A commuting charging stop intelligent guidance method and device driven by user time preference

Abstract

The present invention discloses a method and device for intelligent guidance of commuting and stopping and charging driven by user time-efficiency preference. The method includes constructing a stop-and-charge data set using collected behavioral data, training a new energy user time-efficiency preference portrait model based on the stop-and-charge data set, then collecting behavioral data before the current moment and inputting it into the new energy user time-efficiency preference portrait model for prediction, obtaining the comprehensive commuting and stopping and charging convenience of all users based on the prediction results and the collected commuting parking area planning data, constructing an intelligent guidance parking space model based on the comprehensive commuting and stopping and charging convenience, and using a genetic algorithm to solve and obtain the parking space location corresponding to each user's new energy vehicle. The present invention realizes the advantages of comprehensive commuting and stopping and charging scheduling for all new energy vehicles, achieves the effect of considering the comprehensive commuting and stopping and charging convenience and timeliness of all users, and achieves the goal of optimal comprehensive arrangement of commuting and stopping and charging.

Description

Technical Field

[0001] The present invention belongs to the technical field of commuting stop and charging scheduling for new energy vehicles, and specifically relates to a commuting stop and charging intelligent guidance method and device driven by user time preference. Background Art

[0002] In recent years, the new energy vehicle industry has rapidly developed, driven by both technology and policy, becoming a vital component of urban transportation. Technological advancements have elevated industry standards, while measures such as vehicle purchase subsidies have led to a rapid increase in vehicle ownership.

[0003] The global green mobility revolution is driving the transformation of traditional parking lots, with charging stations rapidly becoming ubiquitous in commercial areas, residential communities, and highway service areas. As demand for charging spaces increases, the question of how to rationally arrange parking and charging, and intelligently guide commuters, has become a pressing issue.

[0004] Most existing parking lots lack a comprehensive commuting and charging scheduling strategy for new energy vehicle owners. This can lead to significant inconvenience for some NEV owners, impacting both efficiency and parking satisfaction. For example, while some parking lots are equipped with charging stations, due to a lack of proper guidance and management, these stations are often occupied by fuel-powered vehicles or are inefficiently used, preventing NEV owners from finding available charging facilities. This situation not only impacts the driver's travel experience but also exacerbates the waste of charging resources. Summary of the Invention

[0005] In order to solve the problems in the background technology, the present invention provides a method and device for intelligent guidance of commuting and charging stops driven by user time preference, which solves the problem of lack of intelligent scheduling for new energy vehicle owners in the existing technology.

[0006] The technical solutions adopted in the present invention include:

[0007] 1. An intelligent guidance method for commuting charging stops driven by user time preference:

[0008] S1. Collect the behavioral data of each new energy vehicle entering and leaving the parking lot over several days in history, and build a parking and charging dataset based on the behavioral data of all new energy vehicles.

[0009] S2. Construct a new energy vehicle user time-efficiency preference portrait model in a computer, input the charging stop data set into the new energy vehicle user time-efficiency preference portrait model for training, and obtain a trained new energy vehicle user time-efficiency preference portrait model.

[0010] S3. Input the collected behavioral data before the current moment into the new energy vehicle user time-efficiency preference portrait model for prediction. Based on the prediction results and the collected commuting parking area planning data within the preset sliding window time, the total commuting, stopping and charging convenience of each new energy vehicle is obtained. Based on the total commuting, stopping and charging convenience, the comprehensive commuting, stopping and charging convenience of all users is obtained.

[0011] S4. Build an intelligent guidance parking space model based on the comprehensive commuting, stopping and charging convenience. Use a genetic algorithm to process the intelligent guidance parking space model to obtain the parking space location corresponding to each user's new energy vehicle. Guide each new energy vehicle into the corresponding parking space based on the obtained parking space location.

[0012] The S1 is specifically:

[0013] S11. Collect behavioral data of each new energy vehicle entering and exiting the parking lot every time within a few days.

[0014] S12. Count the probability values of each new energy vehicle leaving the parking lot from each parking lot exit on all days based on the behavior data, and use the probability values of leaving the parking lot from all parking lot exits as probability data.

[0015] S14. Use the behavior data as input data and the corresponding probability data as labels to construct the charging and stopping data of each new energy vehicle.

[0016] S15. The charging stop data of all new energy vehicles are aggregated to obtain a charging stop data set.

[0017] The behavior data of each new energy vehicle entering and exiting the parking lot in S11 includes the user number of the new energy vehicle, the parking lot entrance number when entering the parking lot, the time period when entering the parking lot entrance, and the parking lot exit number when leaving the parking lot.

[0018] The new energy vehicle user time preference portrait model in S2 adopts a long short-term memory neural network.

[0019] The S3 is specifically:

[0020] S31. Collect the behavior data of all new energy vehicles in a preset time period before the current moment, and input the behavior data into the trained new energy vehicle user time preference portrait model to predict the probability value of each new energy vehicle leaving the parking lot from each parking lot exit within the preset sliding window time after the current moment.

[0021] S32. Collect commuting parking area planning data for each new energy vehicle within a preset sliding window time after the current moment, and obtain the total commuting parking and charging convenience of each new energy vehicle based on the commuting parking area planning data and the probability value of each new energy vehicle leaving the parking lot from each parking lot exit.

[0022] S33. Obtain the comprehensive commuting stop-and-charge convenience of all users based on the total commuting stop-and-charge convenience of each new energy vehicle user.

