CN116659047A - Office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition - Google Patents
Office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition Download PDFInfo
- Publication number
- CN116659047A CN116659047A CN202310506276.6A CN202310506276A CN116659047A CN 116659047 A CN116659047 A CN 116659047A CN 202310506276 A CN202310506276 A CN 202310506276A CN 116659047 A CN116659047 A CN 116659047A
- Authority
- CN
- China
- Prior art keywords
- user
- numbered
- gesture
- determining
- coordinates
- 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 30
- 238000005265 energy consumption Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 50
- 210000003423 ankle Anatomy 0.000 claims description 12
- 210000003127 knee Anatomy 0.000 claims description 12
- 238000004378 air conditioning Methods 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000005096 rolling process Methods 0.000 claims description 9
- 210000004243 sweat Anatomy 0.000 claims description 9
- 238000010792 warming Methods 0.000 claims description 9
- 239000000498 cooling water Substances 0.000 claims description 6
- 238000006748 scratching Methods 0.000 claims description 6
- 230000002393 scratching effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000005855 radiation Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000004060 metabolic process Effects 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims description 2
- 238000005452 bending Methods 0.000 claims 1
- 229920006395 saturated elastomer Polymers 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 238000004134 energy conservation Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 5
- 238000010438 heat treatment Methods 0.000 description 5
- 230000001105 regulatory effect Effects 0.000 description 5
- 238000001816 cooling Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- 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
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
- F24F11/74—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity
-
- 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
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- F24F2120/14—Activity of occupants
-
- 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)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Fluid Mechanics (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The application relates to an office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition, which constructs a user comfort preference model based on a user thermal comfort feedback result, when the user thermal comfort is not ideal through gesture recognition, the user thermal comfort is transmitted to the preference model, the model is optimized by taking the three of high thermal comfort of the user, high working efficiency and low system energy consumption as targets, and the air conditioner parameters are adjusted, so that energy conservation and environmental protection are simultaneously met as much as possible; the user can adjust according to self thermal comfort impression, and feedback is carried out by means of gesture recognition, so that the thermal comfort of the human body is adjusted, and the omnibearing comfort of the body is achieved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition.
Background
At present, the air conditioner is used as a main tool for adjusting heat comfort at present, and plays an irreplaceable role in daily life of people. However, the existing air conditioner parameter regulation mode cannot fully meet the use requirement of users, because most of the existing air conditioner parameter regulation needs to be regulated by people, when people concentrate on doing something, the existing air conditioner parameter regulation mode obviously does not have the condition of manual regulation, and the existing air conditioner parameter regulation mode is required to be regulated automatically, so that the existing air conditioner parameter regulation mode becomes an important problem of current research. Especially for office users, in the process of office work, because of high concentration, even if thermal discomfort occurs, the users can not pay attention to, and the users can not actively adjust the temperature to improve the thermal environment; in addition, the user hopes that the air conditioner can automatically regulate and control the air supply parameters when the user is in a fatigue state so as to provide the working efficiency of the user; therefore, they want the air conditioner to recognize its behavior characteristics to adjust parameters to improve the user's thermal comfort, work efficiency. The existing thermal comfort detection methods have three types, namely: questionnaires, environmental monitoring, and physiological detection methods, however, the above methods do not provide a personalized thermal comfort environment for the user.
Disclosure of Invention
In order to overcome at least one defect in the prior art, the application provides an office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition.
In a first aspect, an office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition is provided, including:
shooting a user to obtain a user image;
determining coordinates of all key points in the user image according to the user image;
determining the confidence level of the user image according to the coordinates of all the key points;
determining whether the user image belongs to the human body image according to the confidence level;
if the user image belongs to the human body image, determining the gesture of the user according to the coordinates of all the key points;
determining a thermal comfort feedback result of the user according to the gesture of the user;
constructing a user comfort preference model based on a user thermal comfort feedback result;
and solving the user comfort preference model to obtain the air conditioner adjusting parameters.
