Remote intelligent control system and method for integrated ceiling
Through deep learning technology, the environmental image and user preferences are analyzed, and the angle of the integrated ceiling air conditioner air outlet is adjusted, which solves the problem of discomfort in the existing air conditioner air supply, and achieves a personalized comfort experience and energy saving effect.
Patent Information
- Application Number
- CN202410968570.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-18
AI Technical Summary
The existing integrated ceiling air conditioner has shortcomings in the air supply vent design, causing the wind to blow directly to the user or some areas, reducing the user's comfort experience.
The camera collects environmental panoramic images and user preferences, uses deep learning technology to extract feature vectors, and judges whether the angle of the integrated ceiling air conditioner air vent needs to be adjusted to achieve the best comfortable effect.
It has achieved personalized comfort experience improvement, improved users' quality of life, and effectively saved energy, in line with the needs of modern society of environmental protection and energy conservation.
Smart Images

Figure CN118915482A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of integrated suspended ceilings, and more specifically, to a remote intelligent control system and method for integrated suspended ceilings. Background Art
[0002] Integrated ceiling is a modern design that integrates lighting, ventilation, air conditioning and sound systems into the ceiling structure, which saves indoor space elegantly and efficiently, and significantly improves the aesthetics and functionality of the interior. In particular, integrated air conditioning, as a key component, adopts a hidden design that perfectly integrates with the overall structure, can accurately adjust the indoor temperature, and provide residents with a comfortable living experience.
[0003] However, the current integrated air conditioners have some shortcomings in the design of air outlets, such as blowing directly towards users or certain areas, which may cause discomfort. This situation significantly reduces the overall user experience quality.
[0004] Therefore, a remote intelligent control system and method for an integrated ceiling is desired. Summary of the invention
[0005] In order to solve the above technical problems, this application is proposed. The embodiment of this application provides a remote intelligent control system and method for an integrated ceiling, which first obtains the environmental panoramic image collected by the camera and the user's preference habits, then uses deep learning technology to perform feature extraction and correlation analysis on the two, and finally obtains the classification result through a classifier to determine whether the angle of the integrated ceiling air conditioner air outlet needs to be adjusted, thereby achieving the best comfort effect and providing a personalized comfort experience.
[0006] According to one aspect of the present application, a remote intelligent control system for an integrated ceiling is provided, comprising:
[0007] Integrated ceiling air conditioning data acquisition module, used to obtain the environment panoramic image and user preference habits collected by the camera;
[0008] An integrated ceiling air conditioning data extraction module is used to extract a home environment panoramic enhancement feature vector and a user air conditioning preference habit multi-scale correlation feature vector from the environment panoramic image collected by the camera and the user preference habit;
[0009] The air-conditioning outlet angle adjustment module is used to determine whether the angle of the integrated ceiling air-conditioning outlet needs to be adjusted based on the panoramic enhancement feature vector of the home environment and the multi-scale correlation feature vector of the user's air-conditioning preference habits.
[0010] According to another aspect of the present application, a remote intelligent control method for an integrated ceiling is provided, comprising:
[0011] Obtaining the panoramic image of the environment and user preferences collected by the camera;
[0012] Extracting a home environment panoramic enhancement feature vector and a user air conditioning preference habit multi-scale correlation feature vector from the environment panoramic image captured by the camera and the user preference habit;
[0013] Based on the panoramic enhancement feature vector of the home environment and the multi-scale correlation feature vector of the user's air-conditioning preference habits, it is determined whether the angle of the integrated ceiling air-conditioning air outlet needs to be adjusted.
[0014] Compared with the prior art, the present application provides a remote intelligent control system and method for an integrated suspended ceiling, which first obtains a panoramic image of the environment and user preferences captured by a camera, then uses deep learning technology to perform feature extraction and correlation analysis on the two, and finally uses a classifier to obtain a classification result to determine whether the angle of the integrated suspended ceiling air conditioner air outlet needs to be adjusted, thereby achieving the best comfort effect and providing a personalized comfort experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0016] Figure 1 It is a block diagram of a remote intelligent control system of an integrated ceiling according to an embodiment of the present application.
[0017] Figure 2 It is a block diagram of an integrated ceiling air conditioning data extraction module in a remote intelligent control system of an integrated ceiling according to an embodiment of the present application.
[0018] Figure 3 It is a block diagram of a home environment panoramic image feature extraction unit in a remote intelligent control system of an integrated ceiling according to an embodiment of the present application.
[0019] Figure 4 This is a block diagram of an air-conditioning outlet angle adjustment module in a remote intelligent control system of an integrated ceiling according to an embodiment of the present application.
[0020] Figure 5 The present invention is a flowchart of a remote intelligent control method for an integrated ceiling according to an embodiment of the present application.
