Temperature control method, system and device and storage medium

Abstract

The invention provides a temperature control method, and belongs to the technical field of temperature control, and the temperature control method comprises the steps: obtaining first temperature control data which comprises at least one of environment perception data, user setting data and user attribute data; processing the first temperature control data by using a temperature control model to obtain a first air outlet temperature of the air conditioning system; and performing temperature control based on the first air outlet temperature. In the embodiment of the invention, the temperature control precision of the air conditioning system can be effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of temperature control, and in particular, to a temperature control method, system, device and storage medium. BACKGROUND

[0002] With the rapid development of the vehicle industry, users' demand for comfort during riding continues to increase. Therefore, the performance optimization of the vehicle air conditioning system, as the core component for adjusting the vehicle environment, is particularly important for improving user experience. However, the control accuracy of the existing air conditioning control technology is low, which makes it difficult to effectively improve user experience. SUMMARY

[0003] The present application aims to solve at least one of the technical problems existing in the prior art, and proposes a temperature control method, system, device and storage medium.

[0004] In a first aspect, an embodiment of the present application provides a temperature control method, which comprises:

[0005] obtaining first temperature control data, wherein the first temperature control data comprises at least one of environment perception data, user setting data and user attribute data;

[0006] processing the first temperature control data by using a temperature control model to obtain a first outlet temperature of the air conditioning system;

[0007] controlling temperature based on the first outlet temperature.

[0008] In some embodiments, the environment perception data comprises vehicle running state data.

[0009] And / or, the user setting data comprises at least one of air volume, humidity, blowing direction mode and inside-outside circulation ratio of the air conditioning system.

[0010] And / or, the user attribute data comprises at least one of user age and user gender.

[0011] In some embodiments, before the temperature control based on the first outlet temperature, the method further comprises:

[0012] obtaining second temperature control data, wherein the second temperature control data comprises at least one of environment temperature, sunlight irradiance and user setting temperature;

[0013] processing the second temperature control data by using a temperature control function to obtain a second outlet temperature of the air conditioning system;

[0014] determining a target outlet temperature of the air conditioning system based on the first outlet temperature and the second outlet temperature;

[0015] the temperature control based on the first outlet temperature comprises:

[0016] the temperature control based on the target outlet temperature.

[0017] In some embodiments, the temperature control function comprises a first sub-function and a second sub-function.

[0018] the processing of the second temperature control data by using the temperature control function to obtain the second outlet temperature of the air conditioning system comprises:

[0019] the processing of the second temperature control data by using the first sub-function to obtain an estimated energy demand.

[0020] the processing of the estimated energy demand by using the second sub-function to obtain the second outlet temperature of the air conditioning system.

[0021] In some embodiments, the determination of the target outlet temperature of the air conditioning system based on the first outlet temperature and the second outlet temperature comprises:

[0022] the weighted sum processing of the first outlet temperature and the second outlet temperature based on a preset weight to obtain the target outlet temperature of the air conditioning system.

[0023] In some embodiments, before the processing of the first temperature control data by using the temperature control model to obtain the first outlet temperature of the air conditioning system, the method further comprises:

[0024] obtaining a training sample set, the training sample set comprising a plurality of training samples and a sample label corresponding to each training sample;

[0025] for each training sample, processing the training sample by using a preset temperature control model to obtain a reference outlet temperature corresponding to the training sample;

[0026] processing the reference outlet temperature of a target training sample and the sample label of the target training sample based on a loss function to obtain a loss function value of the temperature control model, the target training sample being any one of the plurality of training samples;

[0027] training the preset temperature control model by using the plurality of training samples based on the loss function of the preset temperature control model to obtain a trained temperature control model.

[0028] In some embodiments, the preset temperature control model comprises an input layer, a hidden layer and an output layer, the input layer comprising D first neurons, the hidden layer comprising Q second neurons, and the output layer comprising L third neurons.

[0029] processing the training sample by using a preset temperature control model to obtain a reference outlet temperature corresponding to the training sample, comprising:

[0030] processing the training sample by using D first neurons respectively to obtain first information output by the D first neurons respectively;

[0031] processing the second information by using Q second neurons respectively to obtain third information output by the Q second neurons respectively, the second information being determined based on the first information output by the D first neurons respectively, neuron weights of the D first neurons and bias information of the input layer;

[0032] processing the fourth information by using the L third neurons respectively to obtain fifth information output by the L third neurons respectively, the fourth information being determined based on the third information output by the Q second neurons respectively, neuron weights of the Q second neurons and bias information of the hidden layer, D, Q and L being positive integers;

[0033] determining the reference outlet temperature corresponding to the training sample based on the fifth information output by the L third neurons respectively.

[0034] In a second aspect, an embodiment of the present application further provides a temperature control system, comprising:

[0035] an acquisition module configured to acquire first temperature control data, the first temperature control data comprising at least one of environment perception data, user setting data and user attribute data;

[0036] a processing module configured to process the first temperature control data by using a temperature control model to obtain a first outlet temperature of the air conditioning system;

[0037] a control module configured to perform temperature control based on the first outlet temperature.

[0038] In some embodiments, the acquisition module is further configured to acquire second temperature control data, the second temperature control data comprising at least one of an environment temperature, a sunlight irradiance and a user setting temperature;

[0039] the processing module is further configured to process the second temperature control data by using a temperature control function to obtain a second outlet temperature of the air conditioning system;

[0040] the system further comprises a determination module configured to determine a target outlet temperature of the air conditioning system based on the first outlet temperature and the second outlet temperature;

[0041] The control module is specifically configured to perform temperature control based on the target outlet temperature.