[0023] The commuting parking area planning data for each new energy vehicle in S32 includes the user number of the new energy vehicle, the time period when entering the parking lot entrance, the parking lot entrance number when entering the parking lot, the number of the preliminarily estimated parking space, the difficulty value of driving from the parking lot entrance to the parking space, the difficulty value of driving from the parking space to the parking lot exit, the total number of parking lot exits, the power of the new energy vehicle when entering the parking lot entrance, and the density of new energy vehicles in the parking spaces.

[0024] The total commuting stop-and-charge convenience of each new energy vehicle in S32 is obtained by processing according to the following formula:

[0025] ρ i =0.5α i +0.3β i +0.2γ i ;

[0026] α i =1-(D i，INj (P)+∑ k=1 n f i，INj，OUTk ×D i，OUTk (P)) / 2;

[0027] β i =(1-D i，INj (P))×(1-SOC / 100);

[0028] γ i =1-INT(P).

[0029] Where i represents the user number of the new energy vehicle; ρ i represents the total commuting stop and charge convenience of the new energy vehicle with user number i; α i represents the convenience of parking and charging for the new energy vehicle with user number i based on the parking and picking up of the new energy vehicle user; β i represents the convenience of commuting stop and charge for the new energy vehicle with user number i; γ irepresents the convenience of commuting and charging for the new energy vehicle with user number i based on the density of new energy vehicles; j represents the index, and also represents the parking lot entrance number when entering the parking lot; D i，INj (P) represents the difficulty value of the new energy vehicle with user number i driving from the parking lot entrance with number j to the parking space with number P; k represents the index and also represents the parking lot exit number when leaving the parking lot; D i，OUTk (P) represents the difficulty value for a new energy vehicle with user number i to drive from parking space number P to parking lot exit number k; n represents the total number of parking lot exits; f i，INj，OUTk It represents the probability value of a new energy vehicle with user number i leaving the parking lot from the parking lot exit number k, under the premise that the new energy vehicle enters the parking lot entrance number j; SOC represents the power of the new energy vehicle when it enters the parking lot entrance; INT(P) represents the density of new energy vehicles in the parking space numbered P.

[0030] The S4 is specifically:

[0031] S41. Binary encode the numbers of all parking spaces to obtain binary-encoded parking space numbers.

[0032] S42. Determine the constraint conditions based on the binary-coded parking space numbers, and construct an intelligent guidance parking space model using the comprehensive commuting, parking, and charging convenience as the fitness function.

[0033] S43. Use a genetic algorithm to process the intelligent guidance parking space model to obtain a combination of parking space positions for all users' new energy vehicles that maximizes the comprehensive commuting, stopping, and charging convenience, and obtain the parking space position corresponding to each user's new energy vehicle based on the combination of parking space positions.

[0034] S44. Guiding each new energy vehicle to enter a corresponding parking space according to the parking space position obtained in S43.

[0035] The intelligent guided parking space model in S42 is set according to the following formula:

[0036] Max(ρ all (P all ));

[0037] ρ all (P all )=∑ i=1 m ρ i ;

[0038] 0 <P ibin <P max ;

[0039] Pibin ≠P jbin .

[0040] Where i represents the user number of the new energy vehicle; ρ i represents the total commuting stop-and-charge convenience of new energy vehicles with user number i; m represents the total number of new energy vehicle users who need intelligent guidance for commuting stop-and-charge; P all represents the combination of parking spaces of all users’ new energy vehicles; all (P all ) indicates that in P all The comprehensive commuting and charging convenience of new energy vehicles for all users under the combination of Max(ρ all (P all )) represents the maximization of fitness function; P ibin Indicates the binary code of the parking space corresponding to the new energy vehicle with user number i; P jbin Indicates the binary coded number of the parking space corresponding to the new energy vehicle with user number j; P max Indicates the maximum value among the binary-coded numbers of all parking spaces.

[0041] 2. A smart guidance device for commuting charging stops driven by user time preference:

[0042] It includes: an information collection module for collecting behavioral data of new energy vehicles and commuting parking area planning data; an information storage module for storing behavioral data of new energy vehicles and commuting parking area planning data; a model library module for constructing and storing new energy vehicle user time preference portrait models and intelligent guidance parking space models; a calculation module for processing and calculating the total commuting stop and charging convenience of each new energy vehicle, the comprehensive commuting stop and charging convenience of all users, and the combination of the parking space positions of all users' new energy vehicles under the maximum comprehensive commuting stop and charging convenience; a visual guidance module for guiding each new energy vehicle to the corresponding parking space position.

[0043] The innovation of this invention lies in the use of a new energy vehicle user time preference portrait model and an intelligent guidance parking space model, which realizes the advantage of comprehensive commuting, stopping and charging scheduling for all new energy vehicles, achieves the effect of taking into account the comprehensive commuting, stopping and charging convenience and timeliness of all users, and achieves the goal of optimal comprehensive commuting, stopping and charging arrangements.

[0044] The beneficial effects of the present invention are:

[0045] 1. Based on commuting stop and charging, the present invention introduces a new energy vehicle user time preference portrait model and an intelligent guidance parking space model. By calculating the total commuting stop and charging convenience of each user's new energy vehicle and the comprehensive commuting stop and charging convenience of all users, it realizes comprehensive commuting stop and charging scheduling for all new energy vehicles.

