Battery replacement scheduling method and device of shared electric vehicle, electronic equipment and medium
By obtaining and analyzing power and usage data in the shared electric vehicle system, calculating the probability of car selection and performing battery swap dispatch, the problem of abandonment caused by insufficient power is solved, scheduling costs are reduced, and the user experience is improved.
Patent Information
- Application Number
- CN202411255293.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2025-01-10
AI Technical Summary
The power of shared electric vehicles is not enough to meet user needs, which leads to users abandoning their cars, reducing the vehicle experience and increasing the scheduling cost.
By obtaining the electricity list of electric vehicles with electricity in the target area, mapping it into mileage distribution information, and determining the mileage distribution information of vehicle users based on historical usage data, and calculating the selection probability of the user selecting a vehicle that does not meet the mileage requirements in a random situation. When the probability exceeds the preset threshold, the battery swap dispatch is performed.
It effectively reduces the situation where users abandon their cars, reduces the scheduling costs caused by parking at non-parking stations, and improves the user's vehicle experience.
Smart Images
Figure CN119294714A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of shared vehicles, and in particular to a method, device, electronic equipment and medium for scheduling battery replacement of shared electric vehicles. Background Art
[0002] Currently, the dispatching scheme for shared bicycles is relatively mature, while the dispatching scheme for shared electric vehicles is more complicated than that for shared bicycles due to the issue of battery power. The traditional dispatching scheme for shared bicycles is mainly based on the demand for vehicles and the estimated destination of the vehicles. For areas with sufficient vehicle supply, dispatching is generally not carried out unless there is a backlog of vehicles.
[0003] Due to the power factor, when calculating the statistics, it is necessary to dispatch the shared electric vehicles according to whether the vehicles have power. However, in the actual operation process, it is found that when the power of the shared electric vehicles is not enough for users to maintain the required journey, users are prone to abandon the vehicles. On the one hand, the user's vehicle experience is poor, and on the other hand, not parking at the parking station will increase the dispatch cost of the vehicle. Summary of the invention
[0004] The present application provides a battery replacement scheduling method, device, electronic device and medium for a shared electric vehicle, which are used to solve the current problem that when the power of a shared electric vehicle is not enough for the user to maintain the required journey, it is easy for the user to abandon the vehicle, etc., so as to improve the user's vehicle usage experience and reduce the vehicle scheduling cost.
[0005] The present application provides a method for scheduling battery replacement of shared electric vehicles, the method comprising: if the number of powered shared electric vehicles in a target area is greater than a preset number threshold, obtaining a list of power levels of powered shared electric vehicles in the target area; the target area is an area where powered shared electric vehicles meet user usage needs within a future preset time period; mapping the list of power levels into first mileage distribution information; determining second mileage distribution information of vehicle users within the future preset time period based on historical usage data of shared electric vehicles in the target area; determining, based on the first mileage distribution information and the second mileage distribution information, a probability of a vehicle user selecting a powered shared electric vehicle that does not meet the mileage requirements under random circumstances; and scheduling battery replacement for powered shared electric vehicles in the target area when the selection probability is greater than a preset probability threshold.
[0006] According to a battery replacement scheduling method for shared electric vehicles provided in the present application, the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirements in a random situation is determined based on the first mileage distribution information and the second mileage distribution information, including: determining a first distribution probability corresponding to each mileage interval in the first mileage distribution information; determining a second distribution probability corresponding to each mileage interval in the second mileage distribution information; based on each first distribution probability and each second distribution probability, determining the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirements in a random situation.
[0007] According to a battery replacement scheduling method for shared electric vehicles provided in the present application, the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirement under random circumstances is determined based on each first distribution probability and each second distribution probability, including: determining, according to each first distribution probability, the first probability that a car user corresponding to each mileage interval selects an electric shared electric vehicle that does not meet the mileage requirement under random circumstances; determining, according to each first probability and each second distribution probability, the selection probability that a car user selects an electric shared electric vehicle that does not meet the mileage requirement under random circumstances.
[0008] According to a battery replacement scheduling method for shared electric vehicles provided in the present application, the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirements under random circumstances is determined based on each first probability and each second distribution probability, including: for each mileage interval, multiplying the first probability by the second distribution probability to obtain the probability product of the corresponding mileage interval; adding each probability product, and determining the result of the addition operation as the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirements under random circumstances.
[0009] According to a battery replacement scheduling method for shared electric vehicles provided in the present application, before adding each probability product, it also includes: obtaining a weight coefficient for each mileage interval respectively; adjusting the corresponding probability product according to the weight coefficient for each mileage interval respectively, to obtain each adjusted probability product.
