Air conditioner air supply control method and device and air conditioner

Abstract

The invention relates to the field of household appliances, and provides an air conditioner air supply control method and device and an air conditioner. The method comprises the steps that infrared thermal imaging data and binocular vision sensing data are obtained; fusing the infrared thermal imaging data and the binocular vision sensing data to obtain fusion information; and according to the fusion information and an air conditioner air supply mode obtained in advance, an air conditioner air supply strategy is determined, and air conditioner operation is controlled according to the air conditioner air supply strategy. The defect that the air supply control precision is poor due to sensing of a single sensor is overcome, the influence of noise and errors of the single sensor is reduced by fusing useful information in infrared thermal imaging data and binocular vision sensing data, the robustness and the anti-jamming capability of the system are improved, and more comfortable and energy-saving indoor environment control is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of household appliances, and in particular to an air supply control method and device for an air conditioner. Background Art

[0002] In the current development process of intelligent air-conditioning control technology, accurately sensing the indoor environment and intelligently adjusting air supply are the keys to improving user experience and energy-saving efficiency.

[0003] At present, intelligent air supply adjustment mainly uses a single infrared thermal imaging technology to perceive the indoor environment. Infrared thermal imaging technology is based on the infrared radiation characteristics of objects to obtain the surface temperature distribution of objects to detect indoor temperature differences and locate human fever areas.

[0004] However, single infrared thermal imaging technology has obvious defects: on the one hand, its penetrating ability is limited. When the human body or object is blocked by walls, thick furniture, etc., it is difficult to obtain the infrared radiation information of the blocked part, resulting in the inability to accurately detect the target position and temperature; on the other hand, it is unable to accurately identify the shape, posture and spatial position information of the object, and has deficiencies in judging details such as human movements and orientations. It can only present a fuzzy thermal image outline, which is difficult to meet the needs of object status recognition for precise air supply of air conditioners. Summary of the Invention

[0005] The present invention provides an air supply control method, device and air conditioner for air conditioning, which are used to solve the defect of poor air supply control accuracy caused by single sensor perception in the prior art. By fusing useful information from infrared thermal imaging data and binocular visual sensing data, the influence of noise and error of a single sensor is reduced, the robustness and anti-interference ability of the system are improved, and a more comfortable and energy-saving indoor environment control is achieved.

[0006] The present invention provides an air-conditioning air supply control method, comprising: acquiring infrared thermal imaging data and binocular visual sensor data; fusing the infrared thermal imaging data and the binocular visual sensor data to obtain fusion information; determining an air-conditioning air supply strategy based on the fusion information and a previously acquired air-conditioning air supply mode, and controlling the air-conditioning operation according to the air-conditioning air supply strategy.

[0007] It should be noted that by acquiring infrared thermal imaging data, the thermal radiation of objects is perceived, thereby obtaining temperature distribution information, and by acquiring binocular visual sensing data, the visual information of the scene, including the shape and position of objects, is obtained. By fusing useful information in infrared thermal imaging data and binocular visual sensing data, a more complete and accurate environmental model is formed, which helps to eliminate the limitations of single sensor data and improve the overall performance of the system. The fused information can reduce the impact of single sensor noise and errors, and improve the robustness and anti-interference ability of the system. Based on the fused information and the preset air conditioning supply mode, the air conditioning supply strategy can be determined more intelligently to achieve more comfortable and energy-saving indoor environment control.

[0008] According to the present invention, a method for controlling air supply of an air conditioner is provided. The binocular vision sensor includes indoor image data collected by at least two cameras evenly distributed on both sides of an infrared thermal imager. The infrared thermal imaging data and the binocular vision sensor data are fused to obtain fusion information, including: inputting the infrared thermal imaging data and the binocular vision sensor data into a data fusion model to obtain fusion information output by the data fusion model. The data fusion model is trained based on historical infrared thermal imaging data, historical binocular vision sensor data and fusion labels. The data fusion model includes: a feature extraction layer, which performs feature extraction on the indoor image data corresponding to the at least two cameras to obtain corresponding indoor feature maps, and performs feature extraction on the infrared thermal imaging data to obtain temperature distribution features and target thermal features; a feature matching layer, which performs feature point matching on each indoor feature map to obtain disparity information; a visual reconstruction layer, which performs three-dimensional reconstruction of the indoor scene based on the disparity information to obtain indoor visual features; and an information fusion layer, which fuses the indoor visual features, temperature distribution thermal features and target thermal features to obtain fusion information.

[0009] It should be noted that by performing feature extraction on indoor image data separately, key features such as key points, edges, corners, etc. are identified from each image, so as to compress image information to key feature points, reduce the amount of data for subsequent processing, and improve processing speed. Matching is performed based on the extracted indoor feature maps to determine disparity information, and thus the three-dimensional structure of the indoor scene is reconstructed based on the disparity information to accurately obtain the shape, position and motion information of the object. Feature extraction is performed on infrared thermal imaging data to provide temperature distribution information of the scene, which complements the geometric structure features provided by binocular vision data to provide more comprehensive perception information, thereby comprehensively utilizing the information provided by different sensors to improve the comprehensiveness and accuracy of perception, improve the robustness of the system, reduce the impact of single sensor failure on system performance, and facilitate the subsequent air conditioning supply strategy to be flexibly adjusted according to temperature requirements.

