CN116294151A - Air conditioner temperature adjusting method, system, equipment and medium - Google Patents
Air conditioner temperature adjusting method, system, equipment and medium Download PDFInfo
- Publication number
- CN116294151A CN116294151A CN202310244758.9A CN202310244758A CN116294151A CN 116294151 A CN116294151 A CN 116294151A CN 202310244758 A CN202310244758 A CN 202310244758A CN 116294151 A CN116294151 A CN 116294151A
- Authority
- CN
- China
- Prior art keywords
- user
- air conditioner
- vasoconstriction
- comfortable
- degree
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 206010047139 Vasoconstriction Diseases 0.000 claims abstract description 65
- 230000025033 vasoconstriction Effects 0.000 claims abstract description 65
- 238000012545 processing Methods 0.000 claims description 35
- 238000013136 deep learning model Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 25
- 210000004204 blood vessel Anatomy 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 15
- 230000008602 contraction Effects 0.000 claims description 12
- 238000004378 air conditioning Methods 0.000 claims description 10
- 230000017531 blood circulation Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 5
- 239000008280 blood Substances 0.000 claims description 4
- 210000004369 blood Anatomy 0.000 claims description 4
- 230000001413 cellular effect Effects 0.000 claims description 4
- 230000033228 biological regulation Effects 0.000 claims description 2
- 230000001105 regulatory effect Effects 0.000 claims 2
- 230000008901 benefit Effects 0.000 description 13
- 230000000875 corresponding effect Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 8
- 230000017525 heat dissipation Effects 0.000 description 6
- 230000005855 radiation Effects 0.000 description 4
- 238000010977 unit operation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010016326 Feeling cold Diseases 0.000 description 1
- 206010016334 Feeling hot Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/89—Arrangement or mounting of control or safety devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides a method, a system, equipment and a medium for adjusting the temperature of an air conditioner, which comprise the following steps: step S1: acquiring vasoconstriction degree data of a human body; step S2: and adjusting the operation parameters of the air conditioner through an execution unit according to the vasoconstriction degree data. The invention can automatically adjust the environment to the most comfortable state for the user, and can automatically help the user to adjust the most comfortable environment when the user goes to different scenes.
Description
Technical Field
The invention relates to the technical field of air conditioners, in particular to an air conditioner temperature adjusting method, an air conditioner temperature adjusting system, air conditioner temperature adjusting equipment and an air conditioner temperature adjusting medium.
Background
The user can not adjust the temperature which is the most comfortable by the existing method for adjusting the temperature set by the air conditioner. The temperature setting of the air conditioner is not fine enough, and the error is larger; the temperature sensing element of the air conditioner is positioned at the air conditioner and cannot represent the sensing temperature of a user; the air conditioner can change the temperature and the humidity at the same time, and the air conditioner can not ensure the comfort of a user only by adjusting according to the temperature; the most comfortable temperature feeling felt by the user is also different in different human body states in different seasons in different time periods.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an air conditioner temperature adjusting method, an air conditioner temperature adjusting system, air conditioner temperature adjusting equipment and an air conditioner temperature adjusting medium.
According to the air conditioner temperature adjusting method, system, equipment and medium provided by the invention, the scheme is as follows:
in a first aspect, the present invention provides a method for adjusting temperature of an air conditioner, the method comprising:
step S1: acquiring vasoconstriction degree data of a human body;
step S2: according to the vasoconstriction degree data, whether the user feels comfortable or not is calculated/predicted, and then the operation parameters of the air conditioner are adjusted through the execution unit, so that the user finally feels comfortable.
Preferably, the step S1 includes: the skin image of the user is acquired through the image acquisition unit, and the blood vessel contraction degree data of the human body is acquired through the processing of the processing unit.
Preferably, the step S1 includes: inquiring whether the user feels comfortable, adjusting the execution parameters of the execution unit according to feedback of the user, and recording the currently corresponding vasoconstriction degree data when the user comfortable state is reached.
Preferably, the step S2 includes: comparing the obtained parameter value of the vasoconstriction degree data with a set target value, so as to calculate/predict whether the user feels comfortable;
or after obtaining the vasoconstriction degree data through the skin image, inquiring whether the user feels comfortable or not, and adjusting the set target value until the user feeds back the comfort.
Preferably, the processing of the skin image by the processing unit comprises: processing the image frame sequence for a period of time by using an rPPG algorithm to obtain a heartbeat fluctuation curve and the amplitude of the curve, namely the flow of blood in a blood vessel, so as to reversely push the contraction degree of the blood vessel;
the processing unit further includes: and analyzing the skin color of the user by using a skin color method, judging the blood flow, and reversely pushing the contraction degree of the blood vessel.
