Temperature measurement method, air conditioner control method, equipment and medium

Abstract

The embodiment of the invention provides a temperature measurement method, an air conditioner control method, equipment and a storage medium, and is applied to the field of air conditioners. The temperature measurement method can comprise the steps that the measurement temperature and an image of a user are obtained through an infrared camera; determining the distance between the infrared camera and the user according to the image; acquiring the current environment temperature; determining a temperature compensation value according to the distance, the environment temperature and the measured temperature of the user; determining the actual temperature of the user according to the temperature compensation value and the measured temperature of the user; the real body sensing temperature of different users can be sensed more accurately, and the air conditioning system can be flexibly adjusted according to the actual temperature of each user, so that the comfort requirements of different individuals in a scene where multiple persons are located are met, and the accuracy and adaptability of indoor temperature adjustment are improved.

Description

Technical Field

[0001] This invention relates to the field of air conditioning technology, and in particular to a temperature measurement method, an air conditioning control method, equipment, and medium. Background Technology

[0002] With the development of technology and the improvement of living standards, people have increasingly higher requirements for the comfort of their living and working environments. As the core equipment for indoor temperature regulation, air conditioning has become increasingly important. However, traditional air conditioning systems rely on fixed temperature settings or simple temperature control sensors, which make it difficult to accurately sense and adapt to the differences in perceived temperature of different individuals in a space where multiple people are together, and thus cannot meet the comfort needs of everyone. Summary of the Invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a temperature measurement method, air conditioning control method, device and medium that overcome or at least partially solve the above problems.

[0004] In a first aspect, embodiments of the present invention provide a temperature measurement method, the method comprising: The user's measured temperature and images are obtained through an infrared camera; Based on the image, determine the distance between the infrared camera and the user; Get the current ambient temperature; The temperature compensation value is determined based on the distance, the ambient temperature, and the user's measured temperature. The user's actual temperature is determined based on the temperature compensation value and the user's measured temperature.

[0005] Optionally, determining the temperature compensation value based on the distance, the ambient temperature, and the user's measured temperature includes: The temperature compensation value is determined using the artificial lemming algorithm based on the distance, the ambient temperature, and the user's measured temperature.

[0006] Optionally, determining the temperature compensation value using the artificial lemming algorithm based on the distance, the ambient temperature, and the user's measured temperature includes: Acquire historical data, including the user's measured temperature, ambient temperature, and distance between the camera and the user under different conditions; Based on the historical data, a temperature compensation function is constructed with the objective of minimizing the error between the user-compensated temperature and the actual temperature. An initial lemming population is constructed based on the weight parameters of the temperature compensation function, and each lemming in the initial lemming population corresponds to a set of candidate weight parameter values. The initial lemming population is iterated until a preset condition is met, and the target lemming population is output. Determine the optimal compensation coefficient in the target lemming population; The temperature compensation value is determined based on the distance, the ambient temperature, the user's measured temperature, and the optimal temperature compensation coefficient.

[0007] Optionally, determining the optimal compensation coefficient in the target lemming population includes: The mean square error of the weighted parameter combination for each lemming in the target lemming population after being substituted into the temperature compensation function is determined. The mean square error of each lemming species in the target lemming species is compared, and the lemming with the smallest mean square error is selected. The combination of weight parameters corresponding to the lemming with the smallest mean square error is determined as the optimal compensation coefficient.

[0008] Optionally, the mean square error of the weighted parameter combination for each lemming after substituting it into the temperature compensation function can be calculated using the following formula:

[0009] Where MSE refers to mean squared error, n is the number of samples in the historical data, and T (c，i) T is the compensated temperature calculated for the i-th sample using the corresponding weight parameter combination. （b，i） Let be the actual temperature corresponding to the i-th sample.

[0010] Optionally, the iteration condition is that the number of iterations reaches a preset number.

[0011] Optionally, determining the distance between the infrared camera and the user based on the image includes: Based on the image, determine the bounding box coordinates of the user; The distance between the infrared camera and the user is determined based on the bounding box coordinates.

[0012] Optionally, the bounding box coordinates include the coordinates of the upper left corner of the human body and the coordinates of the lower right corner of the human body. Determining the distance between the infrared camera and the user based on the bounding box coordinates includes: The user's human body pixel height is determined based on the coordinates of the upper left corner and the lower right corner of the human body. Obtain the camera focal length of the infrared camera; The distance between the infrared camera and the user is determined based on the human body pixel height and the camera focal length.

[0013] Secondly, the present invention also discloses a method for controlling an air conditioner, the method comprising: The user's measured temperature and images are obtained through an infrared camera; Based on the image, determine the distance between the infrared camera and the user; Get the current ambient temperature; The temperature compensation value is determined based on the distance, the ambient temperature, and the user's measured temperature. The user's actual temperature is determined based on the temperature compensation value and the user's measured temperature. Adjust the output temperature according to the user's actual temperature.

[0014] Thirdly, the present invention also discloses a temperature measuring device, the device comprising: The first acquisition module is used to acquire the user's measured temperature and images via an infrared camera; The first determining module is used to determine the distance between the infrared camera and the user based on the image; The second acquisition module is used to acquire the current ambient temperature; The second determining module is used to determine a temperature compensation value based on the distance, the ambient temperature, and the user's measured temperature. The third determining module is used to determine the user's actual temperature based on the temperature compensation value and the user's measured temperature.

[0015] Thirdly, embodiments of the present invention provide an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of the temperature measurement method as described in the first aspect or the air conditioning control method as described in the second aspect.

[0016] Fourthly, embodiments of the present invention provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the temperature measurement method as described in the first aspect or the air conditioning control method as described in the second aspect.

