second characteristic data in the time domain; peak data and/or trough data of the action curve or the physical sign change curve of the target user;
and/or analyzing the second characteristic data, and extracting frequency domain characteristic data of the target user from the second characteristic data; wherein the frequency domain feature data comprises: and peak data and/or trough data of the characteristic curve corresponding to the second characteristic data in the frequency domain.
In some embodiments, the first noise data comprises: acquiring jitter data of which the jitter frequency is outside the preset frequency range, electromagnetic interference data of which the electromagnetic frequency is outside the preset frequency range and magnetic field noise of which the electromagnetic frequency is outside the preset range of the equipment; and/or, the second noise data comprises: and acquiring jitter data of which the jitter frequency is within the preset frequency range.
In some embodiments, the third obtaining module 140 is specifically configured to perform dimension reduction processing on the third feature data and the environment data according to a dimension reduction processing policy to obtain input data with a preset dimension; and inputting input data of a preset dimension into the regular sleep model and the irregular sleep model to obtain the light control parameters.
In some embodiments, the third obtaining module 140 is specifically configured to determine whether the target user is in an overall still state based on a first preset condition in combination with the motion characteristic data of the target user; if the target user is in an action state, determining whether the target user is in a first type of local static state according to the action characteristic data; if the target user is not in the first type of local static state, determining whether the target user is in a second type of local static state according to the action characteristic data; and if the target user is in an action state, sampling the action characteristic data of the target user according to the current action state of the target user to obtain sampling characteristic data serving as the input data.
In some embodiments, the third obtaining module 140 is specifically configured to, if the target user is in a global stationary state, stop the determination of whether the target user is in the first type of local stationary state and the second type of local stationary state; and/or if the target user is in the first type of local static state, stopping the determination of whether the target user is in the second type of local static state.
In some embodiments, the apparatus further comprises:
a fourth obtaining module, configured to obtain effect data of the light control after controlling light emission of the light emitting device by using the light control parameter, where the effect data includes: sleep effect data and/or sleep activity data of the target user;
and the optimizing module is used for optimizing the regular sleep model and the irregular sleep model according to the effect data.
Several specific examples are provided below in connection with any of the embodiments described above:
example 1:
according to the invention, the actions and the heart rate of a user are acquired through the intelligent bracelet, and color light regulation projection is carried out through intelligent equipment such as an intelligent projection mobile phone or a gateway, so that the learning and working environments are improved in a self-adaptive manner. The method is characterized in that light rays with different wavelengths, seasons and personal physical sign conditions are combined, a color sleep regulation model which is most suitable for each person is predicted through a corresponding portrait model in the whole crowd, and supervised learning is carried out according to an individual sleep effect evaluation model which is established according to the heart rate and action change causing bracelet detection, so that a regular sleep model or an irregular sleep model which is most suitable for individual color sleep regulation is established, and the regular sleep model or the irregular sleep model is continuously corrected according to a genetic algorithm. The opposite direction of promoting sleep at the same time is to inhibit sleep, so that the awake state inhibits sleep.
In some embodiments, a test sample of a primary label is obtained, the test sample is led into the demand model, and the accuracy of the demand model is obtained according to the output result of the demand model; the demand models herein may include the regular sleep models and irregular sleep models previously described.
When the accuracy does not meet the requirement of preset accuracy, modifying the influence weight of each influence factor in the training sample and the training sample according to the accuracy of the demand model;
and training the demand model by using the modified training sample until the accuracy of the obtained demand model meets the preset accuracy requirement.
Optionally, the step of obtaining a generic model matching the primary label from a plurality of generic models of the database includes:
searching a universal model matched with the crowd type of the primary label from the plurality of universal models of the database according to the crowd type of the primary label;
and selecting a universal model consistent with the next-level label forming condition of the first-level label from the searched universal models according to the next-level label forming condition in the first-level label.
Optionally, each of the influencing factors includes a plurality of features, and the step of preprocessing the training samples includes:
detecting whether the comprehensive output amplitude of the plurality of influence factors in the training sample is in a preset range;
if the influence factors are not in the preset range, respectively calculating the variance value of the comprehensive output amplitude of each influence factor relative to the influence factors in the general model;
and detecting whether the variance value corresponding to each influence factor is larger than a preset threshold value, if so, randomly extracting a preset number of influence factors from the plurality of influence factors, and normalizing the characteristics of each influence factor in the extracted influence factors to simplify the data volume of each influence factor.
Optionally, the general model is constructed based on a neural network, the neural network includes an input layer, an output layer, and a hidden layer, the input layer, the output layer, and the hidden layer respectively include a plurality of neurons, the neurons between the input layer, the output layer, and the hidden layer have connection weight values, the step of training the general model by introducing the preprocessed training samples into the general model includes:
leading the preprocessed training sample into an input layer of the neural network, and outputting the training sample from the output layer after the training of the hidden layer;