[0021] Figure 6 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0022] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.
[0023] Figure 1 FIG. 1 is a block diagram of a remote intelligent control system for an integrated ceiling according to an embodiment of the present application. Figure 1 As shown, according to the integrated ceiling remote intelligent control system 100 of the embodiment of the present application, it includes: an integrated ceiling air conditioning data acquisition module 110, which is used to obtain the environment panoramic image collected by the camera and the user preference habits; an integrated ceiling air conditioning data extraction module 120, which is used to extract the home environment panoramic enhancement feature vector and the user air conditioning preference habit multi-scale correlation feature vector from the environment panoramic image collected by the camera and the user preference habits; an air conditioning air outlet angle adjustment module 130, which is used to determine whether the integrated ceiling air conditioning air outlet angle needs to be adjusted based on the home environment panoramic enhancement feature vector and the user air conditioning preference habit multi-scale correlation feature vector.
[0024] In the above-mentioned remote intelligent control system 100 of the integrated ceiling, the integrated ceiling air conditioning data acquisition module 110 is used to obtain the environmental panoramic image and user preference habits collected by the camera. It should be understood that the integrated ceiling is a modern design that cleverly integrates the lighting, ventilation, air conditioning and sound systems into the ceiling structure, which is not only more efficient in the use of indoor space, but also significantly improves the overall beauty and functionality of the interior. In particular, the integrated air conditioner, as its key component, adopts a hidden design and perfectly integrates with the overall structure, which can accurately adjust the indoor temperature and provide the occupants with a comfortable and pleasant living experience. However, the current integrated air conditioner has some shortcomings in the design of the air outlet, such as the air outlet may blow directly to the user or certain specific areas, which may cause some residents to feel uncomfortable. This situation significantly reduces the user's satisfaction and comfort in the overall living experience. Therefore, in the technical solution of the present application, the environmental panoramic image and user preference habits collected by the camera are obtained, and combined with deep learning technology, it is judged whether the angle of the integrated ceiling air conditioner air outlet needs to be adjusted, so as to ensure that the residents enjoy the best comfort and provide a customized comfort experience.
[0025] Specifically, the panoramic image of the environment is captured by the camera, which can provide real-time home environment information, including human activities, furniture placement, and light distribution. This information is crucial for air conditioning regulation, because different environmental conditions will affect the operation effect and energy efficiency of the air conditioner. By analyzing the panoramic image, the system can identify the actual number of people and location distribution in the home, so as to adjust the air supply direction and strength of the air conditioner to achieve precise temperature control and comfort improvement. At the same time, the system also collects users' air conditioning preferences, which include user preferences for temperature, wind speed, air supply direction, and even habitual adjustment modes for specific time periods. These data are collected through specific sensors or user interactions and are used to personalize the air conditioning working mode to provide a comfortable environment that meets user needs. Combining the panoramic image of the environment with user preferences and habits, the system can achieve intelligent air conditioning control through complex algorithms and models.
[0026] In the above-mentioned remote intelligent control system 100 of the integrated ceiling, the integrated ceiling air conditioning data extraction module 120 is used to extract the home environment panoramic enhancement feature vector and the user air conditioning preference habit multi-scale correlation feature vector from the environmental panoramic image collected by the camera and the user preference habit. It should be understood that by comprehensively considering the home environment panoramic enhancement feature vector and the user air conditioning preference habit multi-scale correlation feature vector, the system can achieve highly personalized air conditioning control. This intelligent adjustment can not only improve the user's quality of life, but also effectively save energy, which meets the modern social needs of environmental protection and energy saving.
[0027] Figure 2 FIG. 1 is a block diagram of an integrated ceiling air conditioning data extraction module in a remote intelligent control system of an integrated ceiling according to an embodiment of the present application. Figure 2 As shown, in a specific embodiment of the present application, the integrated ceiling air conditioning data extraction module 120 includes: a home environment panoramic image feature extraction unit 121, used to perform feature extraction on the home environment panoramic image collected by the camera to obtain the home environment panoramic enhancement feature vector; a user preference habit feature extraction unit 122, used to perform feature extraction on the user's air conditioning preference habits to obtain the user's air conditioning preference habit multi-scale correlation feature vector.
[0028] It should be understood that the panoramic image of the home environment provides rich visual information, which can be extracted and analyzed through image processing and computer vision technology. This information is necessary for adjusting the working mode of the air conditioner. Through feature extraction, the system can extract key numerical features from the complex panoramic image of the environment. These features can be the location coordinates of furniture, the number of people, the size ratio of the room, etc. Through these features, the system can establish an understanding of the structure and layout of the indoor environment, thereby providing a more accurate and personalized basis for air conditioning adjustment.
