Air conditioner control method and device, electronic equipment, medium and computer program product
By establishing a comfort control model in the air conditioning system, obtaining environmental parameters and user characteristics, and training the model to determine the air conditioning control parameters, the problem of the inflexible adjustment of the air conditioning system is solved, and personalized comfort control and self-optimization are realized.
Patent Information
- Application Number
- CN202411676544.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2026-05-22
AI Technical Summary
Existing air conditioning systems cannot be flexibly adjusted according to different environmental conditions and user needs, cannot meet personalized comfort requirements, lack self-learning and updating capabilities, and cannot respond to users' dynamic needs in real time.
By establishing a comfort control model, environmental parameters such as temperature and wind speed of the space where the air conditioner is located are obtained, the comfort control model is trained to determine the air conditioner control parameters, and personalized control is carried out in combination with user characteristics, which has the ability to learn and update itself.
It realizes intelligent control of the air conditioning system, which can flexibly adjust according to different users and environmental conditions, improve user comfort, provide personalized services, and has self-optimization capabilities.
Smart Images

Figure CN122072107A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of intelligent control, and specifically relates to an air conditioning control method, device, electronic equipment, medium and computer program product. Background Technology
[0002] Currently, air conditioning systems can provide some comfort adjustment functions, but there are still some problems: current comfort control technology is usually based on fixed parameter settings and cannot be flexibly adjusted according to different environmental conditions. This single comfort adjustment method cannot adapt to different environmental conditions. Summary of the Invention
[0003] This application provides an air conditioning control method, apparatus, electronic device, medium, and computer program product.
[0004] This application provides an air conditioning control method, the method comprising:
[0005] The first environmental parameter is obtained at each sampling point in the space where the air conditioner is located, and the first parameter in the space where the air conditioner is located is determined based on the first environmental parameter; the first environmental parameter includes temperature and wind speed; the first environmental parameter represents the environmental parameter obtained when the air conditioner is running under any control parameter; the first parameter includes the wind feel index and / or temperature range.
[0006] Based on the first environmental parameters and the preset first environmental parameter standard, a comfort control model is trained so that the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters; the first environmental parameter standard includes one or more of the following: the airflow index standard and the temperature range standard.
[0007] Obtain the current environmental parameters, and then use the trained comfort control model to obtain the air conditioning control parameters corresponding to the current environmental parameters.
[0008] In some embodiments, before training the comfort control model based on the first environmental parameters and a preset first environmental parameter standard, the method further includes: obtaining a second environmental parameter standard corresponding to different user characteristics based on the first environmental parameter standard; the user characteristics include one or more of the following: user age group, user gender, number of users, and user's current scenario; training the comfort control model based on the first environmental parameters and the preset first environmental parameter standard includes: training the comfort control model based on the first environmental parameters and the second environmental parameter standard, wherein the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters and user characteristics.
[0009] In some embodiments, before obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model, the method further includes: identifying user characteristics in the current environment; determining target input parameters based on the user characteristics in the current environment and the current environmental parameters; obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model includes: obtaining the air conditioning control parameters corresponding to the target input parameters through the trained comfort control model.
[0010] It can be seen that by using the second environmental parameter standard corresponding to different user characteristics as training data, the trained comfort control model can obtain air conditioning control parameters that meet the comfort of different user characteristics based on different user characteristics, thereby achieving differentiated control of comfort for different groups of people and meeting the needs of different groups for air conditioning comfort.
[0011] In some embodiments, after obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model, the method further includes: running the air conditioner based on the air conditioning control parameters corresponding to the current environmental parameters, and obtaining the user-modified air conditioning control parameters; adjusting the parameters of the comfort control model based on the modified air conditioning control parameters and the air conditioning control parameters obtained by the comfort control model under the current environmental parameters, so that the difference between the adjusted comfort control model and the modified air conditioning control parameters under the current environmental parameters is less than a threshold.
[0012] It can be seen that after the user modifies the air conditioning control parameters, the comfort control model can also modify its own model parameters based on the modified air conditioning control parameters, thereby enabling the comfort control model to actively learn and optimize according to the needs of different users, so as to obtain air conditioning control parameters that meet the current user's comfort requirements.
[0013] In some embodiments, obtaining the first environmental parameters of each sampling point in the space where the air conditioner is located includes: obtaining the first environmental parameters of each sampling point in each sampling plane in the space where the air conditioner is located; the sampling plane represents a plane parallel to the wall where the air conditioner is located.
[0014] In some embodiments, obtaining the first environmental parameter of each sampling point in the space where the air conditioner is located, and determining the first parameter in the space where the air conditioner is located based on the first environmental parameter, includes: obtaining a first preset number of second environmental parameters sampled at each sampling point within a first preset time range; the second environmental parameter represents the environmental parameter obtained when the air conditioner is running under any control parameter; the second environmental parameter includes temperature and wind speed; determining the first environmental parameter of each sampling point based on multiple second environmental parameters; and determining the airflow index in the space where the air conditioner is located based on the first environmental parameter.
