Control method and device for vehicle air conditioner

Abstract

This application relates to the field of new energy vehicle technology, and in particular to a control method and device for vehicle air conditioning. The method includes: collecting the current location, alarm information, and actual step count of a user's mobile terminal; inputting the current location, alarm information, and actual step count into a pre-trained single-layer Long Short-Term Memory (LSTM) network model; outputting the user's likely driving time; determining the optimal start time for the vehicle air conditioning based on the user's likely driving time; and turning on the vehicle air conditioning when the optimal start time is reached at the current moment. This application's embodiment can process user information based on the model to obtain the estimated travel time of the user, and match the optimal time period for turning on the air conditioning based on the estimation result, making the air conditioning start time more accurate. This ensures that the vehicle air conditioning automatically starts on a timed basis in accordance with the user's actual driving situation, reduces vehicle energy consumption, improves the user experience, and is more intelligent and practical.

Description

Technical Field

[0001] This application relates to the field of new energy vehicle technology, and in particular to a control method and device for vehicle air conditioning. Background Technology

[0002] With the continuous development of new energy vehicles, users' demand for intelligent vehicle control is also increasing. In summer and winter, when there is a large temperature difference between indoors and outdoors, prolonged parking of a car outdoors can cause the interior temperature to become too hot or too cold, affecting the user's riding experience.

[0003] In related technologies, such as patent CN111619310A, the air conditioning of a new energy electric vehicle can be turned on in advance via remote control, so that when the user arrives at the car, the interior temperature is roughly at the target set temperature.

[0004] However, the relevant technologies do not take into account the user's actual driving situation when obtaining the advance start time of the vehicle's air conditioning, resulting in a mismatch between the air conditioning start time and the user's driving time. This reduces the accuracy of the air conditioning start time estimation, increases the risk of vehicle energy consumption, affects the user experience, and lacks practicality and intelligence, which urgently needs to be addressed. Summary of the Invention

[0005] This application provides a control method and device for vehicle air conditioning to solve the problems in related technologies, such as the failure to consider the user's actual driving situation when obtaining the advance start time of the vehicle air conditioning, resulting in a mismatch between the air conditioning start time and the user's driving time, reducing the accuracy of the air conditioning start time estimation, increasing the risk of vehicle energy consumption, affecting the user experience, and lacking practicality and intelligence.

[0006] The first aspect of this application provides a method for controlling a vehicle air conditioner, comprising the following steps: collecting the current location, alarm information, and actual step count of a user's mobile terminal; inputting the current location, alarm information, and actual step count into a pre-trained single-layer long short-term memory (LSTM) network model to output the user's possible driving time, wherein the LSTM model is trained based on the relationship between the start time and the alarm time, step count, and region; determining the optimal start time of the vehicle air conditioner based on the user's possible driving time, and turning on the vehicle air conditioner when the optimal start time is reached at the current moment.

[0007] Based on the above technical means, the embodiments of this application can process user information based on the model to obtain the estimated time of the user's ride, and match the best time to turn on the air conditioner according to the estimation result, so that the start time of the air conditioner is more accurate, thereby ensuring that the automatic start of the vehicle air conditioner on a timed basis conforms to the user's actual driving situation, reducing vehicle energy consumption, improving the user experience, and making it more intelligent and practical.

[0008] Optionally, in one embodiment of this application, the LSTM model includes an input layer that takes the alarm time, the number of steps, and the region as input, a Linear fully connected layer structure, an LSTM long short-term memory network structure, a Linear fully connected layer structure, and a dropout layer.

[0009] Based on the above technical means, the LSTM model in this embodiment includes an input layer for input alarm time, steps, and region, a Linear fully connected layer structure, an LSTM long short-term memory network structure, a Linear fully connected layer structure, and a dropout layer. By implementing the LSTM model in a single-tower form, the model training process and the model prediction process are further guaranteed, and the intelligence of data processing is improved.

[0010] Optionally, in one embodiment of this application, determining the start-up time of the vehicle air conditioner based on the user's likely driving time includes: acquiring the actual outside temperature and the actual inside temperature of the vehicle; and estimating the start-up time based on the actual outside temperature and the actual inside temperature, combined with the user's likely driving time and a preset power-temperature curve of the air conditioner.