[0010] According to a battery replacement scheduling method for shared electric vehicles provided in the present application, the preset probability threshold is determined by the following steps: based on the historical parking information of shared electric vehicles, determining the proportion of parking at non-parking sites when the vehicle power does not meet the needs of vehicle users; determining the additional cost based on the proportion, the usage of shared electric vehicles in the historical parking information, the preset probability that vehicle users select vehicles that do not meet the needs, the average scheduling cost of vehicles parked at non-parking sites, and the average amount of cancellation losses for vehicles parked at non-parking sites; determining the scheduling cost based on the proportion, the usage of shared electric vehicles in the historical parking information, the preset probability that vehicle users select vehicles that do not meet the needs, and the average scheduling cost of vehicles parked at parking sites; determining the preset probability when the additional cost is the same as the scheduling cost as the preset probability threshold.
[0011] According to a battery replacement scheduling method for shared electric vehicles provided in the present application, the additional cost is determined based on the ratio, the usage of shared electric vehicles in the historical parking information, the preset probability that the vehicle user selects a vehicle that does not meet the demand, the average scheduling cost of vehicles parked at non-parking sites, and the average amount of cancellation losses for vehicles parked at non-parking sites, including: determining a first cost based on the ratio, the usage of shared electric vehicles in the historical parking information, the preset probability that the vehicle user selects a vehicle that does not meet the demand, and the average scheduling cost of vehicles parked at non-parking sites; determining a second cost based on the ratio, the usage of shared electric vehicles in the historical parking information, the preset probability that the vehicle user selects a vehicle that does not meet the demand, and the average amount of cancellation losses for vehicles parked at non-parking sites; and determining the sum of the first cost and the second cost as the additional cost.
[0012] The present application also provides a battery replacement scheduling device for shared electric vehicles, including: an acquisition module, used to obtain a power list of powered shared electric vehicles in a target area if the number of powered shared electric vehicles in the target area is greater than a preset number threshold; the target area is an area where powered shared electric vehicles meet user usage needs within a future preset time period; a mapping module, used to map the power list into first mileage distribution information; a first determination module, used to determine second mileage distribution information of vehicle users within the future preset time period based on historical usage data of shared electric vehicles in the target area; a second determination module, used to determine, under random circumstances, the probability of a vehicle user selecting a powered shared electric vehicle that does not meet the mileage requirements based on the first mileage distribution information and the second mileage distribution information; a scheduling module, used to schedule battery replacement for powered shared electric vehicles in the target area when the selection probability is greater than a preset probability threshold.
[0013] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the battery replacement scheduling method for a shared electric vehicle as described in any one of the above-mentioned methods is implemented.
[0014] The present application also provides a medium, which is a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the battery replacement scheduling method for a shared electric vehicle as described in any one of the above-mentioned methods is implemented.
[0015] The battery replacement scheduling method, device, electronic device and medium of shared electric vehicles provided in the present application, for a target area where electric shared electric vehicles can meet the user's usage needs within a preset time period in the future, when the number of electric shared electric vehicles in the target area is greater than a preset number threshold, a list of electric power of the electric shared electric vehicles in the target area is obtained, and the list of electric power is further mapped into first mileage distribution information; and, based on the historical usage data of the shared electric vehicles in the target area, second mileage distribution information of the car users within the preset time period in the future is determined; and then, based on the first mileage distribution information and the second mileage distribution information, the selection probability of the car user selecting an electric shared electric vehicle that does not meet the mileage requirement under random circumstances can be determined; thereby, when the selection probability is greater than the preset probability threshold, the electric shared electric vehicles in the target area can be scheduled for battery replacement, which can reduce the probability of the car user selecting an electric shared electric vehicle that does not meet the mileage requirement, effectively reduce the occurrence of users abandoning their vehicles during use, and thus reduce the cost of dispatching vehicles parked at non-parking sites. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0017] Figure 1 It is a flow chart of the battery replacement scheduling method for shared electric vehicles provided in this application.
[0018] Figure 2 It is a structural schematic diagram of the electronic device provided by this application. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0020] It should be noted that in the description of the present application, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For those skilled in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.
[0021] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0022] Combine the following Figure 1-Figure 2 The present invention describes the battery replacement scheduling method, device, electronic equipment and medium for shared electric vehicles.
[0023] Figure 1 It is a flow chart of the battery replacement scheduling method for shared electric vehicles provided in this application, such as Figure 1As shown, the method includes the following steps 100 to 500.
[0024] Step 100: If the number of powered shared electric vehicles in the target area is greater than a preset number threshold, a list of the power levels of powered shared electric vehicles in the target area is obtained; the target area is an area where powered shared electric vehicles can meet user usage needs within a preset time period in the future.
[0025] Step 200: Map the power list to first mileage distribution information.
[0026] Step 300: Determine the second mileage distribution information of the vehicle users within a future preset time period based on the historical usage data of the shared electric vehicles in the target area.