[0015] It can be seen that by sampling the second environmental parameters within the first preset time range, the airflow index in the space where the air conditioner is located can be determined. Training the comfort control model with the airflow index is beneficial to improving the accuracy of the comfort control model in controlling the air conditioner control parameters.
[0016] In some embodiments, obtaining the first environmental parameter of each sampling point in the space where the air conditioner is located, and determining the first parameter in the space where the air conditioner is located based on the first environmental parameter, includes: obtaining a second preset number of third environmental parameters sampled at each sampling point within a second preset time period; the third environmental parameter represents the environmental parameter obtained when the air conditioner is operating under any control parameter; the third environmental parameter includes temperature; determining the first environmental parameter of each sampling point based on multiple third environmental parameters; and determining the temperature range in the space where the air conditioner is located based on the first environmental parameter.
[0017] It can be seen that by sampling the third environmental parameter within the second preset time range, the temperature range within the space where the air conditioner is located can be determined. Training the comfort control model through the temperature range is beneficial to improving the accuracy of the comfort control model in controlling the air conditioner control parameters.
[0018] This application embodiment also provides an air conditioning control device, the device comprising:
[0019] The acquisition module is used to acquire the first environmental parameters of each sampling point in the space where the air conditioner is located, and to determine the first parameters in the space where the air conditioner is located based on the first environmental parameters; the first environmental parameters include temperature and wind speed; the first environmental parameters represent the environmental parameters obtained by the air conditioner operating under any control parameters; the first parameters include the wind feel index and / or temperature range.
[0020] The training module is used to train a comfort control model based on the first environmental parameters and a preset first environmental parameter standard, so that the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters; the first environmental parameter standard includes one or more of the following: the wind feel index standard and the temperature range standard.
[0021] The control module is used to acquire the current environmental parameters and obtain the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model.
[0022] This application provides an electronic device, which includes a processor and a memory for storing computer programs capable of running on the processor; wherein,
[0023] The processor is used to run the computer program to perform any of the above-described air conditioning control methods.
[0024] This application provides a computer storage medium storing a computer program, which, when executed by a processor, implements any of the above-described air conditioning control methods.
[0025] This application provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described air conditioning control methods.
[0026] This application provides an air conditioning control method, device, electronic device, medium, and computer program product. By acquiring temperature and wind speed, determining the wind feel index and / or temperature range, and training a comfort control model based on the wind feel index and / or temperature range, the trained comfort control model can determine highly accurate air conditioning control parameters based on current environmental parameters. This allows the trained comfort control model to flexibly adjust the air conditioning control parameters according to different environmental parameters, making the obtained air conditioning control parameters more suitable for the current environment. Attached Figure Description
[0027] Figure 1 A flowchart of an air conditioning control method provided in an embodiment of this application;
[0028] Figure 2 A flowchart of a control method for a comfort control model provided in this application embodiment;
[0029] Figure 3 This is a schematic diagram of the structure of an air conditioning control device provided in an embodiment of this application;
[0030] Figure 4 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0031] With the development of technology, air conditioning systems have evolved from their initial function of temperature regulation to providing a more comfortable airflow experience. To achieve comfort adjustment, related technologies typically use fixed temperature and fan speed parameters to provide a comfortable environment. However, this single adjustment method cannot meet the personalized needs of different users, nor can it adapt to different environmental conditions. Although existing air conditioning systems can provide some comfort adjustment capabilities, some problems still exist:
[0032] First, current user needs analysis technologies are typically based on historical user behavior data, failing to respond to dynamic user needs in real time. Second, current comfort control technologies are usually based on fixed parameter settings, unable to flexibly adjust according to different environmental conditions and user requirements. Finally, current air conditioning systems generally lack self-learning and updating capabilities, unable to self-optimize based on actual user usage. Current air conditioning systems typically regulate the indoor environment through simple controls, neglecting the impact of other factors on human comfort, especially the different comfort needs of different groups (such as the elderly, youth, and children), making it difficult to meet personalized comfort requirements.
[0033] This application provides an air conditioning control method. By establishing a comfort control model, the model parameters can be optimized according to the needs of different groups of people, thereby realizing intelligent control of the air conditioner and improving user comfort.
[0034] The embodiments of this application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the embodiments provided herein are merely illustrative of the embodiments of this application and are not intended to limit the embodiments of this application. Furthermore, the embodiments provided below are some embodiments for implementing this application, and not all embodiments for implementing this application. Unless otherwise specified, the technical solutions described in the embodiments of this application can be implemented in any combination.
[0035] It should be noted that, in the embodiments of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a method or apparatus that includes a list of elements includes not only the elements expressly described, but also other elements not expressly listed, or elements inherent to implementing the method or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of other related elements in the method or apparatus that includes that element (e.g., steps in the method or units in the apparatus; for example, a unit in the apparatus may be a portion of circuitry, a portion of a processor, a portion of a program or software, etc.).
[0036] The air conditioning control method provided in this application includes a series of steps, but the air conditioning control method provided in this application is not limited to the steps described. Similarly, the air conditioning control device provided in this application includes a series of modules, but the device provided in this application is not limited to the modules explicitly described, but may also include modules that need to be set for obtaining relevant information or processing based on information.
