CN113655730A - Data information processing method and system for home system - Google Patents
Data information processing method and system for home system Download PDFInfo
- Publication number
- CN113655730A CN113655730A CN202111218096.5A CN202111218096A CN113655730A CN 113655730 A CN113655730 A CN 113655730A CN 202111218096 A CN202111218096 A CN 202111218096A CN 113655730 A CN113655730 A CN 113655730A
- Authority
- CN
- China
- Prior art keywords
- sleeping posture
- posture
- sleeping
- sleep
- time sequence
- 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
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 23
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 230000007958 sleep Effects 0.000 claims abstract description 110
- 238000004458 analytical method Methods 0.000 claims abstract description 57
- 230000008859 change Effects 0.000 claims abstract description 25
- 206010062519 Poor quality sleep Diseases 0.000 claims abstract description 16
- 238000012937 correction Methods 0.000 claims abstract description 10
- 230000036544 posture Effects 0.000 claims description 444
- 238000000034 method Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 230000006399 behavior Effects 0.000 claims description 7
- 230000003247 decreasing effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000009191 jumping Effects 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- BULVZWIRKLYCBC-UHFFFAOYSA-N phorate Chemical group CCOP(=S)(OCC)SCSCC BULVZWIRKLYCBC-UHFFFAOYSA-N 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 abstract description 4
- 230000009471 action Effects 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000006641 stabilisation Effects 0.000 description 7
- 238000011105 stabilization Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000009472 formulation Methods 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000000087 stabilizing effect Effects 0.000 description 2
- 206010003497 Asphyxia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Data Mining & Analysis (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Dentistry (AREA)
- Psychiatry (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a data information processing method and a data information processing system of a home system, which comprise the following steps: step S1, carrying out similarity analysis on the biological sleeping posture time sequence data according to a time sequence to obtain a sleeping posture change node time sequence chain; step S2, classifying the plurality of sleeping posture habit analysis samples according to sample labels to obtain a plurality of groups of sleeping posture habit analysis sample sets; and step S3, performing threshold analysis on all the sleep posture habit representative samples to obtain the poor sleep posture adjustment category and the poor sleep posture adjustment scheme of the target object so as to realize correction of the poor sleep posture of the target object. The invention realizes the healthy maintenance of the sleeping posture of the target object, finally ensures the body health degree of the target object, adopts a gradual sleeping posture adjusting mode in the poor sleeping posture adjusting scheme, ensures that the target object adapts to the adjusting action of the adjusting scheme in the invisibility, and realizes the establishment of the scheme for adjusting the poor sleeping posture for a user on the premise of not reducing the use comfort degree of the target object.
Description
Technical Field
The invention relates to the technical field of intelligent home furnishing, in particular to a data information processing method and system of a home furnishing system.
Background
The intelligent home system utilizes advanced computer technology, network communication technology, intelligent cloud control, comprehensive wiring technology and medical electronic technology to integrate individual requirements according to the principle of human engineering, organically combines various subsystems related to home life such as security protection, light control, curtain control, gas valve control, information household appliances, scene linkage, floor heating, health care, epidemic prevention, security protection and the like, and realizes the brand-new home life experience of people-oriented through networked comprehensive intelligent control and management.
The sleep comfort level also is the important ring that intelligent house life experienced, only reflects in the control to the sleep environment to controlling of sleep comfort level at present, for example light automatically regulated and temperature automatically regulated etc. build a comfortable sleep environment for the user, but unable processing user's sleeping posture custom data, lead to unable according to user's sleeping posture custom data accurate analysis and correct user's bad sleeping posture custom.
Disclosure of Invention
The invention aims to provide a data information processing method and a data information processing system of a home system, which aim to solve the technical problem that the prior art cannot process the sleeping posture habit data of a user, so that the poor sleeping posture habit of the user cannot be accurately analyzed and corrected according to the sleeping posture habit data of the user.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
on one hand, the data information processing method of the home system comprises the following steps:
s1, collecting biological sleeping posture time sequence data of the target object, and performing similarity analysis on the biological sleeping posture time sequence data according to a time sequence to obtain a sleeping posture change node time sequence chain so as to realize capturing of key data in the sleeping posture habit of the target object;
step S2, the sleep posture change node time sequence chain is divided at the nodes to obtain a plurality of sleep posture stability time sequence sections representing unique sleep posture habits, labeling processing is carried out on the sleep posture stability time sequence sections to obtain sleep posture habit analysis samples, and then the plurality of sleep posture habit analysis samples are classified according to sample labels to obtain a plurality of groups of sleep posture habit analysis sample sets so as to realize classification of the sleep posture habits of the target object;
and step S3, sequentially carrying out time sequence section mode analysis on all the sleep posture habit analysis samples in the multiple groups of sleep posture habit sample sets to obtain sleep posture habit representative samples representing the main characteristics of the sleep posture habits of the target object, and carrying out threshold analysis on all the sleep posture habit representative samples to obtain the poor sleep posture adjustment category and the poor sleep posture adjustment scheme of the target object so as to realize the correction of the poor sleep posture of the target object.
