Electric vehicle charging station recommendation method and device based on driver charging preference

Abstract

This invention relates to the field of big data analytics, and in particular to a method and apparatus for recommending electric vehicle charging stations based on driver charging preferences. The method collects current user information and historical charging behavior data, and updates the user's range anxiety threshold. L The system collects the status information of the user's vehicle and the operational data of the charging stations; when a user submits a charging request, it first filters candidate charging stations; then it combines the collected information with the user's current status. L Calculate the user's arrival at any candidate charging station i Payment costs C b Parking time cost C t Range anxiety costs C h and charging efficiency U i Then according to U i Calculate the selection probability of each candidate charging station P i Finally, based on user preferences, the candidate charging stations were categorized as follows: P i From high to low or by C b , C t and C h The recommendations are generated by sorting the data from lowest to highest quality. This invention addresses the problem that existing charging station recommendation services cannot meet users' personalized preferences.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, and in particular to a method for recommending electric vehicle charging stations based on driver charging preferences, as well as the corresponding computer program product, storage medium, and data processing device. Background Technology

[0002] With the increasing popularity of electric vehicles, electric vehicle charging stations, as fundamental infrastructure for the automotive and energy industries, are also developing rapidly. As a crucial support for the widespread adoption of electric vehicles, the convenience of charging plays a vital role in improving the driver's experience and promoting the sustainable development of the industry. Unlike gasoline-powered vehicles, the actual range of electric vehicles fluctuates due to factors such as low temperatures and driving habits. Early shortcomings in charging infrastructure, long charging times, and the difficulty in accurately assessing remaining range exacerbated user anxiety. This psychological stress caused by concerns about insufficient battery power while driving an electric vehicle is known as range anxiety.

[0003] During driving, users typically choose to charge their vehicles when the remaining range falls below their personal comfort level. Most users rely on in-vehicle infotainment systems or third-party navigation software for charging station recommendations. Given that each driver has personalized preferences for charging stations, their perceived utility of the same charging station may differ under the same driving conditions. However, current charging station recommendation services often fail to adequately consider these individual preferences. Consequently, under the same driving scenario, the system typically provides the same charging station recommendations to all drivers. This can lead to recommended charging stations that fail to meet individual driver preferences and may even exacerbate congestion at popular charging stations, thus negatively impacting the user's charging experience. Therefore, in-depth analysis of drivers' charging preferences and recommending the most suitable charging stations based on these preferences is crucial for improving the driver's charging experience. Summary of the Invention

[0004] To address the problem that existing charging station recommendation services fail to accurately analyze user personalized preferences, resulting in poor user experience, this invention provides a method for recommending electric vehicle charging stations based on driver charging preferences, along with a corresponding computer program, storage medium, and data processing device.

[0005] The technical solution provided by this invention is as follows:

[0006] A method for recommending electric vehicle charging stations based on driver charging preferences includes the following process:

[0007] Collect personal information and historical charging behavior data that characterize the user's current income level, and update the user's range anxiety threshold accordingly. L .

[0008] The system collects the current vehicle status information and operational data from all charging stations. When a user requests charging, it first considers the vehicle's range and location to identify nearby charging stations as candidate stations, thus creating a candidate station set. I .

[0009] The following formula combines the collected information with the current user's range anxiety threshold. L Calculate the user's arrival at any candidate charging station i Payment costs C b Parking time cost C t Range anxiety costs C h and charging efficiency U i :

[0010] ,

[0011] In the above formula, The number of sites in the candidate site set; D i This indicates that the current user's vehicle has reached the [number]th [location]. i Remaining range at each charging station; C i Indicates the current user's vehicle is in the [number]th position. i The total cost of charging at each charging station.

[0012] According to the following formula U i Calculate the probability of selection P i :

[0013] ,

[0014] In the above formula, This indicates the driver's perception of the effectiveness of charging.

[0015] Based on user preferences, the candidate charging stations were categorized as follows: P i From high to low and by C b , C t and C h Sort the recommendations from lowest to highest quality and return the resulting list to the user.

[0016] As a further improvement to the present invention, personal information includes: the driver's daily income. RDaily working hours H Japanese commute time T w .

[0017] As a further improvement of the present invention, the historical charging behavior data includes: the remaining mileage of the electric vehicle corresponding to each historical charging behavior of the user, the selected charging station, the charging time, the charging cost, the location of the vehicle and each candidate charging station, and the distribution density of the candidate charging stations.

[0018] As a further improvement of the present invention, the vehicle status information includes: real-time location information, current driving range, and total driving range. D Power consumption per kilometer e .

[0019] As a further improvement of the present invention, any candidate charging station i The operational data includes: charging station locations and the number of charging piles. n i Crowding level β i Charging rates m i and charging power W i .

[0020] As a further improvement of the present invention, the payment cost for any charging behavior C b The calculation formula is as follows:

[0021] .

[0022] As a further improvement of the present invention, the time cost of arbitrary charging behavior C t The calculation formula is as follows:

[0023] ,

[0024] In the above formula, C r Indicates that the vehicle is at a candidate charging station i Actual charging time cost; C l This represents the psychologically estimated waiting time cost generated based on the congestion level of candidate charging stations; TC This represents the value of a user's current unit of travel time.

[0025] As a further improvement of this invention, the operating status of charging stations is divided into three types: busy, moderate, and idle, with each type corresponding to a degree of congestion. β i The values ​​are 0.5, 0.35 and 0, respectively.

