CN116130102A

CN116130102A - Sleep environment data determining method and device, storage medium and electronic device

Info

Publication number: CN116130102A
Application number: CN202211670287.XA
Authority: CN
Inventors: 于海松; 李华刚
Original assignee: Qingdao Haier Technology Co Ltd; Haier Smart Home Co Ltd; Haier Uplus Intelligent Technology Beijing Co Ltd
Current assignee: Qingdao Haier Technology Co Ltd; Haier Smart Home Co Ltd; Haier Uplus Intelligent Technology Beijing Co Ltd
Priority date: 2022-12-24
Filing date: 2022-12-24
Publication date: 2023-05-16

Abstract

The application discloses a method and a device for determining sleep environment data, a storage medium and an electronic device, and relates to the technical field of smart families, wherein the method for determining sleep environment data comprises the following steps: acquiring target object feature data of a target object and acquiring target area feature data of a target area where the target object is currently located; determining initial sleep environment data according to the target object characteristic data and the target area characteristic data; performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object. By adopting the technical scheme, the problem that the optimal sleeping environment of the user cannot be determined is solved.

Description

Sleep environment data determining method and device, storage medium and electronic device

Technical Field

The application relates to the technical field of smart families, in particular to a method and a device for determining sleep environment data, a storage medium and an electronic device.

Background

Along with the continuous development of intelligent internet of things technology, more and more people select intelligent home, environmental change factors are identified in real time, and then comfortable home environment is provided for users, currently, users like to use a sleep instrument to monitor own sleep condition when sleeping, but after the users take a sleep report of the sleep instrument, the users can only know the quality of own sleep through the sleep report, other operations can not be further carried out, and the users can not know how the best sleep environment of the users is through the sleep instrument.

Aiming at the problem that the optimal sleeping environment of the user cannot be determined in the related art, no effective solution is proposed at present.

Accordingly, there is a need for improvements in the related art to overcome the drawbacks of the related art.

Disclosure of Invention

The embodiment of the invention provides a method and a device for determining sleep environment data, a storage medium and an electronic device, which are used for at least solving the problem that the optimal sleep environment of a user cannot be determined.

According to an aspect of the embodiment of the present invention, there is provided a method for determining sleep environment data, including: acquiring target object feature data of a target object and acquiring target area feature data of a target area where the target object is currently located; determining initial sleep environment data according to the target object characteristic data and the target area characteristic data; performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object.

In one exemplary embodiment, obtaining target object feature data of a target object includes: acquiring the gender, age and life habit type of the target object; the obtaining the characteristic data of the target area of the current target area of the target object comprises the following steps: determining the current time and the geographic position of a target area where the target object is currently located; and determining a current season and a current weather according to the current time and the geographic position, wherein the target area characteristic data comprises the geographic position, the current season and the current weather.

In one exemplary embodiment, determining initial sleep environment data from the target object feature data and the target region feature data includes: acquiring the corresponding relation between object feature data, regional feature data and sleep environment data; and determining initial sleep environment data corresponding to the target object characteristic data and the target area characteristic data according to the corresponding relation.

In an exemplary embodiment, reinforcement learning is performed on the initial sleep environment data to obtain target sleep environment data, including: in the case that the initial sleep environment data includes parameter values of N sleep environment parameters, determining a target parameter value of an i-th sleep environment parameter of the N sleep environment parameters to obtain target sleep environment data, where i is greater than or equal to 1 and less than or equal to N: increasing the parameter value of the ith sleep environment parameter, and monitoring the sleep quality of the target object in the corresponding sleep environment through a sleep monitoring device; continuing to increase the parameter value of the ith sleep environment parameter until the parameter value of the ith sleep environment parameter is increased to the target parameter value under the condition that the sleep quality of the target object is monitored to be good; when the parameter value of the ith sleep environment parameter is a target parameter value, continuing to increase the parameter value of the ith sleep environment parameter may cause the sleep quality of the target object to be degraded; or reducing the parameter value of the ith sleep environment parameter, and monitoring the sleep quality of the target object in the corresponding sleep environment through a sleep monitoring device; continuing to reduce the parameter value of the ith sleep environment parameter until the parameter value of the ith sleep environment parameter is reduced to the target parameter value under the condition that the sleep quality of the target object is monitored to be good; when the parameter value of the ith sleep environment parameter is the target parameter value, continuing to decrease the parameter value of the ith sleep environment parameter may cause the sleep quality of the target object to be degraded.