[0029] Furthermore, feature extraction of user air conditioning preference habits is performed to achieve personalized response of the remote intelligent control system of the integrated ceiling to user needs and optimize the air conditioning experience. Among them, user air conditioning preference habits refer to the user's preferences and habits for air conditioning working modes in daily life. These habits may cover aspects such as temperature setting, wind speed selection, and air outlet direction preference. Through feature extraction, the system can analyze the key features of these preferences from user behavior and usage data. The extraction of multi-scale correlation feature vectors is to more comprehensively understand and predict the user's air conditioning preferences. This method can include multiple levels of feature extraction and analysis, such as inferring the characteristics of long-term habits from the user's daily operation data, and making real-time adjustments based on current environmental conditions and seasonal changes. This multi-scale correlation feature vector can help the system predict changes in user needs more accurately, thereby improving user comfort and satisfaction.
[0030] Figure 3 FIG. 1 is a block diagram of a home environment panoramic image feature extraction unit in a remote intelligent control system of an integrated ceiling according to an embodiment of the present application. Figure 3 As shown, in a specific embodiment of the present application, the home environment panoramic image feature extraction unit 121 includes: a home environment panoramic image pixel enhancement subunit 1211, which is used to pass the home environment panoramic image collected by the camera through a home environment panoramic pixel enhancement generator to obtain a home environment panoramic pixel enhanced image; a panoramic pixel enhancement feature encoding subunit 1212, which is used to perform feature encoding on the home environment panoramic pixel enhanced image to obtain the home environment panoramic enhancement feature vector.
[0031] It should be understood that panoramic images of home environments are usually affected by shooting conditions and equipment limitations, and may have problems such as uneven lighting, blurred images, or noise interference. These problems will affect the system's ability to accurately understand and analyze the indoor environment. Through the home environment panoramic pixel enhancement generator, the system can process and optimize the original image to improve the image clarity, color accuracy, and detail expression. For example, through noise reduction algorithms and image enhancement technology, noise in the image can be removed, and the edges and contours of objects in the room can be enhanced, making it easier for the system to analyze and identify key information such as furniture placement and personnel activities. The enhanced image generator can also adjust the brightness, contrast, and color balance of the image according to environmental characteristics and visual perception principles, so that the image is more in line with the visual perception and aesthetic needs of the human eye. This can not only improve the viewing experience of the image, but also enhance the system's ability to capture and analyze the details of the indoor environment.
[0032] Furthermore, feature encoding is performed on the panoramic pixel enhanced image of the home environment to obtain the panoramic enhanced feature vector of the home environment, in order to convert visual information into a numerical feature representation that can be understood and processed by the computer, thereby supporting the efficient operation and intelligent decision-making of the smart home system. After the panoramic pixel enhanced image of the home environment is processed by the enhancement generator, the image quality is significantly improved, including clarity, contrast, and detail performance. However, for the remote intelligent control system of the integrated ceiling, it is not enough to have high-quality images. What is more important is to be able to extract meaningful information and features from the image. Feature encoding can reduce the complexity and dimension of the data, thereby improving the efficiency of data processing and storage. By using an appropriate feature encoding algorithm, the system can convert the high-dimensional data of the original image into a low-dimensional feature vector while retaining enough information to support subsequent analysis and decision-making processes.
[0033] In a specific embodiment of the present application, the panoramic pixel enhancement feature encoding subunit 1212 includes: passing the home environment panoramic pixel enhanced image through a home environment panoramic convolutional neural network based on a hybrid convolutional layer to obtain a home environment panoramic enhancement feature map; downsampling the home environment panoramic enhancement feature map to obtain the home environment panoramic enhancement feature vector.