[0046] 2. While meeting the commuting and charging requirements of new energy vehicle owners, the present invention takes into account the comprehensive commuting and charging convenience and timeliness of all users, achieving the optimal commuting and charging comprehensive arrangement. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Flowchart of the method of the present invention.

[0048] Figure 2 This is an exemplary layout diagram of the first parking lot of the present invention.

[0049] Figure 3 This is an exemplary layout diagram of the second parking lot of the present invention.

[0050] Figure 4 Schematic diagram of the main functional modules of the device of the present invention.

[0051] Figure 5 Flowchart of the genetic algorithm used in the method of the present invention. DETAILED DESCRIPTION

[0052] The present invention is described in more detail below with reference to the accompanying drawings and examples. However, the present invention is not limited thereto. A person skilled in the art may make various improvements and modifications without departing from the principles of the present invention, and such improvements and modifications are considered to be within the scope of protection of the present invention. Any matters not described in detail in this specification constitute prior art known to those skilled in the art.

[0053] The specific embodiments of the present invention are as follows:

[0054] Example 1:

[0055] like Figure 1 As shown, the commuting charging intelligent guidance method of this embodiment includes the following steps:

[0056] S1. Collect behavioral data of each new energy vehicle entering and exiting the parking lot several times over several days in the past, and build a parking and charging dataset based on the behavioral data of all new energy vehicles.

[0057] S11. Collect behavioral data of each new energy vehicle entering and exiting the parking lot every time within a few days.

[0058] The behavior data of each new energy vehicle entering and exiting the parking lot each time includes the user number of the new energy vehicle, the parking lot entrance number when entering the parking lot, the time period when entering the parking lot entrance, and the parking lot exit number when leaving the parking lot.

[0059] Specifically, the user number of the new energy vehicle, the parking lot entrance number when entering the parking lot, the time period of entering the parking lot, and the parking lot exit number when leaving the parking lot are combined into a data group as behavior data.

[0060] S12. Count the probability values of each new energy vehicle leaving the parking lot from each parking lot exit on all days based on the behavior data, and combine the probability values of leaving the parking lot from all parking lot exits as probability data.

[0061] In a specific implementation, the probability value of leaving the parking lot at each parking lot exit is the number of times a new energy vehicle leaves the parking lot from the corresponding parking lot exit divided by the total number of times it leaves the parking lot from all parking lot exits. The sum of the probability values of each new energy vehicle leaving the parking lot from all parking lot exits is one.

[0062] S14. Use the behavior data as input data and the corresponding probability data as labels to construct the charging and stopping data of each new energy vehicle.

[0063] S15. The charging stop data of all new energy vehicles are aggregated to obtain a charging stop data set.

[0064] S2. Construct a new energy vehicle user time-efficiency preference portrait model in a computer, input the charging stop data set into the new energy vehicle user time-efficiency preference portrait model for training, and obtain a trained new energy vehicle user time-efficiency preference portrait model.

[0065] The new energy vehicle user time preference portrait model adopts long short-term memory neural network.

[0066] Specifically, behavioral data is used as input data of the new energy vehicle user time-efficiency preference portrait model, and corresponding probability data is used as label data of the new energy vehicle user time-efficiency preference portrait model and input into the new energy vehicle user time-efficiency preference portrait model for training.

[0067] S3. Input the collected behavioral data before the current moment into the new energy vehicle user time-efficiency preference portrait model for prediction. Based on the prediction results and the collected commuting parking area planning data within the preset sliding window time after the current moment, the total commuting, stopping and charging convenience of each new energy vehicle is obtained. Based on the total commuting, stopping and charging convenience, the comprehensive commuting, stopping and charging convenience of all users is obtained.

[0068] S31. Collect the behavior data of all new energy vehicles in a preset time period before the current moment, and input the behavior data into the trained new energy vehicle user time preference portrait model to predict the probability value of each new energy vehicle leaving the parking lot from each parking lot exit within the preset sliding time after the current moment.

[0069] S32. Collect the commuting parking area planning data of each new energy vehicle within the preset sliding window time after the current moment, and obtain the total commuting parking and charging convenience of each new energy vehicle based on the commuting parking area planning data and the probability value of each new energy vehicle leaving the parking lot from each parking lot exit obtained in S31.

[0070] Furthermore, the predicted preset time period after the current moment is longer than the preset sliding window time after the current moment.

[0071] The commuting parking area planning data for each new energy vehicle includes the user number of the new energy vehicle, the time period when entering the parking lot entrance, the parking lot entrance number when entering the parking lot, the preliminary estimated parking space number, the difficulty value of driving from each parking lot entrance to all parking spaces, the difficulty value of driving from each parking space to all parking lot exits, the total number of parking lot exits, the power of the new energy vehicle when entering the parking lot entrance, and the density of new energy vehicles in each parking space.

[0072] Specifically, the difficulty of driving from each parking lot entrance to all parking spaces and the difficulty of driving from each parking space to all parking lot exits are both constants, derived empirically after the parking lot's area design is completed. The power level of the new energy vehicle upon entering the parking lot entrance is obtained from the data link and recorded on the new energy vehicle's dashboard. The new energy vehicle density of each parking space is the ratio of new energy vehicles parked in the Y surrounding parking spaces. For example, if there are 5 new energy vehicles parked in 10 surrounding parking spaces, the ratio is 0.5, indicating a new energy vehicle density of 0.5 in that parking space. The new energy vehicle density of each parking space is obtained by scanning the parking space with a surveillance camera.