[0027] Step 400: Determine, based on the first mileage distribution information and the second mileage distribution information, the probability of a user selecting a shared electric vehicle that does not meet the mileage requirement in a random situation.
[0028] Step 500: When the selection probability is greater than a preset probability threshold, battery replacement scheduling is performed for the shared electric vehicles in the target area.
[0029] It should be noted that the execution subject of the battery replacement scheduling method for shared electric vehicles provided in the embodiment of the present application may be a server, a computer device, etc., wherein the computer device may be, for example, a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The present application may be illustrated by taking the execution subject as a server, but the execution subject of the battery replacement scheduling method for shared electric vehicles of the present application is not limited to only a server.
[0030] It is understandable that the present application can predict the use demand (specifically, the demand ratio or the specific demand amount) of shared electric vehicles in a specified area or site (such as streets, communities, etc.) in the future within a specified time period according to actual demand in advance for the specified area or site. When predicting the use demand of shared electric vehicles, the prediction can be made based on a pre-trained time series prediction model or by other existing methods, and the present application does not limit the specific method.
[0031] Furthermore, the number of shared electric vehicles currently powered in the area or station can be obtained, and the data can be collected and provided by the operator or manager of the shared electric vehicles. It is understandable that the shared electric vehicles powered in the statistical area or station generally refer to shared electric vehicles under the same brand or operator.
[0032] It should be noted that since the present application takes into account the possible behavior of users abandoning their vehicles, such problems will not arise for shared electric vehicles that are out of power. If a user scans a shared electric vehicle that is out of power, it may only lead to a poor user experience and will not result in the situation where the vehicle runs out of power during a ride. Therefore, the present application scheme does not consider shared electric vehicles that are not allowed to be used because they are out of power.
[0033] Furthermore, the present application can match the predicted usage demand of each area or site within a future preset time period with the number of shared electric vehicles currently powered by the area or site, thereby determining whether the shared electric vehicles with power in the area or site can meet user usage needs within the future preset time period.
[0034] Furthermore, the area where electric shared electric vehicles can meet the user's usage needs within a preset time period in the future or the area corresponding to the station can be defined as the target area.
[0035] Based on this, the subsequent process of this application can be carried out separately for each target area.
[0036] A quantity threshold value pre-set according to the actual demand of the target area is obtained, and the number of shared electric vehicles with power in the area is compared with the preset quantity threshold value.
[0037] If it is determined that the number of shared electric vehicles in the area is less than or equal to the preset number threshold, the subsequent process of this application will not be executed, and the process can be directly ended or other scheduling strategies can be executed, which is not specifically limited in this application.
[0038] If it is determined that the number of shared electric vehicles with power in the area is greater than a preset threshold, a list of the power levels of shared electric vehicles with power in the area can be obtained, which can be specifically obtained from the brand or operator after authorization.
[0039] Furthermore, the power list can be mapped to the first mileage distribution information. For example, the overall power can be divided into multiple intervals according to multiple different power values. It should be noted that each power can be converted into a corresponding mileage, so the interval formed by the power value can be converted to obtain multiple corresponding mileage intervals.
[0040] Therefore, the power of each shared electric vehicle in the power list can be converted into the corresponding mileage, and the distribution information of each mileage in each mileage interval can be determined and used as the first mileage distribution information.
[0041] At the same time, the present application can obtain the historical usage data of the shared electric vehicles in the target area, wherein the historical usage data can specifically be the usage of the shared electric vehicles and the mileage of each shared electric vehicle used.
[0042] Therefore, the number of users (i.e., the number of shared electric vehicles used) and the mileage of shared electric vehicles used in the target area in the future preset time period can be predicted based on the historical usage data of shared electric vehicles in the target area, and the second mileage distribution information can be further formed based on the number of users and the mileage of shared electric vehicles used in the target area in the future preset time period. The first mileage distribution information and the second mileage distribution information both include the same multiple mileage intervals.
[0043] Furthermore, the probability of selecting an electric shared electric vehicle that does not meet the mileage requirement when the overall car users (i.e., all car users predicted in the above-mentioned preset time period in the future) randomly select one from all the electric shared electric vehicles in the target area can be determined based on the mileage distribution probability of each mileage interval in the first mileage distribution information and the distribution probability of the car users in each mileage interval in the second mileage distribution information. The selection of an electric shared electric vehicle that does not meet the mileage requirement by the car user means that the mileage supported by the power of the electric shared electric vehicle selected by the user cannot meet the mileage required by the car user.
[0044] For example, the mileage that the car user needs to ride is 10 kilometers. If the power of the randomly selected shared electric vehicle can support a maximum of 9 kilometers, the car user has selected a shared electric vehicle that does not meet the mileage requirement.