[0034] It should be understood that the hybrid convolution layer is a technique that combines convolution kernels of different scales and directions for convolution operations. This layer can effectively capture features at different levels in the image, including edges, textures, shapes, etc. In the home environment panoramic convolutional neural network, the use of hybrid convolution layers can enhance the ability to understand complex indoor environments, thereby more accurately analyzing key information such as furniture layout, personnel activities, and light distribution. Neural networks based on hybrid convolution layers can automatically learn and extract abstract features in images. Through multi-level convolution operations and pooling layers, the network can gradually convert the input enhanced image into higher-level and more abstract feature representations that are easier for intelligent systems to understand and process. For example, the network can extract important information such as the structure of the room, the shape of objects, and spatial relationships from the original image. Specifically, each hybrid convolutional layer of the home environment panoramic convolutional neural network based on the hybrid convolutional layer includes a parallel first convolution branch structure, a second convolution branch structure, a third convolution branch structure and a fourth convolution branch structure, and a multi-scale fusion structure connected to the first to fourth convolution branch structures, wherein the first convolution branch uses a first convolution kernel having a first size, the second convolution branch uses a second convolution kernel having a first size and a first void ratio, the third convolution branch uses a third convolution kernel having a first size and a second void ratio, and the fourth convolution branch uses a fourth convolution kernel having a first size and a third void ratio. More specifically, each hybrid convolutional layer of the home environment panoramic convolutional neural network based on the hybrid convolutional layer is further used to perform the following on the input data in the forward pass of the layer: use a first convolution kernel with a first size to perform convolution encoding on the home environment panoramic pixel enhanced image to obtain a first scale feature map; use a second convolution kernel with a first void rate to perform convolution encoding on the home environment panoramic pixel enhanced image to obtain a second scale feature map; use a third convolution kernel with a second void rate to perform convolution encoding on the home environment panoramic pixel enhanced image to obtain a third scale feature map; use a fourth convolution kernel with a third void rate to perform convolution encoding on the home environment panoramic pixel enhanced image to obtain a third scale feature map. A fourth-scale feature map is obtained, wherein the first convolution kernel, the second convolution kernel, the third convolution kernel and the fourth convolution kernel have the same size, and the second convolution kernel, the third convolution kernel and the fourth convolution kernel have different hole rates; the first-scale feature map, the second-scale feature map, the third-scale feature map and the fourth-scale feature map are aggregated along the channel dimension to obtain an aggregated feature map; the aggregated feature map is pooled to generate a pooled feature map; and the pooled feature map is activated to generate an activated feature map; wherein the output of the last layer of the convolutional neural network model including multiple mixed convolution layers is the home environment panoramic enhancement feature map.
[0035] Furthermore, the home environment panoramic enhancement feature map is downsampled to reduce the dimension and complexity of the data while retaining key information features to support the efficient operation and intelligent decision-making of the smart home system. The home environment panoramic enhancement feature map usually contains a large number of pixels and feature representations, which may be extracted and generated from the original image through a hybrid convolutional neural network. These feature maps may have high spatial resolution and dimension, and in practical applications, processing and storing such large-scale data will not only consume a lot of computing resources, but also increase the operating cost and complexity of the system. Through the downsampling operation, the spatial size and data volume of the feature map can be effectively reduced while retaining its main information features. Downsampling usually includes operations such as spatial average pooling or maximum pooling, which can aggregate the feature values of each region or area of the feature map into a smaller representation. For example, through a 2x2 maximum pooling operation, the maximum value of each 4-pixel region can be represented by a single pixel, thereby reducing the image size to one-fourth of the original.
[0036] In a specific embodiment of the present application, the user preference habit feature extraction unit 122 includes: passing the user air-conditioning preference habits through a user air-conditioning preference habit text semantic encoder to obtain a plurality of user air-conditioning preference habit text semantic feature vectors; passing the plurality of user air-conditioning preference habit text semantic feature vectors through a user air-conditioning preference habit text multi-scale feature extractor to obtain a user air-conditioning preference habit multi-scale associated feature vector.
[0037] It should be understood that user air conditioning preference habits usually cover user preferences and habits for air conditioning settings, temperature preferences, usage time, etc. This information usually exists in text form, such as descriptions of users' daily life patterns, sensitivity to temperature changes, expectations for air conditioning operation modes, etc. Through text semantic encoders, these text descriptions can be converted into semantic feature vectors, which can more accurately express user intentions and preferences. Text semantic encoders are usually based on deep learning models, such as recurrent neural networks, long short-term memory networks, or Transformers. These models can capture semantic and contextual information in text data and convert it into dense vector representations. By learning the semantic structure and relationships of text, the encoder can map users' air conditioning preference habits into efficient mathematical features, which are more expressive and discriminative in the semantic space. Specifically, the user's air-conditioning preference habits are segmented to obtain a word sequence; the embedding layer of the user's air-conditioning preference habit text semantic encoder is used to map each word in the word sequence into a word embedding vector to obtain a sequence of word embedding vectors; the converter-based Bert model of the user's air-conditioning preference habit text semantic encoder is used to perform global context semantic encoding on the sequence of embedding vectors to obtain multiple user air-conditioning preference habit text semantic feature vectors.
[0038] Furthermore, the semantic feature vectors of multiple user air conditioning preference habits are processed by the multi-scale feature extractor of the user air conditioning preference habits text, aiming to fully understand and analyze the user's preferences and habits for air conditioning from different scales and angles, so as to achieve more accurate and personalized air conditioning control and service optimization. The semantic feature vector of the user air conditioning preference habits text may contain the user's diverse descriptions of air conditioning temperature, wind speed, working hours, etc. Through the multi-scale feature extractor, the system can analyze these descriptions at different levels and scales, such as changes from overall habits to specific details, so as to more comprehensively understand the user's needs and preferences. Among them, the multi-scale feature extractor usually combines multiple technologies, including convolutional neural networks, pyramid pooling, multi-scale attention mechanisms, etc. These technologies can extract features at different spatial and semantic levels, so that the system can capture the diversity and complexity of user preference habits. For example, through pyramid pooling, the global and local information of text semantic features can be captured at different resolutions, thereby forming a richer and more accurate feature representation.
