Artificial intelligence-based vehicle air conditioning control method, system, device and medium

Abstract

The present invention discloses an artificial intelligence-based vehicle air conditioning control method, system, device, and medium. The method includes: obtaining cabin temperature distribution data of a target vehicle in the current time period, and determining cabin temperature distribution time series data based on the cabin temperature distribution data; inputting the cabin temperature distribution time series data into a pre-trained temperature distribution prediction model to obtain a cabin temperature distribution prediction result for the target vehicle in the next time period; determining a cabin area to be adjusted and a temperature adjustment value corresponding to the cabin area to be adjusted based on the cabin temperature distribution prediction result; determining a target air conditioning damper based on the cabin area to be adjusted, determining an air volume change value for the cabin area to be adjusted based on the temperature adjustment value, and then adjusting the opening of the target air conditioning damper based on the air volume change value. The present invention improves the efficiency and accuracy of vehicle air conditioning control, as well as the user's driving safety and riding experience, and can be widely applied in the field of vehicle control technology.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to an artificial intelligence-based vehicle air conditioning control method, system, device and medium. Background Art

[0002] As a common means of transportation, cars have become indispensable in human life. The interior environment of a car affects the comfort of the driver and passengers. Currently, most cars are equipped with onboard air conditioning to regulate and control the temperature inside the car to provide users with a good driving environment.

[0003] In the existing technology, the adjustment of car air conditioners is mostly based on the user's active setting of temperature and air volume. The car air conditioner can meet the user's temperature requirements after running according to the parameters set by the user for a period of time. However, if the car air conditioner continues to run according to the parameters set by the user, it will cause the local temperature in the car to be too high or too low, causing the user to feel uncomfortable. Therefore, the user needs to adjust the temperature and air volume settings more frequently, which on the one hand affects the efficiency and accuracy of the car air conditioner control, and on the other hand affects the user's driving experience, and is prone to safety hazards during driving. Summary of the Invention

[0004] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0005] To this end, an object of an embodiment of the present invention is to provide an artificial intelligence-based vehicle air-conditioning control method, which improves the efficiency and accuracy of vehicle air-conditioning control as well as the user's driving safety and driving experience.

[0006] Another object of an embodiment of the present invention is to provide an artificial intelligence-based vehicle air-conditioning control system.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0008] In a first aspect, an embodiment of the present invention provides an artificial intelligence-based vehicle air conditioning control method, comprising the following steps:

[0009] Acquiring cabin temperature distribution data of a target vehicle during a current period, and determining cabin temperature distribution time series data based on the cabin temperature distribution data;

[0010] Inputting the cabin temperature distribution time series data into a pre-trained temperature distribution prediction model to obtain a cabin temperature distribution prediction result for the target vehicle in the next time period;

[0011] determining a cabin area to be adjusted and a temperature adjustment value corresponding to the cabin area to be adjusted according to the cabin temperature distribution prediction result;

[0012] A target air conditioning damper is determined according to the cabin area to be adjusted, an air volume change value of the cabin area to be adjusted is determined according to the temperature adjustment value, and then the opening of the target air conditioning damper is adjusted according to the air volume change value.

[0013] Furthermore, in one embodiment of the present invention, the step of obtaining cabin temperature distribution data of the target vehicle in the current time period and determining cabin temperature distribution time series data based on the cabin temperature distribution data specifically includes:

[0014] Acquiring real-time temperature information of each cabin area by using temperature sensors provided in each cabin area of ​​the target vehicle;

[0015] determining a cabin temperature distribution heat map of the target vehicle at each moment according to the real-time temperature information, and using the cabin temperature distribution heat map as the cabin temperature distribution data;

[0016] The cabin temperature distribution data at each moment is sorted in chronological order to obtain the cabin temperature distribution time series data.

[0017] Furthermore, in one embodiment of the present invention, the temperature distribution prediction model is trained by the following steps:

[0018] Obtain cabin temperature distribution sample data of the test vehicle at multiple times during a historical period;

[0019] Determining a temperature distribution prediction label based on the cabin temperature distribution sample data at the last moment, and determining cabin temperature distribution sample time series data based on the cabin temperature distribution sample data at other moments, and then constructing a training sample set based on the cabin temperature distribution sample time series data and the temperature distribution prediction label;

[0020] The training sample set is input into a pre-built long short-term memory neural network for training, and the model parameters of the long short-term memory neural network are optimized using a back propagation algorithm to obtain a trained temperature distribution prediction model.