[0045] Furthermore, the present application can directly set a probability threshold in advance based on experience. For example, in general, if the user has a 10% probability of getting a vehicle that does not meet the travel requirements, a considerable number of non-parking station parking behaviors will be generated. Therefore, the probability threshold can be pre-set to between 5% and 10%.
[0046] The present application may also pre-set a probability threshold based on historical usage data and dispatch data of shared electric vehicles combined with summarized experience.
[0047] The present application may also set a probability threshold in advance based on the historical usage data and dispatch data of the shared electric vehicles and by evaluating the cost incurred by the dispatch.
[0048] After obtaining the preset probability threshold, the determined selection probability can be compared with the preset probability threshold. If it is determined that the selection probability is greater than the preset probability threshold, it is determined that a considerable number of parking behaviors at non-parking sites may be generated, so the shared electric vehicles with power in the target area can be scheduled for battery replacement. If it is determined that the selection probability is less than or equal to the preset probability threshold, the shared electric vehicles with power in the target area may not be scheduled for battery replacement or other management strategies may not be implemented, which is not specifically limited in this application.
[0049] It should be noted that the present application does not limit the specific scheduling process when scheduling battery replacement for shared electric vehicles in the target area.
[0050] In one embodiment, when scheduling battery replacement for powered shared electric vehicles in a target area, the number of shared electric vehicles that need battery replacement can be determined first, and then battery replacement can be scheduled for a corresponding number of powered shared electric vehicles with the lowest battery levels in the target area.
[0051] It should also be further explained that since the scheduled battery resources are limited, the resource scheduling between different areas can determine the priority of resource allocation based on the probability that car users in each area use shared electric vehicles that can meet their usage needs.
[0052] The battery replacement scheduling method for shared electric vehicles provided in the embodiment of the present application, for a target area where shared electric vehicles can meet the user's usage needs within a preset time period in the future, when the number of shared electric vehicles in the target area is greater than a preset number threshold, obtains a list of the power of shared electric vehicles in the target area, and further maps the power list into first mileage distribution information; and, based on the historical usage data of the shared electric vehicles in the target area, determines the second mileage distribution information of the car users within the preset time period in the future; and then, based on the first mileage distribution information and the second mileage distribution information, determines the selection probability of the car user selecting a shared electric vehicle that does not meet the mileage requirement in a random situation; thereby, when the selection probability is greater than the preset probability threshold, the shared electric vehicles in the target area can be scheduled for battery replacement, which can reduce the probability of the car user selecting a shared electric vehicle that does not meet the mileage requirement, effectively reduce the occurrence of users abandoning their vehicles during use, and thereby reduce the cost of dispatching vehicles parked at non-parking sites.
[0053] This application can promptly detect power problems in a group of vehicles and schedule battery replacement based on actual conditions.
[0054] In one embodiment, based on the first mileage distribution information and the second mileage distribution information, the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirements in a random situation is determined, including: determining a first distribution probability corresponding to each mileage interval in the first mileage distribution information; determining a second distribution probability corresponding to each mileage interval in the second mileage distribution information; based on each first distribution probability and each second distribution probability, determining the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirements in a random situation.
[0055] Furthermore, based on each first distribution probability and each second distribution probability, a selection probability that a car user selects an electric shared electric vehicle that does not meet the mileage requirement under random circumstances is determined, including: determining, according to each first distribution probability, the first probability that a car user corresponding to each mileage interval selects an electric shared electric vehicle that does not meet the mileage requirement under random circumstances; determining, according to each first probability and each second distribution probability, the selection probability that a car user selects an electric shared electric vehicle that does not meet the mileage requirement under random circumstances.
[0056] Furthermore, based on each first probability and each second distribution probability, the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirement under random circumstances is determined, including: for each mileage interval, multiplying the first probability by the second distribution probability to obtain the probability product of the corresponding mileage interval; adding each probability product, and determining the result of the addition operation as the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirement under random circumstances.
[0057] Specifically, when the present application determines the selection probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirements under random circumstances based on the first mileage distribution information and the second mileage distribution information, it can first determine the first distribution probability corresponding to each mileage interval in the first mileage distribution information. Among them, the first distribution probability can represent the distribution probability of the mileage that can be supported by the power of the electric shared electric vehicle. For example, if the first mileage distribution information includes 6 mileage intervals, namely A, B, C, D, E, and F, each mileage interval represents a mileage range. Through the first mileage distribution information, for example, it can be determined that the first distribution probability of mileage interval A is 5%, the first distribution probability of mileage interval B is 10%, the first distribution probability of mileage interval C is 15%, the first distribution probability of mileage interval D is 30%, the first distribution probability of mileage interval E is 30%, and the first distribution probability of mileage interval F is 20%. Specifically, the first mileage distribution information can be constructed into an N-dimensional vector Va (va1, va2, ..., va n ).
