Remote control method and system for parking heater

Abstract

The invention discloses a remote control method and system for a parking heater, and relates to the technical field of data processing.The method comprises the steps that parking heating instruction information sent by a user side is received, and the parking heating instruction information comprises user side position time sequence information before the instruction receiving moment; according to the user side position time sequence information, arrival prediction is carried out in combination with the vehicle position information, and the arrival prediction duration is obtained; performing temperature calibration according to the vehicle model and the environment temperature to obtain a target heating temperature; and according to the target heating temperature and the arrival prediction duration, heating control optimization is carried out based on the heating energy consumption prediction channel, a heating control scheme optimization result is obtained, and remote heating control is carried out. The technical problems that in the prior art, the heating effect and energy consumption are affected due to the fact that the refinement degree of control over the parking heater is low are solved, and the technical effects that refinement control over the parking heater is achieved, the heating effect is improved, and meanwhile energy consumption is reduced are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a remote control method and system for a parking heater. Background Art

[0002] The parking heater is an onboard heating device for the car engine. Its main function is to preheat the engine and cab of a car parked in a cold winter environment without starting the engine, thereby eliminating cold start wear and tear on the car.

[0003] In the prior art, the driver usually actively preheats the car engine and cab through the control device of the parking heater, and the heating power is also controlled based on preset parameters. It is impossible to perform refined heating in combination with actual scenarios, resulting in poor heating effect and high heating energy consumption. Summary of the invention

[0004] The present application provides a remote control method and system for a parking heater, which are used to solve the technical problem in the prior art that the control of the parking heater is of low refinement, affecting the heating effect and energy consumption.

[0005] In a first aspect of the present application, a remote control method for a parking heater is provided, the method comprising: receiving parking heating instruction information issued by a user terminal, wherein the parking heating instruction information comprises user terminal position timing information in a preset time zone before the instruction is received; performing arrival prediction based on the user terminal position timing information in combination with vehicle position information to obtain arrival prediction duration; performing temperature calibration based on vehicle model and ambient temperature to obtain a target heating temperature; configuring a heating energy consumption prediction channel; performing heating control optimization based on the heating energy consumption prediction channel according to the target heating temperature and the arrival prediction duration to obtain a heating control scheme optimization result; and performing remote heating control according to the heating control scheme optimization result.

[0006] According to a second aspect of the present application, a remote control system for a parking heater is provided, the system comprising: a heating instruction information receiving module, the heating instruction information receiving module being used to receive parking heating instruction information issued by a user terminal, wherein the parking heating instruction information comprises user terminal position timing information in a preset time zone before the instruction receiving moment; an arrival time prediction module, the arrival time prediction module being used to perform arrival prediction based on the user terminal position timing information in combination with vehicle position information to obtain a predicted arrival time; a target heating temperature acquisition module, the target heating temperature acquisition module being used to perform temperature calibration based on the vehicle model and ambient temperature to obtain a target heating temperature; an energy consumption prediction channel configuration module, the energy consumption prediction channel configuration module being used to configure a heating energy consumption prediction channel; a heating control scheme optimization module, the heating control scheme optimization module being used to perform heating control optimization based on the heating energy consumption prediction channel according to the target heating temperature and the predicted arrival time to obtain a heating control scheme optimization result; and a remote heating control module being used to perform remote heating control based on the heating control scheme optimization result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application provides a remote control method for a parking heater, which relates to the field of data processing technology. The method performs arrival prediction through user-side position timing information and vehicle position information to obtain the predicted arrival time. The temperature is calibrated according to the vehicle model and the ambient temperature to obtain the target heating temperature. The heating control is optimized according to the target heating temperature and the predicted arrival time to obtain the optimized result of the heating control scheme, and remote heating control is performed. The method solves the technical problems in the prior art that the control of the parking heater is of low refinement, which affects the heating effect and energy consumption, and realizes the refined control of the parking heater, which improves the heating effect while reducing the energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of a remote control method for a parking heater provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart of obtaining a predicted arrival time in a remote control method for a parking heater provided in an embodiment of the present application; Figure 3A schematic diagram of a flow chart of obtaining an optimization result of a heating control scheme in a remote control method for a parking heater provided in an embodiment of the present application; Figure 4 A schematic structural diagram of a remote control system for a parking heater provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: heating instruction information receiving module 11 , arrival time prediction module 12 , target heating temperature acquisition module 13 , energy consumption prediction channel configuration module 14 , heating control scheme optimization module 15 , remote heating control module 16 . DETAILED DESCRIPTION

