Air conditioner intelligent health monitoring system and method

Abstract

The application relates to the field of household appliances, and provides an air conditioner intelligent health monitoring system and method.The system comprises a temperature acquisition module, which acquires infrared radiation of a human body surface in a room to obtain a temperature image; a main control processing module, which performs health detection according to the temperature image to obtain a health detection result; and an early warning feedback module, which generates early warning information according to an abnormal temperature part based on the health detection result, and sends the early warning information to a user end to perform early warning prompting.The application solves the defects of lacking precise health management due to the monitoring and adjustment depending on environmental parameters, realizes rapid health detection by monitoring the temperature change of the human body surface in the room, and provides strong technical support for health safety.

Description

Technical Field

[0001] This invention relates to the field of household appliance technology, and in particular to an intelligent health monitoring system and method for air conditioners. Background Technology

[0002] Since its invention in the early 20th century, air conditioners have evolved from simple cooling to comprehensive temperature control, and from manual operation to intelligent interconnection, gradually becoming an indispensable home appliance in modern life. With the increasing demand for healthy living, smart air conditioners have begun to integrate functions that monitor people's health.

[0003] Currently, air conditioners mainly create a healthy and comfortable indoor environment for users by monitoring indoor air quality, temperature, humidity, etc., and some smart air conditioners can also remind users to replace air filters, etc.

[0004] However, this monitoring method mainly relies on the monitoring and regulation of environmental parameters, lacking direct monitoring of individual physiological conditions, and has certain shortcomings in terms of accuracy and personalized health management. Summary of the Invention

[0005] This invention provides an intelligent health monitoring system and method for air conditioning, which addresses the shortcomings of existing technologies that rely on monitoring and adjusting environmental parameters, resulting in a lack of precise health management. By monitoring changes in indoor human body surface temperature, it achieves rapid health detection, providing strong technical support for health and safety.

[0006] This invention provides an intelligent health monitoring system for air conditioning, comprising: a temperature acquisition module for acquiring infrared radiation from the human body surface indoors to obtain a temperature image; a main control processing module for performing health detection based on the temperature image to obtain health detection results; and an early warning feedback module for generating early warning information based on the health detection results indicating the presence of abnormal temperature locations, and sending the early warning information to the user terminal for early warning notification.

[0007] It should be noted that by collecting infrared radiation from the human body surface indoors, changes in body temperature can be monitored. By analyzing the detected temperature images, abnormal temperature changes can be detected in a timely manner, which helps to identify potential health problems early and provides timely warnings when abnormal temperature areas are detected. While achieving rapid health detection, it also allows users to understand their own health status in a timely manner, providing strong technical support for health and safety, and improving people's health management level.

[0008] According to the present invention, an intelligent health monitoring system for air conditioning includes a main control processing module comprising: a feature extraction unit for extracting features from a temperature image to obtain a temperature feature map; an image segmentation unit for separating human body parts from the image background in the temperature image based on the temperature feature map using a preset segmentation algorithm to obtain a human body temperature feature map; a target detection unit for performing target detection on the human body temperature feature map to obtain a body part detection result; and a health detection unit for performing temperature detection on the human body temperature feature map based on the body part detection result to determine whether there is a health risk and obtain a health detection result.

[0009] It should be noted that the feature extraction unit quickly identifies and extracts important features from the temperature image to provide key information for subsequent processing; the image segmentation unit accurately separates human body parts from the background to reduce background interference and improve the accuracy of subsequent analysis; the target detection unit accurately identifies different parts of the human body to provide location information for health detection; and the health detection unit combines the body part detection results with the human body temperature feature map to comprehensively assess the human body's health status.

[0010] According to the present invention, an intelligent health monitoring system for air conditioning includes a health detection unit comprising: a temperature detection subunit, which performs temperature detection on a human body temperature characteristic map based on the detection results of body parts to obtain the temperature distribution characteristics of each body part; and a health detection subunit, which determines whether the temperature distribution characteristics of each body part exceed the corresponding preset temperature threshold based on the temperature distribution characteristics of each body part and the preset temperature threshold for the corresponding body part. If the temperature distribution characteristics exceed the preset temperature threshold, the health detection result is determined to indicate that there is a health risk in the corresponding body part; otherwise, the health detection result is determined to indicate that there is no health risk in the corresponding body part.

[0011] It should be noted that the temperature detection unit performs temperature detection on the human body temperature distribution characteristic map based on the detection results of body parts. This allows the health detection subunit to accurately determine whether the corresponding temperature is abnormal in combination with the body parts, thereby facilitating the timely detection of health problems in body parts and realizing personalized detection of health risks in different parts.

[0012] According to the present invention, an intelligent health monitoring system for air conditioning includes a target detection unit comprising: a key point detection subunit for detecting key points in a human body temperature feature map to obtain key point detection results; a temperature distribution recognition subunit for recognizing local temperatures at key points in the human body temperature feature map based on the key point detection results to obtain local temperature distribution results at key points; a feature matching subunit for matching the local temperature distribution results at key points with local temperature distribution features at key points in a preset template library to obtain matching results; and a target detection subunit for, based on the matching results indicating successful key point matching, using the corresponding key point as a seed point and employing a preset region growing algorithm to divide the human body temperature feature map into body parts to obtain body part detection results.