[0042] In some embodiments, the obtaining module is further configured to obtain a training sample set, the training sample set including a plurality of training samples and a sample label corresponding to each of the training samples.

[0043] The processing module is further configured to, for each of the training samples, process the training sample by using a preset temperature control model to obtain a reference outlet temperature corresponding to the training sample, and process the reference outlet temperature of a target training sample and the sample label of the target training sample based on a loss function to obtain a loss function value of the temperature control model, the target training sample being any one of the plurality of training samples.

[0044] The system further includes a training module configured to train the preset temperature control model by using the plurality of training samples based on the loss function of the preset temperature control model to obtain a trained temperature control model.

[0045] In a third aspect, an electronic device is provided, including: one or more processors; a memory configured to store one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement the temperature control method according to the first aspect.

[0046] In a fourth aspect, a computer storage medium is provided, and a computer program is stored in the computer storage medium, and when the computer program is executed by a processor, the temperature control method according to the first aspect is implemented.

[0047] The temperature control method provided by the present application can obtain first temperature control data, process the first temperature control data by using a temperature control model to obtain a first outlet temperature of an air conditioning system, and then perform temperature control based on the first outlet temperature. Since the first temperature control data can include at least one of environmental perception data, user setting data and user attribute data, the outlet temperature of the air conditioning system can be accurately determined, the control accuracy of the air conditioning system can be improved, and the user's comfort experience can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 A flowchart of a temperature control method provided by the present application is shown in the figure;

[0049] Figure 2 A flowchart of another temperature control method provided by the present application is shown in the figure;

[0050] Figure 3 is a flowchart of another temperature control method provided by an embodiment of the present application;

[0051] Figure 4 is a structural block diagram of a data processing system provided by an embodiment of the present application;

[0052] Figure 5 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0053] For those skilled in the art to have a better understanding of the technical solutions of the present application, the exemplary embodiments of the present application are described below in conjunction with the drawings, which include various details of the embodiments of the present application to help understanding, and should be considered as merely exemplary. Therefore, those skilled in the art should realize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Also, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0054] In the case of no conflict, each embodiment of the present application and each feature in the embodiments can be combined with each other.

[0055] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0056] The terms used herein are only used to describe specific embodiments, and are not intended to limit the present application. As used herein, the singular forms "a" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the terms "comprise" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. The terms "connected" or "coupled" and / or like terms are not limited to a direct connection or coupling, but also include an indirect connection or coupling, whether or not it is physical, mechanical, electrical, and / or the like.

[0057] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present application, and will not be interpreted in an overly literal or overly formal sense unless expressly so defined herein.

[0058] The collection, storage, use, processing, transmission, provision and disclosure of the user personal information in the technical solution of the present application comply with relevant laws and regulations and do not violate public order and good customs. The use of user data in the technical solution complies with relevant national laws and regulations (for example, the Information Security Technology Personal Information Security Specification). For example, appropriate measures are taken for personal information access control, and restrictions are given for the display of personal information. The use purpose of personal information does not exceed the direct or reasonably related range, and the use of personal information eliminates the explicit identity orientation and avoids accurate positioning to a specific individual.

[0059] As described in the background, as the core component for adjusting the environment in the vehicle, the performance optimization of the vehicle air conditioning system is particularly important for providing user experience. However, the existing vehicle air conditioning system mostly controls the outlet temperature of the air conditioning system through the outside temperature, the inside temperature, the sunlight irradiance and the set temperature. The considered factors are less and not comprehensive enough, such as the inside-out circulation ratio, so that the accuracy of the determined outlet temperature is low, and the control precision is low, thereby resulting in poor user comfort experience.

[0060] To solve at least one of the technical problems in the related art, the present application provides a temperature control method. The temperature control method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0061] Figure 1 is a flowchart of a temperature control method provided by an embodiment of the present application.

[0062] As shown in Figure 1 , the execution subject of the method can be a temperature control system. Based on this, the method can specifically include the following steps:

[0063] Step 110, obtaining first temperature control data.

[0064] The first temperature control data can be related data for temperature control of the air conditioning system. In some embodiments, the first temperature control data can include at least one of environment perception data, user setting data and user attribute data. The environment perception data can be related data in the environment inside and outside the air conditioning system, the user setting data can be data related to the air conditioning system set by the user, and the user attribute data can be related attributes of the user's own attributes, which are not limited here.

[0065] Step 120, processing the first temperature control data by using a temperature control model to obtain a first outlet temperature of the air conditioning system.

[0066] The temperature control model may be a pre-trained model for determining the outlet temperature of the air conditioning system. In some embodiments, the temperature control model may be constructed based on a back propagation neural network (BP).

[0067] In addition, the above-mentioned first air outlet temperature refers to the temperature at the air outlet of the air-conditioning system, which is not specifically limited here.

[0068] Step 130: Perform temperature control based on the first air outlet temperature.

[0069] Specifically, the temperature control system can obtain first temperature control data and process the first temperature control data using a temperature control model to obtain a first air outlet temperature of the air-conditioning system, and then perform temperature control based on the first air outlet temperature.

[0070] Based on the temperature control method provided in the embodiment of the present invention, first temperature control data can be obtained, and the first temperature control data can be processed using a temperature control model to obtain a first air outlet temperature of the air-conditioning system, and then temperature control can be performed based on the first air outlet temperature. Since the above-mentioned first temperature control data may include at least one of environmental perception data, user setting data and user attribute data, the air outlet temperature of the air-conditioning system can be accurately determined, thereby improving the control accuracy of the air-conditioning system and enhancing the user comfort experience.

