A method, device, system and storage medium for self-adaptive adjustment of in-vehicle temperature

Abstract

The present invention relates to the field of temperature control technology, and in particular, to a method, device, system and storage medium for adaptively adjusting the temperature in a vehicle. The method comprises collecting data inside and outside the vehicle within a set period of time, wherein the data inside and outside the vehicle include: the change in body temperature of the occupants, the change in temperature inside and outside the vehicle, the difference in carbon dioxide concentration value inside the vehicle and the difference in air flow value inside the vehicle; determining a temperature adjustment strategy inside the vehicle according to the data inside and outside the vehicle; the temperature adjustment strategy inside the vehicle includes heating up or cooling down; and controlling the vehicle air conditioner according to the temperature adjustment strategy inside the vehicle. The present invention can timely and effectively adjust the temperature inside the vehicle to achieve a comfortable vehicle environment.

Description

Technical Field

[0001] The present invention relates to the field of temperature control technology, and in particular to a method, device, system and storage medium for adaptively adjusting in-vehicle temperature. Background Art

[0002] With the continuous improvement of automobile intelligence, the in-car temperature adaptive adjustment system has become an indispensable part of the smart car ecosystem, deeply integrated with navigation, infotainment and other systems, providing drivers and passengers with a comprehensive intelligent driving experience. The remote control function also allows users to set the in-car temperature in advance through smartphone applications in extreme weather conditions to ensure comfort when entering the vehicle. In the long run, the adaptive adjustment system saves fuel or electricity costs and reduces maintenance costs for users by saving energy and reducing wear and tear on the air conditioning system.

[0003] At present, the implementation methods of the in-vehicle temperature adaptive adjustment system mainly include the following:

[0004] 1. The automatic control system based on the temperature sensor adjusts the temperature inside the car according to the temperature changes inside and outside the car. This method is overly dependent on the detection accuracy of the temperature sensor. When the temperature sensor accuracy is insufficient or the data interpretation is incorrect, it will lead to inaccurate adjustment.

[0005] 2. Intelligent adjustment method based on the body temperature of passengers, that is, when the body temperature is high, the car interior is cooled down, and when the body temperature is low, the car interior is heated up. This method only considers the body temperature of passengers, which is not enough to adapt to complex in-car conditions and it is difficult to achieve a comfortable in-car environment.

[0006] In view of this, the present invention is proposed. Summary of the invention

[0007] The purpose of the present invention is to provide a method, device, system and storage medium for adaptively adjusting the temperature inside a vehicle, so as to determine whether the temperature inside the vehicle is rising or falling through the temperature change of the occupant, the temperature change inside and outside the vehicle, the difference in carbon dioxide concentration values ​​inside the vehicle and the difference in air flow values ​​inside the vehicle, so as to timely and effectively adjust the temperature inside the vehicle to achieve a comfortable vehicle environment.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] In a first aspect, the present invention provides a method for adaptively adjusting the temperature in a vehicle, comprising:

[0010] Collecting data inside and outside the vehicle within a set period of time, the data inside and outside the vehicle including: the change in body temperature of the occupants, the change in temperature inside and outside the vehicle, the difference in carbon dioxide concentration inside the vehicle, and the difference in air flow inside the vehicle;

[0011] Determine a vehicle interior temperature adjustment strategy according to the vehicle interior and exterior data; the vehicle interior temperature adjustment strategy includes heating up or cooling down;

[0012] The vehicle air conditioner is controlled according to the in-vehicle temperature adjustment strategy.

[0013] In a second aspect, the present invention provides an electronic device, comprising:

[0014] at least one processor, and a memory communicatively coupled to at least one of the processors;

[0015] The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the above-mentioned method for adaptively adjusting the in-vehicle temperature.

[0016] In a third aspect, the present invention provides a vehicle interior temperature adaptive adjustment system, comprising: an electronic device; and,

[0017] Human body temperature sensor, used to collect the body temperature of passengers in the car;

[0018] In-vehicle temperature sensor, used to collect the temperature inside the vehicle;

[0019] The vehicle outside temperature sensor is used to collect the vehicle outside temperature;

[0020] Carbon dioxide concentration sensor, used to collect carbon dioxide concentration values ​​in the car;

[0021] Air flow meter, used to collect the air flow value in the car.

[0022] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable the computer to execute the above-mentioned method for adaptively adjusting the temperature inside the vehicle.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. The present invention determines whether the temperature inside the vehicle is rising or falling by jointly determining the temperature change of the occupant temperature, the temperature change inside and outside the vehicle, the difference in the carbon dioxide concentration value inside the vehicle, and the difference in the air flow value inside the vehicle, so as to timely and effectively adjust the temperature inside the vehicle to achieve a comfortable vehicle environment.