In one embodiment, determining coordinates of all keypoints in the user image from the user image comprises:
inputting the user image into the tflite model to obtain initial coordinates of all key points and offset of the initial coordinates relative to real coordinates;
and calculating the real coordinates of all the key points according to the initial coordinates and the offset, namely, the coordinates of all the key points in the user image.
In one embodiment, determining the confidence level of the user image based on the coordinates of all keypoints includes:
determining the confidence coefficient of each key point according to the coordinates of each key point;
and solving the mean value of the confidence degrees of all the key points to serve as the confidence degree of the user image.
In one embodiment, determining whether the user image belongs to a human body image based on the confidence level includes:
if the confidence is greater than the screening threshold, the user image belongs to the human body image, otherwise, the user image does not belong to the human body image.
In one embodiment, determining the pose of the user from the coordinates of all keypoints includes:
determining vectors among different key points according to the coordinates of all the key points; all key points include: nose, left eye, right eye, left ear, right ear, left shoulder, right shoulder, left elbow, right elbow, left hand, right hand, left hip, right hip, left knee, right knee, left ankle, right ankle;
determining the gesture of the user according to the vectors among different key points; the user's gestures include rolling sleeves, grabbing heads, unwinding clothing, fanning hands, wiping sweat, shaking T-shirts, holding hands, crossing arms, scratching the neck with hands, and warming hands.
In one embodiment, determining the gesture of the user from the vector between the different keypoints comprises:
all key points are numbered: nose, numbered 0; the left eye, numbered 1; the right eye, numbered 2; the left ear is numbered 3; the right ear is numbered 4; the left shoulder is numbered 5; the right shoulder is numbered 6; left elbow, number 7; the right elbow is numbered 8; left hand, number 9; right hand, number 10; a left hip, numbered 11; a right hip, numbered 12; a left knee, numbered 13; a right knee, numbered 14; the left ankle is numbered 15; the right ankle, numbered 16;
if the gesture of the user is sleeve rolling, the following formula is satisfied:
wherein ,vectors representing the left elbow numbered 7 to the left hand numbered 9, +.>A vector representing the right elbow numbered 8 to the right hand numbered 10, θ representing the angle between the two vectors;
if the gesture of the user is the head grabbing, the following formula is satisfied:
wherein ,vectors representing the left shoulder numbered 5 to the left elbow numbered 7, < >>Vector representing the left hand numbered 9 to the left elbow numbered 7, < >>Vectors representing the right shoulder numbered 6 to the right elbow numbered 8, +.>Vectors representing the right hand numbered 10 to the right elbow numbered 8, +.>Vectors representing the right elbow numbered 8 to the right hand numbered 10, +.>Vectors representing the right hip numbered 12 to the right shoulder numbered 6, ++>A vector representing the left hip numbered 11 to the left shoulder numbered 5;
if the gesture of the user is to unfasten the clothing, the following formula is satisfied:
if the gesture of the user is a fan, the following formula is satisfied:
if the gesture of the user is sweat wiping, the following formula is satisfied:
if the gesture of the user is to shake the T-shirt, the following formula is satisfied:
if the gesture of the user is hand holding or arm crossing, the following formula is satisfied:
wherein ,vectors representing the right shoulder numbered 6 to the left shoulder numbered 5, < >>A vector representing the left shoulder numbered 5 to the right shoulder numbered 6;
if the gesture of the user is to scratch the neck, the following formula is satisfied:
or
if the gesture of the user is hand warming, the following formula is satisfied:
wherein ,a vector representing the right shoulder numbered 6 to the right hand numbered 10,
a vector representing the left shoulder numbered 5 to the left hand numbered 9;
if the gesture of the user is hand rubbing, the following formula is satisfied:
in one embodiment, determining a thermal comfort feedback result for a user based on a gesture of the user includes:
if the gesture of the user is sleeve rolling or head grabbing, the thermal comfort feedback result of the user is heat;
if the gesture of the user is to unfasten clothes, fan hands, sweat or shake the T-shirt, the thermal comfort feedback result of the user is very hot;
if the gesture of the user is hand holding, arm crossing or neck scratching, the thermal comfort feedback result of the user is cold;
if the gesture of the user is hand warming or hand rubbing, the thermal comfort feedback result of the user is very cold.