[0037] This application provides an air conditioning control method, such as... Figure 1 As shown, Figure 1 A flowchart of an air conditioning control method is shown. Figure 1 The air conditioning control methods shown include:
[0038] Step 101: Obtain the first environmental parameters of each sampling point in the space where the air conditioner is located, and determine the first parameters in the space where the air conditioner is located based on the first environmental parameters; the first environmental parameters include temperature and wind speed; the first environmental parameters represent the environmental parameters obtained when the air conditioner is running under any control parameter; the first parameters include the wind feel index and / or temperature range.
[0039] This application embodiment enables intelligent control of air conditioning control parameters by incorporating a comfort control model into the air conditioning system, and adjusting the air conditioning control parameters through the comfort control model. In this embodiment, the comfort control model in the air conditioning system is first trained.
[0040] First, we acquire the initial environmental parameters such as temperature and wind speed at each of the multiple sampling points within the space where the air conditioner is located. Here, the space can be a laboratory setting. Within this three-dimensional laboratory setting, multiple sampling points can be deployed at preset intervals in both the horizontal and vertical dimensions. Each sampling point can consist of sampling devices such as a temperature sensor and an anemometer. To acquire more environmental parameters, different environmental parameter sampling devices can be deployed to sample humidity, wind direction, air quality, noise, etc., at each sampling point.
[0041] By sampling the primary environmental parameters at each sampling point, the draft index and / or temperature range within the air-conditioned space can be obtained. Alternatively, humidity, wind direction, air quality, and noise levels within the air-conditioned space can be obtained using environmental parameters such as humidity, wind direction, air quality, and noise. By using primary environmental parameters obtained from multiple sampling points, the average value and standard deviation of multiple primary environmental parameters within the space can be calculated. Based on the statistical analysis results, a comprehensive evaluation of the primary environmental parameters of the entire space can be performed to obtain the environmental parameters related to temperature, wind speed, humidity, wind direction, air quality, and noise within the space.
[0042] The airflow perception index is an indicator used to assess the discomfort experienced by the human body due to airflow. When the airflow perception index needs to be obtained from the first environmental parameter, it can be calculated based on formula (1) to obtain the airflow perception index DR within the space:
[0043] DR=(34-t a (v) a -0.05) 0.62 (0.37×v a ×T u +3.14) (1)
[0044] Here, DR represents the airflow discomfort index, which is the percentage of people dissatisfied with the airflow feel; when DR > 100%, DR is considered 100%. a This indicates the local average air temperature, expressed in degrees Celsius (°C). a This represents the local average air velocity, expressed in meters per second (m / s); when v a When <0.05m / s, take v a =0.05m / s; T u The local turbulence intensity (%) is expressed as the ratio of the standard deviation SD of the local air velocity to the local mean air velocity. u The result can be calculated using formula (2):
[0045]
[0046] The standard deviation SD of the local air velocity can be calculated using formula (3):
[0047]
[0048] In formula (3), n represents the number of air velocity samples recorded at the sampling points within a specified time; v ai This represents the local instantaneous air velocity at the sampling point during the i-th sampling within a specified time, expressed in meters per second (m / s).
[0049] Temperature range represents the maximum temperature variation within a specific range or process. It can be calculated by taking the temperature measured at each sampling point within a space and finding the difference between the highest and lowest temperatures measured at those points. Alternatively, the temperature can be obtained at a first moment, and a first average temperature can be calculated based on this. Then, at a second moment after the first moment, the temperature is taken at the same sampling point, and a second average temperature is calculated. Finally, the temperature range is determined based on both the first and second average temperatures.
[0050] It can be seen that both the wind feel index and temperature range are used to evaluate environmental comfort and the uniformity of temperature distribution. Compared with simply obtaining temperature, humidity or wind speed, they can better reflect the user's comfort in the current environment. Therefore, by calculating the wind feel index and / or temperature range through the first environmental parameter, and further training the comfort control model, the accuracy of the comfort control model in adjusting the air conditioning control parameters can be enhanced, thereby improving user comfort and enhancing the user experience.
[0051] Step 102: Based on the first environmental parameters and the preset first environmental parameter standard, train the comfort control model so that the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters; the first environmental parameter standard includes one or more of the following: the wind feel index standard and the temperature range standard.
[0052] To improve the accuracy of the comfort control model, as many first environmental parameters as possible can be obtained. In step 101, the first environmental parameters are the environmental parameters obtained when the air conditioner operates under any control parameter. Therefore, within the variable range of the air conditioner's control parameters, different control parameters and the values of each control parameter can be traversed to obtain multiple first environmental parameters under different control parameters. Here, the air conditioner's control parameters can include the air conditioner's operating mode and operating parameters. The air conditioner's operating mode can include cooling mode, heating mode, air supply mode, dehumidification mode, etc., and the air conditioner's operating parameters can include the air conditioner's set temperature parameters, fan speed parameters, etc. For example, the air conditioner's control parameters can be: in cooling mode, the temperature is set to 20℃ and the fan speed is low; in cooling mode, the temperature is set to 20℃ and the fan speed is high; in cooling mode, the temperature is set to 23℃ and the fan speed is low; in heating mode, the temperature is set to 20℃ and the fan speed is low; in dehumidification mode, the temperature is set to 20℃ and the fan speed is high, etc.