[0039] In a specific embodiment of the present application, the user air-conditioning preference habit text multi-scale feature extractor includes: a first convolutional layer, a second convolutional layer parallel to the first convolutional layer, and a cascade layer connected to the first convolutional layer and the second convolutional layer, wherein the first convolutional layer uses a one-dimensional convolutional kernel with a first scale, and the second convolutional layer uses a one-dimensional convolutional kernel with a second scale.
[0040] It should be understood that, first, the first convolution layer uses a one-dimensional convolution kernel with a first scale. One-dimensional convolution kernels are usually used to process text data and can capture local semantic features and structures in text sequences. For example, for the air conditioning usage habit text described by the user, the first convolution layer can extract information such as keywords, phrases, grammatical structures, etc. in the local window, which is essential for understanding user preferences and habits. Secondly, the second convolution layer in parallel with the first convolution layer uses a one-dimensional convolution kernel with a second scale. The second scale may be larger or smaller than the first scale, which means that it can capture text features at different scales. For example, a larger scale convolution kernel can help capture long-distance dependencies and global semantic structures, while a smaller scale convolution kernel can more keenly identify local semantic fragments and details. Next, a cascade layer is connected to the first convolution layer and the second convolution layer to integrate the features extracted at the two scales. This cascade design can fuse and strengthen feature representations at different levels, improving the model's expressive power and inference accuracy for user preference habit texts. Cascade layers usually integrate feature representations of different scales through pooling operations or feature fusion techniques, making the final feature vector richer and more representative. Combining these designs, the multi-scale feature extractor for user air conditioning preference and habit text can not only effectively process and analyze text data, but also improve the flexibility and adaptability of the model in semantic understanding and feature extraction. Through multi-scale convolution operations, the system can fully capture the diverse information in user preference and habit texts, providing a solid foundation for personalized air conditioning control and service optimization.
[0041] In the above-mentioned remote intelligent control system 100 for integrated ceiling, the air-conditioning outlet angle adjustment module 130 is used to determine whether the angle of the integrated ceiling air-conditioning outlet needs to be adjusted based on the panoramic enhancement feature vector of the home environment and the multi-scale correlation feature vector of the user's air-conditioning preference habits. It should be understood that the panoramic enhancement feature vector of the home environment reflects the characteristics and status of the entire room or home environment, such as temperature distribution, humidity level, lighting conditions, etc. These feature vectors are acquired and processed by sensors or smart devices, which can provide a global perspective on the indoor environment and help the system understand the overall situation of the current environment. The multi-scale correlation feature vector of the user's air-conditioning preference habits covers the user's personalized preferences and habits for the use of air conditioners. These feature vectors are obtained by analyzing the user's historical data, setting preferences, daily behavior patterns and other information, and can accurately describe the user's preferences for air-conditioning working parameters under different conditions, such as temperature settings, wind speed selection, working hours, etc. Therefore, based on the panoramic enhancement feature vector of the home environment and the multi-scale correlation feature vector of the user's air conditioning preference habits, it is judged whether the angle of the integrated ceiling air conditioning outlet needs to be adjusted. In this way, it can not only improve the intelligence level and user experience of the smart home system, but also achieve significant improvements and optimization in energy efficiency. This integrated design makes full use of data-driven intelligent technology and brings new possibilities and opportunities for the development of modern home air conditioning systems.
[0042] Figure 4 FIG. 1 is a block diagram of an air-conditioning outlet angle adjustment module in a remote intelligent control system of an integrated ceiling according to an embodiment of the present application. Figure 4 As shown, in a specific embodiment of the present application, the air-conditioning air supply vent angle adjustment module 130 includes: an air-conditioning air supply angle feature fusion unit 131, which is used to fuse the home environment panoramic enhancement feature vector and the user air-conditioning preference habit multi-scale correlation feature vector to obtain an air-conditioning air supply vent angle classification feature vector; an air-conditioning air supply angle feature optimization unit 132, which is used to perform adaptive stretching-compression optimization on the air-conditioning air supply vent angle classification feature vector based on bidirectional linear manifold modulation to obtain an optimized air-conditioning air supply vent angle classification feature vector; an air-conditioning air supply adjustment angle classification unit 133, which is used to pass the optimized air-conditioning air supply vent angle classification feature vector through a classifier to obtain a classification result, and the classification result is used to determine whether the angle of the integrated ceiling air-conditioning air supply vent needs to be adjusted.