[0073] The total commuting stop and charge convenience of each new energy vehicle is calculated using the following formula:

[0074] ρ Ui，INj，T，P =0.5α Ui，INj，T，P +0.3β Ui，INj，T，P +0.2γ Ui，INj，T，P ;

[0075] α Ui，INj，T，P =1-(D INj (P)+∑ k=1 n f Ui，INj，OUTk，T × D OUTk (P)) / 2;

[0076] β Ui，INj，T，P =(1-D INj (P))×(1-SOC Ui / 100);

[0077] γ Ui，INj，T，P =1-INT(P).

[0078] Where i represents the user number of the new energy vehicle; j represents the parking lot entrance number when entering the parking lot; Ui represents the new energy vehicle with user number i; INj represents the parking lot entrance number j; T represents the time period when entering the parking lot entrance; P represents the number of the initially estimated parking space; ρ Ui，INj，T，P represents the total commuting parking and charging convenience of a new energy vehicle with user number i entering the parking lot entrance with number j and parking in the parking space with number P during time period T; Ui，INj，T，P represents the convenience of parking and charging based on the commuting experience of new energy vehicle users when a new energy vehicle with user ID i enters the parking lot with ID j and parks in the parking space with ID P during the time period T; β Ui，INj，T，P represents the convenience of commuting charging based on charging of new energy vehicles when a new energy vehicle with user number i enters the parking lot with number j and parks at parking space with number P during time period T; γ Ui，INj，T，P represents the convenience of commuting parking and charging based on the density of new energy vehicles when a new energy vehicle with user number i enters the parking lot with number j and parks at parking space with number P during time period T; D INj (P) represents the difficulty of driving from the parking lot entrance numbered j to the parking space numbered P; n represents the total number of parking lot exits; k represents the index, which also represents the parking lot exit number when leaving the parking lot; f Ui，INj，OUTk，T represents the probability value of leaving the parking lot from the exit numbered k under the premise that the new energy vehicle with user numbered i enters the parking lot entrance numbered j during the time period T; D OUTk (P) represents the difficulty value of driving from the parking space at position P to the parking lot exit numbered k; SOC Ui It represents the battery level of the new energy vehicle with user number i when it enters the parking lot entrance, expressed as a percentage; INT(P) represents the density of new energy vehicles in the parking space numbered P.

[0079] In a specific implementation, the intelligent guidance of commuting stop and charge of this method occurs after the new energy vehicle enters the parking lot entrance, so the entrance number of each user's new energy vehicle is fixed.

[0080] S33. Within a preset sliding window time after the current moment, obtain the comprehensive commuting stop-and-charge convenience of all users based on the total commuting stop-and-charge convenience of each new energy vehicle user.

[0081] The comprehensive commuting stop-and-charge convenience for all users is set according to the following formula:

[0082] ρall (P all )=∑ i=1 m ρ Ui，INj，T，P .

[0083] Where i represents the user ID of the new energy vehicle; j represents the parking lot entrance number when entering the parking lot; T represents the time period when entering the parking lot entrance; P represents the parking space number; U i represents the new energy vehicle with user number i; INj represents the parking lot entrance with number j; ρ Ui，INj，T，P represents the total commuting stop-and-charge convenience of a new energy vehicle with user number i entering the parking lot entrance with number j and parking at parking space with number P during time period T; m represents the total number of new energy vehicles that require intelligent guidance for commuting stop-and-charge; P all represents the combination of parking spaces of all users’ new energy vehicles; all (P all ) indicates that in P all The comprehensive commuting and charging convenience of new energy vehicles for all users under the combination.

[0084] S4. Build an intelligent guidance parking space model based on the comprehensive commuting, stopping and charging convenience. Use a genetic algorithm to process the intelligent guidance parking space model to obtain the parking space location corresponding to each user's new energy vehicle. Guide each new energy vehicle into the corresponding parking space based on the obtained parking space location.

[0085] S41. Binary encode the numbers of all parking spaces to obtain binary-encoded parking space numbers.

[0086] S42. Determine the constraint conditions based on the binary-coded parking space numbers, and construct an intelligent guidance parking space model using the comprehensive commuting, parking, and charging convenience as the fitness function.

[0087] The intelligent guided parking space model is set according to the following formula:

[0088] Max(ρ all (P all ));

[0089] ρ all (P all )=∑ i=1 m ρ Ui，INj，T，P ;

[0090] 0 <P ibin <P max ;

[0091] P ibin ≠P jbin .

[0092] Where i represents the user number of the new energy vehicle; j represents the parking entrance number when entering the parking lot; T represents the time period when entering the parking lot entrance; P represents the parking space number; U i represents the new energy vehicle with user number i; INj represents the parking lot entrance with number j; ρ Ui，INj，T，P represents the total commuting stop-and-charge convenience of a new energy vehicle with user number i entering the parking lot entrance with number j and parking at parking space with number P during time period T; m represents the total number of new energy vehicles that require intelligent guidance for commuting stop-and-charge; P all represents the combination of parking spaces of all users’ new energy vehicles within the preset sliding window time; ρ all (P all ) represents the fitness function, that is, in P all The comprehensive commuting and charging convenience of new energy vehicles for all users under the combination of Max(ρ all (P all )) represents the maximization of the fitness function, that is, maximizing the all The comprehensive commuting and charging convenience of new energy vehicles for all users under the combination of P ibin Indicates the binary code of the parking space corresponding to the new energy vehicle with user number i; P jbin Indicates the binary coded number of the parking space corresponding to the new energy vehicle with user number j; P max Indicates the maximum value among the binary-coded numbers of all parking spaces.