detecting whether the result output by the output layer reaches an expected result, if not, obtaining an error signal according to the output result and the expected result, and entering a back propagation stage;
and taking the error signal as an input signal in a back propagation stage to reversely return from the output layer to the input layer, and modifying connection weight values of neurons among the input layer, the output layer and the hidden layer in the process of reversely returning so as to gradually reduce the finally output error signal.
Optionally, the step of modifying the connection weight values of the neurons between the input layer, the output layer and the hidden layer during the backward feedback to gradually reduce the finally output error signal includes:
during the backward feedback, the connection weight values of the neurons between the input layer, the output layer and the hidden layer are modified by the following formula to gradually reduce the finally output error signal:
Figure BDA0001934317190000211
wherein, WijRepresents the weight value of the connection between the ith neuron of the input layer and the jth upgrade of the hidden layer, XPThe ith input value of the P-th training sample in the input layer,
Figure BDA0001934317190000212
representing the threshold of the jth neuron of the hidden layer.
Optionally, the step of modifying the training sample according to the influence weight of the accuracy of the demand model on each influence factor in the training sample includes:
comparing the accuracy of the current demand model with the accuracy of the demand model obtained in the historical times;
if the accuracy of the currently obtained demand model is higher than the accuracy of more than half of the demand model obtained in the historical times, keeping the current training sample, and modifying the influence weight of each influence factor;
and if the accuracy of the currently obtained demand model is lower than the accuracy of more than half of the demand model obtained in the historical times, deleting part of the training samples in the training samples, and adding new training samples.
Optionally, after the step of modifying the training sample according to the influence weight of the accuracy of the demand model on each influence factor in the training sample, the method further includes:
establishing a fitness function to evaluate the fitness value of each training sample in the modified training samples, and selecting the training sample with the highest fitness value by utilizing a selection mechanism of a genetic algorithm;
randomly selecting any two training samples from a plurality of training samples by using a crossing mechanism of a genetic algorithm to cross so as to obtain a next generation of training samples;
calculating a training sample with the highest fitness value in the next generation of training samples by using the fitness function;
detecting whether the fitness value of the training sample of the next generation is lower than that of the training sample of the previous generation, if so, introducing a variation factor by using a variation mechanism of a genetic algorithm to perform variation operation on the training sample of the next generation, and then calculating the fitness value of the training sample after the variation operation;
and modifying the training samples again according to the fitness values of the training samples.
Optionally, after the step of training the demand model by using the modified training sample until the accuracy of the obtained demand model meets the preset accuracy requirement, the method further includes:
receiving currently input information to be detected, wherein the information to be detected carries a plurality of different influence factors, and each influence factor carries a corresponding influence weight;
importing the information to be tested into the demand model for prediction to obtain a prediction result;
receiving feedback information of the prediction result of the demand model, which is input by a user;
and adjusting the model parameters of the demand model according to the feedback information.
Optionally, after the step of obtaining the accuracy of the demand model, the method further includes:
and storing the obtained demand model meeting the preset accuracy requirement into the database so as to update the data in the database.
An embodiment of the present application further provides a data processing apparatus, where the data processing apparatus includes:
the general model acquisition module is used for acquiring a general model matched with the primary label from a plurality of general models of the database;
the training sample acquisition module is used for acquiring a training sample of a primary label, wherein the training sample carries a plurality of different influence factors, each influence factor carries a corresponding influence weight, and the training sample comprises employee characteristics and medical resource allocation information of the primary label;
the requirement model obtaining module is used for preprocessing the training sample, guiding the preprocessed training sample into the general model and training the general model to obtain a requirement model corresponding to the primary label;
the accuracy obtaining module is used for obtaining a test sample of the primary label, introducing the test sample into the demand model, and obtaining the accuracy of the demand model according to the output result of the demand model;
the modification module is used for modifying the influence weight of each influence factor in the training sample and the training sample according to the accuracy of the demand model when the accuracy does not meet the preset accuracy requirement;
and the training module is used for training the demand model by using the modified training sample until the accuracy of the obtained demand model meets the preset accuracy requirement.
The supervised classification algorithm is used, environment data is used as an input layer, and the individual sleep quality score is used as an output layer. By comparing with the model (historical optimal environment data) formed by last environment data input, the quality of individual evaluation is used as a training supervision factor, and is better 1 and worse 0.
And (3) forward propagation of the working signal, wherein the weight and threshold values of each neuron of the network are kept unchanged, each layer of neurons only affects the input and the state of the next layer of neurons, and if the expected output value is not obtained at the output end, the network is switched into a backward propagation process of the error signal. And (3) reversely propagating the error signals, wherein the error signals are transmitted back layer by layer from the output end, and in the propagation process, the weight and the threshold of each neuron of the network are adjusted according to a certain rule by error feedback. The two stages are alternately and circularly carried out, and each time the two stages are completed, the correction is carried out by using a genetic algorithm.