[0010] According to an air conditioning air supply control method provided by the present invention, an indoor scene is reconstructed in three dimensions based on parallax information to obtain indoor visual features, including: obtaining the three-dimensional coordinates of matched feature points based on the parallax information and combining previously acquired camera parameters; and generating a three-dimensional point cloud based on the three-dimensional coordinates of all matched feature points to obtain indoor visual features.

[0011] It should be noted that by utilizing disparity information to accurately calculate the three-dimensional position of the object, and combining it with camera parameters to improve the accuracy of the three-dimensional coordinates of the feature points, the three-dimensional coordinates of all matched feature points are combined to generate a three-dimensional point cloud, thereby improving the accuracy and quality of three-dimensional reconstruction while retaining the scene geometry information.

[0012] According to an air conditioning air supply control method provided by the present invention, after generating a three-dimensional point cloud, the method includes: filtering the three-dimensional point cloud to remove noise and outliers; generating a three-dimensional surface model based on the three-dimensional point cloud after filtering; and mapping the texture of indoor image data onto the three-dimensional surface model.

[0013] It should be noted that by filtering the three-dimensional point cloud, the noise and outliers in the point cloud can be effectively removed, and the quality and accuracy of the point cloud can be improved. By removing the noise and outliers, the robustness of the subsequent reconstruction and texture mapping can be improved, and errors and errors can be reduced. The filtered point cloud can be further converted into a three-dimensional surface model to improve rendering efficiency, facilitate subsequent texture mapping and visualization, and map the texture of the indoor image data to the three-dimensional surface model, so as to generate a realistic indoor three-dimensional model by complementing the provided texture information with the geometric information, enhance the visual effect, and improve the interpretability and application value of the three-dimensional model.

[0014] According to an air conditioning air supply control method provided by the present invention, fusion information includes personnel location information and temperature distribution information; based on the fusion information and the air conditioning air supply mode obtained previously, the air conditioning air supply strategy is determined, including: determining that the air conditioning air supply mode obtained previously is a wind avoiding people mode, and determining a first temperature difference between the temperature of the unmanned area and the air conditioning set temperature based on the fusion information; based on the first temperature difference being greater than a first preset threshold, determining that the air conditioning air supply strategy is to control the air guide plate to blow toward the unmanned area, increase the cooling capacity or heating capacity of the corresponding air conditioning operation mode and increase the air volume; based on the first temperature difference being less than or equal to the first preset threshold, determining that the air conditioning air supply strategy is to control the air guide plate to blow toward the unmanned area, maintain the cooling capacity or heating capacity of the corresponding air conditioning operation mode and maintain the air volume.

[0015] It should be noted that when the wind avoids people mode is determined, the area that needs to be adjusted can be identified by calculating the first temperature difference between the temperature of the unmanned area and the air conditioning set temperature, and the air conditioning supply strategy can be adjusted more accurately based on the size of the first temperature difference to improve energy efficiency. When the first temperature difference is large, the set temperature can be reached faster by increasing the cooling capacity or heating capacity of the corresponding air conditioning operation mode, and the air circulation can be accelerated by increasing the air volume to improve the efficiency of temperature regulation, and the air guide plate is controlled to blow toward the unmanned area to avoid cold wind or hot air blowing directly toward people, while improving the temperature regulation efficiency of the unmanned area. When the first temperature difference is small, the cooling capacity or heating capacity of the corresponding air conditioning operation mode is maintained to avoid over-adjustment and save energy. By maintaining the air volume and air circulation, the freshness of the indoor air is maintained, and the air guide plate is controlled to blow toward the unmanned area to avoid cold wind or hot air blowing directly toward people, while maintaining the temperature regulation effect of the unmanned area.

[0016] According to an air conditioning air supply control method provided by the present invention, the fusion information includes personnel location information and temperature distribution information; the air conditioning air supply strategy is determined based on the fusion information and the previously obtained air conditioning air supply mode, and also includes: determining that the previously obtained air conditioning air supply mode is a wind follows people mode, and determining a second temperature difference between the temperature of the area where the personnel is located and the air conditioning set temperature based on the fusion information; based on the second temperature difference being greater than a second preset threshold, determining that the air conditioning air supply strategy is to control the air guide plate to blow toward the area where the personnel is located, increase the cooling capacity or heating capacity of the corresponding air conditioning operation mode and reduce the air volume; based on the second temperature difference being less than or equal to the second preset threshold, determining that the air conditioning air supply strategy is to control the air guide plate to blow toward the area where the personnel is located, maintain the cooling capacity or heating capacity of the corresponding air conditioning operation mode and maintain the air volume.

[0017] It should be noted that when the wind follows people mode is determined, attention is paid to the temperature of the area where the people are located. By determining the second temperature difference between the temperature of the area where the people are located and the set temperature of the air conditioner, the air supply strategy of the air conditioner is accurately adjusted based on the size of the second temperature difference to improve energy efficiency. When the second temperature difference is large, the cooling capacity or heating capacity of the corresponding air conditioner operation mode is increased to reach the set temperature faster, and the air volume is reduced to avoid excessive airflow directly blowing on people and causing discomfort. Using higher temperature / cooling capacity (intensity) with lower wind speed may achieve the target temperature more energy-efficiently than high wind speed, while improving Provide better physical sensation, improve energy efficiency, and control the air guide to blow toward the area where personnel are located, ensuring that the adjustment effect directly acts on personnel and improving efficiency. When the second temperature difference is small, maintain the cooling capacity or heating capacity of the corresponding air-conditioning operation mode to avoid unnecessary energy consumption and temperature fluctuations, and maintain a comfortable microenvironment around personnel by maintaining the air volume to prevent the temperature around personnel from being too low or too high due to excessive cooling or heating, and control the air guide to blow toward the personnel area to avoid cold air or hot air blowing directly toward the area where personnel are located, ensuring that the adjustment effect directly acts on personnel and improving efficiency.