[0071] To fully and in detail describe the temperature control method provided by the embodiments of the present invention, in some embodiments, when the air conditioning system is a vehicle-mounted air conditioning system, the environmental sensing data may include vehicle operating status data. The vehicle operating status data may be relevant data that characterizes the vehicle's operating status and affects the temperature control of the air conditioning system. For example, the vehicle operating status data may be vehicle speed, which is not specifically limited herein.

[0072] In addition, considering that different setting data when the user turns on the air-conditioning system will also affect the temperature control effect of the air-conditioning system, the above-mentioned user setting data can include at least one of the air volume, humidity, blowing direction mode and internal and external circulation ratio of the air-conditioning system.

[0073] Considering that users of different ages and genders have different requirements for temperature control, the user attribute data includes at least one of the user's age and the user's gender.

[0074] In addition to the above, the environmental perception data can also include at least one of an ambient temperature and a sunlight irradiance, and if the air conditioning system is a vehicle-mounted air conditioning system, the ambient temperature can include an internal temperature of the vehicle and an external temperature of the vehicle, which are not specifically limited herein. The user setting data can also include a user setting temperature, which is not specifically limited herein. Based on this, it should be noted that the internal-external circulation ratio can be related to the ambient temperature, the user setting temperature, the sunlight irradiance, and the vehicle operating state data, and the air volume can be related to the ambient temperature, the sunlight irradiance, and the user setting temperature.

[0075] In this embodiment, the influence of the vehicle operating state data, the user setting data, and the user attribute data on the temperature control of the air conditioning system can be considered, and the outlet temperature of the air conditioning system is determined in combination with at least one of the above vehicle operating state data, user setting data, and user attribute data, which can effectively improve the accuracy of the outlet temperature and further improve the temperature control precision.

[0076] Based on this, it should be noted that in the case where the first temperature control data includes vehicle operating state data, the temperature control system can obtain the vehicle operating state data through related sensors arranged on the vehicle. In the case where the first temperature control data includes user setting data, the temperature control system can obtain the user setting data by receiving user instructions. In the case where the first temperature control data includes user attribute data, the temperature control system can use the face detection algorithm in OpenCV to detect a face image in an input image or video frame, and perform key point positioning on the detected face image, and perform face alignment through methods such as affine transformation to improve the accuracy of subsequent recognition. Further, a deep learning model (such as MTCNN, FaceNet, etc.) can be used to extract features from the aligned face image, which usually contains texture, shape, and other information of the face, and can be used to distinguish different individuals and predict age and gender. Finally, the extracted features are input into a trained classifier to obtain the age and gender prediction results corresponding to the face image. The classifier can be trained using algorithms such as support vector machines, random forests, neural networks, etc.

[0077] In addition, in order to comprehensively and in detail describe the temperature control method provided by the embodiments of the present application, in one embodiment of the present application, as shown in Figure 2 Before the step 130, the temperature control method provided by the embodiments of the present application can further include the following steps:

[0078] Step 210, obtaining second temperature control data.

[0079] In some embodiments, the second temperature control data can include at least one of an ambient temperature, a sunlight irradiance, and a user setting temperature, which are not specifically limited herein.

[0080] Step 220: Process the second temperature control data using a temperature control function to obtain a second air outlet temperature of the air conditioning system.

[0081] Step 230: Determine a target air outlet temperature of the air conditioning system based on the first air outlet temperature and the second air outlet temperature.

[0082] Specifically, the temperature control system can obtain second temperature control data, which may include at least one of the ambient temperature, sunlight irradiance and user-set temperature. In this way, the temperature control function can be used to process at least one of the above-mentioned ambient temperature, sunlight irradiance and user-set temperature to obtain the second outlet temperature of the air-conditioning system, and then the target outlet temperature of the air-conditioning system can be determined based on the first outlet temperature and the second outlet temperature.

[0083] Based on this, the above step 130 may specifically include the following steps:

[0084] Step 1301: Perform temperature control based on the target air outlet temperature.

[0085] Specifically, the temperature control system can determine a target air outlet temperature of the air conditioning system based on the first air outlet temperature and the second air outlet temperature, and then perform temperature control based on the target air outlet temperature.

[0086] It should be noted that the air conditioning system's operating modes can include a first mode (i.e., intelligent mode) and a second mode (i.e., traditional mode). When the user sets the air conditioning system's operating mode to the first mode, the temperature control system can use the temperature control model to determine the air conditioning system's air outlet temperature (i.e., the aforementioned first air outlet temperature). When the user sets the air conditioning system's operating mode to the second mode, the temperature control system can use the energy algorithm (i.e., the aforementioned temperature control function) to determine the air conditioning system's air outlet temperature (i.e., the aforementioned second air outlet temperature). In this way, the temperature control system can combine the air outlet temperatures calculated under different operating modes to determine the final air outlet temperature, thereby avoiding potential deviations in the air outlet temperature calculated using a single method.

[0087] In this embodiment, the first temperature control data is processed using the temperature control model to obtain the first air outlet temperature. The second temperature control data is then processed using the temperature control function to obtain the second air outlet temperature. The first and second air outlet temperatures are then combined to determine the target air outlet temperature for final temperature control. This effectively improves the accuracy of temperature control and, in turn, enhances the user's comfort experience.