In an exemplary embodiment, reinforcement learning is performed on the initial sleep environment data to obtain target sleep environment data, including: determining a target sleep environment parameter to be adjusted of the target object and a corresponding parameter value according to the equipment control instruction when the equipment control instruction sent by the target object is acquired, wherein the equipment control instruction is an instruction sent by the target object in a sleep environment corresponding to the initial sleep environment data; and performing reinforcement learning on the initial sleep environment data through the target sleep environment parameters and the corresponding parameter values to obtain target sleep environment data.

In an exemplary embodiment, after obtaining the target sleep environment data, the method further includes: acquiring historical sleep data of the target object, wherein the historical sleep data is used for describing a historical sleep cycle of the target object; under the condition that the sleep monitoring device determines that the target object enters a first sleep state after a preset time through the historical sleep data, determining first sleep environment data corresponding to the first sleep state through the target sleep environment data, wherein the target sleep environment data comprises sleep environment data corresponding to different sleep states in a sleep period; after the preset time, controlling the equipment in the equipment set to execute target operation according to the first sleep environment data, so that the sleep environment after the preset time is the sleep environment corresponding to the first sleep environment data.

In one exemplary embodiment, controlling devices in a set of devices to perform a target operation according to first sleep environment data includes: determining each sleep environment parameter and corresponding parameter value in the first sleep environment data; determining equipment corresponding to each sleep environment parameter, and controlling the corresponding equipment to adjust each sleep environment parameter in the current sleep environment according to the corresponding parameter value; wherein the sleep environment parameters include at least: temperature, humidity, light intensity, oxygen content, ambient volume.

According to another aspect of the embodiment of the present invention, there is also provided a device for determining sleep environment data, including: the acquisition module is used for acquiring target object characteristic data of a target object and acquiring target area characteristic data of a target area where the target object is currently located; the first determining module is used for determining initial sleep environment data according to the target object characteristic data and the target area characteristic data; the second determining module is used for performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object.

According to still another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium having a computer program stored therein, wherein the computer program is configured to perform the above-described sleep environment data determination method when run.

According to still another aspect of the embodiment of the present invention, there is further provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the method for determining sleep environment data by using the computer program.

According to the invention, initial sleep environment data is determined according to the target object characteristic data of the target object and the target area characteristic data of the target area, and reinforcement learning is carried out on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object. The optimal sleeping environment of the target object is determined in a reinforcement learning mode, so that the problem that the optimal sleeping environment of the user cannot be determined is solved, the user can sleep in the optimal sleeping environment, and the sleeping quality of the user is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a hardware environment schematic of a method for determining sleep environment data according to an embodiment of the present application;

FIG. 2 is a flow chart (one) of a method of determining sleep environment data according to an embodiment of the present invention;

FIG. 3 is a flow chart of a prior art sleep conditioning environment;

FIG. 4 is a flow chart (II) of a method of determining sleep environment data according to an embodiment of the present invention;

FIG. 5 is a timing diagram of a method of determining sleep environment data according to an embodiment of the invention;

FIG. 6 is an overall frame diagram (one) of a method of determining sleep environment data according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a sleep cycle according to an embodiment of the invention;

FIG. 8 is a schematic diagram of reinforcement learning according to an embodiment of the present invention;

fig. 9 is an overall frame diagram (two) of a method of determining sleep environment data according to an embodiment of the present invention;

fig. 10 is a block diagram of a structure of a sleep environment data determining apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

According to one aspect of the embodiments of the present application, a method for determining sleep environment data is provided. The method for determining the sleep environment data is widely applied to full-house intelligent digital control application scenes such as intelligent Home (Smart Home), intelligent Home equipment ecology, intelligent Home (intelligent house) ecology and the like. Alternatively, in the present embodiment, the above-described determination method of sleep environment data may be applied to a hardware environment constituted by the terminal device 102 and the server 104 as shown in fig. 1. As shown in fig. 1, the server 104 is connected to the terminal device 102 through a network, and may be used to provide services (such as application services and the like) for a terminal or a client installed on the terminal, a database may be set on the server or independent of the server, for providing data storage services for the server 104, and cloud computing and/or edge computing services may be configured on the server or independent of the server, for providing data computing services for the server 104.