[0018] According to an air conditioning air supply control method provided by the present invention, an air conditioning air supply strategy is determined based on fusion information and a previously acquired air conditioning air supply mode, and the method also includes: inputting the fusion information, the previously acquired air conditioning air supply mode and the user's usage habits into a strategy prediction model to obtain the air conditioning air supply strategy output by the strategy prediction model; wherein the strategy prediction model is previously trained based on training samples and their corresponding strategy labels, and the training samples include historical fusion information, historical air conditioning air supply modes and historical user usage habits.

[0019] It should be noted that by inputting the fusion information and the previously acquired air-conditioning air supply mode and user usage habits into the strategy prediction model for strategy prediction, the strategy can be dynamically adjusted according to the real-time situation and user habits to achieve true intelligent control, improve the operating efficiency of the air conditioner, and reduce energy consumption.

[0020] According to an air conditioning air supply control method provided by the present invention, before fusing infrared thermal imaging data and binocular visual sensor data to obtain fusion information, the method includes: filtering the infrared thermal imaging data; and performing image correction and dedistortion processing on the binocular visual sensor data.

[0021] It should be noted that filtering can be implemented using a pre-selected filtering algorithm to effectively remove noise, enhance image contrast, and improve image quality. Additionally, binocular cameras typically exhibit radial and tangential distortion, which can affect the accuracy of subsequent feature point extraction and matching. Dedistortion is therefore used to eliminate these distortions and improve image quality. Image correction integrates the image data from the two cameras into a unified coordinate system, facilitating subsequent fusion processing. Image correction and dedistortion improve the positioning accuracy of feature points, thereby improving the accuracy of feature matching and providing more accurate 3D information. This improves the accuracy of 3D reconstruction and provides high-quality image data for subsequent 3D reconstruction.

[0022] The present invention also provides an air-conditioning air supply control device, comprising: a data acquisition module for acquiring infrared thermal imaging data and binocular visual sensing data; a data fusion module for fusing the infrared thermal imaging data and binocular visual sensing data to obtain fusion information; a strategy control module for determining the air-conditioning air supply strategy based on the fusion information and the air-conditioning air supply mode previously acquired, and controlling the air-conditioning operation according to the air-conditioning air supply strategy.

[0023] It should be noted that the infrared thermal imaging data is acquired through the data acquisition module to perceive the thermal radiation of the object, thereby obtaining temperature distribution information, and the binocular visual sensor data is acquired to obtain visual information of the scene, including the shape and position of the object, etc., and the useful information in the infrared thermal imaging data and binocular visual sensor data is integrated through the data fusion module to form a more complete and accurate environmental model, which helps to eliminate the limitations of a single sensor data and improve the overall performance of the system. The fused information can reduce the impact of noise and errors of a single sensor, improve the robustness and anti-interference ability of the system, and thus the air conditioning supply strategy can be determined more intelligently through the strategy control module based on the fused information and the preset air conditioning supply mode, so as to achieve more comfortable and energy-saving indoor environment control.

[0024] The present invention also provides an air conditioner, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of any of the above-described air conditioning air supply control methods are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 This is one of the flow charts of the air-conditioning air supply control method provided by the present invention; Figure 2 This is the second flow chart of the air conditioning air supply control method provided by the present invention; Figure 3 It is a structural schematic diagram of the air-conditioning air supply control device provided by the present invention; Figure 4 It is a structural schematic diagram of the air conditioner provided by the present invention. DETAILED DESCRIPTION

[0027] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0028] Figure 1 A flow chart illustrating an air supply control method for air conditioning according to the present invention is provided, wherein the method comprises: S11, acquiring infrared thermal imaging data and binocular vision sensing data; S12, fusing the infrared thermal imaging data and the binocular vision sensor data to obtain fusion information; S13, determining an air-conditioning air-supply strategy based on the fused information and the previously acquired air-conditioning air-supply mode, and controlling the air-conditioning operation according to the air-conditioning air-supply strategy.

[0029] It should be noted that the step numbers "S1N" in this manual do not represent the order of the air conditioning air supply control method. Figure 2 The air supply control method of the air conditioner of the present invention is described.

[0030] S11, acquiring infrared thermal imaging data and binocular visual sensing data.

[0031] It should be noted that infrared thermal imaging data is obtained by scanning the interior of the room using an infrared thermal imager. The infrared thermal imager can use a high-resolution imager with a resolution of no less than 640×480 pixels and a detection wavelength range of 8-14μm, covering the infrared radiation band of common objects. In the actual design, the selected infrared thermal imager is integrated into a separate metal housing with a germanium lens at the front end to focus infrared radiation and improve image clarity. Furthermore, the infrared thermal imager is allowed to adjust vertically by ±15° to accommodate different installation heights and indoor space layouts, ensuring that it covers the entire indoor space and obtains comprehensive temperature distribution information.