[0088] Based on this, in one embodiment of the present application, the temperature control function can include a first sub-function and a second sub-function, based on which the step 220 can specifically include the following steps:

[0089] The second temperature control data is processed by using the first sub-function to obtain an estimated energy demand;

[0090] The estimated energy demand is matched by using the second sub-function to obtain a second outlet temperature of the air conditioning system.

[0091] Specifically, since the temperature control function can include a first sub-function and a second sub-function, thus, the temperature control system can process the second temperature control data by using the first sub-function to obtain an estimated energy demand, and then can process the estimated energy demand by using the second sub-function to obtain a second outlet temperature of the air conditioning system.

[0092] In one example, the first sub-function can satisfy the following formula (1):

[0093] ER = MidVal - Sunload * K1 + (SetTemp - MidTemp) * K2 + OutTemp * K3 + (SetTemp - IncarCompTemp) * K4 (1)

[0094] Wherein, ER is the estimated energy demand, and its data range is 0~1000. Sunload is the solar irradiance. SetTemp is the user set temperature. OutTemp is the external environment temperature. IncarCompTemp is the internal environment temperature, which together form the ambient temperature. MidVal is the energy intermediate value (data range: 0~1000, usually 500). MidTemp is the comfortable temperature. K1 is the weight coefficient corresponding to the solar irradiance, which can be taken as 0.3, and is generally not more than 0.6. K2 is the weight coefficient corresponding to the user set temperature, which can be taken as 20, and is generally not less than 10. K3 is the weight coefficient corresponding to the external environment temperature, which can be taken as 5. K4 is the weight coefficient corresponding to the internal environment temperature, which can be taken as 30.

[0095] In one example, the second sub-function can represent the corresponding relationship between the estimated energy demand and the outlet temperature, for example, can be as shown in Table 1:

[0096] Table 1

[0097]

[0098] In order to obtain the outlet temperature more accurately, the second sub-function can represent the corresponding relationship between the ambient temperature, the estimated energy demand and the outlet temperature. In an example, the corresponding relationship can be shown in Table 2 as follows: when the ambient temperature (AirTemp) is -40℃ and the energy demand (ER) is 0, the outlet target temperature is 1℃; when the ambient temperature is -40℃ and the energy demand is 200, the outlet target temperature is 3℃, and so on.

[0099] Table 2

[0100]

[0101] Therefore, the outlet temperature can be obtained by the table based on the estimated energy demand, so that the change of the outlet temperature can be reflected by the change of the estimated energy demand, thereby changing the outlet temperature with the change of the working condition. The table can be changed by calibration. The values in the interval are linearly filled. The parameters can be appropriately modified with the change of the ambient temperature during calibration, and the outlet target temperature is appropriately lower when the ambient temperature is higher.

[0102] In this embodiment, the estimated energy demand can be obtained by processing the obtained second temperature control data by the first sub-function, and the second outlet temperature can be obtained by processing the estimated energy demand based on the second sub-function. Therefore, the outlet temperature of the air conditioning system can be effectively obtained, and the temperature control accuracy of the air conditioning system can be improved.

[0103] In addition, in order to comprehensively and specifically describe the temperature control method provided by the embodiment of the present application, in an embodiment of the present application, the step 230 can specifically include the following steps:

[0104] The first outlet temperature and the second outlet temperature are weighted and summed based on a preset weight to obtain the target outlet temperature of the air conditioning system.

[0105] The preset weight can be set based on actual experience or situation, which is not specifically limited here.

[0106] Specifically, after obtaining the first outlet temperature and the second outlet temperature, the temperature control system can weight and sum the first outlet temperature and the second outlet temperature based on the preset weight to obtain the target outlet temperature of the air conditioning system.

[0107] In this embodiment, the effective combination of the first outlet temperature and the second outlet temperature can be realized by weighting and summing the first outlet temperature and the second outlet temperature, thereby effectively improving the accuracy of the target outlet temperature, effectively improving the temperature control accuracy, and effectively improving the user's comfort experience.

[0108] In addition, it should be noted that the temperature control method provided by the embodiments of the present application needs to utilize the temperature control model trained in advance to process the obtained temperature control data. Therefore, in order to better describe the temperature control method provided by the embodiments of the present application, the training method of the temperature control model provided by the embodiments of the present application will be described below in combination with the accompanying drawings.

[0109] The embodiments of the present application provide a training method of a temperature control model. The execution subject of the method can be a temperature control system. The method can be implemented through the following steps.

[0110] I. Obtaining a training sample set

[0111] The training sample set can include a plurality of training samples and a sample label corresponding to each training sample. The sample label can represent the label outlet temperature corresponding to the training sample.

[0112] In order to obtain a more accurate training sample set and further better train the temperature control model, in an embodiment of the present application, obtaining the training sample set can include the following steps.

[0113] Step 1: obtaining a plurality of training samples.

[0114] Each training sample can include at least one of an environment perception sample, a user setting sample, and a user attribute sample.

[0115] Step 2: labeling a sample label corresponding to each of the plurality of training samples.

[0116] Specifically, the sample label of each training sample can be labeled by manual labeling, or the sample label of each training sample can be directly labeled by the temperature control system. The specific labeling method is not limited here.

[0117] It should be noted that during the labeling process, 75% of the labeled samples can be used as training samples, and 25% of the labeled samples can be used as test samples. The distribution ratio of the training samples and the test samples is not limited here.