[0017] The embodiments of the present invention have the following advantages: This invention discloses a temperature measurement method, an air conditioning control method, equipment, and a medium. This invention can simultaneously acquire a user's measured temperature and an image using an infrared camera, determine the distance between the camera and the user by combining image analysis, and then determine a temperature compensation value by integrating the current ambient temperature. Finally, based on the temperature compensation value, the measured temperature is corrected to obtain the user's actual temperature. This effectively solves the problem that traditional air conditioning systems struggle to accurately adapt to individual temperature differences in shared spaces. It can more accurately perceive the true temperature of different users, allowing the air conditioning system to flexibly adjust according to each user's actual temperature, thereby meeting the comfort needs of different individuals in shared spaces and improving the accuracy and adaptability of indoor temperature regulation. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0019] Figure 1 This is a flowchart of a temperature measurement method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating how to determine the distance between an infrared camera and a user, provided by an embodiment of the present invention. Figure 3 This is a schematic diagram of a triangular principle provided in an embodiment of the present invention; Figure 4 This is a schematic flowchart of a temperature measurement method provided in an embodiment of the present invention; Figure 5 This is a flowchart of the steps of an air conditioner control method provided in an embodiment of the present invention; Figure 6 This is a structural block diagram of a temperature measuring device provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] The terms "first," "second," etc., used in the specification and claims of this invention are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0022] One of the core concepts of this invention is that an infrared camera can simultaneously acquire the user's measured temperature and image, combine the image analysis to determine the distance between the camera and the user, and then integrate the current ambient temperature to determine the temperature compensation value. Finally, the measured temperature is corrected based on the temperature compensation value to obtain the user's actual temperature. This effectively solves the problem that traditional air conditioning systems are difficult to accurately adapt to the differences in the perceived temperature of individuals in a space where multiple people are together. It can more accurately perceive the real perceived temperature of different users, allowing the air conditioning system to flexibly adjust according to the actual temperature of each user, thereby meeting the comfort needs of different individuals in a scenario where multiple people are together and improving the accuracy and adaptability of indoor temperature regulation.

[0023] Reference Figure 1 The diagram illustrates a flowchart of a temperature measurement method provided by an embodiment of the present invention, which may include: Step 101: Acquire the user's measured temperature and image using an infrared camera.

[0024] In this embodiment of the invention, an infrared camera can be used to acquire the user's measured temperature and image. The infrared camera has the ability to capture temperature information and visual images simultaneously. In this step, it can scan the user within the monitoring range, recording the initial temperature data of the user's body surface or related areas, and simultaneously acquiring images containing information such as the user's location and shape, providing basic data support for subsequent steps such as distance calculation.

[0025] Step 102: Determine the distance between the infrared camera and the user based on the image.

[0026] In this embodiment of the invention, the image contains the user's positional features in space and the relative positional relationship with the camera. By analyzing and processing the image, such as using information like the user's size ratio and pixel distribution in the image, combined with relevant image ranging algorithms, the actual distance between the infrared camera and each user can be accurately calculated.

[0027] It should be noted that there are multiple ways to determine the distance between the infrared camera and the user using graphics, and the method can be determined according to the user's needs.

[0028] Step 103: Obtain the current ambient temperature.

[0029] In this embodiment of the invention, ambient temperature is one of the important factors affecting the user's comfort and the accuracy of infrared temperature measurement. The overall ambient temperature in the current monitoring space, such as the air temperature in a room, can be obtained in real time through a dedicated ambient temperature sensor or other devices that can collect ambient temperature. This data can be incorporated into the entire temperature measurement process so that the impact of environmental factors on the user's measured temperature can be comprehensively considered in subsequent compensation calculations.

[0030] Step 104: Determine the temperature compensation value based on the distance, ambient temperature, and the user's measured temperature.

[0031] In this embodiment of the invention, infrared thermometry is affected by distance and ambient temperature. For example, if the distance is too far, the measured temperature may be too low. If the ambient temperature is too high or too low, it will also cause deviation in the measurement results. Therefore, it is necessary to combine these three parameters and calculate the temperature compensation value that can correct these interference factors through a preset compensation algorithm. This temperature compensation value can reflect the degree of influence of distance and ambient temperature on the initial measured temperature.

[0032] Step 105: Determine the user's actual temperature based on the temperature compensation value and the user's measured temperature.

[0033] In this embodiment of the invention, the measured temperature and the temperature compensation value can be calculated, for example, by adding them together, to correct the initial measured temperature, thereby obtaining a value that is closer to the user's actual body temperature or the actual surface temperature. This actual temperature can provide a precise basis for adjusting equipment such as air conditioning systems, and better meet the comfort needs of different users.

[0034] This invention discloses a temperature measurement method that can simultaneously acquire a user's measured temperature and image using an infrared camera. By combining image analysis to determine the distance between the camera and the user, and then integrating the current ambient temperature to determine a temperature compensation value, the measured temperature is finally corrected based on the temperature compensation value to obtain the user's actual temperature. This effectively solves the problem that traditional air conditioning systems are difficult to accurately adapt to the differences in perceived temperature among individuals in a space where multiple people are together. It can more accurately perceive the real perceived temperature of different users, allowing the air conditioning system to flexibly adjust according to the actual temperature of each user, thereby meeting the comfort needs of different individuals in a multi-person co-occupancy scenario and improving the accuracy and adaptability of indoor temperature regulation.

[0035] In one embodiment of the present invention, determining a temperature compensation value based on distance, ambient temperature, and the user's measured temperature includes: determining the temperature compensation value based on distance, ambient temperature, and the user's measured temperature using an artificial lemming algorithm.

[0036] In this embodiment of the invention, the artificial lemming algorithm is an intelligent optimization algorithm that simulates the behavior of lemming groups. It has strong global search and local optimization capabilities and can be applied to the determination of actual temperature. First, it uses three key parameters—distance, ambient temperature, and the user's measured temperature—as input variables to construct a multi-dimensional optimization search space. During the initialization phase of the algorithm, a certain number of "lemming individuals" are generated, each corresponding to a set of potential temperature calculation-related parameter combinations. These parameter combinations are directly related to the mapping relationship between the input variables and the actual temperature. Subsequently, the algorithm simulates the foraging, migration, and population renewal behaviors of lemmings. Through information interaction and position iteration between individuals, the weights and values ​​of each parameter combination are continuously adjusted. During the search process, the distance parameter affects the attenuation correction of the infrared thermometry signal, the ambient temperature parameter is related to environmental interference compensation during the heat radiation transfer process, and the measured temperature serves as the basic data anchor point. The algorithm can dynamically optimize the parameter combination based on the interaction relationship of these three variables to reduce calculation errors. After multiple iterations, the algorithm converges to the optimal parameter combination. This combination can be used to establish an accurate calculation model of the input variables and temperature compensation values. The final output is a temperature compensation value that can eliminate the influence of distance attenuation and environmental interference, thus achieving efficient correction of the initial measured temperature.