[0025] 2. The present invention adopts the occupant temperature change, the temperature change inside and outside the vehicle, the difference in carbon dioxide concentration value inside the vehicle and the difference in air flow value inside the vehicle, focusing on the "change", and the "change" can better reflect the changes in the environment inside the vehicle, thereby obtaining an accurate temperature adjustment strategy.

[0026] 3. In real life, human body temperature cannot change rapidly in a short period of time, and the temperature inside and outside the car will not change suddenly. Therefore, in addition to the changes in human body temperature and the temperature changes inside and outside the car, the present invention also observes the changes in carbon dioxide concentration and air flow. When there are a large number of people in the car, or there are a lot of activities in the car (such as chatting), or the car is completely sealed, these two parameter values ​​can change rapidly when the occupants feel uncomfortable, which is more conducive to observing the situation inside the car so as to make better and faster adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a flow chart of a method for adaptively adjusting the temperature in a vehicle provided by the present invention;

[0029] Figure 2 It is a schematic diagram of the structure of a quantum tensor convolution hybrid network provided by an embodiment of the present invention;

[0030] Figure 3 is a schematic diagram of the structure of an MPS block provided by an embodiment of the present invention;

[0031] Figure 4 is a schematic diagram of contraction of high-order tensors provided by an embodiment of the present invention;

[0032] Figure 5 It is a schematic diagram of the structure of a Dense Layer provided in an embodiment of the present invention;

[0033] Figure 6 It is a schematic diagram of the structure of Denseblock provided by an embodiment of the present invention;

[0034] Figure 7 is a flow chart of another method for adaptively adjusting the temperature in a vehicle provided by the present invention;

[0035] Figure 8 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0037] Example 1

[0038] Figure 1 The method provided in this embodiment is applicable to the case where the temperature in the vehicle is adjusted by using a vehicle air conditioner. The method provided in this embodiment is executed by an electronic device, which may be composed of hardware and / or software and integrated in the vehicle.

[0039] See also Figure 1 , the method provided in this embodiment includes:

[0040] S110, collecting data inside and outside the vehicle within a set period of time, wherein the data inside and outside the vehicle include: changes in body temperature of passengers, changes in temperature inside and outside the vehicle, differences in carbon dioxide concentration values ​​inside the vehicle, and differences in air flow values ​​inside the vehicle.

[0041] The set period can be a period set manually, such as 5 minutes. At each moment (e.g., every second) within the set period, sensors arranged inside and outside the vehicle are used to collect the data inside and outside the vehicle, and the data inside and outside the vehicle at adjacent moments are subtracted to obtain the corresponding difference. For example, the human body temperature at 5 minutes and 2 seconds is subtracted from the human body temperature at 5 minutes and 1 second, and the temperature difference within the sub-period from 5 minutes and 1 second to 5 minutes and 2 seconds is obtained.

[0042] A human body temperature sensor is arranged in a position close to the occupants in the vehicle to collect the body temperature of the occupants at each moment. Optionally, an infrared detector using infrared thermal imaging technology is used to measure the temperature of the occupants' facial skin. The serpentine storage technology is used to record the temperature value corresponding to each pixel in the thermal image at a moment, and a vector A(a1, a2, a3, …, ai, …, an) is obtained, where ai is the temperature value corresponding to the i-th pixel, and n=64×64. Then, formula (1) is used to record the temperature difference A[ΔT] at the same pixel at adjacent moments.

[0043] A[ΔT]=A(a1[T2]- a1[T1], a2[T2]- a2[T1],…,ai[T2]- ai[T1],…,an[T2]-an[T1]); (1)

[0044] Where, ai[T2] is the temperature value corresponding to the i-th pixel at time T2, and ai[T1] is the temperature value corresponding to the i-th pixel at time T1. Time T1 and T2 are adjacent.

[0045] In this embodiment, the camera inside the car can be equipped with an infrared detector, which can capture the thermal radiation of the occupants and generate a thermal image. The change in facial temperature within a set period of time is recorded based on the thermal image, and the trend of temperature increase or decrease is analyzed. If the temperature changes rapidly, it indicates that the occupants are experiencing temperature discomfort.