[0118] It should be further noted that the temperature control model needs to be iteratively processed multiple times to adjust its loss function value until the loss function value meets the training stop condition, and the trained temperature control model is obtained. However, in each iteration training, if only one training sample is input, the sample amount is too small to be conducive to the training and adjustment of the temperature control model. Therefore, the training sample set needs to be divided into a plurality of training samples. In this way, the training sample set can be used to iteratively process the temperature control model.

[0119] Thus, the training samples can be labeled to obtain sample labels corresponding to the plurality of training samples, and then a training sample set containing the plurality of training samples can be obtained. In this way, the subsequent model training is facilitated.

[0120] II. For each of the training samples, a preset temperature control model is used to process the training sample to obtain a reference outlet temperature corresponding to the training sample.

[0121] Specifically, after obtaining the plurality of training samples, for each of the plurality of training samples, the preset temperature control model is used to process the training sample to obtain a reference outlet temperature corresponding to the training sample.

[0122] To be able to describe the temperature control method provided by the embodiments of the present application in detail, in an embodiment of the present application, since the preset temperature control model can include an input layer, a hidden layer and an output layer, the input layer includes D first neurons, the hidden layer includes Q second neurons, and the output layer includes L third neurons; based on this, as shown in the figure, Figure 3 The step specifically can include the following steps:

[0123] Step 310: The D first neurons are respectively used to process the training sample to obtain first information output by the D first neurons.

[0124] Step 320: The Q second neurons are respectively used to process the second information to obtain third information output by the Q second neurons.

[0125] Step 330: The L third neurons are respectively used to process the fourth information to obtain fifth information output by the L third neurons.

[0126] Step 340: Based on the fifth information output by the L third neurons, a reference outlet temperature corresponding to the training sample is determined.

[0127] Wherein, D, Q, L are positive integers.

[0128] In some embodiments, the second information is determined based on the first information output by the D first neurons, the neuron weights of the D first neurons, and the bias information of the input layer. The fourth information is determined based on the third information output by the Q second neurons, the neuron weights of the Q second neurons, and the bias information of the hidden layer.

[0129] Specifically, since the preset temperature control model can include an input layer, a hidden layer and an output layer, and the input layer includes D first neurons, the hidden layer includes Q second neurons, and the output layer includes L third neurons, the temperature control system can first input each training sample into the input layer, process the training sample using the D first neurons in the input layer respectively to obtain first information output by the D first neurons respectively. Then, second information determined based on the first information output by the D first neurons respectively, neuron weights of the D first neurons and bias information of the input layer is input into the hidden layer, the Q second neurons in the hidden layer are used to process the second information respectively to obtain third information output by the Q second neurons respectively, and further, fourth information determined based on the third information output by the Q second neurons respectively, neuron weights of the Q second neurons and bias information of the hidden layer is input into the output layer, and the L third neurons are used to process the fourth information respectively to obtain fifth information output by the L third neurons respectively. Finally, based on the fifth information output by the L third neurons respectively, a reference outlet temperature corresponding to the training sample is determined.

[0130] In this embodiment, in the process of transmitting information from the input layer to the hidden layer and from the hidden layer to the output layer, not only the output information of the last layer of neurons is considered, but also the neuron weights and the bias information are combined. Since the neuron weights reflect the importance degree of information transmission between different neurons, and the bias information is used to adjust the activation threshold of the neuron. In this way, the model can fuse and convert the input information, so that the output information of each layer contains more rich and accurate feature information, which facilitates subsequent training of a more accurate temperature control model.

[0131] III. The reference outlet temperature of the target training sample and the sample label of the target training sample are processed based on a loss function to obtain a loss function value of the preset temperature control model.

[0132] In some embodiments, the target training sample described above is any one of the plurality of training samples.

[0133] Specifically, the reference outlet temperature can be obtained based on any training sample in the plurality of training samples, and the loss function value of the preset temperature control model is further accurately determined according to the sample label corresponding to the training sample, which facilitates iterative processing of the preset temperature control model based on the loss function value, and further obtains a more accurate temperature control module.

[0134] V. The preset temperature control model is trained using the plurality of training samples based on the loss function of the preset temperature control model to obtain a trained temperature control model.

[0135] Specifically, in order to obtain a better trained temperature control model, in the case that the loss function value does not satisfy the training stop condition, the model parameters of the preset temperature control model are adjusted, and the temperature control model after the parameter adjustment is continuously trained by using the image sample to be processed until the loss function value satisfies the training stop condition, and the trained temperature control model is obtained. The training stop condition can be that the number of iterations reaches the maximum number of iterations, or the prediction accuracy of the training set reaches a certain threshold, which is not limited here.

[0136] In a complete example, the preset temperature control model in the embodiment of the application can be constructed based on a BP neural network, and the main feature of the BP neural network is that the signal is forward propagated and the error is backward propagated. Specifically, the sample X can be input into the input layer, the hidden layer and the output layer in turn, and then the output value Y output by the output layer is compared with the actual value Z to determine the error therebetween, and the error is backward propagated, and the gradient descent method is used to adjust the network parameters, so that the error gradually decreases until the error therebetween satisfies the preset condition, and the training of the model is stopped.

[0137] Based on this, it should be noted that each layer in the BP neural network can include a plurality of neurons, and each neuron needs to receive the input signals of the neurons of the previous layer, each signal is transmitted through a connection with a weight, the neuron adds up the signals to obtain a total input value, and then compares the total input value with the threshold value of the neuron (simulates the threshold potential), and then processes the final output (simulates the activation of cells) through an activation function. The output will be used as the input of the next neuron layer by layer. The activation function is introduced here to introduce nonlinearity in the model. If there is no activation function (actually the activation function is f(x) = x), no matter how many layers your neural network has, it is ultimately a linear mapping, and the approximation ability of the network is quite limited. A simple linear mapping cannot solve the linearly inseparable problem. Therefore, a nonlinear function is introduced as an activation function, so that the expression ability of the deep neural network is more powerful. Then, the commonly used activation function in the BP neural network is the Sigmoid function, also known as the S-shaped growth curve. When used in a classifier, the effect is better, which can be expressed as .