[0053] Before training the comfort control model, actual environmental parameters within the space, i.e., the first environmental parameters, can be collected when the air conditioner operates under different control parameters. A preset standard for the first environmental parameters can be established, which can be based on multiple environmental factors such as temperature, humidity, airflow velocity, and light intensity. Corresponding to the steps above, the first environmental parameter standard can be determined based on the draft sensation index and temperature range.
[0054] In some embodiments, during the training of the comfort control model, multiple different comfort control models can be established based on different operating modes. For example, when the operating mode is cooling mode, a comfort control model for cooling mode is established; when the operating mode is heating mode, a comfort control model for heating mode is established.
[0055] By setting different operating parameters for the air conditioner under different operating modes, multiple first environmental parameters in the actual space are obtained. The first environmental parameter standards are preset under different operating modes. Based on the different operating modes, the comfort control model is trained so that the trained comfort control model can adjust the operating parameters of the air conditioner under different operating modes, and obtain the operating parameters that can achieve the best user comfort under different operating modes, so that the air conditioner can operate under the operating parameters.
[0056] In some embodiments, during the training of the comfort control model, a separate comfort control model can be established. This model collects first environmental parameters within the actual space under different control parameters while the air conditioner operates. Based on a preset first environmental parameter standard, the comfort control model is trained, enabling it to directly obtain the air conditioning control parameters that provide the most comfort for the user. In this implementation, it is not necessary to strictly set the air conditioner's operating mode; the comfort control model can proactively adjust the operating mode and parameters in the air conditioning control parameters based on the current environmental parameters.
[0057] Specifically, the preset first environmental parameter standard can include one or more of the following: average wind speed standard, draft feel index standard, and temperature range standard. The temperature range standard can include one or more of the following: vertical temperature difference standard and horizontal temperature difference standard. Specifically, the average wind speed standard can be set to an average airflow speed of no more than 0.3 m / s for the multi-dimensional comfort airflow field air conditioner; the draft feel index standard can be set to an average DR (radius density) of no more than 10% for all sampling points on the horizontal plane directly in front of the indoor unit's air outlet; the vertical temperature difference standard can be set to a temperature difference of no more than 1.0℃ between the upper and lower floors of the multi-dimensional comfort airflow field air conditioner; and the horizontal temperature difference standard can be set to a temperature difference of no more than 1.0℃ between the left and right floors of the multi-dimensional comfort airflow field air conditioner.
[0058] When the first environmental parameter standard is the draft feeling index standard, the comfort control model can be trained based on the first environmental parameter in the space obtained by the air conditioner operating under any control parameter and the draft feeling index standard. The trained comfort control model can adjust the control parameters of the air conditioner so that when the air conditioner operates under the control parameters set by the comfort control model, the draft feeling index in the space is no more than 10%.
[0059] When the first environmental parameter standard is the vertical temperature difference standard, the comfort control model can be trained based on the vertical temperature difference within the space obtained under any control parameter of the air conditioner, and the standard vertical temperature difference. This trained comfort control model can then set the control parameters of the air conditioner so that, when the air conditioner operates under the control parameters set by the comfort control model, the vertical temperature difference within the space does not exceed 1.0℃. Here, the vertical temperature difference can be determined based on the vertical height difference between adjacent sampling points, or it can be determined based on the height of the space.
[0060] Step 103: Obtain the current environmental parameters and use the trained comfort control model to obtain the air conditioning control parameters corresponding to the current environmental parameters.
[0061] Corresponding to the steps above, after training the comfort control model, the comfort control model can determine the air conditioning control parameters corresponding to the current environmental parameters based on the acquired current environmental parameters; or, the comfort control model can acquire the current air conditioning operating mode, and based on the current air conditioning operating mode and the acquired current environmental parameters, determine the air conditioning control parameters corresponding to the current environmental parameters.
[0062] As can be seen, the comfort control model can adjust the air conditioning control parameters based on the current environmental parameters through the method given in this embodiment, so that the adjusted air conditioning control parameters can generate the most comfortable environment for the user in the current environment.
[0063] In practical applications, steps 101 to 103 can be implemented based on a processor, which can be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor.
[0064] In some embodiments, before training the comfort control model based on the first environmental parameters and the preset first environmental parameter standard, the method further includes: obtaining a second environmental parameter standard corresponding to different user characteristics based on the first environmental parameter standard; the user characteristics include one or more of the user's age group, user gender, number of users, and the user's scene; the training of the comfort control model based on the first environmental parameters and the preset first environmental parameter standard includes: training the comfort control model based on the first environmental parameters and the second environmental parameter standard, wherein the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters and user characteristics.
[0065] Based on the above embodiments, since different groups of people have different perceptions of comfort, in addition to the preset first environmental parameter standard, second environmental parameter standards corresponding to different user characteristics can also be specified, taking into account different user characteristics. Specifically, the comfort level of different user characteristics can be evaluated through on-site user experience tests, questionnaires, data analysis, and other methods.