[0058] In addition, the present application can also determine the second distribution probability corresponding to each mileage interval in the second mileage distribution information. Among them, the second distribution probability can represent the distribution probability of the mileage required to be traveled by users who need to use shared electric vehicles. For example, if the second mileage distribution information also includes 6 mileage intervals such as A, B, C, D, E, and F. Through the second mileage distribution information, for example, it can be determined that the second distribution probability of mileage interval A is 50%, the second distribution probability of mileage interval B is 30%, the second distribution probability of mileage interval C is 12%, the second distribution probability of mileage interval D is 5%, the second distribution probability of mileage interval E is 2%, and the second distribution probability of mileage interval F is 1%. Specifically, the second mileage distribution information can be constructed into an N-dimensional vector Vc (vc1, vc2,..., vc n ).
[0059] Furthermore, the first probability that the user corresponding to each mileage interval selects a shared electric vehicle that does not meet the mileage requirement under random conditions can be determined based on each first distribution probability combined with the following expression: ; represents the first probability corresponding to the mth mileage interval, represents the kth first distribution probability, and n represents the number of mileage intervals.
[0060] Thus, the first probability corresponding to each mileage interval can be obtained, and based on each first probability, an N-dimensional vector Vb (vb1, vb2, ..., vb n ).
[0061] Based on this, each mileage interval corresponds to a first probability and a second distribution probability. Therefore, for each mileage interval, the present application can further multiply the first probability corresponding to the mileage interval with the second distribution probability corresponding to the mileage interval to obtain the probability product of the mileage interval.
[0062] That is, after obtaining Vb and Vc, Vb and Vc can be multiplied to obtain the inner product. The inner product actually expresses the probability that a user matched under a random state finds a vehicle that does not meet his needs.
[0063] Thus, the probability product corresponding to each mileage interval can be obtained.
[0064] Furthermore, the present application can perform a sum operation on each probability product, and determine the result of the sum operation as the selection probability of a car user selecting a shared electric vehicle that does not meet the mileage requirement under random circumstances.
[0065] For example: in the above embodiment, the probability that a car user finds a car that does not meet his or her needs is (0%, 5%, 15%, 30%, 60%, 80%) * (50%, 30%, 12%, 5%, 2%, 1%) = 0 + 1.5% + 1.8% + 1.5% + 1.2% + 0.8% = 6.8%.
[0066] It should be noted that users who need to travel long distances will pay attention to the mileage that can be traveled by shared electric vehicles. This will make users with longer mileage requirements more cautious when choosing vehicles, thereby reducing the probability that such users will select vehicles that do not meet their needs. Therefore, this application can also appropriately lower the weight of long-mileage users when determining the probability that users select vehicles that do not meet their needs. Based on this, a weight coefficient less than or equal to 1 can be set for each mileage interval, where the larger the value, the smaller the weight coefficient set for the mileage interval.
[0067] Therefore, before adding the probability products, the present application can also obtain the weight coefficient of each mileage interval respectively, and multiply the weight coefficient of each mileage interval by its corresponding probability product respectively, thereby adjusting the probability product to obtain the adjusted probability products.
[0068] Furthermore, the probability products can be summed up, and the result of the summation can be determined as the probability of a user randomly selecting a shared electric vehicle that does not meet the mileage requirement.
[0069] The present application can accurately determine, in a random situation, the probability of a car user selecting an electric shared electric vehicle that does not meet the mileage requirements based on the first mileage distribution information and the second mileage distribution information, so that when the selection probability is greater than a preset probability threshold, the electric shared electric vehicles in the target area can be scheduled for battery replacement, which can reduce the probability of car users selecting electric shared electric vehicles that do not meet the mileage requirements, effectively reduce the occurrence of users abandoning their vehicles during the use of the vehicles, and thereby reduce the cost of dispatching vehicles parked at non-parking sites.
[0070] In one embodiment, the preset probability threshold is determined by the following steps: determining the proportion of parking at non-parking sites when the vehicle power does not meet the needs of the vehicle user based on the historical parking information of the shared electric vehicle; determining the additional cost based on the proportion, the usage of the shared electric vehicle in the historical parking information, the preset probability that the vehicle user selects a vehicle that does not meet the needs, the average dispatch cost of vehicles parked at non-parking sites, and the average amount of cancellation losses for vehicles parked at non-parking sites; determining the dispatch cost based on the proportion, the usage of the shared electric vehicle in the historical parking information, the preset probability that the vehicle user selects a vehicle that does not meet the needs, and the average dispatch cost of vehicles parked at parking sites; determining the preset probability when the additional cost is the same as the dispatch cost as the preset probability threshold.