Preferably, the method comprises: in the use process, taking outdoor environment parameters and indoor air conditioner operation parameters in comfortable states of users at different times as training sets to train a first deep learning model, wherein the input of the first deep learning model is the outdoor environment parameters, and the output is the operation parameters of an execution unit;
and obtaining the operation parameters of the execution unit by using the first deep learning model, and performing fine adjustment by using the vasoconstriction degree data of the human body after performing coarse adjustment.
Preferably, the method further comprises: and directly adjusting the operation parameters output from the execution unit to the model by using the first deep learning model, performing coarse adjustment, then acquiring a skin image of the user, processing by using the processing unit, and comparing the processed parameter value with a target value, so as to calculate/predict whether the user feels comfortable, and performing fine adjustment.
Preferably, the method further comprises: by a curve fitting method or a deep learning method, when only the early data of the skin temperature change process are provided, the final falling point of the skin temperature can be calculated/estimated;
coarsely adjusting the final drop point of the calculated/estimated temperature change curve to a target value, namely the skin temperature in a comfortable state; and then the skin image of the user is acquired, the skin image is processed by the processing unit, and the parameter value obtained by processing is compared with the target value, so that whether the user feels comfortable or not is calculated/predicted, and the fine adjustment is performed.
Preferably, when there are a plurality of users in the room, the degree of vasoconstriction in the recorded comfort situation is S 0 The current degree of vasoconstriction per user is S t ；
Let data of user a be aS aS 0 ，aS t User b's data is bS 0 ，bS t The method comprises the steps of carrying out a first treatment on the surface of the The aim of adjusting the operation parameters of the air conditioner in the room is to enable the value of the parameter T to be minimum through adjustment;
T＝Wa*(|aS 0 -aS t |)+Wb*(|bS 0 -bS t |)+...；
wherein W represents the weight, i.e. the importance of different users, may be the same or different.
Preferably, when the user just enters the room from the outside, training a second deep learning model which is input as the outdoor environment parameter and output as the air conditioner operation parameter by taking the feedback of the user as training data, wherein the second deep learning model is used for the user just entering the room from the outside and operating the air conditioner by using the air conditioner operation parameter in the second deep learning model before the user enters the room;
the method for judging whether the user enters the room comprises the following steps: and 5G cellular positioning of the mobile phone, an Internet of things association method and a sensing result of the indoor living body sensor.
In a second aspect, the present invention provides an air conditioner temperature adjustment system, comprising:
module M1: acquiring vasoconstriction degree data of a human body;
module M2: according to the vasoconstriction degree data, whether the user feels comfortable or not is calculated/predicted, and then the operation parameters of the air conditioner are adjusted through the execution unit, so that the user finally feels comfortable.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor implements steps in the air conditioning temperature adjustment method.
In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements steps in the air conditioning temperature adjustment method.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention can automatically adjust the environment to the most comfortable state of the user, and can automatically help the user to adjust the environment to the most comfortable state when the user goes to different scenes;
2. the invention uses skin temperature to roughly adjust and then finely adjust the operation parameters of the air conditioner, thereby saving operation resources.
Other advantages of the present invention will be set forth in the description of specific technical features and solutions, by which those skilled in the art should understand the advantages that the technical features and solutions bring.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a block diagram of the overall steps of the invention;
fig. 2 is a schematic diagram of embodiment 1;
fig. 3 is a schematic diagram of embodiment 2;
fig. 4 is a schematic diagram of embodiment 3;
fig. 5 is a schematic diagram of embodiment 4;
fig. 6 is a schematic diagram of embodiment 5;
fig. 7 is a schematic diagram of embodiment 6;
fig. 8 is a schematic diagram of embodiment 8.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present invention.
The embodiment of the invention provides an air conditioner temperature adjusting method, which is shown by referring to fig. 1, and specifically comprises the following steps:
step S1: acquiring vasoconstriction degree data of a human body;
step S2: according to the vasoconstriction degree data, whether the user feels comfortable or not is calculated/predicted, and then the operation parameters of the air conditioner are adjusted through the execution unit, so that the user finally feels comfortable.
Specifically, step S1 includes: the skin image of the user is acquired through the image acquisition unit, and the blood vessel contraction degree data of the human body is acquired through the processing of the processing unit.
Step S1 further includes: inquiring whether the user feels comfortable, adjusting the execution parameters of the execution unit according to feedback of the user, and recording the currently corresponding vasoconstriction degree data when the user comfortable state is reached.
The step S2 comprises the following steps: comparing the obtained parameter value of the vasoconstriction degree data with a set target value, so as to calculate/predict whether the user feels comfortable; or after obtaining the vasoconstriction degree data through the skin image, inquiring whether the user feels comfortable or not, and adjusting the set target value until the user feeds back the comfort.
Wherein the processing of the skin image by the processing unit comprises: (1) And processing the image frame sequence for a period of time by using an rPPG algorithm to obtain a heartbeat fluctuation curve and the amplitude of the curve, namely the flow of blood in a blood vessel, so as to reversely push the contraction degree of the blood vessel. (2) the processing unit processing the skin image further comprises: and analyzing the skin color of the user by using a skin color method, judging the blood flow, and reversely pushing the contraction degree of the blood vessel.