[0037] This invention introduces an artificial lemming algorithm to fully explore the nonlinear correlation between distance, ambient temperature, and user-measured temperature. Leveraging the algorithm's powerful optimization capabilities, it achieves precise fusion and dynamic optimization of multiple parameters, effectively offsetting the interference of distance and ambient temperature changes on infrared temperature measurement results. This significantly improves the accuracy of calculating the user's actual temperature, providing air conditioning systems with temperature data that more closely reflects individual body sensations. Consequently, air conditioning systems can accurately adapt to the differences in body sensations among different individuals in a shared space, completely solving the problem of inaccurate temperature control in traditional air conditioning systems and significantly enhancing the personalization and comfort of indoor temperature regulation.

[0038] In one embodiment of the present invention, a temperature compensation value is determined using an artificial lemming algorithm based on distance, ambient temperature, and the user's measured temperature. This includes: acquiring historical data, which includes the user's measured temperature, ambient temperature, and distance between the camera and the user under different conditions; constructing a temperature compensation function based on the historical data, with the objective of minimizing the error between the user's compensated temperature and the actual temperature; constructing an initial lemming population based on the weight parameters of the temperature compensation function, with each lemming in the initial population corresponding to a set of candidate weight parameter values; iterating through the initial lemming population until a preset condition is met, and outputting a target lemming population; determining the optimal compensation coefficient in the target lemming population; and determining the temperature compensation value based on the distance, ambient temperature, the user's measured temperature, and the optimal temperature compensation coefficient.

[0039] In this embodiment of the invention, acquiring historical data is a fundamental step in the entire process of determining the temperature compensation value. It is necessary to collect key parameter information under different scenario conditions. These parameters specifically include the user's measured temperature, the ambient temperature at that time, and the distance between the camera and the user. During the data collection process, it is necessary to cover diverse usage scenarios, such as different indoor space sizes, different population densities, different ambient temperature ranges, and different camera installation heights and distance ranges from the user, to ensure that the historical data is comprehensive and representative. Through continuous data accumulation, a sufficiently large dataset is formed. This data will truly reflect the actual situation of temperature measurement under different parameter combinations, providing reliable sample support for the subsequent construction of the temperature compensation function and algorithm optimization, and avoiding problems such as model bias or inaccurate algorithm optimization due to single data.

[0040] After completing the historical data collection, with the core objective of minimizing the error between the user-compensated temperature and the actual temperature, a temperature compensation function is constructed based on the collected historical data. First, the relationships between various parameters in the historical data need to be analyzed to clarify the mapping logic between the three input variables—distance, ambient temperature, and user-measured temperature—and the temperature compensation value, thus determining the basic form of the function. Subsequently, through data fitting and statistical analysis, the historical data is substituted into the function model for parameter calibration, enabling the constructed temperature compensation function to accurately quantify the influence of each input parameter on the compensation value. The core value of this function lies in establishing mathematical relationships, providing a clear target for subsequent parameter optimization, and ensuring that the final calculated temperature compensation value can effectively correct the deviation between the measured temperature and the actual temperature.

[0041] In one example, based on the collected dataset and these coefficient combinations, a temperature-compensated function can be constructed, such as... .

[0042] in, Indoor ambient temperature, To minimize the error between the compensated temperature and the blackbody temperature, The temperature was measured by an infrared camera. To measure distance, The value is the blackbody temperature (i.e., the actual temperature of the human body). In other words, all the weight values ​​in this function are combinations of temperature compensation coefficients.

[0043] After the temperature compensation function is constructed, the weight parameters in the function can be used as the core optimization objects to form an initial lemming population. The size of the initial lemming population can be reasonably set according to actual needs. It is necessary to ensure that the population size is sufficient to cover a wide range of parameter search, while avoiding an excessive number that would lead to low algorithm iteration efficiency. Each lemming in the population corresponds to a unique set of candidate weight parameter values. These candidate values ​​are determined based on the parameter distribution range of historical data, engineering experience, or random generation. Each set of candidate values ​​represents a possible parameter configuration scheme. By constructing such an initial population, an initial search starting point is provided for the artificial lemming algorithm, ensuring that the algorithm can gradually select the optimal solution from multiple sets of parameter combinations.

[0044] Further, lemming behavior can be simulated. This step is the core mechanism for lemming groups to find the optimal path in complex environments. Based on the temperature compensation effect of each "lemming" under the current parameters, the compensated temperature error is calculated and its performance is evaluated.

[0045] Lemming behavior can specifically include the following steps: Migration behavior: The lemming group moves along the optimal direction and performs a global search. The individual position update is shown in the following formula:

[0046] in, A random number between 0 and 1. Representative of individuals The combined value of the compensation coefficients at the next iteration. This represents the globally optimal position for the entire population at present. The fitness function is used to calculate the error between the compensated temperature and the blackbody temperature. When all lemming paths converge to a local optimum, the population diversity decreases, making it impossible to further explore new solution spaces, causing the algorithm to get stuck in a local optimum. Therefore, a random perturbation term is added. ,in Control the intensity of the disturbance. It is a random direction vector between [-1, 1].

[0047] Aggregation behavior: When lemmings congregate in resource-rich areas, they achieve local fine-grained search. The lemming population continuously moves closer to the current optimal compensation coefficient, which helps to accelerate the convergence speed and avoid getting trapped in local optima. For individuals, randomly selected from the population... Each neighbor is updated with a fitness-weighted location:

[0048] in, As an aggregation factor, Let J be the weight of the j-th neighbor. The better the fitness, the larger the weight setting, which enhances the local search capability of high-quality solutions.