[0071] Furthermore, the additional cost is determined based on the proportion, the usage of shared electric vehicles in historical parking information, the preset probability that the car user selects a vehicle that does not meet the demand, the average dispatch cost of vehicles parked at non-parking stations, and the average amount of cancellation losses for vehicles parked at non-parking stations, including: determining the first cost based on the proportion, the usage of shared electric vehicles in historical parking information, the preset probability that the car user selects a vehicle that does not meet the demand, and the average dispatch cost of vehicles parked at non-parking stations; determining the second cost based on the proportion, the usage of shared electric vehicles in historical parking information, the preset probability that the car user selects a vehicle that does not meet the demand, and the average amount of cancellation losses for vehicles parked at non-parking stations; and determining the sum of the first cost and the second cost as the additional cost.
[0072] It can be understood that when setting the probability threshold, the present application can estimate the cost of battery replacement in the current area and the number of randomly parked vehicles generated in the current area under a certain probability threshold, and convert the corresponding increase in scheduling costs and the estimated amount of order losses, and further reversely deduce a reasonable probability threshold.
[0073] Specifically, the present application can determine the proportion of non-parking station parking when the vehicle power does not meet the needs of the vehicle user based on the historical parking information of all shared electric vehicles or shared electric vehicles in the area.
[0074] Furthermore, based on the above-mentioned ratio, the usage of shared electric vehicles in historical parking information, and the preset probability that car users select vehicles that do not meet their needs, the number of vehicles parked at non-parking stations is determined, and the number of vehicles is multiplied by the average dispatch cost of vehicles parked at non-parking stations. The result of the multiplication is determined as the first cost, thereby determining the cost caused by power shortage under the current probability.
[0075] And, after determining the number of vehicles parked at non-parking stations based on the above-mentioned ratio, the usage of shared electric vehicles in historical parking information and the preset probability that car users select vehicles that do not meet their needs, the second cost is determined by multiplying the number of vehicles by the average amount of order cancellation losses for vehicles parked at non-parking stations.
[0076] Further, the added value of the first cost and the second cost is determined as the additional cost.
[0077] The present application can also determine the number of vehicles parked at non-parking stations based on the proportion, the usage of shared electric vehicles in historical parking information, and the preset probability that the vehicle users select vehicles that do not meet their needs, and determine the scheduling cost by comparing the number of vehicles with the average scheduling cost of vehicles parked at parking stations.
[0078] Finally, the preset probability when the additional cost is the same as the scheduling cost is determined as the preset probability threshold.
[0079] In one embodiment, the proportion of non-site parking when the vehicle power does not meet the user's needs can be counted based on historical data (counting non-site parking, vehicle change, complaints, etc. in the case of low power); the number of vehicles with non-site parking can be calculated based on the vehicle usage and the probability that the user selects a vehicle that does not meet the needs. The number of vehicles multiplied by the average dispatch cost of each vehicle can determine the cost caused by power shortage under the current probability. At the same time, the average loss price of user cancellations due to power shortage is counted, and the additional cost generated under the current proportion is estimated by combining the two main costs. According to the dispatch cost of the area, the corresponding proportion when the dispatch cost and the additional cost are equal is estimated, and the corresponding proportion when the dispatch cost and the additional cost are equal is used as the probability threshold.
[0080] The present application sets the probability threshold accurately in advance, so that when the determined selection probability is greater than the preset probability threshold, the electric shared electric vehicles in the target area can be scheduled for battery replacement, thereby reducing the probability of car users selecting electric shared electric vehicles that do not meet the mileage requirements, effectively reducing the occurrence of users abandoning their vehicles during the use of the vehicle, and thereby reducing the cost of dispatching vehicles that do not park at parking sites.
[0081] The battery replacement scheduling device for a shared electric vehicle provided in the present application is described below. The battery replacement scheduling device for a shared electric vehicle described below and the battery replacement scheduling method for a shared electric vehicle described above can be referenced to each other.
[0082] Furthermore, the present application also provides a battery replacement scheduling device for shared electric vehicles.
[0083] The battery replacement scheduling device for shared electric vehicles includes: an acquisition module, which is used to obtain a power list of powered shared electric vehicles in a target area if the number of powered shared electric vehicles in the target area is greater than a preset number threshold; the target area is an area where powered shared electric vehicles meet user usage needs within a future preset time period; a mapping module, which is used to map the power list into first mileage distribution information; a first determination module, which is used to determine, based on historical usage data of shared electric vehicles in the target area, second mileage distribution information of vehicle users within the future preset time period; a second determination module, which is used to determine, under random circumstances, the probability of a vehicle user selecting a powered shared electric vehicle that does not meet the mileage requirements based on the first mileage distribution information and the second mileage distribution information; a scheduling module, which is used to schedule battery replacement for powered shared electric vehicles in the target area when the selection probability is greater than a preset probability threshold.
[0084] In one embodiment, the second determination module is specifically used to: determine the first distribution probability corresponding to each mileage interval in the first mileage distribution information; determine the second distribution probability corresponding to each mileage interval in the second mileage distribution information; based on each first distribution probability and each second distribution probability, determine the probability of a car user selecting a shared electric vehicle that does not meet the mileage requirements under random circumstances.