[0013] It should be noted that key point detection is performed by the key point detection subunit so that the temperature distribution recognition subunit can identify the local temperature distribution of the key points based on the detected key points. This allows for more accurate identification and location of various parts of the human body. Furthermore, by matching the local temperature distribution of key points, the accuracy of part identification is improved. Then, based on the successfully matched key points, the region growing algorithm is used to divide the body parts, thereby effectively expanding from key points to the entire body parts and improving the efficiency and completeness of detection.

[0014] According to the present invention, an intelligent health monitoring system for air conditioning includes an image segmentation unit comprising: a threshold determination subunit, which selects a preset threshold as a segmentation threshold, or obtains an adaptive threshold based on temperature characteristics using the maximum inter-class variance method or the minimum intra-class variance method, and uses this threshold as a segmentation threshold; a pixel classification subunit, which compares the temperature value corresponding to each pixel in the temperature feature map with the segmentation threshold, and if the temperature value corresponding to the pixel is greater than the segmentation threshold, classifies the corresponding pixel as a foreground pixel; otherwise, classifies the corresponding pixel as a background pixel; and an image segmentation subunit, which performs image segmentation on the temperature feature map based on the foreground pixels and background pixels to obtain a human body temperature feature map corresponding to the foreground pixels.

[0015] It should be noted that the threshold determination subunit selects a preset threshold or an adaptive threshold obtained using the maximum inter-class variance method, and the pixel classification subunit quickly classifies all pixels according to the threshold selected by the threshold determination subunit to ensure the efficiency of the entire segmentation process. Thus, the image segmentation subunit generates clear foreground and background separation based on accurate threshold determination and pixel classification, improving the accuracy of subsequent analysis. This allows subsequent target detection and health detection to focus on the analysis of human body parts, reducing computational complexity and processing time.

[0016] According to the present invention, an intelligent health monitoring system for air conditioning includes a threshold determination subunit, comprising: a statistical subunit, which determines the number of pixels corresponding to each temperature value based on a temperature feature map, and obtains a histogram, wherein each element in the histogram represents the number of pixels corresponding to the temperature value in the temperature feature map; a mean determination subunit, which determines the global temperature mean based on the histogram; and an initialization configuration subunit, which initializes the number of background pixels based on the number of pixels in all elements of the histogram, initializes the mean of background pixels based on the global temperature mean, and initializes the number of foreground pixels, the mean of foreground pixels, the variance of foreground pixels, and the variance of background pixels. The initial threshold is 0; the data processing subunit iterates through the temperature values ​​corresponding to each element in the histogram, uses the iterated temperature value as the current threshold, compares the temperature values ​​corresponding to the remaining elements with the current threshold, updates the number of foreground pixels, the mean foreground pixels, the number of background pixels, and the mean background pixels, and determines the intra-class variance or inter-class variance corresponding to the current threshold based on the updated number of foreground pixels, the mean foreground pixels, the number of background pixels, and the mean background pixels; the threshold determination subunit selects the threshold corresponding to the minimum intra-class variance or the maximum inter-class variance based on the intra-class variance or inter-class variance corresponding to the current threshold, and uses it as the adaptive threshold.

[0017] It should be noted that by statistically analyzing and calculating the histogram features of the image, initializing, traversing, and iteratively updating the statistical information of the foreground and background pixels, the adaptive threshold can be automatically adjusted according to the specific features of the temperature feature map. Furthermore, by calculating the intra-class or inter-class variance, the optimal threshold can be selected in the presence of noise, reducing the impact of noise on the segmentation results. This provides an accurate adaptive threshold for image segmentation, achieving effective separation of the foreground and background, improving the accuracy of image segmentation, and thus significantly improving the performance and practicality of the entire health monitoring system.

[0018] According to the present invention, an intelligent health monitoring system for air conditioning includes a temperature acquisition module comprising: an infrared sensor array unit for acquiring infrared radiation from the human body surface in an indoor target area to obtain an infrared temperature signal; a signal conditioning and amplification unit for amplifying and filtering the infrared temperature signal to obtain a conditioned and amplified signal; an analog-to-digital conversion unit for performing analog-to-digital conversion on the conditioned and amplified signal to obtain a digital temperature signal; and an image processing unit for setting the pixels in the corresponding indoor target area to the corresponding grayscale value according to the digital temperature signal and the corresponding indoor target area to obtain a temperature image.

[0019] It should be noted that the infrared sensor array unit accurately captures temperature changes on the human body surface, providing a reliable data foundation for subsequent health monitoring. The signal conditioning and amplification unit amplifies and filters the signal to improve its stability and signal-to-noise ratio, ensuring the accuracy of the temperature data. The analog-to-digital conversion unit converts the analog infrared signal into a digital signal, making the signal easier to store, transmit, and process, and less susceptible to external interference. The temperature image generated by the image processing unit intuitively displays the temperature distribution on the human body surface, facilitating the rapid identification of abnormal temperature areas and laying a solid data foundation for intelligent health monitoring and early warning.