Meanwhile, the individual serves as a new input factor of the crowd corresponding to the portrait of the whole crowd, the SVM is used for genetically correcting the crowd environment model corresponding to the portrait of the whole crowd, and the user portrait of the sleep environment of the corresponding crowd is continuously and clearly refined. Fitness function f (x) of SVM classifieri)＝min(1-g(xi))，
Figure BDA0001934317190000231
Dividing the sample into correct rate for SVM classifier, and replacing original model with the model if the correct rate is higher than the historical optimum model with the increase of sample amountAnd optimizing the model, so that the model self-adaptation is continuously optimized and perfected as the sample size increases.
The adaptive improvement of the model can comprise: with the increase of the sample size, the SVM classifier can be adaptively and continuously optimized and perfected.
Fitness function f (x) of SVM classifieri)＝min(1-g(xi))，
Figure BDA0001934317190000241
The sample division accuracy for the SVM classifier comprises the following steps:
performing 3D modeling;
setting a boundary condition;
calculating an unsteady state;
is the boundary condition judged to change?
If not, the judgment result is constant? If not, setting the angle, the advancing path and the rendering effect of the camera; if yes, returning to the non-constant calculation;
if yes, returning to set boundary conditions.
The boundary condition here is the boundary of the classification of the SVM classifier.
The appropriate illumination of the sleep-assisting lamp (N1 light sleep stage (1200 + 7000L ux, N4 before automatic wake-up, and 2500 + 10000lux received in REM stage) can increase the generation of melatonin in the organism, which has circadian rhythm and reaches the peak in midnight secretion, contributes to deepening the sleep depth (the specific gravity of REM and N4), changes the sleep-wake-up rhythm, adjusts the physiological clock, and adjusts the sleep quality.
The genetic research shows that the non-visual effect is the maximum in 480-485 nm, the sensitivities of different wavelengths of visible light are different, the sensitivity of the visible light to yellow and green light is the highest, and the sensitivities to red light, blue light and purple light are very low. Under the irradiation of 1000lx, the red, green and blue 3 color lights respectively have the inhibition rate on black fading hormone, the red light is small, the green light is the largest, the blue light is slightly low, the heart rate can be obviously increased by the irradiation of the light, the shorter the wavelength is, the more obvious the heart rate is, and the younger people are more obvious than the old people. Human beings are most sensitive to light with the wavelength of 480-485 nm, different people are affected by yellow pigment in a macular region in the retina of the human eyes, and the visual crystals become yellow with the increase of age, so that individual difference can be caused.
People with different ages and sleeping constitutions can have different time for entering each sleeping stage and different sensitivity degrees to light, and the same sleep-assisting illumination adjusting mechanism for each person is set according to the time for general people to enter each sleeping stage. Sleep may be adversely affected, e.g. shallow sleep for the elderly, 24: 00 has not yet entered a light sleep, and sleep may instead be affected.
Example 2:
as shown in fig. 4, the present example provides a data processing method for sleep adjustment, and in particular, for sleep adjustment of irregular sleep, the method specifically includes:
detecting current state data of a target user;
judging whether the sleep of the current user is regular sleep according to the current state data;
if so, carrying out light control by combining the collected environmental data and the characteristic data of the target user by using a regular sleep model;
if not, the light control is carried out by combining the collected environmental parameters, the characteristic data and the current state data by using the irregular sleep model.
Further, as shown in fig. 5, the data processing method provided by this example may include the following steps when adjusting for irregular sleep:
determining whether the target user is in a sleep lacking state or not according to the current state data;
if not, controlling the light-emitting equipment to emit light for suppressing sleep;
if yes, determining whether the current time zone of the target user is in the sleep time range according to the position of the target user; the sleep time range can be the insomnia time range of the target user regularly sleeping in one day;
if yes, controlling the light-emitting device to emit light for promoting sleep;
if not, determining whether the absent level of sleep is greater than a predetermined level;
if the light emitting time is greater than the preset level, controlling the light emitting equipment to emit light for promoting sleep within a preset time period, and controlling the light emitting equipment to emit light for inhibiting sleep after the light for promoting sleep is emitted for the preset time period;
if the level is not more than the preset level, the light-emitting device is controlled to emit light for suppressing the sleep.
Determining that the absent level of the target user in sleep is greater than a preset level, and judging whether the duration of the target user in continuous sleep reaches the duration corresponding to the preset level; or, the current state of the target user represents that the physical sign state of the target user lacking sleep is not good than the physical sign state corresponding to the predetermined grade, and the like. In summary, there are many ways to determine whether the level of the target user's lack of consciousness during sleep is greater than a predetermined level, and is not limited to any one of the above. As shown in fig. 6, the present embodiment provides an electronic apparatus including:
a memory for information storage;
and the processor is connected with the memory and used for realizing the method provided by one or more of the technical schemes, such as one or more of the methods shown in fig. 1, fig. 2, fig. 4, fig. 5, by executing the computer-executable instructions stored by the memory. In some embodiments, the electronic device further comprises: a communication interface and/or a human-machine interaction interface, the communication interface may include: the receiving and transmitting antenna and/or the network interface can be used for information interaction with other electronic equipment. The human-computer interaction interface can be used for interacting with a human, and the human-computer interaction interface can comprise: physical keys and/or a touch screen.
The present embodiments provide a computer storage medium for storing computer-executable instructions; the computer-executable instructions, when executed by a processor, enable one or more of the methods provided by the foregoing aspects, for example, one or more of the methods shown in fig. 1, fig. 2, fig. 4, and fig. 5.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may be separately used as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims (16)

