User shunting method and device for battery swap station, and medium

Abstract

The embodiment of the invention discloses a user shunting method and device for a battery swap station, and a medium, is used for the technical field of battery swap, and is used for solving the problem that the current shunting mode based on user selection is easy to cause unbalanced tasks of the battery swap station. The method comprises the steps of predicting a station peak time period of each battery swap station based on to-be-analyzed recent battery swap data of each battery swap station in a current shunting area; according to the exposure click data corresponding to each battery swap station, the user data corresponding to the exposure click data and the current battery number, predicting the number of arrival battery swap vehicles and the number of station end replaceable batteries of each battery swap station in the peak time period of the corresponding station; and by comparing the number of arrival battery replacement vehicles between the battery replacement stations with the number of station-end replaceable batteries, exposure adjustment is carried out on the battery replacement stations to realize user shunting.

Description

[0001] This application claims priority based on the invention patent application titled "A User Diversion Method, Device and Medium for Battery Swap Stations" with the application number 202311867248.3 filed with the China National Intellectual Property Administration on December 29, 2023. The entire content of the above Chinese patent application is incorporated herein by reference. Technical Field

[0002] This specification relates to the field of battery swap technology, and particularly to a user diversion method, device and medium for battery swap stations. Background Art

[0003] When users conduct offline battery swap services, they query station information through the App and select a battery swap station based on the distance and the current queue number. However, due to the superior location of some stations, more drivers operate nearby. Therefore, when the battery swap time approaches, although the queue number is small when the user queries, there may be too many people in the queue and insufficient batteries after the user actually arrives at the station, thus affecting the business operation and user experience. Therefore, how to divert users among battery swap stations is an important means to relieve the difficulty of supporting business during peak hours at battery swap stations.

[0004] The current diversion method mainly relies on users querying the distance and current queue number of stations through the App to select a battery swap station. However, this method ignores the influence of other factors, such as the battery supply capacity of the station and the traffic conditions. Therefore, when actually arriving at the station, there may be a situation of too long waiting time in the queue and insufficient batteries, thus affecting the user experience and the smooth progress of the business. The current diversion method may lack a systematic diversion strategy. And when using this method that relies on users' own judgment and selection for diversion, due to the possible synchronization delay of battery swap station data, the user's selection cannot be synchronized in time. Therefore, during the process of the user arriving at the station, the station may be overcrowded while other stations are relatively empty. The method of diversion based solely on users' own selection is not conducive to the rational utilization and balance of resources. Summary of the Invention

[0005] To solve the above technical problems, one or more embodiments of this specification provide a user diversion method, device and medium for battery swap stations.

[0006] One or more embodiments of this specification adopt the following technical solutions:

[0007] On the one hand, an embodiment of this specification provides a method for user diversion at a battery swapping station. The method includes: collecting recent battery swapping data of each battery swapping station in the current diversion area, and preprocessing the recent battery swapping data to obtain recent battery swapping data to be analyzed; predicting the peak time period of each battery swapping station based on the recent battery swapping data to be analyzed; predicting the arriving battery swapping vehicles and the available battery data at the station end during the peak time period of the station according to the exposure click data and the current battery data corresponding to each battery swapping station; adjusting the exposure of each battery swapping station by comparing the arriving battery swapping vehicles and the available battery data at the station end between each battery swapping station, and the battery swapping records during the historical peak time period within each battery swapping station, so as to achieve user diversion based on the exposure adjustment.

[0008] On the other hand, an embodiment of this specification provides a method for user diversion at a battery swapping station. The method includes: predicting the peak time period of each battery swapping station based on the recent battery swapping data to be analyzed of each battery swapping station in the current diversion area; predicting the number of arriving battery swapping vehicles (i.e., the arriving battery swapping vehicles) and the number of available batteries at the station end (i.e., the available battery data at the station end) during the corresponding peak time period of each battery swapping station according to the exposure click data corresponding to each battery swapping station, the user data corresponding to the exposure click data, and the current number of batteries (i.e., the current battery data); adjusting the exposure of each battery swapping station by comparing the number of arriving battery swapping vehicles and the number of available batteries at the station end between each battery swapping station to achieve user diversion.

[0009] In this specification, by obtaining the machine battery swapping data of each battery swapping station, data acquisition based on multiple sources and multiple dimensions is realized, which helps to improve the rationality in the diversion analysis process. In addition, by preprocessing the recent battery swapping data to obtain the recent battery swapping data to be analyzed, it helps to ensure the consistency of the recent battery swapping data of each battery swapping station and at the same time helps to reduce the adverse impact of redundant data on the prediction. Through the statistical comparison method of the recent battery swapping data to be analyzed, the time period with a large battery swapping flow can be quickly determined as the peak time period of the station. In addition, by determining the intended battery swapping flow of each battery swapping station based on the exposure click data, it helps to understand the selection intention of each user for each battery swapping station in the current diversion area, and the prediction accuracy of the number of arriving battery swapping vehicles and the number of available batteries at the station end during the peak time period of the station is improved by considering the selection intention. By adjusting the exposure rate, and adjusting the exposure degree by comparing between each battery swapping station, the problem of poor balanced diversion effect caused only by user selection is avoided.

[0010] In a feasible implementation manner, before collecting the recent battery swapping data of each battery swapping station in the current diversion area, the method further includes: dividing and determining a plurality of initial diversion areas with administrative regions as boundaries, and obtaining the road network structure data and the positions of battery swapping stations in each of the initial diversion areas; wherein, the road network structure data includes: expressway network structure data, elevated highway network structure data; based on the positions of each battery swapping station and the road network structure data, establishing a plurality of traffic directed graphs of the battery swapping stations in the initial diversion area; wherein, the edges of the traffic directed graphs are traffic costs; determining the passing paths and traffic costs between each battery swapping station according to the plurality of traffic directed graphs; clustering each battery swapping station based on the passing paths and traffic costs in sequence, and dividing the initial diversion area based on the clustering result to obtain the current diversion area.

[0011] In this specification, by obtaining the road network structure data and the positions of battery swapping stations, it is convenient to better determine the position distribution of battery swapping stations in each initial diversion area, which helps to better divert the unevenly distributed battery swapping stations in the subsequent process, and solve the problem that it is easy to have difficulties in operation during peak periods due to the influence of geographical location and traffic factors, etc., on the uneven distribution of the passenger flow of battery swapping stations. By establishing the traffic directed graphs of the battery swapping stations in the initial diversion area, the passing paths and traffic costs between different battery swapping stations are clearly represented, which helps to determine the passable paths between battery swapping stations and road conditions such as traffic congestion. By including the road conditions in the diversion consideration scope, the comprehensive consideration of multi-dimensional parameters is realized, which is closer to the actual scenario of vehicle driving compared with the existing diversion method based only on distance. And further dividing the initial diversion area based on the clustering result helps to better organize and manage the diversion between battery swapping stations and avoid the problem of low customer experience caused by long-distance diversion.

[0012] In a feasible implementation manner, collect the recent battery swapping data of each battery swapping station in the current diversion area, and preprocess the recent battery swapping data to obtain the recent battery swapping data to be analyzed, specifically including: obtaining the recent battery swapping data of each battery swapping station through the API interface of the battery swapping server in each battery swapping station; performing duplicate detection on the recent battery swapping data of each battery swapping station to implement data cleaning and obtain the initial recent battery swapping data; obtaining the data composition elements of each initial recent battery swapping data to perform integrity detection on each initial recent battery swapping data based on the data composition elements; if it is determined that there is data missing, obtain the recent battery swapping variables corresponding to the data composition elements in each recent battery swapping data, obtain the mean value of the corresponding recent battery swapping variables, and perform data filling based on the mean value to obtain the recent battery swapping data to be analyzed.

[0013] The process based on data cleaning in this specification can exclude duplicate data and error data, thereby reducing the computing power cost consumed by redundant data repetitive analysis. At the same time, it reduces the impact of error data on accuracy, which is beneficial to improving the credibility in the subsequent prediction process. After obtaining the initial recent battery swapping data, detecting based on the data composition elements can ensure the integrity and consistency of the data. After processing in this way, the recent battery swapping data becomes more complete and reliable, which helps to analyze the patterns and trends of battery swapping behaviors, providing reliable data support for subsequent prediction of peak time periods and improving the operation efficiency of battery swapping stations.

[0014] In a feasible embodiment, before predicting the site peak time period of each battery swapping station based on the recent battery swapping data to be analyzed of each battery swapping station in the current diversion area, the method further includes:

[0015] Obtaining the battery swapping orders of each battery swapping station in the current diversion area within a preset time period to determine the recent battery swapping data of each battery swapping station based on the battery swapping orders; obtaining the data composition elements of each recent battery swapping data to perform integrity detection on each recent battery swapping data based on the data composition elements; if it is determined that there is missing data, obtaining the recent battery swapping variables corresponding to the data composition elements in each recent battery swapping data, and obtaining the mean value of the corresponding recent battery swapping variables; filling the missing data corresponding to the data composition elements in the recent battery swapping data based on the mean value to obtain the recent battery swapping data to be analyzed; and / or, before obtaining the battery swapping orders of each battery swapping station in the current diversion area within a preset time period to determine the recent battery swapping data of each battery swapping station based on the battery swapping orders, the method further includes: dividing and determining a plurality of initial diversion areas with administrative regions as boundaries, and obtaining the road network structure data and battery swapping station locations within each initial diversion area; based on each battery swapping station location and the road network structure data, establishing a plurality of traffic directed graphs of the battery swapping stations within the initial diversion area; where the edges of the traffic directed graph are traffic costs; determining the passing paths and traffic costs between each battery swapping station according to the plurality of traffic directed graphs; clustering each battery swapping station based on the passing paths and traffic costs in sequence, and dividing the initial diversion area based on the clustering result to obtain the current diversion area.

[0016] In the embodiments of this specification, after obtaining the initial recent battery swapping data, detecting based on the data composition elements can ensure the integrity and consistency of the data. After processing based on this method, the recent battery swapping data becomes more complete and reliable, which helps to analyze the patterns and trends of battery swapping behaviors, provides reliable data support for predicting peak time periods and improving the operation efficiency of battery swapping stations in the subsequent process. Moreover, by taking administrative regions as the basis and combining road network structure data and the locations of battery swapping stations, multiple initial diversion regions can be more accurately divided. These regions not only consider geographical boundaries but also incorporate the actual traffic flow conditions, making the region division more in line with actual needs. The traffic directed graph established based on the battery swapping stations and road network structure data provides a scientific basis for determining the optimal passing path between battery swapping stations by quantifying the traffic cost, which helps to ensure that when users need to swap batteries, they can find a battery swapping station that is close and has convenient transportation faster, thereby shortening the waiting time of users and improving the efficiency of battery swapping diversion. In addition, through the clustering analysis combining the passing path and traffic cost, the system can identify the distribution of battery swapping stations within each diversion region, and then cluster the stations with low traffic cost and short distance to obtain the current diversion region. This reasonable diversion region division and determination of battery swapping station layout help to subsequently guide users to disperse to other battery swapping stations with short distance and convenient transportation within the current diversion region through reasonable exposure adjustment, thereby reducing the pressure on popular stations and avoiding the occurrence of queuing waiting phenomena. At the same time, it can also improve the utilization rate of idle stations and optimize the overall allocation of battery swapping resources.