[0066] For example, the average wind speed standard in the first environmental parameter standard can be adjusted for users of different age groups: for the elderly, the average airflow speed of the multi-dimensional comfort air field air conditioner can be set to no more than 0.1 m / s; for young people, the average airflow speed can be set to no more than 0.3 m / s. The draft feel index standard in the first environmental parameter standard can also be adjusted for users of different age groups: for the elderly, the average DR (radius density) of all sampling points on the horizontal sampling plane directly in front of the indoor unit's air outlet can be set to no more than 8%; for young people, the average DR of all sampling points on the horizontal sampling plane directly in front of the indoor unit's air outlet can be set to no more than 10%. The left-right temperature difference standard can be adjusted according to the user's location: in a bedroom, the temperature difference between the left and right sides of the multi-dimensional comfort air field air conditioner can be set to no more than 0.5℃; in a living room, the temperature difference between the left and right sides can be set to no more than 1℃.
[0067] In this embodiment, the comfort control model can be defined as a feature vector f, where f(m1, m2, ..., m) is defined. n )={V, F, θ, T, H}, where m i m represents the input parameters in different scenarios. iThese can be user characteristics, operating modes, environmental parameters, etc., where V represents wind speed (m / s), F represents air conditioning operating frequency (Hz), θ represents airflow direction (degrees), T represents temperature setting (°C), and H represents humidity control (%). These feature vectors clearly represent the operating parameter settings of the comfort control model, allowing for the selection of appropriate target input parameters based on different operating scenarios in practical applications.
[0068] In some embodiments, before obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model, the method further includes: identifying user characteristics in the current environment; determining target input parameters based on the user characteristics in the current environment and the current environmental parameters; obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model includes: obtaining the air conditioning control parameters corresponding to the target input parameters through the trained comfort control model.
[0069] After obtaining the trained comfort control model based on the method described in the above embodiments, the trained comfort control model is integrated into the air conditioning system and runs in a real-world scenario. During operation, the air conditioning system first identifies user characteristics within the current operating space. Specifically, the air conditioning system can be equipped with an image acquisition device to capture images of the space during operation. Using an image recognition algorithm, user characteristics are identified from the captured images. These user characteristics and current environmental parameters are then used as target input parameters for the comfort control model. Based on these target input parameters, the comfort control model outputs corresponding air conditioning control parameters.
[0070] In addition to incorporating image acquisition devices into the air conditioning system, the system can also identify user characteristics within the space using technologies such as infrared sensing and millimeter-wave radar. The identification results are then used as target input parameters (m1, m2, ..., m) for the comfort control model. n The system autonomously selects the optimal comfort control model f. best It also automatically adjusts the air conditioner's control parameters (V). best F best θ best T best H best ).
[0071] In some embodiments, after obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model, the method further includes: running the air conditioner based on the air conditioning control parameters corresponding to the current environmental parameters, and obtaining the air conditioning control parameters modified by the user; adjusting the parameters of the comfort control model based on the modified air conditioning control parameters and the air conditioning control parameters obtained by the comfort control model under the current environmental parameters, so that the difference between the adjusted comfort control model and the modified air conditioning control parameters is less than a threshold.
[0072] Because different users have different perceptions and preferences for environmental parameters, in practical applications, after the air conditioner's control parameters are determined through a comfort control model and the air conditioner is operated based on these control parameters, it may also receive adjustments to the control parameters from the user, resulting in the user-modified air conditioner control parameters.
[0073] To ensure that the comfort control model can accurately adjust the control parameters based on user preferences, the number of times the user modifies the control parameters set by the comfort control model can be counted. If the number of modifications exceeds a threshold, the model parameters of the comfort control model will be automatically adjusted.
[0074] Specifically, based on the user-modified air conditioning control parameters and the air conditioning control parameters obtained by the comfort control model under the current environmental parameters, the parameters of the comfort control model can be adjusted using algorithms such as gradient descent, cross-validation, and second-order optimization. This allows the adjusted comfort control model to update the corresponding control parameters (V) in real time. b ′ est F ′ best ,θ ′ best ,T ′ best H ′ best To improve user comfort.
[0075] The comfort control model, through the method presented in this embodiment, can learn and update itself based on the control parameters modified by the user, and can optimize itself according to the user's actual usage, continuously improving the model's performance and user experience.
[0076] In some embodiments, obtaining the first environmental parameters of each sampling point in the space where the air conditioner is located includes: obtaining the first environmental parameters of each sampling point in each sampling plane in the space where the air conditioner is located; the sampling plane represents a plane parallel to the wall where the air conditioner is located.
[0077] This embodiment provides an environmental parameter sampling method. It can take the wall where the air conditioner is located as a reference, and obtain multiple sampling planes that are parallel to the wall where the air conditioner is located but at different distances from the wall. Then, based on the multiple sampling planes, the first environmental parameters of multiple sampling points on each sampling plane are sampled.