[0049] Lemming behavior: When encountering obstacles or dangerous areas, lemmings will suddenly "jump" to a new location to avoid unfavorable areas, thus increasing diversity. In infrared temperature compensation, this can prevent the population from prematurely converging to local optima, improving the model's robustness. This behavior is only triggered when the fitness change value is less than a set threshold, and the individual position update is as follows:

[0050] in, This is the jump coefficient, which decreases with the number of iterations. For Levi's flight stride.

[0051] In each iteration, the fitness value of each lemming is first calculated. The fitness value is based on the error of the temperature compensation function, that is, the compensated temperature is calculated by combining the weight parameters of the lemming and then compared with the actual temperature in the historical data. The smaller the error, the higher the fitness. Subsequently, the lemmings' positions are updated, information is exchanged, and the fittest are eliminated according to the algorithm rules. Lemmings with high fitness are retained and pass their superior parameter information to other individuals, while lemmings with low fitness are eliminated or have their parameter positions adjusted to find a better solution. This iterative process is repeated until the preset convergence conditions are met. Common preset conditions may include the number of iterations reaching a set threshold, the overall error of the population being lower than a specified standard, or the parameter update amplitude being less than a critical value. When the conditions are met, the iteration stops, and the target lemming population after multiple rounds of optimization is output.

[0052] After the target lemming population is output, the optimal compensation coefficient needs to be selected. First, for each lemming in the population, its corresponding weight parameter combination is substituted into the previously constructed temperature compensation function. The compensated temperature is calculated by combining the input parameters from historical data. Then, the deviation between the compensated temperature and the actual temperature is calculated using the mean square error formula, obtaining the mean square error value for each lemming. The mean square error can accurately reflect the compensation effect of the parameter combination. The smaller the value, the closer the compensated temperature is to the actual temperature. Then, the mean square error values ​​of all lemmings are compared, and the lemming with the smallest mean square error is selected. The weight parameter combination corresponding to this lemming has undergone multiple rounds of algorithm optimization and is the parameter configuration that best reduces temperature deviation in the historical data sample. Finally, this set of weight parameter combinations is determined as the optimal compensation coefficient.

[0053] After determining the optimal compensation coefficient, the temperature compensation value can be calculated by combining the real-time collected parameters. First, the user's measured temperature and image in the current scene are obtained through an infrared camera. The distance between the camera and the user is obtained based on image analysis. At the same time, the current ambient temperature is collected to ensure the accuracy and timeliness of these three real-time parameters. Then, these three real-time parameters are substituted into the constructed temperature compensation function, and the previously determined optimal compensation coefficient is applied to the function calculation. The final temperature compensation value is obtained through mathematical calculation logic. This temperature compensation value fully considers the interference of distance and ambient temperature on the measured temperature and can provide a direct basis for correcting the user's measured temperature and obtaining the true actual temperature.

[0054] Assuming an infrared camera simultaneously detects two users in a multi-person office, the algorithm first collects historical data on measured and actual temperatures at different distances and ambient temperatures in similar scenarios. This data is used to construct a temperature compensation function with the goal of minimizing error. The function's weight parameters are then transformed into an initial population of 50 lemmings, each corresponding to a set of candidate weight values. The algorithm iterates. In the first iteration, lemming number 23 is eliminated due to a large compensation error caused by its weight combination, while lemming number 17 is retained and its parameter information is passed on due to a smaller error. After 30 iterations, once the preset convergence condition is met, the temperature is calculated from the target population. The mean square error of each lemming was analyzed, and it was found that the weight combination corresponding to lemming number 42 minimized the deviation between the compensated temperature and the actual temperature. This was determined as the optimal compensation coefficient. At this time, real-time monitoring showed that user A was 1.5 meters away from the camera and the measured temperature was 25℃, while user B was 3 meters away from the camera and the measured temperature was 24℃. The current ambient temperature was 23℃. Substituting the two sets of real-time parameters into the temperature compensation function and applying the optimal compensation coefficient, the final calculated temperature compensation value for user A was +0.8℃ and the temperature compensation value for user B was +1.2℃. This provided a precise basis for subsequent correction of the actual temperatures of the two individuals and for targeted adjustment of the air conditioning.

[0055] This invention constructs a precise temperature compensation function by collecting historical data from multiple scenarios. Using the artificial lemming algorithm as its core, it iteratively optimizes the function's weight parameters through multiple rounds. The optimal compensation coefficient is determined by mean square error filtering, and finally, a precise temperature compensation value is calculated by combining real-time parameters. This effectively overcomes the interference of factors such as distance and ambient temperature on temperature measurement, significantly improving the accuracy and reliability of temperature compensation. It provides scientific support for obtaining the user's actual temperature, enabling the air conditioning system to accurately perceive the temperature differences felt by different individuals in a shared space. This completely solves the problem of insufficient temperature control adaptability caused by traditional air conditioning relying on fixed settings or simple sensors, significantly improving the personalization and precision of indoor temperature regulation, and comprehensively optimizing the indoor comfort experience in multi-person shared scenarios.

[0056] In one embodiment of the present invention, determining the optimal compensation coefficient in the target lemming population includes: determining the mean square error of the weight parameter combination corresponding to each lemming in the target lemming population after substituting it into the temperature compensation function; comparing the mean square errors of each lemming in the target lemming population and selecting the lemming with the smallest mean square error; and determining the weight parameter combination corresponding to the lemming with the smallest mean square error as the optimal compensation coefficient.

[0057] In this embodiment of the invention, after obtaining the target lemming population that has undergone multiple rounds of iterative optimization, the primary task is to calculate the mean squared error (MSE) for each lemming in the population. Each lemming represents a unique set of weighted parameter combinations. These parameter combinations are directly related to the influence weights of distance, ambient temperature, and user-measured temperature on the compensation value in the temperature compensation function. The weighted parameter combinations of each lemming can be input one by one into the temperature compensation function previously constructed based on historical data. At the same time, the corresponding input parameters such as user-measured temperature, ambient temperature, and distance between the camera and the user from the historical data are substituted. The compensated temperature under each parameter combination is obtained through function calculation. Then, the calculated compensated temperature is paired with the actual user temperature under the same conditions recorded in the historical data. According to the formula for calculating the MSE, that is, first calculate the difference between each group of compensated temperature and the actual temperature, then square the difference, and finally calculate the average of all squared values ​​to obtain the MSE for each lemming. This value can objectively and accurately reflect the degree of deviation between the compensated temperature output by the temperature compensation function under this set of weighted parameter combinations and the user's actual temperature, providing a quantitative basis for subsequent selection of optimal parameters.