[0017] In a feasible implementation manner, predicting the site peak time periods of each battery swapping station based on the to-be-analyzed recent battery swapping data specifically includes: determining the historical peak time periods of each battery swapping station based on the to-be-analyzed recent battery swapping data of each battery swapping station; determining the segment interval of the statistical time of the battery swapping data within the current diversion region based on the historical peak time periods of each battery swapping station; grouping the to-be-analyzed recent battery swapping data of each battery swapping station based on the segment interval to obtain groups of to-be-analyzed recent battery swapping data, and counting the battery swapping flow of the groups of to-be-analyzed recent battery swapping data; and determining the site peak time periods of each battery swapping station within the current diversion region by comparing the preset battery swapping flow threshold with the battery swapping flow of each group of to-be-analyzed recent battery swapping data.

[0018] In another feasible embodiment of this specification, based on the recent battery swapping data to be analyzed of each battery swapping station in the current diversion area, predicting the peak time periods of each of the battery swapping stations specifically includes: sorting the recent battery swapping data to be analyzed in chronological order to determine the number of battery swapping users corresponding to each of the preset time periods based on the sorted recent battery swapping data to be analyzed; determining the peak time periods of each of the battery swapping stations based on the number of battery swapping users corresponding to each of the preset time periods for each of the battery swapping stations; and / or, based on the recent battery swapping data to be analyzed of each battery swapping station in the current diversion area, predicting the peak time periods of each of the battery swapping stations specifically includes: determining the historical peak time periods of each of the battery swapping stations based on the recent battery swapping data to be analyzed of each battery swapping station; grouping the recent battery swapping data to be analyzed of each of the battery swapping stations based on the historical peak time periods of each of the battery swapping stations to obtain groups of recent battery swapping data to be analyzed, and counting the battery swapping flow of the groups of recent battery swapping data to be analyzed; determining the peak time periods of each battery swapping station in the current diversion area by comparing a preset battery swapping flow threshold with the battery swapping flow of each of the groups of recent battery swapping data to be analyzed.

[0019] In a feasible implementation manner, by comparing a preset battery replacement flow threshold with the battery replacement flows of each of the recently analyzed battery replacement data groups to be analyzed, the peak time periods of each substation site in the current shunt area are determined, including: determining the change trend of the battery replacement flow of each substation site according to the battery replacement flows of each of the recently analyzed battery replacement data groups to be analyzed; if the change trend is an upward trend and the battery replacement flow of the recently analyzed battery replacement data group to be analyzed exceeds the preset battery replacement flow threshold, determining the time point when the battery replacement flow of the recently analyzed battery replacement data group to be analyzed reaches the preset battery replacement flow threshold as the start time point of the peak time period; if the change trend is a downward trend and the battery replacement flow of the recently analyzed battery replacement data group to be analyzed exceeds the preset battery replacement flow threshold, determining the time point when the battery replacement flow of the recently analyzed battery replacement data group to be analyzed reaches the preset battery replacement flow threshold as the end time point of the peak time period; determining the peak time period of each substation site according to the start time point and the end time point; and / or, grouping the recently analyzed battery replacement data of each substation site based on the historical peak time periods of each substation site, including: determining the segmentation interval of the battery replacement data statistical time in the current shunt area based on the historical peak time periods of the substation sites; grouping the recently analyzed battery replacement data of the substation sites based on the segmentation interval; or, determining the segmentation interval and the average peak time period of the battery replacement data statistical time in the current shunt area based on the historical peak time periods of the substation sites; grouping the recently analyzed battery replacement data of the substation sites based on the segmentation interval and the average peak time period; or, determining the segmentation interval of the battery replacement data statistical time in the current shunt area based on the historical peak time periods of the substation sites; if the segmentation interval is an integer, grouping the recently analyzed battery replacement data of the substation sites based on the segmentation interval; if the segmentation interval is not an integer, determining the average peak time period of the battery replacement data statistical time in the current shunt area based on the historical peak time periods of the substation sites, and grouping the recently analyzed battery replacement data of the substation sites based on the segmentation interval and the average peak time period; preferably, after predicting the peak time periods of each substation site, the method further includes: if it is determined that the current time is within the time range corresponding to the peak time period of the substation site, regularly obtaining the exposure click data of each substation site in the current shunt area and the user data corresponding to each exposure click data based on the App buried point data; wherein, the user data at least includes: the user location corresponding to the vehicle intending to go to the substation site for battery replacement, the remaining SOC value of the vehicle, and the current battery quantity.

[0020] In this specification, the daily pattern of the change in the battery swapping demand over time is analyzed and determined as a conventional experience through the historical peak time period. Thus, based on the historical peak time periods of each battery swapping station, the segmentation interval of the statistical time of the battery swapping data within the current diversion area is determined, and then the station peak time periods of each battery swapping station within the current diversion area are statistically obtained. Based on this method, the conventional demand of the battery swapping stations in the actual operation scenario is fully incorporated, and grouping helps to conduct a more refined analysis of the recent battery swapping data, and further determine the change in the battery swapping flow of the battery swapping stations within each time segment. Moreover, through the method of statistics and comparison, the time period with a large battery swapping flow can be quickly and intuitively determined as the station peak time period, improving the analysis efficiency. By directly analyzing the latest battery swapping data and sorting them in chronological order, the change in the usage situation of the battery swapping stations can be more real-time reflected, and a rapid response can be made to the sudden increase or decrease in the battery swapping demand. By setting a battery swapping flow threshold, it is possible to intuitively determine whether a certain time period belongs to the peak period, improving the determination efficiency. By analyzing the change trend of the battery swapping flow of the recent battery swapping data group, the change in the battery swapping demand can be accurately captured. Especially when the flow shows an upward trend and exceeds the preset threshold, it is immediately determined as the start of the peak time period, and when it exceeds the threshold during the downward trend, it is regarded as the end. This method ensures that the judgment of the peak time period is both timely and accurate, and since it is based on the dynamic analysis of data, this method can predict the peak time period in advance. Moreover, this specification takes into account the situation where the segmentation interval may be an integer or not an integer, and corresponding processing strategies are given respectively. By grouping the data by combining the segmentation interval and the average peak time period, the battery swapping peak period can be determined more accurately.

[0021] In a feasible implementation manner, according to the exposure click data and the current battery data corresponding to each battery swapping station, the arriving battery swapping vehicles and the station-side replaceable battery data during the peak time period of the station are predicted, which specifically includes: if it is determined that the current time is within the time range corresponding to the peak time period of the station, the exposure click data and the current battery data of each battery swapping station in the current diversion area are regularly obtained based on the App buried point data; the intended battery swapping flow of each battery swapping station is determined based on the exposure click data; the user location and the remaining SOC value of the vehicle corresponding to each exposure click data are obtained, and the intended battery swapping flow is filtered based on the user location and the remaining SOC value of the vehicle to obtain the initially predicted arriving vehicles; the distance between the user location corresponding to the initially predicted arriving vehicles and the corresponding battery swapping station is determined, and based on the distance and the driving data of the user, the arrival time of the user is estimated, and by comparing the arrival time with the time range, it is determined whether to filter the initially predicted arriving vehicles to predict the arriving battery swapping vehicles during the peak time period of the station; the average battery swapping flow reaching the peak time period of the station is estimated according to the historical battery swapping records corresponding to the current time, and the station-side replaceable battery data during the peak time period of the station is predicted based on the current battery data and the average battery swapping flow.

[0022] In a feasible embodiment, according to the exposure click data corresponding to each battery swapping station, the user data corresponding to the exposure click data, and the current number of batteries, the number of arriving battery swapping vehicles and the number of replaceable batteries at the station end during the peak time period of the station are predicted, which specifically includes: determining the intended battery swapping flow of each battery swapping station based on the exposure click data, where the intended battery swapping flow represents the vehicle data of vehicles intending to go to the battery swapping station for battery swapping; filtering the intended battery swapping flow based on the user location and the remaining SOC value of the vehicle to obtain the initial predicted arriving vehicles; predicting the number of arriving battery swapping vehicles during the peak time period of the station based on the user data corresponding to the initial predicted arriving vehicles, the location information of the battery swapping station, and the peak time period of the station; determining the average battery swapping flow of the battery swapping station during the corresponding peak time period of the arrival station, and predicting the number of replaceable batteries at the station end of the battery swapping station during the corresponding peak time period of the arrival station based on the current number of batteries and the average battery swapping flow; preferably, the user data includes the driving data of the user, and predicting the number of arriving battery swapping vehicles during the peak time period of the station based on the user data corresponding to the initial predicted arriving vehicles, the location information of the battery swapping station, and the peak time period of the station includes: determining the distance between the initial predicted arriving vehicle and the corresponding battery swapping station based on the user location and the location information of the battery swapping station, and predicting the arrival time of the user based on the distance and the driving data of the user; filtering the initial predicted arriving vehicles based on the comparison result between the arrival time and the time range corresponding to the peak time period of the station to determine the number of arriving battery swapping vehicles at the battery swapping station during the peak time period of the station.

[0023] In this specification, by determining the intended battery swapping flow of each battery swapping station based on the exposure click data, it helps to understand the selection intention of each user for each battery swapping station in the current diversion area, so as to facilitate the statistics of the possible arriving battery swapping vehicles at each battery swapping station, and helps to provide an analysis basis for the operation decision-making of each battery swapping station. By filtering based on the remaining SOC value of the vehicle, the vehicle flow that cannot arrive is filtered, thus concentrating the attention on those vehicles that are truly likely to arrive at the station for battery swapping, improving the accuracy and efficiency of the prediction. By determining that the initial predicted arriving vehicle can reach the battery swapping station within the time range of the peak time period based on the driving vehicle data and distance of the user, the driving habits of different users are fully considered, making the prediction and filtering process more rigorous.

[0024] In a feasible implementation, the average battery swapping flow rate of the swapping station corresponding to the peak time period of the station is determined, and based on the current number of batteries and the average battery swapping flow rate, the number of replaceable batteries at the station end of the swapping station corresponding to the peak time period of the station is predicted. Specifically, it includes: determining the initial number of replaceable batteries corresponding to each time period of the swapping station based on the current number of batteries and the battery swapping speed of the swapping station; estimating the average battery swapping flow rate of the swapping station during the peak time period of the station based on the historical battery swapping records corresponding to the current time of the swapping station; determining the remaining number of replaceable batteries corresponding to each time period of the swapping station according to the average battery swapping flow rate and the initial number of replaceable batteries, and summarizing the remaining number of replaceable batteries corresponding to each time period to determine the number of replaceable batteries at the station end during the peak time period of the station.