[0032] Furthermore, the binocular vision sensor includes indoor image data collected by at least two cameras evenly distributed on either side of the infrared thermal imager. These cameras can be identical high-definition CMOS cameras, each with a resolution of 1920×1080, a frame rate of at least 30 fps, a lens focal length of 5mm, and a field of view of 75°. For example, when using two cameras, they are mounted parallel to each other, one on the left and one on the right of the infrared thermal imager, maintaining horizontal alignment with the infrared thermal imager. The baseline distance between the two cameras is maintained at a fixed 12cm to meet the parallax calculation requirements for binocular vision.

[0033] It should be noted that the optical axes of the two cameras are parallel to the optical axis of the infrared thermal imager and are located on the same horizontal plane to ensure that the fields of view of the three cameras can fully overlap, thereby facilitating subsequent data fusion processing.

[0034] In addition, the acquisition of infrared thermal imaging data and binocular vision sensor data can be based on the user turning on the power, setting the cooling or heating mode, and selecting the air conditioning and ventilation mode, and then synchronously triggering the infrared thermal imager and binocular vision camera to collect corresponding data.

[0035] S12, fusing the infrared thermal imaging data and the binocular vision sensor data to obtain fusion information.

[0036] In this embodiment, infrared thermal imaging data and binocular visual sensor data are fused to obtain fusion information, including: inputting the infrared thermal imaging data and binocular visual sensor data into a data fusion model to obtain fusion information output by the data fusion model; wherein the data fusion model is trained based on historical infrared thermal imaging data, historical binocular visual sensor data and fusion labels; the data fusion model includes: a feature extraction layer, which performs feature extraction on indoor image data corresponding to at least two cameras to obtain corresponding indoor feature maps, and performs feature extraction on infrared thermal imaging data to obtain temperature distribution features and target thermal features; a feature matching layer, which performs feature point matching on each indoor feature map to obtain disparity information; a visual reconstruction layer, which performs three-dimensional reconstruction of the indoor scene based on the disparity information to obtain indoor visual features; and an information fusion layer, which fuses indoor visual features, temperature distribution thermal features and target thermal features to obtain fusion information.

[0037] It should be noted that by performing feature extraction on indoor image data separately, key features such as key points, edges, corners, etc. are identified from each image, so as to compress image information to key feature points, reduce the amount of data for subsequent processing, and improve processing speed. Matching is performed based on the extracted indoor feature maps to determine disparity information, and thus the three-dimensional structure of the indoor scene is reconstructed based on the disparity information to accurately obtain the shape, position and motion information of the object. Feature extraction is performed on infrared thermal imaging data to provide temperature distribution information of the scene, which complements the geometric structure features provided by binocular vision data to provide more comprehensive perception information, thereby comprehensively utilizing the information provided by different sensors to improve the comprehensiveness and accuracy of perception, improve the robustness of the system, reduce the impact of single sensor failure on system performance, and facilitate the subsequent air conditioning supply strategy to be flexibly adjusted according to temperature requirements.

[0038] In addition, disparity information is used to characterize the positional differences between two images of the same object. Indoor visual features include information about people, objects, and the environment in the three-dimensional indoor space, while target thermal features include information about people and objects in the three-dimensional indoor space. The data fusion model can be implemented using a previously trained deep neural network model. This model inputs infrared thermal imaging data and binocular vision sensor data into the deep neural network model to generate corresponding fusion information. The deep neural network model is trained based on historical infrared thermal imaging data, historical binocular vision sensor data, and their corresponding fusion labels. By learning the association and complementary relationship between the two types of data, the model achieves comprehensive and accurate perception of human position, posture, movement, and indoor temperature distribution.

[0039] Specifically, the indoor scene is reconstructed in three dimensions based on the disparity information to obtain indoor visual features, including: obtaining the three-dimensional coordinates of the matching feature points based on the disparity information and the previously acquired camera parameters; generating a three-dimensional point cloud based on the three-dimensional coordinates of all matching feature points to obtain indoor visual features.

[0040] It's important to note that disparity information is used to accurately calculate the 3D position of objects. This information is combined with camera parameters to improve the accuracy of the 3D coordinates of feature points. By combining the 3D coordinates of all matched feature points to generate a 3D point cloud, the accuracy and quality of 3D reconstruction are improved while preserving the scene's geometric information. Camera parameters include focal length, principal point coordinates, rotation matrix, and translation vector; the 3D coordinates of matched feature points can be calculated using triangulation.

[0041] In addition, after generating the three-dimensional point cloud, the method includes: filtering the three-dimensional point cloud to remove noise and outliers; generating a three-dimensional surface model based on the three-dimensional point cloud after filtering; and mapping the texture of the indoor image data onto the three-dimensional surface model.

[0042] It should be noted that by filtering the three-dimensional point cloud, the noise and outliers in the point cloud can be effectively removed, and the quality and accuracy of the point cloud can be improved. By removing the noise and outliers, the robustness of the subsequent reconstruction and texture mapping can be improved, and errors and errors can be reduced. The filtered point cloud can be further converted into a three-dimensional surface model to improve rendering efficiency, facilitate subsequent texture mapping and visualization, and map the texture of the indoor image data to the three-dimensional surface model, so as to generate a realistic indoor three-dimensional model by complementing the provided texture information with the geometric information, enhance the visual effect, and improve the interpretability and application value of the three-dimensional model.