[0021] Furthermore, in one embodiment of the present invention, the model parameters include a forget gate weight matrix, an input gate weight matrix, an output gate weight matrix, a unit state weight matrix, a forget gate bias term, an input gate bias term, an output gate bias term, and a unit state bias term. The step of optimizing the model parameters of the long short-term memory neural network using a backpropagation algorithm specifically includes:

[0022] Forward calculation of the forget gate, input gate, output gate and unit state of each storage unit;

[0023] Reversely calculating the error term value of each storage unit according to the forget gate, the input gate, the output gate and the unit state;

[0024] Determining a first gradient of the forget gate weight matrix, a second gradient of the input gate weight matrix, a third gradient of the output gate weight matrix, and a fourth gradient of the unit state weight matrix according to the error term value;

[0025] Gradient updating is performed on the first gradient, the second gradient, the third gradient, and the fourth gradient, thereby optimizing the forget gate weight matrix, the input gate weight matrix, the output gate weight matrix, the unit state weight matrix, the forget gate bias term, the input gate bias term, the output gate bias term, and the unit state bias term.

[0026] Furthermore, in one embodiment of the present invention, determining the cabin area to be adjusted and the temperature adjustment value corresponding to the cabin area to be adjusted based on the cabin temperature distribution prediction result specifically includes:

[0027] determining a temperature prediction value for each cabin area according to the cabin temperature distribution prediction result;

[0028] obtaining a temperature setting value of the target vehicle, and determining the corresponding cabin area as the cabin area to be adjusted when the absolute value of the difference between the temperature setting value and the temperature prediction value is greater than or equal to a preset temperature difference threshold;

[0029] The temperature adjustment value is determined according to a difference between the temperature setting value of the cabin area to be adjusted and the temperature prediction value.

[0030] Furthermore, in one embodiment of the present invention, determining a target air conditioning damper according to the cabin area to be adjusted, and determining an air volume change value for the cabin area to be adjusted according to the temperature adjustment value, specifically includes:

[0031] Determining, according to the cabin area to be adjusted, an air conditioning damper at a corresponding position as the target air conditioning damper;

[0032] determining an air thermal energy adjustment value for the cabin area to be adjusted according to the temperature adjustment value and the space size of the cabin area to be adjusted;

[0033] The air conditioning cold air temperature of the target vehicle is obtained, and the air volume change value is determined according to the air conditioning cold air temperature and the air thermal energy adjustment value.

[0034] Furthermore, in one embodiment of the present invention, adjusting the target air-conditioning damper opening according to the air volume change value specifically includes:

[0035] Determining the current air volume of the target air conditioning damper according to the current opening of the target air conditioning damper and a preset damper opening-air volume mapping table;

[0036] Determining a target air volume of the target air conditioning damper according to the air volume change value and the current air volume;

[0037] determining a target opening of the target air-conditioning damper according to the target air volume and the damper opening-air volume mapping table;

[0038] The target air-conditioning damper is adjusted according to the target opening.

[0039] In a second aspect, an embodiment of the present invention provides an artificial intelligence-based vehicle air conditioning control system, comprising:

[0040] a temperature distribution time series data acquisition module, configured to acquire cabin temperature distribution data of a target vehicle in a current period, and determine cabin temperature distribution time series data based on the cabin temperature distribution data;

[0041] a temperature distribution prediction module, configured to input the cabin temperature distribution time series data into a pre-trained temperature distribution prediction model to obtain a cabin temperature distribution prediction result of the target vehicle in the next time period;

[0042] a module for determining a cabin area to be adjusted and a temperature adjustment value, configured to determine a cabin area to be adjusted and a temperature adjustment value corresponding to the cabin area to be adjusted based on the cabin temperature distribution prediction result;

[0043] The air conditioning damper opening adjustment module is used to determine a target air conditioning damper according to the cabin area to be adjusted, determine an air volume change value for the cabin area to be adjusted according to the temperature adjustment value, and then adjust the opening of the target air conditioning damper according to the air volume change value.

[0044] In a third aspect, an embodiment of the present invention provides an artificial intelligence-based vehicle air conditioning control device, comprising:

[0045] at least one processor;

[0046] at least one memory for storing at least one program;

[0047] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned vehicle air conditioning control method based on artificial intelligence.

[0048] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor, wherein the program executable by the processor is used to execute the above-mentioned artificial intelligence-based vehicle air-conditioning control method when executed by the processor.

[0049] The advantages and benefits of the present invention will be described in part in the following description and will become apparent from the following description or learned through practice of the present invention:

[0050] An embodiment of the present invention obtains cabin temperature distribution data of a target vehicle in a current time period, determines cabin temperature distribution time series data based on the cabin temperature distribution data, inputs the cabin temperature distribution time series data into a pre-trained temperature distribution prediction model, obtains a cabin temperature distribution prediction result of the target vehicle in a next time period, determines a cabin area to be adjusted and a temperature adjustment value corresponding to the cabin area to be adjusted based on the cabin temperature distribution prediction result, determines a target air-conditioning damper based on the cabin area to be adjusted, determines an air volume change value of the cabin area to be adjusted based on the temperature adjustment value, and then adjusts the opening of the target air-conditioning damper based on the air volume change value. The embodiment of the present invention predicts the cabin temperature distribution of the target vehicle in the next time period, and determines the cabin area to be adjusted and the corresponding temperature adjustment value based on the cabin temperature distribution prediction result, so as to determine the target air-conditioning damper to be adjusted and the corresponding air volume change value, and then adjust the opening of the target air-conditioning damper according to the air volume change value, thereby realizing pre-adjustment of the vehicle's air conditioning, eliminating the need for users to manually adjust repeatedly, improving the efficiency and accuracy of the vehicle's air-conditioning control, and being able to provide users with a more comfortable driving environment, thereby improving the user's driving safety and driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0052] Figure 1 A flowchart of a vehicle air conditioning control method based on artificial intelligence provided by an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of the sequential structure of a long short-term memory neural network repeating unit provided by an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of gate control of a long short-term memory neural network provided by an embodiment of the present invention;

[0055] Figure 4 This is a structural block diagram of an artificial intelligence-based vehicle air-conditioning control system provided by an embodiment of the present invention;

[0056] Figure 5This is a structural block diagram of an artificial intelligence-based vehicle air-conditioning control device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided for ease of explanation only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0058] In the description of the present invention, "a plurality" means two or more. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly indicating the number of the indicated technical features, or as implicitly indicating the order of the indicated technical features. Furthermore, unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art.

[0059] Reference Figure 1 The embodiment of the present invention provides a vehicle air conditioning control method based on artificial intelligence, which specifically includes the following steps:

[0060] S101. Acquire cabin temperature distribution data of a target vehicle in a current period, and determine cabin temperature distribution time series data based on the cabin temperature distribution data;

[0061] S102: Input the cabin temperature distribution time series data into a pre-trained temperature distribution prediction model to obtain a cabin temperature distribution prediction result for the target vehicle in the next time period;

[0062] S103: Determine a cabin area to be adjusted and a temperature adjustment value corresponding to the cabin area according to the cabin temperature distribution prediction result;

[0063] S104: Determine a target air conditioning damper according to the cabin area to be adjusted, determine an air volume change value for the cabin area to be adjusted according to the temperature adjustment value, and then adjust the opening of the target air conditioning damper according to the air volume change value.

[0064] The embodiment of the present invention predicts the cabin temperature distribution of the target vehicle in the next time period, and determines the cabin area to be adjusted and the corresponding temperature adjustment value based on the cabin temperature distribution prediction result, so as to determine the target air-conditioning damper to be adjusted and the corresponding air volume change value, and then adjust the opening of the target air-conditioning damper according to the air volume change value, thereby realizing pre-adjustment of the vehicle's air conditioning, eliminating the need for users to manually adjust repeatedly, improving the efficiency and accuracy of the vehicle's air-conditioning control, and being able to provide users with a more comfortable driving environment, thereby improving the user's driving safety and driving experience.

[0065] As a further optional implementation, obtaining cabin temperature distribution data of the target vehicle in the current time period and determining cabin temperature distribution time series data based on the cabin temperature distribution data specifically include:

[0066] S1011, obtaining real-time temperature information of each cabin area through temperature sensors installed in each cabin area of ​​the target vehicle;

[0067] S1012. Determine a cabin temperature distribution heat map of the target vehicle at each time point based on the real-time temperature information, and use the cabin temperature distribution heat map as cabin temperature distribution data;

[0068] S1013. Sort the cabin temperature distribution data at each moment in chronological order to obtain cabin temperature distribution time series data.

[0069] Specifically, temperature sensors are pre-installed in each cabin area of ​​the target vehicle to obtain real-time temperature information for the corresponding area. Based on this real-time temperature information and the target vehicle's cabin area distribution map, a cabin temperature distribution heat map is created. This cabin temperature distribution heat map uses color to indicate the temperature of each cabin area. For example, high-temperature areas may be darker, while low-temperature areas may be lighter. This cabin temperature distribution heat map spatially correlates the temperatures of each cabin area, allowing the spatial positional relationship of each cabin area to be factored into the subsequent model recognition process, improving the accuracy of cabin temperature distribution prediction. The cabin temperature distribution heat maps at each moment are sorted chronologically to generate cabin temperature distribution time series data.

[0070] As an optional embodiment, the temperature distribution prediction model is trained by the following steps:

[0071] S201. Obtain cabin temperature distribution sample data of a test vehicle at multiple moments in a historical period;

[0072] S202: Determine a temperature distribution prediction label based on the cabin temperature distribution sample data at the last moment, and determine cabin temperature distribution sample time series data based on the cabin temperature distribution sample data at other moments, and then construct a training sample set based on the cabin temperature distribution sample time series data and the temperature distribution prediction label;

[0073] S203: Input the training sample set into the pre-built long short-term memory neural network for training, and optimize the model parameters of the long short-term memory neural network using the back propagation algorithm to obtain a trained temperature distribution prediction model.