1. A data processing method, comprising:
acquiring environmental data;
acquiring current state data and characteristic data of a target user;
selecting a regular sleep model or an irregular sleep model as a target model according to the current state data;
inputting the environmental data and the characteristic data into a selected target model to obtain light control parameters;
controlling light emission of a light emitting device using the light control parameter, wherein the controlling light emission of the light emitting device comprises: controlling the light emitting device to emit light that promotes sleep of the target user, or controlling the light emitting device to emit light that inhibits sleep of the target user.
2. The method of claim 1, wherein selecting a regular sleep model or an irregular sleep model as a target model according to the current sleep state of the target user comprises at least one of:
if the current state data indicate that the current sleep state of the target user does not accord with the sleep rule corresponding to the regular sleep model, selecting the irregular sleep model as the target model;
and if the current state data indicate that the current sleep state of the target user accords with the sleep rule corresponding to the regular sleep model, selecting the regular sleep model as the target model.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
if the target model is a non-sleep regular model, acquiring non-regular sleep data of the target user;
the step of inputting the environment data and the feature data into a selected target model to obtain light control parameters comprises the following steps:
and inputting the environment data, the feature data and the irregular sleep-comforting data into the irregular sleep model to obtain the light control parameters.
4. The method of claim 3, wherein the irregular sleep data comprises at least one of:
sleep time deviation data for going to sleep;
time zone deviation data of the time zone in which the target user is located;
continuous state data of the irregular sleep;
frequency of occurrence of irregular sleep.
5. The method of claim 1,
the obtaining environmental data includes at least one of:
acquiring current season data;
acquiring illumination data of a space where a current target user is located;
acquiring temperature data of a space where a current target user is located;
and/or the presence of a gas in the gas,
the acquiring of the feature data of the target user comprises:
acquiring static characteristic data of the user;
and acquiring the dynamic characteristic data of the user.
6. The method of claim 5, wherein the obtaining dynamic profile data of the user comprises at least one of:
acquiring current action characteristic data of the target user;
and acquiring current physical sign characteristic data of the target user.
7. The method according to claim 1 or 2, characterized in that the method further comprises:
performing first denoising processing on the characteristic data, removing first noise data outside a preset frequency range and obtaining first characteristic data;
performing correlation analysis filtering on the first characteristic data, removing second noise data located in the preset frequency range and obtaining second characteristic data;
analyzing the second characteristic data to obtain third characteristic data representing the state of the target user;
the step of inputting the environment data and the feature data into a selected target model to obtain light control parameters comprises the following steps:
and inputting the third characteristic data and the environment data into a target model of the target user to obtain the light control parameter.
8. The method of claim 7, wherein the parsing the second feature data to obtain third feature data characterizing the target user state comprises:
analyzing the second feature data, and extracting time domain feature data of the target user from the second feature data, wherein the time domain feature data comprises: peak data and/or trough data of a characteristic curve corresponding to the second characteristic data in the time domain;
peak data and/or trough data of the action curve or the physical sign change curve of the target user;
and/or the presence of a gas in the gas,
analyzing the second characteristic data, and extracting frequency domain characteristic data of the target user from the second characteristic data; wherein the frequency domain feature data comprises: and peak data and/or trough data of the characteristic curve corresponding to the second characteristic data in the frequency domain.
9. The method of claim 7,
the first noise data includes: acquiring jitter data of which the jitter frequency is outside the preset frequency range, electromagnetic interference data of which the electromagnetic frequency is outside the preset frequency range and magnetic field noise of which the electromagnetic frequency is outside the preset range of the equipment;