[0043] In addition, the three-dimensional surface model can select the corresponding surface reconstruction method according to actual design requirements, such as Poisson surface reconstruction, spherical wave surface reconstruction, etc., which is not further limited here.

[0044] In an optional embodiment, before the infrared thermal imaging data and the binocular vision sensing data are fused to obtain fusion information, the following steps are included: filtering the infrared thermal imaging data; and image correction and dedistortion processing are performed on the binocular vision sensing data.

[0045] It should be noted that filtering can be implemented using a pre-selected filtering algorithm to effectively remove noise, enhance image contrast, and improve image quality. Additionally, binocular cameras typically exhibit radial and tangential distortion, which can affect the accuracy of subsequent feature point extraction and matching. Dedistortion is therefore used to eliminate these distortions and improve image quality. Image correction integrates the image data from the two cameras into a unified coordinate system, facilitating subsequent fusion processing. Image correction and dedistortion improve the positioning accuracy of feature points, thereby improving the accuracy of feature matching and providing more accurate 3D information. This improves the accuracy of 3D reconstruction and provides high-quality image data for subsequent 3D reconstruction.

[0046] S13, determining an air-conditioning air-supply strategy based on the fused information and the previously acquired air-conditioning air-supply mode, and controlling the air-conditioning operation according to the air-conditioning air-supply strategy.

[0047] In an alternative embodiment, reference Figure 2 , the fusion information includes personnel location information and temperature distribution information; based on the fusion information and the previously acquired air-conditioning air supply mode, the air-conditioning air supply strategy is determined, including: determining that the previously acquired air-conditioning air supply mode is a wind avoiding people mode, and determining a first temperature difference between the temperature of the unmanned area and the air-conditioning set temperature based on the fusion information; based on the first temperature difference being greater than a first preset threshold, determining that the air-conditioning air supply strategy is to control the air guide plate to blow toward the unmanned area, increase the cooling capacity or heating capacity of the corresponding air-conditioning operation mode, and increase the air volume; based on the first temperature difference being less than or equal to the first preset threshold, determining that the air-conditioning air supply strategy is to control the air guide plate to blow toward the unmanned area, maintain the cooling capacity or heating capacity of the corresponding air-conditioning operation mode, and maintain the air volume.

[0048] It should be noted that when the wind avoids people mode is determined, the area that needs to be adjusted can be identified by calculating the first temperature difference between the temperature of the unmanned area and the air conditioning set temperature, and the air conditioning supply strategy can be adjusted more accurately based on the size of the first temperature difference to improve energy efficiency. When the first temperature difference is large, the set temperature can be reached faster by increasing the cooling capacity or heating capacity of the corresponding air conditioning operation mode, and the air circulation can be accelerated by increasing the air volume to improve the efficiency of temperature regulation, and the air guide plate is controlled to blow toward the unmanned area to avoid cold wind or hot air blowing directly toward people, while improving the temperature regulation efficiency of the unmanned area. When the first temperature difference is small, the cooling capacity or heating capacity of the corresponding air conditioning operation mode is maintained to avoid over-adjustment and save energy. By maintaining the air volume and air circulation, the freshness of the indoor air is maintained, and the air guide plate is controlled to blow toward the unmanned area to avoid cold wind or hot air blowing directly toward people, while maintaining the temperature regulation effect of the unmanned area.

[0049] In cooling mode, the first temperature difference can be calculated by subtracting the air conditioner set temperature from the unoccupied area temperature; in heating mode, the first temperature difference can be calculated by subtracting the air conditioner set temperature from the unoccupied area temperature. Furthermore, the first preset threshold corresponding to cooling mode or heating mode can be set based on actual needs and can be the same or different, and is not further limited here.

[0050] In an alternative embodiment, continue to refer to Figure 2 , determining the air conditioning air supply strategy based on the fusion information and the previously acquired air conditioning air supply mode, also includes: determining that the previously acquired air conditioning air supply mode is the wind follows people mode, and determining the second temperature difference between the temperature of the area where the personnel are located and the air conditioning set temperature based on the fusion information; based on the second temperature difference being greater than the second preset threshold, determining the air conditioning air supply strategy to be controlling the air guide plate to blow toward the area where the personnel are located, increasing the cooling capacity or heating capacity of the corresponding air conditioning operation mode and reducing the air volume; based on the second temperature difference being less than or equal to the second preset threshold, determining the air conditioning air supply strategy to be controlling the air guide plate to blow toward the area where the personnel are located, maintaining the cooling capacity or heating capacity of the corresponding air conditioning operation mode and maintaining the air volume.