[0026] As a further improvement of this invention, the range anxiety cost of arbitrary charging behavior. C h The calculation formula is as follows:

[0027] ,

[0028] In the above formula, x This represents the driving range of the electric vehicle; α is a preset power parameter. F ( x () is a power function representing the degree of change in the user's current mileage anxiety; C n This represents the cost of anxiety per unit of mileage.

[0029] As a further improvement to this invention, the unit mileage anxiety cost C n Cost of maximum range anxiety C p This is obtained by dividing by the preset total range anxiety value. Among them, [the following is included] D i The towing cost incurred after resetting the trip to zero is the maximum mileage anxiety cost for the current journey. C p .

[0030] As a further improvement of the present invention, the value of a user's unit travel time... TC The calculation formula is as follows:

[0031] ,

[0032] In the above formula, This represents the travel urgency coefficient, obtained based on the user's current travel purpose.

[0033] As a further improvement of this invention, the user's travel purpose is divided into work commuting, entertainment, and emergency tasks, with the urgency coefficient corresponding to each of the three. The values ​​are 1, 0.7 and 1.5 respectively.

[0034] As a further improvement of the present invention, the mileage anxiety threshold for any user L The update formula is as follows:

[0035] ,

[0036] In the above formula, This represents the percentage of the base range anxiety threshold relative to the total driving range. =0.2; S This represents a quantitative value indicating the driver's driving style. This represents the coefficient indicating the influence of driving style on the range anxiety threshold. This represents the coefficient representing the influence of charging station distribution density on the range anxiety threshold. Z This indicates the distribution density of candidate charging stations; Z 0 indicates the distribution density of benchmark charging stations;

[0037] As a further improvement of the present invention, S , and The value is obtained by evaluating the user's historical charging behavior data. Represents a conservative driver. Represents an aggressive type of driver; ; .

[0038] The present invention also includes a computer program product comprising a computer program that, when executed by a processor, implements the steps of the aforementioned electric vehicle charging station recommendation method based on driver charging preferences, and then generates a recommended list of candidate charging stations that match the user's preferences based on the user's current vehicle status and the operating data of surrounding charging stations, and returns it to the user.

[0039] The present invention also includes a storage medium storing a computer program, which, when executed by a processor, implements the steps of the electric vehicle charging station recommendation method based on driver charging preferences as described above, and then generates a recommended list of candidate charging stations that match the user's preferences based on the user's current vehicle status and the operation data of surrounding charging stations, and returns it to the user.

[0040] The present invention also includes a data processing device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the computer program is executed by the processor, it implements the steps of the electric vehicle charging station recommendation method based on driver charging preferences as described above, and then generates a recommended list of candidate charging stations that match the user's preferences based on the user's current vehicle status and the operation data of surrounding charging stations, and returns it to the user.

[0041] The present invention has the following beneficial effects:

[0042] Unlike traditional technologies that focus on a single factor (such as distance or price), this invention innovatively integrates multiple factors, including distance, price, time, and user experience, to comprehensively and realistically describe drivers' charging station selection behavior in real-world scenarios. By introducing key factors such as range anxiety threshold, charging station congestion level, and the value of time per unit of travel, this solution can flexibly adapt to various complex real-world scenarios and accurately describe the charging selection behavior of different drivers in various driving situations. This multi-dimensional comprehensive consideration provides drivers with personalized charging station recommendation services that match their charging preferences and habits, significantly improving driver charging satisfaction.

[0043] This invention fully utilizes historical charging behavior data to comprehensively analyze drivers' charging behavior characteristics. Through in-depth analysis of historical data, key parameters of each driver's range anxiety threshold model are obtained, thereby accurately quantifying the driver's range anxiety and significantly improving the accuracy and reliability of the model's personalized recommendations. Furthermore, this invention also obtains specific environmental data from historical data, such as towing costs on urban roads, rural roads, and highways, to accurately characterize the range anxiety costs in different scenarios, further optimizing the charging selection model to better meet actual needs.

[0044] This invention provides drivers with a one-stop charging station recommendation service by comprehensively considering multiple key factors such as charging costs, parking time, and range anxiety. The system can flexibly adjust its charging recommendation strategy based on different driving scenarios (such as urban roads and highways) and the driver's travel purpose (such as commuting, entertainment, or emergency travel), combined with real-time vehicle data and the status of nearby charging stations. This personalized charging station recommendation method breaks through the limitations of traditional single-dimensional recommendations, eliminating the need for drivers to repeatedly weigh multiple factors and significantly saving them decision-making time and effort. Simultaneously, the system also provides charging station recommendation lists for each individual dimension (lowest charging cost, shortest parking time, and lowest range anxiety), offering comprehensive decision support to drivers and meeting diverse user needs. Attached Figure Description

[0045] Figure 1 This is a flowchart of a method for recommending electric vehicle charging stations based on driver charging preferences, provided in Embodiment 1 of the present invention.

[0046] Figure 2 This is a schematic diagram of the interactive interface of the data processing device provided in Embodiment 2 of the present invention.

[0047] Figure 3 This is a schematic diagram of a typical research scenario in a simulation experiment.

[0048] Figure 4The curves show the impact of different unit travel time values ​​on the selection probability of each charging station in this scenario during the simulation experiment.

[0049] Figure 5 The curves show the influence of different charging powers on the selection probability of each charging station in this scenario during the simulation experiment.