In one embodiment, the user comfort preference model is:
wherein wr denotes a work efficiency index value, PMV denotes a thermal comfort index value, P t Indicating the energy consumption index value of the cold machine, Q chi Represents the actual refrigerating capacity, COP represents the rated energy efficiency ratio of the chiller, a 0 ~a 17 All are constant coefficients, r tci Represents the temperature deviation rate of cooling water, r q Represents the deviation rate of refrigerating capacity, r teo Represents the temperature deviation rate of chilled water, r ew Represents the deviation rate of cooling water flow, r te Represents the deviation rate of the water temperature of cooling water in and out, r tc Represents the deviation rate of the water temperature of the chilled water, M represents the metabolism rate and P a Represents the partial pressure of water vapor, f cl Represents the ratio of the body surface area of the human body when wearing and the body surface area of the human body when bare, t cl Representing the surface temperature of the clothing, t r Average radiation temperature, h c Represents the surface heat transfer coefficient, t a The temperature of the air conditioner parameter is represented, W represents the external power consumption heat, I cl Representing the thermal resistance of the garment, t r Mean radiation temperature, v ar Represents the air flow rate, P s Represents saturated water vapor pressure, w? max Represents the maximum value of the work efficiency index value, H represents the relative humidity, t a0 The original air conditioning parameter temperature V is represented as the air conditioning parameter wind speed.
In a second aspect, an office environment air conditioner air supply parameter adjusting device based on user behavior feature recognition is provided, including:
the user image acquisition module is used for shooting a user and acquiring a user image;
the key point coordinate determining module is used for determining the coordinates of all key points in the image according to the user image;
the confidence coefficient determining module is used for determining the confidence coefficient of the user image according to the coordinates of all the key points;
the human body image determining module is used for determining whether the user image belongs to the human body image according to the confidence level;
the user gesture determining module is used for determining the gesture of the user according to the coordinates of all the key points if the user image belongs to the human body image;
the thermal comfort feedback determining module is used for determining a thermal comfort feedback result of the user according to the gesture of the user;
the model building module is used for building a user comfort preference model based on a user thermal comfort feedback result;
and the model solving module is used for solving the user comfort preference model to obtain the air conditioner parameter temperature.
In a third aspect, a computer readable storage medium is provided, where a computer program is stored, and when the computer program is executed by a processor, the method for adjusting an air supply parameter of an air conditioner in an office environment based on user behavior feature recognition is implemented.
Compared with the prior art, the application has the following beneficial effects:
1. the application has convenient collection operation for the thermal comfort feedback of the user, does not need to wear a sensor for thermal comfort feedback, and only needs to receive the thermal comfort feedback condition of the user by real-time monitoring and posture estimation of the collected image.
2. According to the user comfort preference model, when the user thermal comfort is not ideal through gesture recognition, the user thermal comfort is transmitted to the preference model, the model is optimized by taking three of high thermal comfort of the user, high working efficiency and low system energy consumption as targets, and air conditioning parameters such as wind speed, temperature and the like are regulated, so that energy conservation and environmental protection are simultaneously met as much as possible.
3. The user can adjust according to self thermal comfort impression, and feedback is carried out by means of gesture recognition, so that the thermal comfort of the human body is adjusted, and the omnibearing comfort of the body is achieved.
Drawings
The application may be better understood by reference to the following description taken in conjunction with the accompanying drawings, which are incorporated in and form a part of this specification, together with the following detailed description. In the drawings:
FIG. 1 shows a flow diagram of an office environment air conditioning supply parameter adjustment method based on user behavior feature recognition according to an embodiment of the present application;
FIG. 2 shows a schematic diagram of the respective keypoint numbering;
fig. 3 is a block diagram showing a configuration of an office environment air conditioner air supply parameter adjusting device based on user behavior feature recognition according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application will be described hereinafter with reference to the accompanying drawings. In the interest of clarity and conciseness, not all features of an actual embodiment are described in the specification. It will of course be appreciated that in the development of any such actual embodiment, numerous implementation-specific decisions may be made to achieve the developers' specific goals, and that these decisions may vary from one implementation to another.