[0051] It should be noted that when the wind follows people mode is determined, attention is paid to the temperature of the area where the people are located. By determining the second temperature difference between the temperature of the area where the people are located and the set temperature of the air conditioner, the air supply strategy of the air conditioner is accurately adjusted based on the size of the second temperature difference to improve energy efficiency. When the second temperature difference is large, the cooling capacity or heating capacity of the corresponding air conditioner operation mode is increased to reach the set temperature faster, and the air volume is reduced to avoid excessive airflow directly blowing on people and causing discomfort. Using higher temperature / cooling capacity (intensity) with lower wind speed may achieve the target temperature more energy-efficiently than high wind speed, while improving Provide better physical sensation, improve energy efficiency, and control the air guide to blow toward the area where personnel are located, ensuring that the adjustment effect directly acts on personnel and improving efficiency. When the second temperature difference is small, maintain the cooling capacity or heating capacity of the corresponding air-conditioning operation mode to avoid unnecessary energy consumption and temperature fluctuations, and maintain a comfortable microenvironment around personnel by maintaining the air volume to prevent the temperature around personnel from being too low or too high due to excessive cooling or heating, and control the air guide to blow toward the personnel area to avoid cold air or hot air blowing directly toward the area where personnel are located, ensuring that the adjustment effect directly acts on personnel and improving efficiency.

[0052] In cooling mode, the second temperature difference can be calculated by subtracting the air conditioner set temperature from the temperature of the area where the user is located; in heating mode, the first temperature difference can be calculated by subtracting the air conditioner set temperature from the temperature of the area where the user is located. Furthermore, the second preset threshold corresponding to cooling mode or heating mode can be set based on actual needs and can be the same or different, and this is not further defined here.

[0053] It should be noted that when determining air conditioning airflow strategies, user habits can also be considered, such as posture-adjusted airflow, wide-angle airflow, centralized airflow, and zoned airflow, to enhance the user experience. Specifically, the fusion information, previously acquired airflow modes, airflow operation modes, and user habits are input into a strategy prediction model to generate an airflow strategy output by the strategy prediction model. The strategy prediction model is previously trained based on training samples and their corresponding strategy labels. The training samples include historical fusion information, historical airflow modes, and historical user habits.

[0054] In an optional embodiment, the air conditioning operation is controlled according to the air conditioning air supply strategy, including: generating air guide plate control instructions, fan control instructions and compressor control instructions according to the air conditioning air supply strategy; sending the air guide plate control instructions, fan control instructions and compressor control instructions to the corresponding air guide plates, fans and compressors respectively to perform regulation.

[0055] It should be noted that by inputting the fusion information and the previously acquired air-conditioning air supply mode and user usage habits into the strategy prediction model for strategy prediction, the strategy can be dynamically adjusted according to the real-time situation and user habits to achieve true intelligent control, improve the operating efficiency of the air conditioner, and reduce energy consumption.

[0056] In summary, the embodiments of the present invention obtain infrared thermal imaging data to sense the thermal radiation of objects, thereby obtaining temperature distribution information, and obtain binocular visual sensor data to obtain visual information of the scene, including the shape and position of the object, etc., and form a more complete and accurate environmental model by fusing useful information in infrared thermal imaging data and binocular visual sensor data, which helps to eliminate the limitations of single sensor data and improve the overall performance of the system. The fused information can reduce the impact of single sensor noise and errors, improve the robustness and anti-interference ability of the system, and thus more intelligently determine the air conditioning supply strategy based on the fused information and the preset air conditioning supply mode, thereby achieving more comfortable and energy-saving indoor environment control.

[0057] The air-conditioning air supply control device provided by the present invention is described below. The air-conditioning air supply control device described below and the air-conditioning air supply control method described above can be referred to in correspondence with each other.

[0058] Figure 3 The figure shows a schematic structural diagram of an air supply control device for an air conditioner, which comprises: Data acquisition module 31, acquires infrared thermal imaging data and binocular vision sensor data; The data fusion module 32 fuses the infrared thermal imaging data and the binocular vision sensor data to obtain fusion information; The strategy control module 33 determines the air-conditioning air-supply strategy based on the fusion information and the air-conditioning air-supply mode previously acquired, and controls the air-conditioning operation according to the air-conditioning air-supply strategy.

[0059] In this embodiment, the data fusion module 32 is used to: input infrared thermal imaging data and binocular visual sensor data into a data fusion model to obtain fusion information output by the data fusion model; wherein the data fusion model is trained based on historical infrared thermal imaging data, historical binocular visual sensor data and fusion labels; the data fusion model includes: a feature extraction layer, which performs feature extraction on the indoor image data corresponding to at least two cameras to obtain corresponding indoor feature maps, and performs feature extraction on the infrared thermal imaging data to obtain temperature distribution features and target thermal features; a feature matching layer, which performs feature point matching on each indoor feature map to obtain disparity information; a visual reconstruction layer, which performs three-dimensional reconstruction of the indoor scene based on the disparity information to obtain indoor visual features; and an information fusion layer, which fuses the indoor visual features, temperature distribution thermal features and target thermal features to obtain fusion information.

[0060] Specifically, the visual reconstruction unit includes: a coordinate calculation subunit, which obtains the three-dimensional coordinates of the matching feature points based on the disparity information and the previously acquired camera parameters; a visual reconstruction subunit, which generates a three-dimensional point cloud based on the three-dimensional coordinates of all matching feature points to obtain indoor visual features.

[0061] In addition, the data fusion module 32 also includes: a filtering unit, which filters the three-dimensional point cloud after generating it to remove noise and outliers; a surface model production unit, which generates a three-dimensional surface model based on the three-dimensional point cloud after filtering; and a texture mapping unit, which maps the texture of the indoor image data onto the three-dimensional surface model.