[0058] Furthermore, a comprehensive and systematic comparison of the mean square error values ​​of all lemmings in the target lemming population can be conducted. Since the magnitude of the mean square error directly corresponds to the quality of the compensation effect, the smaller the value, the closer the compensated temperature is to the actual temperature, and the higher the compensation accuracy. Therefore, after the comparison is completed, the lemming with the smallest mean square error value is selected. The weight parameter combination corresponding to this lemming is the optimal parameter configuration in the historical data sample set after multiple rounds of iterative optimization by the artificial lemming algorithm. It can minimize the deviation in the temperature compensation process and is the core candidate parameter for achieving accurate compensation.

[0059] After selecting the lemming with the smallest mean square error, the corresponding weight parameter combination for that lemming is formally determined as the optimal compensation coefficient. This determination process is based on thorough verification of historical data and intelligent optimization of the algorithm, ensuring the scientific validity and reliability of the optimal compensation coefficient. This optimal compensation coefficient integrates the interference patterns of distance and ambient temperature on temperature measurement, and can accurately quantify the degree of influence of each factor on the compensation value. In subsequent practical applications, simply substitute the real-time collected distance, ambient temperature, and user-measured temperature into the temperature compensation function, and combine it with the optimal compensation coefficient to quickly calculate the accurate temperature compensation value. This provides a solid guarantee for correcting user-measured temperatures and obtaining the true actual temperature, making the temperature compensation process more targeted and accurate.

[0060] This invention calculates the mean square error by substituting weighted parameters one by one, and after comprehensive comparison, selects the lemming with the smallest error and determines the optimal compensation coefficient. From quantitative evaluation to precise selection, a complete closed loop is formed, which effectively ensures the accuracy and adaptability of the optimal compensation coefficient. It can minimize the deviation after temperature compensation and lay the core foundation for subsequent accurate calculation of temperature compensation value and acquisition of the user's actual temperature. In turn, the air conditioning system can more accurately sense the differences in the perceived temperature of different users, solve the problem of insufficient temperature control accuracy of traditional air conditioners, significantly improve the personalization and precision of indoor temperature regulation, and optimize the comfort experience in scenarios where multiple people are together.

[0061] In one embodiment of the present invention, the mean square error of the weighted parameter combination corresponding to each lemming is calculated by substituting it into the temperature compensation function using the following formula: Formula (1) Where MSE refers to mean squared error, n is the number of samples in the historical data, and T (c，i） T is the compensated temperature calculated for the i-th sample using the corresponding weight parameter combination. （b，i） Let be the actual temperature corresponding to the i-th sample.

[0062] In this embodiment of the invention, the current compensated temperature can be obtained by compensating based on the current coefficient, and then the mean square error between the compensated temperature and the true temperature can be calculated to select the lemming with the smallest error.

[0063] In one embodiment of the present invention, the iteration condition is that the number of iterations reaches a preset number.

[0064] In this embodiment of the invention, the number of iterations can be set according to the user's needs. In one example, the number of iterations is 100.

[0065] In one embodiment of the present invention, determining the distance between the infrared camera and the user based on the image includes: determining the bounding box coordinates of the user based on the image; and determining the distance between the infrared camera and the user based on the bounding box coordinates.

[0066] In this embodiment of the invention, after acquiring an image containing the user captured by an infrared camera, the pixel information in the image can be analyzed to identify the differences between the user's area and the background area. For example, through human body contour features, color distribution, or texture information, the user's range in the image can be accurately delineated. The bounding box coordinates are generally represented by the image's pixel coordinate system, including the coordinate values ​​of the upper left and lower right corners of the bounding box. These two coordinate values ​​together form a rectangular box that completely surrounds the user's overall outline in the image, ensuring that key parts such as the user's head and torso are included within the box. This avoids deviations in subsequent distance calculations due to inaccurate bounding boxes. By determining the bounding box coordinates, the user's position and size in the image can be presented in a quantitative way, providing basic data for the next step of calculating the distance between the infrared camera and the user.

[0067] After obtaining the user's bounding box coordinates, the distance between the infrared camera and the user can be calculated based on this coordinate information. Firstly, the size of the bounding box directly reflects the user's proportion within the camera's field of view in the image. This proportion is related to the actual distance between the user and the camera. Generally, the closer the user is to the camera, the larger their bounding box in the image; the farther away, the smaller the bounding box. This principle can be utilized, combined with the infrared camera's intrinsic parameters and preset human body size reference data, to calculate the distance using perspective projection principles or a pre-calibrated model of the correspondence between distance and bounding box size. For example, based on the height pixel value of the bounding box, combined with the camera's focal length and the known average human height, the actual distance can be calculated using a formula; alternatively, by searching a historical calibration table mapping bounding box size to actual distance, the distance value corresponding to the current bounding box coordinates can be quickly matched. The resulting distance data accurately reflects the spatial interval between the infrared camera and the user, providing crucial parameters for subsequent temperature compensation calculations.

[0068] This invention can determine the user's bounding box coordinates through image recognition, and then calculate the actual distance between the infrared camera and the user based on the correlation between the bounding box size and distance. This achieves accurate quantification of the spatial distance between the user and the device, effectively overcoming the limitations of traditional ranging methods. It provides reliable data support for subsequent temperature measurement results correction based on distance factors, thereby improving the accuracy of the actual temperature perception of users in different locations. This helps the air conditioning system better adapt to the positional differences of individuals in a space where multiple people are together, and optimizes the targeting and comfort of temperature regulation.