[0020] According to the present invention, an intelligent health monitoring system for air conditioning includes a main control processing module, which further includes a data preprocessing unit for preprocessing the temperature image before performing health detection based on the temperature image. The preprocessing includes at least one of noise filtering and temperature calibration.

[0021] It should be noted that by preprocessing the temperature image to improve the signal-to-noise ratio, the temperature data becomes more accurate, providing a clear and accurate temperature image for subsequent health monitoring. This improves the accuracy of the entire health monitoring process, reduces false alarms caused by image noise or calibration deviations, and enhances the reliability of the system.

[0022] According to the present invention, an intelligent health monitoring system for air conditioning includes an early warning feedback module comprising: an early warning information generation unit, which generates early warning information based on the presence of abnormal temperature locations in a health monitoring result, according to the abnormal temperature locations and corresponding abnormal temperature differences, and in conjunction with preset early warning information generation rules; wherein, the preset early warning information generation rules are used to limit the alarm methods adopted for different body parts and their corresponding abnormal temperature differences; and a feedback unit, which sends the early warning information to the user terminal to remind the user according to the alarm method corresponding to the early warning information.

[0023] It should be noted that the early warning information generation unit generates corresponding early warning information based on the location of abnormal temperature and the corresponding abnormal temperature difference, combined with preset early warning information generation rules, according to the importance of different body parts and the severity of abnormal temperature differences. The user is then notified through the feedback unit, enabling the user to understand their own health status in a timely manner, enhancing the user's attention to and participation in their own health, and promoting the formation of a healthy lifestyle.

[0024] The present invention also provides an intelligent health monitoring method for air conditioners, comprising: collecting infrared radiation from the surface of a human body indoors to obtain a temperature image; performing health detection based on the temperature image to obtain a health detection result; generating early warning information based on the presence of abnormal temperature areas according to the health detection result, and sending the early warning information to the user terminal for early warning notification.

[0025] It should be noted that by collecting infrared radiation from the human body surface indoors, changes in body temperature can be monitored. By analyzing the detected temperature images, abnormal temperature changes can be detected in a timely manner, which helps to identify potential health problems early and provides timely warnings when abnormal temperature areas are detected. While achieving rapid health detection, it also allows users to understand their own health status in a timely manner, providing strong technical support for health and safety, and improving people's health management level.

[0026] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-described intelligent health monitoring methods for air conditioning.

[0027] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described intelligent health monitoring methods for air conditioning. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0029] Figure 1 This is one of the structural schematic diagrams of the intelligent health monitoring system for air conditioning provided by the present invention; Figure 2 This is the second structural schematic diagram of the intelligent health monitoring system for air conditioning provided by the present invention; Figure 3 This is a flowchart illustrating the intelligent health monitoring method for air conditioners provided by the present invention; Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this 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 this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0031] The following is combined Figures 1 to 2 A schematic diagram illustrating the structure of an intelligent health monitoring system for air conditioning according to the present invention is shown below. Figure 1 The system includes: Temperature acquisition module 11 acquires infrared radiation from the human body surface indoors to obtain temperature images; The main control processing module 12 performs health detection based on the temperature image and obtains the health detection results; The early warning feedback module 13 generates early warning information based on the health detection results indicating the presence of abnormal temperature areas, and sends the early warning information to the user terminal for early warning notification.

[0032] In this embodiment, the temperature acquisition module 11 includes: an infrared sensor array unit for acquiring infrared radiation from the human body surface in an indoor target area to obtain an infrared temperature signal; a signal conditioning and amplification unit for amplifying and filtering the infrared temperature signal to obtain a conditioned and amplified signal; an analog-to-digital conversion unit for performing analog-to-digital conversion on the conditioned and amplified signal to obtain a digital temperature signal; and an image processing unit for setting the pixels in the corresponding indoor target area to the corresponding grayscale value according to the digital temperature signal and the corresponding indoor target area to obtain a temperature image.

[0033] It should be noted that the infrared sensor array unit accurately captures temperature changes on the human body surface, providing a reliable data foundation for subsequent health monitoring. The signal conditioning and amplification unit amplifies and filters the signal to improve its stability and signal-to-noise ratio, ensuring the accuracy of the temperature data. The analog-to-digital conversion unit converts the analog infrared signal into a digital signal, making the signal easier to store, transmit, and process, and less susceptible to external interference. The temperature image generated by the image processing unit intuitively displays the temperature distribution on the human body surface, facilitating the rapid identification of abnormal temperature areas and laying a solid data foundation for intelligent health monitoring and early warning.

[0034] It should be added that the temperature acquisition module can take full advantage of the location of the air conditioning unit, being installed inside the indoor unit to capture the body surface temperature of people indoors. Additionally, the infrared sensor array unit includes a high-resolution infrared sensor array to capture body surface temperature, with a resolution accurate to 0.1℃, thereby improving detection accuracy.