[0050] Figure 6 The curves show the impact of different congestion levels on the selection probability of each charging station in this scenario during the simulation experiment.

[0051] Figure 7 The curves show the impact of different maximum range anxiety costs on the selection probability of each charging station in this scenario during the simulation experiment.

[0052] Figure 8 The curves show the impact of different range anxiety thresholds on the selection probability of each charging station in this scenario during the simulation experiment.

[0053] Figure 9 The curves show the influence of different remaining mileage on the selection probability of each charging station in this scenario during the simulation experiment. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "or / and" as used herein includes any and all combinations of one or more of the associated listed items.

[0056] Example 1

[0057] This embodiment provides a method for recommending electric vehicle charging stations based on driver charging preferences. Typical application scenarios for this method include... Figure 1 As shown, when a user requests charging, the system backend can combine various collected data to evaluate the overall cost and probability of choosing each charging station. Then, based on the evaluation results, it returns at least one recommendation list that matches the user's personalized preferences to the user's driver terminal for reference.

[0058] Specifically, the electric vehicle charging station recommendation method based on driver charging preferences provided in this embodiment includes the following process:

[0059] I. Create user profiles based on users' historical charging behavior data

[0060] In this embodiment, the system can collect the user's personal information and historical charging behavior data, and update the user's range anxiety threshold accordingly. L This allows for a precise depiction of users' charging preferences and behavioral patterns.

[0061] In this embodiment, the collected personal information mainly refers to various data that help determine a user's income level. This type of data can be used to assess the user's time value and to calculate the costs of the user's subsequent decision-making behavior regarding choosing different charging stations. For example, in practical applications, the personal information collected for each user may include: the driver's daily income. R (Unit: Yuan) Daily Working Hours H (Unit: hours) and daily commute time T w (Unit: hour). Based on the above data, the current user's hourly wage can be calculated as follows: R / ( H + T w Generally speaking, users with higher hourly wages have higher time costs and are more willing to spend more money to save time.

[0062] Historical charging behavior data is primarily used to assess each individual's range anxiety threshold. In this embodiment, the range anxiety threshold... L This refers to the minimum driving range of an electric vehicle that each user can tolerate, when the remaining range is below the range anxiety threshold. L When the battery is depleted, drivers experience anxiety, known as "range anxiety." At this point, users are more likely to choose to charge rather than continue driving. In reality, the range anxiety threshold... L Range anxiety is a parameter related to multiple factors and has a significant impact on users' charging decisions. In the same driving scenario, different drivers have different range anxiety thresholds due to their different driving styles. Therefore, the same remaining range will elicit different range anxiety values ​​from different drivers, resulting in different range anxiety costs. Furthermore, in different driving scenarios, the same driver's range anxiety threshold will also change based on their observation and judgment of the environment.

[0063] To more accurately analyze users' charging decision preferences, this embodiment first needs to quantify each user's range anxiety threshold. The technical personnel in this embodiment analyzed and determined the range anxiety threshold that influences each user.L The main factors influencing range anxiety threshold include the following: First, the vehicle's total driving range is a crucial factor. Vehicles with higher driving range generally experience higher range anxiety thresholds, primarily because when an electric vehicle's battery level drops below 20%, the dashboard indicator light will warn the driver to charge. Therefore, 20% of the total driving range is a critical point for driver range anxiety. Second, the density and distribution of charging stations significantly impact the range anxiety threshold. If charging stations are widely available and convenient, the driver's range anxiety threshold will decrease. Finally, the driver's driving experience and charging habits also affect the range anxiety threshold. Aggressive driving styles (such as extreme charging) tend to reduce the range anxiety threshold, while conservative driving styles (avoiding risks early) tend to increase it.

[0064] Taking into account the three key factors mentioned above, this embodiment uses 20% of the vehicle's driving range as the base component of the range anxiety threshold. Based on this, the threshold is dynamically adjusted according to the charging station density and driving style to more accurately reflect changes in the driver's range anxiety threshold. Therefore, the following calculation model for the range anxiety threshold is constructed:

[0065] ,

[0066] In the above formula, This represents the proportion of the baseline range anxiety threshold to the total driving range. Generally, when the remaining range is less than 20%, range anxiety will significantly increase when driving arbitrarily. Therefore, in this embodiment, =0.2. S This represents a quantitative value indicating the driver's driving style. This embodiment classifies users into two driving types: conservative and aggressive. Conservative drivers tend to be more conservative and therefore need to charge when the vehicle's range is high, resulting in a higher range anxiety threshold. Conversely, aggressive drivers are more likely to drive the vehicle until the battery is almost depleted before charging, leading to a lower range anxiety threshold. Under these conditions, this embodiment will... S The value range is set to -1 to 1, when Represents a conservative driver. This represents an aggressive driver. Considering that driving style is not the only factor influencing the range anxiety threshold, this embodiment includes a parameter. This represents the coefficient of influence of driving style on the range anxiety threshold; in this embodiment, Accordingly, this embodiment also includes a parameter. This represents the influence coefficient of charging station distribution density on the range anxiety threshold; in this embodiment, . Z This indicates the distribution density of candidate charging stations;Z 0 represents the distribution density of the baseline charging stations. Z and Z The difference of 0 multiplied by The corresponding weights can precisely reflect the degree to which the difference in the distribution density of charging stations in different scenarios affects users' charging decisions.