It should be noted here that, in order to avoid obscuring the present application due to unnecessary details, only the device structures closely related to the solution according to the present application are shown in the drawings, and other details not greatly related to the present application are omitted.
It is to be understood that the application is not limited to the described embodiments, as a result of the following description with reference to the drawings. In this context, embodiments may be combined with each other, features replaced or borrowed between different embodiments, one or more features omitted in one embodiment, where possible.
The application provides an office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition, which predicts 16 skeleton key points of a human body and defines 11 conventional gestures according to tflite algorithm, and carries out thermal comfort judgment through human body detection and gesture recognition; based on the above, based on the air conditioner air supply parameter adjustment of gesture control, the user is utilized to detect and verify the rationality of the method, and the corresponding data of the air supply parameter to be adjusted is output as a result.
The embodiment of the application provides an office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition, and fig. 1 shows a flow chart of the office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition according to the embodiment of the application, wherein the method comprises the following steps:
step S1, shooting a user to obtain a user image; here, a camera may be used to capture a user, obtain an image, and pre-process the obtained image to obtain a user image.
And S2, determining coordinates of all key points in the user image according to the user image.
Specifically, inputting a user image into a tflite model to obtain initial coordinates of all key points and offset of the initial coordinates relative to real coordinates; and calculating the real coordinates of all the key points according to the initial coordinates and the offset, namely, the coordinates of all the key points in the user image.
And S3, determining the confidence level of the user image according to the coordinates of all the key points.
Specifically, determining the confidence level of the key points through a sigmoid function according to the coordinates of each key point; and solving the mean value of the confidence degrees of all the key points to serve as the confidence degree of the user image.
Step S4, determining whether the user image belongs to the human body image according to the confidence coefficient; specifically, if the confidence is greater than the screening threshold, the user image belongs to the human body image, otherwise, the user image does not belong to the human body image. Here, the screening threshold may be set to 0.5.
Step S5, if the user image belongs to the human body image, determining the gesture of the user according to the coordinates of all the key points;
step S6, determining a thermal comfort feedback result of the user according to the gesture of the user;
s7, constructing a user comfort preference model based on a user thermal comfort feedback result;
and S8, solving a user comfort preference model to obtain air conditioner adjusting parameters. The genetic algorithm may be used to solve the user comfort preference model, or other solving methods may be used, which are not particularly limited herein.
In the embodiment, a user comfort preference model is built based on a user thermal comfort feedback result, when the user thermal comfort is not ideal through gesture recognition, the user thermal comfort is transmitted to the preference model, the model is optimized by taking three of high thermal comfort of the user, high working efficiency and low system energy consumption as targets, air conditioning parameters are regulated, and energy conservation and environmental protection are simultaneously met as much as possible; the user can adjust according to self thermal comfort impression, and feedback is carried out by means of gesture recognition, so that the thermal comfort of the human body is adjusted, and the omnibearing comfort of the body is achieved.
In one embodiment, if the user image belongs to the human body image in step S5, determining the gesture of the user according to the coordinates of all the key points includes:
determining vectors among different key points according to the coordinates of all the key points; all key points include: nose, left eye, right eye, left ear, right ear, left shoulder, right shoulder, left elbow, right elbow, left hand, right hand, left hip, right hip, left knee, right knee, left ankle, right ankle;
determining the gesture of the user according to the vectors among different key points; the user's gestures include rolling sleeves, grabbing heads, unwinding clothing, fanning hands, wiping sweat, shaking T-shirts, holding hands, crossing arms, scratching the neck with hands, and warming hands. Here, all keypoints are numbered: nose, numbered 0; the left eye, numbered 1; the right eye, numbered 2; the left ear is numbered 3; the right ear is numbered 4; the left shoulder is numbered 5; the right shoulder is numbered 6; left elbow, number 7; the right elbow is numbered 8; left hand, number 9; right hand, number 10; a left hip, numbered 11; a right hip, numbered 12; a left knee, numbered 13; a right knee, numbered 14; the left ankle is numbered 15; the right ankle, numbered 16. Fig. 2 shows a schematic diagram of the respective keypoint numbers.