and/or the presence of a gas in the gas,
the second noise data includes: and acquiring jitter data of which the jitter frequency is within the preset frequency range.
10. The method of claim 7, wherein inputting the environmental data and the characteristic data into a selected target model to obtain light control parameters comprises:
performing dimensionality reduction processing on the third characteristic data and the environmental data according to a dimensionality reduction processing strategy to obtain input data with preset dimensionality;
and inputting input data of a preset dimension into the target model to obtain the light control parameters.
11. The method according to claim 10, wherein performing dimension reduction processing on the third feature data and the environment data according to a dimension reduction processing policy to obtain input data of a preset dimension comprises:
determining whether the target user is in an overall static state or not based on a first preset condition and the action characteristic data of the target user;
if the target user is in an action state, determining whether the target user is in a first type of local static state according to the action characteristic data;
if the target user is not in the first type of local static state, determining whether the target user is in a second type of local static state according to the action characteristic data;
and if the target user is in an action state, sampling the action characteristic data of the target user according to the current action state of the target user to obtain sampling characteristic data serving as the input data.
12. The method according to claim 11, wherein the performing dimension reduction processing on the third feature data and the environment data according to a dimension reduction processing policy to obtain input data of a preset dimension further comprises:
if the target user is in the overall static state, stopping determining whether the target user is in the first type of local static state and the second type of local static state;
and/or the presence of a gas in the gas,
and if the target user is in the first type of local static state, stopping the determination of whether the target user is in the second type of local static state.
13. The method according to claim 1 or 2, wherein after said controlling the lighting of the lighting device using said light control parameter, the method further comprises:
obtaining effect data for light control, wherein the effect data comprises: at least one of sleep effect data, sleep activity data, and non-sleep activity data of the target user;
and optimizing the regular sleep model and/or the irregular sleep model according to the effect data.
14. A data processing apparatus, comprising:
the first acquisition module is used for acquiring environmental data;
the second acquisition module is used for acquiring the current state data and the characteristic data of the target user;
the selection module is used for selecting a regular sleep model or an irregular sleep model as a target model according to the current state data;
the third acquisition module is used for inputting the environmental data and the characteristic data into the selected target model to obtain light control parameters;
a control module for controlling light emission of the light emitting device using the light control parameter, wherein the controlling light emission of the light emitting device includes: controlling the light emitting device to emit light that promotes sleep of the target user, or controlling the light emitting device to emit light that inhibits sleep of the target user.
15. An electronic device, comprising:
a memory;
a processor coupled to the memory for implementing the data processing method provided in any one of claims 1 to 13 by executing computer executable instructions located on the memory.
16. A computer storage medium having stored thereon computer-executable instructions; the computer-executable instructions, when executed, enable the data processing method provided in any one of claims 1 to 13 to be implemented.
CN201910002765.1A 2019-01-02 2019-01-02 Data processing method and device, electronic equipment and storage medium Active CN111460850B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910002765.1A CN111460850B (en) 2019-01-02 2019-01-02 Data processing method and device, electronic equipment and storage medium
PCT/CN2019/130837 WO2020140913A1 (en) 2019-01-02 2019-12-31 Data processing method and apparatus, electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910002765.1A CN111460850B (en) 2019-01-02 2019-01-02 Data processing method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN111460850A true CN111460850A (en) 2020-07-28
CN111460850B CN111460850B (en) 2023-05-12