[0093] In the specific implementation, P all Each user selects a parking space for commuting and charging to form a combination. Each user selects different parking spaces for commuting and charging to form multiple P all .

[0094] S43. Use a genetic algorithm to process the intelligent guidance parking space model to obtain a combination of parking space positions for all users' new energy vehicles that maximizes the comprehensive commuting, stopping, and charging convenience, and obtain the parking space position corresponding to each user's new energy vehicle based on the combination of parking space positions.

[0095] In specific implementation, Figure 5 As shown in Figure 2, the genetic algorithm is specifically:

[0096] Initialize the population: Generate a set of possible parking combinations.

[0097] Fitness evaluation: Calculate the comprehensive commuting and charging convenience of each parking space combination.

[0098] Selection: Select a better parking space combination based on the fitness value.

[0099] Crossover: Perform crossover operations on the selected parking space combinations to generate new combinations.

[0100] Mutation: Perform mutation operations on some parking space combinations to introduce randomness.

[0101] Iteration: Repeat the above steps until the optimal solution is found or the maximum number of iterations is reached.

[0102] S44. Guiding each new energy vehicle to enter a corresponding parking space according to the parking space position obtained in S43.

[0103] Furthermore, S3-S4 are repeated to realize the intelligent guidance of continuous commuting and charging of new energy vehicles.

[0104] like Figure 4 As shown, the device of the present invention includes an information collection module for collecting behavioral data and commuting parking area planning data of new energy vehicles; an information storage module for storing behavioral data and commuting parking area planning data of new energy vehicles; a model library module for constructing and storing a time-sensitive preference portrait model of new energy vehicle users and an intelligent guidance parking space model; a calculation module for processing and calculating the total commuting stop-and-charge convenience of each new energy vehicle, the comprehensive commuting stop-and-charge convenience of all users, and the combination of the parking space positions of all users' new energy vehicles under the maximum comprehensive commuting stop-and-charge convenience; and a visual guidance module for guiding each new energy vehicle to drive to the corresponding parking space position.

[0105] Example 2:

[0106] This embodiment is implemented using the same method as in Example 1. During the implementation process:

[0107] This embodiment collects behavioral data of 200 new energy vehicles in the past month. Figure 2 and Figure 3 The following are two exemplary parking lot layouts; this embodiment adopts Figure 2 The parking lot has three entrances and exits. Taking the new energy vehicle with user number 1 as an example, the input data of the new energy vehicle user time preference portrait model is [U1, IN1, 13:00, OUT1], [U1, IN1, 13:00, OUT2], [U1, IN1, 13:00, OUT3], and the output is f U1，IN1，OUT1，13:00 =0.4, f U1，IN1，OUT2，13:00 =0.2, f U1，IN1，OUT1，13:00=0.4, so the output of the new energy vehicle user time preference portrait model is [0.4, 0.2, 0.4]. In this embodiment, the 13:00 time period refers to the 13:00-14:00 time period.

[0108] In addition to the new energy vehicle with user number 1, two other new energy vehicles, user number 2 and user number 3, also entered the parking lot between 13:00 and 14:00. Similarly, the output of the time-efficiency preference profile model for the new energy vehicle with user number 2 is [0.6, 0.2, 0.2], and the output of the time-efficiency preference profile model for the new energy vehicle with user number 3 is [0.2, 0.3, 0.5].

[0109] The new energy vehicle with user number 1 enters the parking lot through the parking lot entrance with number 1 between 13:00 and 14:00. The initial estimated parking position is P 23 , the following formula is used to obtain the total commuting stop-and-charge convenience of the new energy vehicle with user number 1:

[0110] ρ U1，IN1，13:00，P37 =0.5α U1，IN1，13:00，P37 +0.3β U1，IN1，13:00，P37 +0.2γ U1，IN1，13:00，P37 ;

[0111] α U1，IN1，13:00，P37 =1-(D IN1 (P 37 )+∑ k=1 3 f U1，IN1，OUTk，13:00 × D OUTk (P 37 )) / 2;

[0112] β U1，IN1，13:00，P37 =(1-D IN1 (P 37 ))×(1-SOC U1 / 100);

[0113] γ U1，IN1，13:00，P37 =1-INT(P 37 ).

[0114] Among them, drive from the parking lot entrance numbered 1 to parking space P 37 The difficulty value D IN1 (P 37 )=0.3, from parking space P 37 The difficulty value D of driving to the exit of parking lot numbered 1 OUT1 (P 37 )=0.5, from parking space P 37 The difficulty value D of driving to the exit of parking lot numbered 2OUT2 (P 37 )=0.4, from parking space P 37 The difficulty value D of driving to the exit of parking lot number 3 OUT3 (P 37 )=0.7, and f U1，IN1，OUTk，13:00 The SOC of the new energy vehicle when entering the parking lot numbered 1 is [0.4, 0.2, 0.4]. U1 =60, parking space P 37 The density of new energy vehicles = 0.2.