[0074] Specifically, when constructing the training sample set, the cabin temperature distribution sample time series data and the temperature distribution prediction label are determined based on the changes in the cabin temperature distribution of the test vehicle during actual operation. For example, the cabin temperature distribution sample data from time 1 to time 10 are obtained, of which the cabin temperature distribution sample data from time 1 to time 9 constitute the cabin temperature distribution sample time series data, and the cabin temperature distribution sample data at time 10 is used to determine the temperature distribution prediction label, that is, the temperature prediction value label of each cabin area.

[0075] The Long Short-Term Memory (LSTM) neural network is an improved recurrent neural network. In an LSTM network, conventional neurons are replaced by memory cells, each of which consists of an input gate, an output gate, and a cell state. The following describes the LSTM neural network used in the embodiments of the present invention.

[0076] The sequential structure of the LSTM network repetitive units is as follows Figure 2 As shown, at time t, the LSTM has three inputs: the input value X of the network at the current moment t , the output value X of LSTM at the previous moment t-1 , and the unit state C at the previous moment t-1 LSTM has two outputs: the current LSTM output value h t , and the current cell state C t .

[0077] For the control of the long-term state c, three gate control switches are used for measurement. It is necessary to consider the influence of the output of the previous storage unit, the influence of the current input value, and the influence of the current storage unit on subsequent transmission. Therefore, the rational use of the three gate control switches becomes an important link in signal transmission and parameter update.

[0078] In the process of transferring information over time, three control switches are used to measure the state unit c. The specific allocation is as follows: Figure 3As shown, the first switch (left) controls the continued storage of the long-term state c, measuring the influence of the previous storage unit on the current storage unit and determining the impact of memory experience on the current time point. The second switch (bottom) controls the input of the immediate state into the long-term state c. The input signal does not need to be passed to the model in full; only the measurement values ​​that need to be considered are passed. The third switch (right) controls whether the long-term state c is used as the output of the current LSTM. It is worth noting that the gate switch used here is only a gate definition for its function. Its value is a vector between 0 and 1, and it is calculated using a weighted metric, rather than a gate switch that is simply considered to be 0 or 1.

[0079] A gate switch is essentially a fully connected layer. Its input is a vector, and its output is a real number vector between 0 and 1. To use it, the gate switch output vector is element-wise multiplied by the vector to be controlled. The gate output is a real number vector between 0 and 1. When the gate output is 0, multiplying any vector with it yields a 0 vector, meaning nothing passes through. When the gate output is 1, multiplying any vector with it yields no change, meaning everything passes through. The sigmoid function normalizes the output, giving the output a probability value between 0 and 1.

[0080] In this embodiment of the present invention, cabin temperature distribution sample time series data is used as input data for the LSTM model to train the network. This process can perform layer-by-layer feature learning and mapping on the data. The deep time-frequency feature signal characteristics are then fed into the SoftMax classifier for training. The trained weights are then used to initialize the LSTM. The backpropagation algorithm is then used to optimize the weights of the constructed LSTM network model, so that the LSTM network model converges to the global optimum, ultimately achieving the purpose of temperature distribution prediction.

[0081] As an optional implementation, the model parameters include a forget gate weight matrix, an input gate weight matrix, an output gate weight matrix, a unit state weight matrix, a forget gate bias term, an input gate bias term, an output gate bias term, and a unit state bias term. The step of optimizing the model parameters of the long short-term memory neural network using a backpropagation algorithm specifically includes:

[0082] S2031, forward calculation of the forget gate, input gate, output gate and unit state of each storage unit;

[0083] S2032, reversely calculating the error term value of each storage unit according to the forget gate, input gate, output gate and unit state;

[0084] S2033, determining a first gradient of a forget gate weight matrix, a second gradient of an input gate weight matrix, a third gradient of an output gate weight matrix, and a fourth gradient of a unit state weight matrix according to the error term value;

[0085] S2034. Perform gradient update on the first gradient, the second gradient, the third gradient, and the fourth gradient, thereby optimizing the forget gate weight matrix, the input gate weight matrix, the output gate weight matrix, the unit state weight matrix, the forget gate bias item, the input gate bias item, the output gate bias item, and the unit state bias item.

[0086] Specifically, when constructing a long short-term memory neural network, in addition to determining the initial model parameters, it is also necessary to determine the forget gate function, input gate function, output gate function, and unit state function.