The network may include, but is not limited to, at least one of: wired network, wireless network. The wired network may include, but is not limited to, at least one of: a wide area network, a metropolitan area network, a local area network, and the wireless network may include, but is not limited to, at least one of: WIFI (Wireless Fidelity ), bluetooth. The terminal device 102 may not be limited to a PC, a mobile phone, a tablet computer, an intelligent air conditioner, an intelligent smoke machine, an intelligent refrigerator, an intelligent oven, an intelligent cooking range, an intelligent washing machine, an intelligent water heater, an intelligent washing device, an intelligent dish washer, an intelligent projection device, an intelligent television, an intelligent clothes hanger, an intelligent curtain, an intelligent video, an intelligent socket, an intelligent sound box, an intelligent fresh air device, an intelligent kitchen and toilet device, an intelligent bathroom device, an intelligent sweeping robot, an intelligent window cleaning robot, an intelligent mopping robot, an intelligent air purifying device, an intelligent steam box, an intelligent microwave oven, an intelligent kitchen appliance, an intelligent purifier, an intelligent water dispenser, an intelligent door lock, and the like.

In order to solve the above-mentioned problems, there is provided a method for determining sleep environment data in the present embodiment, including but not limited to being applied to the above-mentioned server or terminal, fig. 2 is a flowchart of a method for determining sleep environment data according to an embodiment of the present invention, the flowchart including the steps of:

step S202, obtaining target object characteristic data of a target object and obtaining target area characteristic data of a target area where the target object is currently located;

as an alternative example, the target object is a user. The target zone is the current living zone of the target object, for example: a city, a county/district, etc. The target region feature data may be used to reflect features of the target region in different dimensions. For example: location, season, weather, etc.

As an alternative example, acquiring target object feature data of a target object includes: and acquiring the gender, age and lifestyle type of the target object. It should be noted that, the lifestyle types are types selected from several types defined in advance by analyzing lifestyle data of the target object, and include, but are not limited to: the high intensity exercise type, the low intensity exercise type, the high protein food type, the electronic product type used for a long time before sleeping, the work type before sleeping, etc. are frequently performed. The lifestyle type of the target object.

It should be noted that, the feature data of the target object includes tags of the target object in different dimensions, which may be used to describe the portrait of the target object.

As an optional example, acquiring target area feature data of a target area where the target object is currently located includes: determining the current time and the geographic position of a target area where the target object is currently located; and determining a current season and a current weather according to the current time and the geographic position, wherein the target area characteristic data comprises the geographic position, the current season and the current weather.

The current time includes the current year, month, date, and specific time of day (xx hours xx minutes xx seconds). The geographic location includes the province, city, county, room location, room orientation, etc. where the current location is located, and may also include latitude and longitude. The current season includes: spring, summer, autumn and winter; current weather includes: cloudy, sunny, cloudy, rainy, snowy, etc.

In this embodiment, the target area feature data of the target area where the user is currently located can be accurately determined through the time and the position.

Step S204, determining initial sleep environment data according to the target object characteristic data and the target area characteristic data;

It should be noted that, the initial sleep environment data includes parameter values corresponding to a plurality of sleep environment parameters; the sleep environment parameters include at least: temperature, humidity, light intensity, oxygen content, ambient volume.

As an alternative example, the above step S204 may be implemented by: acquiring the corresponding relation between object feature data, regional feature data and sleep environment data; and determining initial sleep environment data corresponding to the target object characteristic data and the target area characteristic data according to the corresponding relation.

It should be noted that the object feature data and the region feature data are one general term, and the target object feature data and the target region feature data are one specific term, that is, the target object feature data is one specific term of the object feature data, and the target region feature data is one specific term of the region feature data. For example, fruit is a flood finger, while the target fruit (fruit) is a particular one.

It should be noted that, the corresponding relation between the object feature data and the region feature data and the sleep environment data may be stored in a database, where the database has different object feature data and different sleep environment data corresponding to different region feature data. It should be noted that, the optimal sleep environment data of the target object corresponding to the different object feature data is different, and the optimal sleep environment data of the user in the region corresponding to the different region feature data is also different. And then the initial sleep environment data which is close to the optimal sleep environment of the user can be found out in the database through the target object characteristic data and the target area characteristic data.

In this embodiment, by the above manner, the initial sleep environment data corresponding to the target object feature data and the target area feature data may be quickly and accurately determined, so that the optimal sleep environment data close to the optimal sleep environment of the user may be determined by the target object feature data and the target area feature data, and the reinforcement learning time may be reduced.

Step S206, performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in the target area, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object.

As an alternative example, the initial sleep environment data may be reinforcement-learned by the reinforcement-learning model and the sleep monitoring device to obtain the target sleep environment data. The principle of the reinforcement learning model is illustrated in fig. 8, for example.

As an alternative example, the sleep monitoring apparatus includes, but is not limited to, a sleep monitor for monitoring a sleep state of a user, deriving a sleep report, the sleep including a sleep quality that may reflect a target subject.