[0115] Therefore, we get α U1，IN1，13:00，P37 =0.57, β U1，IN1，13:00，P37 =0.28,γ U1，IN1，13:00，P37 =0.8, and then we can get the time period from 13:00 to 14:00, the new energy vehicle with user number 1 is expected to drive from the entrance of parking lot number 1 to P 37 The total commuting parking convenience of a parking space is ρ U1，IN1，13:00，P37 =0.529.

[0116] Since the intelligent guidance for commuting charging occurs after the new energy vehicle enters the parking lot entrance, the entrance number for each user's new energy vehicle is fixed.

[0117] Therefore, in the same way, during the time period of 13:00-14:00, the new energy vehicle with user number 2 is expected to drive from the entrance of parking lot number 2 to P 15 The total commuting parking convenience of a parking space is ρ U2，IN2，13:00，P15 =0.433; During the period from 13:00 to 14:00, the new energy vehicle with user number 3 drives from the entrance of parking lot number 1 to P 50 The total commuting parking convenience of a parking space is ρ U3，IN1，13:00，P50 =0.561.

[0118] An intelligent parking guidance model is constructed based on the comprehensive convenience of commuting, stopping, and charging. The constructed intelligent parking guidance model is set according to the following formula:

[0119] Max(ρ all (P all ));

[0120] ρ all (P all )=∑ i=1 3 ρ Ui，INj，13:00，P ;

[0121] 0 <P ibin <P max ;

[0122] P ibin ≠P jbin .

[0123] Among them, ρ Ui，INj，13:00，P They are: U1，IN1，13:00，P37 , ρ U2，IN2，13:00，P15 and ρ U3，IN1，13:00，P50 .

[0124] First, encode the parking spaces and use a genetic algorithm to process the intelligent guidance parking space model to obtain the parking space location corresponding to each user's new energy vehicle. The specific steps of encoding and genetic algorithm processing are as follows:

[0125] 1. Coding: Each parking space is represented by a 6-bit binary code (because there are 63 parking spaces in the parking lot, 26 = 64 is enough to cover it).

[0126] For a new energy vehicle with three users, the parking space combination P all The binary code length of is 12 bits (6 × 2). For example, P all = [P 37 , P 15 , P 50 ] is encoded in binary as 100101001111110010, where: 37 The binary code is 100101, P 15 The binary code is 001111 and P 50 The binary code is 110010.

[0127] 2. Constraints: The binary encoding of each parking space location must satisfy:

[0128] 0 <P ibin <P max ;

[0129] P ibin ≠P jbin .

[0130] Among them, P ibin Indicates the binary code of the parking space corresponding to the new energy vehicle with user number i; P jbin Indicates the binary code of the parking space corresponding to the new energy vehicle with user number j; P max The maximum value of the binary code representing a parking space is 1111111.

[0131] 3. Fitness function:

[0132] The fitness function is the comprehensive commuting stop and charge convenience ρ all (P all ), the calculation formula is:

[0133] ρ all (P all ) =∑ i=1 3 ρ Ui，INj，13:00，P .

[0134] The goal is to optimize the parking space combination P all , so that ρ all (P all )maximize.

[0135] 4. Genetic algorithm process:

[0136] 4.1. Initialize the population: Randomly generate a set of binary codes for parking space combinations, for example:

[0137] Combination 1: 011110001100001110(P 30 , P 12 , P 14 ), combination 2: 010101100011001101(P 21 , P 35 , P 13 ), combination 3: 101010010101010001(P 42 , P 21 , P 17 ).

[0138] 4.2. Fitness Evaluation: Calculate the comprehensive commuting parking and charging convenience ρ for each parking space combination all (P all ).

[0139] 4.3. Selection: Select a better parking space combination based on the fitness value, for example, select combination 1 and combination 2.

[0140] 4.4. Intersection: Perform an intersection operation on the selected parking space combination, for example: combination 1: 011110|001100|001110, combination 2: 010101|100011|001101, after intersection, new combinations are generated: 011110|100011|001110 and 010101|001100|001101.

[0141] 4.5. Mutation: Randomly mutate the newly generated parking space combination. For example, change the third bit of 011110|100011|001110 from 1 to 0 to obtain 010110|100011|001110.

[0142] 4.6. Iteration: Repeat the above steps until the optimal solution is found or the maximum number of iterations is reached.

[0143] 5. Result output:

[0144] The genetic algorithm finally outputs the optimal parking space combination P all and the corresponding maximum comprehensive commuting stop-and-charge convenience ρ all (P all ). For example, the optimal parking space combination P all The optimal result is: P all =[P 29 ,P7,P 41 ],ρ all (P all )=1.677.

[0145] 6. Intelligent guidance:

[0146] Based on the optimal result of the genetic algorithm, the system intelligently guides users to designated parking spaces: User 1: Guided to parking space P 29 , User 2: guided to parking space P7, User 3: guided to parking space P 41 .

[0147] In order to demonstrate the beneficial effects of the present invention, this embodiment further provides a method for averaging user satisfaction of new energy vehicles. The average user satisfaction of new energy vehicles is set according to the following formula:

[0148] S(P all )=∑ i=1 I S Ui (P) / I;

[0149] S Ui (P)=1-(S0(IN j , P)×L(IN j ,P)+ S0(P,OUTk)×L(P,OUTk)).