[0011] The present application provides a remote control method for a parking heater, which is used to solve the technical problem in the prior art that the control of the parking heater is of low refinement, affecting the heating effect and energy consumption.

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0013] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0014] Embodiment 1 like Figure 1 As shown, the present application provides a remote control method for a parking heater, the method comprising: P10: receiving parking heating instruction information sent by the user terminal, wherein the parking heating instruction information includes the user terminal position timing information in a preset time zone before the instruction receiving time; It should be understood that the system receives parking heating command information sent from the user end, and the user end can be a mobile phone APP or other remote control device. The parking heating command information includes the user end position timing information in a preset time zone before the command is received, that is, the position change information of the user end device in a preset time zone before the parking heating command is issued, which can characterize the user's position change, moving speed, etc., and can be used as the basic data for subsequent user arrival prediction.

[0015] P20: performing arrival prediction based on the user terminal location time series information and the vehicle location information to obtain the arrival prediction time; Further, such as Figure 2 As shown, step P20 of the embodiment of the present application also includes: P21: Perform speed calibration according to the user terminal position time series information to obtain the user's travel speed; Furthermore, step P21 of the embodiment of the present application further includes: P21-1: Calculate the travel distance per unit time zone according to the user terminal position time series information to obtain a user characteristic speed set; P21-2: traverse the user characteristic speed set to perform density analysis to obtain a distribution density set; P21-3: Add the distribution density sets to obtain a distribution density sum result; P21-4: traverse the distribution density set, and compare with the sum of the distribution density to obtain the weight distribution result; P21-5: Calculate the weighted mean of the user characteristic speed set according to the weight distribution result to obtain the user's travel speed.

[0016] P22: Obtaining a target travel distance according to the vehicle position information and the tail position information of the user terminal position time series information; P23: Perform arrival prediction based on the user's travel speed and the target travel distance to obtain the predicted arrival time.

[0017] Optionally, the user's arrival time is predicted based on the user-side location timing information and the current location information of the target vehicle. First, the location timing information in the user-side location timing information is divided according to time units, and the travel distance of the user in each unit time zone is calculated to obtain the user's characteristic speed in each unit time zone to form a user characteristic speed set.

[0018] Furthermore, the user characteristic speed set is traversed to perform density analysis. Specifically, for each speed value in the user characteristic speed set, its k-distance is calculated respectively, that is, the difference between each speed value and other k speed values, k is a predefined parameter, indicating the number of neighbors considered. Further, the maximum value of the k-distance is selected as the reachable distance, and multiple differences between each speed value and other speed values ​​within the reachable distance range are calculated, and then the inverse of the average of the multiple differences is calculated as the distribution density to obtain a distribution density set.

[0019] Furthermore, the data in the distribution density set are summed to obtain a distribution density sum result, the distribution density set is traversed, and the distribution density of each speed value is compared with the distribution density sum result to obtain a weighted distribution result, which can characterize the relative importance or contribution of each speed value in the user characteristic speed set. Finally, a weighted mean calculation is performed on all speed values ​​in the user characteristic speed set according to the weighted distribution result to obtain the user's travel speed.