As an alternative example, the above step S206 may be implemented by:

Under the condition that the initial sleep environment data comprises parameter values of N sleep environment parameters, determining target parameter values of an ith sleep environment parameter in the N sleep environment parameters in a first mode or a second mode to obtain target sleep environment data, wherein i is greater than or equal to 1 and less than or equal to N:

mode one: increasing the parameter value of the ith sleep environment parameter, and monitoring the sleep quality of the target object in the corresponding sleep environment through a sleep monitoring device; continuing to increase the parameter value of the ith sleep environment parameter until the parameter value of the ith sleep environment parameter is increased to the target parameter value under the condition that the sleep quality of the target object is monitored to be good; when the parameter value of the ith sleep environment parameter is a target parameter value, continuing to increase the parameter value of the ith sleep environment parameter may cause the sleep quality of the target object to be degraded;

as an alternative example, the sleep monitoring apparatus may obtain a sleep report of the user, and may determine the sleep quality of the user by a duration of deep sleep of the user in the sleep report, where the longer the deep sleep time, the better the sleep quality of the user.

Mode two: reducing the parameter value of the ith sleep environment parameter, and monitoring the sleep quality of the target object in the corresponding sleep environment through a sleep monitoring device; continuing to reduce the parameter value of the ith sleep environment parameter until the parameter value of the ith sleep environment parameter is reduced to the target parameter value under the condition that the sleep quality of the target object is monitored to be good; when the parameter value of the ith sleep environment parameter is the target parameter value, continuing to decrease the parameter value of the ith sleep environment parameter may cause the sleep quality of the target object to be degraded.

In the case of increasing or decreasing the parameter value of the ith sleep environment parameter, the parameter values of the other sleep environment parameters are not changed.

That is, reinforcement learning can be actively performed on the initial sleep environment data, and the parameter value of each sleep environment parameter is adjusted, so that the parameter value of each sleep environment parameter reaches a corresponding target value, and target sleep environment data is obtained. In this embodiment, by adopting the above manner, the target sleep environment data can be quickly and accurately determined by determining the target parameter value corresponding to each sleep environment parameter.

In an exemplary embodiment, the above step S206 may be implemented by: determining a target sleep environment parameter to be adjusted of the target object and a corresponding parameter value according to the equipment control instruction when the equipment control instruction sent by the target object is acquired, wherein the equipment control instruction is an instruction sent by the target object in a sleep environment corresponding to the initial sleep environment data; and performing reinforcement learning on the initial sleep environment data through the target sleep environment parameters and the corresponding parameter values to obtain target sleep environment data.

The method can collect the feedback of the current sleep environment of the user in the sleep environment corresponding to the initial sleep environment data, and the initial sleep environment data is subjected to reinforcement learning passively through the feedback of the user, so that the target sleep environment data suitable for individuation of the user can be determined more timely and accurately, and the comfortable home sleep experience of the user is achieved.

Determining initial sleep environment data according to target object characteristic data of a target object and target area characteristic data of a target area, and performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object. The optimal sleeping environment of the target object is determined in a reinforcement learning mode, so that the problem that the optimal sleeping environment of the user cannot be determined is solved, the user can sleep in the optimal sleeping environment, and the sleeping quality of the user is improved.

In one exemplary embodiment, after obtaining the target sleep environment data, there are also the following steps S11-S13:

step S11: acquiring historical sleep data of the target object, wherein the historical sleep data is used for describing a historical sleep cycle of the target object;

it should be noted that the historical sleep data may be determined by a plurality of sleep reports obtained by the sleep monitoring apparatus. The historical sleep data of the target subject may be identical to a description of how long the user enters the sleep session, how long the user enters the light sleep session, and how long the user enters the deep sleep session after using the sleep monitoring device.

Step S12: under the condition that the sleep monitoring device determines that the target object enters a first sleep state after a preset time through the historical sleep data, determining first sleep environment data corresponding to the first sleep state through the target sleep environment data, wherein the target sleep environment data comprises sleep environment data corresponding to different sleep states in a sleep period;

note that the sleep state includes: a sleep-in period, a light sleep period and a deep sleep period. The first sleep state is one of the sleep states. The sleep cycle is used for describing the time corresponding to different sleep states of the user and the conversion condition of the sleep states. Specifically, the sleep cycle is shown in fig. 7.

Step S13: after the preset time, controlling the equipment in the equipment set to execute target operation according to the first sleep environment data, so that the sleep environment after the preset time is the sleep environment corresponding to the first sleep environment data.

In this embodiment, the next sleep state of the user can be predicted in advance, so that corresponding sleep environment data can be prepared in advance. Avoiding the user from sleeping and being hot or cold.