[0078] For example, a test vehicle can be used to sample environmental parameters. The test vehicle can be placed on the floor of the space where the air conditioner is located. A sampling rod, parallel to the floor and the wall where the air conditioner is located, can be placed on the test vehicle. The length of the sampling rod can be equal to or less than the width of the plane where the air conditioner is located. Multiple sampling points are deployed on the sampling rod at preset intervals. The sampling rod on the test vehicle can be configured to extend and retract freely, allowing it to collect environmental parameters from the ground and also extend to collect environmental parameters from the ceiling.
[0079] Assuming the sampling rod can collect data from Y1 to Y2 on it... n The environmental parameters at each sampling point can be collected vertically at heights Z1, Z2, Z3, Z4, and Z5. The interval between each adjacent sampling height (Z1, Z2, Z3, Z4, Z5) can be set to 0.5 meters. Therefore, by using the sampling rod mounted on the testing vehicle, environmental parameters can be collected at 5×n sampling points on the same sampling plane.
[0080] During initial sampling, the sampling plane of the test vehicle can be set to start sampling 0.5 meters away from the wall where the air conditioner is located. The test vehicle can be moved 0.5 meters each time to obtain the environmental parameters of the sampling point on the new sampling plane, until the distance between the sampling plane and the wall opposite the air conditioner is less than 0.5 meters.
[0081] In actual sampling, to improve the accuracy of the comfort control model, the spacing between sampling points can be shortened, for example, by reducing the interval to 0.2 meters; the number of sampling points on the sampling rod can also be increased, enabling the sampling rod to collect data from Y1 to Y2. 2n One sampling point.
[0082] In some embodiments, based on the above embodiments, the above-mentioned acquisition of the first environmental parameters of each sampling point in the space where the air conditioner is located, and the determination of the first parameters in the space where the air conditioner is located based on the first environmental parameters, includes: acquiring a first preset number of second environmental parameters sampled at each sampling point within a first preset time range; the second environmental parameters represent the environmental parameters obtained when the air conditioner is running under any control parameter; the second environmental parameters include temperature and wind speed; determining the first environmental parameters of each sampling point based on multiple second environmental parameters; and determining the airflow index in the space where the air conditioner is located based on the first environmental parameters.
[0083] When it is necessary to obtain the wind feel index within a space, based on the sampling method given in the above embodiments, sampling can be set within a first preset time range, which can be set to 3 minutes. Within the first preset time range, data can be collected at an interval of at least 1 second, and multiple temperatures and wind speeds collected within the first preset time range can be obtained. The average wind speed value and average temperature value within the first preset time range are taken, and the DR value of each sampling point is calculated based on formula (1). Then, the average DR value of all sampling points on each sampling plane is calculated as the wind feel index of each sampling plane.
[0084] In some embodiments, based on the above embodiments, the above-mentioned acquisition of the first environmental parameters of each sampling point in the space where the air conditioner is located, and the determination of the first parameters in the space where the air conditioner is located based on the first environmental parameters, includes: acquiring a second preset number of third environmental parameters sampled at each sampling point within a second preset time period; the third environmental parameters represent the environmental parameters obtained when the air conditioner is operating under any control parameter; the third environmental parameters include temperature; determining the first environmental parameters of each sampling point based on multiple third environmental parameters; and determining the temperature range in the space where the air conditioner is located based on the first environmental parameters.
[0085] When the temperature range within a space needs to be obtained, the uniform airflow function can be activated, and the system can run for a second preset time, which can be set to 60 minutes. The system records the temperature values at various sampling points on both sides of the indoor unit of the air conditioner every 5 minutes. The difference between the highest and lowest average real-time dry-bulb temperature values at different vertical heights every 5 minutes is taken as the temperature range. In practical applications, to obtain the temperature range within a space when the air conditioner operates under different control parameters, the indoor unit of the air conditioner can be placed on the central axis of any wall in the laboratory space.
[0086] Those skilled in the art will recognize that the environmental parameter collection methods provided in the embodiments of this application are exemplary, and the sampling distance, sampling time, sampling method, etc., provided in the above embodiments can be adjusted according to actual needs.
[0087] Based on the method given in the above embodiments, Figure 2 A flowchart of a control method for a comfort control model is shown, including:
[0088] Step 201: Detection and Data Acquisition.
[0089] The first environmental parameters in the space where the air conditioner is located can be collected based on the method given in the above embodiments.
[0090] Step 202: Establish a comfort control model.
[0091] Based on the method described in the above embodiments, a comfort control model is established. One or more comfort control models can be established according to different operating modes (such as cooling mode, heating mode, dehumidification mode, etc.). Each comfort control model can output multiple air conditioning control parameters, such as fan speed, air conditioning operating frequency, and airflow direction.
[0092] Step 203: User experience testing and model optimization.
[0093] User experience testing was conducted for different user characteristics. Comfort levels under different comfort control models were evaluated using methods such as questionnaires and data analysis. Based on the comfort evaluation results, the optimal comfort control model was selected.
[0094] Step 204: Intelligent recognition and model application.
[0095] When the air conditioner is running, the system uses technologies such as image recognition, infrared sensing, and millimeter-wave radar to identify user characteristics (such as age and gender) within the space. Based on the identification results, the system uses these characteristics as target input parameters for the comfort control model and autonomously selects the optimal comfort control model.
[0096] Step 205: Self-learning and model update.