[0011] Based on the above technical means, the embodiments of this application can obtain the actual outside temperature and the actual inside temperature of the vehicle; based on the actual outside temperature and the actual inside temperature, combined with the user's possible driving time and the preset power-temperature curve of the air conditioner, the start time is estimated, and the air conditioner start time is calculated according to the actual environmental conditions to ensure that the inside temperature is at a suitable level, thereby further improving the user experience and making the vehicle more interactive.

[0012] Optionally, in one embodiment of this application, before estimating the start-up time, the method further includes: obtaining the vehicle's usage information; updating the power-temperature curve of the initial air conditioner based on the usage information to obtain the power-temperature curve of the preset air conditioner.

[0013] Based on the above technical means, the embodiments of this application can obtain vehicle usage information and update the initial air conditioner power-temperature curve according to the usage information to obtain the preset air conditioner power-temperature curve, thereby further improving the vehicle data processing process and ensuring the accuracy of the air conditioner start-up time calculation results.

[0014] Optionally, in one embodiment of this application, before inputting the current location, alarm clock information, and actual step count into the pre-trained single-layer long short-term memory network (LSTM) model, the method further includes: collecting the user's alarm clock time, step count statistics, GPS information, and home arrival time; preprocessing the alarm clock time, step count statistics, GPS information, and home arrival time to generate a training set; and using the training set to train the LSTM model to obtain the pre-trained single-layer LSTM model.

[0015] Based on the above technical means, the embodiments of this application can preprocess the collected alarm clock time, step count statistics, GPS information and home arrival time of users to generate a training set, use the training set to train an LSTM model, obtain a pre-trained single-layer LSTM model, and further improve the data processing process for estimating time calculation by building a model based on user data, thereby improving the intelligence level of the model.

[0016] A second aspect of this application provides a control device for a vehicle air conditioner, comprising: a data acquisition module for acquiring the current location, alarm information, and actual step count of a user's mobile terminal; an input module for inputting the current location, alarm information, and actual step count into a pre-trained single-layer long short-term memory (LSTM) network model to output the user's possible driving time, wherein the LSTM model is trained based on the relationship between the start time and the alarm time, step count, and region; and a control module for determining the optimal start time of the vehicle air conditioner based on the user's possible driving time, and turning on the vehicle air conditioner when the optimal start time is reached at the current moment.

[0017] Optionally, in one embodiment of this application, the LSTM model includes an input layer that takes the alarm time, the number of steps, and the region as input, a Linear fully connected layer structure, an LSTM long short-term memory network structure, a Linear fully connected layer structure, and a dropout layer.

[0018] Optionally, in one embodiment of this application, the control module includes: a first acquisition unit, configured to acquire the actual outside temperature and the actual inside temperature of the vehicle; and an estimation unit, configured to estimate the start-up time based on the actual outside temperature and the actual inside temperature, combined with the user's likely driving time and a preset power-temperature curve of the air conditioner.

[0019] Optionally, in one embodiment of this application, the control module further includes: a second acquisition unit, configured to acquire vehicle usage information before estimating the start-up time; and an update unit, configured to update the power-temperature curve of the initial air conditioner according to the usage information to obtain the power-temperature curve of the preset air conditioner.

[0020] Optionally, in one embodiment of this application, the input module includes: a collection unit, used to collect the user's alarm time, step count statistics, GPS information, and home arrival time before inputting the current location, alarm clock information, and actual step count into the pre-trained single-layer long short-term memory network (LSTM) model; a generation unit, used to preprocess the alarm time, step count statistics, GPS information, and home arrival time to generate a training set; and a training unit, used to train the LSTM model using the training set to obtain the pre-trained single-layer LSTM model.

[0021] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle air conditioning control method as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vehicle air conditioning control method.

[0023] The beneficial effects of this application are:

[0024] (1) The embodiments of this application can process user information based on the model to obtain the estimated time of the user's ride, and match the best time to turn on the air conditioner according to the estimation result, so that the start time of the air conditioner is more accurate, thereby ensuring that the automatic start of the vehicle air conditioner is in line with the user's actual driving situation, reducing vehicle energy consumption, improving user experience, and making it more intelligent and practical.

[0025] (2) The embodiments of this application can preprocess the alarm clock time, step count statistics, GPS information and home arrival time of the collected users to generate a training set, use the training set to train the LSTM model, and obtain a pre-trained single-layer LSTM model. By constructing the model based on user data, the data processing process for estimating time calculation can be further improved, thereby enhancing the intelligence level of the model.