[0067] It should be noted that, in this embodiment, S , and The parameters are not fixed, but are evaluated by the historical charging behavior data of each driver. That is, the charging preference characteristics of drivers are extracted from the collected historical charging behavior data, and the driving style or driving experience factors, the degree of trust in driving experience, and the sensitivity to the distribution density of charging stations are obtained. In this way, the range anxiety threshold of different drivers in different driving scenarios can be calculated.

[0068] In practical applications, data such as the remaining mileage of the electric vehicle, selected charging station, charging time, charging cost, vehicle location relative to each candidate charging station, and the density of candidate charging stations can be collected for each historical charging behavior of a user. This data is then recorded as the user's historical driving behavior data. Next, a comprehensive analysis is conducted based on the user's historical charging behavior data, considering factors such as driving style and the degree to which driving style and charging station density influence the user's charging behavior decisions, and the data is updated accordingly. S , and The specific values ​​for the three parameters. For example, if a user's historical charging behavior data shows that they always charge when the battery is almost depleted, it indicates that the user... S The value is closer to 1. If a user consistently charges when their remaining battery is higher in an area with a low density of charging stations, it indicates that their corresponding... The value is larger.

[0069] In summary, the range anxiety threshold constructed in this embodiment... L This effectively allows for a precise depiction of the user's behavioral patterns each time they make a charging decision. Therefore, incorporating this parameter into recommendations for each user's charging behavior will make the recommendations more aligned with the user's charging preferences.

[0070] II. Providing recommendation results based on acquired data and known user profiles.

[0071] 2.1. Collect the status information of the vehicle currently being driven by the user and the operational data of all charging stations.

[0072] In this embodiment, the essence of implementing the charging station recommendation service is to match all charging stations currently accessible to the user with the user's current vehicle, then select several charging stations most suitable for the current vehicle, and recommend them to the user. To achieve this matching between charging stations and users, this embodiment first needs to determine the relevant attributes of the vehicle and charging stations, namely the vehicle's status information and the charging station's operational data. Then, the degree of matching between the two is quantified according to specified evaluation indicators.

[0073] Specifically, in this embodiment, the vehicle's status information includes: real-time location information, current driving range, and total driving range. D Power consumption per kilometer e And any candidate charging station i The operational data includes: charging station locations and the number of charging piles. n i Crowding level β i Charging rates m i and charging power W i .

[0074] For example, the location information of the vehicle and the charging station determines the distance between them, and users generally prefer to choose the nearest charging station. Current driving range and energy consumption per kilometer. e This determines the accessibility between each charging station and the vehicle; a vehicle can only receive charging services if it can reach the charging station. The number of charging stations... n i Crowding level β i and charging power W i This will affect the user experience at each charging station, and the charging fee rate... m i This will affect the payment cost of the charging services that users enjoy.

[0075] 2.2 When a user submits a charging request, the system combines the vehicle's driving range and location to select nearby charging stations as candidate charging stations, forming a candidate station set. I .

[0076] In this embodiment, the technical personnel believe that a user's ability to drive their vehicle to a charging station is a prerequisite for them to choose that charging station and accept the charging service. Given other options, users generally would not accept having their vehicle run out of power before reaching the charging station and then having to pay extra for a tow truck to take their vehicle there. Therefore, to reduce the amount of data processing involved in the recommendation process, the solution provided in this embodiment calculates the accessibility of the vehicle to various charging stations each time a user submits a charging request, based on the vehicle's status information and the charging station's operational data. It then selects the most suitable charging station from among the accessible charging stations listed as candidates.

[0077] In this embodiment, the criterion for determining whether any charging station is reachable is that the vehicle's driving range is greater than the distance traveled between the vehicle's real-time location and the location of the charging station. Note: The distance traveled here refers to the shortest path along municipal roads between the two locations, not the geographical straight-line distance.

[0078] 2.3. Evaluate the decision-making cost for users to choose each candidate charging station, and rank each charging station according to the probability of selection.

[0079] In this embodiment, electric vehicle drivers typically consider two types of attributes when choosing a charging station: decision attributes and solution attributes. The decision attribute is the remaining mileage, and the solution attribute is the charging cost. The charging cost, in a broad sense, usually encompasses multiple aspects that cannot be precisely calculated. To more accurately assess the differences in charging costs corresponding to different charging station choices, this embodiment divides the charging cost into three levels: first, the charging fee paid by the user; second, the time cost of completing the charging action, mainly including the user's charging time and the waiting time after arriving at the charging station; and third, the user experience brought by different charging station choices, mainly manifested in the difference in the user's anxiety level when choosing different charging stations. Based on the above three points, this embodiment defines each of the three as payment costs. C b Parking time cost C t Range anxiety costs C h The cost of any single charging action. C b Parking time cost C t and the cost of range anxiety C h The calculation method is as follows:

[0080] (2.3.1) Payment Costs C b

[0081] Users typically choose to fully charge their vehicle each time they charge before leaving the charging station. Therefore, this embodiment will include the total driving range. D Electric vehicles arrive at charging stations i Remaining mileage D i The difference, multiplied by the power consumption per kilometer e Calculate the total amount of electricity needed for charging, then multiply by the number of charging stations. i Unit charging price m i Get out of the charging station i Payment costs C b The calculation formula is as follows:

[0082] .