[0020] P30: Perform temperature calibration according to vehicle model and ambient temperature to obtain target heating temperature; Furthermore, step P30 of the embodiment of the present application further includes: P31: Taking the vehicle model and the ambient temperature as constraints, obtaining a set of heating end point recorded temperatures; P32: Obtain the one-quarter sequence number and the three-quarter sequence number of the heating endpoint recording temperature set; P33: Arrange the heating endpoint recorded temperature set in ascending order to obtain the first endpoint recorded temperature of the one-quarter sequence number and the second endpoint recorded temperature of the three-quarter sequence number; P34: Calculate the characteristic deviation value of the second endpoint recorded temperature minus the first endpoint recorded temperature; P35: Obtain a first selection boundary according to the first endpoint recorded temperature minus 1.5 times the characteristic deviation value, and obtain a second selection boundary according to the second endpoint recorded temperature plus 1.5 times the characteristic deviation value; P36: Delete the heating endpoint recorded temperatures that are less than the first selection boundary or greater than the second selection boundary, obtain a retained heating endpoint recorded temperature set, calculate the mean of the retained heating endpoint recorded temperature set, and obtain the target heating temperature.

[0021] It should be understood that the heating temperature is calibrated according to the model of the target vehicle and the temperature of the environment. First, the model of the target vehicle and the current ambient temperature are used as constraints, and multiple historical heating end point record temperatures are retrieved from the database to form a heating end point record temperature set. Further, according to the amount of data in the heating end point record temperature set, the sequence numbers of the one-quarter and three-quarter positions of this set are determined, and the data in the heating end point record temperature set are arranged in order from small to large to obtain a temperature sequence. Further, from the temperature sequence, the temperature corresponding to the one-quarter sequence number is extracted as the first end point record temperature, and the temperature corresponding to the three-quarter sequence number is extracted as the second end point record temperature.

[0022] Furthermore, the difference between the second endpoint recorded temperature and the first endpoint recorded temperature is calculated as a characteristic deviation value, which can reflect the temperature variation range of the denser part of the temperature data set. According to the characteristic deviation value, the first endpoint recorded temperature is subtracted by 1.5 times the characteristic deviation value to obtain a first selection boundary, and the second endpoint recorded temperature is added by 1.5 times the characteristic deviation value to obtain a second selection boundary, which is used to further screen outliers in the temperature data set.

[0023] Furthermore, the temperature values ​​in the heating endpoint recorded temperature set that are less than the first selection boundary or greater than the second selection boundary are deleted, and the temperature data within the boundary is retained as the retained heating endpoint recorded temperature set. Finally, the data in the retained heating endpoint recorded temperature set are averaged to obtain the target heating temperature.

[0024] P40: Configure heating energy consumption prediction channel; Furthermore, step P40 of the embodiment of the present application also includes: P41: Collect output power time series record data set and heating energy consumption identification data set; P42: Using the heating energy consumption identification data set as supervision data and the output power time series record data set, the LSTM neural network is configured through a stochastic gradient descent algorithm to obtain the heating energy consumption prediction channel.

[0025] Exemplarily, the output power data of the vehicle heater currently in use at different time points during past operation are collected to form an output power time series record data set, and a heating energy consumption identification data set corresponding to the output power data is collected. Furthermore, the heating energy consumption identification data set is used as supervisory data, that is, these actual heating energy consumption values ​​are used to guide the training process of the neural network. At the same time, the output power time series record data set is used as input data, and the LSTM neural network is configured and trained through the stochastic gradient descent algorithm. During the training process, the network parameters are continuously adjusted according to the difference between the output data and the supervisory data, and the LSTM neural network is trained to predict the corresponding heating energy consumption according to the output power time series data until the output data reaches convergence, and the heating energy consumption prediction channel is obtained.

[0026] Among them, the LSTM neural network, namely the long short-term memory network, is a time recurrent neural network that has good performance in processing time series data and can capture long-term dependencies in time series.