[0062] In an optional embodiment, the device further includes: a data preprocessing module, which filters the infrared thermal imaging data and performs image correction and dedistortion processing on the binocular vision sensing data before fusing the infrared thermal imaging data and the binocular vision sensing data to obtain fusion information.

[0063] In an optional embodiment, the fused information includes personnel location information and temperature distribution information.

[0064] In an optional embodiment, the strategy control module 33 includes: a temperature difference determination unit, which determines that the air conditioning air supply mode previously obtained is a wind avoiding people mode, and determines the first temperature difference between the temperature of the unmanned area and the air conditioning set temperature based on the fusion information; a strategy determination unit, which determines that the air conditioning air supply strategy is to control the air guide plate to blow toward the unmanned area, increase the cooling capacity or heating capacity of the corresponding air conditioning operation mode and increase the air volume based on the first temperature difference being greater than the first preset threshold; and determines that the air conditioning air supply strategy is to control the air guide plate to blow toward the unmanned area, maintain the cooling capacity or heating capacity of the corresponding air conditioning operation mode and maintain the air volume based on the first temperature difference being less than or equal to the first preset threshold.

[0065] In an optional embodiment, the temperature difference determination unit is further configured to: determine that the previously acquired air conditioning air supply mode is the wind-follows-person mode, and determine, based on the fusion information, a second temperature difference between the temperature of the area where the person is located and the air conditioning set temperature. Accordingly, the strategy determination unit is further configured to: determine, based on the second temperature difference being greater than a second preset threshold, that the air conditioning air supply strategy is to control the air deflector to blow toward the area where the person is located, thereby increasing the cooling capacity or heating capacity of the corresponding air conditioning operating mode and reducing the air volume; and based on the second temperature difference being less than or equal to the second preset threshold, determine, based on the second temperature difference being less than or equal to the second preset threshold, that the air conditioning air supply strategy is to control the air deflector to blow toward the area where the person is located, thereby maintaining the cooling capacity or heating capacity of the corresponding air conditioning operating mode and maintaining the air volume.

[0066] In an optional embodiment, the policy control module 33 determines the air conditioning air supply strategy based on the fusion information and the previously acquired air conditioning air supply mode, and is also used to: input the fusion information and the previously acquired air conditioning air supply mode and user usage habits into the policy prediction model to obtain the air conditioning air supply strategy output by the policy prediction model; wherein the policy prediction model is previously trained based on training samples and their corresponding policy labels, and the training samples include historical fusion information, historical air conditioning air supply modes and historical user usage habits.

[0067] In an optional embodiment, the strategy control module 33 also includes: an instruction generation unit, which generates air guide plate control instructions, fan control instructions and compressor control instructions, etc. according to the air conditioning air supply strategy; a control unit, which sends the air guide plate control instructions, fan control instructions and compressor control instructions to the corresponding air guide plates, fans and compressors respectively to perform regulation.

[0068] In summary, the embodiments of the present invention acquire infrared thermal imaging data through a data acquisition module to sense the thermal radiation of an object, thereby acquiring temperature distribution information, and acquire visual information of a scene, including the shape and position of the object, by acquiring binocular visual sensing data, and integrate useful information in the infrared thermal imaging data and binocular visual sensing data through a data fusion module to form a more complete and accurate environmental model, which helps to eliminate the limitations of single sensor data and improve the overall performance of the system. The fused information can reduce the impact of noise and errors of a single sensor, and improve the robustness and anti-interference ability of the system, so that the strategy control module can more intelligently determine the air conditioning air supply strategy based on the fused information and the preset air conditioning air supply mode, thereby achieving more comfortable and energy-saving indoor environment control.

[0069] Figure 4 An example of a physical structure diagram of an air conditioner is shown below. Figure 4 As shown, the air conditioner may include: a processor 410, a communications interface 420, a memory 430, and a communications bus 440. The processor 410, the communications interface 420, and the memory 430 communicate with each other via the communications bus 440. The processor 410 may invoke logic instructions in the memory 430 to execute an air conditioning air supply control method, which includes: acquiring infrared thermal imaging data and binocular visual sensor data; fusing the infrared thermal imaging data and the binocular visual sensor data to obtain fused information; determining an air conditioning air supply strategy based on the fused information and a previously acquired air conditioning air supply mode, and controlling air conditioning operation according to the air conditioning air supply strategy.

[0070] Furthermore, the logic 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 portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0071] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the air conditioning and air supply control method provided by the above methods, and the method includes: obtaining infrared thermal imaging data and binocular visual sensing data; fusing the infrared thermal imaging data and binocular visual sensing data to obtain fusion information; determining the air conditioning and air supply strategy based on the fusion information and the air conditioning and air supply mode obtained previously, and controlling the air conditioning operation according to the air conditioning and air supply strategy.

[0072] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned air conditioning and air supply control methods, the methods comprising: acquiring infrared thermal imaging data and binocular visual sensing data; fusing the infrared thermal imaging data and binocular visual sensing data to obtain fusion information; determining an air conditioning and air supply strategy based on the fusion information and a previously acquired air conditioning and air supply mode, and controlling the air conditioning operation according to the air conditioning and air supply strategy.