[0138] In this way, in the process of forward propagation (i.e. the process of allowing information to enter the network from the input layer, and sequentially passing through the calculation of each layer to obtain the final output layer result. In the above network, the numerical value of each layer is directly multiplied by the corresponding weight + bias variable (activation function)), since the BP neural network can include an input layer, a hidden layer and an output layer, the forward propagation between the input layer and the hidden layer can be calculated by the following formula (2);

[0139] (2)

[0140] wherein, denotes the number of first neurons of the input layer. denotes the weight of the i-th neuron of the j-th first neuron, the first information representing the weight output of the i-th neuron of the j-th first neuron. is the bias information of the input layer. The forward propagation from the hidden layer to the output layer can be calculated by the following formula (3):

[0141]

[0142] (3)

[0143] wherein, denotes the number of second neurons of the hidden layer. denotes the weight of the i-th neuron of the j-th second neuron, the third information representing the weight output of the i-th neuron of the j-th second neuron. is the bias information of the hidden layer. Thus, the fifth information output by each third neuron in the output layer can be calculated.

[0144] Because the parameters are random, the first output result of the model will have a very large error from the true result, thus, the parameters need to be adjusted according to the error, so that the parameters can better fit, until the error reaches the minimum value, at this time the back propagation of the model is needed. That is, by calculating the square of the difference between the model output value and the actual value, and based on the square of the difference, the weights are constantly updated according to the gradient descent method, so that the error between the model output value and the actual value gradually decreases. In the process of adjusting the weights, the learning rate can be adjusted, and the appropriate learning rate can make the objective function converge to the local minimum value in the appropriate time. The learning rate is generally set to 0.01-0.8.

[0145] Because the parameters are random, the first output result of the model will have a very large error from the true result, thus, the parameters need to be adjusted according to the error, so that the parameters can better fit, until the error reaches the minimum value, at this time the back propagation of the model is needed. That is, by calculating the square of the difference between the model output value and the actual value, and based on the square of the difference, the weights are constantly updated according to the gradient descent method, so that the error between the model output value and the actual value gradually decreases. In the process of adjusting the weights, the learning rate can be adjusted, and the appropriate learning rate can make the objective function converge to the local minimum value in the appropriate time. The learning rate is generally set to 0.01-0.8.

[0146] ​​​In this embodiment, a training sample set is obtained, and for each training sample in the training sample set, the preset temperature control model is used to process the training sample to obtain a reference outlet temperature corresponding to the training sample. Then, the reference outlet temperature of a target training sample and a sample label of the target training sample can be processed based on a loss function to obtain a loss function value of the model, so as to train the preset temperature control model based on the loss function value of the preset temperature control model by using a plurality of training samples until the loss function value meets a training stop condition, so as to ensure that a more accurate temperature control model can be obtained.

[0147] Based on the same inventive concept, the present application provides a temperature control system, which can be specifically combined with Figure 4 The temperature control system provided by the present application is described in detail.

[0148] As Figure 4 shown, the temperature control system 400 can include:

[0149] The acquisition module 410 is configured to acquire first temperature control data, wherein the first temperature control data includes at least one of environment perception data, user setting data, and user attribute data.

[0150] The processing module 420 is configured to process the first temperature control data by using a temperature control model to obtain a first outlet temperature of the air conditioning system.

[0151] The control module 430 is configured to perform temperature control based on the first outlet temperature.

[0152] In an embodiment of the present application, in the case where the air conditioning system includes a vehicle-mounted air conditioning system, the environment perception data includes vehicle operating state data.

[0153] The user setting data includes at least one of air volume, humidity, air blowing direction mode, and inside-outside circulation ratio of the air conditioning system.

[0154] The user attribute data includes at least one of user age and user gender.

[0155] In an embodiment of the present application, the temperature control system provided by the present application can include:

[0156] The acquisition module is further configured to acquire second temperature control data, wherein the second temperature control data includes at least one of environment temperature, sunlight irradiance, and user setting temperature.

[0157] The processing module is further configured to process the second temperature control data by using a temperature control function to obtain a second outlet temperature of the air conditioning system.

[0158] determining module, configured to determine a target outlet temperature of the air conditioning system based on the first outlet temperature and the second outlet temperature.

[0159] Based on this, the control module is specifically configured to perform temperature control based on the target outlet temperature.

[0160] In an embodiment of the present application, the temperature control function includes a first sub-function and a second sub-function; based on this, the temperature control system provided by the embodiment of the present application can include:

[0161] The processing module is specifically configured to process the second temperature control data by using the first sub-function to obtain an estimated energy demand;

[0162] The matching module is configured to perform matching processing on the estimated energy demand based on a corresponding relationship between the energy demand and the outlet temperature to obtain the second outlet temperature of the air conditioning system, and the second sub-function represents the corresponding relationship between the energy demand and the outlet temperature.

[0163] In an embodiment of the present application, the temperature control system provided by the embodiment of the present application can include:

[0164] The weighted summation module is configured to perform weighted summation processing on the first outlet temperature and the second outlet temperature based on a preset weight to obtain the target outlet temperature of the air conditioning system.