[0027] P50: According to the target heating temperature and the predicted arrival time, heating control optimization is performed based on the heating energy consumption prediction channel to obtain a heating control scheme optimization result; Further, such as Figure 3 As shown, step P50 of the embodiment of the present application also includes: P51: collecting a first output power historical record time series data set according to the target heating temperature, the vehicle model and the ambient temperature; P52: Obtaining the heating record duration and heating energy consumption record value of the first output power historical record time series data set; P53: Constructing fitness function: ; in, Characterizing the first preset weight, Characterizing the second preset weight, Represents the predicted arrival time, Characterizes the heating record duration of any second output power historical record time series data, Characterizing the second preset weight, Characterizes the expected heating energy consumption, The heating energy consumption record value of any second output power historical record time series data, Q represents the adaptability; P54: According to the heating record duration and the heating energy consumption record value, based on the fitness function, traverse the first output power historical record time series data set to perform fitness evaluation, and obtain a first fitness evaluation value set; It should be understood that the target heating temperature and the predicted arrival time are input into the heating energy consumption prediction channel to optimize the heating control scheme to obtain the best heating control scheme. Specifically, the target heating temperature, the vehicle model and the ambient temperature are used as constraints, and sample data matching the constraints are retrieved or collected from the database to obtain a first output power historical record time series data set, which contains heating records of multiple historical heating schemes. Furthermore, the heating record duration and heating energy consumption record value of each group of records in the first output power historical record time series data set are traversed and extracted as key indicators for evaluating the performance of the historical heating process.

[0028] Furthermore, according to the actual needs of heating control, a fitness function is constructed: ;in, Characterizing the first preset weight, Characterizing the second preset weight, Represents the predicted arrival time, Characterizes the heating record duration of any second output power historical record time series data, Characterizing the second preset weight, Characterizes the expected heating energy consumption, For any heating energy consumption record value of the second output power historical record time series data, Q represents the fitness, and the greater the fitness, the better the corresponding heating scheme.

[0029] Furthermore, the heating record duration and the heating energy consumption record value are respectively substituted into the fitness function to perform fitness calculation, so as to obtain a first fitness evaluation value set corresponding to each heating scheme in the first output power historical record time series data set.

[0030] P55: According to the first fitness evaluation value set, heating control optimization is performed based on the heating energy consumption prediction channel to obtain the optimization result of the heating control scheme.

[0031] Furthermore, step P55 of the embodiment of the present application also includes: P55-1: sorting the first output power historical record time series data set from large to small according to the first fitness evaluation value set to obtain a first preset number of head solutions and a second preset number of tail solutions; P55-2: Taking any one of the first preset number of head solutions as the target solution, mutating any one of the second preset number of tail solutions, repeating for several times, and obtaining several expanded new solutions, wherein the difference in average output power between any one of the expanded new solutions and the target solution is smaller than the difference in average output power between the tail solution before the mutation and the first preset number of head solutions; P55-3: Through the heating energy consumption prediction channel, the fitness of the several expanded new solutions is evaluated in combination with the fitness function to obtain the fitness of the expanded new solutions; P55-4: Perform maximum value sorting based on the fitness of the expanded new solution and the first fitness evaluation value set to obtain the optimization result of the heating control scheme.

[0032] Optionally, according to the first fitness evaluation value set, heating control optimization is performed based on the heating energy consumption prediction channel. First, with reference to the order of the first fitness evaluation value set from large to small, the data in the first output power history record time series data set are sorted accordingly. Further, a first preset number of solutions with the highest fitness value are selected as the head solution, and a second preset number of solutions with the lowest fitness value are selected as the tail solution. The first preset number can be the first 10%, and the second preset number can be the last 10%, thereby obtaining a first preset number of head solutions and a second preset number of tail solutions.

[0033] Further, any one of the first preset number of head solutions is selected as the target solution, any one of the second preset number of tail solutions is mutated, a new solution is generated by the parameter value in the tail solution, and the process is repeated several times to obtain several expanded new solutions. Moreover, the difference in average output power between any expanded new solution and the target solution should be smaller than the difference in average output power between the tail solution before the mutation and the first preset number of head solutions, so as to ensure that the mutation operation is searching for a better solution space.

[0034] Furthermore, the several expanded new solutions are input into the heating energy consumption prediction channel, and their fitness is evaluated in combination with the fitness function to obtain the fitness of the expanded new solution, and then the fitness of the expanded new solution and the first fitness evaluation value set are sorted for the maximum value, and the heating control scheme corresponding to the solution with the largest fitness is selected as the optimization result of the heating control scheme.

[0035] P60: Perform remote heating control according to the optimization result of the heating control scheme.

[0036] Specifically, according to the parameters and instructions in the optimization result of the heating control scheme, the parking heater is configured and controlled, including the control of heating power, heating time, heating mode, etc., to achieve precise control of the heating equipment, thereby improving heating efficiency, reducing energy consumption and enhancing user experience.

[0037] In summary, the embodiments of the present application have at least the following technical effects: The present application performs arrival prediction through user-side location timing information and vehicle location information to obtain the predicted arrival time, performs temperature calibration according to the vehicle model and ambient temperature to obtain the target heating temperature, performs heating control optimization according to the target heating temperature and the predicted arrival time, obtains the optimization result of the heating control scheme, and performs remote heating control.

[0038] The parking heater is finely controlled, which improves the heating effect and reduces energy consumption.

[0039] Embodiment 2 Based on the same inventive concept as the remote control method for a parking heater in the aforementioned embodiment, Figure 4 As shown, the present application provides a remote control system for a parking heater, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: A heating instruction information receiving module 11, the heating instruction information receiving module 11 is used to receive parking heating instruction information issued by a user terminal, wherein the parking heating instruction information includes the user terminal position timing information in a preset time zone before the instruction receiving moment; An arrival time prediction module 12, the arrival time prediction module 12 is used to perform arrival prediction based on the user terminal position time series information and the vehicle position information to obtain the arrival prediction time; A target heating temperature acquisition module 13, wherein the target heating temperature acquisition module 13 is used to perform temperature calibration according to the vehicle model and the ambient temperature to obtain the target heating temperature; An energy consumption prediction channel configuration module 14, wherein the energy consumption prediction channel configuration module 14 is used to configure a heating energy consumption prediction channel; A heating control scheme optimization module 15, wherein the heating control scheme optimization module 15 is used to perform heating control optimization based on the heating energy consumption prediction channel according to the target heating temperature and the arrival prediction time, and obtain a heating control scheme optimization result; The remote heating control module 16 is used to perform remote heating control according to the optimization result of the heating control scheme.

[0040] Furthermore, the arrival time prediction module 12 is further configured to perform the following steps: Perform speed calibration according to the user terminal position time series information to obtain the user's travel speed; Obtaining a target travel distance according to the vehicle position information and the tail position information of the user terminal position time series information; An arrival prediction is performed based on the user's travel speed and the target travel distance to obtain the predicted arrival time.

[0041] Furthermore, the arrival time prediction module 12 is further configured to perform the following steps: Calculate the travel distance per unit time zone according to the user terminal position time series information to obtain a user characteristic speed set; Traversing the user characteristic speed set to perform density analysis to obtain a distribution density set; Adding the distribution density sets to obtain a distribution density sum result; Traversing the distribution density set, respectively comparing with the sum of the distribution densities, to obtain a weight distribution result; A weighted mean value of the user characteristic speed set is calculated according to the weight distribution result to obtain the user travel speed.

[0042] Furthermore, the target heating temperature acquisition module 13 is further configured to perform the following steps: Taking the vehicle model and the ambient temperature as constraints, obtaining a set of heating end point recorded temperatures; Obtaining a quarter sequence number and a three-quarter sequence number of the heating endpoint recorded temperature set; Arrange the heating endpoint recorded temperature set in ascending order to obtain the first endpoint recorded temperature of the one-quarter sequence number, and obtain the second endpoint recorded temperature of the three-quarter sequence number; Calculate a characteristic deviation value of the second endpoint recorded temperature minus the first endpoint recorded temperature; A first selection boundary is obtained by subtracting 1.5 times the characteristic deviation value from the first endpoint recorded temperature, and a second selection boundary is obtained by adding 1.5 times the characteristic deviation value to the second endpoint recorded temperature; The heating endpoint recorded temperatures that are less than the first selection boundary or greater than the second selection boundary are deleted to obtain a retained heating endpoint recorded temperature set, and the mean of the retained heating endpoint recorded temperature set is calculated to obtain the target heating temperature.