[0087] The forget gate function is:

[0088] f t =σ(W f [h t-1 ,x t ]+b f )

[0089] Among them, f t represents the forget gate, W f represents the forget gate weight matrix, [h t-1 ,x t ] represents the input signal of the previous layer output and the current layer input as a whole, b f represents the forget gate bias term, σ represents the sigmoid function;

[0090] The input gate function is:

[0091] i t =σ(W i [h t-1 ,x t ]+b i )

[0092] Among them, i t represents the input gate, W i represents the input gate weight matrix, [h t-1 ,x t ] represents the input signal of the previous layer output and the current layer input as a whole, b i Represents the input gate bias term, σ represents the sigmoid function;

[0093] The output gate function is:

[0094] o t =σ(W o .[h t-1 ,xt ]+b o )

[0095] Among them, t represents the output gate, W o represents the output gate weight matrix, [h t-1 ,x t ] represents the input signal of the previous layer output and the current layer input as a whole, b o Represents the output gate bias term, σ represents the sigmoid function;

[0096] The cell state function is:

[0097] C t =f t *C t-1 +i t *C′ t

[0098] C′ t =tanh(W c .[h t-1 ,x t ]+b c )

[0099] Among them, C t Indicates the current unit state, f t represents the forget gate, C t-1 Indicates the unit state at the previous moment, i t represents the input gate, C′ t Represents the current input unit state, tanh represents the tanh function, W c represents the unit state weight matrix, [h t-1 ,x t ] represents the input signal of the previous layer output and the current layer input as a whole, b c Represents the unit state bias term.

[0100] During the forward transmission process, the signal transmission process is controlled by controlling the gate control switches between adjacent storage units. It can be mainly divided into three categories, as follows:

[0101] 1) Forget gate: determines the cell state C at the previous moment t-1 How much information is still retained at the current moment C t In the implementation, the memory update of data is realized.

[0102] 2) Input gate: determines the input X of the network at the current moment t How much is saved to the cell state C t , to achieve the screening of input data and reduce the purpose of data input.

[0103] 3) Output gate: controls the cell state C t How many outputs are given to the LSTM's current output value h? t , reducing data output.

[0104] The forget gate can preserve earlier information, normalize the output value through the σ function, and use the influence of the original information as an important reference to determine the propagation process of the current value, thereby achieving the purpose of memory updating.

[0105] The input gate can filter the current input data to prevent currently irrelevant content from entering the storage unit.

[0106] The unit state of the current input is calculated based on the previous output and this input; the unit state C at the current moment t Calculation: Based on the last cell state C t-1 Multiply the forget gate f element-wise t , and then use the current input unit state C t Element-wise multiplication of the input gate i t , then add the two products: In this way, the current memory C t and long-term memory C t-1 Combined together, a new unit state C is formed t Due to the control of the forget gate, it can save information from a long time ago, and due to the control of the input gate, it can prevent currently irrelevant content from entering the storage unit.

[0107] The main function of the output gate is to control the influence of long-term memory on the current output. The output value h of the output gate t as follows:

[0108] h t =o t *tanh(C t )

[0109] Similar to the BP neural network, the reverse update of the LSTM network can be divided into three steps: determining parameters, calculating errors, and updating gradients.

[0110] 1) Determine the parameters: forward calculate the output value of each storage unit, a total of 4 variables (f t 、i t 、c' t 、o t ), the calculation method is shown in the above specific formula.

[0111] 2) Error Calculation: Reversely calculate the error term value of each storage unit. Like RNN, the backpropagation of LSTM error terms also includes two directions: one is backpropagation along time, that is, starting from the current time t, calculating the error term at each moment; the other is propagating the error term to the previous layer.

[0112] 3) Gradient update: Calculate the gradient of each weight based on the corresponding error term.

[0113]

[0114] σ′(z)=y(1-y)

[0115] The activation function of the door switch is defined as the sigmoid function, the output activation function is the tanh function, and the derivatives are:

[0116]

[0117] tanh′(z)=1-y 2

[0118] The goal of network optimization is to learn 8 sets of parameters, including the weight matrix and bias term of the forget gate, the weight matrix and bias term of the input gate, the weight matrix and bias term of the output gate, and the weight matrix and bias term of the unit state.

[0119] The weight matrix W is composed of two matrices. The two parts use different formulas in the back propagation. In the subsequent derivation, the weight matrix should also be written as two separate matrices [w fh ,w fx ].

[0120] In the reverse propagation of the error term along time, the error term at time t-1 is calculated as follows:

[0121]

[0122] Using h t and C t The definition of and the total derivative formula can be used to obtain the formula for passing the error term forward to any k moment:

[0123]

[0124] The gradient update is shown in Table 1 below.

[0125]

[0126] Table 1

[0127] The present invention utilizes a backpropagation algorithm to optimize and update the model parameters of the long short-term memory neural network. A trained temperature distribution prediction model can be obtained after several iterations. The specific number of iterations can be pre-set, or training is considered complete when the test set meets the required accuracy.