[0083] (2.3.2) Parking time cost C t

[0084] In payment costs C b Based on this, and considering that drivers are influenced not only by charging costs but also by charging time when choosing a charging station, parking time costs are introduced. C t Parking time cost C t Firstly, this includes electric vehicles at charging stations. i Actual charging time cost C r It also takes into account the psychological cost of waiting in line for drivers due to the perceived congestion of charging stations provided by the system. C l Specifically, this embodiment will include the total driving range. D Electric vehicles arrive at charging stations i Remaining mileage D i The difference multiplied by the power consumption per kilometer e Calculate the amount of electricity required to charge the electric vehicle. Then divide the amount of electricity by the number of charging stations. i charging power W i Obtain the actual charging time, then multiply the actual charging time by the value of the driver's unit travel time. TC To obtain the actual charging time cost C r Furthermore, this embodiment is based on the charging station. i level of congestion β i Multiplied by charging station i Number of charging stationsn i Calculations of driver's charging station i The expected number of vehicles in the queue. Assuming these vehicles require charging distances equal to their total driving range. D Multiply the number of vehicles in the queue by the charging distance, and then multiply by the power consumption per kilometer. e Obtain the total charging amount of the vehicles in the queue. Divide the total charging amount by the charging power. W i Multiply by the value of the driver's unit travel time. TC To obtain the driver's expected waiting time cost in the queue C l Therefore, parking time cost C t The calculation formula is as follows:

[0085] ,

[0086] In this embodiment, β i Charging stations displayed in the navigation system i The congestion level is displayed according to the navigation system's "red, yellow, and green" congestion levels. This embodiment categorizes charging station congestion feedback into three levels: busy, moderate, and idle, each corresponding to a different color. A busy state typically refers to a charging station with queuing vehicles reaching 50% of the number of charging piles; a moderate state typically refers to a charging station with... i The number of vehicles queuing for charging stations reaches 20-50% of the number of charging stations; idle status usually refers to the charging station i The number of vehicles queuing is less than 20% of the number of charging stations. When the navigation system directs the vehicle to a charging station... i When the state is classified as busy, then... β i =0.5. When the navigation system will take you to the charging station i When the level of congestion is classified as moderate, let β i =0.35. When the navigation system will take you to the charging station... i When the state is divided into idle, let β i =0.

[0087] In this embodiment, the value of a driver's unit travel time is taken into account. TC This is primarily influenced by the user's income level and travel purpose. In the same driving scenario, the value of each unit of travel time varies among different drivers due to differences in their individual income levels. TC It will also differ. For example, the higher a user's income level, the higher the value of their unit travel time, and vice versa. Furthermore, the value of the same driver's unit travel time will vary depending on the driving scenario and the purpose of their trip. TC This will also change. For example, the value per unit of time for recreational travel will be lower than that for commuting, and far lower than that for emergency travel.

[0088] The value of a unit travel time is constructed by taking into account the two key factors mentioned above. TC The mathematical model. The previous text has already introduced the model based on the driver's daily income. R Daily working hours H Japanese commute time T w Based on the method for calculating a user's hourly wage, this embodiment further constructs a travel urgency coefficient by combining the user's travel purpose. This coefficient is then used to adjust the value of a driver's unit travel time. TC Value:

[0089]

[0090] In the practical application of this embodiment, the urgency coefficient for commuting can be set to 1, the urgency coefficient for recreational travel can be set to 0.7, and the urgency coefficient for emergency travel can be set to 1.5.

[0091] (2.3.3) Cost of mileage anxiety C h

[0092] Every electric vehicle driver experiences a range anxiety threshold during their journey. L To describe a driver's range anxiety, this embodiment introduces a range anxiety cost. C h The larger the value of this parameter, the greater the driver's range anxiety, and the more they want to charge as soon as possible to alleviate travel risks.

[0093] For quantification C h The value that the technicians in this embodiment first thought of was: when the electric vehicle has remaining range x Greater than the range anxiety threshold L At that time, the driver's range anxiety was always 0; when the electric vehicle had remaining range x Less than L At that time, with x As the remaining mileage gradually decreases, the driver's range anxiety rises rapidly. x When the driver's range anxiety reaches zero, the electric vehicle can no longer continue driving, resulting in towing costs. This cost represents the maximum range anxiety cost at which the driver's range anxiety peaks, and is denoted as [value missing]. C pTo ensure that the maximum anxiety level reached when the remaining mileage is 0 remains unchanged, this embodiment chooses to use a power function to describe mileage anxiety, thereby constructing a power function that characterizes the degree of change in the current user's mileage anxiety. F ( x ):

[0094] ,

[0095] In the above formula, α is a preset power parameter.

[0096] Building upon this, the technicians in this embodiment further considered that during driving, as the remaining range of the electric vehicle continuously decreases, the driver's range anxiety continuously increases. Therefore, the remaining range is adjusted based on the range anxiety threshold. L Reduce to D i Integrating the mileage anxiety function yields the driver's cumulative anxiety value as the remaining mileage changes. This is then multiplied by the unit mileage anxiety cost. C n This allows us to calculate the cost of driver range anxiety.

[0097] Thus, this embodiment yields the cost of range anxiety. C h The calculation formula is as follows:

[0098] ,

[0099] In the above formula, x This indicates the driving range of an electric vehicle. C n This represents the unit mileage anxiety cost, which can be expressed as the maximum mileage anxiety cost. C p This is calculated by dividing by a preset total range anxiety value. In practical applications, the maximum range anxiety cost is... C p The corresponding towing fee can also be calculated in detail based on the type of road in the actual scenario (urban roads, rural roads, and highways).