According to the air conditioner temperature regulation method, in the using process, outdoor environment parameters and indoor air conditioner operation parameters at different times are used as training sets, a deep learning model is trained, the input of the deep learning model is the outdoor environment parameters in a human body comfort state, and the output is the operation parameters of an execution unit; and obtaining the operation parameters of the execution unit by using a deep learning model, and performing fine adjustment by using the vasoconstriction degree data after performing coarse adjustment.
According to the air conditioner temperature adjusting method, the deep learning model can be used for directly adjusting the operation parameters from the execution unit to the model output, coarse adjustment is performed, then the skin image of the user is obtained, the skin image is processed through the processing unit, the parameter value obtained through processing is compared with the target value, and therefore whether the user feels comfortable or not is calculated/predicted, and fine adjustment is performed.
According to the air conditioner temperature adjusting method, the final falling point of the skin temperature can be calculated/estimated through a curve fitting method or a deep learning method when only the early data of the skin temperature change process are provided; coarsely adjusting the final drop point of the calculated/estimated temperature change curve to a target value, namely the skin temperature in a comfortable state; and then the skin image of the user is acquired, the skin image is processed by the processing unit, and the parameter value obtained by processing is compared with the target value, so that whether the user feels comfortable or not is calculated/predicted, and the fine adjustment is performed.
When there are multiple users in the room, the degree of vasoconstriction in the recorded comfort situation is S 0 The current degree of vasoconstriction per user is S t ；
Let data of user a be aS aS 0 ，aS t User b's data is bS 0 ，bS t The method comprises the steps of carrying out a first treatment on the surface of the The aim of adjusting the operation parameters of the air conditioner in the room is to enable the value of the parameter T to be minimum through adjustment;
T＝Wa*(|aS 0 -aS t |)+Wb*(|bS 0 -bS t |)+...；
wherein W represents the weight, i.e. the importance of different users, may be the same or different.
Training a deep learning model which is input as an outdoor environment parameter and output as an air conditioner operation parameter when a user just enters the room from the outside, and operating the air conditioner by the air conditioner operation parameter in the deep learning model before the user just enters the room from the outside;
the method for judging whether the user enters the room comprises the following steps: and 5G cellular positioning of the mobile phone, an Internet of things association method and a sensing result of the indoor living body sensor.
The present invention also provides an air conditioner temperature adjusting system, which can be implemented by executing the flow steps of the air conditioner temperature adjusting method, that is, the air conditioner temperature adjusting method can be understood by those skilled in the art as a preferred embodiment of the air conditioner temperature adjusting system.
Next, the present invention will be described in more detail.
Embodiment 1: referring to fig. 2, an image of the skin of a user is acquired through an image acquisition unit, and is processed through a processing unit to obtain some parameter values, and compared with target values, so that whether the user feels comfortable is calculated/predicted, and thus the user feels comfortable finally through execution of an execution unit (including, but not limited to, changing factors that influence the cold and hot feeling of the user by various means such as the temperature, humidity, wind speed, radiation intensity, etc. of the environment).
The advantages are that: bypassing the traditional mode of setting the ambient temperature, the most fundamental feeling of the user is directly calculated, and the operation of the execution unit is adjusted accordingly (including but not limited to all factors which can influence the cold and hot feeling of the user, such as temperature, humidity, wind speed, radiation intensity, and the like, and devices possibly related include but are not limited to air conditioners, humidifiers, heaters, fresh air systems, and the like).
Embodiment 2: referring to fig. 3, the method of acquiring the human vasoconstriction degree data in step S1 in claim 1, that is, the method of acquiring the target value in embodiment 1 is described. The target value in embodiment 1 may be human average data from a research institution; the execution unit may be adjusted in accordance with the feedback of the user by inquiring whether the user feels comfortable or not in the software/hardware configuration of embodiment 1, and recording and storing the current corresponding value (degree of vasoconstriction) until the user feedback is comfortable.
Meanwhile, the acquiring manner may be that, under the software and hardware setting of embodiment 1, the user is asked whether to feel comfortable, and the set target value is adjusted according to the feedback of the user, so that the software and hardware can target the adjusted target value, embodiment 1 is executed, and after multiple adjustments, the current corresponding value (vasoconstriction degree) is recorded and stored until the user feedback is comfortable.
Embodiment 2 may be executed alone or after embodiment 1 is executed.