[0025] In this specification, by comprehensively considering the static factor of the current number of batteries and the battery swapping speed and the dynamic factor of the historical battery swapping records, the average battery swapping flow rate during the peak time period is comprehensively predicted, making the prediction result more accurate. Based on the predicted average battery swapping flow rate and the initial number of replaceable batteries, the remaining number of replaceable batteries corresponding to each time period can be determined more accurately. By predicting in advance the number of replaceable batteries at the station end during the peak time period, the number of battery swapping vehicles that each swapping station can support can be clarified, which helps to avoid the problem that the arriving vehicles cannot obtain battery swapping services due to insufficient batteries.

[0026] In a feasible implementation, the intended battery swapping flow rate is filtered based on the user location and the remaining SOC value of the vehicle to obtain the initial predicted arriving vehicles. Specifically, it includes: determining the swapping station corresponding to the user according to the exposure click data, and obtaining one or more traffic directed graphs where the corresponding swapping station is located; determining one or more passable paths between the user location and the corresponding swapping station based on the one or more traffic directed graphs; determining the total SOC demand value of each passable road section based on the SOC demand values of each road section in the passable path; if it is determined that the total SOC demand values of all the passable road sections are greater than the remaining SOC value of the vehicle, then the intended battery swapping flow rate is filtered to obtain the initial predicted arriving vehicles.

[0027] In this specification, by determining the passable path between the user location and the swapping station based on the directed graph with the passing cost as the edge in the above embodiments, it avoids the problem that the passable path determined only based on distance in the prior art is difficult to adapt to the complex needs of users, and further leads to the difficulty in considering the user's personal habits for the predicted initial arrival vehicles, resulting in inaccurate prediction. By calculating the different total SOC demand values of each passable section, it helps to understand the battery demand of the swapping vehicles on different sections. Furthermore, when it is determined that the total SOC demand value of each passable section is greater than the remaining SOC value of the vehicle in combination with the actual scenario, it indicates that the vehicle is difficult to reach the intended swapping station. Through this method, the diversion process is more targeted at the vehicles that can arrive during the peak period, thereby reducing the diversion pressure in the current diversion area.

[0028] In a feasible implementation manner, by comparing the arriving swapping vehicles between the swapping stations with the battery data that can be swapped at the station end, and the swapping records during the historical peak periods in each swapping station, the exposure adjustment of each swapping station is performed, which specifically includes: comparing the arriving swapping vehicles between the swapping stations with the battery data that can be swapped at the station end, and determining the swapping stations to be balanced in the current diversion area based on the comparison results; determining multiple historical arriving swapping vehicles corresponding to the battery data that can be swapped at the station section and the historical feedback information during each historical peak period based on the historical peak periods of each swapping station to be balanced; filtering the multiple historical arriving vehicles based on the historical feedback information to obtain the historical arriving swapping vehicles after filtering of the swapping stations to be balanced; determining the sustainable arriving swapping vehicles corresponding to the swapping stations based on the average value of the historical arriving swapping vehicles; if it is determined that the sustainable arriving swapping vehicles are less than the arriving swapping vehicles, then based on the difference between the arriving swapping vehicles and the sustainable arriving swapping vehicles, determine the downward adjustment positions of each swapping station for exposure adjustment.

[0029] In a feasible implementation manner of this specification, by comparing the number of arriving battery - swapping vehicles between each battery - swapping station and the number of replaceable batteries at the station end, as well as the battery - swapping records during the historical peak time periods within each battery - swapping station, the exposure adjustment of each battery - swapping station is performed, which specifically includes: determining the battery - swapping stations to be balanced within the current diversion area based on the number of arriving battery - swapping vehicles between the battery - swapping stations and the number of replaceable batteries at the station end; determining, based on the historical peak time periods of each battery - swapping station to be balanced, a plurality of historical arriving battery - swapping vehicles corresponding to the number of replaceable batteries at the station end, and the historical feedback information of the users corresponding to the vehicles during each historical peak time period; wherein the historical feedback information is used to indicate whether the user obtains effective charging services; filtering the plurality of historical arriving vehicles based on the historical feedback information to obtain the historical arriving battery - swapping vehicles after filtering for the battery - swapping stations to be balanced; determining the number of maintainable arriving battery - swapping vehicles corresponding to the battery - swapping station based on the average value of the filtered historical arriving battery - swapping vehicles; if it is determined that the number of maintainable arriving battery - swapping vehicles is less than the number of arriving battery - swapping vehicles, then based on the difference between the number of arriving battery - swapping vehicles and the number of maintainable arriving battery - swapping vehicles, the exposure adjustment of each battery - swapping station is performed; preferably, the exposure adjustment of each battery - swapping station based on the difference between the number of arriving battery - swapping vehicles and the number of maintainable arriving battery - swapping vehicles specifically includes: determining the difference between the number of arriving battery - swapping vehicles and the number of maintainable arriving battery - swapping vehicles, so as to determine the downward adjustment value of the exposure rate of the battery - swapping station based on the magnitude of the difference of each battery - swapping station; updating the exposure of the battery - swapping station through the downward adjustment value of the exposure rate to determine the current exposure position of the battery - swapping station; and / or, determining the difference between the number of arriving battery - swapping vehicles and the number of maintainable arriving battery - swapping vehicles, so as to determine the search difficulty value of the battery - swapping station based on the magnitude of the difference; sorting and updating the search position of the battery - swapping station through the search difficulty value to determine the current search position of the battery - swapping station; and / or, determining the difference between the number of arriving battery - swapping vehicles and the number of maintainable arriving battery - swapping vehicles to obtain the comparison result of the difference with a preset threshold; according to the comparison result, determining whether to add a reminder pop - up window for off - peak use at the current exposure position corresponding to the battery - swapping station.

[0030] In this specification, by comparing the arrival of battery swapping vehicles and the available battery data at the station end among different battery swapping stations, and the battery swapping records during the historical peak periods at each battery swapping station, after adjusting the exposure of each battery swapping station, the method further includes: obtaining in real time the current exposure click data corresponding to each battery swapping station; comparing the current exposure click data with the exposure click data to determine the change value of the intended battery swapping traffic volume for each battery swapping station; determining the downward adjustment value of the exposure rate of the battery swapping station based on the change value of the intended battery swapping traffic volume; updating the exposure of the battery swapping station through the downward adjustment value of the exposure rate, determining the current exposure position, and triggering the pop-up of a peak-shifting prompt window at the current exposure position based on a preset downward threshold.

[0031] In a feasible implementation manner, by comparing the arrival of battery swapping vehicles and the available battery data at the station end among different battery swapping stations, and the battery swapping records during the historical peak periods at each battery swapping station, after adjusting the exposure of each battery swapping station, the method further includes: obtaining in real time the current exposure click data corresponding to each battery swapping station; comparing the current exposure click data with the exposure click data to determine the change value of the intended battery swapping traffic volume for each battery swapping station; determining the downward adjustment value of the exposure rate of the battery swapping station based on the change value of the intended battery swapping traffic volume; updating the exposure of the battery swapping station through the downward adjustment value of the exposure rate, determining the current exposure position, and triggering the pop-up of a peak-shifting prompt window at the current exposure position based on a preset downward threshold.

[0032] In this specification, the current exposure click data corresponding to each battery swapping station is obtained in real time, so as to avoid the problem of inaccurate traffic diversion caused by untimely data synchronization due to user update selection. By triggering the prompt window, suggestions for peak-shifting battery swapping are provided to the user. By triggering the pop-up of the prompt window, suggestions for peak-shifting battery swapping can be provided to the user. When a peak-shifting prompt is made at the exposure position, the user may choose to perform battery swapping during non-peak hours, thereby optimizing the load balance of the battery swapping station and reducing the waiting time of the user.

[0033] On the other hand, an embodiment of the present invention further provides a user diversion device for a battery swapping station. The device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to: execute the user diversion method for a battery swapping station described in any one of the above.

[0034] Finally, an embodiment of this specification also provides a non-volatile computer storage medium storing computer-executable instructions, and the computer-executable instructions are configured to be able to execute the user diversion method for a battery swapping station described in any one of the above.

[0035] The above at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects:

[0036] In this specification, by obtaining the machine battery swapping data of each battery swapping station, data acquisition based on multiple sources and multiple dimensions is realized, which helps to improve the rationality in the diversion analysis process. In addition, through the preprocessing of the recent battery swapping data, the recent battery swapping data to be analyzed is obtained, which helps to ensure the consistency of the recent battery swapping data of each battery swapping station and at the same time helps to reduce the adverse impact of redundant data on the prediction. By means of the statistical comparison method of the recent battery swapping data to be analyzed, the time period with a large battery swapping flow can be quickly determined as the peak time period of the station. In addition, by determining the intended battery swapping flow of each battery swapping station based on the exposure click data, this helps to understand the selection intention of each user for each battery swapping station in the current diversion area, and the prediction accuracy of the arrival battery swapping vehicles and the number of replaceable batteries at the station end during the peak time period of the station is improved by considering the selection intention. By adjusting the exposure rate, that is, adjusting the exposure degree by comparing between each battery swapping station, the problem of poor balanced diversion effect caused only by user selection is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0038] Figure 1 is a schematic flow chart of a user diversion method for a battery swapping station provided by an embodiment of this specification;

[0039] Figure 2 is another schematic flow chart of a user diversion method for a battery swapping station provided by an embodiment of this specification;

[0040] Figure 3 Schematic diagram of the internal structure of a user diversion device for a battery swapping station provided in an embodiment of this specification;

[0041] Figure 4 Schematic diagram of the internal structure of a non-volatile storage medium provided in an embodiment of this specification. Specific implementation manners

[0042] An embodiment of this specification provides a user diversion method, device, and medium for a battery swapping station.

[0043] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

[0044] An embodiment of the specification provides a user diversion method for a battery swapping station. As Figure 1 shown, the method specifically includes the following steps S101 - S103:

[0045] S101: Predict the peak time periods of each of the battery swapping stations based on the recent battery swapping data to be analyzed of each battery swapping station in the current diversion area.

[0046] First, in order to be able to determine the peak time periods of the stations in the current diversion area and avoid the problem that it is difficult to analyze a single data source to obtain the peak time that can accurately reflect the area, in a feasible embodiment of this specification, different time period division methods will be customarily determined according to different operation requirements of the battery swapping stations. For example: Divide according to granularities such as hours, half - hours, or ten - minutes. For example, a day is divided into time periods such as morning (6:00 - 9:00), forenoon (9:00 - 12:00), noon (12:00 - 14:00), afternoon (14:00 - 18:00), and evening (18:00 - 23:00). Then, the recent battery swapping data to be analyzed of each battery swapping station in the corresponding time period is merged, and the number of battery swapping vehicles in each time period can be obtained. Furthermore, the time period with a large number of battery swapping vehicles can be estimated as the peak time period of the battery swapping station through the number of battery swapping vehicles in each time period.