[0165] In an embodiment of the present application, the temperature control system provided by the embodiment of the present application can include:

[0166] The acquisition module is further configured to acquire a training sample set, the training sample set including a plurality of training samples and a sample label corresponding to each training sample;

[0167] The processing module is further configured to, for each training sample, process the training sample by using a preset temperature control model to obtain a reference outlet temperature corresponding to the training sample;

[0168] The processing module is further configured to process the reference outlet temperature of a target training sample and the sample label of the target training sample based on a loss function to obtain a loss function value of the temperature control model, the target training sample being any one of the plurality of training samples.

[0169] The training module is configured to train the preset temperature control model by using the plurality of training samples based on the loss function of the preset temperature control model to obtain a trained temperature control model.

[0170] In one embodiment of the present application, the preset temperature control model comprises an input layer, a hidden layer and an output layer, the input layer comprises D first neurons, the hidden layer comprises Q second neurons, and the output layer comprises L third neurons; based on this, the above processing module is specifically configured to:

[0171] process the training sample by using the D first neurons respectively to obtain first information respectively output by the D first neurons;

[0172] process the second information by using the Q second neurons respectively to obtain third information respectively output by the Q second neurons, the second information being determined based on the first information respectively output by the D first neurons, neuron weights of the D first neurons and bias information of the input layer;

[0173] process the fourth information by using the L third neurons respectively to obtain fifth information respectively output by the L third neurons, the fourth information being determined based on the third information respectively output by the Q second neurons, neuron weights of the Q second neurons and bias information of the hidden layer, D, Q and L being positive integers;

[0174] determine the reference outlet temperature corresponding to the training sample based on the fifth information respectively output by the L third neurons.

[0175] In the temperature control method provided by the present application, the first temperature control data can be obtained by the air conditioning system, and the first temperature control data is processed by using the temperature control model to obtain the first outlet temperature of the air conditioning system, and then the temperature control can be performed based on the first outlet temperature. Since the above-mentioned first temperature control data can include at least one of environmental perception data, user setting data and user attribute data, the outlet temperature of the air conditioning system can be accurately determined, and the control accuracy of the air conditioning system can be improved, and the user comfort experience can also be improved.

[0176] Each module in the off-range detection system provided by the present application can implement the method steps of any one of the embodiments shown in the above-mentioned embodiments, and can achieve the corresponding technical effects, and for the sake of brevity, the description is not repeated here. Figures 1 to 3

[0177] Based on the same inventive concept, the present application also provides an electronic device. Figure 5 The structural block diagram of the electronic device provided by the present application is shown in FIG. 1. Figure 5 ​As shown, the electronic device provided by the embodiment of the present application includes one or more processors 501, a memory 502, and one or more I / O interfaces 503. The memory 502 stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the temperature control method in any of the above embodiments. The one or more I / O interfaces 503 are connected between the processor and the memory and are configured to implement information interaction between the processor and the memory.

[0178] The processor 501 is a device with data processing capability, including but not limited to a central processing unit (CPU) and the like. The memory 502 is a device with data storage capability, including but not limited to a random access memory (RAM, more specifically, SDRAM, DDR, etc.), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), and a flash memory (FLASH). The I / O interface (read-write interface) 503 is connected between the processor 501 and the memory 502 and can implement information interaction between the processor 501 and the memory 502, including but not limited to a data bus (Bus) and the like.

[0179] In some embodiments, the processor 501, the memory 502, and the I / O interface 503 are connected to each other and to other components of the computing device through a bus 504.

[0180] In some embodiments, the one or more processors 501 include a field programmable gate array.

[0181] The embodiment of the present application also provides a computer readable medium. The computer readable medium stores a computer program, and when the program is executed by a processor, the steps in the temperature control method in any of the above embodiments are implemented. The computer readable storage medium can be a volatile or non-volatile computer readable storage medium.

[0182] The embodiment of the present application also provides a computer program product including computer readable code or a non-volatile computer readable storage medium carrying computer readable code, and when the computer readable code is run in a processor of an electronic device, the processor in the electronic device executes the above temperature control method.

[0183] Those of ordinary skill in the art will realize and understand that all or some of the steps in the methods disclosed above and the functional modules / units in the systems and devices can be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementation, the division between the functional modules / units referred to in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be performed by several physical components in cooperation. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software can be distributed on computer readable storage media, which can include computer storage media (or non-transitory media) and communication media (or transitory media).

[0184] As is well known to those of ordinary skill in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable program instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disc read only memory (CD-ROM), digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer. Further, it is well known to those of ordinary skill in the art that communication media typically embodies computer readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. As a result, the foregoing description of computer storage media, along with communication media, applies to and fully integrates software and / or programs such as program modules, program data, and / or computer readable program instructions.

[0185] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0186] Computer readable program instructions for carrying out operations of the present application can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can 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 the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present application.

[0187] The computer program product described herein can be embodied in a specific manner by hardware, software, or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), and the like.

[0188] The computer program product described herein can be embodied in a specific manner by hardware, software, or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), and the like.