[0069] In one embodiment of the present invention, the bounding box coordinates include the coordinates of the upper left corner of the human body and the coordinates of the lower right corner of the human body. Determining the distance between the infrared camera and the user based on the bounding box coordinates includes: determining the pixel height of the user's human body based on the coordinates of the upper left corner and the lower right corner of the human body; obtaining the camera focal length of the infrared camera; and determining the distance between the infrared camera and the user based on the pixel height of the human body and the camera focal length.

[0070] In this embodiment of the invention, the coordinates of the top left and bottom right corners of the human body are defined based on the pixel coordinate system of the image, corresponding to the pixel positions of the top and bottom of the human body in the image, respectively. In one example, the bounding box coordinates are: The coordinates of the top left corner (x) min ,y min ), lower right corner coordinates (x max, y max Since the change in the value of the vertical coordinate in the image pixel coordinate system directly reflects the difference in length in the vertical direction, the number of pixels occupied by the user in the vertical direction in the image can be obtained by subtracting the vertical coordinate of the upper left corner of the human body from the vertical coordinate of the lower right corner of the human body. This value is the pixel height of the user's human body.

[0071] The focal length of an infrared camera is one of its core intrinsic parameters, representing the distance from the center of the lens to the imaging plane. This value is usually determined during camera manufacturing and can be obtained directly from the camera's product technical manual, hardware parameter configuration file, or dedicated testing equipment. This focal length parameter is a key factor affecting imaging quality and distance calculation accuracy. When cameras with different focal lengths photograph the same object, the pixel size of the object in the image will differ. Therefore, it is essential to accurately obtain the actual focal length value of the infrared camera being used to avoid deviations in subsequent distance calculations due to incorrect focal length parameters, ensuring the consistency and accuracy of parameters throughout the ranging process.

[0072] After obtaining the user's human pixel height and the infrared camera's focal length, and combining this with a preset reference value for the average actual height of the human body, the actual distance between the infrared camera and the user can be determined using distance calculation formulas related to optical imaging principles. In optical imaging, there is a fixed proportional relationship between the actual height of an object, the camera's focal length, the object's pixel height in the image, and the actual distance from the camera to the object. That is, the actual distance is directly proportional to the focal length, inversely proportional to the human pixel height, and also related to the average actual height of the human body. In specific calculations, the product of the camera's focal length and the average actual height of the human body is divided by the user's human pixel height to obtain the actual spatial distance between the infrared camera and the user. For example, if the average actual height of the human body is known to be 1.7 meters, the camera's focal length is 50 millimeters, and the calculated human pixel height is 85 pixels, then the actual distance is (50 × 1.7) ÷ 85 = 1 meter. Through this scientific calculation logic, the transformation from the image pixel dimension to the real spatial dimension is realized, ultimately obtaining accurate actual distance data.

[0073] This invention accurately calculates the pixel height of the human body using bounding box coordinates, combines this with accurately obtained camera focal length parameters, and scientifically derives the actual distance using optical imaging ratios. This enables precise and efficient measurement of the distance between the infrared camera and the user, effectively avoiding the errors and limitations of traditional ranging methods. It provides accurate distance parameters to support subsequent temperature compensation calculations, thereby improving the accuracy of actual temperature calculations for the user. This helps the air conditioning system better adapt to the different physical sensations of users in different positions in a shared space, significantly enhancing the targetedness and comfort of temperature regulation.

[0074] like Figure 2 This diagram illustrates an embodiment of the present invention for determining the distance between an infrared camera and a user. The infrared camera collects human image data streams, inputs the images into a YOLOv10 model for inference calculations, outputs a bounding box containing human position information, and then calculates the distance from the human body to the infrared camera using the principle of similar triangles. Figure 3 The diagram illustrates the principle of similar triangles. This proposal uses human height for subsequent calculations. Since different people have different heights, in practical applications, the average height in that scenario can be chosen as the calculation standard, denoted as W. The human pixel height is obtained by taking a picture of the object with a camera and measuring it. If the distance between the human body and the camera is D, then the formula for calculating the camera focal length F (this value is obtained through camera calibration) is: Formula (2) Using the above formula, the distance between the human body and the camera can be estimated as follows: Formula (3) This invention discloses a temperature measurement method that can simultaneously acquire a user's measured temperature and image using an infrared camera. By combining image analysis to determine the distance between the camera and the user, and then integrating the current ambient temperature to determine a temperature compensation value, the measured temperature is finally corrected based on the temperature compensation value to obtain the user's actual temperature. This effectively solves the problem that traditional air conditioning systems are difficult to accurately adapt to the differences in perceived temperature among individuals in a space where multiple people are together. It can more accurately perceive the real perceived temperature of different users, allowing the air conditioning system to flexibly adjust according to the actual temperature of each user, thereby meeting the comfort needs of different individuals in a multi-person co-occupancy scenario and improving the accuracy and adaptability of indoor temperature regulation.

[0075] like Figure 4 The diagram illustrates a flow chart of a temperature measurement method provided by an embodiment of the present invention. An infrared camera can be installed on an air conditioner to detect a human body frame. The size of the detected frame is used to perform geometric distance measurement based on the principle of similar triangles to calculate the distance between the camera and the human body. Then, a lemming temperature compensation model is constructed based on the collected historical data. The temperature measured by the infrared camera is compensated using the distance and the indoor ambient temperature to estimate the actual human body temperature, thereby enabling the air conditioner to adjust the temperature according to the human body.

[0076] like Figure 5 The diagram illustrates a flowchart of an air conditioner control method according to an embodiment of the present invention, which may include the following steps: Step 201: Acquire the user's measured temperature and image using an infrared camera.

[0077] Step 202: Determine the distance between the infrared camera and the user based on the image.

[0078] Step 203: Obtain the current ambient temperature.

[0079] Step 204: Determine the temperature compensation value based on the distance, ambient temperature, and the user's measured temperature.

[0080] Step 205: Determine the user's actual temperature based on the temperature compensation value and the user's measured temperature.

[0081] Step 206: Adjust the output temperature according to the user's actual temperature.