[0043] It should be understood that the purpose of fusing the panoramic enhancement feature vector of the home environment and the multi-scale correlation feature vector of the user's air conditioning preference habits to obtain the air conditioning outlet angle classification feature vector is to achieve intelligent, personalized and energy-efficient air conditioning air supply control. This comprehensive design not only improves the user's quality of life and comfort, but also helps to establish an environmentally friendly and energy-saving smart home environment.
[0044] Furthermore, in the technical solution of the present application, considering that different home environments have differences in layout, decoration, furniture placement, etc., these factors will affect the feature extraction of panoramic images, resulting in differences in the distribution of feature vectors in local areas. The user's air conditioning preference habits may vary due to personal comfort, health status, living habits and other factors. This diversity may lead to uneven local distribution of feature vectors in the text semantic encoding and multi-scale feature extraction process. The home environment panoramic convolutional neural network and the user air conditioning preference habit text multi-scale feature extractor may not be able to fully capture all relevant feature information, or have different sensitivities to certain features, resulting in differences in the distribution of feature vectors in local areas. When fusing the home environment panoramic enhancement feature vector and the user air conditioning preference habit multi-scale correlation feature vector, the importance and weights of different features may not be properly processed, resulting in inconsistency in the fused air conditioning outlet angle classification feature vector in some local areas, resulting in the air conditioning outlet angle classification feature vector being classified by the classifier. There is a class harmony offset relative to the predetermined class label of the classifier, affecting the classification iteration effect. Based on this, the air-conditioning outlet angle classification feature vector is subjected to adaptive stretching-compression optimization based on bidirectional linear manifold modulation.
[0045] Among them, the air-conditioning air outlet angle classification feature vector is subjected to adaptive stretching-compression optimization based on bidirectional linear manifold modulation to obtain an optimized air-conditioning air outlet angle classification feature vector, including: determining a weight learning parameter matrix of the classifier; extracting each column vector in the weight learning parameter matrix to obtain a set of weight learning parameter column vectors; using the following optimization formula to respectively calculate the metric correlation prediction factor between each weight learning parameter column vector in the set of weight learning parameter column vectors and the air-conditioning air outlet angle classification feature vector to obtain a metric correlation prediction factor modulation vector, wherein the optimization formula is:
[0046]
[0047] Among them, V i represents each weight learning parameter column vector in the set of weight learning parameter column vectors, V c represents the air-conditioning outlet angle classification feature vector, It means subtracting by position. is the superposition norm of the two norms of the eigenvectors, ‖·‖ F is the Frobenius norm of the eigenvector, M p represents the weight learning parameter matrix, exp(·) represents the exponential operation with the natural constant e as the base, V pRepresenting the metric correlation prediction factor modulation vector; using the metric correlation prediction factor modulation vector as the weight vector, calculating the point-by-point multiplication between the metric correlation prediction factor modulation vector and the air-conditioning air supply outlet angle classification feature vector to obtain the optimized air-conditioning air supply outlet angle classification feature vector.
[0048] In the technical solution of the present application, it is considered that there are local distribution differences in the air-conditioning air outlet angle classification feature vector, which leads to the problem that when it is classified by the classifier, there will be a class harmony offset relative to the predetermined class label of the classifier, affecting the classification iteration effect. Based on this, in the technical solution of the present application, the air-conditioning air outlet angle classification feature vector is subjected to adaptive stretching-compression optimization based on bidirectional linear manifold modulation, which uses the superposition paradigm of the two norms between each column vector in the weight learning parameter matrix of the classifier and the air-conditioning air outlet angle classification feature vector as the subclass label related metric integral factor and the matrix norm of the weight learning parameter of the classifier as the differential factor, and then uses the association paradigm between the subclass label related metric integral factor and the differential factor to perform bidirectional linear manifold modulation on the air-conditioning air outlet angle classification feature vector, thereby improving the local feature distribution consistency of the air-conditioning air outlet angle classification feature vector by adaptively stretching-compressing the air-conditioning air outlet angle classification feature vector, thereby reducing the harmony offset of the air-conditioning air outlet angle classification feature vector relative to the predetermined class label of the classifier, thereby improving the accuracy of the classification result.
[0049] Furthermore, the optimized air outlet angle classification feature vector is processed by the classifier in the deep learning model. After the previous feature extraction and fusion, the optimized air outlet angle classification feature vector contains indoor environmental characteristics, user preferences and other possible key information to achieve the best air supply effect and uniform distribution of indoor air.