In an exemplary embodiment, the above step S13 may be implemented by the following steps S131 to S133:

step S131: determining each sleep environment parameter and corresponding parameter value in the first sleep environment data; for example, the first sleep environment data includes: the temperature is 23 ℃ and the humidity is 50%.

Step S132: determining equipment corresponding to each sleep environment parameter, and controlling the corresponding equipment to adjust each sleep environment parameter in the current sleep environment according to the corresponding parameter value;

it should be noted that, the device corresponding to each sleep environment parameter is a device for controlling a corresponding sleep environment parameter in an environment, for example, when the first sleep environment data is { temperature 23 degrees, humidity 50% }, the corresponding device is an air conditioner, a humidifier, a dehumidifier, or the like. The air conditioner is controlled to adjust the current environmental temperature to 23 ℃, and when the current environmental humidity is greater than 50%, the dehumidifier is used to make the current environmental humidity be 50%, and when the current environmental temperature is less than 50%, the humidifier is used to make the current environmental humidity be 50%.

It should be noted that, the sleep environment parameters at least include: temperature, humidity, light intensity, oxygen content, ambient volume. In this embodiment, through the real-time linkage with intelligent house, can be more accurate for the user automatically regulated is fit for sleep environment, let the user feel comfortable enjoying comfortable sleep environment, improve user's sleep experience and sleep quality.

It will be apparent that the embodiments described above are merely some, but not all, embodiments of the invention. For better understanding of the above method, the following description will explain the above process with reference to the examples, but is not intended to limit the technical solution of the embodiments of the present invention, specifically:

in an alternative embodiment, if the user feels uncomfortable while sleeping, the user gets up to manually adjust the device until the current sleeping environment meets the user's requirements, the specific flow is shown in fig. 3. The invention provides relevant intelligent regulation service by aiming at real-time automatic regulation of indoor environment of a user and through acquired user characteristic information (equivalent to the target object characteristic data), and scientifically calculates the most comfortable sleeping environment of each person in view of environmental factors such as temperature, humidity, illumination and the like, highlights real-time identification of environmental change, and combines user habit to regulate and control the temperature, humidity, lighting and the like in an air conditioner and curtain control room in real time. The detailed operation steps are as follows:

The first step: and acquiring user intelligent home environment data and user attribute data, and acquiring 'quintuple' data related to user behaviors, wherein the key point is to acquire environment related data of quintuple context.

And a second step of: and converting objective data into subjective cognition according to the objective conditions of the quintuple, and determining the daily temperature, humidity and illumination intensity change curve of each city.

And a third step of: and carrying out decision execution according to the cognitive data, recording the suitable environment of the user in each sleep stage in real time, and after reinforcement learning, predicting the arrival of the next sleep stage in advance, and preparing corresponding environmental factors such as temperature, humidity and the like in advance.

Fourth step: and acquiring corresponding behavior feedback of the user when the environment changes such as different temperatures, humidity, illumination, noise and the like, including but not limited to voice control feedback, APP feedback, equipment control feedback, screen end feedback and the like.

Fifth step: the combination of the time of day (weather, sunrise and sunset), geography (city and county of province and household space position) and people and (manual control inverse control information) forms the combination of objective condition and subjective consciousness form, and finally thousands of people and thousands of users' requirements suitable for sleeping of each person are formed.

It should be noted that, the five-tuple set is mainly a comprehensive description of the behavior, including: user information wha: u (u_1, u_2, u_3, …, u_n), time information white: t (t_1, t_2, t_3, …, t_n), address information Where: a (a_1, a_2, a_3, …, a_n), intention information What: i (i_1, i_2, i_3, …, i_n), context information Context: (c_1, c_2, c_3, …, c_n).

User information collection: u (x) denotes the user feature, u (u_1, u_2, u_3, …, u_n) denotes the 1 st to k th feature of the user. Such as user age, user gender, character, etc., for recommending optimal sleep parameter initialization for the corresponding population.

Time attribute information set: t (x) represents a time attribute, and t (t_1, t_2, t_3, …, t_n) represents 1 st to k th attributes of time. Such as time contains year, month, day, period information, etc.

Address information set: a (x) represents address features, a (a_1, a_2, a_3, …, a_n) represents 1 st to k th features of an address. Such as province, city, county, room location, room orientation, etc.

Intent information set: i (x) denotes user intention information, i (i_1, i_2, i_3, …, i_n) identifying different intents of the user. The intent includes the user's sleep state at the next stage.

Context information set: c (c_1, c_2, c_3, …, c_n) represent behavior information, weather information, ultraviolet rays, device state information, and the like.

It should be noted that fig. 4 illustrates a flowchart. Sleep data of the next stage is predicted through sleep data of the five-tuple user stage, and therefore the equipment is accurately controlled.

As an alternative example, fig. 5 illustrates a timing diagram for controlling a user's sleep environment based on five-tuple behavior data. As an alternative example, there are the following:

1. contextual environmental information processing

1.1 cleaning and standardizing the existing five-tuple user sleep stage data, taking a space, a sleep stage, an address, a temperature, a geographic position and an orientation as main element data formats, and sequencing the historical actions of the user to obtain a data structure shown in the following table 1.

TABLE 1

Space of

Sleep stage

Season

Geographic location

Temperature (degree)

Humidity of the water

Character figure

Bedroom

1

Wakening

Spring

Beijing city

23

50％

Father (father)

Bedroom 1

Shallow sleep

Summer with air conditioner

Qingdao city

24

55％

Mother's mother

Bedroom

1

Deep sleep

Autumn of autumn

Jinan City

25

60％

Grandpa (grandpa)

Bedroom 2

Sleep well

Winter

Three-city

26

65％

Milk

1.2, judging the sleeping time point of the user on the same day and different corresponding environmental factors of the sleeping stage according to the comprehensive factors of indoor lamps, curtains, sound boxes and the like, and performing reinforcement learning on the environmental factors suitable for the different stages through a reinforcement learning algorithm so as to adapt to sleeping of the user in the different stages.

As an alternative example, an overall frame diagram of the sleep environment of the user of the embodiment of the present application is shown in fig. 6.

1.3 investigation to study the optimal sleep environment in different seasons in north and south, an initialization of the optimal sleep environment was made in combination with the sleep habit data of the user himself, and an example is shown in table 2 below.

TABLE 2

2. Collecting behavior feedback of user control equipment in an intelligent curtain scene; exemplary, as shown in table 3 below:

TABLE 3 Table 3

Speech feedback	APP feedback	Device feedback
			Too bright	Curtain opening	Curtain turning left
Too dark	Curtain closing	Curtain turning right
			Too much heat	Opening the air conditioner	21-degree starting of air conditioner
Too dry	Starting the humidifying function	Air conditioner humidification function start

And calculating the deviation between user feedback and decision, namely the difference of individual users to environmental factors according to historical data, so as to calculate the temperature, humidity and illumination decision coefficients of each person, continuously calculating the environmental sensitivity coefficient of the user according to the user feedback in a user image, multiplying the environmental sensitivity coefficient of the individual according to the standard decision when deciding next time, obtaining a final execution decision, and providing the indoor sleep environment suitable for each user according to each sleep period stage of the user in real time. Wherein, the user environment sensitivity coefficient formula: w = user feedback regulation/criteria execution decision. Specifically, the following table 4 shows:

TABLE 4 Table 4

3. The intensity of comfortable illumination in various environments of the user history is enhanced, and an exemplary reinforcement learning model is shown in fig. 8.

The optimal sleep environment factors of the user in different seasons are counted, feedback of the user is collected, reinforcement learning is timely conducted, sleep preference factors of the user in different conditions are dynamically adjusted, and the environment factors suitable for individuation of the user can be timely and accurately recommended and adjusted, so that comfortable household sleep experience of the user is achieved.

As an alternative example, fig. 9 illustrates another overall frame diagram of an embodiment of the present application. The finally determined sleep environment data are shown in table 5 below.

TABLE 5

It should be noted that, in the embodiment of the present application, each user is taken as an analysis object, statistical analysis is performed on a historical sleep curve, each time a single factor change is performed, the influence of different factors of the user on the sleep curve is found, the optimal sleep environment of the user is sequentially adjusted in real time, a user behavior system is constructed, the sleep sensitivity point of each user is found, and the habit is a silenced change, so that the method can adapt to the sleep requirements in various environments and continuously strengthen learning to optimize.

In addition, according to the five-tuple context information, the sleep sensitive points of the user are personalized and ordered, the most comfortable sleep environment of each person under various environments is found, so that the comfortable user of the sleep environment (temperature, humidity, illumination and the like) is automatically adjusted in advance, different environment changes under the sleep period of the user are prejudged in advance, the sleep factors of the user due to the external environment changes are reduced, the better sleep experience of the user is realized, and the physical health of the user is improved.

From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method of the various embodiments of the present invention.

The embodiment also provides a device for determining sleep environment data, which is used for implementing the foregoing embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the devices described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware, are also possible and contemplated.

Fig. 10 is a block diagram of a sleep environment data determining apparatus according to an embodiment of the present invention, the apparatus including:

an obtaining module 1002, configured to obtain target object feature data of a target object, and obtain target area feature data of a target area where the target object is currently located;

a first determining module 1004, configured to determine initial sleep environment data according to the target object feature data and the target area feature data;

a second determining module 1006, configured to perform reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object.