[0035] Furthermore, the temperature acquisition module can continuously acquire temperature data according to a preset sampling frequency and transmit the data to the main control processing module at certain time intervals. The preset sampling frequency can be set according to health monitoring needs or user habits, and is not further limited here.

[0036] In one alternative embodiment, reference Figure 2 The temperature acquisition module 11 also includes a power supply regulator unit, which provides power and regulates the voltage for the infrared sensor array unit, the signal conditioning and amplification unit and the analog-to-digital conversion unit.

[0037] In addition, the main control processing module 12 includes: a feature extraction unit, which extracts features from the temperature image to obtain a temperature feature map; an image segmentation unit, which separates the human body parts in the temperature image from the image background using a preset segmentation algorithm based on the temperature feature map to obtain a human body temperature feature map; a target detection unit, which performs target detection on the human body temperature feature map to obtain body part detection results; and a health detection unit, which performs temperature detection on the human body temperature feature map based on the body part detection results to determine whether there is a health risk and obtain health detection results.

[0038] It should be noted that the feature extraction unit quickly identifies and extracts important features from the temperature image to provide key information for subsequent processing; the image segmentation unit accurately separates human body parts from the background to reduce background interference and improve the accuracy of subsequent analysis; the target detection unit accurately identifies different parts of the human body to provide location information for health detection; and the health detection unit combines the body part detection results with the human body temperature feature map to comprehensively assess the human body's health status.

[0039] In addition, the main control processing module can use a microprocessor to integrate data processing and control functions, and connect to the temperature acquisition module through a high-speed data bus, while controlling communication and early warning feedback.

[0040] Specifically, the image segmentation unit includes: a threshold determination subunit, which selects a preset threshold as the segmentation threshold, or obtains an adaptive threshold based on temperature features using the maximum inter-class variance method or the minimum intra-class variance method, and uses it as the segmentation threshold; a pixel classification subunit, which compares the temperature value corresponding to each pixel in the temperature feature map with the segmentation threshold. If the temperature value corresponding to the pixel is greater than the segmentation threshold, the corresponding pixel is classified as a foreground pixel; otherwise, the corresponding pixel is classified as a background pixel; and an image segmentation subunit, which performs image segmentation on the temperature feature map based on the foreground pixels and background pixels to obtain the human body temperature feature map corresponding to the foreground pixels.

[0041] It should be noted that the threshold determination subunit selects a preset threshold or an adaptive threshold obtained using the maximum inter-class variance method, and the pixel classification subunit quickly classifies all pixels based on the threshold selected by the threshold determination subunit. This ensures the efficiency of the entire segmentation process. Thus, by using precise threshold determination and pixel classification, the image segmentation subunit generates clear foreground and background separation, improving the accuracy of subsequent analysis. This allows subsequent target detection and health detection to focus on the analysis of human body parts, reducing computational complexity and processing time. Furthermore, the preset threshold can be configured based on human body temperature distribution characteristics or prior experience; the specific setting can be tailored to actual needs and is not further limited here.

[0042] Further, the threshold determination subunit includes: a statistical subunit, which determines the number of pixels corresponding to each temperature value based on the temperature feature map, and obtains a histogram, where each element in the histogram represents the number of pixels corresponding to the temperature value in the temperature feature map; a mean determination subunit, which determines the global temperature mean based on the histogram; an initialization configuration subunit, which initializes the number of background pixels based on the number of pixels in all elements of the histogram, initializes the mean of background pixels based on the global temperature mean, and initializes the number of foreground pixels, the mean of foreground pixels, the variance of foreground pixels, and the variance of background pixels to 0; and a data processing subunit. The first unit iterates through the temperature values ​​corresponding to each element in the histogram, uses the iterated temperature value as the current threshold, and compares the temperature values ​​corresponding to the remaining elements with the current threshold. It then updates the number of foreground pixels, the mean foreground pixels, the number of background pixels, and the mean background pixels. Based on the updated number of foreground pixels, the mean foreground pixels, the number of background pixels, and the mean background pixels, it determines the intra-class variance or inter-class variance corresponding to the current threshold. The second unit determines the threshold by selecting the threshold corresponding to the minimum intra-class variance or the maximum inter-class variance based on the intra-class variance or inter-class variance corresponding to the current threshold, and using this as the adaptive threshold.

[0043] It should be noted that by statistically analyzing and calculating the histogram features of the image, initializing, traversing, and iteratively updating the statistical information of the foreground and background pixels, the adaptive threshold can be automatically adjusted according to the specific features of the temperature feature map. Furthermore, by calculating the intra-class or inter-class variance, the optimal threshold can be selected in the presence of noise, reducing the impact of noise on the segmentation results. This provides an accurate adaptive threshold for image segmentation, achieving effective separation of the foreground and background, improving the accuracy of image segmentation, and thus significantly improving the performance and practicality of the entire health monitoring system.