[0150] Among them, S Ui (P) represents the user satisfaction of the new energy vehicle with user number i; S0(IN j , P) represents the dissatisfaction of the new energy vehicle from the parking lot entrance numbered j to the parking space P per unit distance; S0(P, OUTk) represents the dissatisfaction of the new energy vehicle from the parking space P to the parking lot exit numbered k per unit distance; L(IN j , P) represents the distance traveled by a new energy vehicle from the entrance of parking lot numbered j to parking space P; L(P, OUTk) represents the distance traveled by a new energy vehicle from parking space P to the exit of parking lot numbered k; P all represents the combination of parking spaces for all users’ new energy vehicles; I represents the total number of users of new energy vehicles that require intelligent guidance for commuting parking and charging; i represents the user number of the new energy vehicle; S(P all) indicates that in P all Average user satisfaction of new energy vehicles under the combination.

[0151] In order to evaluate the effect of intelligent guidance on the three new energy vehicle users in this embodiment, this embodiment adopts the average new energy vehicle user satisfaction method to evaluate the P all =[P 29 ,P7,P 41 ] This combination of three new energy vehicle users is processed. During the processing:

[0152] S0(IN j , P) is set to 0.001 / m, S0(P, OUTk) is set to 0.0015 / m, L(IN1, P 29 ) is 100m, L(P 29 , OUT2) = 120m, thus obtaining S U1 (P 29 )=0.72. Similarly, S U2 (P7)=0.68, S U1 (P 41 )=0.67, thus obtaining S(P all )=0.69.

[0153] Comparative Example:

[0154] This comparison adopts the method of randomly selecting parking spaces nearby. When the new energy vehicle with user number i enters the parking lot after passing the parking lot entrance with number j, the vehicle searches for the vacant parking space P closest to the parking lot entrance with number j. nearest , define P nearest Center, radius R near The set of free parking spaces within is P near , gather P in the free parking spaces near A parking space P is randomly selected as the target parking space for the new energy vehicle of user number i.

[0155] In Example 2, after the new energy vehicle with user number 1 enters the parking lot through the parking lot entrance with number 1, it searches for the vacant parking space P closest to the parking lot entrance with number 1. nearest P 10 , defined by P nearest =P 10 Center, radius R near =The set of free parking spaces within 10m is P near =[P8, P9, P 10 , P 15 ], meet at the parking lot P near =[P8, P9, P 10 , P 15] randomly select a parking space P 15 As the target parking space for the new energy vehicle of user number 1. Similarly, select P 40 As the target parking space for the new energy vehicle of user number 2, P9 is selected as the target parking space for the new energy vehicle of user number 3.

[0156] The average new energy vehicle user satisfaction method in Example 2 is used to calculate P all =[P 15 , P 40 , P9] The three new energy vehicle users under this combination are processed to obtain the average new energy vehicle user satisfaction S (P all ) = 0.53. This result is lower than 0.69 obtained in Example 2, indicating that the average new energy vehicle user satisfaction obtained after the method of the present invention intelligently guides new energy vehicle users is very good.

[0157] The innovation of this invention lies in the use of a new energy vehicle user time preference portrait model and an intelligent guidance parking space model, which realizes the advantage of comprehensive commuting, stopping and charging scheduling for all new energy vehicles, achieves the effect of taking into account the comprehensive commuting, stopping and charging convenience and timeliness of all users, and achieves the goal of optimal comprehensive commuting, stopping and charging arrangements.

[0158] The above embodiments are merely preferred embodiments for the purpose of fully illustrating the present invention, and the scope of protection of the present invention is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on the present invention are within the scope of protection of the present invention. The scope of protection of the present invention shall be subject to the claims.

Claims

1. A commuting charging and stopping intelligent guidance method driven by user time preference, characterized in that: The steps include: S1. Collect the behavior data of each new energy vehicle entering and leaving the parking lot over several days in history, and build a parking and charging dataset based on the behavior data of all new energy vehicles; S2. Build a new energy vehicle user time-efficiency preference portrait model, input the charging stop dataset into the new energy vehicle user time-efficiency preference portrait model for training, and obtain a trained new energy vehicle user time-efficiency preference portrait model; S3. Input the collected behavioral data before the current moment into the new energy vehicle user time-efficiency preference profiling model for prediction. Based on the prediction results and the collected commuting parking area planning data within a preset sliding window time, the total commuting parking convenience of each new energy vehicle is obtained. Based on the total commuting parking convenience, the comprehensive commuting parking convenience of all users is obtained. The S3 is specifically: S31. Collecting behavioral data of all new energy vehicles within a preset time period before the current moment, and inputting the behavioral data into a trained new energy vehicle user time preference profile model to predict the probability of each new energy vehicle leaving the parking lot from each parking lot exit within a preset sliding window time after the current moment; S32. Collect commuting parking area planning data for each new energy vehicle within a preset sliding window time, and obtain the total commuting parking and charging convenience of each new energy vehicle based on the commuting parking area planning data and the probability value of each new energy vehicle leaving the parking lot from each parking lot exit; The total commuting stop-and-charge convenience of each new energy vehicle is obtained by the following formula: r i =0.5a i +0.3b i +0.2c i α i =1-(D i，INj (P)+∑ k=1 n f i，INj，OUTk ×D i，OUTk (P)) / 2 β i =(1-D i，INj (P))×(1-SOC / 100) γ i =1-INT(P) Where i represents the user number of the new energy vehicle; ρ i represents the total commuting stop-and-charge convenience of the new energy vehicle of user number i; α i represents the convenience of parking and charging for new energy vehicle users during commuting; β i represents the convenience of commuting and charging based on new energy vehicle charging; γ i represents the convenience of commuting and charging based on the density of new energy vehicles; k and j both represent indexes; D i，INj (P) represents the difficulty of a new energy vehicle driving from the entrance of parking lot numbered j to the parking space numbered P; D i，OUTk (P) represents the difficulty value of a new energy vehicle driving from a parking space numbered P to a parking lot exit numbered k; n represents the total number of parking lot exits; f i，INj，OUTk represents the probability of a new energy vehicle leaving the parking lot from the exit numbered k, given that the new energy vehicle enters the parking lot entrance numbered j; SOC represents the battery level of the new energy vehicle when it enters the parking lot entrance; INT(P) represents the density of new energy vehicles in the parking space numbered P; S33. Obtaining the comprehensive commuting stop-and-charge convenience of all users based on the total commuting stop-and-charge convenience of each new energy vehicle user; S4. Build an intelligent guidance parking space model based on the comprehensive commuting, stopping and charging convenience. Use a genetic algorithm to process the intelligent guidance parking space model to obtain the parking space location corresponding to each user's new energy vehicle. Guide each new energy vehicle into the corresponding parking space based on the obtained parking space location.