[0046] Temperature sensors, such as thermistors or thermocouples, are installed on the outside and inside of the vehicle to directly measure and record the temperature inside and outside the vehicle at each moment, and transmit the temperature inside and outside the vehicle to the electronic equipment. The temperature inside and outside the vehicle at a moment is recorded as a vector B(b1,b2) where b1 represents the temperature inside the vehicle and b2 represents the temperature outside the vehicle. Then, the temperature change between adjacent moments is recorded using formula (2) B[ΔT].

[0047] B[ΔT]= B(b1[T2]-b1[T1] ,b2[T2]-b2[T1] ); (2)

[0048] A carbon dioxide concentration sensor is arranged in the vehicle to monitor the carbon dioxide concentration level in the vehicle in real time. There can be multiple carbon dioxide concentration sensors, which are integrated into the vehicle's ventilation system or air conditioning system. The carbon dioxide concentration in the vehicle at a certain moment is recorded as value C. Then, the carbon dioxide concentration value difference C[ΔT] from time T1 to time T2 is calculated using formula (3).

[0049] C[ΔT]=C[T2]- C[T1]; (3)

[0050] The air flow meter can be installed in the vehicle's ventilation or air conditioning system to collect the air flow value in the vehicle. Specifically, the air flow value usually refers to the volume of air passing through a specific cross section per unit time. The air flow meter can be installed in the air outlet or air inlet duct of the air conditioner to measure the air flow passing through a specific cross section. The air flow rate in the vehicle at a certain moment is recorded as value D. Then, the air flow value difference D[ΔT] from time T1 to time T2 is calculated using formula (4).

[0051] Record the difference in air flow values ​​at corresponding points from time T1 to time T2:

[0052] D[ΔT]=D[T2]- D[T1]; (4)

[0053] In summary, the human body temperature, indoor and outdoor temperature, carbon dioxide concentration value and in-car air flow value at multiple times are obtained within the set period. The aforementioned data of the same type at adjacent times (constituting the same period) are subtracted to obtain the difference value of each sub-period. It can be seen that the set period includes the human body temperature change, indoor and outdoor temperature change, in-car carbon dioxide concentration value difference and in-car air flow value difference of multiple sub-periods.

[0054] S120, determining an in-vehicle temperature adjustment strategy according to the in-vehicle and out-vehicle data; the in-vehicle temperature adjustment strategy includes heating up or cooling down.

[0055] The change in human body temperature, the change in temperature inside and outside the car, the difference in carbon dioxide concentration inside the car and the difference in air flow inside the car directly affect the feelings of the occupants in the car. In order to make the occupants feel comfortable, the temperature inside the car can be increased or decreased based on the changing trend of the data inside and outside the car.

[0056] Optionally, a nonlinear relationship between the data inside and outside the vehicle and the temperature control strategy inside the vehicle is learned through a machine learning model. The machine learning model may be a deep neural network model, which performs convolution feature extraction, full connection and classification on the data inside and outside the vehicle, and finally outputs the temperature control strategy inside the vehicle.

[0057] S130: Control the vehicle air conditioner according to the in-vehicle temperature adjustment strategy.

[0058] This embodiment does not limit the temperature adjustment step of the vehicle air conditioner, which can be 1 degree or 0.5 degree. When the vehicle temperature adjustment strategy is to increase the temperature, the temperature of the vehicle air conditioner is controlled to be +1, and the process returns to S110. When the vehicle temperature adjustment strategy is to decrease the temperature, the temperature of the vehicle air conditioner is controlled to be -1, and the process returns to S110.

[0059] Optionally, in order to avoid errors in the in-vehicle temperature adjustment strategy and improve the fault tolerance of the embodiment of the present invention, after S120 and before S130, the correctness of the in-vehicle temperature adjustment strategy is determined based on the current body temperature of the occupants or the relationship between the inside and outside temperatures of the vehicle.

[0060] In a specific implementation, if the in-car temperature adjustment strategy is cooling, it is determined whether the current occupant's body temperature is greater than a temperature threshold, or whether the in-car temperature is greater than the outside temperature; wherein the temperature threshold is the normal body temperature of the occupant, for example, 36.5 degrees. If the current occupant's body temperature is greater than the temperature threshold, or the in-car temperature is greater than the outside temperature, it means that the occupant feels hot and the car needs to be cooled, and then it is determined that the in-car temperature adjustment strategy is correct. On the contrary, if the current occupant's body temperature is less than or equal to the temperature threshold, and the in-car temperature is less than or equal to the outside temperature, it means that the occupant feels cold and the car needs to be heated, and then the in-car temperature adjustment strategy is wrong.