If the gesture of the user is sleeve rolling, the following formula is satisfied:
wherein ,vectors representing the left elbow numbered 7 to the left hand numbered 9, +.>A vector representing the right elbow numbered 8 to the right hand numbered 10, θ representing the angle between the two vectors;
if the gesture of the user is the head grabbing, the following formula is satisfied:
wherein ,vectors representing the left shoulder numbered 5 to the left elbow numbered 7, < >>Vector representing the left hand numbered 9 to the left elbow numbered 7, < >>Vectors representing the right shoulder numbered 6 to the right elbow numbered 8, +.>Vectors representing the right hand numbered 10 to the right elbow numbered 8, +.>Vectors representing the right elbow numbered 8 to the right hand numbered 10, +.>Vectors representing the right hip numbered 12 to the right shoulder numbered 6, ++>A vector representing the left hip numbered 11 to the left shoulder numbered 5;
if the gesture of the user is to unfasten the clothing, the following formula is satisfied:
if the gesture of the user is a fan, the following formula is satisfied:
if the gesture of the user is sweat wiping, the following formula is satisfied:
if the gesture of the user is to shake the T-shirt, the following formula is satisfied:
if the gesture of the user is hand holding or arm crossing, the following formula is satisfied:
wherein ,vectors representing the right shoulder numbered 6 to the left shoulder numbered 5, < >>A vector representing the left shoulder numbered 5 to the right shoulder numbered 6;
if the gesture of the user is to scratch the neck, the following formula is satisfied:
or
if the gesture of the user is hand warming, the following formula is satisfied:
wherein ,a vector representing the right shoulder numbered 6 to the right hand numbered 10,
a vector representing the left shoulder numbered 5 to the left hand numbered 9;
if the gesture of the user is hand rubbing, the following formula is satisfied:
in one embodiment, step S6, determining a thermal comfort feedback result of the user according to the gesture of the user, includes:
if the gesture of the user is sleeve rolling or head grabbing, the thermal comfort feedback result of the user is heat;
if the gesture of the user is to unfasten clothes, fan hands, sweat or shake the T-shirt, the thermal comfort feedback result of the user is very hot;
if the gesture of the user is hand holding, arm crossing or neck scratching, the thermal comfort feedback result of the user is cold;
if the gesture of the user is hand warming or hand rubbing, the thermal comfort feedback result of the user is very cold.
In one embodiment, the user comfort preference model is:
TABLE 1 user comfort preference model variable description
/>
Here, the length of the cooling and heating days and the specific date of the building air conditioning system have a great influence on the peak value of the cooling and heating loads and the cumulative amount of the cooling and heating loads in the building air conditioning season. The typical climate zone is defined to represent the refrigerating and heating season of the city according to the outdoor dry bulb temperature, and the specific rules are as follows: (1) The start-stop date with a daily average temperature higher than 25 ℃ is defined as a refrigerating season; (2) A start-stop date with a daily average temperature of less than 5 ℃ is defined as a heating season; and (3) the rest time is transitional season.
In this embodiment, the user comfort preference model is constructed based on the user's thermal comfort feedback result, and when the user's thermal comfort feedback result is hot and very hot, the adjustment temperature should be lower than the original temperature, and when the thermal feedback is cold and very cold, the adjustment temperature should be higher than the original temperature.
With the same inventive concept as the method for adjusting the air supply parameters of the office environment air conditioner based on the user behavior feature recognition, the embodiment also provides a corresponding device for adjusting the air supply parameters of the office environment air conditioner based on the user behavior feature recognition, and fig. 3 shows a block diagram of the device for adjusting the air supply parameters of the office environment air conditioner based on the user behavior feature recognition according to an embodiment of the present application, including:
a user image acquisition module 31, configured to capture a user and acquire a user image;
a key point coordinate determining module 32, configured to determine coordinates of all key points in the image according to the user image;
a confidence determining module 33, configured to determine a confidence level of the user image according to coordinates of all the key points;
a human body image determining module 34, configured to determine whether the user image belongs to the human body image according to the confidence level;
a user gesture determining module 35, configured to determine a gesture of the user according to coordinates of all the key points if the user image belongs to the human body image;
a thermal comfort feedback determination module 36 for determining a thermal comfort feedback result of the user based on the gesture of the user;
a model construction module 37 for constructing a user comfort preference model based on the user's thermal comfort feedback result;
the model solving module 38 is configured to solve the user comfort preference model to obtain the air conditioning parameter temperature.