Specifically, the difference between the software and hardware settings of the embodiment 1 and the embodiment 2 is not great, and the difference is that the embodiment 1 does not need the manual participation of the user, and the whole course is that the system is automatically adjusted to the most comfortable environment of the user, and the embodiment 2 needs the manual feedback of the user, so as to obtain the personalized value (vasoconstriction degree) of each user; the values obtained in embodiment 2 can be used for automatic adjustment of the system in embodiment 1; embodiment 2 generally needs to be executed once without repeated execution, and may be executed multiple times; the "target value" obtained after performing 2 in a certain environment is strongly correlated with the user instead of the environment, i.e. can be used for the scenario of the same user in any other environment.
The advantages are that: after the corresponding vasoconstriction degree under the personalized most comfortable state of the user is obtained, the personalized adjustment can be provided for the user according to the vasoconstriction degree, and the method is not limited to specific environments, for example, a room is replaced, the corresponding vasoconstriction degree under the personalized most comfortable state can still be in different rooms, and the operation parameters of the air conditioner can be automatically adjusted for the user, so that the user feels the most comfortable.
Embodiment 3: referring to fig. 4, in the current environment, a deep learning model is trained, the input of which is the outdoor environment parameter, and the output is the operating parameter of the execution unit. The training set of the model is collected by the current outdoor environment parameters and the current running parameters of the execution unit when the user is in a state of no cold or no heat comfort in the current environment. It is noted that this model is strongly related to the current environment and not to the user, i.e. this model cannot be used for the user's scenario in another environment.
The advantages are that: the advantage of using embodiment 3 is that training data of the deep learning model can be automatically collected, i.e. after each time the user reaches a comfortable state using embodiment 1, the outdoor environment parameters and the execution unit operation parameters corresponding to that time are recorded.
Embodiment 4: referring to fig. 5, the model trained in embodiment 3 is used to directly adjust execution unit parameters from execution unit to model output. Embodiment 1 is then performed.
The advantages are that: an initial rough execution unit operation parameter can be provided, so that the operation parameter of the execution unit has a relatively rough initial value which is almost the same as a final stable value, and the operation resource is saved.
Embodiment 5: referring to fig. 6, if there is a temperature acquisition unit in the system, the degree of vasoconstriction and skin temperature in a comfortable state are simultaneously acquired from the stored target values using a possible existing temperature acquisition unit. By curve fitting/deep learning, the final skin temperature drop point can be calculated/inferred when only the skin temperature change process is performed on the earlier data. The calculated/estimated final drop point of the temperature change curve is adjusted to the target value, i.e. the skin temperature in a comfortable state, i.e. the operating parameters of the actuator are adjusted to influence the final drop point of the temperature change curve. Embodiment 1 is then performed.
The advantages are that: the temperature acquisition unit can save the consumption of a large amount of computing resources in embodiment 1, because the image processing and the arithmetic operation are required to consume a large amount of computing resources; however, the temperature acquired by the temperature sensor is hysteresis, because the temperature change is not performed at a time, but a certain time is needed, and the change of cold and hot feeling of a person is a rapid process. Thus, a need arises between the two: the temperature acquisition unit can help to save the computing resource, but a long time is required until the temperature of the user is stable, so that the user can know the cold and hot feeling. By using embodiment 5, the user does not need to wait for the skin temperature to be finally stabilized and then adjust the air conditioner operation parameters, but can adjust the air conditioner operation parameters more quickly, thereby achieving the purpose of making the user feel comfortable more quickly.
Embodiment 6: referring to fig. 7, the stable skin temperature in the comfortable state in embodiment 5 is optimized, and in the case of having the personalized vasoconstriction degree of the user in embodiment 1, the stable skin temperature in the comfortable state of the user is automatically acquired and stored.
The advantages are that: having a skin temperature in a personalized comfort state for the user can be used to enhance the user experience of embodiment 5. And embodiment 6 is fully automatic, does not require manual feedback to query the user, is therefore more user friendly, and does not require the user to do anything else manually.
Embodiment 7: when there are multiple users in the room, the degree of vasoconstriction in the recorded comfort situation is S 0 The current degree of vasoconstriction per user is S t ；
Let data of user a be aS aS 0 ，aS t User b's data is bS 0 ，bS t The method comprises the steps of carrying out a first treatment on the surface of the The aim of adjusting the operation parameters of the air conditioner in the room is to enable the value of the parameter T to be minimum through adjustment;
T＝Wa*(|aS 0 -aS t |)+Wb*(|bS 0 -bS t |)+...；
wherein W represents the weight, i.e. the importance of different users, may be the same or different.
The advantages are that: in most current air conditioning environments, when there are multiple people in the environment, it is common for a user to dispute about a set temperature, either by feeling too hot or by feeling too cold. Embodiment 7, based on the software and hardware settings, directly calculates/predicts whether the user feels comfortable, and compared with the existing temperature control mode, the method is more accurate, so that the problem can be better alleviated/avoided; meanwhile, the target value balancing the feeling of each user is automatically distributed directly according to the difference value of the current cold and hot feeling/vasoconstriction degree and the ideal cold and hot feeling/vasoconstriction degree of each different user, and the negotiation among the users is actively carried out by each user in a mode which does not need to go as a current mode.