[0061] If the in-car temperature adjustment strategy is heating, it is determined whether the current occupant's body temperature is less than the temperature threshold, or whether the in-car temperature is less than the outside temperature; if the current occupant's body temperature is less than the temperature threshold, or the in-car temperature is less than the outside temperature, it means that the occupant feels cold and the car needs to be heated, and the in-car temperature adjustment strategy is determined to be correct. Conversely, if the current occupant's body temperature is greater than or equal to the temperature threshold, and the in-car temperature is greater than or equal to the outside temperature, it means that the occupant feels hot and the car needs to be cooled, and the in-car temperature adjustment strategy is wrong.

[0062] If the in-car temperature adjustment strategy is correct, the operation of controlling the vehicle air conditioner according to the in-car temperature adjustment strategy is executed; if the in-car temperature adjustment strategy is wrong, the operation of collecting in-car and out-car data within the set time period is returned, that is, the operations of S110~130 are re-executed.

[0063] This embodiment provides two specific implementation methods for correctness evaluation, which are more in line with the actual feelings of the passengers and the environmental conditions, and effectively evaluate the correctness of the in-vehicle temperature adjustment strategy.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] 1. The present invention determines whether the temperature inside the vehicle is rising or falling by jointly determining the temperature change of the occupant temperature, the temperature change inside and outside the vehicle, the difference in the carbon dioxide concentration value inside the vehicle, and the difference in the air flow value inside the vehicle, so as to timely and effectively adjust the temperature inside the vehicle to achieve a comfortable vehicle environment.

[0066] 2. The present invention uses the occupant temperature change, the temperature change inside and outside the vehicle, the difference in carbon dioxide concentration in the vehicle and the difference in air flow in the vehicle, focusing on the "change", which can better reflect the changes in the vehicle environment, thereby obtaining an accurate temperature adjustment strategy.

[0067] 3. In real life, human body temperature cannot change rapidly in a short period of time, and the temperature inside and outside the car will not change suddenly. Therefore, in addition to the changes in human body temperature and the temperature changes inside and outside the car, the present invention also observes the changes in carbon dioxide concentration and air flow. When there are a large number of people in the car, or there are a lot of activities in the car (such as chatting), or the car is completely sealed, these two parameter values ​​can change rapidly when the occupants feel uncomfortable, which is more conducive to observing the situation inside the car so as to make better and faster adjustments.

[0068] 4. This embodiment sets a fault-tolerant measure after determining the in-vehicle temperature adjustment strategy to avoid errors in the in-vehicle temperature adjustment strategy and improve the accuracy of the in-vehicle temperature adjustment.

[0069] Example 2

[0070] Based on the above embodiment, this embodiment refines the in-vehicle temperature adjustment strategy determined according to the in-vehicle and in-vehicle data. Optionally, the in-vehicle and in-vehicle data are input into a quantum tensor convolutional hybrid network (QTCHN) to obtain the in-vehicle temperature adjustment strategy output by the QTCHN; wherein the QTCHN includes a feature mapping layer, multiple feature extraction layers, and a fully connected layer connected in sequence.

[0071] QTCHN is a machine learning model that combines quantum computing and classical computing. This model takes advantage of the potential advantages of quantum computers in processing data, such as low number of parameters, extremely short analysis time, and high accuracy, while combining the powerful capabilities of classical computers in feature reuse, low number of parameters, enhanced feature fusion, and easy implementation. If a quantum computer is used later, the computing speed will be faster, which not only reduces costs but also increases the reaction processing speed.

[0072] Here, in order to ensure the differentiation between different data, four independent input channels are designed, each channel corresponds to a type of data, and then the data on each channel is normalized to ensure that the data is on the same scale, while maintaining the integrity of similar data and related data. Based on this, the data inside and outside the car are organized into a third-order tensor Q=(4,N1, ΔT).

[0073] For the four sets of data in different sub-periods (i.e., the change in body temperature of the occupants, the change in temperature inside and outside the vehicle, the difference in carbon dioxide concentration inside the vehicle, and the difference in air flow inside the vehicle), each set of data is expressed as a second-order tensor, i.e., (N1, ΔT), where N1 represents the sub-period, and ΔT represents each set of inside and outside vehicle data in this sub-period. For these four sets of data, the size of the data is Q.

[0074] The third-order tensor Q is input into QTCHN for analysis to determine whether to increase or decrease the temperature. Figure 2 Schematic diagram of the structure of the QTCHN provided by the embodiment of the present invention. The structure and function of each layer are introduced in order from left to right.