[0082] In this embodiment of the invention, the air conditioning control system can make a comprehensive judgment and adjustment based on the actual temperature of each user determined in step 205 and the needs of the scenario where multiple people are in the same space. If there are multiple users in the space, the actual temperature differences of different users can be taken into account. The comfort needs of each user can be balanced through algorithms, and parameters such as the output temperature, air supply direction or wind speed of the air conditioner can be dynamically adjusted. For example, the local output temperature can be appropriately reduced for user areas with higher actual temperatures, and the air supply strategy can be adjusted for user areas with lower actual temperatures, so as to achieve a precise match between the air conditioning output and the actual needs of users.

[0083] This air conditioning control method uses an infrared camera to collect user temperature measurements and images, combined with environmental parameters obtained from an ambient temperature sensor. Through a series of scientific processes, including distance calculation, temperature compensation, and actual temperature derivation, the air conditioning output is dynamically adjusted based on the user's actual temperature. This effectively solves the problem that traditional air conditioners rely on fixed settings or simple sensors, making it difficult to adapt to individual differences in body temperature in multi-person shared spaces. It significantly improves the accuracy of temperature sensing and the targeted nature of air conditioning adjustment, allowing the air conditioner to flexibly respond to users in different locations and with different body temperature needs. This significantly optimizes the indoor temperature environment in multi-person shared scenarios and comprehensively enhances the user's comfort experience.

[0084] Assuming there is only one user in the bedroom, after the air conditioner is turned on, it first uses an infrared camera to measure the user's temperature as 36.3℃, simultaneously capturing an image containing the user. Next, based on the image, it identifies the user's bounding box coordinates, calculates the human pixel height using the difference in the ordinate, and combines this with a preset average human height and the infrared camera's focal length, calculating the distance between the user and the camera using an optical scaling formula to be 1.8 meters. Then, the air conditioner's ambient temperature sensor collects the current indoor ambient temperature as 32℃. The distance, ambient temperature, and the user's measured temperature are then substituted into a temperature compensation model optimized using an artificial lemming algorithm, calculating a corresponding temperature compensation value of +0.9℃. This compensation value is then used to correct the measured temperature, resulting in the user's actual temperature of 37.2℃. Finally, based on this actual temperature, the air conditioner control system adjusts the initial output temperature from 26℃ to 23℃, ensuring the user experiences a precisely tailored and comfortable temperature.

[0085] This invention discloses an air conditioning control method that can simultaneously acquire the user's measured temperature and image using an infrared camera, determine the distance between the camera and the user by combining image analysis, determine a temperature compensation value by integrating the current ambient temperature, and finally correct the measured temperature based on the temperature compensation value to obtain the user's actual temperature. Finally, the air conditioner is controlled to adjust the output temperature according to the actual temperature. This effectively solves the problem that traditional air conditioning systems are difficult to accurately adapt to the differences in the perceived temperature of individuals in a space where multiple people are together. It can more accurately perceive the real perceived temperature of different users, allowing the air conditioning system to flexibly adjust according to the actual temperature of each user, thereby meeting the comfort needs of different individuals in a multi-person co-op scenario and improving the accuracy and adaptability of indoor temperature regulation.

[0086] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0087] like Figure 6 The diagram shows a structural block diagram of a temperature measuring device provided in an embodiment of the present invention. The device may include the following modules: The first acquisition module 301 is used to acquire the user's measured temperature and image through an infrared camera; The first determining module 302 is used to determine the distance between the infrared camera and the user based on the image; The second acquisition module 303 is used to acquire the current ambient temperature; The second determining module 304 is used to determine the temperature compensation value based on the distance, ambient temperature and the user's measured temperature; The third determining module 305 is used to determine the user's actual temperature based on the temperature compensation value and the user's measured temperature.

[0088] This invention discloses a temperature measuring device that can simultaneously acquire a user's measured temperature and image using an infrared camera. By combining image analysis to determine the distance between the camera and the user, and then integrating the current ambient temperature to determine a temperature compensation value, the device can finally correct the measured temperature based on the temperature compensation value to obtain the user's actual temperature. This effectively solves the problem that traditional air conditioning systems are difficult to accurately adapt to the differences in perceived temperature among individuals in a space where multiple people are together. It can more accurately perceive the real perceived temperature of different users, allowing the air conditioning system to flexibly adjust according to the actual temperature of each user, thereby meeting the comfort needs of different individuals in a multi-person co-occupancy scenario and improving the accuracy and adaptability of indoor temperature regulation.

[0089] In one embodiment of the present invention, the second determining module may include: The first determination submodule is used to determine the user's actual temperature based on distance, ambient temperature, and the user's measured temperature using an artificial lemming algorithm.

[0090] In one embodiment of the present invention, determining a submodule includes: The acquisition unit is used to acquire historical data, which includes the user's measured temperature, ambient temperature, and distance between the camera and the user under different conditions. The building unit is used to construct a temperature compensation function based on historical data, with the goal of minimizing the error between the user-compensated temperature and the actual temperature. The population building unit is used to form an initial lemming population based on the weight parameters of the temperature compensation function. Each lemming in the initial lemming population corresponds to a set of candidate weight parameter values. The iteration unit is used to iterate the initial lemming population until the preset conditions are met, and then output the target lemming population. The first determining unit is used to determine the optimal compensation coefficient in the target lemming population; The second determining unit is used to determine the temperature compensation value based on the distance, ambient temperature, user's measured temperature, and optimal temperature compensation coefficient.

[0091] In one embodiment of the present invention, the first determining unit includes: The first determining subunit is used to determine the mean square error of the weight parameter combination corresponding to each lemming in the target lemming population after substituting it into the temperature compensation function; The comparison unit is used to compare the mean square error of each lemming in the target lemming species and select the lemming with the smallest mean square error. The second determining subunit is used to combine the weight parameters corresponding to the lemming with the smallest mean square error and determine the optimal compensation coefficient.

[0092] In one embodiment of the present invention, the mean square error of the weighted parameter combination corresponding to each lemming is calculated by substituting it into the temperature compensation function using the following formula:

[0093] Where MSE refers to mean squared error, n is the number of samples in the historical data, and T (c，i） T is the compensated temperature calculated for the i-th sample using the corresponding weight parameter combination. （b，i） Let be the actual temperature corresponding to the i-th sample.