[0097] After the air conditioning operating mode is successfully set, the air conditioning system will perform self-learning optimization of the comfort control model based on the user's active control operations, such as manually adjusting the temperature and fan speed, and correct the model parameters of the comfort control model.
[0098] This application provides an air conditioning control method. Compared with related technologies, the control method provided in this application can respond to user needs in real time: By establishing a comfort control model, this application can optimize control parameters according to the needs of different users, achieving intelligent control of the air conditioner, improving user comfort, and providing more personalized services by responding to dynamic user needs in real time; This application can adapt to different environmental conditions. By detecting parameters such as the airflow index and temperature range in each area of the space, a comfort control model is established, which can be flexibly adjusted according to different environmental parameters, better adapting to different environmental conditions and providing a more comfortable airflow experience; The comfort control model provided in this application has self-learning and updating capabilities: Through self-learning and model updating methods, this application can self-optimize the comfort control model based on the actual usage of users, continuously improving model parameters, enhancing model performance and user experience; Through intelligent recognition and model application, this application can achieve intelligent control of the air conditioner, improving user comfort, providing more convenient services by controlling the air conditioner more intelligently.
[0099] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.
[0100] Based on the air conditioning control method proposed in the foregoing embodiments, this application also provides an air conditioning control device, such as... Figure 3 As shown, the air conditioning control device includes:
[0101] The acquisition module 301 is used to acquire the first environmental parameters of each sampling point in the space where the air conditioner is located, and to determine the first parameters in the space where the air conditioner is located based on the first environmental parameters; the first environmental parameters include temperature and wind speed; the first environmental parameters represent the environmental parameters obtained by the air conditioner operating under any control parameter; the first parameters include the wind feel index and / or temperature range.
[0102] Training module 302 is used to train a comfort control model based on a first environmental parameter and a preset first environmental parameter standard, so that the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameter; the first environmental parameter standard includes one or more of the following: the wind feel index standard and the temperature range standard.
[0103] The control module 303 is used to acquire the current environmental parameters and obtain the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model.
[0104] In practical applications, the acquisition module 301, training module 302, and control module 303 can be implemented based on a processor and a communication device.
[0105] In some embodiments, before training the comfort control model based on the first environmental parameters and the preset first environmental parameter standard, the acquisition module 301 is further used to acquire the second environmental parameter standard corresponding to different user characteristics based on the first environmental parameter standard; the user characteristics include one or more of the user's age group, user gender, number of users, and the user's scene; the training module 302 is specifically used to train the comfort control model based on the first environmental parameters and the second environmental parameter standard, wherein the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters and user characteristics.
[0106] In some embodiments, before obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model, the control module 303 is further used to identify user characteristics in the current environment; based on the user characteristics in the current environment and the current environmental parameters, the target input parameters are determined; specifically, the control module 303 is used to obtain the air conditioning control parameters corresponding to the target input parameters through the trained comfort control model.
[0107] In some embodiments, after obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model, the training module 302 is further used to run the air conditioner based on the air conditioning control parameters corresponding to the current environmental parameters, and then obtain the air conditioning control parameters modified by the user; based on the modified air conditioning control parameters and the air conditioning control parameters obtained by the comfort control model under the current environmental parameters, the comfort control model is adjusted so that the difference between the adjusted comfort control model and the modified air conditioning control parameters under the current environmental parameters is less than a threshold.
[0108] In some embodiments, the acquisition module 301 is specifically used to acquire the first environmental parameters of each sampling point in each sampling plane within the space where the air conditioner is located; the sampling plane represents a plane parallel to the wall where the air conditioner is located.
[0109] In some embodiments, the acquisition module 301 is specifically used to acquire a first preset number of second environmental parameters sampled at each sampling point within a first preset time range; the second environmental parameters represent the environmental parameters obtained when the air conditioner is running under any control parameter; the second environmental parameters include temperature and wind speed; based on multiple second environmental parameters, a first environmental parameter is determined for each sampling point; and based on the first environmental parameters, the airflow index in the space where the air conditioner is located is determined.
[0110] In some embodiments, the acquisition module 301 is specifically used to acquire a second preset number of third environmental parameters sampled at each sampling point within a second preset time period; the third environmental parameters represent the environmental parameters obtained when the air conditioner is running under any control parameter; the third environmental parameters include temperature; based on multiple third environmental parameters, a first environmental parameter is determined for each sampling point; and based on the first environmental parameters, the temperature range within the space where the air conditioner is located is determined.
[0111] It should be noted that the descriptions of the above device embodiments are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.
[0112] It should be noted that, in the embodiments of this application, if the above methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a terminal, server, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.
[0113] This application also provides an electronic device. Figure 4 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of this application, as shown below. Figure 4 As shown, the electronic device 40 may include:
[0114] Memory 401 is used to store executable instructions.
[0115] The processor 402 is used to execute executable instructions stored in the memory 401 to implement any of the above-mentioned air conditioning control methods.
[0116] The processor 402 mentioned above can be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor.
[0117] The aforementioned computer-readable storage medium or memory 401 may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it may also be various terminals that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.