In this embodiment, the specific implementation function of each module is identical to the specific implementation manner of the method embodiment, and the technical effects are the same, which is not described herein again.
The embodiment of the application provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for adjusting the air supply parameters of an air conditioner in an office environment based on user behavior feature identification is realized.
In summary, the office environment air conditioner air supply parameter adjusting method and device based on user behavior feature recognition have the following technical effects:
1. the application has convenient collection operation for the thermal comfort feedback of the user, does not need to wear a sensor for thermal comfort feedback, and only needs to receive the thermal comfort feedback condition of the user by real-time monitoring and posture estimation of the collected image.
2. According to the user comfort preference model, when the user thermal comfort is not ideal through gesture recognition, the user thermal comfort is transmitted to the preference model, the model is optimized by taking three of high thermal comfort of the user, high working efficiency and low system energy consumption as targets, and air conditioning parameters such as wind speed, temperature and the like are regulated, so that energy conservation and environmental protection are simultaneously met as much as possible.
3. The user can adjust according to self thermal comfort impression, and feedback is carried out by means of gesture recognition, so that the thermal comfort of the human body is adjusted, and the omnibearing comfort of the body is achieved.
The above description is merely illustrative of various embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the scope of the present application, and the application is intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition is characterized by comprising the following steps:
shooting a user to obtain a user image;
determining coordinates of all key points in the user image according to the user image;
determining the confidence level of the user image according to the coordinates of all the key points;
determining whether the user image belongs to a human body image according to the confidence degree;
if the user image belongs to a human body image, determining the gesture of the user according to the coordinates of all the key points;
determining a thermal comfort feedback result of the user according to the gesture of the user;
constructing a user comfort preference model based on the thermal comfort feedback result of the user;
and solving the user comfort preference model to obtain the air conditioner adjusting parameters.
2. The method of claim 1, wherein determining coordinates of all keypoints in the user image from the user image comprises:
inputting the user image into a tflite model to obtain initial coordinates of all key points and offset of the initial coordinates relative to real coordinates;
and calculating the real coordinates of all key points according to the initial coordinates and the offset, namely the coordinates of all key points in the user image.
3. The method of claim 1, wherein determining the confidence level of the user image based on the coordinates of all keypoints comprises:
determining the confidence coefficient of each key point according to the coordinates of the key point;
and solving the mean value of the confidence degrees of all the key points to serve as the confidence degree of the user image.
4. The method of claim 1, wherein determining whether the user image belongs to a human body image based on the confidence level comprises:
if the confidence coefficient is larger than the screening threshold value, the user image belongs to the human body image, otherwise, the user image does not belong to the human body image.
5. The method of claim 1, wherein determining the pose of the user from the coordinates of all keypoints comprises:
determining vectors among different key points according to the coordinates of all the key points; all the key points comprise: nose, left eye, right eye, left ear, right ear, left shoulder, right shoulder, left elbow, right elbow, left hand, right hand, left hip, right hip, left knee, right knee, left ankle, right ankle;
determining the gesture of the user according to the vectors among the different key points; the user's gestures include rolling sleeves, grabbing heads, unrolling clothing, fanning hands, wiping sweat, shaking T-shirts, holding hands, crossing arms, scratching the neck with hands, warming hands.