As a preferable aspect of the present invention, in step S1, the specific method for analyzing the similarity of the biological sleep posture time series data according to time series to obtain the sleep posture change node time series chain includes:
s101, carrying out similarity analysis on data of adjacent time sequences in the biological sleeping posture time sequence data to obtain a similarity data chain, wherein a calculation formula of the similarity is as follows:
wherein,
step S102, selecting all jump nodes on the similarity data chain, selecting data corresponding to time sequences at two sides of all jump nodes from biological sleeping posture time sequence data as sleeping posture change nodes, and arranging the sleeping posture change nodes according to time sequences to form a sleeping posture change node time sequence chain;
the jumping node refers to a data node of which the numerical value difference between a node on the similarity data chain and a left adjacent node and a right adjacent node exceeds a similarity threshold value.
As a preferable aspect of the present invention, in step S2, the method for obtaining the sleeping posture habit analysis sample includes:
step S201, establishing a sleeping posture identification sample set according to sleeping posture types, and establishing a sleeping posture type identification model based on the sleeping posture identification sample set;
step S202, the stable sleeping postures in the sleeping posture stable time sequence section are subjected to type identification by using the sleeping posture type identification model, and the sleeping posture type is used as a sample label to mark the sleeping posture stable time sequence section to obtain the sleeping posture habit analysis sample.
As a preferable aspect of the present invention, in step S201, the method for constructing the sleep posture identification sample includes:
the target object carries out the simulation of the sleeping posture behavior according to the sleeping posture type, records the characteristic data of the sleeping posture behavior as a sleeping posture sample corresponding to the sleeping posture type, and takes the sleeping posture type as a sample label of the sleeping posture sample;
and mixing the sleeping posture samples of all sleeping posture types into a sleeping posture identification sample set according to equal proportion so as to keep the balance of the samples trained by the sleeping posture type identification model.
As a preferable aspect of the present invention, in step S201, the method for establishing the sleep posture type recognition model includes:
step S2011, the sleep posture identification sample set is divided into a training set and a testing set according to a preset proportion, and the training set is applied to a convolutional neural network for model identification training, wherein the characteristic data of the sleep posture samples in the training set is used as the input of the convolutional neural network, and the sample labels of the sleep posture samples in the training set are used as the output of the convolutional neural network;
and step S2012, carrying out output test and parameter correction on the recognition model trained in the step S2011 in the test set to obtain a recognition model with the highest precision, and using the recognition model with the highest precision after correction as the sleeping posture type recognition model, wherein the feature data of the sleeping posture samples in the test set is used as the input of the recognition model, and the sample labels of the sleeping posture samples in the test set are used as the output of the recognition model.
As a preferred embodiment of the present invention, in step S202, the input of the sleep posture type recognition model is biological sleep posture time sequence data representing stable sleep postures in the sleep posture stable time sequence section, and the output of the sleep posture type recognition model is the sleep posture type of the stable sleep postures in the sleep posture stable time sequence section.
As a preferable aspect of the present invention, in step S3, the method for acquiring the sleep habit representative sample includes:
sequentially carrying out time sequence section duration statistics on all the sleep habit analysis samples in the sleep habit sample set, and screening out the sleep habit analysis samples with the same time sequence section duration and the largest number;
randomly selecting one sleeping posture habit analysis sample from the largest number of sleeping posture habit analysis samples with the same length in the time sequence section as a sleeping posture habit representative sample of the corresponding sleeping posture habit sample set.
As a preferable aspect of the present invention, in step S3, the method for obtaining the poor sleep posture adjustment category and the poor sleep posture adjustment plan of the target object includes:
comparing the time sequence section duration of the sleeping posture habit representative sample with a sleeping posture standard duration threshold of the sleeping posture type corresponding to the sample label of the sleeping posture habit representative sample, wherein,
if the time sequence section duration exceeds the sleeping posture standard duration threshold, the sleeping posture type corresponding to the sample label of the sleeping posture habit representative sample belongs to a bad sleeping posture adjustment type, and the time sequence section duration of the sleeping posture habit representative sample is used as the type duration of the bad sleeping posture adjustment type;
obtaining the category duration of each poor sleeping posture adjustment category, setting the sleeping posture adjustment duration of the poor sleeping posture adjustment category as the corresponding category duration to be gradually decreased by 10% at regular intervals until the duration is decreased to a sleeping posture standard duration threshold, and maintaining the duration on the sleeping posture standard duration threshold as a poor sleeping posture adjustment scheme so as to gradually adjust the poor sleeping posture of the target object and reduce the discomfort of the target object to the adjustment of the sleeping posture;
the regular decrement is represented as the time length that the sleeping posture adjustment time length is equal to the category time length reduced by 10% every other preset period, and the operation formula of the regular decrement is as follows:
wherein H is the sleeping posture adjustment time length of the nth period, and H is the category time length.