[0044] In addition, the target detection unit includes: a key point detection subunit, which performs key point detection on the human body temperature feature map to obtain key point detection results; a temperature distribution recognition subunit, which performs local temperature recognition on key points on the human body temperature feature map based on the key point detection results to obtain local temperature distribution results for key points; a feature matching subunit, which matches the local temperature distribution results of key points with the local temperature distribution features of key points in a preset template library to obtain matching results; and a target detection subunit, which, based on the matching results showing that the key point matching is successful, uses the corresponding key point as a seed point and uses a preset region growing algorithm to divide the human body temperature feature map into body parts to obtain body part detection results.

[0045] It should be noted that key point detection is performed by the key point detection subunit so that the temperature distribution recognition subunit can identify the local temperature distribution of the key points based on the detected key points. This allows for more accurate identification and location of various parts of the human body. Furthermore, by matching the local temperature distribution of key points, the accuracy of part identification is improved. Then, based on the successfully matched key points, the region growing algorithm is used to divide the body parts, thereby effectively expanding from key points to the entire body parts and improving the efficiency and completeness of detection.

[0046] Furthermore, the target detection unit also includes a post-processing subunit, which can either ignore the corresponding key point if the key point is not matched successfully, or mark the corresponding key point for subsequent manual review or other processing. The specific settings can be configured according to actual design requirements, and no further limitations are made here.

[0047] In addition, the health detection unit includes: a temperature detection subunit, which performs temperature detection on the human body temperature characteristic map based on the detection results of body parts to obtain the temperature distribution characteristics of each body part; and a health detection subunit, which determines whether the temperature distribution characteristics of each body part exceed the corresponding preset temperature threshold based on the temperature distribution characteristics of each body part and the preset temperature threshold of the corresponding body part. If it exceeds the preset temperature threshold, the health detection result is determined to be that there is a health risk in the corresponding body part; otherwise, the health detection result is determined to be that there is no health risk in the corresponding body part.

[0048] It should be noted that the temperature detection unit performs temperature detection based on the body part detection results, analyzing the human body temperature distribution characteristic map. This allows the health detection subunit to accurately determine whether the corresponding temperature is abnormal, facilitating the timely detection of health problems in different body parts and enabling personalized health risk detection for different areas. Furthermore, the preset temperature threshold can be set based on the critical values ​​between normal and abnormal temperatures for the corresponding body part; this will not be further elaborated upon here.

[0049] In an optional embodiment, the main control processing module further includes: a data preprocessing unit, which preprocesses the temperature image before performing health detection based on the temperature image, the preprocessing including at least one of noise filtering and temperature calibration.

[0050] It should be noted that by preprocessing the temperature image to improve the signal-to-noise ratio, the temperature data becomes more accurate, providing a clear and accurate temperature image for subsequent health monitoring. This improves the accuracy of the entire health monitoring process, reduces false alarms caused by image noise or calibration deviations, and enhances the reliability of the system.

[0051] In one optional embodiment, the early warning feedback module 13 includes: an early warning information generation unit, which generates early warning information based on the health detection result indicating the presence of an abnormal temperature location, according to the abnormal temperature location and the corresponding abnormal temperature difference, and in conjunction with preset early warning information generation rules; wherein, the preset early warning information generation rules are used to restrict the alarm methods adopted for different body parts and their corresponding abnormal temperature differences; and a feedback unit, which sends the early warning information to the user terminal to remind the user according to the alarm method corresponding to the early warning information.

[0052] It should be noted that the early warning information generation unit generates corresponding early warning information based on the location of abnormal temperature and the corresponding abnormal temperature difference, combined with preset early warning information generation rules, according to the importance of different body parts and the severity of abnormal temperature differences. The user is then notified through the feedback unit, enabling the user to understand their own health status in a timely manner, enhancing the user's attention to and participation in their own health, and promoting the formation of a healthy lifestyle.

[0053] It should be added that the early warning information generation unit is also used to generate a health alert message based on the health detection results indicating that there are no abnormal temperature areas, and send it to the user terminal using the feedback unit.

[0054] Furthermore, the preset warning information generation rules can be customized according to different users' needs and preferences, providing personalized alarm services. For example, if the temperature of a certain part of the body is abnormal, but the abnormal temperature difference is small, only a prompt message can be generated and sent to the user's terminal. If the abnormal temperature difference is large, a voice alarm can also be generated and sent to the user's terminal at the same time. The specific configuration can be based on actual user needs, and no further limitations are made here. In addition, the warning feedback module can initiate the transmission of warning signals within milliseconds, so that users can know about abnormal body temperature as soon as possible, thereby ensuring the real-time nature of message reminders.

[0055] In an optional embodiment, the system can communicate with the user terminal via a wireless network or Bluetooth to facilitate the transmission and feedback of early warning information.

[0056] In an optional embodiment, the system further includes a storage management module that stores temperature images, health detection results, and / or early warning information in local storage or uploads them to a cloud platform to facilitate subsequent statistical analysis of health data.