6. The method of claim 5, wherein determining the gesture of the user from the vector between the different keypoints comprises:
numbering all key points: nose, numbered 0; the left eye, numbered 1; the right eye, numbered 2; the left ear is numbered 3; the right ear is numbered 4; the left shoulder is numbered 5; the right shoulder is numbered 6; left elbow, number 7; the right elbow is numbered 8; left hand, number 9; right hand, number 10; a left hip, numbered 11; a right hip, numbered 12; a left knee, numbered 13; a right knee, numbered 14; the left ankle is numbered 15; the right ankle, numbered 16;
if the gesture of the user is sleeve rolling, the following formula is satisfied:
wherein ,vectors representing the left elbow numbered 7 to the left hand numbered 9, +.>A vector representing the right elbow numbered 8 to the right hand numbered 10, θ representing the angle between the two vectors;
if the gesture of the user is the head grabbing, the following formula is satisfied:
wherein ,vectors representing the left shoulder numbered 5 to the left elbow numbered 7, < >>Vector representing the left hand numbered 9 to the left elbow numbered 7, < >>Vectors representing the right shoulder numbered 6 to the right elbow numbered 8, +.>Vectors representing the right hand numbered 10 to the right elbow numbered 8, +.>Vectors representing the right elbow numbered 8 to the right hand numbered 10, +.>Vectors representing the right hip numbered 12 to the right shoulder numbered 6, ++>A vector representing the left hip numbered 11 to the left shoulder numbered 5;
if the gesture of the user is to unfasten clothes, the following formula is satisfied:
if the gesture of the user is a fan, the following formula is satisfied:
if the gesture of the user is sweat wiping, the following formula is satisfied:
if the gesture of the user is to shake the T-shirt, the following formula is satisfied:
if the gesture of the user is hand holding or arm crossing, the following formula is satisfied:
wherein ,vectors representing the right shoulder numbered 6 to the left shoulder numbered 5, < >>A vector representing the left shoulder numbered 5 to the right shoulder numbered 6;
if the gesture of the user is hand bending neck, the following formula is satisfied:
or
if the gesture of the user is hand warming, the following formula is satisfied:
wherein ,vectors representing the right shoulder numbered 6 to the right hand numbered 10, +.>A vector representing the left shoulder numbered 5 to the left hand numbered 9;
if the gesture of the user is hand rubbing, the following formula is satisfied:
7. the method of claim 1, wherein determining the thermal comfort feedback result of the user based on the user's gesture comprises:
if the gesture of the user is sleeve rolling or head grabbing, the thermal comfort feedback result of the user is heat;
if the user's posture is to unfasten clothes, fan hands, sweat or shake a T-shirt, the user's thermal comfort feedback result is very hot;
if the gesture of the user is hand holding, arm crossing or neck scratching, the thermal comfort feedback result of the user is cold;
if the gesture of the user is hand warming or hand rubbing, the thermal comfort feedback result of the user is very cold.
8. The method of claim 1, wherein the user comfort preference model is:
wherein wr denotes a work efficiency index value, PMV denotes a thermal comfort index value, P t Indicating the energy consumption index value of the cold machine, Q chi Represents the actual refrigerating capacity, COP represents the rated energy efficiency ratio of the chiller, a 0 ~a 17 All are constant coefficients, r tci Represents the temperature deviation rate of cooling water, r q Represents the deviation rate of refrigerating capacity, r teo Represents the temperature deviation rate of chilled water, r ew Represents the deviation rate of cooling water flow, r te Represents the deviation rate of the water temperature of cooling water in and out, r tc Represents the deviation rate of the water temperature of the chilled water, M represents the metabolism rate and P a Represents the partial pressure of water vapor, f cl Represents the ratio of the body surface area of the human body when wearing and the body surface area of the human body when bare, t cl Representing the surface temperature of the clothing, t r Average radiation temperature, h c Represents the surface heat transfer coefficient, t a The temperature of the air conditioner parameter is represented, W represents the external power consumption heat, I cl Representing the thermal resistance of the garment, t r Mean radiation temperature, v ar Represents the air flow rate, P s Represents saturated steam pressure, wr max Represents the maximum value of the work efficiency index value, H represents the relative humidity, t a0 The original air conditioning parameter temperature V is represented as the air conditioning parameter wind speed.