[0047] Preferably, in order to be able to determine the peak time period of stations in the current diversion area and at the same time avoid the problem that it is difficult to analyze a single data source to obtain the peak time that can accurately reflect the area, in a feasible embodiment, before predicting the peak time period of each of the swapping stations based on the recent swapping data to be analyzed of each swapping station in the current diversion area, the method further includes the following process:

[0048] First, obtain the swapping orders of each of the swapping stations in the current diversion area within a preset time period to determine the recent swapping data of each of the swapping stations based on the swapping orders. That is, the recent swapping data of each swapping station can be obtained through the API interface of the swapping server in each swapping station. However, during the data transmission and data acquisition process, data quality problems may occur due to various reasons. Therefore, in order to be able to fully reflect the passenger flow changes of each swapping station and improve the accuracy of the peak period prediction range, obtain the data composition elements of each initial recent swapping data to perform integrity detection on each recent swapping data based on the data composition elements. If data loss is found during the integrity detection process, the recent swapping variable corresponding to the data composition element can be obtained, and its mean value can be calculated, and then the mean value is used to fill the data. After processing based on this method, the recent swapping data is more complete and reliable, which helps to analyze the rules and trends of swapping behaviors and provides reliable data support for subsequent prediction of peak time periods and improvement of the operation efficiency of swapping stations.

[0049] And / or, before obtaining the swapping orders of each of the swapping stations in the current diversion area within a preset time period to determine the recent swapping data of each of the swapping stations based on the swapping orders, the method further includes:

[0050] First, divide with the administrative region as the boundary to obtain the initial diversion areas corresponding to multiple administrative regions. Then obtain the road network structure data and the swapping station locations within the initial diversion areas. It should be noted that the road network structure data includes: expressway network structure data, elevated highway network structure data, etc. By obtaining the road network structure data and the swapping station locations, it is convenient to better determine the location distribution of swapping stations in each initial diversion area, which helps to better divert the unevenly distributed swapping stations subsequently and solve the problem that it is easy to have difficulties in operation during the peak period due to factors such as geographical location and traffic. And by taking the administrative region as the basis and combining the road network structure data and the swapping station locations, multiple initial diversion areas can be more accurately divided. These areas not only consider the geographical boundaries but also incorporate the actual traffic flow conditions, making the area division more in line with the actual needs.

[0051] After obtaining the road network structure data and the positions of battery swapping stations within the initial diversion area, multiple traffic directed graphs of the battery swapping stations within the initial diversion area are established based on the positions of each battery swapping station and the road network structure data. It should be noted that the edges of the traffic directed graph are traffic costs, and the traffic costs include data such as distance, time, and highway tolls. By establishing the traffic directed graph of the battery swapping stations within the initial diversion area, the passing paths and traffic costs between different battery swapping stations are clearly represented, which helps to determine the passable paths between battery swapping stations and road conditions such as traffic congestion. By taking the road conditions into consideration for diversion, a comprehensive consideration of multi-dimensional parameters is achieved, which is closer to the actual scenario of vehicle driving compared to the existing method of diversion based only on distance. Then, based on the multiple traffic directed graphs, the passing paths and traffic costs between each battery swapping station are determined. Then, each battery swapping station is clustered in turn based on the passing paths and traffic costs, and the initial diversion area is divided based on the clustering results to obtain the current diversion area.

[0052] In this process, the traffic directed graph established based on the positions of battery swapping stations and road network structure data provides a scientific basis for determining the optimal passing path between battery swapping stations by quantifying traffic costs, which helps to ensure that when users need to swap batteries, they can find a battery swapping station that is close and has convenient transportation faster, thereby shortening the waiting time of users and improving the efficiency of battery swapping diversion. Through the clustering analysis combining passing paths and traffic costs, the system can identify the distribution of battery swapping stations within each diversion area, and then cluster the stations with low traffic costs and short distances to obtain the current diversion area. This reasonable diversion area division and determination of the layout of battery swapping stations help to guide users to disperse to other battery swapping stations that are close and have convenient transportation within the current diversion area through reasonable exposure adjustment in the future, thereby reducing the pressure on popular battery swapping stations and avoiding the occurrence of queuing waiting phenomena. At the same time, it can also improve the utilization rate of idle stations and optimize the overall allocation of battery swapping resources.

[0053] In a feasible embodiment, based on the recent battery swapping data to be analyzed of each battery swapping station within the current diversion area, the peak time periods of each battery swapping station are predicted, which specifically includes:

[0054] Sort the recent battery swapping data to be analyzed according to the chronological order, so as to determine the number of battery swapping users corresponding to each preset time period based on the sorted recent battery swapping data to be analyzed. For example, in an application scenario, assuming that a battery swapping station needs to determine the preset time period, taking each hour as an example, it is necessary to export the battery swapping data of each hour in the recent day from the system of the battery swapping station. These battery swapping data should at least include the battery swapping time and user information. Then, sort these battery swapping data based on the battery swapping time corresponding to each battery swapping data. After sorting, count the IDs of each battery swapping user corresponding to each hour in the recent day. According to the number of battery swapping user IDs in the battery swapping data corresponding to each hour in the recent day, the number of battery swapping users corresponding to each preset time period can be determined. Then, based on the number of battery swapping users corresponding to each battery swapping station in each preset time period, determine the peak time period of each battery swapping station. That is, after obtaining the number of battery swapping users corresponding to each battery swapping station in each time period, by observing the change in the number of battery swapping users at each battery swapping station in each time period, the time period with a significant increase in the number of users can be found. A threshold of the number of battery swapping users can be set, such as 1.5 times or higher of the average number of battery swapping users, so as to regard the time period with the number of users exceeding this threshold as the peak time period.

[0055] In another feasible embodiment, based on the recent battery swapping data to be analyzed of each battery swapping station in the current diversion area, predicting the peak time period of each said battery swapping station may further include the following steps:

[0056] First, according to the recent battery swapping data to be analyzed of each battery swapping station, battery swapping records similar to the current recent battery swapping data to be analyzed can be obtained from the historical records of each battery swapping station, so as to determine the historical peak time period of each battery swapping station corresponding to the recent battery swapping data to be analyzed according to the battery swapping records. Analyze and determine the daily law of the change of battery swapping demand over time by using the historical peak time period as a conventional experience. Thus, according to the historical peak time period of each battery swapping station, determine the segmentation interval of the statistical time of the battery swapping data in the current diversion area.

[0057] Group the recent battery swapping data to be analyzed of each battery swapping station according to the determined segmentation interval to obtain a group of recent battery swapping data to be analyzed, and count the battery swapping flow of the group of recent battery swapping data to be analyzed. Based on this method, the conventional demand of the battery swapping stations in the actual operation scenario is fully considered, and grouping helps to analyze the recent battery swapping data more precisely, and further determine the change of the battery swapping flow of the battery swapping stations in each time segment.

[0058] To determine the traffic flow in each time period, the charging and swapping traffic of the recently analyzed charging and swapping data group to be analyzed is statistically counted, which can clearly and intuitively reflect the charging and swapping traffic of each charging and swapping station within the segmented interval. After statistically counting the charging and swapping traffic of the recently analyzed charging and swapping data group to be analyzed, by comparing the preset charging and swapping traffic threshold with the charging and swapping traffic of each recently analyzed charging and swapping data group to be analyzed, the peak time period of each charging and swapping station in the current shunt area can be determined. Through the method of statistical counting and comparison, the time period with a large charging and swapping traffic can be quickly determined as the peak time period of the station.

[0059] Preferably, in a feasible implementation manner, by comparing the preset charging and swapping traffic threshold with the charging and swapping traffic of each recently analyzed charging and swapping data group to be analyzed, the peak time period of each charging and swapping station in the current shunt area is determined, which is specifically implemented by the following method:

[0060] First, in order to accurately capture the change in charging and swapping demand, so as to determine the time range corresponding to the peak time period of the station, and thus facilitate targeted shunt processing for the peak time period of the station, in the embodiments of this specification, the change trend of the charging and swapping traffic of each charging and swapping station will be determined according to the charging and swapping traffic of each recently analyzed charging and swapping data group to be analyzed. If it is determined after analysis that the change trend is an upward trend and the charging and swapping traffic of the recently analyzed charging and swapping data group to be analyzed exceeds the preset charging and swapping traffic threshold, then it can be determined that this process is in the starting stage or the continuous stage of the charging and swapping peak. Therefore, the time point when the charging and swapping traffic of the recently analyzed charging and swapping data group to be analyzed reaches the preset charging and swapping traffic threshold is determined as the starting time point of the peak time period. On the contrary, if the change trend is a downward trend and the charging and swapping traffic of the recently analyzed charging and swapping data group to be analyzed exceeds the preset charging and swapping traffic threshold, then it can be determined that the time point when the charging and swapping traffic of the recently analyzed charging and swapping data group to be analyzed reaches the preset charging and swapping traffic threshold is the end time point of the peak time period. Then, according to the starting time point and the end time point, the peak time period of each charging and swapping station is determined. This method ensures that the judgment of the peak time period is both timely and accurate, and because it is based on the dynamic analysis of data, this method can predict the peak time period in advance.

[0061] In a feasible implementation manner of this specification, the process of grouping the recently analyzed charging and swapping data of each charging and swapping station based on the historical peak time period of each charging and swapping station can be implemented by the following method:

[0062] One method is to determine the segmentation interval of the statistical time of the battery replacement data in the current diversion area according to the historical peak time period of the battery replacement station. Then, group the recent battery replacement data to be analyzed at the battery replacement station based on the segmentation interval. However, this method generally targets the grouping process where the segmentation interval is an integer. Therefore, in the second method, when the segmentation interval is not an integer, in order to ensure that the segmentation interval corresponds to the peak time period of the station, the segmentation interval and the average peak time period of the statistical time of the battery replacement data in the current diversion area are determined based on the historical peak time period of the battery replacement station. Then, group the recent battery replacement data to be analyzed at the battery replacement station based on the segmentation interval and the average peak time period. The third method is to determine the segmentation interval of the statistical time of the battery replacement data in the current diversion area according to the historical peak time period of the battery replacement station. If the segmentation interval is an integer, then group the recent battery replacement data to be analyzed at the battery replacement station according to the segmentation interval. If the segmentation interval is not an integer, then determine the average peak time period of the statistical time of the battery replacement data in the current diversion area based on the historical peak time period of the battery replacement station, and group the recent battery replacement data to be analyzed at the battery replacement station based on the segmentation interval and the average peak time period. In this process, by determining the segmentation interval and the average peak time period based on the historical peak time period, the data grouping is closer to the periodic change of the actual battery replacement demand. For the case where the segmentation interval is an integer, group directly based on the segmentation interval, which simplifies the processing flow and improves the analysis efficiency. For the case where the segmentation interval is not an integer, introduce the average peak time period to assist in grouping, so that through accurate data grouping, the change of the battery replacement demand in different time periods can be understood more accurately.