[0057] In summary, this invention collects infrared radiation from the surface of the human body indoors to monitor changes in body temperature. By detecting the obtained temperature images, abnormal temperature changes can be detected in a timely manner, which helps to identify potential health problems early and provides timely warnings when abnormal temperature areas are detected. This enables rapid health detection and allows users to understand their own health status in a timely manner, providing strong technical support for health and safety and improving people's health management level.

[0058] The intelligent health monitoring method for air conditioners provided by this invention is described below. The intelligent health monitoring method for air conditioners described below can be referred to in correspondence with the intelligent health monitoring system for air conditioners described above.

[0059] Figure 3 A flowchart illustrating an intelligent health monitoring method for air conditioners is shown. The method includes: S31 collects infrared radiation from the human body surface indoors to obtain temperature images; S32, perform health detection based on temperature image to obtain health detection results; S33, based on the health detection results indicating the presence of abnormal temperature areas, generates early warning information according to the abnormal temperature areas and sends the early warning information to the user terminal for early warning notification.

[0060] It should be noted that the step numbers "S31-S33" in this specification do not represent the order of the air conditioner intelligent health monitoring method. The air conditioner intelligent health monitoring method of the present invention will be described in detail below.

[0061] Step S31: Collect infrared radiation from the human body surface indoors to obtain a temperature image.

[0062] In this embodiment, acquiring infrared radiation from the human body surface indoors to obtain a temperature image includes: acquiring infrared radiation from the human body surface of a target area indoors to obtain an infrared temperature signal; amplifying and filtering the infrared temperature signal to obtain a conditioned and amplified signal; performing analog-to-digital conversion on the conditioned and amplified signal to obtain a digital temperature signal; and setting the pixels in the corresponding target area indoors to the corresponding grayscale value according to the digital temperature signal based on the digital temperature signal to obtain a temperature image.

[0063] In one alternative embodiment, the method of acquiring infrared radiation from the human body surface indoors to obtain a temperature image also includes: a power supply and voltage regulation circuit.

[0064] Step S32: Perform health detection based on the temperature image to obtain the health detection result.

[0065] Specifically, health detection based on temperature images to obtain health detection results includes: extracting features from the temperature images to obtain temperature feature maps; using a preset segmentation algorithm based on the temperature feature maps to separate human body parts from the image background in the temperature images to obtain human body temperature feature maps; performing target detection on the human body temperature feature maps to obtain body part detection results; and performing temperature detection on the human body temperature feature maps based on the body part detection results to determine whether there are any health risks, thereby obtaining health detection results.

[0066] Furthermore, based on the temperature feature map, a preset segmentation algorithm is used to separate the human body parts in the temperature image from the image background to obtain a human body temperature feature map. This includes: selecting a preset threshold as a segmentation threshold, or, based on the temperature features, using the maximum inter-class variance method or the minimum intra-class variance method to obtain an adaptive threshold as a segmentation threshold; comparing the temperature value corresponding to each pixel in the temperature feature map with the segmentation threshold; if the temperature value corresponding to a pixel is greater than the segmentation threshold, the corresponding pixel is classified as a foreground pixel; otherwise, the corresponding pixel is classified as a background pixel; and performing image segmentation on the temperature feature map based on the foreground and background pixels to obtain the human body temperature feature map corresponding to the foreground pixels.

[0067] Further, based on the temperature characteristics, an adaptive threshold is obtained using either the maximum inter-class variance method or the minimum intra-class variance method. This includes: determining the number of pixels corresponding to each temperature value based on the temperature feature map, obtaining a histogram, where each element in the histogram represents the number of pixels corresponding to the temperature value in the temperature feature map; determining the global temperature mean based on the histogram; initializing the number of background pixels based on the number of pixels in all elements of the histogram, initializing the background pixel mean based on the global temperature mean, and initializing the number of foreground pixels, the foreground pixel mean, the foreground pixel variance, and the background pixel variance to 0; traversing the temperature values ​​corresponding to each element in the histogram, using the traversed temperature values ​​as the current threshold, and comparing the temperature values ​​corresponding to the remaining elements with the current threshold, updating the number of foreground pixels, the foreground pixel mean, the number of background pixels, and the background pixel mean, and determining the intra-class variance or inter-class variance corresponding to the current threshold based on the updated number of foreground pixels, the foreground pixel mean, the background pixel number, and the background pixel mean; and selecting the threshold corresponding to the minimum intra-class variance or the maximum inter-class variance as the adaptive threshold based on the intra-class variance or inter-class variance corresponding to the current threshold.

[0068] In addition, target detection is performed on the human body temperature feature map to obtain body part detection results, including: key point detection on the human body temperature feature map to obtain key point detection results; based on the key point detection results, local temperature recognition of key points is performed on the human body temperature feature map to obtain local temperature distribution results of key points; the local temperature distribution results of key points are matched with the local temperature distribution features of key points in a preset template library to obtain matching results; if the matching result shows that the key point is successfully matched, the corresponding key point is used as a seed point, and a preset region growing algorithm is used to divide the human body temperature feature map into body parts to obtain body part detection results.