In another aspect, the present invention provides a processing system, configured to execute the data information processing method, including: the device comprises a model establishing unit, a scheme making unit, a sleeping posture collecting assembly arranged on the upper surface of a mattress and a sleeping posture adjusting unit arranged on the lower surface of the mattress;
the sleeping posture acquisition component is used for acquiring data related to biological sleeping postures of the target object;
the model establishing unit is used for establishing a sleeping posture type identification model for the target object;
the scheme making unit is used for establishing a poor sleeping posture adjusting scheme for the target object;
and the sleeping posture adjusting unit is used for adjusting the sleeping posture of the target object according to the poor sleeping posture adjusting scheme.
As a preferred scheme of the present invention, the system further comprises an identity account unit, wherein the identity account unit stores identity accounts of a plurality of different target objects, and a poor sleeping posture adjustment scheme and a sleeping posture type identification model corresponding to a target object are uniquely bound in the identity accounts, so as to implement that the processing system is used for switching different target objects.
Compared with the prior art, the invention has the following beneficial effects:
the invention captures the sleeping posture habit of the target object by utilizing the biological sleeping posture data of the target object, screens out the bad sleeping posture habit from the sleeping posture habit, and a bad sleeping posture adjustment scheme is formulated for correcting bad sleeping posture habits of the target object, the healthy maintenance of the sleeping posture of the target object is realized, the body health degree of the target object is finally ensured, a sleeping posture step-by-step adjustment mode is adopted in the bad sleeping posture adjustment scheme, the adjustment action of the adjustment scheme is adapted in the target object invisibility, and the formulation of the bad sleeping posture adjustment scheme for a user is realized on the premise of not reducing the use comfort degree of the target object, the similarity analysis and recognition model is used for building in the process of processing the data of the sleeping posture of the target object and recognizing the sleeping posture habit of the target object, the sleep posture data processing amount and the sleep posture type identification precision can be effectively reduced, and the data information processing efficiency and accuracy of the home system are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
FIG. 1 is a flow chart of a data information processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a similarity data chain according to an embodiment of the present invention;
fig. 3 is a block diagram of a processing system according to an embodiment of the present invention.
The reference numerals in the drawings denote the following, respectively:
1-a sleeping posture acquisition component; 2-a sleeping posture adjusting unit; 3-a model building unit; 4-a scheme making unit; 5-identity account number unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1 to 3, the present invention provides a data information processing method of a home system, including the following steps:
s1, collecting biological sleeping posture time sequence data of the target object, and performing similarity analysis on the biological sleeping posture time sequence data according to a time sequence to obtain a sleeping posture change node time sequence chain so as to capture key data in the sleeping posture habit of the target object;
the sleep posture of a human being in the sleeping process presents a staged characteristic, so that the staged evolution characteristic of the sleep posture of a target object can be obtained only by performing time-sequence staged analysis on the biological sleep posture time sequence data of the target object, and the embodiment provides a method for performing time-sequence staged analysis on the biological sleep posture time sequence data of the target object, which can extract a data node of the target object with posture change from the biological sleep posture time sequence data of the target object, and the method specifically comprises the following steps:
in step S1, the specific method for analyzing the similarity of the biological sleep posture time series data according to the time series to obtain the sleep posture change node time series chain includes:
step S101, carrying out similarity analysis on data of adjacent time sequences in the biological sleeping posture time sequence data to obtain a similarity data chain, wherein a calculation formula of the similarity is as follows:
wherein,
step S102, selecting all jump nodes on the similarity data chain, selecting data corresponding to time sequences at two sides of all jump nodes from biological sleeping posture time sequence data as sleeping posture change nodes, and arranging the sleeping posture change nodes according to time sequences to form a sleeping posture change node time sequence chain;
the jumping node refers to a data node of which the numerical value difference between a node on the similarity data chain and a left adjacent node and a right adjacent node exceeds a similarity threshold value.
The similarity is an index for measuring the similarity degree of data of adjacent time sequences in the biological sleeping posture time sequence data, the higher the similarity is, the more similar the data of adjacent time sequences in the biological sleeping posture time sequence data is, the data of adjacent time sequences in the biological sleeping posture time sequence data is represented as the same biological sleeping posture, namely, the target object is represented to keep the same biological sleeping posture on the adjacent time sequences, the adjacent time sequences are positioned on the same stable sleeping posture time sequence stage of the target object and are mapped to a similarity data chain, and because the difference value of the adjacent time sequences in the biological sleeping posture time sequence data is 1 time unit, the similarity of the data of the adjacent time sequences in the biological sleeping posture time sequence data is
The absolute value of the slope of the data adjacent to the time sequence in the biological sleeping posture time sequence data
The similarity data chain is equivalent to a slope absolute value data chain of biological sleeping posture time sequence data, and a jump node on the similarity data chain is characterized in that the slope absolute value of the biological sleeping posture time sequence data in time sequences at two sides of the jump node changes, and the biological sleeping posture time sequence data is mapped to the biological sleeping posture time sequence data to indicate that the biological sleeping posture time sequence data in the time sequences at two sides of the jump node has low similarity, so that the target object is indicated to have sleeping posture change in the time sequences at two sides of the jump nodeAnd then the data of the biological sleeping posture time sequence data at the time sequences at the two sides of the jump node represents the sleeping posture change node, namely the target object at the sleeping posture change node has a sleeping posture change, and the biological sleeping posture time sequence data can be converted from the zero-dispersion characteristic-free time sequence data into the time sequence data containing the sleeping posture change characteristic.
As shown in FIG. 2, the biological sleeping posture time sequence data is
The similarity data chain is
Then the above calculation obtains the jumping node as
The sleeping posture changing node is
……
、
And is and
for the first sleep posture stabilization period, the target object is
The user can keep a stable sleeping posture in the middle,
a second time sequence section for stabilizing the sleeping posture,
a third time sequence section for stabilizing the sleeping posture,
is the fourth sleep posture stable time sequence section.
According to the method, the target object is only changed in the sleeping posture changing nodes, the target object is in a stable sleeping posture in the time sequence stage between the adjacent sleeping posture changing nodes, a plurality of sleeping posture stable time sequence sections representing unique sleeping posture habits can be obtained by segmenting the sleeping posture changing node time sequence chain at the nodes, and bad habits of the target object are excavated based on the sleeping posture stable time sequence sections, and the method is concretely as follows:
step S2, the sleeping posture change node time sequence chain is divided at the nodes to obtain a plurality of sleeping posture stable time sequence sections representing unique sleeping posture habits, labeling processing is carried out on the sleeping posture stable time sequence sections to obtain sleeping posture habit analysis samples, and then the plurality of sleeping posture habit analysis samples are classified according to sample labels to obtain a plurality of groups of sleeping posture habit analysis sample sets so as to realize classification of the sleeping posture habits of the target object;
in step S2, the method for obtaining the sleeping posture habit analysis sample includes:
step S201, establishing a sleeping posture identification sample set according to sleeping posture types, and establishing a sleeping posture type identification model based on the sleeping posture identification sample set;
in step S201, the method for constructing the sleep posture identification sample includes:
the target object carries out the simulation of the sleeping posture behaviors according to the sleeping posture types, records the characteristic data of the sleeping posture behaviors as sleeping posture samples corresponding to the sleeping posture types, and takes the sleeping posture types as sample labels of the sleeping posture samples;
and mixing the sleeping posture samples of all sleeping posture types into a sleeping posture identification sample set according to equal proportion so as to keep the balance of the samples trained by the sleeping posture type identification model.
In step S201, the method for establishing the sleep posture type identification model includes:
step S2011, a sleeping posture identification sample set is divided into a training set and a testing set according to a preset proportion, and the training set is applied to a convolutional neural network for model identification training, wherein the characteristic data of the sleeping posture samples in the training set is used as the input of the convolutional neural network, and the sample labels of the sleeping posture samples in the training set are used as the output of the convolutional neural network;
and S2012, applying the test set to the recognition model trained in the step S2011 to perform output test and parameter correction so as to obtain the recognition model with the highest precision, and using the recognition model with the highest precision after correction as the sleeping posture type recognition model, wherein the feature data of the sleeping posture sample in the test set is used as the input of the recognition model, and the sample label of the sleeping posture sample in the test set is used as the output of the recognition model.
Step S202, the stable sleeping postures in the sleeping posture stable time sequence section are subjected to type identification by using the sleeping posture type identification model, and the sleeping posture type is used as a sample label to mark the sleeping posture stable time sequence section to obtain a sleeping posture habit analysis sample.
In step S202, the input of the sleep posture type identification model is biological sleep posture time series data representing stable sleep postures in the sleep posture stable time series section, and the output of the sleep posture type identification model is the sleep posture type of the stable sleep postures in the sleep posture stable time series section.
In order to identify the only sleeping posture habit represented in each sleeping posture stabilization time sequence section, firstly, a sleeping posture type identification model belonging to a target object needs to be established, so that biological sleeping posture time sequence data in the sleeping posture stabilization time sequence section can be input into the sleeping posture type identification model, the sleeping posture type of the stable sleeping posture in the sleeping posture stabilization time sequence section can be output, the sleeping posture type identification of all the sleeping posture stabilization time sequence sections can be realized, the sleeping posture type is used as a label of the sleeping posture stabilization time sequence section, and the labeling processing of the sleeping posture stabilization time sequence section is completed to obtain a sleeping posture habit analysis sample.
The device has the advantages that the target object is directly used for simulating sleeping posture behaviors according to the sleeping posture types to manufacture training sample data of the sleeping posture type identification model, the sleeping posture type identification model can be guaranteed to be only exclusive to one target object, the sleeping posture types of the target object can be accurately and rapidly identified, the training samples are accurate and small in quantity, the sleeping posture type identification model can be rapidly trained, the data processing efficiency is improved, exclusive service is integrally provided for the target object, and the use experience of the target object is improved.