Family

ID=71407277

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910002765.1A Active CN111460850B (en) 2019-01-02 2019-01-02 Data processing method and device, electronic equipment and storage medium

Country Status (2)

Country Link
CN (1) CN111460850B (en)
WO (1) WO2020140913A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022056916A1 (en) * 2020-09-21 2022-03-24 Siemens Aktiengesellschaft Controlling method and device for industrial device
CN116095922A (en) * 2023-03-13 2023-05-09 广州易而达科技股份有限公司 Lighting lamp control method and device, lighting lamp and storage medium
CN116170915A (en) * 2023-04-23 2023-05-26 深圳市帝狼光电有限公司 Eye-protection lamp system, eye-protection lamp control method and eye-protection lamp
WO2023236668A1 (en) * 2022-06-06 2023-12-14 北京芯格诺微电子有限公司 Adaptive switch-cycle control method applied to switch power supply

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112799572B (en) * 2021-01-28 2023-04-07 维沃移动通信有限公司 Control method, control device, electronic equipment and storage medium
CN114675556B (en) * 2022-03-29 2023-12-26 浙江想能睡眠科技股份有限公司 Personalized sleep-aiding intelligent pillow device and control method
CN114767910A (en) * 2022-04-13 2022-07-22 山东浪潮新基建科技有限公司 Disinfection control method and controller

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012146256A2 (en) * 2011-04-28 2012-11-01 Lighten Aps A lighting system and a method for locally changing light conditions
CN105873319A (en) * 2016-04-25 2016-08-17 乐视控股（北京）有限公司 Light control method and terminal equipment
CN106879133A (en) * 2016-12-29 2017-06-20 固安翌光科技有限公司 The control method and device of light during a kind of sleep
WO2017101111A1 (en) * 2015-12-18 2017-06-22 苏州大学 Biological rhythm adjustment system and biological rhythm adjustment method
CN106913313A (en) * 2015-12-28 2017-07-04 中国移动通信集团公司 A kind of sleep monitor method and system
WO2018049842A1 (en) * 2016-09-13 2018-03-22 深圳市迈迪加科技发展有限公司 Sleep control system, control method for sleep device, and processing device
CN108201435A (en) * 2017-12-06 2018-06-26 深圳和而泰数据资源与云技术有限公司 Sleep stage determines method, relevant device and computer-readable medium
CN109084432A (en) * 2018-08-20 2018-12-25 广东美的暖通设备有限公司 The regulation method and air conditioner of sleep environment