The device determines initial sleep environment data according to target object characteristic data of a target object and target area characteristic data of a target area, and performs reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object. The optimal sleeping environment of the target object is determined in a reinforcement learning mode, so that the problem that the optimal sleeping environment of the user cannot be determined is solved, the user can sleep in the optimal sleeping environment, and the sleeping quality of the user is improved.

In an exemplary embodiment, the obtaining module 1002 is further configured to obtain the target object feature data of the target object by: acquiring the gender, age and life habit type of the target object; the acquisition module is further used for acquiring target area characteristic data of a target area where the target object is currently located by the following method: determining the current time and the geographic position of a target area where the target object is currently located; and determining a current season and a current weather according to the current time and the geographic position, wherein the target area characteristic data comprises the geographic position, the current season and the current weather.

In an exemplary embodiment, the first determining module 1004 is further configured to obtain a correspondence between the object feature data, the region feature data, and the sleep environment data; and determining initial sleep environment data corresponding to the target object characteristic data and the target area characteristic data according to the corresponding relation.

In an exemplary embodiment, the second determining module 1006 is further configured to determine, in a case where the initial sleep environment data includes parameter values of N sleep environment parameters, a target parameter value of an ith sleep environment parameter of the N sleep environment parameters to obtain target sleep environment data, where i is greater than or equal to 1 and less than or equal to N: increasing the parameter value of the ith sleep environment parameter, and monitoring the sleep quality of the target object in the corresponding sleep environment through a sleep monitoring device; continuing to increase the parameter value of the ith sleep environment parameter until the parameter value of the ith sleep environment parameter is increased to the target parameter value under the condition that the sleep quality of the target object is monitored to be good; when the parameter value of the ith sleep environment parameter is a target parameter value, continuing to increase the parameter value of the ith sleep environment parameter may cause the sleep quality of the target object to be degraded; or reducing the parameter value of the ith sleep environment parameter, and monitoring the sleep quality of the target object in the corresponding sleep environment through a sleep monitoring device; continuing to reduce the parameter value of the ith sleep environment parameter until the parameter value of the ith sleep environment parameter is reduced to the target parameter value under the condition that the sleep quality of the target object is monitored to be good; when the parameter value of the ith sleep environment parameter is the target parameter value, continuing to decrease the parameter value of the ith sleep environment parameter may cause the sleep quality of the target object to be degraded.

In an exemplary embodiment, the second determining module 1006 is further configured to determine, according to the device control instruction, a target sleep environment parameter to be adjusted by the target object and a corresponding parameter value when a device control instruction sent by the target object is acquired, where the device control instruction is an instruction sent by the target object in a sleep environment corresponding to the initial sleep environment data; and performing reinforcement learning on the initial sleep environment data through the target sleep environment parameters and the corresponding parameter values to obtain target sleep environment data.

In an exemplary embodiment, the apparatus further includes a control module configured to obtain historical sleep data of the target subject after obtaining the target sleep environment data, where the historical sleep data is used to describe a historical sleep cycle of the target subject; under the condition that the sleep monitoring device determines that the target object enters a first sleep state after a preset time through the historical sleep data, determining first sleep environment data corresponding to the first sleep state through the target sleep environment data, wherein the target sleep environment data comprises sleep environment data corresponding to different sleep states in a sleep period; after the preset time, controlling the equipment in the equipment set to execute target operation according to the first sleep environment data, so that the sleep environment after the preset time is the sleep environment corresponding to the first sleep environment data.

In an exemplary embodiment, the control module is further configured to determine each sleep environment parameter and a corresponding parameter value in the first sleep environment data; determining equipment corresponding to each sleep environment parameter, and controlling the corresponding equipment to adjust each sleep environment parameter in the current sleep environment according to the corresponding parameter value; wherein the sleep environment parameters include at least: temperature, humidity, light intensity, oxygen content, ambient volume.

Embodiments of the present invention also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

Alternatively, in the present embodiment, the above-described storage medium may be configured to store a computer program for performing the steps of:

s1, acquiring target object characteristic data of a target object and acquiring target area characteristic data of a target area where the target object is currently located;

s2, determining initial sleep environment data according to the target object characteristic data and the target area characteristic data;

S3, performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object.

In one exemplary embodiment, the computer readable storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.

Specific examples in this embodiment may refer to the examples described in the foregoing embodiments and the exemplary implementation, and this embodiment is not described herein.