And step S3, sequentially carrying out time sequence section mode analysis on all the sleep posture habit analysis samples in the multiple groups of sleep posture habit sample sets to obtain sleep posture habit representative samples representing the main characteristics of the sleep posture habits of the target object, and carrying out threshold analysis on all the sleep posture habit representative samples to obtain the poor sleep posture adjustment category and the poor sleep posture adjustment scheme of the target object so as to realize correction of the poor sleep posture of the target object.
In step S3, the method for obtaining the sleep posture habit representative sample includes:
sequentially carrying out time sequence section duration statistics on all the sleep habit analysis samples in the sleep habit sample set, and screening out the sleep habit analysis samples with the same time sequence section duration and the largest number;
randomly selecting one sleeping posture habit analysis sample from the largest number of sleeping posture habit analysis samples with equal length in time sequence section as a sleeping posture habit representative sample of the corresponding sleeping posture habit sample set.
All the sleeping posture habit analysis samples in the same sleeping posture habit sample set have the same sample label, namely the same sleeping posture type, the time sequence section duration of the sleeping posture habit analysis samples is the time sequence of the tail end minus the head end of the sleeping posture habit analysis samples, namely the duration representing the sleeping posture type of the target object in the sleeping posture habit analysis samples, because the target object has the sleeping posture habit preference of the target object, the target object can be repeatedly kept in the same sleeping posture type and last for the same duration, the sleeping posture habit analysis samples with the most number of equal time sequence section duration in each sleeping posture habit sample set are selected, the duration of the target object for the sleeping posture type can be embodied, the duration of the target object which prefers under the sleeping posture type is compared with the standard duration threshold under the sleeping posture type, whether the target object has bad sleeping posture habit or not can be judged, if then show this appearance of sleeping kind and adjust the classification for the bad appearance of sleeping of target object, for example target object is in the appearance of sleeping kind for lie prone when the preference of sleeping last long-term be 10 minutes, lie prone when the preference of sleeping last long-term be higher than lie prone when the standard of sleeping last long-term threshold value, map to and mean in the reality that long-time lying prone sleeps and can lead to stifling danger, consequently lie prone and sleep and be defined as target object's bad appearance of sleeping habit, need carry out the appointed of appearance of sleeping adjustment scheme to lying prone, specific bad appearance of sleeping adjustment classification is judged and bad appearance of sleeping adjustment scheme formulation method as follows.
In step S3, the method for obtaining the poor sleep posture adjustment category and the poor sleep posture adjustment plan of the target object includes:
comparing the time sequence section duration of the sleeping posture habit representative sample with the sleeping posture standard duration threshold of the sleeping posture type corresponding to the sample label of the sleeping posture habit representative sample, wherein,
if the time length of the time sequence section exceeds the time length threshold of the standard sleeping posture, the sleeping posture type corresponding to the sample label of the sample represented by the sleeping posture habit is attributed to a poor sleeping posture adjustment type, and the time length of the time sequence section of the sample represented by the sleeping posture habit is taken as the type time length of the poor sleeping posture adjustment type;
obtaining the category duration of each poor sleeping posture adjustment category, setting the sleeping posture adjustment duration of the poor sleeping posture adjustment category as the corresponding category duration to be gradually decreased by 10% at regular intervals until the duration is decreased to a sleeping posture standard duration threshold, and maintaining the duration on the sleeping posture standard duration threshold as a poor sleeping posture adjustment scheme so as to gradually adjust the poor sleeping posture of the target object and reduce the discomfort of the target object to the sleeping posture adjustment;
the regular decrement is represented as the time length that the sleeping posture adjustment time length is equal to the category time length reduced by 10% every other preset period, and the operation formula of the regular decrement is as follows:
wherein H is the sleeping posture adjustment time length of the nth period, H is the category time length, and 10% can be adjusted according to actual use.
The adjustment of the bad sleeping posture of the target object is performed on the premise of not reducing the comfortable sensation of the target object, and the present embodiment adopts a mode of gradually increasing the adjustment strength, for example, the sleeping posture of the target object lying prone for sleeping prefers to last for 10 minutes, the standard duration threshold of lying prone for sleeping is 5 minutes (the longest duration of the lying prone for sleeping causing suffocation danger), compared with the method of directly setting the sleeping posture adjustment duration of lying prone for sleeping as 5 minutes, namely, the lying prone sleeping posture of the target object is identified as the timing starting point, after 5 minutes, adjustment reminding is performed to help the target object to perform sleeping posture adjustment, and the lying prone sleeping posture is changed into other sleeping postures, so that the target object is uncomfortable due to directly changing the sleeping posture habit of the target object, while the method of the present embodiment adopts the method of setting the sleeping posture adjustment duration of lying prone for sleeping as 9 minutes in the first period, and only decreasing by 10% compared with the original lying prone sleeping habit of the target object, the target object is difficult to perceive and easy to adapt even if perceived, the target object is adapted for 9 minutes after a period, the sleeping posture adjustment time of lying prone sleeping is determined as 8 minutes in the second period, the sleeping posture adjustment time of lying prone sleeping is determined as 7 minutes in the third period, and the rest is done in sequence, the sleeping posture adjustment time of lying prone sleeping is determined as 5 minutes, the sleeping posture preference duration time of lying prone sleeping of the target object is adjusted to 5 minutes, the adjustment of bad sleeping posture of the target object is completed, the adjustment of bad sleeping posture is completed in the migration default mode, the uncomfortable feeling of the target object in the adjustment process is reduced, and the comfort level of the target object in the adjustment process is improved.
As shown in fig. 3, based on the data information processing method of the home system, the present invention provides a processing system for executing the data information processing method, including: the device comprises a model establishing unit 3, a scheme making unit 4, a sleeping posture collecting assembly 1 arranged on the upper surface of a mattress and a sleeping posture adjusting unit 2 arranged on the lower surface of the mattress;
the sleeping posture acquisition component 1 is used for acquiring data related to biological sleeping postures of a target object;
the model establishing unit 3 is used for establishing a sleeping posture type identification model for the target object;
the scheme making unit 4 is used for establishing a poor sleeping posture adjusting scheme for the target object;
and the sleeping posture adjusting unit 2 is used for adjusting the sleeping posture of the target object according to the poor sleeping posture adjusting scheme.
For example, the sleeping posture adjusting unit can be a telescopic rod arranged on the lower surface, when the target object is identified to lie prone and sleep on the left side, the length of the adjusting time is adjusted and then the adjusting unit is lifted towards the opposite direction of the sleeping posture of the target object, so that the target object can naturally adjust the sleeping posture under the gradient trend formed by the telescopic rod on the mattress, the lying prone sleep is changed into the side sleep or the lying sleep, the left side sleep is changed into the lying sleep or the right side sleep, and the like.
The processing system further comprises an identity account number unit 5, wherein identity account numbers of a plurality of different target objects are stored in the identity account number unit, and a poor sleeping posture adjusting scheme and a sleeping posture type identification model corresponding to the target objects are uniquely bound in the identity account numbers, so that the processing system is used for switching different target objects, the use range is expanded, and multiple purposes are realized.
The invention captures the sleeping posture habit of the target object by utilizing the biological sleeping posture data of the target object, screens out the bad sleeping posture habit from the sleeping posture habit, and a bad sleeping posture adjustment scheme is formulated for correcting bad sleeping posture habits of the target object, the healthy maintenance of the sleeping posture of the target object is realized, the body health degree of the target object is finally ensured, a sleeping posture step-by-step adjustment mode is adopted in the bad sleeping posture adjustment scheme, the adjustment action of the adjustment scheme is adapted in the target object invisibility, and the formulation of the bad sleeping posture adjustment scheme for a user is realized on the premise of not reducing the use comfort degree of the target object, the similarity analysis and recognition model is used for building in the process of processing the data of the sleeping posture of the target object and recognizing the sleeping posture habit of the target object, the sleep posture data processing amount and the sleep posture type identification precision can be effectively reduced, and the data information processing efficiency and accuracy of the home system are improved.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (10)
1. A data information processing method of a home system is characterized by comprising the following steps:
s1, collecting biological sleeping posture time sequence data of the target object, and performing similarity analysis on the biological sleeping posture time sequence data according to a time sequence to obtain a sleeping posture change node time sequence chain so as to realize capturing of key data in the sleeping posture habit of the target object;
step S2, the sleep posture change node time sequence chain is divided at the nodes to obtain a plurality of sleep posture stability time sequence sections representing unique sleep posture habits, labeling processing is carried out on the sleep posture stability time sequence sections to obtain sleep posture habit analysis samples, and then the plurality of sleep posture habit analysis samples are classified according to sample labels to obtain a plurality of groups of sleep posture habit analysis sample sets so as to realize classification of the sleep posture habits of the target object;
and step S3, sequentially carrying out time sequence section mode analysis on all the sleep posture habit analysis samples in the multiple groups of sleep posture habit sample sets to obtain sleep posture habit representative samples representing the main characteristics of the sleep posture habits of the target object, and carrying out threshold analysis on all the sleep posture habit representative samples to obtain the poor sleep posture adjustment category and the poor sleep posture adjustment scheme of the target object so as to realize the correction of the poor sleep posture of the target object.
2. The data information processing method of the home system according to claim 1, characterized in that: in step S1, the specific method for analyzing the similarity of the biological sleep posture time series data according to the time series to obtain the sleep posture change node time series chain includes:
s101, carrying out similarity analysis on data of adjacent time sequences in the biological sleeping posture time sequence data to obtain a similarity data chain, wherein a calculation formula of the similarity is as follows:
wherein,
step S102, selecting all jump nodes on the similarity data chain, selecting data corresponding to time sequences at two sides of all jump nodes from biological sleeping posture time sequence data as sleeping posture change nodes, and arranging the sleeping posture change nodes according to time sequences to form a sleeping posture change node time sequence chain;
the jumping node refers to a data node of which the numerical value difference between a node on the similarity data chain and a left adjacent node and a right adjacent node exceeds a similarity threshold value.
3. The data information processing method of the home system according to claim 2, characterized in that: in step S2, the method for obtaining the sleeping posture habit analysis sample includes:
step S201, establishing a sleeping posture identification sample set according to sleeping posture types, and establishing a sleeping posture type identification model based on the sleeping posture identification sample set;
step S202, the stable sleeping postures in the sleeping posture stable time sequence section are subjected to type identification by using the sleeping posture type identification model, and the sleeping posture type is used as a sample label to mark the sleeping posture stable time sequence section to obtain the sleeping posture habit analysis sample.
4. The data information processing method of the home system according to claim 3, wherein: in step S201, the method for constructing the sleep posture identification sample includes:
the target object carries out the simulation of the sleeping posture behavior according to the sleeping posture type, records the characteristic data of the sleeping posture behavior as a sleeping posture sample corresponding to the sleeping posture type, and takes the sleeping posture type as a sample label of the sleeping posture sample;
and mixing the sleeping posture samples of all sleeping posture types into a sleeping posture identification sample set according to equal proportion so as to keep the balance of the samples trained by the sleeping posture type identification model.
5. The data information processing method of the home system according to claim 4, wherein: in step S201, the method for establishing the sleep posture type recognition model includes:
step S2011, the sleep posture identification sample set is divided into a training set and a testing set according to a preset proportion, and the training set is applied to a convolutional neural network for model identification training, wherein the characteristic data of the sleep posture samples in the training set is used as the input of the convolutional neural network, and the sample labels of the sleep posture samples in the training set are used as the output of the convolutional neural network;
and step S2012, carrying out output test and parameter correction on the recognition model trained in the step S2011 in the test set to obtain a recognition model with the highest precision, and using the recognition model with the highest precision after correction as the sleeping posture type recognition model, wherein the feature data of the sleeping posture samples in the test set is used as the input of the recognition model, and the sample labels of the sleeping posture samples in the test set are used as the output of the recognition model.
6. The data information processing method of the home system according to claim 5, wherein: in step S202, the input of the sleep posture type identification model is biological sleep posture time sequence data representing stable sleep postures in the sleep posture stable time sequence section, and the output of the sleep posture type identification model is the sleep posture type of the stable sleep posture in the sleep posture stable time sequence section.
7. The data information processing method of a home furnishing system according to claim 6, wherein in step S3, the method for obtaining the sleep habit representative sample comprises:
sequentially carrying out time sequence section duration statistics on all the sleep habit analysis samples in the sleep habit sample set, and screening out the sleep habit analysis samples with the same time sequence section duration and the largest number;
randomly selecting one sleeping posture habit analysis sample from the largest number of sleeping posture habit analysis samples with the same length in the time sequence section as a sleeping posture habit representative sample of the corresponding sleeping posture habit sample set.
8. The data information processing method of a home furnishing system according to claim 7, wherein in step S3, the obtaining method of the poor sleeping posture adjustment category and the poor sleeping posture adjustment scheme of the target object comprises:
comparing the time sequence section duration of the sleeping posture habit representative sample with a sleeping posture standard duration threshold of the sleeping posture type corresponding to the sample label of the sleeping posture habit representative sample, wherein,
if the time sequence section duration exceeds the sleeping posture standard duration threshold, the sleeping posture type corresponding to the sample label of the sleeping posture habit representative sample belongs to a bad sleeping posture adjustment type, and the time sequence section duration of the sleeping posture habit representative sample is used as the type duration of the bad sleeping posture adjustment type;
obtaining the category duration of each poor sleeping posture adjustment category, setting the sleeping posture adjustment duration of the poor sleeping posture adjustment category as the corresponding category duration to be gradually decreased by 10% at regular intervals until the duration is decreased to a sleeping posture standard duration threshold, and maintaining the duration on the sleeping posture standard duration threshold as a poor sleeping posture adjustment scheme so as to gradually adjust the poor sleeping posture of the target object and reduce the discomfort of the target object to the adjustment of the sleeping posture;
the regular decrement is represented as the time length that the sleeping posture adjustment time length is equal to the category time length reduced by 10% every other preset period, and the operation formula of the regular decrement is as follows:
wherein H is the sleeping posture adjustment time length of the nth period, and H is the category time length.
9. A processing system for performing the data-information processing method of any one of claims 1-8, comprising: the device comprises a model establishing unit, a scheme making unit, a sleeping posture collecting assembly arranged on the upper surface of a mattress and a sleeping posture adjusting unit arranged on the lower surface of the mattress;
the sleeping posture acquisition component is used for acquiring data related to biological sleeping postures of the target object;
the model establishing unit is used for establishing a sleeping posture type identification model for the target object;
the scheme making unit is used for establishing a poor sleeping posture adjusting scheme for the target object;
and the sleeping posture adjusting unit is used for adjusting the sleeping posture of the target object according to the poor sleeping posture adjusting scheme.