[0063] Preferably, after predicting the site peak time period of each battery replacement station, the method further includes:

[0064] If it is determined that the current time is within the time range corresponding to the site peak time period, obtain the exposure click data of each battery replacement station in the current diversion area, the user data corresponding to each exposure click data, and the current battery quantity at regular intervals according to the App buried point data; it should be noted that the user data at least includes: the user location corresponding to the vehicle intending to go to the battery replacement station for battery replacement, the remaining SOC value of the vehicle, and the current battery quantity. By obtaining the exposure click data, the user data corresponding to each exposure click data, and the current battery quantity, it facilitates the subsequent judgment on whether the load of each battery replacement station exceeds the threshold, helps to adjust the exposure degree of the overloaded battery replacement station in a timely manner, and realizes battery replacement diversion.

[0065] S102: Predict the number of arriving battery replacement vehicles and the number of replaceable batteries at the station end at the corresponding site peak time period for each battery replacement station according to the exposure click data corresponding to each battery replacement station, the user data corresponding to the exposure click data, and the current battery quantity.

[0066] In a feasible embodiment of this specification, according to the exposure click data corresponding to each swapping station site, the user data corresponding to the exposure click data, and the current number of batteries, the number of arriving swapping vehicles during the peak time period of the site and the number of swappable batteries at the station end are predicted, which specifically includes:

[0067] First, determine the intended swapping traffic of each swapping station site through the exposure click data. The method of determining the intended swapping traffic of each swapping station site based on the exposure click data helps to understand the selection intention of each user for each swapping station in the current diversion area, thus facilitating the statistics of the possible arriving swapping vehicles at each swapping station site and providing an analysis basis for the operation decision-making of each swapping station site. After obtaining the exposure click data of each item, in order to remove the vehicles that cannot reach due to insufficient power in the determined intended swapping traffic, thereby improving the accuracy. It is necessary to obtain the user location and the remaining SOC value of the vehicle corresponding to each exposure data, and then filter the intended swapping traffic according to the user location and the remaining SOC value of the vehicle to obtain the initially predicted arriving vehicles. By filtering based on the remaining SOC value of the vehicle, the vehicle traffic that cannot reach is filtered, thus concentrating the attention on those vehicles that are truly likely to arrive at the station for swapping, improving the accuracy and efficiency of the prediction. Then, according to the user data corresponding to the initially predicted arriving vehicles, the location information of the swapping station site, and the peak time period of the site, predict the number of arriving swapping vehicles during the peak time period of the site, that is, determine that the initially predicted arriving vehicles can reach the swapping station site within the time range of the peak time period. At the same time, determine the average swapping traffic of the swapping station site corresponding to the peak time period of the site, and based on the current number of batteries and the average swapping traffic, predict the number of swappable batteries at the station end of the swapping station site corresponding to the peak time period of the site. By fully combining the average swapping traffic corresponding to the peak time period of the site with the real scenario, the stable and reliable number of swappable batteries at the station end during the peak time period of the site is predicted in a stable manner by using the average swapping traffic.

[0068] Preferably, in one or more embodiments of this specification, the user data includes the driving data of the user. Predicting the number of arriving swapping vehicles during the peak time period of the site based on the user data corresponding to the initially predicted arriving vehicles, the location information of the swapping station site, and the peak time period of the site includes the following process:

[0069] First, determine the distance between the user location corresponding to the initially predicted arriving vehicle and the corresponding battery swapping station. Then, based on the distance and the user's driving data, estimate the user's arrival time. Next, compare the arrival time with the time range to determine whether to filter the initially predicted arriving vehicle, and predict the arriving battery swapping vehicles during the peak time period of the station. By determining that the initially predicted arriving vehicle can reach the battery swapping station within the time range of the peak time period based on the user's driving vehicle data and the distance, different users' driving habits are fully considered, making the prediction and filtering process more rigorous. According to the historical battery swapping records corresponding to the current time, estimate the average battery swapping flow rate during the peak time period of the station. Then, based on the current battery quantity and the average battery swapping flow rate, predict the number of replaceable batteries at the station end during the peak time period of the station. By combining the historical battery swapping records, the real-world scenario is fully integrated, and the number of replaceable batteries at the station end during the peak time period of the station is predicted in a stable and reliable manner in the form of the average battery swapping flow rate.

[0070] Preferably, in a feasible embodiment of this specification, determine the average battery swapping flow rate of the battery swapping station corresponding to the peak time period of the arrival station, and based on the current battery quantity and the average battery swapping flow rate, predict the number of replaceable batteries at the station end of the battery swapping station corresponding to the peak time period of the arrival station. The specific process includes the following:

[0071] Based on the current battery quantity and the battery swapping speed of the battery swapping station, determine the initial number of replaceable batteries corresponding to each time period of the battery swapping station, achieving accurate prediction based on actual data. Then, according to the historical battery swapping records corresponding to the current time of the battery swapping station, estimate the average battery swapping flow rate of the battery swapping station during the peak time period of the arrival station. Based on the average battery swapping flow rate and the initial number of replaceable batteries, determine the remaining number of replaceable batteries corresponding to each time period of the battery swapping station, and summarize the remaining number of replaceable batteries corresponding to each time period to determine the number of replaceable batteries at the station end during the peak time period of the station. By predicting the number of replaceable batteries at the station end during the peak time period of the station, it is convenient to divert user vehicles in a timely manner during the peak time period, thus avoiding the problem of long waiting times for users to queue for battery swapping due to overloading at a single station end.

[0072] Preferably, in a feasible embodiment of this specification, filter the intended battery swapping flow rate based on the user location and the remaining SOC value of the vehicle to obtain the initially predicted arriving vehicle. Specifically, it includes:

[0073] Determine the user's location and the corresponding battery swapping station based on the exposure click data, obtain one or more traffic directed graphs where the battery swapping stations are located, and determine the passable paths between the user's location and the battery swapping stations based on these directed graphs. By determining the passable paths between the user's location and the battery swapping stations based on the directed graph with the passing cost as the edge in the above embodiments, it avoids the problem that the passable paths determined only based on distance in the prior art are difficult to adapt to the complex needs of users, and further leads to the difficulty in considering the user's personal habits for the initially predicted arriving vehicles, resulting in inaccurate prediction. Then, based on the SOC demand values of each section in the passable paths, determine the total SOC demand values of each passable section. It can be understood that the SOC demand value is the SOC value that the vehicle to be battery-swapped needs to consume when passing through different sections from a current coordinate position to each initial battery swapping station. That is, by calculating the different total SOC demand values of each passable section, it helps to understand the battery demand situation of the battery-swapped vehicle on different sections. Furthermore, when it is determined that the total SOC demand values of each passable section are all greater than the remaining SOC value of the vehicle in combination with the actual scenario, it indicates that the vehicle is difficult to reach the intended battery swapping station. Therefore, this arriving vehicle in the intended battery swapping traffic can be filtered to obtain the initially predicted arriving vehicles.

[0074] S103: Adjust the exposure of each battery swapping station by comparing the number of arriving battery-swapped vehicles and the number of replaceable batteries at the station end between each battery swapping station to achieve user diversion.

[0075] In one embodiment, when adjusting the exposure of the battery swapping station to achieve user peak shaving and diversion, based on the obtained number of arriving battery-swapped vehicles and the number of replaceable batteries at the station end, it is possible to estimate how many people are expected to go to the station during the peak time period and how many replaceable batteries are left at the station, and then compare to see if the exposure needs to be adjusted. When the expected number of people going is higher than the battery supply at the station, it means that the exposure of the station in the App needs to be adjusted. The adjustment method is to reduce the exposure of this station in the App. For example, in the sorting of the station list, move the station to the bottom as much as possible to reduce the exposure rate; increase the difficulty of searching for these stations, and the search ranking is behind; or add a prompt at the position of information exposure to let users go during off-peak hours. By adjusting the exposure rate in this way, it avoids the problem of poor equal diversion effect caused only by user selection.

[0076] Specifically, in a feasible implementation manner of this specification, by comparing the number of arriving battery-swapped vehicles and the number of replaceable batteries at the station end between each battery swapping station, and the battery swapping records during the historical peak time period in each battery swapping station, adjust the exposure of each battery swapping station. Specifically, it includes:

[0077] Compare the arriving battery - swapping vehicles between different battery - swapping stations and the number of replaceable batteries at the station end, so as to determine the battery - swapping stations to be balanced in the current diversion area based on the comparison results. Through the comparison between each battery - swapping station, the battery - swapping stations that need to be balanced in the current diversion area can be determined, thus facilitating the targeted adjustment of the battery - swapping stations to be balanced, solving the problem that when based on user selection, due to personal preference problems, the diversion is likely to be unbalanced, which in turn affects the operation and promotion of the battery - swapping stations. Based on the historical peak time period of the battery - swapping stations to be balanced, multiple historical arriving battery - swapping vehicles corresponding to the number of replaceable batteries at the station end and historical feedback information during the historical peak time period can be determined. Since the historical feedback information is used to indicate whether users obtain effective charging services. Therefore, through the filtered historical arriving battery - swapping vehicle data, that is, removing the vehicles that do not receive effective charging according to user feedback, the number of vehicles that the battery - swapping station can actually support during the peak time period can be estimated more accurately, and the historical arriving battery - swapping vehicles after screening can be obtained. Then, based on the average value of the historical arriving battery - swapping vehicles, the sustainable arriving battery - swapping vehicles corresponding to the battery - swapping station are determined. If it is determined that the sustainable arriving battery - swapping vehicles are less than the arriving battery - swapping vehicles, it means that the battery - swapping station is difficult to handle a large number of arriving battery - swapping vehicles during the peak time period. Therefore, at this time, based on the difference between the arriving battery - swapping vehicles and the sustainable arriving battery - swapping vehicles, the number of vehicles exceeding the capacity of the battery - swapping station can be determined, and the degree of reduction can be obtained based on the vehicle data exceeding the capacity to determine the downward adjustment position of each battery - swapping station, realizing the adjustment of the exposure rate.