[0128] For the cabin temperature distribution time series data to be predicted, input it into the trained temperature distribution prediction model to obtain the cabin temperature distribution prediction result of the target vehicle in the next period

[0129] As a further optional implementation, determining the cabin area to be adjusted and the temperature adjustment value corresponding to the cabin area to be adjusted based on the cabin temperature distribution prediction result specifically includes:

[0130] S1031. Determine a predicted temperature value for each cabin area based on the cabin temperature distribution prediction result;

[0131] S1032: Obtain a temperature setting value for the target vehicle. When the absolute value of the difference between the temperature setting value and the temperature prediction value is greater than or equal to a preset temperature difference threshold, determine the corresponding cabin area as the cabin area to be adjusted.

[0132] S1033: Determine a temperature adjustment value according to a difference between the temperature setting value and the temperature prediction value of the cabin area to be adjusted.

[0133] Specifically, the temperature prediction value of each cabin area is determined based on the cabin temperature distribution prediction result and the cabin area distribution map; the temperature setting value set by the current user of the target vehicle is obtained, and when the absolute value of the difference between the temperature setting value and the temperature prediction value is greater than or equal to a preset temperature difference threshold (such as 1 degree), it means that the temperature value of the corresponding cabin area in the next time period is significantly different from the temperature setting value, so the cabin area is used as the cabin area to be adjusted, and the temperature adjustment value is determined based on the difference between the temperature setting value and the temperature prediction value of the cabin area to be adjusted. It can be recognized that when the temperature setting value is greater than the temperature prediction value, the temperature adjustment value is positive, and vice versa, the temperature adjustment value is negative.

[0134] As a further optional embodiment, determining a target air conditioning damper according to the cabin area to be adjusted, and determining an air volume change value for the cabin area to be adjusted according to the temperature adjustment value, specifically includes:

[0135] S1041. Determine, based on the cabin area to be adjusted, an air conditioning damper at a corresponding position as a target air conditioning damper;

[0136] S1042: Determine an air thermal energy adjustment value for the cabin area to be adjusted based on the temperature adjustment value and the size of the cabin area to be adjusted;

[0137] S1043. Obtain the air conditioning cold air temperature of the target vehicle, and determine the air volume change value according to the air conditioning cold air temperature and the air thermal energy adjustment value.

[0138] Specifically, in an embodiment of the present invention, each cabin area is provided with a corresponding air-conditioning damper for adjusting the temperature of the corresponding cabin area. The corresponding unknown air-conditioning damper is determined as the target air-conditioning damper that needs to adjust the opening according to the cabin area to be adjusted. At the same time, based on the temperature adjustment value and the space size of the cabin area to be adjusted, the air thermal energy adjustment value of the cabin area to be adjusted can be calculated in combination with the principles of thermodynamics. Finally, the current air-conditioning cold air temperature of the target vehicle is obtained, and the air thermal energy change value that can be brought about by unit air volume is determined according to the air-conditioning cold air temperature. Therefore, the air volume change value can be calculated in combination with the air thermal energy adjustment value.

[0139] It should be noted that the temperature distribution prediction result predicted by the embodiment of the present invention is the predicted value when the target vehicle is not adjusted according to the current air-conditioning settings. Therefore, the calculated air thermal energy adjustment value is relative to the air thermal energy adjustment value required when the current air-conditioning settings are not adjusted. Therefore, the air volume change value calculated based on the air thermal energy adjustment value is also relative to the air volume change value when the current air-conditioning settings are not adjusted.

[0140] As a further optional implementation, adjusting the target air conditioner damper opening according to the air volume change value specifically includes:

[0141] S1044: Determine the current air volume of the target air conditioner damper according to the current opening of the target air conditioner damper and a preset damper opening-air volume mapping table;

[0142] S1045: Determine the target air volume of the target air conditioning damper according to the air volume change value and the current air volume;

[0143] S1046, determining a target opening of the target air conditioning damper according to the target air volume and a damper opening-air volume mapping table;

[0144] S1047. Adjust the target air-conditioning damper according to the target opening.

[0145] Specifically, a damper opening-air volume mapping table is pre-constructed based on the structural parameters of the air-conditioning damper and the operating parameters of the vehicle air-conditioning. The current air volume is determined based on the current opening, and the target air volume is obtained in combination with the air volume change value. The target opening is then obtained by looking up the table, so that the target air-conditioning damper can be adjusted.

[0146] The above describes the method steps of an embodiment of the present invention. It is understood that the embodiment of the present invention predicts the cabin temperature distribution of the target vehicle in the next time period, determines the cabin area to be adjusted and the corresponding temperature adjustment value based on the cabin temperature distribution prediction results, and thus determines the target air conditioning damper to be adjusted and the corresponding air volume change value. The opening of the target air conditioning damper is then adjusted based on the air volume change value, thereby achieving pre-adjustment of the vehicle's air conditioning, eliminating the need for the user to perform repeated manual adjustments, improving the efficiency and accuracy of the vehicle's air conditioning control, and providing users with a more comfortable driving environment, enhancing the user's driving safety and driving experience.