[0118] This application embodiment further provides a computer storage medium storing computer-executable instructions, which are used to implement any of the air conditioning control methods provided in the above embodiments.
[0119] Correspondingly, this application embodiment further provides a computer program product, the computer program product including computer executable instructions, which are used to implement any of the air conditioning control methods provided in the above embodiments.
[0120] In some embodiments, the functions or modules of the apparatus provided in this application can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.
[0121] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.
[0122] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.
[0123] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.
[0124] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.
[0125] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0126] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims. All of these forms are within the protection scope of this application.
Claims
1. An air conditioning control method, characterized in that, The method includes: The first environmental parameter is obtained at each sampling point in the space where the air conditioner is located, and the first parameter in the space where the air conditioner is located is determined based on the first environmental parameter; the first environmental parameter includes temperature and wind speed; the first environmental parameter represents the environmental parameter obtained when the air conditioner is running under any control parameter; the first parameter includes the wind feel index and / or temperature range. Based on the first environmental parameters and the preset first environmental parameter standard, a comfort control model is trained so that the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters; the first environmental parameter standard includes one or more of the following: the airflow index standard and the temperature range standard. Obtain the current environmental parameters, and then use the trained comfort control model to obtain the air conditioning control parameters corresponding to the current environmental parameters.
2. The method according to claim 1, characterized in that, Before training the comfort control model based on the first environmental parameters and a preset first environmental parameter standard, the method further includes: Based on the first environmental parameter standard, a second environmental parameter standard corresponding to different user characteristics is obtained; the user characteristics include one or more of the following: user age group, user gender, number of users, and user's current scenario. The step of training a comfort control model based on the first environmental parameters and a preset first environmental parameter standard includes: Based on the first environmental parameter and the second environmental parameter standard, a comfort control model is trained, wherein the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters and user characteristics.
3. The method according to claim 2, characterized in that, Before obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model, the method further includes: Identify user characteristics in the current environment; based on the user characteristics in the current environment and the current environment parameters, determine the target input parameters; The process of obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model includes: The air conditioning control parameters corresponding to the target input parameters are obtained through the trained comfort control model.
4. The method according to claim 1, characterized in that, After obtaining the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model, the method further includes: After running the air conditioner based on the air conditioner control parameters corresponding to the current environmental parameters, the user-modified air conditioner control parameters are obtained. Based on the modified air conditioning control parameters and the air conditioning control parameters obtained by the comfort control model under the current environmental parameters, the parameters of the comfort control model are adjusted so that the difference between the adjusted comfort control model and the modified air conditioning control parameters under the current environmental parameters is less than a threshold.
5. The method according to claim 1, characterized in that, The acquisition of the first environmental parameters at each sampling point within the space where the air conditioner is located includes: Obtain the first environmental parameters of each sampling point in each sampling plane within the space where the air conditioner is located; the sampling plane represents a plane parallel to the wall where the air conditioner is located.
6. The method according to claim 1 or 5, characterized in that, The step of acquiring the first environmental parameters of each sampling point within the space where the air conditioner is located, and determining the first parameters within the space where the air conditioner is located based on the first environmental parameters, includes: For each sampling point, within a first preset time range, a first preset number of second environmental parameters are obtained; the second environmental parameters represent the environmental parameters obtained when the air conditioner operates under any control parameter; the second environmental parameters include temperature and wind speed. Based on multiple second environmental parameters, the first environmental parameter of each sampling point is determined; The draft index within the space where the air conditioner is located is determined based on the first environmental parameter.
7. The method according to claim 1 or 5, characterized in that, The step of acquiring the first environmental parameters of each sampling point within the space where the air conditioner is located, and determining the first parameters within the space where the air conditioner is located based on the first environmental parameters, includes: For each sampling point, within a second preset time period, a second preset number of third environmental parameters are obtained; the third environmental parameters represent the environmental parameters obtained when the air conditioner operates under any control parameter; the third environmental parameters include temperature; Based on multiple third environmental parameters, the first environmental parameter of each sampling point is determined; The temperature range within the space where the air conditioner is located is determined based on the first environmental parameter.
8. An air conditioning control device, characterized in that, The device includes: The acquisition module is used to acquire the first environmental parameters of each sampling point in the space where the air conditioner is located, and to determine the first parameters in the space where the air conditioner is located based on the first environmental parameters; the first environmental parameters include temperature and wind speed; the first environmental parameters represent the environmental parameters obtained by the air conditioner operating under any control parameters; the first parameters include the wind feel index and / or temperature range. The training module is used to train a comfort control model based on the first environmental parameters and a preset first environmental parameter standard, so that the trained comfort control model can obtain the control parameters of the air conditioner based on the environmental parameters; the first environmental parameter standard includes one or more of the following: the wind feel index standard and the temperature range standard. The control module is used to acquire the current environmental parameters and obtain the air conditioning control parameters corresponding to the current environmental parameters through the trained comfort control model.
9. An electronic device, characterized in that, The electronic device includes a processor and a memory for storing computer programs capable of running on the processor; wherein, The processor is used to run the computer program to perform the method according to any one of claims 1 to 7.
10. A computer storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method described in any one of claims 1 to 7.
11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.