Embodiment 8: referring to fig. 8, when a user just enters indoors from outdoors, a deep learning model is trained, input as outdoor environment parameters, and output as initial operation parameters of the execution unit. The training data is that when the model is used for iterative training, the setting of the similar GAN generation countermeasure network is used, the feeling of the user when the user just enters the room is taken as a discriminator, and the final target network generator, namely, the user just enters the room and feels too cold or too hot as negative feedback in the network countermeasure training process, so as to perform countermeasure network training.
It should be noted that the arbiter at this setting is feedback of the user, not another deep learning model. The feedback of the user of the discriminator may be the adjustment of the operating parameters of the execution unit manually by the user, i.e. the difference between the operating parameters of the execution unit which have been manually adjusted by the user just when entering the room and the initial operating parameters of the execution unit obtained by the user before entering the room using the generator; it may also be a value automatically derived by the system, i.e. the difference between the degree of vasoconstriction of the user just entering the room and the degree of vasoconstriction of the user in a comfortable state. The former manual adjustment of the operation parameters of the execution unit is a commonly accepted mode for users in the market at present; the numerical value obtained automatically by the system of the latter is automatic in the whole process compared with the former, does not need any intervention of a user, and is more user-friendly. Each time the user enters a room, the optimal iteration training of the network is performed.
The advantages are that: when a user just enters the room from the outside, the user also hopes to feel comfortable when standing a horse, so the Internet of things application of remotely starting an air conditioning system exists in the market at present. However, because the user can contract/expand the blood vessel by feeling cold/hot outdoors, thereby reducing/increasing the heat dissipation, there is a difference between the execution unit operation parameters that the user just feels comfortable when the user just enters indoors and the execution unit operation parameters that the user just feels comfortable after waiting a while indoors. At the same time, the magnitude of this difference, or the operating parameters of the execution unit that the user just feels comfortable when he/she just enters the room, often has a direct relationship with the outdoor environmental parameters. The contraction/expansion of the blood vessel of the user is a relatively rapid procedure, so that if the training data acquisition method of embodiment 3 is directly adopted, no suitable training data can be acquired. Therefore, by adopting GAN-like generation to combat network setting and taking feedback of a user as a discriminator, each time the user enters a room, the user can perform optimal iterative training on the network. Finally, a proper generator network is trained, the input is the outdoor environment parameter, and the output is the initial operation parameter of the execution unit, so that a user can feel just comfortable when entering a room.
The invention is further described. According to the cold and hot feeling of the user, the operation parameters of the air conditioner are adjusted, and the operation parameters are not necessarily a traditional temperature setting, but the power of the air conditioner, the air quantity of the air conditioner, the air outlet direction of the air conditioner and the like. The specific cold and hot feeling obtaining mode is as follows: the skin image of a person is acquired by using a sensor (including, but not limited to, a front camera of a mobile phone, a camera of a DMS system of an automobile, and a healthy bracelet), and then is processed to measure or predict whether the user feels too cold or too hot or just comfortable.
The healthy bracelet can be taken by itself, and the heartbeat function of the user can be acquired. The specific implementation mode is that the bracelet lights the wrist of the user with LED light, then obtains reflected light, and then processes the reflected light to obtain a heartbeat curve.
There are 2 ways of processing skin images: 1. processing the image frame sequence for a period of time by using an rPPG algorithm to obtain a heartbeat fluctuation curve, and then obtaining the amplitude of the curve, namely the flow of blood in a blood vessel, so that the contraction degree of a blood vessel can be reversely pushed; 2. and analyzing the skin color of the user, judging the blood flow, and pushing the contraction degree of the blood vessel back.
The degree of vasoconstriction is positively correlated with the cold and hot sensation of the user. Because people feel cold, the blood vessels are not automatically contracted, so that the blood flow is reduced, and the heat dissipation is reduced; accordingly, when people feel hot, the blood vessels are not expanded autonomously, so that the blood flow is increased, and the heat dissipation is increased.
The above operations may use a popular average, such as that given by a research institution, the degree of vasoconstriction of the user, etc., but it is also recognized that each individual varies. Therefore, the user can be asked by the system whether he feels too cold or too hot or just comfortable, and then go to make a personalized adjustment. And finally, when the user comfort of the individual user is reached, recording the currently corresponding vasoconstriction degree.
Prior to using the degree of vasoconstriction to adjust the operating parameters of the execution unit, the operating resources may be saved by first coarsely adjusting the skin temperature of the user, and using the detected skin temperature of the user (e.g., using a healthy wristband to measure the skin temperature of the user, or using an infrared sensor to measure the skin temperature of the user, or otherwise) to target the temperature at which it reaches a comfortable state.