[0085] In one embodiment, the second determination module includes a first determination unit, which is used to: determine, based on each first distribution probability, the first probability that the car user corresponding to each mileage interval selects an electric shared electric vehicle that does not meet the mileage requirement under random circumstances; and determine, based on each first probability and each second distribution probability, the selection probability that the car user selects an electric shared electric vehicle that does not meet the mileage requirement under random circumstances.
[0086] In one embodiment, the second determination module includes a second determination unit, which is used to: multiply the first probability by the second distribution probability for each mileage interval to obtain the probability product of the corresponding mileage interval; add the probability products, and determine the result of the addition operation as the selection probability of the car user selecting a shared electric vehicle that does not meet the mileage requirement under random circumstances.
[0087] In one embodiment, the second determination module further includes an adjustment unit, which is used to: obtain a weight coefficient for each mileage interval respectively; and adjust the corresponding probability products according to the weight coefficient for each mileage interval respectively to obtain adjusted probability products.
[0088] The battery replacement scheduling device for shared electric vehicles provided in the embodiment of the present application, for a target area where shared electric vehicles can meet the user's usage needs within a preset time period in the future, obtains a list of the power of the shared electric vehicles in the target area when the number of shared electric vehicles in the target area is greater than a preset number threshold, and further maps the power list into first mileage distribution information; and, based on the historical usage data of the shared electric vehicles in the target area, determines the second mileage distribution information of the car users within the preset time period in the future; and then, based on the first mileage distribution information and the second mileage distribution information, determines the probability of the car users selecting the shared electric vehicles that do not meet the mileage requirements in a random situation; thereby, when the selection probability is greater than the preset probability threshold, the shared electric vehicles in the target area can be scheduled for battery replacement, which can reduce the probability of the car users selecting the shared electric vehicles that do not meet the mileage requirements, effectively reduce the occurrence of users abandoning their cars during use, and thereby reduce the cost of dispatching vehicles parked at non-parking sites.
[0089] Figure 2 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 2 As shown, the electronic device may include: a processor 210, a communication interface 220, a memory 230 and a communication bus 240, wherein the processor 210, the communication interface 220 and the memory 230 communicate with each other through the communication bus 240. The processor 210 may call the logic instructions in the memory 230 to execute the battery replacement scheduling method for shared electric vehicles, the method comprising: if the number of shared electric vehicles with power in the target area is greater than a preset number threshold, then obtaining a list of power of shared electric vehicles with power in the target area; the target area is an area where shared electric vehicles with power meet the user's use needs within a preset time period in the future; mapping the list of power to first mileage distribution information; determining the second mileage distribution information of the user within the preset time period in the future according to the historical use data of the shared electric vehicles in the target area; determining the selection probability of the user selecting a shared electric vehicle with power that does not meet the mileage requirement under random conditions according to the first mileage distribution information and the second mileage distribution information; when the selection probability is greater than the preset probability threshold, performing battery replacement scheduling for the shared electric vehicles with power in the target area.
[0090] In addition, the logic instructions in the above-mentioned memory 230 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0091] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the battery replacement scheduling method for shared electric vehicles provided by the above-mentioned methods, the method comprising: if the number of powered shared electric vehicles in a target area is greater than a preset number threshold, obtaining a list of power levels of powered shared electric vehicles in the target area; the target area is an area where powered shared electric vehicles meet user usage needs within a preset time period in the future; mapping the power list into first mileage distribution information; determining second mileage distribution information of vehicle users within the preset time period in the future based on historical usage data of shared electric vehicles in the target area; determining, based on the first mileage distribution information and the second mileage distribution information, the probability of a vehicle user selecting a powered shared electric vehicle that does not meet the mileage requirements under random circumstances; and when the selection probability is greater than a preset probability threshold, scheduling battery replacement for the powered shared electric vehicles in the target area.
[0092] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0093] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A battery replacement scheduling method for shared electric vehicles, characterized in that: The method comprises: If the number of shared electric vehicles with power in the target area is greater than a preset number threshold, a list of the power levels of shared electric vehicles with power in the target area is obtained; the target area is an area where shared electric vehicles with power can meet the user's usage needs within a preset time period in the future; Mapping the power list into first mileage distribution information; Determine the second mileage distribution information of the vehicle users within the future preset time period according to the historical usage data of the shared electric vehicles in the target area; Determine, according to the first mileage distribution information and the second mileage distribution information, a probability of a user selecting a shared electric vehicle that does not meet the mileage requirement in a random situation; When the selection probability is greater than a preset probability threshold, battery replacement scheduling is performed for the shared electric vehicles with power in the target area.