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104121515B (en) * 2014-06-27 2017-02-15 河海大学常州校区 Sleep adjusting lamp and method
US20170065792A1 (en) * 2015-09-03 2017-03-09 Withings Method and System to Optimize Lights and Sounds For Sleep
CN105517302B (en) * 2016-01-29 2019-08-02 宇龙计算机通信科技(深圳)有限公司 A kind of method for controlling lamp and lamp control device
CN107743331B (en) * 2017-10-18 2019-11-05 普联技术有限公司 Light source control method, device and system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012146256A2 (en) * 2011-04-28 2012-11-01 Lighten Aps A lighting system and a method for locally changing light conditions
WO2017101111A1 (en) * 2015-12-18 2017-06-22 苏州大学 Biological rhythm adjustment system and biological rhythm adjustment method
CN106913313A (en) * 2015-12-28 2017-07-04 中国移动通信集团公司 A kind of sleep monitor method and system
CN105873319A (en) * 2016-04-25 2016-08-17 乐视控股（北京）有限公司 Light control method and terminal equipment
WO2018049842A1 (en) * 2016-09-13 2018-03-22 深圳市迈迪加科技发展有限公司 Sleep control system, control method for sleep device, and processing device
CN106879133A (en) * 2016-12-29 2017-06-20 固安翌光科技有限公司 The control method and device of light during a kind of sleep
CN108201435A (en) * 2017-12-06 2018-06-26 深圳和而泰数据资源与云技术有限公司 Sleep stage determines method, relevant device and computer-readable medium
CN109084432A (en) * 2018-08-20 2018-12-25 广东美的暖通设备有限公司 The regulation method and air conditioner of sleep environment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张俊民;王蓓;王行愚;: "基于特征融合的ARMA短时睡眠状态分析" *
张朕;焦学军;潘津津;姜劲;曹勇;杨涵钧;徐凤刚;: "基于fNIRs技术的清醒-睡眠状态识别" *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022056916A1 (en) * 2020-09-21 2022-03-24 Siemens Aktiengesellschaft Controlling method and device for industrial device
WO2023236668A1 (en) * 2022-06-06 2023-12-14 北京芯格诺微电子有限公司 Adaptive switch-cycle control method applied to switch power supply
CN116095922A (en) * 2023-03-13 2023-05-09 广州易而达科技股份有限公司 Lighting lamp control method and device, lighting lamp and storage medium
CN116095922B (en) * 2023-03-13 2023-08-18 广州易而达科技股份有限公司 Lighting lamp control method and device, lighting lamp and storage medium
CN116170915A (en) * 2023-04-23 2023-05-26 深圳市帝狼光电有限公司 Eye-protection lamp system, eye-protection lamp control method and eye-protection lamp
CN116170915B (en) * 2023-04-23 2023-08-08 深圳市帝狼光电有限公司 Eye-protection lamp control method, eye-protection lamp system and medium

Also Published As

Publication number Publication date
WO2020140913A1 (en) 2020-07-09
CN111460850B (en) 2023-05-12

Similar Documents

Publication Publication Date Title
CN111460850B (en) Data processing method and device, electronic equipment and storage medium
US10589056B2 (en) Sleep inducing device and sleep management system including same
US20200178892A1 (en) Systems and methods for monitoring and modulating circadian rhythms
CN108310587A (en) A kind of sleep control device and method
CN110163371B (en) Dimming optimization method for sleep environment
JP4192127B2 (en) Sleep state management device and sleep state management method
CN105592777A (en) Method and system for sleep management
US20220370757A1 (en) Personalized sleep wellness score for treatment and/or evaluation of sleep conditions
CN110706816A (en) Method and equipment for regulating sleep environment based on artificial intelligence
CN111657855B (en) Sleep evaluation and sleep awakening method and device and electronic equipment
KR20220110475A (en) Cluster-Based Sleep Analysis
US20220375572A1 (en) Iterative generation of instructions for treating a sleep condition
US11395902B2 (en) System and method for waking a user up with a stimulus of varying intensity
CN114073493B (en) Physiological data acquisition method and device and wearable equipment
KR101912860B1 (en) Smart jewelry system for depression cognitive and care
KR102026774B1 (en) Smart emotion lighting device
CN109999310A (en) Light source and the combination control method of sound source, device and computer readable storage medium
CN115779227A (en) Method and system for improving deep sleep quality and pleasure feeling in closed-loop manner
US20230329631A1 (en) Systems and methods involving sleep management
US20210011614A1 (en) Method and apparatus for mood based computing experience
CN210583316U (en) Sleep-assisting system and sleep-assisting lamp thereof
US20230277106A1 (en) Hot flash multi-sensor circuit system
CN110169202A (en) Lighting control
US20230059947A1 (en) Systems and methods for awakening a user based on sleep cycle
US20220176152A1 (en) Method and system for improving light intake, light exposure, and lifestyle management of a user

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant