Intelligent positioning air conditioner panel system and method under building heating ventilation and air conditioning centralized control scene

Abstract

The application provides an intelligent positioning air conditioner panel system and method under a building heating and ventilation centralized control scene; the method comprises the following steps: obtaining an air conditioner panel positioning instruction; obtaining a feature matrix of a space of the air conditioner panel according to the air conditioner panel positioning instruction; generating a unique physical address code of the air conditioner panel according to the feature matrix; and generating unique positioning information of the air conditioner panel according to the unique physical address code. The method can construct the relationship between the space feature of the air conditioner panel and the unique positioning information of the air conditioner panel, and can more conveniently obtain the positioning information of the air conditioner panel and modify the communication address of the air conditioner panel.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of digital control, and particularly relates to an intelligent positioning air conditioner panel system and method in a building heating and ventilation centralized control scene. BACKGROUND

[0002] With the development of air conditioner control technology, digital control air conditioner technology appears, and the technology can be used to control the air conditioner indoor unit in a room, thereby reducing the situation that the central air conditioner cannot control individual air conditioner indoor units.

[0003] In the digital control air conditioner technology, a gateway and an air conditioner controller are added to a centralized control system, after the system is powered on, the communication address of the air conditioner panel and the unique address number of the corresponding indoor unit are set, and the binding with the room is completed through the panel query in the room, so that the air conditioner indoor unit in the room is controlled through the air conditioner panel in the room.

[0004] However, when the physical structure of the building space changes (such as wall removal and function area reconstruction), the physical position of the original binding panel deviates from the system logical position, and the effective control of the air conditioner requires changing the communication address of the control panel according to the original construction drawing, which lacks convenience. SUMMARY

[0005] Therefore, it is necessary to provide an intelligent positioning air conditioner panel system and method in a building heating and ventilation centralized control scene.

[0006] The application provides an intelligent positioning air conditioner panel method in a building heating and ventilation centralized control scene, which comprises the following steps:

[0007] An air conditioner panel positioning instruction is obtained;

[0008] According to the air conditioner panel positioning instruction, a feature matrix of the space of the air conditioner panel is obtained;

[0009] According to the feature matrix, a unique physical address code of the air conditioner panel is generated;

[0010] According to the unique physical address code, unique positioning information of the air conditioner panel is generated.

[0011] Further, according to the air conditioner panel positioning instruction, the feature matrix of the space of the air conditioner panel is obtained, which comprises the following steps:

[0012] According to the air conditioner panel positioning instruction, the altitude, space number and space structure diagram of the space where the air conditioner panel is located are obtained;

[0013] The altitude, space number and space structure diagram are input into a space neural network model to obtain the feature matrix of the space.

[0014] Furthermore, the spatial neural network model includes:

[0015] Input layer: Used to input altitude, spatial number, and spatial structure diagram;

[0016] Multi-layer graph convolutional layers: used to extract local and intermediate features of the spatial structure map, resulting in a feature map of the spatial structure; the output of each multi-layer graph convolutional layer serves as the input to the next multi-layer graph convolutional layer; the convolution output formula in the multi-layer graph convolutional layer is: ,in, It is the number of convolutional layers. It is the first The output matrix of the layer, It is the convolution kernel weight matrix. It is the input matrix. It is a non-linear activation function. The bias parameters of the convolutional layer;

[0017] Pooling layers: used to compress the spatial dimension of feature maps to obtain dimensionality-reduced feature maps;

[0018] Extended layer: used to expand the altitude and spatial numbering into a spatial feature map of the same size as the reduced feature map, resulting in an altitude feature map and a numbering feature map;

[0019] Fully connected layer: used to comprehensively analyze the dimensionality-reduced feature map, elevation feature map, and numbered feature map, and calculate the feature matrix;

[0020] Output layer: Used to output the feature matrix.

[0021] Furthermore, based on the feature matrix, a unique physical address code for the air conditioner panel is generated, including:

[0022] Based on the feature matrix, a hash mapping table is constructed to obtain the feature mapping matrix of the space;

[0023] Based on the space-filling curve algorithm, the feature mapping matrix is ​​mapped to obtain a one-dimensional feature sequence;

[0024] Binarize and XOR the one-dimensional feature sequence to encode a unique address.

[0025] The one-dimensional feature sequence is obtained through the following formula:

[0026]

[0027] in, It is a one-dimensional feature sequence. It is the feature mapping matrix. It is the sequence number The coordinates of the feature mapping matrix corresponding to each bit;

[0028] Where the sequence number is The digit is calculated using the following formula:

[0029]

[0030] in, It is the sequence position. It is the x-coordinate of the feature mapping matrix. It is the ordinate of the feature mapping matrix. It is a function to extract binary values. It is the number of binary bits in the feature map coordinates.

[0031] Furthermore, based on the feature matrix, a hash mapping table is constructed to obtain the feature mapping matrix of the space, including:

[0032] The feature matrix is ​​normalized to obtain the normalized feature matrix;

[0033] Based on the normalized feature matrix, a preprocessed feature matrix is ​​obtained using a dimensionality reduction algorithm;

[0034] Based on the preprocessed feature matrix, the hash key corresponding to the preprocessed feature matrix is ​​determined using the multiplicative hash algorithm, and a hash mapping table is obtained.

[0035] Based on the hash map table, the feature mapping matrix of the space is obtained using the following formula:

[0036]

[0037] in, It is the feature mapping matrix. It is a fusion weight. It is a preprocessed feature matrix. Hash matrix;

[0038] The hash matrix is ​​calculated using the following formula:

[0039]

[0040] in, It is a hash matrix of Yuan, It is a number system conversion function. It is a hash key. It is the size of the hash matrix.

[0041] Furthermore, based on the unique physical address code, unique location information for the air conditioner panel is generated, including:

[0042] Obtain the indoor unit number of the air conditioner in the space;

[0043] According to the air conditioner inner machine number and the unique physical address code, the unique positioning information of the air conditioner panel is generated.

[0044] Further, the intelligent positioning air conditioner panel method under the building heating and ventilation centralized control scene further comprises:

[0045] Obtain space change information; the space change information comprises a transformation space number;

[0046] According to the transformation space number, a hash mapping table is matched to obtain a new feature mapping matrix;

[0047] According to the new feature mapping matrix, the new unique positioning information of the air conditioner panel is updated.

[0048] Further, the present application also provides a system for implementing the intelligent positioning air conditioner panel method under the building heating and ventilation centralized control scene, comprising:

[0049] An instruction obtaining module is configured to obtain an air conditioner panel positioning instruction;

[0050] A feature information obtaining module is configured to obtain a feature matrix of a space of the air conditioner panel according to the air conditioner panel positioning instruction;

[0051] An address code generating module is configured to generate a unique physical address code of the air conditioner panel according to the feature matrix;

[0052] A positioning information generating module is configured to generate unique positioning information of the air conditioner panel according to the unique physical address code.

[0053] Further, the present application also provides a computer device comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above-mentioned intelligent positioning air conditioner panel method under the building heating and ventilation centralized control scene when executing the computer program.

[0054] Further, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above-mentioned intelligent positioning air conditioner panel method under the building heating and ventilation centralized control scene.

[0055] The present application has the following beneficial effects:

[0056] The application provides an intelligent positioning air conditioner panel system and method under a building heating and ventilation centralized control scene. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0058] Figure 1 A flowchart of an intelligent positioning air conditioner panel method under a building heating and ventilation centralized control scene is provided for an exemplary embodiment of the present application.

[0059] Figure 2 A structural block diagram of an intelligent positioning air conditioner panel system under a building heating and ventilation centralized control scene is provided for an exemplary embodiment of the present application.

[0060] Figure 3 A structural block diagram of a computer device of an intelligent positioning air conditioner panel under a building heating and ventilation centralized control scene is provided for an exemplary embodiment of the present application.

[0061] In the figure: 201 - instruction acquisition module; 202 - feature information acquisition module; 203 - address code generation module; 204 - positioning information generation module; 301 - processor; 302 - memory; 303 - sensor. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0063] The method of the intelligent positioning air conditioner panel under the building heating and ventilation centralized control scene provided by the embodiments of the present application can be applied to the application scene of setting the air conditioner panel communication address and positioning information by the user.

[0064] In one embodiment, as Figure 1As shown, a method for intelligently positioning an air conditioner panel in a building HVAC centralized control scenario is provided. In this embodiment, the method is applied to a terminal. It should be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction of the terminal and the server. In this embodiment, the method includes the following steps:

[0065] In step S101, an air conditioner panel positioning instruction is obtained.

[0066] Specifically, the terminal obtains an air conditioner panel positioning instruction. Illustratively, the instruction can be input by a user according to the demand for configuring the air conditioner panel. Before inputting the instruction, the user can have prepared a plan for the air conditioner panel, the corresponding air conditioner indoor unit, and the placement space in advance.

[0067] In step S102, a feature matrix of the space of the air conditioner panel is obtained according to the air conditioner panel positioning instruction.

[0068] Specifically, the terminal obtains the feature information of the space of the air conditioner panel according to the positioning instruction, extracts features from the feature information, and generates a feature matrix of the space. Illustratively, the feature information of the space can be input by the user and can include a photo of the space, name representation information, and a floor on which the space is located.

[0069] In step S103, a unique physical address code of the air conditioner panel is generated according to the feature matrix.

[0070] Specifically, the terminal performs dimension reduction, merging, and padding operations according to the feature matrix to generate a unique physical address code of the air conditioner panel. Illustratively, the unique physical address code can represent the unique physical address information of the space, and the unique physical address code can be applied to other air conditioner panels placed in the same space.

[0071] In step S104, unique positioning information of the air conditioner panel is generated according to the unique physical address code.

[0072] Specifically, the terminal generates unique positioning information of the air conditioner panel according to the unique physical address code in combination with the information of the air conditioner indoor unit controlled by the air conditioner panel. Illustratively, the unique positioning information can be in a unique correspondence relationship with the air conditioner panel and the air conditioner indoor unit controlled thereby.

[0073] In this embodiment, by obtaining an air conditioner panel positioning instruction, extracting features of the space where the air conditioner panel is located, generating a unique address information of the air conditioner panel according to the feature matrix of the space, and generating unique positioning information of the air conditioner panel according to the unique address information of the air conditioner panel and the information of the air conditioner indoor unit controlled thereby, a mapping relationship between the space features and the unique address information of the air conditioner panel is established, and the convenience of adjusting the unique positioning information of the air conditioner panel and modifying the communication address is improved.

[0074] In one of the embodiments, according to the air conditioner panel positioning instruction, a feature matrix of a space where the air conditioner panel is located is obtained, including:

[0075] S201, according to the air conditioner panel positioning instruction, the altitude, space number and space structure diagram of the space where the air conditioner panel is located are obtained.

[0076] Specifically, the terminal obtains the altitude, space number and space structure diagram of the space where the air conditioner panel is located according to the air conditioner panel positioning instruction. Illustratively, the altitude, space number and space structure diagram of the space can be input by the user. Alternatively, the space number can be set by the user according to the demand, which can be a room number. Illustratively, the space structure diagram can be a building drawing, a 3D model and a panoramic photo of the room.

[0077] S202, the altitude, space number and space structure diagram are input into a space neural network model to obtain a feature matrix of the space.

[0078] Specifically, the terminal inputs the altitude, space number and space structure diagram of the space into the space neural network model to obtain the feature matrix of the space. Illustratively, the space neural network model can be a convolutional neural network. Alternatively, the feature matrix contains the altitude, space number and space structure feature information of the space, and the feature matrix can be a unique feature matrix representing the space.

[0079] The embodiment obtains the altitude, space number and space structure feature of the space where the air conditioner panel is located, and obtains a unique feature matrix of the space based on the space neural network model.

[0080] In one of the embodiments, the space neural network model includes:

[0081] Input layer: used for inputting the altitude, space number and space structure diagram.

[0082] Specifically, the input layer is used to receive the altitude, space number and space structure diagram of the space where the air conditioner panel is located. Illustratively, the altitude can be in the form of pure numbers. Alternatively, the space number can include numbers and letters. Illustratively, the space structure diagram can be a building drawing, a 3D model and a panoramic photo of the room.

[0083] Multi-layer graph convolution layer: used for extracting local features and intermediate features of the space structure diagram to obtain a feature map of the space structure; wherein the output of each multi-layer graph convolution layer is used as the input of the next multi-layer graph convolution layer; the convolution output formula in the multi-layer graph convolution layer is: wherein, is the number of convolution layers, is the number of input features of the i-th convolution layer, the output matrix of the layer, is a convolution kernel weight matrix, is an input matrix, is a nonlinear activation function, is a bias parameter of the convolution layer.

[0084] Specifically, the role of the multi-layer graph convolution base layer is to extract local features and intermediate features of the spatial structure graph through layer-by-layer convolution operations, and generate a feature map. The output of each layer will be used as the input of the next layer, forming a layer-by-layer progressive feature extraction process. Illustratively, is the output matrix of the layer, which can be used as the input matrix of the layer +1. Optionally, is a convolution kernel weight matrix, which can be set according to the characteristics of the features to be extracted and the input matrix. Illustratively, is an input matrix, which can be a spatial structure graph or the output matrix of the layer -1. Optionally, is an activation function, which can be a ReLU function. is a bias parameter of the convolution layer, which can be set according to the output channels of the convolution kernel.

[0085] Pooling layer: used to compress the spatial dimension of the feature map to obtain a reduced dimension feature map.

[0086] Specifically, the role of the pooling layer is to reduce the size of the feature map through dimension reduction operation while preserving important feature information, to obtain a reduced dimension feature map. Illustratively, the user can set the pooling window size and step of the pooling operation according to the user's needs, and generate a reduced dimension feature map that meets the user's requirements.

[0087] Expansion layer: used to expand the altitude and spatial number into a spatial feature map with the same size as the reduced dimension feature map, to obtain an altitude feature map and a number feature map.

[0088] Specifically, the role of the expansion layer is to convert the altitude and spatial number into matrices consistent with the size of the reduced dimension feature map, to generate an altitude feature map and a number feature map, ensuring that the reduced dimension feature map, the altitude feature map, and the number feature map can be fused and processed in the same spatial dimension.

[0089] Fully connected layer: used to comprehensively analyze the reduced dimension feature map, the altitude feature map, and the number feature map, to calculate a feature matrix.

[0090] Specifically, the role of the fully connected layer is to receive the reduced dimension feature map, the altitude feature map, and the number feature map, apply linear transformation and nonlinear activation function, and calculate a feature matrix. Illustratively, the feature matrix contains comprehensive information of the spatial structure, altitude, and spatial number.

[0091] Output layer: used for outputting the feature matrix.

[0092] Specifically, the output layer is used to output the feature matrix calculated by the fully connected layer.

[0093] In this embodiment, the space neural network model is constructed, the convolution layer, the pooling layer and the output layer are reasonably set, the altitude, the space number and the space structure feature of the space where the air conditioner panel is located are comprehensively considered, and the unique feature matrix of the space is calculated.

[0094] In one of the embodiments, according to the feature matrix, a unique physical address code of the air conditioner panel is generated, including:

[0095] S401, according to the feature matrix, a hash mapping table is constructed to obtain a feature mapping matrix of the space.

[0096] Specifically, according to the feature matrix, a hash mapping table is constructed to obtain a hash matrix corresponding to the feature matrix, the feature matrix is preprocessed, and the preprocessed feature matrix and the corresponding hash matrix obtained by preprocessing are weighted and combined to obtain a feature mapping matrix. Illustratively, the preprocessing can include normalization and dimensionality reduction.

[0097] S402, based on the space filling curve algorithm, the feature mapping matrix is mapped to obtain a one-dimensional feature sequence.

[0098] Specifically, based on the space filling curve algorithm, the elements in the feature mapping matrix are sorted and filled according to certain rules, and the feature mapping matrix is mapped to obtain a corresponding one-dimensional feature sequence. Illustratively, the space filling curve can be a Z-order curve.

[0099] S403, the one-dimensional feature sequence is binarized and XOR processed to obtain a unique address code.

[0100] Specifically, according to a predetermined threshold, the terminal performs binarization processing on the one-dimensional feature sequence to obtain a one-dimensional sequence composed of 0 and 1; for the one-dimensional sequence, according to the predetermined address code length, segment XOR is performed to obtain a unique address code. Illustratively, the user can set the threshold according to the demand of the space feature. Alternatively, the user can set the predetermined address code length according to the unified management needs of the address length of the air conditioner panel.

[0101] wherein the one-dimensional feature sequence is obtained by the following formula:

[0102]

[0103] wherein, is the one-dimensional feature sequence, is a feature mapping matrix, is a sequence of is a feature mapping matrix coordinate corresponding to the bit;

[0104] is a sequence of is calculated by the following formula:

[0105]

[0106] is a sequence of is a sequence of is a horizontal coordinate of the feature mapping matrix, is a vertical coordinate of the feature mapping matrix, is a binary value function, is a number of binary bits of the feature mapping coordinate.

[0107] Specifically, according to the feature mapping matrix, elements corresponding to coordinates in the feature mapping matrix are sorted in a one-dimensional index bit order to obtain a one-dimensional feature sequence, wherein coordinates of each element in the feature mapping matrix are calculated, and a one-dimensional index bit order to which the element is mapped is obtained by alternately arranging and weightedly summing binary bits of the horizontal coordinate and the vertical coordinate in the coordinate. Illustratively, the one-dimensional feature sequence can be the only one-dimensional feature sequence of the space. Optionally, the feature mapping matrix can be obtained by weightedly combining a feature matrix and a hash matrix corresponding to the feature matrix. Illustratively, the one-dimensional index bit order can be determined by Z-order curve calculation. Illustratively, the sequence bit can be an index bit corresponding to a conversion of any element in the feature mapping matrix into a one-dimensional sequence. Optionally, the horizontal coordinate of the feature mapping matrix can be a horizontal coordinate corresponding to any element in the feature mapping matrix. Illustratively, the vertical coordinate of the feature mapping matrix can be a vertical coordinate corresponding to any element in the feature mapping matrix. Optionally, the binary value function can convert a decimal number into a corresponding binary number. Illustratively, the number of binary bits of the feature mapping coordinate can be a number of decimal bits of the feature mapping coordinate obtained by conversion.

[0108] The embodiment converts a feature matrix into a feature mapping matrix by constructing a hash mapping table, maps a one-dimensional feature sequence by using a space-filling curve algorithm, converts a unique address code by binaryzation and XOR processing, converts the unique feature matrix of the space to obtain the unique address code of the space, retains the space features, simplifies the data structure, optimizes the storage and retrieval efficiency of the features, and improves the distinguishability and uniqueness of the unique address code.

[0109] In one embodiment, a hash mapping table is constructed according to a feature matrix to obtain a feature mapping matrix of a space, including:

[0110] S501, normalize the feature matrix to obtain a normalized feature matrix.

[0111] Specifically, the feature matrix is normalized to obtain a normalized feature matrix. Illustratively, the feature matrix can be normalized by a min-max normalization method.

[0112] S502, according to the normalized feature matrix, a pre-processing feature matrix is obtained based on a dimension reduction algorithm.

[0113] Specifically, according to the normalized feature matrix, a pre-processing feature matrix is obtained based on a dimension reduction algorithm. Illustratively, the dimension reduction algorithm can be principal component analysis.

[0114] S503, according to the pre-processing feature matrix, a hash key corresponding to the pre-processing feature matrix is determined based on a multiplication hash algorithm, and a hash mapping table is obtained.

[0115] Specifically, according to the pre-processing feature matrix, a hash key corresponding to the pre-processing feature matrix is determined based on a multiplication hash algorithm, and a hash mapping table is obtained. Illustratively, based on the multiplication hash algorithm, the pre-processing feature matrix is multiplied with a randomly generated hash matrix element by element, and then the result is modulated to obtain the hash key corresponding to the pre-processing feature matrix. Optionally, the user can store the pre-processing feature matrix and the corresponding hash key of several spaces according to the demand to obtain the hash mapping table.

[0116] S504, according to the hash mapping table, the feature mapping matrix of the space is obtained using the following formula:

[0117]

[0118] wherein, is the feature mapping matrix, is the fusion weight, is the pre-processing feature matrix, is the hash matrix.

[0119] wherein, the hash matrix is calculated by the following formula:

[0120]

[0121] wherein, is the hash matrix of the element, is the base conversion function, is the hash key, is the size of the hash matrix.

[0122] Specifically, the hash mapping table and the pre-processed feature matrix are combined by weighting to obtain a feature mapping matrix of the space, wherein the hash matrix is calculated by extracting a specific byte in the hash key and converting it into an integer. Illustratively, the feature mapping matrix can be a unique feature mapping matrix of the space. Optionally, a fusion weight can be used to control the contribution proportion of the pre-processed feature matrix and the hash matrix in the final feature mapping matrix, and the user can set the fusion weight according to the space feature fusion requirement, and the numerical range of the fusion weight is [0, 1]. Illustratively, the pre-processed feature matrix can be a feature matrix that has been normalized and dimensionally reduced. Optionally, the hash matrix is composed of elements in the hash matrix. Illustratively, the base conversion function can convert two consecutive bytes in the hash key into an integer value. Optionally, the hash key can be a hash key corresponding to the pre-processed feature matrix. Illustratively, the size of the hash matrix can be determined by the size of the pre-processed feature matrix.

[0123] The embodiment improves the storage and retrieval efficiency of the space feature matrix by pre-processing the feature matrix, obtaining the corresponding hash key based on the multiplication hash algorithm, and constructing the hash mapping table. The corresponding hash key in the hash mapping table is converted into the corresponding hash matrix, and the hash matrix and the pre-processed feature matrix are combined by weighting to obtain the corresponding feature mapping matrix, ensuring the uniqueness of the features.

[0124] In one of the embodiments, the unique positioning information of the air conditioner panel is generated according to the unique physical address code, including:

[0125] S601, obtaining an air conditioner indoor unit number of a space.

[0126] S602, generating unique positioning information of an air conditioner panel according to the air conditioner indoor unit number and the unique physical address code.

[0127] Specifically, the terminal obtains the air conditioner indoor unit number controlled by the air conditioner panel in the space, and generates the unique positioning information of the air conditioner panel according to the number and the unique physical address code of the air conditioner panel. Illustratively, the air conditioner indoor unit number can be input by the user according to the requirement. Optionally, the user can set the communication address of the air conditioner panel according to the unique positioning information of the air conditioner panel.

[0128] The embodiment combines the information of the air conditioner panel controlling the indoor unit and the unique positioning information generated by the space features of the air conditioner panel, generates the unique positioning information, and ensures that the positioning information of the air conditioner panel contains the identification of the control device and combines the physical location features, thereby realizing accurate device positioning and management.

[0129] In one of the embodiments, the method further includes:

[0130] S701, obtain space change information; the space change information includes a transform space number.

[0131] S702, match a hash mapping table according to the transform space number to obtain a new feature mapping matrix.

[0132] S703, update new unique positioning information of the air conditioner panel according to the new feature mapping matrix.

[0133] Specifically, the terminal obtains space change information of a space where the air conditioner panel is located, the space change information including a transform space number; according to the transform space number, a hash mapping table is queried to obtain a preprocessed feature matrix, a hash key and a hash matrix corresponding to the new space, and a new feature mapping matrix is calculated; and according to the new feature mapping matrix, new unique positioning information of the air conditioner panel is updated. Illustratively, the space change information can be input by a user according to a transfer condition of the air conditioner panel. Alternatively, the user can update new unique positioning information of the air conditioner panel according to a new controlled indoor unit number of the air conditioner panel, and reset a communication address of the air conditioner panel according to the new unique positioning information.

[0134] The embodiment updates a corresponding new feature mapping matrix and new unique positioning information of the air conditioner panel by obtaining a transform space number of the air conditioner panel, so as to ensure that the positioning information of the air conditioner panel can adapt to space change, and provides precise and real-time positioning information for the air conditioner panel by matching a hash mapping table and updating a feature mapping matrix.

[0135] In the above method for intelligently positioning an air conditioner panel in a building heating and ventilation centralized control scene, a space feature matrix of a space where the air conditioner panel is located is obtained, the space feature matrix is hashed to obtain a unique feature mapping matrix of the space, a unique physical address code of the space is generated according to the feature mapping matrix, the unique physical address code and an indoor unit number controlled by the air conditioner panel are combined to generate unique positioning information of the air conditioner panel, space features and unique positioning information of the air conditioner panel are constructed, and the communication address information of the air conditioner panel is more conveniently modified according to space transform information of the air conditioner panel and effective control of the air conditioner is maintained.

[0136] It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0137] Based on the same inventive concept, the embodiments of the present application also provide a system for implementing the above-mentioned method of intelligently positioning an air conditioner panel in a building HVAC centralized control scene. The system provides a solution to the problem similar to the implementation scheme described in the above method, so the specific limitations in one or more system embodiments of the intelligent positioning of the air conditioner panel in the building HVAC centralized control scene below can be referred to the limitations of the method of intelligently positioning the air conditioner panel in the building HVAC centralized control scene in the above, which will not be repeated here.

[0138] In an exemplary embodiment, as shown in Figure 2 A system for intelligently positioning an air conditioner panel in a building HVAC centralized control scene is provided, comprising:

[0139] The instruction acquisition module 201 is configured to acquire an air conditioner panel positioning instruction.

[0140] The feature information acquisition module 202 is configured to acquire a feature matrix of the space of the air conditioner panel according to the air conditioner panel positioning instruction.

[0141] The address code generation module 203 is configured to generate a unique physical address code of the air conditioner panel according to the feature matrix.

[0142] The positioning information generation module 204 is configured to generate unique positioning information of the air conditioner panel according to the unique physical address code.

[0143] Further, the feature information acquisition module is further configured to:

[0144] According to the air conditioner panel positioning instruction, the altitude, the space number and the space structure diagram of the space where the air conditioner panel is located are acquired.

[0145] The altitude, the space number and the space structure diagram are input into a space neural network model to obtain the feature matrix of the space.

[0146] Furthermore, the spatial neural network model includes:

[0147] Input layer: Used to input altitude, spatial number, and spatial structure diagram;

[0148] Multi-layer graph convolutional layers: used to extract local and intermediate features of the spatial structure map, resulting in a feature map of the spatial structure; the output of each multi-layer graph convolutional layer serves as the input to the next multi-layer graph convolutional layer; the convolution output formula in the multi-layer graph convolutional layer is: ,in It is the number of convolutional layers. It is the first The output matrix of the layer, It is the convolution kernel weight matrix. It is the input matrix. It is a non-linear activation function. The bias parameters of the convolutional layer;

[0149] Pooling layers: used to compress the spatial dimension of feature maps to obtain dimensionality-reduced feature maps;

[0150] Extended layer: used to expand the altitude and spatial numbering into a spatial feature map of the same size as the reduced feature map, resulting in an altitude feature map and a numbering feature map;

[0151] Fully connected layer: used to comprehensively analyze the dimensionality-reduced feature map, elevation feature map, and numbered feature map, and calculate the feature matrix;

[0152] Output layer: Used to output the feature matrix.

[0153] Furthermore, the address encoding generation module includes:

[0154] The feature mapping matrix acquisition unit constructs a hash mapping table based on the feature matrix to obtain the feature mapping matrix of the space;

[0155] The one-dimensional feature sequence acquisition unit, based on the space filling curve algorithm, maps the feature mapping matrix to obtain a one-dimensional feature sequence;

[0156] The unique address encoding acquisition unit performs binarization and XOR processing on the one-dimensional feature sequence to obtain a unique address encoding.

[0157] The one-dimensional feature sequence is obtained through the following formula:

[0158]

[0159] in, It is a one-dimensional feature sequence. It is the feature mapping matrix. It is the sequence number The coordinates of the feature mapping matrix corresponding to each bit;

[0160] wherein the sequence bit is calculated by the following formula:

[0161]

[0162] wherein is the sequence bit, is the horizontal coordinate of the feature mapping matrix, is the vertical coordinate of the feature mapping matrix, is the extraction binary value function, is the number of binary bits of the feature mapping coordinate.

[0163] Further, the feature mapping matrix acquisition unit is further configured to:

[0164] normalize the feature matrix to obtain a normalized feature matrix;

[0165] obtain a preprocessed feature matrix based on a dimension reduction algorithm according to the normalized feature matrix;

[0166] determine a hash key corresponding to the preprocessed feature matrix based on a multiplication hash algorithm according to the preprocessed feature matrix to obtain a hash mapping table;

[0167] obtain the feature mapping matrix of the space according to the hash mapping table using the following formula:

[0168]

[0169] wherein, is the feature mapping matrix, is the fusion weight, is the preprocessed feature matrix, is the hash matrix.

[0170] wherein, the hash matrix is calculated by the following formula:

[0171]

[0172] wherein is the element of the hash matrix , is the base conversion function, is the hash key, is the size of the hash matrix. Further, the positioning information generation module is further configured to:

[0173] obtain the air conditioner indoor unit number of the space;

[0174]

[0175] ​​​According to the air conditioner indoor unit number and the unique physical address code, the unique positioning information of the air conditioner panel is generated.

[0176] Further, the system is also used for:

[0177] Obtaining spatial variation information; the spatial variation information includes a transformation space number;

[0178] According to the transformation space number, a hash mapping table is matched to obtain a new feature mapping matrix;

[0179] According to the new feature mapping matrix, the new unique positioning information of the air conditioner panel is updated.

[0180] In one embodiment, as Figure 3 A computer device is provided, comprising:

[0181] At least one processor 301;

[0182] And a memory 302 connected with the at least one processor 301 in communication: the memory stores an application program code executable by the at least one processor, and the application program code is executed by the at least one processor to enable the at least one processor to execute the method for intelligently positioning the air conditioner panel in the building HVAC centralized control scene as described above.

[0183] The computer device can further comprise: a sensor 303.

[0184] The processor 301, the memory 302 and the sensor 303 can be connected through a bus or other means, and the connection through the bus is taken as an example in the figure.

[0185] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in each method embodiment described above.

[0186] For the device embodiment, since it basically corresponds to the method embodiment, the related parts can refer to the part of the method embodiment. The device embodiments described above are only illustrative, and the components described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the present disclosure. Those skilled in the art can understand and implement it without creative labor.

[0187] The above-described embodiments only express several implementation manners of the application, the description is more specific and detailed, but it cannot be understood as the limitation of the patent scope of the application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the application, several modifications and improvements can be made, which are within the protection scope of the application.

Claims

1. A method for intelligent positioning of an air conditioner panel in a building heating, ventilation, and air conditioning (HVAC) centralized control scenario, characterized in that, The method includes: Obtain the air conditioner panel positioning command; Based on the air conditioner panel positioning command, obtain the spatial feature matrix of the air conditioner panel; Based on the feature matrix, generate a unique physical address code for the air conditioner panel; Generate unique location information for the air conditioner panel based on the unique physical address code; The step of obtaining the spatial feature matrix of the air conditioner panel according to the air conditioner panel positioning command includes: Based on the air conditioner panel positioning command, obtain the altitude, space number, and space structure diagram of the space where the air conditioner panel is located; Input the altitude, spatial number, and spatial structure map into the spatial neural network model to obtain the spatial feature matrix; The step of generating a unique physical address code for the air conditioner panel based on the feature matrix includes: Based on the feature matrix, a hash mapping table is constructed to obtain the feature mapping matrix of the space; Based on the space-filling curve algorithm, the feature mapping matrix is ​​mapped to obtain a one-dimensional feature sequence; The one-dimensional feature sequence is binarized and XORed to generate a unique address code. The one-dimensional feature sequence is obtained through the following formula: Code = [... M fused [i n-1 ,j n-1 ], M fused [i n ,j n ],...] Wherein, Code is a one-dimensional feature sequence, M fused is a feature mapping matrix, [i n ,j n ] is the feature mapping matrix coordinate corresponding to the nth position of the sequence. The nth position of the sequence is calculated using the following formula: where n is the sequence bit, i is the horizontal coordinate of the feature mapping matrix, j is the vertical coordinate of the feature mapping matrix, bit b is the extraction binary value function, and B is the binary bit number of the feature mapping coordinate. The step of generating unique location information for the air conditioner panel based on the unique physical address code includes: Obtain the indoor unit number of the air conditioner in the space; Generate unique location information for the air conditioner panel based on the indoor unit number and unique physical address code. In building HVAC centralized control scenarios, intelligent positioning methods for air conditioning panels also include: Acquire spatial change information, which includes the transformed spatial number; Based on the transformation space number, match the hash mapping table to obtain the new feature mapping matrix; Update the new unique location information of the air conditioner panel based on the new feature mapping matrix.

2. The method of claim 1, wherein the method is performed in a building heating, ventilation, and air conditioning (HVAC) control scene. The spatial neural network model includes: Input layer: Used to input altitude, spatial number, and spatial structure diagram; The multi-layer graph convolutional layer is used for extracting local features and intermediate features of a spatial structure graph, and obtaining a feature map of the spatial structure; wherein, the output of each multi-layer graph convolutional layer is used as the input of the next multi-layer graph convolutional layer; the convolution output formula in the multi-layer graph convolutional layer is as follows: Y (l) = σ (W (l) *X (l-1) +b (l) ), wherein, l is the number of convolutional layers, Y (l) is the output matrix of the lth layer, W (l) is a convolution kernel weight matrix, X (l-1) is an input matrix, σ is a nonlinear activation function, and b (l) is a bias parameter of the convolutional layer. Pooling layers: used to compress the spatial dimension of feature maps to obtain dimensionality-reduced feature maps; Extended layer: used to expand the altitude and spatial numbering into a spatial feature map of the same size as the reduced feature map, resulting in an altitude feature map and a numbering feature map; Fully connected layer: used to comprehensively analyze the dimensionality-reduced feature map, elevation feature map, and numbered feature map, and calculate the feature matrix; Output layer: Used to output the feature matrix.

3. The method of claim 1, wherein the method further comprises: determining a location of the air conditioning panel based on the set of data. The step of constructing a hash mapping table based on the feature matrix to obtain the feature mapping matrix of the space includes: The feature matrix is ​​normalized to obtain the normalized feature matrix; Based on the normalized feature matrix, a preprocessed feature matrix is ​​obtained using a dimensionality reduction algorithm; Based on the preprocessed feature matrix, the hash key corresponding to the preprocessed feature matrix is ​​determined using the multiplicative hash algorithm, and a hash mapping table is obtained. Based on the hash map table, the feature mapping matrix of the space is obtained using the following formula: M fused = a · M reduced + (1 - a) · H wherein M fused is a feature mapping matrix, a is a fusion weight, M reduced is a pre-processed feature matrix, and H is a hash matrix. The hash matrix is ​​calculated using the following formula: H[i,j] = ByteToInt(k 2(iw+j):2(iw+j)+2 ) Where H[i,j] is the [i,j] element of the hash matrix H, ByteToInt is the base conversion function, k is the hash key, and w is the size of the hash matrix.

4. A system for implementing the method of claim 1 for intelligent positioning of air conditioning panels in a building HVAC centralized control scenario, characterized by, include: The instruction acquisition module is used to acquire the positioning instruction of the air conditioner panel; The feature information acquisition module is used to acquire the spatial feature matrix of the air conditioner panel according to the air conditioner panel positioning command; An address code generation module is configured to generate a unique physical address code of the air conditioner panel according to the feature matrix. A positioning information generation module is configured to generate unique positioning information of the air conditioner panel according to the unique physical address code.

5. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor implements the steps of the method for intelligently positioning the air conditioner panel in the building HVAC centralized control scene according to any one of claims 1 to 3 when executing the computer program.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the steps of the method for intelligently positioning the air conditioner panel in the building HVAC centralized control scene according to any one of claims 1 to 3 when executed by the processor.

Images