[0050] In summary, the embodiment of the present application first obtains the panoramic image of the environment and the user's preference habits collected by the camera, and then uses deep learning technology to perform feature extraction and correlation analysis on the two. Finally, a classifier is used to obtain the classification result to determine whether the angle of the integrated ceiling air-conditioning outlet needs to be adjusted, so as to achieve the best comfort effect and provide a personalized comfort experience.
[0051] As described above, the remote intelligent control system 100 for the integrated ceiling according to the embodiment of the present application can be implemented in various terminal devices. In one example, the remote intelligent control system 100 for the integrated ceiling can be integrated into the terminal device as a software module and / or a hardware module. For example, the remote intelligent control system 100 for the integrated ceiling can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the remote intelligent control system 100 for the integrated ceiling can also be one of the many hardware modules of the terminal device.
[0052] Alternatively, in another example, the remote intelligent control system 100 of the integrated ceiling and the terminal device may also be separate devices, and the remote intelligent control system 100 of the integrated ceiling may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.
[0053] Figure 5 FIG. 1 is a flow chart of a remote intelligent control method for an integrated ceiling according to an embodiment of the present application. Figure 5 As shown, according to the remote intelligent control method of the integrated ceiling of the embodiment of the present application, it includes: S110, acquiring the environment panoramic image collected by the camera and the user preference habits; S120, extracting the home environment panoramic enhancement feature vector and the user air-conditioning preference habit multi-scale correlation feature vector from the environment panoramic image collected by the camera and the user preference habits; S130, based on the home environment panoramic enhancement feature vector and the user air-conditioning preference habit multi-scale correlation feature vector, judging whether the integrated ceiling air-conditioning air outlet angle needs to be adjusted.
[0054] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned remote intelligent control method of the integrated ceiling have been described in the above reference. Figures 1 to 4 The description of the remote intelligent control system of the integrated ceiling has been introduced in detail, and therefore, its repeated description will be omitted.
[0055] Below, reference Figure 6 To describe an electronic device according to an embodiment of the present application.
[0056] Figure 6 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:
[0057] The processor 11 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in the embodiment of the present application; the memory 12 can be implemented in the form of a read-only memory (Read Only Memory, ROM), a static storage device, a dynamic storage device or a random access memory (Random Access Memory, RAM), etc.
[0058] The memory 12 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 12, and the processor 11 calls and executes the remote intelligent control method of the integrated ceiling in the embodiment of the present application;
[0059] Input / output interface 13, used to implement information input and output;
[0060] The communication interface 14 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);
[0061] A bus 15 that transmits information between the various components of the device (e.g., the processor 11, the memory 12, the input / output interface 13, and the communication interface 14);
[0062] The processor 11 , the memory 12 , the input / output interface 13 and the communication interface 14 are connected to each other in communication within the device via a bus 15 .
[0063] An embodiment of the present application further provides a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the remote intelligent control method of the above-mentioned integrated ceiling is implemented.
[0064] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0065] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0066] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0067] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0068] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0069] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0070] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0071] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0072] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0073] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-On lyMemory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs. The preferred embodiment of the embodiment of the present application is described above with reference to the accompanying drawings, and the scope of rights of the embodiment of the present application is not limited thereto. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of rights of the embodiments of the present application.
Claims
1. A remote intelligent control system for an integrated ceiling, characterized in that: include: Integrated ceiling air conditioning data acquisition module, used to obtain the environment panoramic image and user preference habits collected by the camera; An integrated ceiling air conditioning data extraction module is used to extract a home environment panoramic enhancement feature vector and a user air conditioning preference habit multi-scale correlation feature vector from the environment panoramic image collected by the camera and the user preference habit; The air-conditioning outlet angle adjustment module is used to determine whether the angle of the integrated ceiling air-conditioning outlet needs to be adjusted based on the panoramic enhancement feature vector of the home environment and the multi-scale correlation feature vector of the user's air-conditioning preference habits.
2. The remote intelligent control system of the integrated ceiling according to claim 1, characterized in that: The integrated ceiling air conditioner data extraction module includes: A home environment panoramic image feature extraction unit, used for extracting features from the home environment panoramic image captured by the camera to obtain the home environment panoramic enhancement feature vector; The user preference habit feature extraction unit is used to extract features of the user's air-conditioning preference habits to obtain a multi-scale correlation feature vector of the user's air-conditioning preference habits.
3. The remote intelligent control system of the integrated ceiling according to claim 2 is characterized in that: The home environment panoramic image feature extraction unit comprises: A home environment panoramic image pixel enhancement subunit, used for passing the home environment panoramic image collected by the camera through a home environment panoramic pixel enhancement generator to obtain a home environment panoramic pixel enhanced image; The panoramic pixel enhancement feature encoding subunit is used to perform feature encoding on the panoramic pixel enhancement image of the home environment to obtain the panoramic enhancement feature vector of the home environment.