[0100] (2.3.4) Charging efficiency U i With choice probability P i

[0101] The recommendation problem for charging stations is a typical discrete choice model. Based on stochastic utility theory, this embodiment will use charging stations... i Total charging cost C iAs a utility metric, it is used to evaluate the probability of a user choosing each charging option. A multinomial Logit model is constructed to describe the charging choice behavior of electric vehicle drivers. Generally speaking, rational users will consider the generalized total cost of charging when choosing a charging station. C i Costs to be paid soon C b Parking time cost C t Range anxiety costs C h All of these are taken into account.

[0102] In addition, considering the cost of range anxiety C h This typically only exists when the user anticipates that the vehicle may not be able to reach a charging station. Therefore, this embodiment further adjusts the total charging cost based on different scenarios. C i The calculation methods are divided into the following two types: (1) When the electric vehicle arrives at the charging station i Remaining mileage D i Greater than the range anxiety threshold L If the driver is confident of reaching their destination, it indicates that they are not experiencing range anxiety during the journey. In this case, the total charging cost of choosing this charging station is... C i Only include C b and C t (2) When the electric vehicle arrives at the charging station i Remaining mileage D i Less than the range anxiety threshold L If the driver experiences range anxiety (doubt about reaching the destination) during the journey, it indicates that they are experiencing range anxiety. In this case, the total charging cost of choosing this charging station will be... C i include C b , C t and C h . That is:

[0103] ,

[0104] Based on this, charging efficiency U i The calculation formula is as follows:

[0105] ,

[0106] In the above formula, The number of sites in the candidate site set; D i This indicates that the current user's vehicle has reached the [number]th [location]. i Remaining range at each charging station; C i Indicates the current user's vehicle is in the [number]th position. i The total cost of charging at each charging station.

[0107] Based on this, assuming the utility random term follows a Gumbel distribution, in any driving scenario, the choice probability function has two cases: when the electric vehicle reaches the... i Remaining range at each charging station D i A value greater than 0 indicates that the charging station is a possible selection, thus a multinomial logit model is used to calculate the selection probability. Otherwise, when the remaining mileage... D i When the value is less than 0, electric vehicles cannot reach charging stations. i If the probability of it being selected is 0, then this embodiment uses the following formula... U i Calculate the probability of selection P i :

[0108] ,

[0109] In the above formula, This indicates the driver's perception of the effectiveness of charging.

[0110] Of course, since this case has already excluded [certain] candidate charging stations during the screening process mentioned earlier. D i Since the value is less than 0, in practical applications, this embodiment only calculates the values ​​of each candidate charging station ( The probability of choosing ).

[0111] (2.3.5) Generation of the recommendation list

[0112] In this embodiment, each candidate charging station can be classified according to... P i The charging stations are sorted from highest to lowest quality, and the resulting recommendation list is returned to the user. This recommendation list can actually reflect the charging efficiency of each candidate charging station. U i Therefore, it better meets the preferences of users who require lower overall charging costs.

[0113] Considering charging efficiency U i The calculation process also realizes the calculation of payment costs. C b Parking time costC t and the cost of range anxiety C h The three individual costs are quantified. Therefore, this embodiment can also categorize the generated recommendation list by... C b , C t and C h The candidate charging stations are sorted from lowest to highest quality to obtain three additional recommendation lists, which are then returned to the user. These three recommendation lists can meet the needs of users who place greater emphasis on economic cost, time cost, and user experience.

[0114] In the practical application of this embodiment, electric vehicle drivers can pre-provide their location, destination, and travel purpose through the driver terminal. The system then calculates the probability of the driver selecting each charging station based on their charging preferences, recommends the charging station with the highest probability to the driver on the terminal, and provides a list of recommended charging stations. After the driver finally selects a charging station from the recommended list on the terminal, a new historical charging behavior record is generated. This allows for the system to profile the user's current charging station selection behavior pattern and assess the user's range anxiety threshold. L Update the system to improve its adaptability.

[0115] Example 2

[0116] Based on the solution in Embodiment 1, this embodiment further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the electric vehicle charging station recommendation method based on driver charging preferences as in Embodiment 1, and then generates a recommended list of candidate charging stations that match the user's preferences based on the user's current vehicle status and the operation data of surrounding charging stations, and returns it to the user.

[0117] This embodiment also provides a storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the electric vehicle charging station recommendation method based on driver charging preferences as described in Embodiment 1. Then, based on the user's current vehicle status and the operation data of surrounding charging stations, it generates a recommended list of candidate charging stations that match the user's preferences and returns it to the user.

[0118] This embodiment also provides a data processing device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the computer program is executed by the processor, it implements the steps of the electric vehicle charging station recommendation method based on driver charging preferences as in Embodiment 1, and then generates a recommended list of candidate charging stations that match the user's preferences based on the user's current vehicle status and the operation data of surrounding charging stations, and returns it to the user.

[0119] This data processing device is essentially a computer device. In practical applications, it can be embedded and deployed within the vehicle's infotainment system to support data processing and interaction. Alternatively, it can be used as a standalone computer device, for example, integrated into the computer equipment of the backend data center connected to the vehicle's infotainment system, thus enabling the aforementioned processes during interaction between the vehicle and the backend data center. The non-embedded computer equipment used in the backend data center can be medium to large-sized computer equipment such as laptops, tablets, desktop computers, or rack servers, blade servers, tower servers, or cabinet servers (including standalone servers or server clusters composed of multiple servers) capable of executing computer programs.