[0147] Reference Figure 4 , an embodiment of the present invention provides an artificial intelligence-based vehicle air conditioning control system, comprising:

[0148] A temperature distribution time series data acquisition module is used to obtain the cabin temperature distribution data of the target vehicle in the current period and determine the cabin temperature distribution time series data based on the cabin temperature distribution data;

[0149] The temperature distribution prediction module is used to input the cabin temperature distribution time series data into the pre-trained temperature distribution prediction model to obtain the cabin temperature distribution prediction result of the target vehicle in the next time period;

[0150] A module for determining a cabin area to be adjusted and a temperature adjustment value, configured to determine a cabin area to be adjusted and a temperature adjustment value corresponding to the cabin area to be adjusted based on the cabin temperature distribution prediction result;

[0151] The air conditioning damper opening adjustment module is used to determine the target air conditioning damper according to the cabin area to be adjusted, determine the air volume change value of the cabin area to be adjusted according to the temperature adjustment value, and then adjust the opening of the target air conditioning damper according to the air volume change value.

[0152] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0153] Reference Figure 5 , an embodiment of the present invention provides an artificial intelligence-based vehicle air conditioning control device, comprising:

[0154] at least one processor;

[0155] at least one memory for storing at least one program;

[0156] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned artificial intelligence-based vehicle air conditioning control method.

[0157] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0158] An embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor. When the program is executed by the processor, it is used to execute the above-mentioned artificial intelligence-based vehicle air conditioning control method.

[0159] A computer-readable storage medium according to an embodiment of the present invention can execute an artificial intelligence-based vehicle air-conditioning control method provided by an embodiment of the method of the present invention, can execute any combination of implementation steps of the embodiment of the method, and has the corresponding functions and beneficial effects of the method.

[0160] The embodiment of the present invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs Figure 1 The method shown.

[0161] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0162] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present invention set forth in the claims using ordinary skills without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0163] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0164] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0165] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable media on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0166] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0167] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0168] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0169] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A vehicle air conditioning control method based on artificial intelligence, characterized in that: The following steps are involved: Acquiring cabin temperature distribution data of a target vehicle during a current period, and determining cabin temperature distribution time series data based on the cabin temperature distribution data; Inputting the cabin temperature distribution time series data into a pre-trained temperature distribution prediction model to obtain a cabin temperature distribution prediction result for the target vehicle in the next time period; determining a cabin area to be adjusted and a temperature adjustment value corresponding to the cabin area to be adjusted according to the cabin temperature distribution prediction result; determining a target air conditioning damper according to the cabin area to be adjusted, determining an air volume change value for the cabin area to be adjusted according to the temperature adjustment value, and then adjusting the opening of the target air conditioning damper according to the air volume change value; The temperature distribution prediction model is trained by the following steps: Obtain cabin temperature distribution sample data of the test vehicle at multiple times during a historical period; Determining a temperature distribution prediction label based on the cabin temperature distribution sample data at the last moment, and determining cabin temperature distribution sample time series data based on the cabin temperature distribution sample data at other moments, and then constructing a training sample set based on the cabin temperature distribution sample time series data and the temperature distribution prediction label; Inputting the training sample set into a pre-built long short-term memory neural network for training, optimizing the model parameters of the long short-term memory neural network using a back propagation algorithm to obtain a trained temperature distribution prediction model; The model parameters include a forget gate weight matrix, an input gate weight matrix, an output gate weight matrix, a unit state weight matrix, a forget gate bias term, an input gate bias term, an output gate bias term, and a unit state bias term. The back propagation algorithm is used to optimize the model parameters of the long short-term memory neural network, which specifically includes: Forward calculation of the forget gate, input gate, output gate and unit state of each storage unit; Reversely calculating the error term value of each storage unit according to the forget gate, the input gate, the output gate and the unit state; Determining a first gradient of the forget gate weight matrix, a second gradient of the input gate weight matrix, a third gradient of the output gate weight matrix, and a fourth gradient of the unit state weight matrix according to the error term value; Gradient updating is performed on the first gradient, the second gradient, the third gradient, and the fourth gradient, thereby optimizing the forget gate weight matrix, the input gate weight matrix, the output gate weight matrix, the unit state weight matrix, the forget gate bias term, the input gate bias term, the output gate bias term, and the unit state bias term.

2. The vehicle air conditioning control method based on artificial intelligence according to claim 1, characterized in that: The step of obtaining cabin temperature distribution data of the target vehicle in the current time period and determining cabin temperature distribution time series data based on the cabin temperature distribution data specifically includes: Acquiring real-time temperature information of each cabin area by using temperature sensors provided in each cabin area of ​​the target vehicle; determining a cabin temperature distribution heat map of the target vehicle at each moment according to the real-time temperature information, and using the cabin temperature distribution heat map as the cabin temperature distribution data; The cabin temperature distribution data at each moment is sorted in chronological order to obtain the cabin temperature distribution time series data.