[0078] Preferably, in a feasible implementation manner of this specification, based on the difference between the number of arriving battery - swapping vehicles and the number of sustainable arriving battery - swapping vehicles, the exposure of each battery - swapping station is adjusted, specifically including:

[0079] Determine the difference between the number of arriving battery - swapping vehicles and the number of sustainable arriving battery - swapping vehicles, so as to determine the downward adjustment value of the exposure rate of the battery - swapping station based on the size of the difference of each battery - swapping station. Then, update the exposure of the battery - swapping station through the downward adjustment value of the exposure rate to determine the current exposure position of the battery - swapping station. For example: At 10 am on a certain day, the system detects that the number of arriving battery - swapping vehicles at Station A is 50, while the current number of sustainable battery - swapping vehicles at this station, that is, the maximum number of vehicles that the station can handle without causing too long a queue, is 40. Then, at this time, the difference between the number of arriving battery - swapping vehicles and the number of sustainable arriving battery - swapping vehicles at Station A is 10. Assuming that the preset rule is that for every vehicle exceeding the limit, the exposure rate is reduced by 0.5%, then the exposure rate of Station A needs to be reduced by 5%. That is, by calculating the difference between the number of arriving battery - swapping vehicles and the number of sustainable battery - swapping vehicles in real - time, the system can dynamically adjust the exposure rate of each battery - swapping station, which helps to guide users to relatively idle stations during the peak period of battery - swapping demand, thereby optimizing the allocation of battery - swapping resources, reducing user waiting time, and improving battery - swapping efficiency.

[0080] And / or, determine the difference between the number of vehicles arriving at the power swap station for battery replacement and the number of vehicles that can maintain the arrival of vehicles for battery replacement, and based on the magnitude of the difference, determine the search difficulty value of the power swap station. Then, through the search difficulty value, sort and update the search positions of the power swap stations to determine the current search positions of the power swap stations. Continuing with the above example, if it is set that for each vehicle exceeding the limit, the search difficulty value increases by 1 point, then the search difficulty value of Station A increases by 10 points. At this time, in the user's search results, Station A will be ranked in a more backward position due to the higher search difficulty value, reducing the likelihood of the user directly selecting this station. By increasing the search difficulty for changes in search positions, it can indirectly inform users which stations are currently busy, thus prompting users to choose other more convenient stations for battery replacement. By increasing the search difficulty of busy stations, the operating pressure on these stations can be effectively alleviated, avoiding problems such as a decline in service quality caused by overcrowding.

[0081] And / or, determine the difference between the number of vehicles arriving at the power swap station for battery replacement and the number of vehicles that can maintain the arrival of vehicles for battery replacement to obtain a comparison result between the difference and a preset threshold; according to the comparison result, determine whether to add a reminder pop-up window for off-peak periods at the current exposure position corresponding to the power swap station. Continuing with the above example, if a preset threshold is set, for example, when the number of vehicles arriving at the power swap station for battery replacement exceeds 20% of the maintainable quantity, a reminder for off-peak periods is triggered. Then, the excess ratio of Station A is 25%, exceeding the preset threshold. At this time, when the user searches for or navigates to Station A, the system automatically pops up a reminder pop-up window saying "The current station is busy. It is recommended to replace the battery during off-peak hours" at its current exposure position, such as next to the icon on the map or in the search result list, guiding the user to consider other stations. In this way, when the power swap station is approaching or reaching its carrying capacity, the system can immediately remind the user through a pop-up window of the possible waiting situation for battery replacement at this station. It can assist users in selecting other power swap stations for battery replacement operations, thus avoiding unnecessary waiting time for users. By guiding users to replace the battery during off-peak hours, the system can balance the battery replacement load of each station, avoiding resource waste and efficiency decline caused by overcrowding at some stations.

[0082] In another embodiment of this specification, a method for diverting users of power swap stations is provided, as Figure 2 shown. The method specifically includes the following steps S201 - S204:

[0083] S201: Collect the recent battery replacement data of each power swap station within the current diversion area, and preprocess the recent battery replacement data to obtain the recent battery replacement data to be analyzed.

[0084] First, in order to determine the peak time period of stations in the current diversion area and avoid the problem that it is difficult to analyze a single data source to obtain the peak time that can accurately reflect the area, in a feasible embodiment of this specification, the recent battery swapping data of each battery swapping station in the current diversion area is collected. By obtaining the machine battery swapping data of each battery swapping station, multi-source and multi-dimensional data acquisition is achieved, which helps to improve the rationality in the diversion analysis process. In addition, through the preprocessing of the recent battery swapping data, the recent battery swapping data to be analyzed is obtained, which helps to ensure the consistency of the recent battery swapping data of each battery swapping station and helps to reduce the adverse impact of redundant data on prediction.

[0085] In a feasible embodiment, when dividing the current diversion area, first, it is divided with the administrative region as the boundary to obtain the initial diversion areas corresponding to multiple administrative regions. Then, the road network structure data and the positions of battery swapping stations within the initial diversion areas are obtained. Among them, it should be noted that the road network structure data includes data such as the expressway network structure data and the elevated highway network structure data. By obtaining the road network structure data and the positions of battery swapping stations, it is convenient to better determine the location distribution of battery swapping stations in each initial diversion area, which helps to better divert the unevenly distributed battery swapping stations in the subsequent process and solve the problem that it is easy to have difficulties in operation during the peak period due to factors such as geographical location and traffic factors, resulting in uneven distribution of the passenger flow of battery swapping stations.

[0086] After obtaining the road network structure data and the positions of battery swapping stations within the initial diversion area, based on the positions of each battery swapping station and the road network structure data, multiple traffic directed graphs of battery swapping stations within the initial diversion area are established. Among them, it should be noted that the edges of the traffic directed graph are traffic costs, and the traffic costs include data such as distance, time, and highway tolls. By establishing the traffic directed graphs of battery swapping stations within the initial diversion area, the passing paths and traffic costs between different battery swapping stations are clearly represented, which helps to determine the passable paths between battery swapping stations and road conditions such as traffic congestion. By including the road conditions in the scope of diversion consideration, comprehensive consideration of multi-dimensional parameters is achieved. Compared with the existing method of only diverting based on distance, it is closer to the actual scenario of vehicle driving and also helps to improve the traffic efficiency of reaching the battery swapping stations.

[0087] Furthermore, after obtaining multiple traffic directed graphs of battery swapping stations within the initial diversion area, each battery swapping station can be clustered in turn based on the passing paths and traffic costs, and the initial diversion area can be further divided based on the clustering results, which helps to better organize and manage the diversion between battery swapping stations and avoid the problem of low customer experience caused by long-distance diversion.

[0088] In a feasible embodiment, in the process of obtaining the recent battery swapping data to be analyzed, first, the recent battery swapping data of each battery swapping station is obtained through the API interface of the battery swapping server in each battery swapping station. Due to various reasons during data transmission and data acquisition, the data quality may be problematic. Therefore, duplicate detection is performed on the recent battery swapping data of each battery swapping station to achieve data cleaning, and then the initial recent battery swapping data is obtained. Based on the data cleaning process, duplicate data and error data can be excluded, thereby reducing the computing power cost consumed by the redundant data repetition analysis, and at the same time reducing the impact of error data on accuracy, which is beneficial to improving the credibility in the subsequent prediction process. In addition, in order to fully reflect the passenger flow changes of each battery swapping station and improve the accuracy of the peak period prediction range, the data composition elements of each initial recent battery swapping data are obtained to perform integrity detection on each initial recent battery swapping data based on the data composition elements. After obtaining the initial recent battery swapping data, detection based on the data composition elements can ensure the integrity and consistency of the data. If data loss is found during the integrity detection process, the recent battery swapping variables corresponding to the data composition elements can be obtained, their mean value can be calculated, and then the data can be filled with the mean value. After processing based on this method, the recent battery swapping data is more complete and reliable, which helps to analyze the rules and trends of battery swapping behaviors, provides reliable data support for predicting peak time periods in the future, and improves the operation efficiency of the battery swapping stations.

[0089] S202: Predict the peak time periods of each of the battery swapping stations based on the recent battery swapping data to be analyzed.

[0090] In an embodiment, after obtaining the recent battery swapping data to be analyzed based on the above step S101S, different time period division methods can be customarily determined based on different operation requirements of the battery swapping stations. For example: division can be made according to granularities such as hours, half-hours, or ten minutes. For example, a day can be divided into time periods such as morning (6:00 - 9:00), forenoon (9:00 - 12:00), noon (12:00 - 14:00), afternoon (14:00 - 18:00), and evening (18:00 - 23:00). Then, the recent battery swapping data to be analyzed of each battery swapping station within the corresponding time period is merged, and the number of battery swapping vehicles in each time period can be obtained. Furthermore, the time period with a large number of battery swapping vehicles can be estimated through the number of battery swapping vehicles in each time period as the peak time period of the battery swapping station.

[0091] In another feasible embodiment, the method for predicting the peak time periods of each battery swapping station based on the recent battery swapping data to be analyzed can also be:

[0092] First, based on the recent battery swapping data to be analyzed for each battery swapping station, battery swapping records similar to the current recent battery swapping data to be analyzed can be obtained from the historical records of each battery swapping station, so as to determine the historical peak time periods of each battery swapping station corresponding to the recent battery swapping data to be analyzed according to the battery swapping records. Analyze and determine the daily law of the change of battery swapping demand over time by taking the historical peak time period as a conventional experience. Then, according to the historical peak time periods of each battery swapping station, determine the segmentation interval of the statistical time of the battery swapping data within the current diversion area.

[0093] Group the recent battery swapping data to be analyzed for each battery swapping station according to the determined segmentation interval to obtain a group of recent battery swapping data to be analyzed, and count the battery swapping flow of the group of recent battery swapping data to be analyzed. Based on this method, the conventional requirements of the battery swapping stations in the actual operation scenario are fully incorporated, and grouping helps to analyze the recent battery swapping data more precisely, and further determine the change of the battery swapping flow of the battery swapping stations within each time segment.

[0094] To determine the flow situation in each time period, count the battery swapping flow of the group of recent battery swapping data to be analyzed, which can clearly and intuitively reflect the battery swapping flow situation of each battery swapping station within the segmentation interval. After counting the battery swapping flow of the group of recent battery swapping data to be analyzed, it is convenient to determine the site peak time periods of each battery swapping station within the current diversion area by comparing the preset battery swapping flow threshold with the battery swapping flow of each group of recent battery swapping data to be analyzed. Through the methods of statistics and comparison, the time period with a large battery swapping flow can be quickly determined as the site peak time period.

[0095] S203: Predict the arriving battery swapping vehicles and the available battery data at the station end during the site peak time period according to the exposure click data and the current battery data corresponding to each battery swapping station.

[0096] In one embodiment, when calculating the arriving battery - swapping vehicles and the available battery data at the station end during the peak period of the computing station, first, in the period approaching the peak battery - swapping time, the exposure - click data of the station is obtained regularly through the App buried - point data to roughly obtain the user data of those who currently intend to go to the station. At the same time, combining the user location and the remaining SOC data of the vehicle, the number of users whose battery power can support arriving at the station is screened out. By screening based on the remaining SOC, the roughly estimated user data can be filtered, thereby improving the prediction accuracy. After filtering out the number of users whose battery power can support arriving at the station, the estimated arrival time of the vehicle can be calculated through the vehicle speed, the distance between the user and the station, and then the number of users whose arrival time is during the peak period is further screened out from the number of users whose battery power can support arriving at the station. By successively superimposing different levels of screening methods, the reliability of the prediction of battery - swapping vehicles is improved, avoiding the problem of low prediction accuracy due to less consideration of actual problems in single - method prediction. Then, based on the current battery data at the station end, the current battery - swapping traffic flow, the charging speed, and the average traffic flow during the previous peak - approaching period, it is estimated how many available batteries are left during the peak period, so as to subsequently determine whether the battery - swapping station during the peak period can meet the demand of battery - swapping vehicles based on the available battery data at the station end, and then make timely scheduling adjustments based on the judgment result to ensure that users can carry out normal battery - swapping driving.