[0073] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0074] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion 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, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An air supply control method for air conditioning, characterized in that: include: Acquire infrared thermal imaging data and binocular visual sensing data; fusing the infrared thermal imaging data and the binocular vision sensing data to obtain fusion information; An air conditioning air supply strategy is determined based on the fusion information and the previously acquired air conditioning air supply mode, and the air conditioning operation is controlled according to the air conditioning air supply strategy.

2. The air-conditioning air supply control method according to claim 1, characterized in that: The binocular vision sensor includes indoor image data collected by at least two cameras evenly distributed on both sides of the infrared thermal imager; The infrared thermal imaging data and the binocular vision sensor data are fused to obtain fusion information, including: Inputting the infrared thermal imaging data and the binocular vision sensor data into a data fusion model to obtain fusion information output by the data fusion model; wherein the data fusion model is trained based on historical infrared thermal imaging data, historical binocular vision sensor data, and fusion labels; The data fusion model includes: a feature extraction layer for performing feature extraction on the indoor image data collected by the at least two cameras to obtain corresponding indoor feature maps, and for performing feature extraction on the infrared thermal imaging data to obtain temperature distribution features and target thermal features; A feature matching layer performs feature point matching on each of the indoor feature maps to obtain disparity information; A visual reconstruction layer, which performs three-dimensional reconstruction of the indoor scene based on the disparity information to obtain indoor visual features; The information fusion layer fuses the indoor visual features, the temperature distribution thermal features and the target thermal features to obtain fusion information.

3. The air-conditioning air supply control method according to claim 2, characterized in that: Performing three-dimensional reconstruction of the indoor scene based on the disparity information to obtain indoor visual features includes: According to the disparity information, combined with the previously acquired camera parameters, the three-dimensional coordinates of the matched feature points are obtained; According to the 3D coordinates of all matched feature points, a 3D point cloud is generated to obtain indoor visual features.

4. The air-conditioning air supply control method according to claim 3, characterized in that: After generating the 3D point cloud, including: Performing filtering on the three-dimensional point cloud to remove noise and outliers; Generate a three-dimensional surface model based on the three-dimensional point cloud after filtering; The texture of the indoor image data is mapped onto a three-dimensional surface model.

5. The air-conditioning air supply control method according to claim 1, characterized in that: The fused information includes personnel location information and temperature distribution information; and determining an air conditioning air supply strategy based on the fused information and the previously acquired air conditioning air supply mode, including: Determining that the previously acquired air supply mode of the air conditioner is a wind avoiding people mode, and determining a first temperature difference between the temperature of the unmanned area and the set temperature of the air conditioner based on the fusion information; Based on the first temperature difference being greater than a first preset threshold, determining that the air supply strategy for the air conditioner is to control the air guide plate to blow toward the unoccupied area, increase the cooling capacity or heating capacity of the corresponding air conditioner operating mode, and increase the air volume; Based on the first temperature difference being less than or equal to the first preset threshold, the air conditioning air supply strategy is determined to control the air guide plate to blow toward the unmanned area, maintain the cooling capacity or heating capacity of the corresponding air conditioning operation mode, and maintain the air volume.

6. The air-conditioning air supply control method according to claim 1, characterized in that: The fused information includes personnel location information and temperature distribution information; determining an air conditioning air supply strategy based on the fused information and the previously acquired air conditioning air supply mode, further comprising: Determining that the previously acquired air supply mode of the air conditioner is a wind-follows-people mode, and determining a second temperature difference between the temperature of the area where the person is located and the set temperature of the air conditioner based on the fusion information; Based on the second temperature difference being greater than a second preset threshold, determining that the air supply strategy for the air conditioner is to control the air guide plate to blow toward the area where the personnel are located, increase the cooling capacity or heating capacity of the corresponding air conditioner operation mode, and reduce the air volume; Based on the fact that the second temperature difference is less than or equal to the second preset threshold, the air conditioning air supply strategy is determined to control the air guide plate to blow toward the area where the personnel are located, maintain the cooling capacity or heating capacity of the corresponding air conditioning operation mode and maintain the air volume.

7. The air-conditioning air supply control method according to claim 1, characterized in that: Determining an air-conditioning air-supply strategy based on the fused information and the previously acquired air-conditioning air-supply mode further includes: The fusion information and the previously acquired air-conditioning air supply mode and user usage habits are input into the strategy prediction model to obtain the air-conditioning air supply strategy output by the strategy prediction model; wherein, the strategy prediction model is previously trained based on training samples and their corresponding strategy labels, and the training samples include historical fusion information, historical air-conditioning air supply modes and historical user usage habits.

8. The air-conditioning air supply control method according to any one of claims 1 to 7, characterized in that: Before fusing the infrared thermal imaging data and the binocular vision sensor data to obtain fusion information, the method includes: performing filtering processing on the infrared thermal imaging data; Perform image correction and dedistortion processing on the binocular vision sensing data.

9. An air supply control device for air conditioning, characterized in that: include: Data acquisition module, which acquires infrared thermal imaging data and binocular vision sensing data; A data fusion module, fusing the infrared thermal imaging data and the binocular vision sensor data to obtain fusion information; The strategy control module determines an air-conditioning air-supply strategy based on the fusion information and the air-conditioning air-supply mode previously acquired, and controls the air-conditioning operation according to the air-conditioning air-supply strategy.

10. An air conditioner comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the air conditioning air supply control method according to any one of claims 1 to 8 are implemented.

Images