9. An office environment air conditioner air supply parameter adjusting device based on user behavior feature recognition is characterized by comprising:
the user image acquisition module is used for shooting a user and acquiring a user image;
the key point coordinate determining module is used for determining the coordinates of all key points in the image according to the user image;
the confidence coefficient determining module is used for determining the confidence coefficient of the user image according to the coordinates of all the key points;
the human body image determining module is used for determining whether the user image belongs to a human body image according to the confidence coefficient;
the user gesture determining module is used for determining the gesture of the user according to the coordinates of all the key points if the user image belongs to a human body image;
the thermal comfort feedback determining module is used for determining a thermal comfort feedback result of the user according to the gesture of the user;
the model building module is used for building a user comfort preference model based on the thermal comfort feedback result of the user;
and the model solving module is used for solving the user comfort preference model to obtain the air conditioner parameter temperature.
10. A computer readable storage medium, wherein the computer readable storage medium stores a computer program, which when executed by a processor, implements the office environment air conditioner air supply parameter adjustment method based on user behavior feature recognition according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310506276.6A CN116659047A (en) | 2023-05-06 | 2023-05-06 | Office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310506276.6A CN116659047A (en) | 2023-05-06 | 2023-05-06 | Office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116659047A true CN116659047A (en) | 2023-08-29 |
Family
ID=87718070
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310506276.6A Pending CN116659047A (en) | 2023-05-06 | 2023-05-06 | Office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116659047A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117255451A (en) * | 2023-10-24 | 2023-12-19 | 快住智能科技(苏州)有限公司 | Intelligent living guest control method and system for hotel guest room management |
-
2023
- 2023-05-06 CN CN202310506276.6A patent/CN116659047A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117255451A (en) * | 2023-10-24 | 2023-12-19 | 快住智能科技(苏州)有限公司 | Intelligent living guest control method and system for hotel guest room management |
CN117255451B (en) * | 2023-10-24 | 2024-05-03 | 快住智能科技(苏州)有限公司 | Intelligent living guest control method and system for hotel guest room management |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111720963B (en) | Air conditioning method and device in sleep environment and electronic equipment | |
CN213501729U (en) | Thermal management system for a motor vehicle passenger compartment | |
JP6333486B2 (en) | Device control apparatus and device control method | |
CN109405232B (en) | Based on infrared temperature sensing and the dynamic air-conditioning Automatic adjustment method of human body | |
CN104896663B (en) | Method of adjustment, adjustment system and the air conditioner of air conditioner air supply mode | |
CN116659047A (en) | Office environment air conditioner air supply parameter adjusting method based on user behavior feature recognition | |
CN113339950A (en) | Air conditioner control system | |
CN106642513A (en) | Intelligent energy-saving environment regulation and control system and method | |
CN113339952A (en) | Air conditioning system | |
CN105841317B (en) | Intelligent air condition bracelet and air conditioning control method | |
CN109442687A (en) | Control method and device of air conditioner, storage medium and air conditioner | |
CN108361928B (en) | Air conditioner control method and system based on image recognition | |
JP6668010B2 (en) | Air conditioning control device, air conditioning control method, and air conditioning control program | |
CN110030699A (en) | Air conditioning equipment control method, air conditioner and storage medium | |
CN112032970B (en) | Intelligent air conditioner regulation and control method based on body surface temperature monitoring | |
CN113418286B (en) | Self-adaptive thermal sensing robot and air conditioner temperature adjusting method | |
CN112303861A (en) | Air conditioner temperature adjusting method and system based on human body thermal adaptability behavior | |
CN106440209A (en) | Control method and control device for movable air conditioner and movable air conditioner | |
CN205536386U (en) | A control terminal and system for adjusting air conditioner temperature | |
CN106765986A (en) | Air-conditioning and its air-out control method | |
Choi et al. | Seasonal effects of thermal comfort control considering real-time clothing insulation with vision-based model | |
CN113303624A (en) | Temperature control mattress control system and method based on sleep posture detection | |
Zhang et al. | Strategy-proof thermal comfort voting in buildings | |
CN115682368A (en) | Non-contact indoor thermal environment control system and method based on reinforcement learning | |
CN208941088U (en) | Heating garment |
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 |