[0094] In one embodiment of the present invention, the iteration condition is that the number of iterations reaches a preset number.

[0095] In one embodiment of the present invention, the first determining module includes: The second determination submodule is used to determine the user's bounding box coordinates based on the image; The third determination submodule is used to determine the distance between the infrared camera and the user based on the bounding box coordinates.

[0096] In one embodiment of the present invention, the bounding box coordinates include the coordinates of the upper left corner of the human body and the coordinates of the lower right corner of the human body. The third determining submodule includes: The third determining subunit is used to determine the user's human body pixel height based on the coordinates of the upper left corner and the lower right corner of the human body; The acquisition subunit is used to acquire the camera focal length of the infrared camera; The fourth determining subunit is used to determine the distance between the infrared camera and the user based on the human body pixel height and the camera focal length.

[0097] This invention discloses a temperature measuring device that can simultaneously acquire a user's measured temperature and image using an infrared camera. By combining image analysis to determine the distance between the camera and the user, and then integrating the current ambient temperature to determine a temperature compensation value, the device can finally correct the measured temperature based on the temperature compensation value to obtain the user's actual temperature. This effectively solves the problem that traditional air conditioning systems are difficult to accurately adapt to the differences in perceived temperature among individuals in a space where multiple people are together. It can more accurately perceive the real perceived temperature of different users, allowing the air conditioning system to flexibly adjust according to the actual temperature of each user, thereby meeting the comfort needs of different individuals in a multi-person co-occupancy scenario and improving the accuracy and adaptability of indoor temperature regulation.

[0098] This invention also provides an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the various processes of the above-described temperature measurement method or air conditioning control method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0099] It should be noted that the electronic devices in the embodiments of the present invention include the mobile electronic devices and non-mobile electronic devices described above.

[0100] This invention also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described temperature measurement method or air conditioning control method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0101] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0102] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0108] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0109] The above provides a detailed description of the temperature measurement method, air conditioning control method, equipment, and medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A temperature measurement method, characterized in that, The method includes: The user's measured temperature and images are obtained through an infrared camera; Based on the image, determine the distance between the infrared camera and the user; Get the current ambient temperature; The temperature compensation value is determined based on the distance, the ambient temperature, and the user's measured temperature. The user's actual temperature is determined based on the temperature compensation value and the user's measured temperature.

2. The temperature measurement method according to claim 1, characterized in that, The step of determining the temperature compensation value based on the distance, the ambient temperature, and the user's measured temperature includes: The temperature compensation value is determined using the artificial lemming algorithm based on the distance, the ambient temperature, and the user's measured temperature.

3. The temperature measurement method according to claim 2, characterized in that, The process of determining a temperature compensation value using an artificial lemming algorithm, based on the distance, the ambient temperature, and the user's measured temperature, includes: Acquire historical data, including the user's measured temperature, ambient temperature, and distance between the camera and the user under different conditions; Based on the historical data, a temperature compensation function is constructed with the objective of minimizing the error between the user-compensated temperature and the actual temperature. An initial lemming population is constructed based on the weight parameters of the temperature compensation function, and each lemming in the initial lemming population corresponds to a set of candidate weight parameter values. The initial lemming population is iterated until a preset condition is met, and the target lemming population is output. Determine the optimal compensation coefficient in the target lemming population; The temperature compensation value is determined based on the distance, the ambient temperature, the user's measured temperature, and the optimal temperature compensation coefficient.

4. The temperature measurement method according to claim 3, characterized in that, Determining the optimal compensation coefficient in the target lemming population includes: The mean square error of the weighted parameter combination for each lemming in the target lemming population after being substituted into the temperature compensation function is determined. The mean square error of each lemming species in the target lemming species is compared, and the lemming with the smallest mean square error is selected. The combination of weight parameters corresponding to the lemming with the smallest mean square error is determined as the optimal compensation coefficient.

5. The temperature measurement method according to claim 4, characterized in that, The mean squared error of each lemming's weighted parameter combination, after being substituted into the temperature compensation function, is calculated using the following formula: Where MSE refers to mean squared error, n is the number of samples in the historical data, and T (c，i) T is the compensated temperature calculated for the i-th sample using the corresponding weight parameter combination. （b，i） Let be the actual temperature corresponding to the i-th sample.

6. The temperature measurement method according to claim 3, characterized in that, The iteration condition is that the number of iterations reaches a preset number.

7. The temperature measurement method according to claim 1, characterized in that, Determining the distance between the infrared camera and the user based on the image includes: Based on the image, determine the bounding box coordinates of the user; The distance between the infrared camera and the user is determined based on the bounding box coordinates.

8. The temperature measurement method according to claim 7, characterized in that, The bounding box coordinates include the coordinates of the upper left corner of the human body and the coordinates of the lower right corner of the human body. Determining the distance between the infrared camera and the user based on the bounding box coordinates includes: The user's human body pixel height is determined based on the coordinates of the upper left corner and the lower right corner of the human body. Obtain the camera focal length of the infrared camera; The distance between the infrared camera and the user is determined based on the human body pixel height and the camera focal length.

9. A method for controlling an air conditioner, characterized in that, The method includes: The user's measured temperature and images are obtained through an infrared camera; Based on the image, determine the distance between the infrared camera and the user; Get the current ambient temperature; The temperature compensation value is determined based on the distance, the ambient temperature, and the user's measured temperature. The user's actual temperature is determined based on the temperature compensation value and the user's measured temperature. Adjust the output temperature according to the user's actual temperature.

10. A temperature measuring device, characterized in that, The device includes: The first acquisition module is used to acquire the user's measured temperature and images via an infrared camera; The first determining module is used to determine the distance between the infrared camera and the user based on the image; The second acquisition module is used to acquire the current ambient temperature; The second determining module is used to determine a temperature compensation value based on the distance, the ambient temperature, and the user's measured temperature. The third determining module is used to determine the user's actual temperature based on the temperature compensation value and the user's measured temperature.

11. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the temperature measurement method as described in claims 1-8 or the air conditioning control method as described in claim 9.

12. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the temperature measurement method as described in claims 1-8 or the air conditioning control method as described in claim 8.

Images