[0097] In another feasible embodiment, based on the exposure - click data and the current battery data corresponding to each battery - swapping station, the arriving battery - swapping vehicles and the available battery data at the station end during the peak period of the station are predicted, which specifically includes:

[0098] First, if it is determined that the current time is within the time range corresponding to the peak period of the station, the exposure - click data and the current battery data of each battery - swapping station in the current diversion area are obtained regularly based on the App buried - point data, so as to determine the intended battery - swapping traffic flow of each battery - swapping station based on the exposure - click data. By determining the intended battery - swapping traffic flow of each battery - swapping station based on the exposure - click data, this helps to understand the selection intention of each user for each battery - swapping station in the current diversion area, thus facilitating the statistics of the possible arriving battery - swapping vehicles at each battery - swapping station and providing an analysis basis for the operation decision - making of each battery - swapping station. After obtaining the exposure - click data of each station, in order to remove the vehicles whose battery power cannot support reaching the station from the determined intended battery - swapping traffic flow, thereby improving the accuracy. It is necessary to obtain the user location and the remaining SOC value of the vehicle corresponding to each exposure data, and then filter the intended battery - swapping traffic flow according to the user location and the remaining SOC value of the vehicle to obtain the initial predicted arriving vehicles. By filtering based on the remaining SOC value of the vehicle, the traffic flow of vehicles that cannot reach is filtered, thus concentrating on those vehicles that are truly likely to arrive at the station for battery - swapping, improving the prediction accuracy and efficiency.

[0099] Further, when predicting the arriving battery - swapping vehicles during the peak period of a station, in order to determine whether a vehicle can reach the battery - swapping station during the peak period. First, determine the distance between the user location corresponding to the initially predicted arriving vehicle and the corresponding battery - swapping station, and then, based on the distance and the user's driving data, estimate the user's arrival time. Then, compare the arrival time with the time range to determine whether to filter the initially predicted arriving vehicle, so as to predict the arriving battery - swapping vehicles during the peak period of the station. By determining that the initially predicted arriving vehicle can reach the battery - swapping station within the time range of the peak period based on the user's driving vehicle data and the distance, different users' driving habits are fully considered, making the prediction and filtering process more rigorous. According to the historical battery - swapping records corresponding to the current time, estimate the average battery - swapping flow during the peak period of the station, and then, based on the current battery data and the average battery - swapping flow, predict the available battery data at the station end during the peak period of the station. By combining the historical battery - swapping records, the real - world scenario is fully integrated, and the stable and reliable available battery data at the station end during the peak period of the station is predicted in a stable way with the average battery - swapping flow.

[0100] Further, in a feasible embodiment, filter the intended battery - swapping flow based on the user location and the remaining SOC value of the vehicle to obtain the initially predicted arriving vehicles, which specifically includes:

[0101] Determine the user location and the corresponding battery - swapping station according to the exposure - click data, obtain one or more traffic directed graphs where the battery - swapping station is located, and determine the passable path between the user location and the battery - swapping station based on these directed graphs. By determining the passable path between the user location and the battery - swapping station based on the directed graph with the passing cost as the edge determined in the above - mentioned embodiment, it avoids the problem that the passable path determined only based on the distance in the prior art is difficult to meet the complex needs of users, and further leads to the difficulty in considering the user's personal habits in the initially predicted arriving vehicles, resulting in inaccurate prediction. Then, based on the SOC demand values of each section in the passable path, determine the total SOC demand value of each passable section. It can be understood that the SOC demand value is the SOC value that the vehicle to be battery - swapped needs to consume when passing through different sections from a current coordinate position to each initial battery - swapping station. That is to say, by calculating the different total SOC demand values of each passable section, it helps to understand the battery demand situation of the battery - swapping vehicle on different sections. Then, when it is determined that the total SOC demand value of each passable section is greater than the remaining SOC value of the vehicle in combination with the actual scenario, it means that the vehicle is difficult to reach the intended battery - swapping station. Therefore, this arriving vehicle in the intended battery - swapping flow can be filtered to obtain the initially predicted arriving vehicles.

[0102] S204: By comparing the arriving battery - swapping vehicles and the available batteries at the station terminals among the battery - swapping stations, as well as the battery - swapping records during the historical peak periods within each battery - swapping station, exposure adjustment is performed on each of the battery - swapping stations to achieve user diversion based on the exposure adjustment.

[0103] In one embodiment, when performing exposure adjustment on the battery - swapping stations to achieve off - peak user visits and reach the purpose of diversion, based on the obtained arriving battery - swapping vehicles and the available batteries at the station terminals, it is possible to estimate how many people are expected to go to the station during the peak period and how many available batteries are left at the station to compare whether to adjust the exposure. When the expected number of people going is higher than the battery supply at the station, it means that the exposure of the station in the APP needs to be adjusted. The adjustment method is to reduce the exposure of the station in the APP. For example, in the sorting of the station list, the station is placed as far as possible at the bottom to reduce the exposure rate; increase the difficulty of searching for these stations, and the search ranking is behind; or add a prompt at the position of information exposure to let users visit during off - peak periods. By adjusting the exposure rate in this way, the problem of poor balanced diversion effect caused only by user selection is avoided.

[0104] In another embodiment, the specific process of performing exposure adjustment on each battery - swapping station to achieve user diversion based on the exposure adjustment includes the following:

[0105] Compare the arriving battery - swapping vehicles and the available batteries at the station terminals among the battery - swapping stations, and thus determine the battery - swapping stations to be balanced in the current diversion area based on the comparison results. Through the comparison among the battery - swapping stations, it is possible to determine the battery - swapping stations that need to be balanced in the current diversion area, which facilitates the purpose of targeted adjustment for these battery - swapping stations to be balanced, and solves the problem that when based on user selection, it is easy to cause unbalanced diversion due to personal preferences, which in turn affects the operation and promotion of the battery - swapping stations. Based on the historical peak periods of the battery - swapping stations to be balanced, a plurality of historical arriving battery - swapping vehicles corresponding to the available batteries at the station terminals and historical feedback information during the historical peak periods can be determined, so as to filter the historical arriving battery - swapping vehicles with the historical feedback information to obtain the filtered historical arriving battery - swapping vehicles. By filtering, abnormal situations or situations with poor user feedback are excluded, improving the reliability and accuracy of historical data. Then, based on the average value of the historical arriving battery - swapping vehicles, the maintainable arriving battery - swapping vehicles corresponding to the battery - swapping stations are determined. If it is determined that the maintainable arriving battery - swapping vehicles are less than the arriving battery - swapping vehicles, it means that the battery - swapping station is difficult to handle a large number of arriving battery - swapping vehicles during the peak period. Therefore, at this time, based on the difference between the arriving battery - swapping vehicles and the maintainable arriving battery - swapping vehicles, the number of vehicles exceeding the capacity of the battery - swapping station can be determined, and the degree of reduction can be obtained based on the vehicle data exceeding the capacity to determine the reduction positions of each battery - swapping station, so as to achieve the adjustment of the exposure degree.

[0106] In a specific embodiment, assume that there are three battery swapping stations, namely A, B, and C. By comparing the battery swapping vehicles arriving at these stations and the battery data available for swapping at the station end, it is found that there are more battery swapping vehicles arriving at station A, while fewer battery swapping vehicles arrive at stations B and C. Based on the comparison results, station A is determined as the battery swapping station to be balanced. At this time, according to the historical peak time period of station A, a plurality of historical battery swapping vehicles corresponding to the battery data available for swapping at the station segment of station A, as well as the historical feedback information during these historical peak time periods, are determined. Then, based on the historical feedback information, these historical battery swapping vehicles are filtered to obtain the filtered historical battery swapping vehicles of station A. According to the average value of the historical battery swapping vehicles, the number of battery swapping vehicles that can be maintained at station A is determined. Assume that it is determined that the number of battery swapping vehicles that can be maintained at station A is less than the number of battery swapping vehicles arriving at station A, indicating that station A needs to be adjusted. According to the difference between the two, the downward adjustment position of station A is determined, that is, the exposure of this station is reduced to make its load more balanced with other stations, achieving task zoning among various battery swapping stations during peak time periods, thereby reducing the waiting time of users in line and improving the user experience during the battery swapping process.

[0107] Further, in an embodiment, after adjusting the exposure of each of the battery swapping stations by comparing the battery swapping vehicles arriving at each of the battery swapping stations with the battery data available for swapping at the station end, and the battery swapping records during the historical peak time periods within each battery swapping station, the method further includes:

[0108] Real-time obtain the current exposure click data corresponding to each battery swapping station, so as to avoid the problem of inaccurate traffic diversion caused by untimely data synchronization due to user update selection. Then, compare the current exposure click data with the exposure click data to determine the change value of the intended battery swapping traffic at each battery swapping station. That is to say, the change value of the intended battery swapping traffic at each battery swapping station is grasped in real time, and the changing trend of the user's battery swapping demand is determined. Thus, based on this changing trend, if the change value of the intended battery swapping traffic at this battery swapping station continues to increase, it means that the degree of reduction in the above-mentioned exposure cannot achieve battery swapping balance. At this time, based on the change value of the intended battery swapping traffic, the downward adjustment value of the exposure rate of the battery swapping station is determined. Then, the exposure of the battery swapping station is updated through the downward adjustment value of the exposure rate to determine the current exposure position. Then, based on a preset downward adjustment threshold, it is determined whether the current exposure position has reached a certain degree of downward adjustment. If the exposure position is adjusted downward to a certain extent, a pop-up window for off-peak prompt is triggered at the current exposure position. For example, if the exposure position is adjusted downward by more than 20%, a pop-up window for off-peak prompt is triggered. By triggering the prompt pop-up window, suggestions for off-peak battery swapping are provided to users. By triggering the pop-up of the prompt pop-up window, suggestions for off-peak battery swapping can be provided to users. When the exposure position gives an off-peak prompt, users may choose to swap batteries during off-peak hours, thereby optimizing the load balance of the battery swapping station and reducing the waiting time of users.

[0109] In addition, the embodiments of this specification also provide a user diversion device for a battery swapping station, such as Figure 2 shown, a recommendation device for a battery swapping station, the device includes:

[0110] At least one processor; and,

[0111] A memory communicatively connected to the at least one processor; wherein,

[0112] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to:

[0113] Execute the user diversion method for the battery swapping station described in any of the above.