[0026] (3) The embodiments of this application can obtain the actual outside temperature and the actual inside temperature of the vehicle; based on the actual outside temperature and the actual inside temperature, combined with the user's possible driving time and the preset power temperature curve of the air conditioner, the start time is estimated, and the air conditioner start time is calculated according to the actual environmental conditions to ensure that the inside temperature is at a suitable level, thereby further improving the user experience and making the vehicle more interactive.

[0027] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0028] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0029] Figure 1 This is a flowchart of a vehicle air conditioning control method according to an embodiment of this application;

[0030] Figure 2 This is a schematic diagram illustrating the usage process of vehicle air conditioning control according to an embodiment of this application;

[0031] Figure 3 This is a schematic diagram of the computation layer of a single-layer LSTM algorithm according to an embodiment of this application;

[0032] Figure 4 This is a schematic diagram of the data collection and algorithm flow according to one embodiment of this application;

[0033] Figure 5 A schematic diagram of the structure of the vehicle air conditioning control device according to an embodiment of this application;

[0034] Figure 6 This is a structural schematic diagram of a vehicle according to an embodiment of this application.

[0035] Among them, 10-the control device for vehicle air conditioning; 100-the acquisition module, 200-the input module and 300-the control module; 601-the memory, 602-the processor and 603-the communication interface. Detailed Implementation

[0036] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0037] The following describes a control method and apparatus for a vehicle air conditioner according to embodiments of this application, with reference to the accompanying drawings. Addressing the issues mentioned in the background art, where the actual user's driving situation is not considered when obtaining the advance start time of the vehicle air conditioner, leading to a mismatch between the air conditioner start time and the user's driving time, reducing the accuracy of the air conditioner start time estimation, increasing the risk of vehicle energy consumption, affecting the user experience, and resulting in insufficient practicality and intelligence, this application provides a control method for a vehicle air conditioner. This method collects the user's current location, alarm information, and actual step count from their mobile terminal, inputs these data into a pre-trained single-layer Long Short-Term Memory (LSTM) network model, outputs the user's likely driving time, and determines the optimal start time of the vehicle air conditioner based on this time. When the optimal start time is reached at the current moment, the vehicle air conditioner is turned on, making the start time more accurate. This ensures that the vehicle air conditioner automatically starts on time according to the user's actual driving situation, reduces vehicle energy consumption, improves the user experience, and is more intelligent and practical. This solves the problems in related technologies where the actual user's driving situation is not considered when obtaining the advance start time of the vehicle's air conditioning, resulting in a mismatch between the air conditioning start time and the user's driving time, which reduces the accuracy of the air conditioning start time estimation, increases the risk of vehicle energy consumption, affects the user experience, and results in insufficient practicality and intelligence.

[0038] Specifically, Figure 1 This is a flowchart illustrating a method for controlling a vehicle air conditioner according to an embodiment of this application.

[0039] like Figure 1 As shown, the control method for the vehicle air conditioner includes the following steps:

[0040] In step S101, the user's current location, alarm information, and actual number of steps are collected from the mobile terminal.

[0041] It is understood that the current location of the mobile terminal in this embodiment can be realized through the GPS function of the mobile terminal, the alarm clock information can be the actual usage of the alarm clock function in the user's mobile terminal device, and the actual number of steps can be counted by the step counting sensor of the mobile terminal device.

[0042] For example, when the user's mobile terminal device is an Android phone, the user's current location can be obtained by acquiring the Android phone's GPS information. Sensor events can be monitored by inheriting from `android.hardware.SensorEventListener`, listening to the Android phone's sensor information, obtaining sensor services from the `android.hardware.SensorManager`, and obtaining real-time step count sensor data. The system alarm clock can be accessed by inheriting from `android.provider.AlarmClock`, reading the system alarm settings, sorting the alarms between 7 and 9 AM, and taking the last alarm as the final alarm time.

[0043] This application embodiment can collect the user's current location, alarm clock information, and actual step count from the user's mobile terminal. By reading relevant data from the user's mobile terminal, it can further enrich the information collection on the user's travel habits and improve the comprehensiveness of the required data foundation.

[0044] In step S102, the current location, alarm information, and actual number of steps are input into a pre-trained single-layer long short-term memory network (LSTM) model, which outputs the user's possible driving time. The LSTM model is trained based on the relationship between the start time, alarm time, number of steps, and region.