Under current air conditioner operating parameters, the skin temperature of the user changes, not immediately at a stroke, but rather with a change process. By curve fitting or by training a deep learning model, it is achieved that the final skin temperature drop point can be calculated/deduced only with the earlier data of the skin temperature course. The advantage of doing so is, need not wait for user skin temperature to stabilize finally, go to adjust air conditioner operating parameter again, but can be faster go to adjust air conditioner operating parameter to reach the purpose that lets the user feel comfortable more soon.
The corresponding degree of vasoconstriction of the user, when the user feels the most comfortable, recorded before use, serves as a target for adjusting the operating parameters of the air conditioner. (for each user, only the first time it is required to actively ask the user if he feels too cold or too hot, and then record the corresponding degree of vasoconstriction; the air-conditioning operating parameters can then be automatically adjusted to make the user feel the most comfortable) (because the degree of vasoconstriction is directly related to whether the user feels too cold or too hot; regardless of what state the user is in, e.g., whether the user is moving, whether the user is feverish, the difference in state of the user may result in a difference in skin temperature corresponding to when the user feels just comfortable, but does not change the degree of vasoconstriction corresponding to when the user feels just comfortable).
The process of obtaining the personalized, comfortable vasoconstriction degree of each user can be carried out by firstly adjusting to the popular average vasoconstriction degree, then inquiring the user so as to adjust to the personalized vasoconstriction degree, and recording; this step can also be accomplished by not adjusting to the mass average degree of vasoconstriction and then querying the user to adjust to the personalized degree of vasoconstriction, but rather querying the user continuously from the beginning whether he feels too cold or too hot, so that the personalized degree of vasoconstriction for each user is adjusted in place in one step and recorded.
Outdoor environmental parameters (illumination intensity, temperature, humidity, etc.) and indoor air conditioning operation parameters at different times during one year were used as training sets. Training a deep learning model, wherein the input of the model is an outdoor environment parameter, and the output of the model is an air conditioner operation parameter. For each room, a coarsely adjusted air conditioning operating parameter is obtained in an extremely short time.
The present outdoor environment parameters are input using a deep learning model of the configuration for this (room+air conditioner), and the air conditioner operation parameters are obtained and coarsely adjusted.
The skin temperature in the most comfortable state of the current user individualization is recorded by collecting the skin temperature in the most comfortable state of the current user. Is used for replacing the prior popular skin temperature under the most comfortable state.
And (3) using a deep learning model, obtaining air conditioner operation parameters by inputting current outdoor environment parameters, and performing fine adjustment by using the personalized vasoconstriction degree of the current user after performing coarse adjustment.
And (3) using the acquired temperature and combining a prediction mode (fitting method/deep learning method) of a final falling point of the temperature change curve to perform rough adjustment towards the skin temperature corresponding to the most comfortable state of the individuation of the current user. The personalized vasoconstriction of the current user is then used for fine adjustment.
When there are multiple users in the room, the degree of vasoconstriction in the recorded comfort situation is S 0 The current degree of vasoconstriction per user is S t ；
Let data of user a be aS aS 0 ，aS t User b's data is bS 0 ，bS t The method comprises the steps of carrying out a first treatment on the surface of the Target for adjusting air conditioner operation parameters of multiple persons in roomThat is, by adjusting, the value of the parameter T is minimized;
T＝Wa*(|aS 0 -aS t |)+Wb*(|bS 0 -bS t |)+...；
wherein W represents the weight, i.e. the importance of different users, may be the same or different.
The output of the first deep learning model, in addition to being a coarse adjustment prior to fine adjustment, may also be used when the user enters indoors from outdoors. But the user just enters the room from the outside, typically feels that the air-conditioning operation parameters derived by the first deep learning model are too cold (when the outside temperature is high) or too hot (when the outside temperature is low). Because when outdoor temperature is high, people can expand blood vessels outdoors to increase heat dissipation, in this way, the heat dissipation can be too large when entering the air conditioner operation parameters obtained by the indoor first deep learning model at a time, so that people feel too cold in a short time, and blood vessels are contracted to reduce heat dissipation. Otherwise, the same is true. Although the latter fine tuning will eventually be tuned to the point where the user just feels comfortable, it will still feel too cold/too hot for a period of time. Therefore, the air conditioner can be operated with a lower air conditioner operation parameter before the user enters the room. As to how this 'lower' is decided, that is, one is trained for each room and each user combination in combination with the outdoor environment parameters, input as the outdoor environment parameters, and output as the air conditioner operation parameters, for the deep learning model that the user just enters from the outside into the inside. The method for judging whether the user just enters the room can be a mobile phone 5G cellular positioning method, an Internet of things association method, or a sensing result of an indoor living body sensor, and the like.