10. The processing system of claim 9, further comprising an identity account unit, wherein the identity account unit stores identity accounts of a plurality of different target objects, and a poor sleeping posture adjustment scheme and a sleeping posture type recognition model corresponding to a target object are uniquely bound in the identity accounts, so that the processing system is used for switching different target objects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111218096.5A CN113655730B (en) | 2021-10-20 | 2021-10-20 | Data information processing method and system for home system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111218096.5A CN113655730B (en) | 2021-10-20 | 2021-10-20 | Data information processing method and system for home system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113655730A true CN113655730A (en) | 2021-11-16 |
| CN113655730B CN113655730B (en) | 2022-02-15 |
Family
ID=78484265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111218096.5A Active CN113655730B (en) | 2021-10-20 | 2021-10-20 | Data information processing method and system for home system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113655730B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114205393A (en) * | 2022-02-16 | 2022-03-18 | 慕思健康睡眠股份有限公司 | Data reporting method and system of intelligent home system |
| CN114724550A (en) * | 2022-06-10 | 2022-07-08 | 慕思健康睡眠股份有限公司 | Audio identification method and device based on sleep, mattress and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104720753A (en) * | 2015-03-07 | 2015-06-24 | 黎曦 | Sleeping monitoring system and method thereof |
| US20170135881A1 (en) * | 2015-11-16 | 2017-05-18 | Eight Sleep Inc. | Adjustable bedframe and operating methods |
| CN106913124A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | Sleeping position control method and device |
| CN107944462A (en) * | 2016-10-12 | 2018-04-20 | 东莞丹蒂诗智能家居科技有限公司 | Sleeping position recognition methods based on intelligent-induction |
| CN113487845A (en) * | 2021-06-25 | 2021-10-08 | 中国科学院重庆绿色智能技术研究院 | Artificial intelligence learning system and posture correction method |
-
2021
- 2021-10-20 CN CN202111218096.5A patent/CN113655730B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104720753A (en) * | 2015-03-07 | 2015-06-24 | 黎曦 | Sleeping monitoring system and method thereof |
| US20170135881A1 (en) * | 2015-11-16 | 2017-05-18 | Eight Sleep Inc. | Adjustable bedframe and operating methods |
| CN106913124A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | Sleeping position control method and device |
| CN107944462A (en) * | 2016-10-12 | 2018-04-20 | 东莞丹蒂诗智能家居科技有限公司 | Sleeping position recognition methods based on intelligent-induction |
| CN113487845A (en) * | 2021-06-25 | 2021-10-08 | 中国科学院重庆绿色智能技术研究院 | Artificial intelligence learning system and posture correction method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114205393A (en) * | 2022-02-16 | 2022-03-18 | 慕思健康睡眠股份有限公司 | Data reporting method and system of intelligent home system |
| CN114205393B (en) * | 2022-02-16 | 2022-05-17 | 慕思健康睡眠股份有限公司 | Data reporting method and system of intelligent home system |
| CN114724550A (en) * | 2022-06-10 | 2022-07-08 | 慕思健康睡眠股份有限公司 | Audio identification method and device based on sleep, mattress and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113655730B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113655730B (en) | Data information processing method and system for home system | |
| CN106604508B (en) | Light environment control method and control system based on self study | |
| KR102312180B1 (en) | Personalized plants recommendation system | |
| CN109491253B (en) | Online learning type personalized intelligent home system and control method thereof | |
| Rees et al. | Why do big plants make big seeds? | |
| CN111488522A (en) | Personalized multidimensional scenic spot recommendation method | |
| CN109883016B (en) | Air comfort level adjusting method and device | |
| CN106372729B (en) | Deep learning method and device for psychological analysis | |
| CN104216325B (en) | A kind of Intellectualized monitoring method of smart pen | |
| CN114648156A (en) | Time series load prediction method based on convolutional neural network | |
| CN117729672A (en) | Healthy lighting control method, device, equipment and medium based on human body rhythm | |
| Wang et al. | Modeling rangelands as spatially-explicit complex adaptive systems | |
| CN108444076B (en) | Push method, air conditioning equipment, mobile terminal and storage medium | |
| CN105662394B (en) | A kind of method and apparatus prompting the user with information | |
| Rand | A stochastic model of the temporal aspect of breeding strategies | |
| Moon et al. | Comparison of individualized facial growth prediction models based on the partial least squares and artificial intelligence | |
| CN108376093B (en) | Sharing method, air conditioning equipment, mobile terminal and storage medium | |
| CN117762032A (en) | Intelligent equipment control system and method based on scene adaptation and artificial intelligence | |
| Metcalf et al. | Environmental uncertainty, autocorrelation and the evolution of survival | |
| CN109373499A (en) | Air conditioner control method and device | |
| CN104678843A (en) | Indoor plant recommendation method based on human health information and air composition data | |
| CN107883520A (en) | Reminding method and device based on air conditioning equipment and terminal | |
| CN107743331A (en) | Light source control method, device and system | |
| CN111797980A (en) | Self-adaptive learning method for personalized floor heating use habits | |
| CN114564517B (en) | Method for evaluating healthy and healthy climate by combining climate data and social perception data |
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 |