[0045] It is understood that in this application embodiment, the user's driving time may be the estimated time when the user starts using the car. The vehicle system can receive the current location, alarm information and actual steps sent by the mobile terminal, as well as the pre-trained LSTM model, and activate the model according to the actual instruction to obtain the estimated value of the user's driving time.

[0046] For example, pre-trained model files and the latest alarm time, step count, and region can be sent to the vehicle's infotainment system via the TSP (Telematics Service Provider) platform. The vehicle's infotainment system receives the command from the user's mobile terminal to activate the smart air conditioning function and receives the latest alarm time, step count, and region information to predict the possible time when the customer will start the vehicle.

[0047] In this embodiment, the current location, alarm information, and actual step count can be input into a pre-trained single-layer long short-term memory network (LSTM) model to output the user's possible driving time. Based on the user data information obtained in the above steps, the user's vehicle start time can be estimated to further determine the pre-start time of the vehicle's air conditioning.

[0048] Optionally, in one embodiment of this application, before inputting the current location, alarm clock information, and actual step count into the pre-trained single-layer long short-term memory network (LSTM) model, the method further includes: collecting the user's alarm clock time, step count statistics, GPS information, and home arrival time; preprocessing the alarm clock time, step count statistics, GPS information, and home arrival time to generate a training set; and using the training set to train the LSTM model to obtain the pre-trained single-layer LSTM model.

[0049] It is understood that, in this embodiment, the time to return home can be the time difference between when the car is parked and when the user arrives home. It should be noted that the above explanation of the process for collecting the user's current location, alarm clock information, and actual step count also applies to the process of obtaining the user's alarm clock time, step count statistics, GPS information, and time to return home in this embodiment, and will not be repeated here.

[0050] Specifically, the time it takes for a user to return home can be calculated by acquiring data from the phone's step counter sensor. The time of arrival home is determined by whether the phone has been connected to Wi-Fi for three minutes or whether the step counter sensor data shows no significant change within ten minutes.

[0051] In some embodiments, when the user's mobile terminal device is an Android phone, the Android `android.database.sqlite.SQLiteOpenHelper` lightweight database helper class can be inherited to implement a custom micro-database. The `onCreate(SQLiteDatabase db)` method is redefined to create the database tables. Using the `insert` method of the `SQLiteDatabase` lightweight database, the collected user's alarm time, step count statistics, GPS information, and return time are temporarily stored in the lightweight database space of the mobile device. When the information storage in the `SQLiteDatabase` lightweight database meets the usage conditions, such as every morning, an interface is established with the model computing platform via the `java.net.HttpURLConnection` network communication protocol to send the information related to the lightweight database space to the model computing platform. After successful transmission, the database data is cleared.

[0052] Secondly, a multi-layer LSTM model is constructed using the model computing platform to establish the relationship between startup time, alarm time, step count, and region. The region is represented by hexagonal region codes derived from mobile phone GPS and vehicle GPS. The collected data is divided into a test set and a training set. The training set is used to train the model, while the test set is used to verify the model's accuracy.

[0053] Then, data normalization is performed on the training set, removing the units from the alarm time and step count, i.e.:

[0054] x = (x - Min) / (Max - Min),

[0055] Where x represents the current data processing object, Max represents the maximum value of a column of data, and Min represents the minimum value of a column of data. Planning operations are performed for each column of data. The mean square error (MSE) loss function can be used as the model's loss function, which includes the startup time and the model prediction startup time. Model training is performed on the training set. When the loss function converges smoothly and the loss value reaches the expected level, the training is considered complete, and the required pre-trained single-layer LSTM model is finally obtained. The model result file is then saved.

[0056] For example, such as Figure 2 The diagram shown is a schematic of the usage process of vehicle air conditioning control according to an embodiment of this application. Taking the user's first use of the vehicle air conditioning control function as an example, the model platform can calculate the model by collecting data from existing customers, and then send the single-layer LSTM model and the normalized model to the vehicle. The vehicle section receives the user's actual data information to realize the model operation and output the optimal air conditioning start time.

[0057] This application embodiment can preprocess the collected alarm clock time, step count statistics, GPS information and return time of users to generate a training set, use the training set to train an LSTM model to obtain a pre-trained single-layer LSTM model, and further improve the data processing process for estimating time calculation by building the model based on user data, thereby enhancing the intelligence level of the model.

[0058] Optionally, in one embodiment of this application, the LSTM model includes an input layer for input alarm time, steps, and region, a Linear fully connected layer structure, an LSTM long short-term memory network structure, a Linear fully connected layer structure, and a dropout layer.