[0120] Specifically, the computer device in this embodiment includes, but is not limited to, a memory and a processor that can be interconnected via a system bus. In this embodiment, the memory (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory can be an internal storage unit of the computer device, such as the hard disk or RAM of the computer device. In other embodiments, the memory can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Of course, the memory can also include both internal storage units and external storage devices of the computer device. In this embodiment, the memory is typically used to store the operating system and various application software installed on the computer device. Furthermore, the memory can also be used to temporarily store various types of data that have been output or will be output.

[0121] In some embodiments, the processor may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor is typically used to control the overall operation of a computer device.

[0122] Figure 2 The figure provides a typical interactive interface that the data processing device of this embodiment can adopt in practical applications. As shown in the figure, on interface 1, the user can submit a charging request and input their location (which can also be actively obtained by the device), destination, and travel purpose, and set their preferences for overall utility, payment cost, time cost, and user experience when selecting a charging station. On interface 2, the system can intuitively present the current location, destination, and the spatial distribution of various candidate charging stations. On interface 3, the system can display the geographical location, charging price, congestion level, and charging power of each charging station according to the user's instructions. On interface 4, the system can simultaneously display the ranking results of various best charging stations corresponding to different user preferences. On interface 5, the system can calculate the best charging station selected according to the user's specified preferences and display the geographical location, charging price, congestion level, and charging power of the charging station in real time.

[0123] Performance testing

[0124] To verify the performance of the present invention, technicians developed an experimental plan and conducted simulation tests on the relevant solutions.

[0125] I. Solution Verification

[0126] 1. Experimental Scenario

[0127] This experiment uses Figure 3 Using the road network as the research scenario, when the driver has 100km of remaining range, they can choose any one of the four candidate charging stations (1-4) to charge the car to ensure the normal operation of the electric vehicle.

[0128] In this research scenario, the driver sends their location, destination, travel purpose, and desired charging station characteristics to the backend system via their terminal. The backend system then calculates the probability of the driver selecting each charging station according to the following steps. In this scenario, the initial settings for each parameter are: total vehicle range... D =250km, initial remaining distance D 0 = 100km, power consumption per kilometer e =0.15kWh / km (based on the national average electricity consumption per kilometer for electric vehicles), the unit charging price at charging stations. m=0.8 yuan / kWh (based on State Grid charging station fee details), rescue towing cost C p =500 yuan (based on the national average towing cost of passenger cars), charging power of the charging station W =60kW (based on the commonly used power of electric vehicle charging stations), the driver's range anxiety threshold L =50km, value of driver's unit travel time TC =38 yuan / hour (based on the average salary level in a certain area), range anxiety function power parameter α=-2, driver perception level =0.8, the degree of congestion at charging stations β =0.

[0129] 2. Evaluation and Analysis

[0130] This experiment used the method in Example 1 to calculate the remaining mileage of the vehicle after reaching four charging stations. D i Payment costs C b Parking time cost C t Range anxiety costs C h Total charging cost C i Charging efficiency U i and choice probability P i The following tables show the results:

[0131] Table 1: Calculation results of various evaluation indicators for users selecting different charging stations

[0132]

[0133] 3. Generation of the recommendation list

[0134] Based on the data in the table above, this experiment shows that the charging station with the highest selection probability based on charging utility is charging station 3, the optimal charging station based on payment cost is charging station 3, the optimal charging station based on parking time cost is charging station 3, and the optimal charging station based on range anxiety cost is either charging station 1 or 3.

[0135] II. Sensitivity Analysis of Core Parameters in the Scheme

[0136] This experiment focuses on six key parameters that influence the probability of a user choosing various charging stations using the method of this invention (including: value per unit travel time). TC Charging power W Crowding level βMaximum range anxiety cost C p Range anxiety threshold L and remaining mileage D i Sensitivity analysis was conducted. During the analysis, the values ​​of parameters such as remaining mileage, maximum mileage anxiety cost (i.e., towing cost), charging power, mileage anxiety threshold, value of time per unit of trip, and charging station congestion were adjusted sequentially. The impact of these parameter changes on drivers' charging preferences was observed, and the results are as follows: Figures 4-9 As shown.

[0137] Analyzing the data in the graph reveals the following patterns:

[0138] (1) Remaining mileage has the greatest impact. The less the remaining mileage, the more the driver wants to charge sooner and the more likely they are to choose a nearby charging station; the more the remaining mileage, the less the driver's range anxiety and the more inclined they are to delay charging.

[0139] (2) Range anxiety thresholds for different drivers L Unlike conservative drivers, L (Higher) prefers to charge promptly to avoid risks; aggressive drivers ( L (Smaller) tends to charge to the maximum when the battery is low enough to reduce the number of times it needs to be charged.

[0140] (3) Drivers’ behavior varies in different scenarios. The higher the maximum range anxiety cost, the earlier drivers will charge to reduce risk. For example, in urban areas, towing costs are low, so drivers are less likely to experience range anxiety and will generally delay charging; however, on highways, towing costs are extremely high, so drivers’ range anxiety will rise rapidly and they will generally charge earlier.

[0141] (4) The higher the charging power of the charging station, the shorter the charging time. The time cost of rescue towing caused by the depletion of power is much higher than the actual charging time cost. Therefore, drivers tend to charge in advance to avoid risks.

[0142] (5) When the charging station is moderately or busy, drivers may delay charging because they are waiting for the congestion to clear.