[0075] The feature mapping layer is used to perform feature mapping on the vehicle interior and exterior data generated during the set period, i.e., the third-order tensor Q, to obtain a tensor product. Specifically, the third-order tensor Q is feature mapped according to formula (5) to obtain the mapped features; the mapped features are tensor-calculated using formula (6) to obtain the tensor product .

[0076] ; (5)

[0077] In formula (5) Indicates the matrix of the third-order tensor Q The value of a matrix element, the matrix includes at least one set of vehicle internal and external data collected during a certain period of time, Represents the dimension of the feature map, with a size of 1 to In order to reduce the number of parameters, the present invention can set d to 2, that is, each are mapped into one dimensional vector, here =2, =2. This feature mapping method can provide a new way to represent data and help the model discover unknown correlations and patterns in the data.

[0078] Each vector will obtain a tensor product of the local state vector after passing through formula (6) .

[0079] ; (6)

[0080] In formula (6), represents all Q of the input, that is, the input vector. Map the vector Q to A vector in the dimensional feature space, and for the number of channels The local feature map is applied to each channel separately, and the final spatial dimension is ,For example =4, =2, N represents the number of matrix elements.

[0081] Figure 2 Three feature extraction layers are shown, namely feature extraction layer 1, feature extraction layer 2 and feature extraction layer 3. Each feature extraction layer has the same structure, including a matrix product state (MPS) layer and a dense block Denseblock. Multiple feature extraction layers are connected in sequence to extract deep features of the data inside and outside the vehicle.

[0082] This embodiment takes into account the huge amount of data inside and outside the vehicle. In order to speed up the processing of data and better extract the features of the same data and different data, the data is first input into the PMS in QTCHN, and effective features are extracted faster with the minimum number of parameters, involving the long-range entanglement and short-range entanglement characteristics of the quantum tensor network model. At the same time, more generalized features can be learned to improve the adaptability to new data.

[0083] The MPS layer is used to shrink the tensor product and the MPS block to obtain tensor features. The MPS layer includes multiple MPS blocks. In order to facilitate the differentiation between the four groups of data, see Figure 3The four data input by each MPS block are the changes in body temperature of the passengers, the changes in the temperature inside and outside the vehicle, the difference in the carbon dioxide concentration value inside the vehicle, and the difference in the air flow value inside the vehicle extracted from the same sub-period, so that the correlation between these data in the same sub-period can be better compared. The number of MPS blocks needs to be set according to the number of sub-periods. The four data of the same sub-period are collapsed with one MPS block.

[0084] Figure 4 In the above example, W is a high-order array representing the weight tensor. The high-order matrix product calculation is performed between W and W. However, when the amount of data is large, the parameter value of W will explode exponentially. Therefore, the idea of ​​quantum tensor network is introduced, and the weight tensor W is regarded as a Order tensor, using MPS to represent the weight tensor , as shown in formula (7).

[0085] ; (7)

[0086] For a graphical representation of formula (7), see Figure 8 , where T and M both represent the contracted tensor, and It is the connection line mark of each tensor, and N is the number of dimensions. and Used as a subscript to distinguish different tensors T and M. Indicates the Nth connection line l , Indicates the Nth connection line r . Representation and connection lines and connecting wires The concatenated tensor T, Representation and connection lines , connecting wire and connecting wires The tensor M is connected. Representation and connection lines , connecting wire and connecting wires The tensor M is connected. Representation and connection lines and connecting wires The concatenated tensor T.

[0087] MPS is used to represent the original high-order tensor as a contraction of multiple 3rd-order tensors M and two 2nd-order tensors T, which greatly reduces the number of weight coefficient parameters, thereby achieving the effect of reducing parameter complexity. Through the MPS layer, each four data and MPS block are contracted to obtain multiple 5th-order tensors R (a_1, a_2, a_3, a_4, m), where a_1, a_2, a_3, a_4 represent the tensor features of the occupant's body temperature change, the temperature change inside and outside the car, the difference in carbon dioxide concentration in the car, and the difference in air flow in the car, respectively, and m is the output tensor feature.

[0088] In order to further refine the extracted features and better enhance the expressiveness of the features, a dense block Denseblock is added after MPS. However, in order to adapt to the data output of the quantum tensor network layer, Denseblock is customized: in the present invention, a dense block DenseBlock has multiple sequentially connected dense layers Dense Layer, for example, 4 layers, and the growth rate of each layer is 8. Each dense layer Dense Layer performs the following operations:

[0089] Each dense layer is used to normalize the tensor features; perform convolution feature extraction on the normalized tensor features to obtain convolution features; perform batch normalization on the convolution features to obtain standard features; and activate the standard features to obtain activated features.