[0059] In actual implementation, such as Figure 3 As shown, the LSTM model can be in the form of a single tower. The first layer is the input layer, which takes the alarm time, number of steps, and region as input. The second layer is a Linear fully connected layer structure. The third layer is an LSTM long short-term memory network structure, which is used to obtain the relationship between the input data. The fourth layer is a Linear fully connected layer structure. The fifth layer is a dropout layer, which is used to reduce model overfitting. The final layer is the output layer, which gives the output data information.

[0060] In this embodiment, the LSTM model includes an input layer for input alarm time, steps, and region, a Linear fully connected layer structure, an LSTM long short-term memory network structure, a Linear fully connected layer structure, and a dropout layer. By implementing the LSTM model in a single-tower form, the model training and prediction processes are further guaranteed, and the intelligence of data processing is improved.

[0061] In step S103, the optimal start time for the vehicle air conditioner is determined based on the user's likely driving time, and the vehicle air conditioner is turned on when the optimal start time is reached at the current moment.

[0062] It is understood that the optimal start-up time of the vehicle air conditioner in this application embodiment can be the moment when the air conditioner is turned on so that the interior space of the vehicle reaches a suitable temperature when the user uses the vehicle, so that the vehicle air conditioner can achieve temperature regulation of the interior space with the shortest possible working time.

[0063] In some embodiments, such as Figure 4 The diagram shown is a schematic of the data collection and algorithm flow of one embodiment of this application. Data can be collected through a mobile phone, which sends and stores the collected data information. After receiving the information, the model calculation platform performs calculations to obtain output data, and then loads the vehicle system and starts the air conditioning based on the model output data.

[0064] The embodiments of this application can determine the optimal start time of the vehicle air conditioner based on the user's possible driving time, and turn on the vehicle air conditioner when the optimal start time is reached at the current moment, thereby realizing remote and precise control of the vehicle air conditioner, thus avoiding unnecessary energy consumption of the vehicle, and improving the vehicle's interactivity and intelligence.

[0065] Optionally, in one embodiment of this application, determining the start-up time of the vehicle air conditioner based on the user's likely driving time includes: acquiring the actual outside temperature and the actual inside temperature of the vehicle; and estimating the start-up time based on the actual outside temperature and the actual inside temperature, combined with the user's likely driving time and a preset power-temperature curve of the air conditioner.

[0066] It is understood that in the embodiments of this application, the actual outside temperature and the actual inside temperature of the vehicle can be collected by the vehicle's actual temperature sensor. By combining the collected outside temperature and inside temperature with the user's possible driving time output by the model and comparing it with the preset power-temperature curve of the air conditioner, the final air conditioner start time is estimated, thereby determining the optimal start time of the vehicle air conditioner and giving the optimal start time to turn on the vehicle's air conditioner.

[0067] It should be noted that the preset power-temperature curve of the air conditioner is set by those skilled in the art based on actual conditions, and no specific limitations are made here.

[0068] In actual implementation, when obtaining the air conditioner start time based on the preset air conditioner power-temperature curve and the user's possible driving time, the specific calculation process is as follows: Air conditioner start time = predicted customer's possible driving time - air conditioner power-temperature curve time.

[0069] This application embodiment can obtain the actual outside temperature and the actual inside temperature of the vehicle; based on the actual outside temperature and the actual inside temperature, combined with the user's possible driving time and the preset power-temperature curve of the air conditioner, the start time is estimated. By calculating the air conditioner turn-on time according to the actual environmental conditions, the inside temperature is kept at a suitable level, thereby further improving the user experience and making the vehicle more interactive.

[0070] Optionally, in one embodiment of this application, before estimating the start-up time, the method further includes: obtaining vehicle usage information; updating the power-temperature curve of the initial air conditioner based on the usage information to obtain a preset power-temperature curve of the air conditioner.

[0071] It is understood that the vehicle usage information in this application embodiment may be the actual usage of in-vehicle equipment, such as the energy consumption of the vehicle battery and the operation of the vehicle air conditioner. Based on the obtained actual usage information of the vehicle, the power and temperature curve of the air conditioner at the current moment is recalculated on the basis of the initial power and temperature curve of the air conditioner.