[0143] (6) The value of a unit of travel time will make drivers have a slight tendency to delay charging, but the degree is very small and hardly changes.

[0144] Based on the combined effects of all the above factors, it can be demonstrated that in the solution provided by this invention, electric vehicle drivers tend to choose charging stations with higher charging power, lower congestion, and closer distance when the remaining mileage drops to their own mileage anxiety threshold; this also happens to match the actual needs of users.

[0145] The above-described embodiments are merely one implementation of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the inventive concept, and these all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A method for recommending electric vehicle charging stations based on driver charging preferences, characterized in that, It includes: Collect personal information and historical charging behavior data that characterize the user's current income level, and update the user's range anxiety threshold accordingly. L ; Range anxiety threshold for any user L The update formula is as follows: ， In the above formula, This represents the percentage of the base range anxiety threshold relative to the total driving range. =0.2; S This represents a quantitative value indicating the driver's driving style. This represents the coefficient indicating the influence of driving style on the range anxiety threshold. This represents the coefficient representing the influence of charging station distribution density on the range anxiety threshold. Z This indicates the distribution density of candidate charging stations; Z 0 indicates the distribution density of benchmark charging stations; S , and The value is obtained by evaluating the user's historical charging behavior data. Represents a conservative type of driver. Represents an aggressive type of driver; ; ; D This indicates the total driving range of the vehicle currently being driven by the user; The system collects the current vehicle status information and operational data from all charging stations. When a user requests charging, it first considers the vehicle's range and location to identify nearby charging stations as candidate stations, thus creating a candidate station set. I ; The following formula combines collected information with the current user's range anxiety threshold. L Calculate the user's arrival at any candidate charging station i Payment costs C b Parking time cost C t Range anxiety costs C h and charging efficiency U i : ， In the above formula, The number of sites in the candidate site set; D i This indicates that the current user's vehicle has reached the [number]th [location]. i Remaining range at each charging station; C i Indicates the current user's vehicle is in the [number]th position. i The total charging cost of a single charging station; According to the following formula U i Calculate the probability of selection P i : ， In the above formula, This indicates the driver's perceived efficiency of charging. Based on user preferences, the candidate charging stations were categorized as follows: P i From high to low and by C b , C t and C h Sort the recommendations from lowest to highest quality and return the resulting list to the user. Among them, the range anxiety cost of arbitrary charging behavior C h The calculation formula is as follows: ， In the above formula, x This indicates the driving range of an electric vehicle. This is a preset power parameter; C n This represents the unit range anxiety cost; it is composed of the maximum range anxiety cost. C p Dividing by the preset total range anxiety value, we get, among which, D i The towing cost incurred after resetting the trip to zero is the maximum mileage anxiety cost for the current journey. C p .

2. The electric vehicle charging station recommendation method based on driver charging preferences according to claim 1, characterized in that: The personal information includes: the driver's daily income. R Daily working hours H Japanese commute time T w ; The historical charging behavior data includes: the remaining mileage of the electric vehicle, the selected charging station, the charging time, the charging cost, the location of the vehicle and each candidate charging station, and the distribution density of the candidate charging stations for each historical charging behavior of the user. The vehicle's status information includes: real-time location information, current driving range, and total driving range. D Power consumption per kilometer e ; Any candidate charging station i The operational data includes: charging station locations and the number of charging piles. n i Crowding level β i Charging rates m i and charging power W i .

3. The electric vehicle charging station recommendation method based on driver charging preferences according to claim 2, characterized in that: Payment costs for any charging activity C b The calculation formula is as follows: 。 4. The electric vehicle charging station recommendation method based on driver charging preferences according to claim 3, characterized in that, Time cost of any charging action C t The calculation formula is as follows: ， In the above formula, C r Indicates that the vehicle is at a candidate charging station i Actual charging time cost; C l This represents the psychologically estimated waiting time cost generated based on the congestion level of candidate charging stations; TC This represents the value of a user's unit of travel time. and / or The operating status of charging stations is divided into three categories: busy, moderate, and idle, corresponding to the degree of congestion. β i The values ​​are 0.5, 0.35 and 0, respectively.

5. The electric vehicle charging station recommendation method based on driver charging preferences according to claim 1, characterized in that: Current user's unit travel time value TC The calculation formula is as follows: ， In the above formula, This represents the travel urgency coefficient obtained based on the user's current travel purpose; and / or When the purpose of travel is work commuting, entertainment, and urgent tasks, the corresponding urgency coefficients are: The values ​​are 1, 0.7 and 1.5 respectively.

6. A computer program product comprising a computer program, characterized in that: When the computer program is executed by the processor, it implements the steps of the electric vehicle charging station recommendation method based on driver charging preferences as described in any one of claims 1-5, and then generates a recommended list of candidate charging stations that match the user's preferences based on the user's current vehicle status and the operation data of surrounding charging stations, and returns it to the user.

7. A storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements the steps of the electric vehicle charging station recommendation method based on driver charging preferences as described in any one of claims 1-5, and then generates a recommended list of candidate charging stations that match the user's preferences based on the user's current vehicle status and the operation data of surrounding charging stations, and returns it to the user.

8. A data processing apparatus comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the computer program is executed by the processor, it implements the steps of the electric vehicle charging station recommendation method based on driver charging preferences as described in any one of claims 1-5, and then generates a recommended list of candidate charging stations that match the user's preferences based on the user's current vehicle status and the operation data of surrounding charging stations, and returns it to the user.

Images