3. The vehicle air conditioning control method based on artificial intelligence according to claim 1, characterized in that: The step of determining the cabin area to be adjusted and the temperature adjustment value corresponding to the cabin area to be adjusted according to the cabin temperature distribution prediction result specifically includes: determining a temperature prediction value for each cabin area according to the cabin temperature distribution prediction result; obtaining a temperature setting value of the target vehicle, and determining the corresponding cabin area as the cabin area to be adjusted when the absolute value of the difference between the temperature setting value and the temperature prediction value is greater than or equal to a preset temperature difference threshold; The temperature adjustment value is determined according to a difference between the temperature setting value of the cabin area to be adjusted and the temperature prediction value.

4. The vehicle air conditioning control method based on artificial intelligence according to claim 1, characterized in that: The step of determining a target air-conditioning damper according to the cabin area to be adjusted, and determining an air volume change value of the cabin area to be adjusted according to the temperature adjustment value, specifically includes: Determining, according to the cabin area to be adjusted, an air conditioning damper at a corresponding position as the target air conditioning damper; determining an air thermal energy adjustment value for the cabin area to be adjusted according to the temperature adjustment value and the space size of the cabin area to be adjusted; The air conditioning cold air temperature of the target vehicle is obtained, and the air volume change value is determined according to the air conditioning cold air temperature and the air thermal energy adjustment value.

5. The vehicle air conditioning control method based on artificial intelligence according to any one of claims 1 to 4, characterized in that: The adjusting the opening of the target air-conditioning damper according to the air volume change value specifically includes: Determining the current air volume of the target air conditioning damper according to the current opening of the target air conditioning damper and a preset damper opening-air volume mapping table; Determining a target air volume of the target air conditioning damper according to the air volume change value and the current air volume; determining a target opening of the target air-conditioning damper according to the target air volume and the damper opening-air volume mapping table; The target air-conditioning damper is adjusted according to the target opening.

6. An artificial intelligence-based vehicle air conditioning control system, characterized in that: include: a temperature distribution time series data acquisition module, configured to acquire cabin temperature distribution data of a target vehicle in a current period, and determine cabin temperature distribution time series data based on the cabin temperature distribution data; a temperature distribution prediction module, configured to input the cabin temperature distribution time series data into a pre-trained temperature distribution prediction model to obtain a cabin temperature distribution prediction result of the target vehicle in the next time period; a module for determining a cabin area to be adjusted and a temperature adjustment value, configured to determine a cabin area to be adjusted and a temperature adjustment value corresponding to the cabin area to be adjusted based on the cabin temperature distribution prediction result; an air conditioning damper opening adjustment module, configured to determine a target air conditioning damper according to the cabin area to be adjusted, determine an air volume change value for the cabin area to be adjusted according to the temperature adjustment value, and further adjust the opening of the target air conditioning damper according to the air volume change value; The temperature distribution prediction model is trained by the following steps: Obtain cabin temperature distribution sample data of the test vehicle at multiple times during a historical period; Determining a temperature distribution prediction label based on the cabin temperature distribution sample data at the last moment, and determining cabin temperature distribution sample time series data based on the cabin temperature distribution sample data at other moments, and then constructing a training sample set based on the cabin temperature distribution sample time series data and the temperature distribution prediction label; Inputting the training sample set into a pre-built long short-term memory neural network for training, optimizing the model parameters of the long short-term memory neural network using a back propagation algorithm to obtain a trained temperature distribution prediction model; The model parameters include a forget gate weight matrix, an input gate weight matrix, an output gate weight matrix, a unit state weight matrix, a forget gate bias term, an input gate bias term, an output gate bias term, and a unit state bias term. The back propagation algorithm is used to optimize the model parameters of the long short-term memory neural network, which specifically includes: Forward calculation of the forget gate, input gate, output gate and unit state of each storage unit; Reversely calculating the error term value of each storage unit according to the forget gate, the input gate, the output gate and the unit state; Determining a first gradient of the forget gate weight matrix, a second gradient of the input gate weight matrix, a third gradient of the output gate weight matrix, and a fourth gradient of the unit state weight matrix according to the error term value; Gradient updating is performed on the first gradient, the second gradient, the third gradient, and the fourth gradient, thereby optimizing the forget gate weight matrix, the input gate weight matrix, the output gate weight matrix, the unit state weight matrix, the forget gate bias term, the input gate bias term, the output gate bias term, and the unit state bias term.

7. An artificial intelligence-based vehicle air conditioning control device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the artificial intelligence-based vehicle air-conditioning control method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to execute the vehicle air-conditioning control method based on artificial intelligence as described in any one of claims 1 to 5 when executed by the processor.

Images