[0189] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can be a computer- readable storage medium having no data storage cycles that change state. The instructions can be executed by one or more processors of a computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process such that the instructions which execute via the one or more processors of the computer or other programmable data processing devices create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0190] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0191] The flow and block diagrams in the drawings show the architectural, functional, and operational views of possible implementations of systems, methods, and computer program products according to the present application. In this regard, each block in the flow and block diagrams can represent a module, a segment, or a portion of instructions which contain one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0192] Example embodiments have been disclosed and, although specific terms are employed, they are used in a generic and descriptive sense only and not for purposes of limitation. In some instances, it will be apparent to those skilled in the art that features, characteristics or elements described with reference to one embodiment can be used in combination with features, characteristics or elements described with reference to other embodiments unless otherwise explicitly stated. Accordingly, it will be understood that various changes in form and details can be made without departing from the scope of the present application as set forth in the appended claims.

Claims

1. A temperature control method, characterized in that: include: Acquire first temperature control data, where the first temperature control data includes at least one of environment perception data, user setting data, and user attribute data; Processing the first temperature control data using a temperature control model to obtain a first air outlet temperature of the air conditioning system; Temperature control is performed based on the first air outlet temperature.

2. The method according to claim 1, characterized in that The environmental perception data includes vehicle operating status data; and / or, the user setting data includes at least one of the air volume, humidity, blowing direction mode, and internal and external circulation ratio of the air conditioning system; And / or, the user attribute data includes at least one of user age and user gender.

3. The method according to claim 1, characterized in that Before performing temperature control based on the first air outlet temperature, the method further includes: Acquiring second temperature control data, where the second temperature control data includes at least one of an ambient temperature, sunlight irradiance, and a user-set temperature; Processing the second temperature control data using a temperature control function to obtain a second air outlet temperature of the air conditioning system; determining a target air outlet temperature of the air conditioning system based on the first air outlet temperature and the second air outlet temperature; The performing temperature control based on the first air outlet temperature includes: Temperature control is performed based on the target air outlet temperature.

4. The method according to claim 3, characterized in that The temperature control function includes a first sub-function and a second sub-function; The processing of the second temperature control data by using a temperature control function to obtain a second air outlet temperature of the air-conditioning system includes: Processing the second temperature control data using the first sub-function to obtain an estimated energy demand; The estimated energy demand is processed based on the second sub-function to obtain a second air outlet temperature of the air-conditioning system.

5. The method according to claim 3, characterized in that The determining the target air outlet temperature of the air conditioning system based on the first air outlet temperature and the second air outlet temperature includes: A weighted summation process is performed on the first air outlet temperature and the second air outlet temperature based on a preset weight to obtain a target air outlet temperature of the air conditioning system.

6. The method according to claim 1, characterized in that Before processing the first temperature control data using a temperature control model to obtain a first air outlet temperature of the air-conditioning system, the method further includes: Obtaining a training sample set, the training sample set including a plurality of training samples and a sample label corresponding to each of the training samples; For each of the training samples, the training sample is processed using a preset temperature control model to obtain a reference air outlet temperature corresponding to the training sample; Processing a reference outlet temperature of a target training sample and a sample label of the target training sample based on a loss function to obtain a loss function value of the temperature control model, wherein the target training sample is any one of the multiple training samples; Based on the loss function of the preset temperature control model, the preset temperature control model is trained using the multiple training samples to obtain a trained temperature control model.

7. The method according to claim 6, characterized in that The preset temperature control model includes an input layer, a hidden layer and an output layer, the input layer includes D first neurons, the hidden layer includes Q second neurons, and the output layer includes L third neurons; The training sample is processed using a preset temperature control model to obtain a reference air outlet temperature corresponding to the training sample, including: Using D first neurons to process the training samples respectively to obtain first information output by the D first neurons respectively; Processing the second information using the Q second neurons respectively to obtain third information output by the Q second neurons respectively, where the second information is determined based on the first information output by the D first neurons respectively, neuron weights of the D first neurons, and bias information of the input layer; Using the L third neurons to process the fourth information respectively, to obtain fifth information output by the L third neurons respectively, wherein the fourth information is determined based on the third information output by the Q second neurons respectively, the neuron weights of the Q second neurons, and the bias information of the hidden layer, where D, Q, and L are all positive integers; Based on the fifth information respectively output by the L third neurons, a reference air outlet temperature corresponding to the training sample is determined.

8. A temperature control system, characterized in that: include: an acquisition module, configured to acquire first temperature control data, wherein the first temperature control data includes at least one of environment perception data, user setting data, and user attribute data; a processing module, configured to process the first temperature control data using a temperature control model to obtain a first air outlet temperature of the air-conditioning system; A control module is used to perform temperature control based on the first air outlet temperature.

9. The system according to claim 8, characterized in that The acquisition module is further configured to acquire second temperature control data, the second temperature control data comprising at least one of ambient temperature, sunlight irradiance, and a user-set temperature; The processing module is further configured to process the second temperature control data using a temperature control function to obtain a second air outlet temperature of the air conditioning system; The system further includes: a determination module configured to determine a target air outlet temperature of the air conditioning system based on the first air outlet temperature and the second air outlet temperature; The control module is specifically configured to perform temperature control based on the target air outlet temperature.

10. The system according to claim 8, wherein: The acquisition module is further configured to acquire a training sample set, wherein the training sample set includes a plurality of training samples and a sample label corresponding to each training sample; The processing module is further configured to process each of the training samples using a preset temperature control model to obtain a reference air outlet temperature corresponding to the training sample, and to process the reference air outlet temperature of a target training sample and a sample label of the target training sample based on a loss function to obtain a loss function value of the temperature control model, where the target training sample is any one of the multiple training samples; The system further includes: a training module, which is used to train the preset temperature control model based on the loss function of the preset temperature control model using the multiple training samples to obtain a trained temperature control model.

11. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

12. A computer-readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images