[0072] This application embodiment can obtain vehicle usage information and update the initial air conditioner power-temperature curve based on the usage information to obtain a preset air conditioner power-temperature curve, thereby further improving the vehicle data processing process and ensuring the accuracy of the air conditioner start-up time calculation results.

[0073] The vehicle air conditioning control method proposed in this application can collect the user's current location, alarm information, and actual step count from their mobile terminal. This data is then input into a pre-trained single-layer Long Short-Term Memory (LSTM) network model, which outputs the user's likely driving time. Based on this time, the optimal start time for the vehicle air conditioning is determined, and the air conditioning is activated when the optimal start time is reached. This ensures more accurate start-up timing, guaranteeing that the automatic, timed start-up of the vehicle air conditioning aligns with the user's actual driving conditions. This reduces vehicle energy consumption, improves user experience, and enhances intelligence and practicality. Therefore, this method solves the problems in related technologies where the estimated start-up time for the vehicle air conditioning is not considered in relation to the user's actual driving conditions, leading to a mismatch between the air conditioning start-up time and the user's driving time. This reduces the accuracy of the estimated start-up time, increases the risk of energy consumption, negatively impacts user experience, and results in insufficient practicality and intelligence.

[0074] Next, the control device for a vehicle air conditioner according to an embodiment of this application is described with reference to the accompanying drawings.

[0075] Figure 5 This is a schematic diagram of the structure of the vehicle air conditioning control device according to an embodiment of this application.

[0076] like Figure 5 As shown, the control device 10 of the vehicle air conditioner includes: a data acquisition module 100, an input module 200, and a control module 300.

[0077] The data collection module 100 is used to collect the user's current location, alarm clock information, and actual number of steps on the mobile terminal.

[0078] The input module 200 is used to input the current location, alarm information and actual number of steps into a pre-trained single-layer long short-term memory network (LSTM) model, and output the user's possible driving time. The LSTM model is trained by the relationship between the start time and the alarm time, number of steps and region.

[0079] The control module 300 is used to determine the optimal start time of the vehicle air conditioner based on the user's possible driving time, and to turn on the vehicle air conditioner when the optimal start time is reached at the current moment.

[0080] Optionally, in one embodiment of this application, the LSTM model includes an input layer for input alarm time, steps, and region, a Linear fully connected layer structure, an LSTM long short-term memory network structure, a Linear fully connected layer structure, and a dropout layer.

[0081] Optionally, in one embodiment of this application, the control module 300 includes: a first acquisition unit and an estimation unit.

[0082] The first acquisition unit is used to acquire the actual outside temperature and the actual inside temperature of the vehicle.

[0083] The estimation unit is used to estimate the start-up time based on the actual outside temperature and the actual inside temperature of the vehicle, combined with the user's likely driving time and the preset power-temperature curve of the air conditioner.

[0084] Optionally, in one embodiment of this application, the control module 300 further includes a second acquisition unit and an update unit.

[0085] The second acquisition unit is used to acquire vehicle usage information before estimating the start-up time.

[0086] The update unit is used to update the power-temperature curve of the initial air conditioner based on the usage information to obtain the preset power-temperature curve of the air conditioner.

[0087] Optionally, in one embodiment of this application, the input module 200 includes: a data acquisition unit, a generation unit, and a training unit.

[0088] The data acquisition unit is used to collect the user's alarm time, step count statistics, GPS information, and return time before inputting the current location, alarm information, and actual step count into the pre-trained single-layer long short-term memory network (LSTM) model.

[0089] The generation unit is used to preprocess alarm clock time, step count statistics, GPS information, and return time to generate a training set.

[0090] The training unit is used to train the LSTM model using the training set to obtain a pre-trained single-layer LSTM model.

[0091] It should be noted that the foregoing explanation of the control method embodiment for vehicle air conditioning also applies to the control device of the vehicle air conditioning in this embodiment, and will not be repeated here.

[0092] The vehicle air conditioning control device proposed in this application can collect the user's current location, alarm information, and actual step count from their mobile terminal. This data is then input into a pre-trained single-layer Long Short-Term Memory (LSTM) network model, which outputs the user's likely driving time. Based on this time, the optimal start time for the vehicle air conditioning is determined, and the air conditioning is activated when the optimal start time is reached. This ensures more accurate start-up time, guaranteeing that the automatic, timed start-up of the air conditioning matches the user's actual driving situation, reducing vehicle energy consumption, improving user experience, and making the device more intelligent and practical. This solves the problems in related technologies where the estimated start-up time for the vehicle air conditioning is not considered in relation to the user's actual driving situation, leading to a mismatch between the air conditioning start-up time and the user's driving time, reduced accuracy of start-up time estimation, increased vehicle energy consumption risk, negatively impacting user experience, and insufficient practicality and intelligence.