An embodiment of the invention also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:

In an exemplary embodiment, the electronic apparatus may further include a transmission device connected to the processor, and an input/output device connected to the processor.

It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.

Claims

1. A method for determining sleep environment data, comprising:

acquiring target object feature data of a target object and acquiring target area feature data of a target area where the target object is currently located;

determining initial sleep environment data according to the target object characteristic data and the target area characteristic data;

performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

acquiring target object feature data of a target object, including: acquiring the gender, age and life habit type of the target object;

The obtaining the characteristic data of the target area of the current target area of the target object comprises the following steps: determining the current time and the geographic position of a target area where the target object is currently located; and determining the current season and the current weather of the target area according to the current time and the geographic position, wherein the target area characteristic data comprise the geographic position, the current season and the current weather.

3. The method of claim 1, wherein determining initial sleep environment data from the target object feature data and the target region feature data comprises:

acquiring the corresponding relation between object feature data, regional feature data and sleep environment data;

and determining initial sleep environment data corresponding to the target object characteristic data and the target area characteristic data according to the corresponding relation.

4. The method of claim 1, wherein performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data comprises:

in the case that the initial sleep environment data includes parameter values of N sleep environment parameters, determining a target parameter value of an i-th sleep environment parameter of the N sleep environment parameters to obtain target sleep environment data, where i is greater than or equal to 1 and less than or equal to N:

Increasing the parameter value of the ith sleep environment parameter, and monitoring the sleep quality of the target object in the corresponding sleep environment through a sleep monitoring device; continuing to increase the parameter value of the ith sleep environment parameter until the parameter value of the ith sleep environment parameter is increased to the target parameter value under the condition that the sleep quality of the target object is monitored to be good; when the parameter value of the ith sleep environment parameter is a target parameter value, continuing to increase the parameter value of the ith sleep environment parameter may cause the sleep quality of the target object to be degraded; or (b)

Reducing the parameter value of the ith sleep environment parameter, and monitoring the sleep quality of the target object in the corresponding sleep environment through a sleep monitoring device; continuing to reduce the parameter value of the ith sleep environment parameter until the parameter value of the ith sleep environment parameter is reduced to the target parameter value under the condition that the sleep quality of the target object is monitored to be good; when the parameter value of the ith sleep environment parameter is the target parameter value, continuing to decrease the parameter value of the ith sleep environment parameter may cause the sleep quality of the target object to be degraded.

5. The method of claim 1, wherein performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data comprises:

determining a target sleep environment parameter to be adjusted of the target object and a corresponding parameter value according to the equipment control instruction when the equipment control instruction sent by the target object is acquired, wherein the equipment control instruction is an instruction sent by the target object in a sleep environment corresponding to the initial sleep environment data;

and performing reinforcement learning on the initial sleep environment data through the target sleep environment parameters and the corresponding parameter values to obtain target sleep environment data.

6. The method of claim 1, wherein after obtaining the target sleep environment data, the method further comprises:

acquiring historical sleep data of the target object, wherein the historical sleep data is used for describing a historical sleep cycle of the target object;

under the condition that the sleep monitoring device determines that the target object enters a first sleep state after a preset time through the historical sleep data, determining first sleep environment data corresponding to the first sleep state through the target sleep environment data, wherein the target sleep environment data comprises sleep environment data corresponding to different sleep states in a sleep period;

After the preset time, controlling the equipment in the equipment set to execute target operation according to the first sleep environment data, so that the sleep environment after the preset time is the sleep environment corresponding to the first sleep environment data.

7. The method of claim 6, wherein controlling devices in the set of devices to perform the target operation based on the first sleep environment data comprises:

determining each sleep environment parameter and corresponding parameter value in the first sleep environment data;

determining equipment corresponding to each sleep environment parameter, and controlling the corresponding equipment to adjust each sleep environment parameter in the current sleep environment according to the corresponding parameter value;

wherein the sleep environment parameters include at least: temperature, humidity, light intensity, oxygen content, ambient volume.

8. A sleep environment data determining apparatus, comprising:

the acquisition module is used for acquiring target object characteristic data of a target object and acquiring target area characteristic data of a target area where the target object is currently located;

the first determining module is used for determining initial sleep environment data according to the target object characteristic data and the target area characteristic data;

The second determining module is used for performing reinforcement learning on the initial sleep environment data to obtain target sleep environment data; when the target object is located in a target area corresponding to the target area characteristic data, the target sleep environment corresponding to the target sleep environment data is the optimal sleep environment of the target object.

9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program when run performs the method of any one of claims 1 to 7.

10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method according to any of claims 1 to 7 by means of the computer program.