2. The method for intelligent guidance of commuting stop and charge driven by user time preference according to claim 1, characterized in that: The S1 is specifically: S11. Collect behavioral data of each new energy vehicle entering and exiting the parking lot over several days; S12. Counting the probability values of each new energy vehicle leaving the parking lot from each parking lot exit on all days based on the behavior data, and using the probability values of each new energy vehicle leaving the parking lot from all parking lot exits as probability data; S14, using the behavior data as input data and the corresponding probability data as labels to construct charging and stopping data for each new energy vehicle; S15. The charging stop data of all new energy vehicles are aggregated to obtain a charging stop data set.

3. The method for intelligent guidance of commuting charging and stopping driven by user time preference according to claim 2 is characterized by: The behavior data of each new energy vehicle entering and exiting the parking lot in S11 includes the user number of the new energy vehicle, the parking lot entrance number when entering the parking lot, the time period when entering the parking lot entrance, and the parking lot exit number when leaving the parking lot.

4. The method for intelligently guiding commuting charging and stopping based on user time preference according to claim 1, characterized in that: The new energy vehicle user time preference portrait model in S2 adopts a long short-term memory neural network.

5. The method for intelligent guidance of commuting charging and stopping driven by user time preference according to claim 1 is characterized by: The commuting parking area planning data for each new energy vehicle in S32 includes the user number of the new energy vehicle, the time period when entering the parking lot entrance, the parking lot entrance number when entering the parking lot, the number of the preliminarily estimated parking space, the difficulty value of driving from the parking lot entrance to the parking space, the difficulty value of driving from the parking space to the parking lot exit, the total number of parking lot exits, the power of the new energy vehicle when entering the parking lot entrance, and the density of new energy vehicles in the parking spaces.

6. The method for intelligent guidance of commuting stop and charge driven by user time preference according to claim 1, characterized in that: The S4 is specifically: S41. Binary-code the numbers of all parking spaces to obtain binary-coded parking space numbers. S42. Determine constraints based on the binary-coded parking space numbers, and construct an intelligent parking guidance model using the comprehensive commuting, parking, and charging convenience as a fitness function. S43. Using a genetic algorithm to process the intelligent guidance parking space model, obtain a combination of parking space locations for all users' new energy vehicles that maximizes comprehensive commuting parking and charging convenience, and obtain a parking space location corresponding to each user's new energy vehicle based on the combination of parking space locations; S44. Guiding each new energy vehicle to enter a corresponding parking space according to the parking space position obtained in S43.

7. The method for intelligent guidance of commuting charging and stopping driven by user time preference according to claim 6, characterized in that: The intelligent guided parking space model in S42 is set according to the following formula: Max(r all (P all )) r all (P all )=∑ i=1 m r i 0<P ibin <P max P ibin ≠P jbin Where i represents the user number of the new energy vehicle; ρ i represents the total commuting stop-and-charge convenience of new energy vehicles with user number i; m represents the total number of new energy vehicle users who need intelligent guidance for commuting stop-and-charge; P all represents the combination of parking spaces of all users’ new energy vehicles; all (P all ) indicates that in P all The comprehensive commuting and charging convenience of new energy vehicles for all users under the combination of Max(ρ all (P all )) represents the maximization of fitness function; P ibin Indicates the binary code of the parking space corresponding to the new energy vehicle with user number i; P jbin Indicates the binary coded number of the parking space corresponding to the new energy vehicle with user number j; P max Indicates the maximum value among the binary-coded numbers of all parking spaces.

8. A device for implementing the intelligent guidance method for commuting charging and stopping according to any one of claims 1 to 7, characterized in that: include: Information collection module, used to collect new energy vehicle behavior data and commuter parking area planning data; An information storage module is used to store the behavior data of new energy vehicles and commuting parking area planning data; The model library module is used to build and store the new energy vehicle user time preference portrait model and the intelligent guidance parking space model; a calculation module for processing and calculating the total commuting stop-and-charge convenience of each new energy vehicle, the comprehensive commuting stop-and-charge convenience of all users, and the combination of parking space locations of all users' new energy vehicles under the maximum comprehensive commuting stop-and-charge convenience; The visual guidance module is used to guide each new energy vehicle to the corresponding parking space.

Images