[0090] Figure 5 This is a schematic diagram of the structure of the dense layer provided by an embodiment of the present invention. First, the tensor features obtained by MPS are group normalized (Group Normalization, GN), and the input channels are divided into four groups according to the data type (i.e., the change in body temperature of the occupants, the change in temperature inside and outside the car, the difference in carbon dioxide concentration values ​​inside the car, and the difference in air flow values ​​inside the car), and each group is normalized separately. Then, a convolution layer (Conv2d) with a convolution kernel size of 4*2 is used to capture the local horizontal features in the tensor features. At the same time, the size of 4*2 just meets the dimension of the output feature of the previous tensor network, so as to better standardize the dimension of the output data and allow the data to be better transferred and shrunk. Then, a batch normalization (BN) operation is performed, for example, each feature channel is batch normalized through the BatchNorm2d function, the mean and variance of the normalized features are calculated, and the aforementioned mean and variance are scaled and translated to obtain standard features. Finally, after an activation layer (AL), the activated features are obtained. The nonlinear activation function enables the neural network to learn the complex features and patterns in the input data, while accelerating convergence and preventing overfitting.

[0091] Optional, see Figure 5 Each dense layer is used to perform linear rectification on the normalized tensor features, and then perform convolution feature extraction to obtain convolution features; the standard features are linearly rectified and then activated to obtain activated features. Linear rectification function (ReLU) can be used for linear rectification. Although ReLU is linear in the positive part, it is a nonlinear function as a whole because it introduces a nonlinear change at the zero point, which can increase the nonlinear expression ability of the network.

[0092] Figure 6 It is a structural diagram of a dense block Denseblock provided in an embodiment of the present invention, including four dense layers Dense Layer connected in sequence, which can increase the depth of feature extraction.

[0093] Optionally, when the Dense Layer is the first 3 layers of the DenseBlock, the activated features are input as new tensor features to the next Dense Layer. When the DenseBlock is the last layer of the DenseBlock and not the last MPS layer, the activated features are input as new tensor features to the next MPS layer. When the Dense Layer is the last layer of the DenseBlock and is the last MPS layer, the activated features are input as new tensor features to the fully connected layer.

[0094] See also Figure 2 , the feature input to the fully connected layer is represented as FC, and the FC is reduced in dimension by the fully connected layer to output low-dimensional features, indicating heating or cooling.

[0095] This embodiment uses QTCHN to identify temperature rise or temperature drop in the vehicle, which has the following technical effects:

[0096] 1. Quantum acceleration: QTCHN can provide exponential storage and computational acceleration, especially when processing high-dimensional data.

[0097] 2. Enhanced feature extraction: The MPS layer may reveal features that traditional convolutional neural networks (CNNs) cannot capture, thus enhancing the representation capabilities of the model.

[0098] 3. Quantum-classical synergy: combining the advantages of quantum and classical computing to achieve more efficient data processing and learning.

[0099] 4. Innovative data representation: QTCHN provides a completely new way of representing data, which may discover unknown correlations and patterns in the data.

[0100] 5. Reduce computational complexity: Through tensor decomposition, the number of model parameters can be reduced and the computational complexity can be reduced.

[0101] 6. Improve model generalization ability: Tensor feature extraction may help the model learn more generalized features and improve its adaptability to new data.

[0102] 7. Adapt to future technologies: As quantum computing technology matures, this model will be able to adapt to future computing needs.

[0103] Example 3

[0104] This embodiment adds ventilation operation in the vehicle on the basis of the temperature adjustment in the above embodiment. It should be noted that some vehicle air conditioners also perform ventilation operation in the process of adjusting the temperature, while this embodiment further performs ventilation operation according to the air quality in the vehicle after the temperature adjustment. After ventilation, the temperature in the vehicle will be more or less affected, so it is necessary to return to 110 to continue the temperature adjustment.

[0105] See also Figure 7 The method provided in this embodiment includes:

[0106] S210, collecting data inside and outside the vehicle within a set period of time, wherein the data inside and outside the vehicle include: a change in body temperature of the occupant, a change in temperature inside and outside the vehicle, a difference in carbon dioxide concentration inside the vehicle, and a difference in air flow inside the vehicle.

[0107] S220, determining a vehicle interior temperature adjustment strategy according to the vehicle interior and exterior data, if the temperature is to be raised, jumping to S230, if the temperature is to be lowered, jumping to S140.

[0108] S230: Control the vehicle air conditioner to heat up, and execute S250.