Because the situation that the user just feels comfortable just when entering the room is rare and insufficient for training the deep learning model, the setting similar to the GAN generation countermeasure network is adopted, the feeling of the user when just entering the room is taken as a discriminator, and the final target network generator, namely, the user just when entering the room feels too cold or too hot as negative feedback in the network countermeasure training process, is taken for countermeasure network training. It should be noted that the arbiter at this setting is feedback of the user, not another deep learning model. The feedback of the user of the discriminator may be the adjustment of the operating parameters of the execution unit manually by the user, i.e. the difference between the operating parameters of the execution unit which have been manually adjusted by the user just when entering the room and the initial operating parameters of the execution unit obtained by the user before entering the room using the generator; it may also be a value automatically derived by the system, i.e. the difference between the degree of vasoconstriction of the user just entering the room and the degree of vasoconstriction of the user in a comfortable state. The former manual adjustment of the operation parameters of the execution unit is a commonly accepted mode for users in the market at present; the numerical value obtained automatically by the system of the latter is automatic in the whole process compared with the former, does not need any intervention of a user, and is more user-friendly. Each time the user enters a room, the optimal iteration training of the network is performed.
The embodiment of the invention provides an air conditioner temperature adjusting method, an air conditioner temperature adjusting system, an air conditioner temperature adjusting device and an air conditioner temperature adjusting medium, which can automatically adjust the environment to the most comfortable state perceived by a user, and can automatically help the user to adjust the environment to the most comfortable state when the user goes to different scenes. In addition, the invention is not limited to the use of an air conditioner, the temperature, the humidity, the wind speed, the radiation intensity and the like can influence the cold and hot feeling of a human body, other electric appliances besides the electric appliances for changing the temperature and the humidity of the air conditioner can also change the cold and hot feeling, such as a warm oil heater, a radiation warmer and the like, and the method provided by the invention can be used.
Those skilled in the art will appreciate that the invention provides a system and its individual devices, modules, units, etc. that can be implemented entirely by logic programming of method steps, in addition to being implemented as pure computer readable program code, in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, the system and various devices, modules and units thereof provided by the invention can be regarded as a hardware component, and the devices, modules and units for realizing various functions included in the system can also be regarded as structures in the hardware component; means, modules, and units for implementing the various functions may also be considered as either software modules for implementing the methods or structures within hardware components.
The foregoing describes specific embodiments of the present invention. It is to be understood that the invention is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the invention. The embodiments of the present application and features in the embodiments may be combined with each other arbitrarily without conflict.
Claims (13)
1. An air conditioner temperature adjusting method, comprising:
step S1: acquiring vasoconstriction degree data of a human body;
step S2: according to the vasoconstriction degree data, whether the user feels comfortable or not is calculated/predicted, and then the operation parameters of the air conditioner are adjusted through the execution unit, so that the user finally feels comfortable.
2. The air conditioner temperature adjusting method according to claim 1, wherein the step S1 includes: the skin image of the user is acquired through the image acquisition unit, and the blood vessel contraction degree data of the human body is acquired through the processing of the processing unit.
3. The air conditioner temperature adjusting method according to claim 1, wherein the step S1 includes: inquiring whether the user feels comfortable, adjusting the execution parameters of the execution unit according to feedback of the user, and recording the currently corresponding vasoconstriction degree data when the user comfortable state is reached.
4. The air conditioner temperature adjusting method according to claim 2, wherein the step S2 includes: comparing the obtained parameter value of the vasoconstriction degree data with a set target value, so as to calculate/predict whether the user feels comfortable;
or after obtaining the vasoconstriction degree data through the skin image, inquiring whether the user feels comfortable or not, and adjusting the set target value until the user feeds back the comfort.
5. The air conditioner temperature adjustment method according to claim 2, wherein the processing of the skin image by the processing unit includes: processing the image frame sequence for a period of time by using an rPPG algorithm to obtain a heartbeat fluctuation curve and the amplitude of the curve, namely the flow of blood in a blood vessel, so as to reversely push the contraction degree of the blood vessel;
the processing unit further includes: and analyzing the skin color of the user by using a skin color method, judging the blood flow, and reversely pushing the contraction degree of the blood vessel.
6. The air conditioner temperature adjusting method according to claim 1, characterized in that the method comprises: in the use process, taking outdoor environment parameters and indoor air conditioner operation parameters in comfortable states of users at different times as training sets to train a first deep learning model, wherein the input of the first deep learning model is the outdoor environment parameters, and the output is the operation parameters of an execution unit;
and obtaining the operation parameters of the execution unit by using the first deep learning model, and performing fine adjustment by using the vasoconstriction degree data of the human body after performing coarse adjustment.
7. The air conditioner temperature adjusting method according to claim 6, further comprising: and directly adjusting the operation parameters output from the execution unit to the model by using the first deep learning model, performing coarse adjustment, then acquiring a skin image of the user, processing by using the processing unit, and comparing the processed parameter value with a target value, so as to calculate/predict whether the user feels comfortable, and performing fine adjustment.