[0069] Furthermore, target detection is performed on the human body temperature feature map to obtain the body part detection results. This also includes: ignoring the corresponding key point based on the failure of the key point match, or marking the corresponding key point for subsequent manual review or other processing, etc. The specific settings can be set according to the actual design requirements, and no further limitations are made here.

[0070] In addition, based on the body part detection results, temperature detection is performed on the human body temperature characteristic map to determine whether there is a health risk, and the health detection results are obtained, including: based on the body part detection results, temperature detection is performed on the human body temperature characteristic map to obtain the temperature distribution characteristics of each body part; based on the temperature distribution characteristics of each body part and the corresponding preset temperature threshold, it is determined whether the temperature distribution characteristics of the body part exceed the corresponding preset temperature threshold. If it exceeds the threshold, the health detection result is determined that there is a health risk in the corresponding body part; otherwise, the health detection result is determined that there is no health risk in the corresponding body part.

[0071] In one alternative embodiment, prior to performing health checks based on the temperature image, the method further includes preprocessing the temperature image, the preprocessing including at least one of noise filtering and temperature calibration.

[0072] Step S33: Based on the health detection results indicating the presence of abnormal temperature areas, generate early warning information according to the abnormal temperature areas, and send the early warning information to the user terminal for early warning notification.

[0073] In this embodiment, an early warning message is generated based on the location of the abnormal temperature and sent to the user terminal for early warning notification. This includes: generating an early warning message based on the health detection result indicating the presence of an abnormal temperature location, the location of the abnormal temperature, and the corresponding abnormal temperature difference, combined with a preset early warning message generation rule; wherein, the preset early warning message generation rule is used to restrict the alarm methods for different body parts and their corresponding abnormal temperature differences; and sending the early warning message to the user terminal to remind the user according to the alarm method corresponding to the early warning message.

[0074] It should be added that generating early warning information based on abnormal temperature locations and sending the early warning information to the user's terminal also includes: generating a health alert message based on the health detection results indicating that there are no abnormal temperature locations and sending it to the user's terminal.

[0075] In an optional embodiment, the method further includes: storing temperature images, health detection results, and / or early warning information in local storage or uploading them to a cloud platform to facilitate subsequent statistical analysis of health data.

[0076] In summary, this invention collects infrared radiation from the surface of the human body indoors to monitor changes in body temperature. By detecting the obtained temperature images, abnormal temperature changes can be detected in a timely manner, which helps to identify potential health problems early and provides timely warnings when abnormal temperature areas are detected. This enables rapid health detection and allows users to understand their own health status in a timely manner, providing strong technical support for health and safety and improving people's health management level.

[0077] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 410, a communication interface 420, a memory 430, and a communication bus 440. The processor 410, communication interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions stored in the memory 430 to execute an intelligent health monitoring method for air conditioning. This method includes: collecting infrared radiation from the human body surface indoors to obtain a temperature image; performing health detection based on the temperature image to obtain health detection results; and generating early warning information based on the presence of abnormal temperature areas according to the health detection results, and sending the early warning information to the user terminal for alert.

[0078] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, 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 personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0079] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer can execute the air conditioning intelligent health monitoring method provided by the above methods, the method including: collecting infrared radiation from the surface of a human body indoors to obtain a temperature image; performing health detection based on the temperature image to obtain a health detection result; generating early warning information based on the presence of an abnormal temperature area according to the health detection result, and sending the early warning information to the user terminal for early warning prompt.

[0080] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the aforementioned intelligent health monitoring methods for air conditioning. The method includes: collecting infrared radiation from the surface of a human body indoors to obtain a temperature image; performing health detection based on the temperature image to obtain a health detection result; generating early warning information based on the presence of an abnormal temperature location according to the health detection result; and sending the early warning information to the user terminal for early warning notification.

[0081] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0082] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, 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 can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent health monitoring system for air conditioning, characterized in that, include: The temperature acquisition module collects infrared radiation from the human body surface indoors to obtain a temperature image. The main control processing module performs health detection based on the temperature image and obtains the health detection result; The early warning feedback module generates early warning information based on the health detection results indicating the presence of abnormal temperature areas, and sends the early warning information to the user terminal for early warning notification.

2. The intelligent health monitoring system for air conditioning according to claim 1, characterized in that, The main control processing module includes: The feature extraction unit extracts features from the temperature image to obtain a temperature feature map. The image segmentation unit, based on the temperature feature map, uses a preset segmentation algorithm to separate the human body parts in the temperature image from the image background to obtain the human body temperature feature map; The target detection unit performs target detection on the human body temperature feature map to obtain the body part detection result; The health detection unit performs temperature detection on the human body temperature characteristic map based on the detection results of the body parts to determine whether there is a health risk and obtain the health detection result.