[0109] S240: Control the vehicle air conditioner to cool down, and execute S250.

[0110] S250: Determine the current air quality according to the current carbon dioxide concentration value or the current air flow value in the vehicle.

[0111] The current moment here is the adjacent moment after the temperature adjustment is performed in S230 and S240. In this embodiment, the air quality at the current moment is determined by comparing the carbon dioxide concentration value or the air flow value in the vehicle with the corresponding threshold value.

[0112] S260: Determine whether the air quality meets the requirements. If the air quality meets the requirements, execute S210 and continue to adjust the temperature in the vehicle; if the air quality does not meet the requirements, execute S270.

[0113] S270, control the vehicle air conditioner to perform ventilation operation. Return to S210, continue to adjust the temperature in the vehicle.

[0114] If the carbon dioxide concentration is greater than the concentration threshold, or the air flow value is less than the flow threshold, it means that the air quality in the car does not meet the requirements, the car is stuffy, and ventilation is required, such as controlling the vehicle air conditioning ventilation +1 gear. If the carbon dioxide concentration is less than or equal to the concentration threshold, and the air flow value is greater than or equal to the flow threshold, it means that the air quality in the car meets the requirements, ventilation is not required, and the temperature adjustment in the car for the next period of time is performed. Among them, the concentration threshold is, for example, 1000 ppm, and the flow threshold is, for example, 50 L / min.

[0115] This embodiment determines the air quality through carbon dioxide concentration and air flow on the basis of in-car temperature regulation, thereby performing ventilation regulation, improving the in-car environment from the perspectives of temperature and air quality; moreover, the in-car temperature can be improved synchronously through ventilation operation, which is conducive to reaching a comfortable temperature for passengers as soon as possible. This embodiment achieves more intelligent regulation of in-car temperature and ventilation, improves the passenger comfort experience and safety factor during driving, and also saves fuel or electricity costs and reduces maintenance costs for users by saving energy and reducing wear of the air conditioning system.

[0116] Example 4

[0117] like Figure 8 As shown, this embodiment provides an electronic device, including:

[0118] at least one processor; and

[0119] a memory communicatively connected to at least one of the processors; wherein,

[0120] The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the above-mentioned method for adaptively adjusting the temperature in the vehicle. At least one processor in the electronic device can execute the above-mentioned method, and thus has at least the same advantages as the above-mentioned method.

[0121] Optionally, the electronic device also includes interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on a memory to display graphical information of a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to an interface). In other embodiments, if necessary, multiple processors can be used together with multiple memories, and / or multiple buses can be used together with multiple memories. Similarly, multiple electronic devices can be connected (for example, as a server array, a group of blade servers, or a multi-processor system), and each device provides some necessary operations. Figure 8 A processor 301 is taken as an example.

[0122] The memory 302 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the in-vehicle temperature adaptive adjustment method in the embodiment of the present invention. The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 302, that is, implements the above-mentioned in-vehicle temperature adaptive adjustment method.

[0123] The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 302 may further include a memory remotely arranged relative to the processor 301, and these remote memories may be connected to the device 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.

[0124] The electronic device may further include: an input device 303 and an output device 304. The processor 301, the memory 302, the input device 303 and the output device 304 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0125] The input device 303 can receive input digital or character information, and the output device 304 can include a display device, an auxiliary lighting device (e.g., LED), and a tactile feedback device (e.g., a vibration motor), etc. The display device can include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device can be a touch screen.

[0126] Example 5

[0127] An embodiment of the present invention provides an in-vehicle temperature adaptive adjustment system, comprising: the electronic device provided in Example 4; and a human body temperature sensor, an in-vehicle temperature sensor, an outside-vehicle temperature sensor, a carbon dioxide concentration sensor, and an air flow meter.

[0128] Among them, the human body temperature sensor is used to collect the body temperature of the passengers in the car; the in-car temperature sensor is used to collect the in-car temperature; the out-car temperature sensor is used to collect the out-car temperature; the carbon dioxide concentration sensor is used to collect the carbon dioxide concentration value in the car; the air flow meter is used to collect the air flow value in the car.

[0129] The arrangement positions and functions of the sensors, as well as the functions of the electronic devices, refer to the descriptions of the above embodiments and will not be repeated here.

[0130] Example 6

[0131] This embodiment provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable the computer to execute the above method. The computer instructions on the computer-readable storage medium are used to enable the computer to execute the above method, and thus have at least the same advantages as the above method.