8. The air conditioner temperature adjusting method according to claim 1, wherein the method further comprises: by a curve fitting method or a deep learning method, when only the early data of the skin temperature change process are provided, the final falling point of the skin temperature can be calculated/estimated;
coarsely adjusting the final drop point of the calculated/estimated temperature change curve to a target value, namely the skin temperature in a comfortable state; and then the skin image of the user is acquired, the skin image is processed by the processing unit, and the parameter value obtained by processing is compared with the target value, so that whether the user feels comfortable or not is calculated/predicted, and the fine adjustment is performed.
9. The air conditioner temperature adjusting method according to claim 1, wherein when there are a plurality of users in a room, the degree of vasoconstriction in the recorded comfort condition is S 0 The current degree of vasoconstriction per user is S t ；
Let data of user a be aS aS 0 ，aS t User b's data is bS 0 ，bS t The method comprises the steps of carrying out a first treatment on the surface of the The aim of adjusting the operation parameters of the air conditioner in the room is to enable the value of the parameter T to be minimum through adjustment;
T＝Wa*(|aS 0 -aS t |)+Wb*(|bS 0 -bS t |)+...；
wherein W represents the weight, i.e. the importance of different users, may be the same or different.
10. The air conditioner temperature adjusting method according to claim 1, wherein when a user just enters the room from the outside, training a second deep learning model which is inputted as an outdoor environment parameter and outputted as an air conditioner operation parameter by using the user's feedback as training data, for operating the air conditioner with the air conditioner operation parameter in the second deep learning model just before the user enters the room from the outside;
the method for judging whether the user enters the room comprises the following steps: and 5G cellular positioning of the mobile phone, an Internet of things association method and a sensing result of the indoor living body sensor.
11. An air conditioner temperature regulation system, comprising:
module M1: acquiring vasoconstriction degree data of a human body;
module M2: according to the vasoconstriction degree data, whether the user feels comfortable or not is calculated/predicted, and then the operation parameters of the air conditioner are adjusted through the execution unit, so that the user finally feels comfortable.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the air conditioning temperature regulating method of any one of claims 1 to 10.
13. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the air conditioning temperature regulating method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310244758.9A CN116294151A (en) | 2023-03-14 | 2023-03-14 | Air conditioner temperature adjusting method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310244758.9A CN116294151A (en) | 2023-03-14 | 2023-03-14 | Air conditioner temperature adjusting method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116294151A true CN116294151A (en) | 2023-06-23 |
Family
ID=86797356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310244758.9A Pending CN116294151A (en) | 2023-03-14 | 2023-03-14 | Air conditioner temperature adjusting method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116294151A (en) |
-
2023
- 2023-03-14 CN CN202310244758.9A patent/CN116294151A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114237069B (en) | Indoor environment control method, device, system and storage medium | |
| US20180195752A1 (en) | Air-conditioning control method, air-conditioning control apparatus, and storage medium | |
| CN110529988B (en) | Control method, device and equipment of air conditioner, air conditioner and storage medium | |
| WO2020258779A1 (en) | Air conditioner control method and control system | |
| CN111076375A (en) | Control method and system for fresh air ventilation of air conditioner and information data processing terminal | |
| CN112378056B (en) | Intelligent air conditioner control method and device, computer equipment and storage medium | |
| CN110631218B (en) | Control method, device and system for air equipment and computer storage medium | |
| CN110631220B (en) | Control method, device and system for air equipment and computer storage medium | |
| CN108954662A (en) | Air conditioner temperature control method and device | |
| CN110701750A (en) | Operation control method, operation control device, air conditioner, and storage medium | |
| CN115585538B (en) | Indoor temperature adjusting method and device, electronic equipment and storage medium | |
| CN107229262A (en) | A kind of intelligent domestic system | |
| CN110631219B (en) | Control method, device and system for air equipment and computer storage medium | |
| CN105910224A (en) | Adaptive air-conditioning adjusting system and method based on environment detection and automatic learning | |
| CN110822616A (en) | Automatic air conditioner adjusting method and device | |
| CN109357366B (en) | Regulation control method and device, storage medium and air conditioning system | |
| CN111033136B (en) | Air environment control system, air environment control device and air environment control method | |
| CN110578961A (en) | wall-mounted boiler control method, control equipment, wall-mounted boiler and computer storage medium | |
| CN110285537A (en) | Control method, air conditioner and the storage medium of air conditioner | |
| CN112361542B (en) | Control method and device of kitchen air conditioner, controller and electric appliance system | |
| CN116294151A (en) | Air conditioner temperature adjusting method, system, equipment and medium | |
| CN108489032A (en) | air conditioning system control method and device | |
| CN112013519A (en) | Air conditioning equipment, automatic control method thereof and terminal control equipment | |
| CN114608172A (en) | Method and device for controlling air conditioner, air conditioner and storage medium | |
| CN111442512A (en) | Intelligent air environment adjusting method and environment adjusting system |
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 |