[0043] Furthermore, the energy consumption prediction channel configuration module 14 is also used to perform the following steps: Collect output power time series record data set and heating energy consumption identification data set; The heating energy consumption identification data set is used as the supervision data, and the output power time series record data set is used to configure the LSTM neural network through a stochastic gradient descent algorithm to obtain the heating energy consumption prediction channel.

[0044] Furthermore, the heating control scheme optimization module 15 is also used to perform the following steps: Collecting a first output power historical record time series data set according to the target heating temperature, the vehicle model and the ambient temperature; Obtaining the heating record duration and heating energy consumption record value of the first output power historical record time series data set; Construct a fitness function: ; in, Characterizing the first preset weight, Characterizing the second preset weight, Represents the predicted arrival time, Characterizes the heating record duration of any second output power historical record time series data, Characterizing the second preset weight, Characterizes the expected heating energy consumption, The heating energy consumption record value of any second output power historical record time series data, Q represents the adaptability; According to the heating record duration and the heating energy consumption record value, based on the fitness function, traverse the first output power historical record time series data set to perform fitness evaluation to obtain a first fitness evaluation value set; According to the first fitness evaluation value set, heating control optimization is performed based on the heating energy consumption prediction channel to obtain the optimization result of the heating control scheme.

[0045] Furthermore, the remote heating control module 16 is further configured to perform the following steps: According to the first fitness evaluation value set, the first output power historical record time series data set is sorted from large to small to obtain a first preset number of head solutions and a second preset number of tail solutions; Taking any one of the first preset number of head solutions as a target solution, mutating any one of the second preset number of tail solutions, repeating the process several times, and obtaining several expanded new solutions, wherein the difference between the average output power of any one of the expanded new solutions and the target solution is smaller than the difference between the average output power of the tail solution before the mutation and the first preset number of head solutions; Through the heating energy consumption prediction channel, in combination with the fitness function, the fitness of the plurality of expanded new solutions is evaluated to obtain the fitness of the expanded new solutions; The maximum value is sorted according to the fitness of the expanded new solution and the first fitness evaluation value set to obtain the optimization result of the heating control scheme.

[0046] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0047] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0048] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A remote control method for a parking heater, characterized in that: include: Receiving parking heating instruction information sent by a user terminal, wherein the parking heating instruction information includes the user terminal position timing information in a preset time zone before the instruction receiving time; According to the user terminal location time series information, combined with the vehicle location information, an arrival prediction is performed to obtain an arrival prediction time; Perform temperature calibration according to vehicle model and ambient temperature to obtain target heating temperature; Configure heating energy consumption prediction channel; According to the target heating temperature and the predicted arrival time, heating control optimization is performed based on the heating energy consumption prediction channel to obtain an optimization result of the heating control scheme; Remote heating control is performed according to the optimization result of the heating control scheme.

2. The method according to claim 1, characterized in that According to the user terminal location time series information, combined with the vehicle location information, the arrival prediction is performed to obtain the arrival prediction time, including: Perform speed calibration according to the user terminal position time series information to obtain the user's travel speed; Obtaining a target travel distance according to the vehicle position information and the tail position information of the user terminal position time series information; An arrival prediction is performed based on the user's travel speed and the target travel distance to obtain the predicted arrival time.

3. The method according to claim 2, characterized in that The speed calibration is performed according to the user terminal position time sequence information to obtain the user travel speed, including: Calculate the travel distance per unit time zone according to the user terminal position time series information to obtain a user characteristic speed set; Traversing the user characteristic speed set to perform density analysis to obtain a distribution density set; Adding the distribution density sets to obtain a distribution density sum result; Traversing the distribution density set, respectively comparing with the sum of the distribution densities, to obtain a weight distribution result; A weighted mean value of the user characteristic speed set is calculated according to the weight distribution result to obtain the user travel speed.