[0132] The medium in the present invention may adopt any combination of one or more computer-readable media. The medium may be a computer-readable signal medium or a computer-readable storage medium. The medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of the medium (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, the medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0133] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0134] The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

[0135] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0136] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0137] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for adaptively adjusting the temperature in a vehicle. It is characterized in that include: Collecting data inside and outside the vehicle within a set period of time, the data inside and outside the vehicle including: the change in body temperature of the occupants, the change in temperature inside and outside the vehicle, the difference in carbon dioxide concentration inside the vehicle, and the difference in air flow inside the vehicle; Determine the in-vehicle temperature adjustment strategy according to the in-vehicle and out-vehicle data; the in-vehicle temperature adjustment strategy includes heating or cooling; if the in-vehicle temperature adjustment strategy is cooling, determine whether the body temperature of the occupant at the current moment is greater than the temperature threshold, or whether the in-vehicle temperature is greater than the outside temperature; if the body temperature of the occupant at the current moment is greater than the temperature threshold, or the in-vehicle temperature is greater than the outside temperature, determine that the in-vehicle temperature adjustment strategy is correct; if the in-vehicle temperature adjustment strategy is heating, determine whether the body temperature of the occupant at the current moment is less than the temperature threshold, or whether the in-vehicle temperature is less than the outside temperature; if the body temperature of the occupant at the current moment is less than the temperature threshold, or the in-vehicle temperature is less than the outside temperature, determine that the in-vehicle temperature adjustment strategy is correct; The vehicle air conditioner is controlled according to the in-vehicle temperature adjustment strategy.

2. The method according to claim 1, It is characterized in that The determining of the in-vehicle temperature adjustment strategy according to the in-vehicle and in-vehicle data includes: Inputting the in-vehicle and out-vehicle data into a quantum tensor convolution hybrid network to obtain an in-vehicle temperature adjustment strategy output by the quantum tensor convolution hybrid network; Among them, the quantum tensor convolution hybrid network includes a feature mapping layer, multiple feature extraction layers and a fully connected layer connected in sequence; each of the feature extraction layers includes a matrix product state MPS layer and a dense block Denseblock.

3. The method according to claim 2, It is characterized in that The feature mapping layer is used to perform feature mapping on the vehicle interior and exterior data generated during the set period to obtain a tensor product; the matrix product state MPS layer is used to shrink the tensor product and the matrix product state MPS block to obtain a tensor feature; The dense block Denseblock includes multiple dense layers Dense Layer connected in sequence; each dense layer DenseLayer is used to normalize the tensor features; convolutional features are extracted on the normalized tensor features to obtain convolutional features; the convolutional features are batch standardized to obtain standard features; the standard features are activated to obtain activated features; the activated features are input into the next dense layer Dense Layer as new tensor features, or into the next matrix product state MPS layer, or into the fully connected layer.

4. The method according to claim 3, It is characterized in that Each dense layer is used to perform linear rectification on the normalized tensor features and then perform convolution feature extraction to obtain convolution features; the standard features are linearly rectified and then activated to obtain activated features.

5. The method according to claim 1, It is characterized in that After confirming that the in-car temperature control strategy is correct, it also includes: If the in-vehicle temperature adjustment strategy is correct, then executing an operation of controlling the vehicle air conditioner according to the in-vehicle temperature adjustment strategy; If the in-vehicle temperature adjustment strategy is wrong, the operation returns to collecting in-vehicle and in-vehicle data within a set period of time.

6. The method according to claim 1, It is characterized in that After the vehicle air conditioner is controlled according to the vehicle temperature adjustment strategy, the method further includes: Determine the air quality at the current moment according to the carbon dioxide concentration value or the air flow value in the vehicle at the current moment; If the air quality does not meet the requirement, the vehicle air conditioner is controlled to perform ventilation operation.

7. An electronic device, It is characterized in that include: at least one processor, and a memory communicatively coupled to at least one of the processors; The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the method for adaptively adjusting the in-vehicle temperature according to any one of claims 1 to 6.

8. An in-vehicle temperature adaptive adjustment system, It is characterized in that include: The electronic device according to claim 7; as well as, Human body temperature sensor, used to collect the body temperature of passengers in the car; In-vehicle temperature sensor, used to collect the temperature inside the vehicle; The vehicle outside temperature sensor is used to collect the vehicle outside temperature; Carbon dioxide concentration sensor, used to collect carbon dioxide concentration values ​​in the car; Air flow meter, used to collect the air flow value in the car.

9. A computer-readable storage medium, It is characterized in that The medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for adaptively adjusting the in-vehicle temperature according to any one of claims 1 to 6.

Images