[0093] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0094] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0095] When the processor 602 executes the program, it implements the vehicle air conditioning control method provided in the above embodiments.

[0096] Furthermore, the vehicle also includes:

[0097] Communication interface 603 is used for communication between memory 601 and processor 602.

[0098] The memory 601 is used to store computer programs that can run on the processor 602.

[0099] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0100] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0101] Alternatively, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0102] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0103] This embodiment also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described vehicle air conditioning control method.

[0104] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0105] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0106] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing 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 (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0108] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0109] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0110] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0111] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for controlling a vehicle air conditioner, characterized in that, Includes the following steps: Collect the user's current location, alarm information, and actual number of steps on their mobile device; The current location, alarm information, and actual number of steps are input into a pre-trained single-layer long short-term memory network (LSTM) model to output the user's possible driving time. The optimal start time for the vehicle's air conditioning is determined based on the user's likely driving time, and the vehicle's air conditioning is turned on when the optimal start time is reached at the current moment. Before inputting the current location, alarm information, and actual step count into the pre-trained single-layer Long Short-Term Memory (LSTM) network model, the following steps are also included: The system collects the user's alarm clock time, step count statistics, GPS information, and home arrival time. The home arrival time is obtained by acquiring data from the mobile phone's step count sensor and calculating the time difference between when the car stops and when the user arrives home. The alarm clock time is obtained by reading the system's alarm clock settings, sorting the alarm information between 7 and 9 o'clock, and taking the last alarm information. The alarm clock time, step count statistics, GPS information, and return time are preprocessed to generate a training set; The LSTM model is trained using the training set to obtain the pre-trained single-layer LSTM model; Determining the optimal start-up time for the vehicle's air conditioning based on the user's likely driving time includes: Obtain the actual outside temperature and actual inside temperature of the vehicle. Based on the actual outside temperature and the actual inside temperature of the vehicle, combined with the user's likely driving time and the preset power-temperature curve of the air conditioner, the start-up time of the vehicle air conditioner is estimated, thereby determining the optimal start-up time of the vehicle air conditioner.

2. The method according to claim 1, characterized in that, The system receives the latest alarm time, step count, and region information to predict the user's likely driving time. The region is a hexagonal region code defined by the mobile phone GPS and vehicle GPS. The LSTM model includes an input layer that takes the alarm time, step count, and region as inputs, a Linear fully connected layer structure, an LSTM long short-term memory network structure, a Linear fully connected layer structure, and a dropout layer.

3. The method according to claim 1, characterized in that, Before estimating the start-up time of the vehicle's air conditioning system, the following is also included: Obtain the vehicle's usage information; The power-temperature curve of the initial air conditioner is updated based on the usage information to obtain the power-temperature curve of the preset air conditioner.

4. A control device for a vehicle air conditioner, characterized in that, A method for controlling an in-vehicle air conditioner as described in any one of claims 1-3, comprising: The data collection module is used to collect the user's current location, alarm information, and actual number of steps on the mobile terminal. The input module is used to input the current location, alarm information and actual number of steps into a pre-trained single-layer long short-term memory network (LSTM) model, and output the user's possible driving time. The control module is used to determine the optimal start time of the vehicle air conditioner based on the user's possible driving time, and to turn on the vehicle air conditioner when the optimal start time is reached at the current moment. The control module includes: The first acquisition unit is used to acquire the actual outside temperature and the actual inside temperature of the vehicle. The estimation unit is used to estimate the start-up time of the vehicle air conditioner based on the actual outside temperature and the actual inside temperature, combined with the user's likely driving time and the preset power-temperature curve of the air conditioner, thereby determining the optimal start-up time of the vehicle air conditioner.

5. The apparatus according to claim 4, characterized in that, The control module also includes: The second acquisition unit is used to acquire the vehicle's usage information before estimating the start-up time of the vehicle's air conditioning. The update unit is used to update the power-temperature curve of the initial air conditioner according to the usage information to obtain the power-temperature curve of the preset air conditioner.

6. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the vehicle air conditioning control method as described in any one of claims 1-3.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the vehicle air conditioning control method as described in any one of claims 1-3.

Images