4. The method according to claim 1, characterized in that Perform temperature calibration according to vehicle model and ambient temperature to obtain the target heating temperature, including: Taking the vehicle model and the ambient temperature as constraints, obtaining a set of heating end point recorded temperatures; Obtaining a quarter sequence number and a three-quarter sequence number of the heating endpoint recorded temperature set; Arrange the heating endpoint recorded temperature set in ascending order to obtain the first endpoint recorded temperature of the one-quarter sequence number, and obtain the second endpoint recorded temperature of the three-quarter sequence number; Calculate a characteristic deviation value of the second endpoint recorded temperature minus the first endpoint recorded temperature; A first selection boundary is obtained by subtracting 1.5 times the characteristic deviation value from the first endpoint recorded temperature, and a second selection boundary is obtained by adding 1.5 times the characteristic deviation value to the second endpoint recorded temperature; The heating endpoint recorded temperatures that are less than the first selection boundary or greater than the second selection boundary are deleted to obtain a retained heating endpoint recorded temperature set, and the mean of the retained heating endpoint recorded temperature set is calculated to obtain the target heating temperature.

5. The method according to claim 1, characterized in that Configure the heating energy consumption prediction channel, including: Collect output power time series record data set and heating energy consumption identification data set; The heating energy consumption identification data set is used as the supervision data, and the output power time series record data set is used to configure the LSTM neural network through a stochastic gradient descent algorithm to obtain the heating energy consumption prediction channel.

6. The method according to claim 1, characterized in that According to the target heating temperature and the predicted arrival time, heating control optimization is performed based on the heating energy consumption prediction channel to obtain a heating control scheme optimization result, including: Collecting a first output power historical record time series data set according to the target heating temperature, the vehicle model and the ambient temperature; Obtaining the heating record duration and heating energy consumption record value of the first output power historical record time series data set; Construct a fitness function: ； in, Characterizing the first preset weight, Characterizing the second preset weight, Represents the predicted arrival time, Characterizes the heating record duration of any second output power historical record time series data, Characterizing the second preset weight, Characterizes the expected heating energy consumption, The heating energy consumption record value of any second output power historical record time series data, Q represents the adaptability; According to the heating record duration and the heating energy consumption record value, based on the fitness function, traverse the first output power historical record time series data set to perform fitness evaluation to obtain a first fitness evaluation value set; According to the first fitness evaluation value set, heating control optimization is performed based on the heating energy consumption prediction channel to obtain the optimization result of the heating control scheme.

7. The method according to claim 6, characterized in that According to the first fitness evaluation value set, heating control optimization is performed based on the heating energy consumption prediction channel to obtain the heating control scheme optimization result, including: According to the first fitness evaluation value set, the first output power historical record time series data set is sorted from large to small to obtain a first preset number of head solutions and a second preset number of tail solutions; Taking any one of the first preset number of head solutions as a target solution, mutating any one of the second preset number of tail solutions, repeating the process several times, and obtaining several expanded new solutions, wherein the difference between the average output power of any one of the expanded new solutions and the target solution is smaller than the difference between the average output power of the tail solution before the mutation and the first preset number of head solutions; Through the heating energy consumption prediction channel, in combination with the fitness function, the fitness of the plurality of expanded new solutions is evaluated to obtain the fitness of the expanded new solutions; The maximum value is sorted according to the fitness of the expanded new solution and the first fitness evaluation value set to obtain the optimization result of the heating control scheme.

8. A remote control system for a parking heater, characterized in that: The system comprises: A heating instruction information receiving module, the heating instruction information receiving module is used to receive parking heating instruction information issued by a user terminal, wherein the parking heating instruction information includes the user terminal position timing information in a preset time zone before the instruction receiving time; An arrival time prediction module, the arrival time prediction module is used to perform arrival prediction based on the user terminal position time sequence information and the vehicle position information to obtain the arrival prediction time; A target heating temperature acquisition module, which is used to perform temperature calibration according to the vehicle model and the ambient temperature to obtain the target heating temperature; An energy consumption prediction channel configuration module, wherein the energy consumption prediction channel configuration module is used to configure a heating energy consumption prediction channel; A heating control scheme optimization module, the heating control scheme optimization module is used to perform heating control optimization based on the heating energy consumption prediction channel according to the target heating temperature and the arrival prediction time, and obtain an optimization result of the heating control scheme; A remote heating control module is used to perform remote heating control according to the optimization result of the heating control scheme.

Images