2. The battery replacement scheduling method for shared electric vehicles according to claim 1 is characterized in that: The determining, based on the first mileage distribution information and the second mileage distribution information, the probability of a user selecting a shared electric vehicle that does not meet the mileage requirement under random conditions includes: Determine a first distribution probability corresponding to each mileage interval in the first mileage distribution information; Determine a second distribution probability corresponding to each mileage interval in the second mileage distribution information; Based on the first distribution probabilities and the second distribution probabilities, the probability of a vehicle user selecting a shared electric vehicle that does not meet the mileage requirement under random circumstances is determined.
3. The battery replacement scheduling method for shared electric vehicles according to claim 2 is characterized in that: The determining, based on each first distribution probability and each second distribution probability, the probability of a user selecting a shared electric vehicle that does not meet the mileage requirement under random conditions includes: According to each first distribution probability, a first probability that a user corresponding to each mileage interval selects a shared electric vehicle that does not meet the mileage requirement is determined in a random situation; According to each first probability and each second distribution probability, the selection probability of a car user selecting a shared electric vehicle that does not meet the mileage requirement under random circumstances is determined.
4. The battery replacement scheduling method for shared electric vehicles according to claim 3 is characterized in that: The determining, based on each first probability and each second distribution probability, the probability of a user selecting a shared electric vehicle that does not meet the mileage requirement under random conditions includes: For each mileage interval, the first probability is multiplied by the second distribution probability to obtain the probability product of the corresponding mileage interval; The products of the probabilities are summed up, and the result of the summation is determined as the probability of a user selecting a shared electric vehicle that does not meet the mileage requirement under random circumstances.
5. The battery replacement scheduling method for shared electric vehicles according to claim 4 is characterized in that: Before adding the probability products, it also includes: Obtain the weight coefficient of each mileage interval respectively; The corresponding probability products are adjusted according to the weight coefficient of each mileage interval to obtain the adjusted probability products.
6. The battery replacement scheduling method for shared electric vehicles according to claim 1, characterized in that: The preset probability threshold is determined by the following steps: Based on the historical parking information of shared electric vehicles, determine the proportion of non-parking station parking when the vehicle power does not meet the needs of vehicle users; Determine the additional cost based on the ratio, the usage of shared electric vehicles in the historical parking information, the preset probability that the vehicle user selects a vehicle that does not meet the demand, the average dispatch cost of vehicles parked at non-parking stations, and the average amount of chargeback losses of vehicles parked at non-parking stations; Determine the dispatch cost according to the ratio, the usage of shared electric vehicles in the historical parking information, the preset probability that the vehicle user selects a vehicle that does not meet the demand, and the average dispatch cost of the vehicles parked at the parking station; The preset probability when the additional cost is the same as the scheduling cost is determined as a preset probability threshold.
7. The battery replacement scheduling method for shared electric vehicles according to claim 6 is characterized in that: The additional cost is determined according to the ratio, the usage of shared electric vehicles in the historical parking information, the preset probability that the vehicle user selects a vehicle that does not meet the demand, the average dispatch cost of vehicles parked at non-parking stations, and the average amount of return losses of vehicles parked at non-parking stations, including: Determine a first cost according to the ratio, the usage of shared electric vehicles in the historical parking information, a preset probability that a vehicle user selects a vehicle that does not meet the demand, and an average dispatch cost of vehicles parked at non-parking sites; Determine the second cost based on the ratio, the usage of shared electric vehicles in the historical parking information, the preset probability that the user selects a vehicle that does not meet the user's needs, and the average amount of loss from chargebacks of vehicles parked at non-parking sites; An additional value of the first cost and the second cost is determined as an additional cost.
8. A battery replacement scheduling device for a shared electric vehicle, characterized in that: include: An acquisition module, configured to acquire a list of the power levels of the powered shared electric vehicles in the target area if the number of the powered shared electric vehicles in the target area is greater than a preset number threshold; The target area is an area where electric shared electric vehicles can meet the needs of users within a preset time period in the future; A mapping module, used for mapping the power list into first mileage distribution information; A first determination module is used to determine the second mileage distribution information of the vehicle users within the future preset time period according to the historical usage data of the shared electric vehicles in the target area; A second determination module is used to determine, based on the first mileage distribution information and the second mileage distribution information, a probability of a user selecting a shared electric vehicle that does not meet the mileage requirement under random circumstances; The scheduling module is used to schedule battery replacement for the shared electric vehicles with power in the target area when the selection probability is greater than a preset probability threshold.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the battery replacement scheduling method for a shared electric vehicle as described in any one of claims 1 to 7.
10. A medium, the medium being a non-transitory computer-readable storage medium, on which a computer program is stored, characterized in that: When the computer program is executed by a processor, the battery replacement scheduling method for a shared electric vehicle as described in any one of claims 1 to 7 is implemented.