3. The intelligent health monitoring system for air conditioning according to claim 2, characterized in that, The health detection unit includes: The temperature detection subunit performs temperature detection on the human body temperature feature map based on the detection results of the body parts, and obtains the temperature distribution characteristics of each body part. The health detection subunit determines whether the temperature distribution characteristics of each body part exceed the corresponding preset temperature threshold based on the temperature distribution characteristics of each body part and the preset temperature threshold of the corresponding body part. If it exceeds the threshold, the health detection result is determined to be that there is a health risk in the corresponding body part; otherwise, the health detection result is determined to be that there is no health risk in the corresponding body part.

4. The intelligent health monitoring system for air conditioning according to claim 2, characterized in that, The target detection unit includes: The key point detection subunit performs key point detection on the human body temperature feature map to obtain key point detection results. The temperature distribution recognition subunit performs local temperature recognition of key points on the human body temperature feature map based on the key point detection results, and obtains the local temperature distribution results of key points. The feature matching subunit matches the local temperature distribution results of the key points with the local temperature distribution features of key points in the preset template library, and the matching result is as follows: The target detection subunit, based on the matching result showing that the key point matching is successful, uses the corresponding key point as a seed point and uses a preset region growing algorithm to divide the human body temperature feature map into body parts to obtain the body part detection result.

5. The intelligent health monitoring system for air conditioning according to claim 2, characterized in that, The image segmentation unit includes: The threshold determination subunit selects a preset threshold as the segmentation threshold, or, based on the temperature characteristics, uses the maximum inter-class variance method or the minimum intra-class variance method to obtain an adaptive threshold as the segmentation threshold. The pixel classification subunit compares the temperature value corresponding to each pixel in the temperature feature map with the segmentation threshold. If the temperature value corresponding to the pixel is greater than the segmentation threshold, the corresponding pixel is classified as a foreground pixel; otherwise, the corresponding pixel is classified as a background pixel. The image segmentation subunit performs image segmentation on the temperature feature map based on the foreground pixels and the background pixels to obtain the human body temperature feature map corresponding to the foreground pixels.

6. The intelligent health monitoring system for air conditioning according to claim 5, characterized in that, The threshold determination subunit includes: The statistical unit determines the number of pixels corresponding to the temperature value for each pixel based on the temperature feature map, and obtains a histogram. Each element in the histogram is used to represent the number of pixels corresponding to the temperature value in the temperature feature map. The mean value determination subunit determines the global temperature mean based on the histogram; The initial configuration unit initializes the background pixel count based on the pixel count of all elements in the histogram, initializes the background pixel average based on the global temperature average, and initializes the foreground pixel count, foreground pixel average, foreground pixel variance, and background pixel variance to 0. The data processing unit iterates through the temperature values ​​corresponding to each element in the histogram, uses the iterated temperature values ​​as the current threshold, compares the temperature values ​​corresponding to the remaining elements with the current threshold, updates the number of foreground pixels, the average foreground pixels, the number of background pixels, and the average background pixels, and determines the intra-class variance or inter-class variance corresponding to the current threshold based on the updated number of foreground pixels, the average foreground pixels, the number of background pixels, and the average background pixels. The threshold determination subunit selects the threshold corresponding to the minimum intra-class variance or the maximum inter-class variance based on the intra-class variance or inter-class variance corresponding to the current threshold, and uses it as the adaptive threshold.

7. The intelligent health monitoring system for air conditioning according to claim 1, characterized in that, The temperature acquisition module includes: The infrared sensor array unit collects infrared radiation from the human body surface in the indoor target area to obtain infrared temperature signals; The signal conditioning and amplification unit amplifies and filters the infrared temperature signal to obtain a conditioned and amplified signal; An analog-to-digital conversion unit performs analog-to-digital conversion on the conditioned and amplified signal to obtain a digital temperature signal; The image processing unit sets the pixels in the corresponding indoor target area to the corresponding grayscale value according to the digital temperature signal and the corresponding indoor target area to obtain a temperature image.

8. The intelligent health monitoring system for air conditioning according to claim 1, characterized in that, The main control processing module also includes: The data preprocessing unit preprocesses the temperature image before performing health checks based on the temperature image. The preprocessing includes at least one of noise filtering and temperature calibration.

9. The intelligent health monitoring system for air conditioning according to claim 1, characterized in that, The early warning feedback module includes: The early warning information generation unit generates early warning information based on the health detection result indicating the presence of abnormal temperature areas, according to the abnormal temperature areas and corresponding abnormal temperature differences, and in conjunction with preset early warning information generation rules; wherein, the preset early warning information generation rules are used to restrict the alarm methods for different body parts and their corresponding abnormal temperature differences. The feedback unit sends the warning information to the user terminal to remind the user according to the alarm method corresponding to the warning information.

10. A method for intelligent health monitoring of air conditioners, characterized in that, include: Infrared radiation from the human body surface is collected indoors to obtain temperature images; A health check is performed based on the temperature image to obtain the health check result; Based on the health detection results indicating the presence of abnormal temperature areas, an early warning message is generated according to the location of the abnormal temperature and sent to the user's terminal for early warning notification.

Images