4. The remote intelligent control system of the integrated ceiling according to claim 3 is characterized in that: The panoramic pixel enhancement feature encoding subunit includes: Passing the home environment panoramic pixel enhanced image through a home environment panoramic convolutional neural network based on a hybrid convolutional layer to obtain a home environment panoramic enhanced feature map; The home environment panoramic enhancement feature map is downsampled to obtain the home environment panoramic enhancement feature vector.
5. The remote intelligent control system of the integrated ceiling according to claim 4, characterized in that: The user preference habit feature extraction unit comprises: Passing the user's air conditioning preference habits through a user's air conditioning preference habit text semantic encoder to obtain a plurality of user's air conditioning preference habit text semantic feature vectors; The multiple user air-conditioning preference habit text semantic feature vectors are passed through a user air-conditioning preference habit text multi-scale feature extractor to obtain a user air-conditioning preference habit multi-scale associated feature vector.
6. The remote intelligent control system of the integrated ceiling according to claim 5, characterized in that: The user air conditioning preference habit text multi-scale feature extractor includes: a first convolution layer, a second convolution layer parallel to the first convolution layer, and a cascade layer connected to the first convolution layer and the second convolution layer, wherein the first convolution layer uses a one-dimensional convolution kernel with a first scale, and the second convolution layer uses a one-dimensional convolution kernel with a second scale.
7. The remote intelligent control system of the integrated ceiling according to claim 6, characterized in that: The air-conditioning air outlet angle adjustment module comprises: An air-conditioning air supply angle feature fusion unit, used to fuse the home environment panoramic enhancement feature vector and the user air-conditioning preference habit multi-scale correlation feature vector to obtain an air-conditioning air supply vent angle classification feature vector; An air-conditioning air supply angle feature optimization unit, used for performing adaptive stretching-compression optimization on the air-conditioning air supply vent angle classification feature vector based on bidirectional linear manifold modulation to obtain an optimized air-conditioning air supply vent angle classification feature vector; The air conditioning air supply adjustment angle classification unit is used to pass the optimized air conditioning air supply vent angle classification feature vector through a classifier to obtain a classification result, and the classification result is used to determine whether the integrated ceiling air conditioning air supply vent angle needs to be adjusted.
8. The remote intelligent control system of the integrated ceiling according to claim 7, characterized in that: The air conditioner air supply angle characteristic optimization unit comprises: Determining a weight learning parameter matrix of the classifier; Extracting each column vector in the weight learning parameter matrix to obtain a set of weight learning parameter column vectors; Respectively calculating the metric correlation prediction factor between each weight learning parameter column vector in the set of weight learning parameter column vectors and the air conditioner air outlet angle classification feature vector to obtain a metric correlation prediction factor modulation vector; The metric correlation prediction factor modulation vector is used as a weight vector, and the position point multiplication between the metric correlation prediction factor modulation vector and the air conditioning air supply outlet angle classification feature vector is calculated to obtain the optimized air conditioning air supply outlet angle classification feature vector.
9. A remote intelligent control method for an integrated ceiling, characterized in that: include: Obtaining the panoramic image of the environment and user preferences collected by the camera; Extracting a home environment panoramic enhancement feature vector and a user air conditioning preference habit multi-scale correlation feature vector from the environment panoramic image captured by the camera and the user preference habit; Based on the panoramic enhancement feature vector of the home environment and the multi-scale correlation feature vector of the user's air-conditioning preference habits, it is determined whether the angle of the integrated ceiling air-conditioning air outlet needs to be adjusted.
10. The remote intelligent control method of the integrated ceiling according to claim 9, characterized in that: Extracting a home environment panoramic enhancement feature vector and a user air conditioning preference habit multi-scale correlation feature vector from the environment panoramic image captured by the camera and the user preference habit, including: Performing feature extraction on the home environment panoramic image captured by the camera to obtain the home environment panoramic enhancement feature vector; Feature extraction is performed on the user's air-conditioning preference habits to obtain a multi-scale associated feature vector of the user's air-conditioning preference habits.
Citation Information
Patent Citations
Air supply control method of air conditioner, air conditioner and storage medium
CN110195923A
Air conditioner control method, air conditioner and computer readable storage medium
CN112923537A
Air conditioner wind direction intelligent control method and system based on flow field information prediction
CN113719974A
Control method, device and equipment of air conditioning system and storage medium
CN114251798A
Air conditioner control method and device based on air conditioner intelligent monitoring and environment data collection
CN115727475A
Cited By
Intelligent control method for storage environment of tea storage cabinet
CN119717969A