[0114] Finally, the embodiments of this specification also provide a non-volatile storage medium, such as Figure 4 shown, a non-volatile storage medium stores computer-executable instructions 401, and the computer-executable instructions 401 can: execute the user diversion method for the battery swapping station described in any of the above.

[0115] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a device, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0116] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 this flow or multiple flows and / or Figure 1 these blocks or multiple blocks.

[0117] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the functions specified in the flowchart Figure 1 one or more flowcharts and / or boxes Figure 1 one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart Figure 1 one or more flowcharts and / or boxes Figure 1 one or more boxes.

[0119] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory. The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0120] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transitory media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0121] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0122] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0123] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the apparatus, device, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments.

[0124] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0125] The above is only one or more embodiments of this specification and is not used to limit this specification. For those skilled in the art, there can be various modifications and changes to one or more embodiments of this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. A method for user diversion at a battery swapping station, characterized in that, The method includes: Based on the recent battery replacement data to be analyzed of each battery replacement station in the current diversion area, predicting the peak time period of each battery replacement station; According to the exposure click data corresponding to each battery replacement station, the user data corresponding to the exposure click data, and the current number of batteries, predicting the number of incoming battery replacement vehicles and the number of replaceable batteries at the station end of each battery replacement station during the corresponding peak time period of the station; By comparing the number of incoming battery replacement vehicles and the number of replaceable batteries at the station end between each battery replacement station, adjusting the exposure of each battery replacement station to achieve user diversion.

2. The user flow diversion method for a battery swapping station according to claim 1, wherein, Before predicting the peak time period of each battery replacement station based on the recent battery replacement data to be analyzed of each battery replacement station in the current diversion area, the method further includes: Obtaining the battery replacement orders of each battery replacement station in the current diversion area within a preset time period to determine the recent battery replacement data of each battery replacement station based on the battery replacement orders; Obtaining the data composition elements of each recent battery replacement data to perform integrity detection on each recent battery replacement data based on the data composition elements; If it is determined that there is missing data, obtaining the recent battery replacement variables corresponding to the data composition elements in each recent battery replacement data, and obtaining the average value of the corresponding recent battery replacement variables; Filling the missing data corresponding to the data composition elements in the recent battery replacement data based on the average value to obtain the recent battery replacement data to be analyzed; And / or, before obtaining the battery replacement orders of each battery replacement station in the current diversion area within a preset time period to determine the recent battery replacement data of each battery replacement station based on the battery replacement orders, the method further includes: Dividing with administrative regions as boundaries to determine multiple initial diversion areas, and obtaining the road network structure data and the positions of battery replacement stations in each initial diversion area; Based on the positions of each battery replacement station and the road network structure data, establishing multiple traffic directed graphs of the battery replacement stations in the initial diversion area; wherein, the edges of the traffic directed graph are traffic costs; Determining the passing paths and traffic costs between each battery replacement station according to the multiple traffic directed graphs; Successively clustering each battery replacement station based on the passing paths and traffic costs, and dividing the initial diversion area based on the clustering result to obtain the current diversion area.

3. The user flow diversion method for a battery swapping station according to claim 2, wherein, Predicting the peak time period of each battery replacement station based on the recent battery replacement data to be analyzed of each battery replacement station in the current diversion area specifically includes: Sorting the recent battery replacement data to be analyzed based on the time sequence to determine the number of battery replacement users corresponding to each preset time period based on the sorted recent battery replacement data to be analyzed; Determining the peak time period of each battery replacement station based on the number of battery replacement users corresponding to each battery replacement station in each preset time period; And / or, predicting the peak time period of each battery replacement station based on the recent battery replacement data to be analyzed of each battery replacement station in the current diversion area specifically includes: Determining the historical peak time period of each battery replacement station based on the recent battery replacement data to be analyzed of each battery replacement station. Group the recent battery swapping data to be analyzed for each battery swapping station based on the historical peak time periods of each said battery swapping station, so as to obtain a group of recent battery swapping data to be analyzed, and count the battery swapping flow of the group of recent battery swapping data to be analyzed; By comparing the preset battery swapping flow threshold with the battery swapping flow of each group of recent battery swapping data to be analyzed, determine the site peak time periods of each battery swapping station within the current diversion area.

4. A method for user diversion at a battery swapping station according to claim 3, characterized in that, The step of determining the site peak time periods of each battery swapping station within the current diversion area by comparing the preset battery swapping flow threshold with the battery swapping flow of each group of recent battery swapping data to be analyzed includes: Determine the changing trend of the battery swapping flow of each battery swapping station according to the battery swapping flow of each group of recent battery swapping data to be analyzed; If the changing trend is an upward trend and the battery swapping flow of the group of recent battery swapping data to be analyzed exceeds the preset battery swapping flow threshold, then determine the time point when the battery swapping flow of the group of recent battery swapping data to be analyzed reaches the preset battery swapping flow threshold as the starting time point of the peak time period; If the changing trend is a downward trend and the battery swapping flow of the group of recent battery swapping data to be analyzed exceeds the preset battery swapping flow threshold, then determine the time point when the battery swapping flow of the group of recent battery swapping data to be analyzed reaches the preset battery swapping flow threshold as the ending time point of the peak time period; Determine the site peak time periods of each battery swapping station according to the starting time point and the ending time point; And / or, the step of grouping the recent battery swapping data to be analyzed for each battery swapping station based on the historical peak time periods of each said battery swapping station includes: Based on the historical peak time periods of the battery swapping stations, determine the segmentation interval of the battery swapping data statistical time within the current diversion area; Group the recent battery swapping data to be analyzed for the battery swapping stations based on the segmentation interval; Or, Based on the historical peak time periods of the battery swapping stations, determine the segmentation interval and the average peak time period of the battery swapping data statistical time within the current diversion area; Group the recent battery swapping data to be analyzed for the battery swapping stations based on the segmentation interval and the average peak time period; Or, based on the historical peak time periods of the battery swapping stations, determine the segmentation interval of the battery swapping data statistical time within the current diversion area; If the segmentation interval is an integer, group the recent battery swapping data to be analyzed for the battery swapping stations based on the segmentation interval; If the segmentation interval is not an integer, based on the historical peak time periods of the battery swapping stations, determine the average peak time period of the battery swapping data statistical time within the current diversion area, and group the recent battery swapping data to be analyzed for the battery swapping stations based on the segmentation interval and the average peak time period; Preferably, after predicting the site peak time periods of each battery swapping station, the method further includes: If it is determined that the current time is within the time range corresponding to the peak time period of the site, the exposure click data of each battery swapping station in the current diversion area and the user data corresponding to each exposure click data are obtained regularly based on the App buried point data; wherein, the user data at least includes: the user location corresponding to the vehicle intending to go to the battery swapping station for battery swapping, the remaining SOC value of the vehicle, and the current number of batteries.

5. A method for user diversion at a battery swapping station according to claim 4, characterized in that, Predicting the number of arriving battery swapping vehicles and the number of replaceable batteries at the station end during the peak time period of the site according to the exposure click data corresponding to each battery swapping station, the user data corresponding to the exposure click data, and the current number of batteries specifically includes: Determining the intended battery swapping flow of each battery swapping station based on the exposure click data, where the intended battery swapping flow represents the vehicle data intending to go to the battery swapping station for battery swapping; Filtering the intended battery swapping flow based on the user location and the remaining SOC value of the vehicle to obtain the initial predicted arriving vehicles; Predicting the number of arriving battery swapping vehicles during the peak time period of the site based on the user data corresponding to the initial predicted arriving vehicles, the location information of the battery swapping station, and the peak time period of the site; Determining the average battery swapping flow of the battery swapping station corresponding to the peak time period of the arrival station, and predicting the number of replaceable batteries at the station end of the battery swapping station during the corresponding peak time period of the site based on the current number of batteries and the average battery swapping flow; Preferably, the user data includes the driving data of the user, and predicting the number of arriving battery swapping vehicles during the peak time period of the site based on the user data corresponding to the initial predicted arriving vehicles, the location information of the battery swapping station, and the peak time period of the site includes: Determining the distance between the initial predicted arriving vehicle and the corresponding battery swapping station based on the user location and the location information of the battery swapping station, and predicting the arrival time of the user based on the distance and the driving data of the user; Filtering the initial predicted arriving vehicles based on the comparison result between the arrival time and the time range corresponding to the peak time period of the site to determine the number of arriving battery swapping vehicles at the battery swapping station during the peak time period of the site.

6. The user flow diversion method for a battery swapping station according to claim 5, characterized in that, Determining the average battery swapping flow of the battery swapping station corresponding to the peak time period of the arrival station, and predicting the number of replaceable batteries at the station end of the battery swapping station during the corresponding peak time period of the site based on the current number of batteries and the average battery swapping flow, specifically includes: Determining the initial number of replaceable batteries corresponding to each time period of the battery swapping station based on the current number of batteries and the battery swapping speed of the battery swapping station; Estimating the average battery swapping flow of the battery swapping station during the peak time period of the arrival station according to the historical battery swapping records corresponding to the current time of the battery swapping station; Determining the remaining number of replaceable batteries corresponding to each time period of the battery swapping station according to the average battery swapping flow and the initial number of replaceable batteries, and summarizing the remaining number of replaceable batteries corresponding to each time period to determine the number of replaceable batteries at the station end during the peak time period of the site.

7. A method for user diversion at a battery swapping station according to claim 6, characterized in that, Filter the intended battery swapping traffic based on the user location and the remaining SOC value of the vehicle to obtain the initially predicted arriving vehicles, specifically including: Determine the battery swapping station points corresponding to the user according to the exposure click data, and obtain one or more traffic directed graphs where the corresponding battery swapping station points are located; Based on the one or more traffic directed graphs, determine one or more passable paths between the user location and the corresponding battery swapping station points; Based on the SOC demand values of each section in the passable paths, determine the total SOC demand value of each passable section; If it is determined that the total SOC demand values of all the passable sections are greater than the remaining SOC value of the vehicle, filter the intended battery swapping traffic to obtain the initially predicted arriving vehicles.

8. A method for user diversion at a battery swapping station according to claim 1, characterized in that, The exposure adjustment of each battery swapping station point is specifically carried out by comparing the number of arriving battery swapping vehicles and the number of replaceable batteries at the station end between each battery swapping station point, and the battery swapping records during the historical peak time periods in each battery swapping station point, specifically including: Based on the number of arriving battery swapping vehicles and the number of replaceable batteries at the station end between the battery swapping station points, determine the battery swapping station points to be balanced in the current diversion area; Based on the historical peak time periods of each battery swapping station point to be balanced, determine a plurality of historical arriving battery swapping vehicles corresponding to the number of replaceable batteries at the station end, and the historical feedback information of the users corresponding to the vehicles during each historical peak time period; wherein, the historical feedback information is used to indicate whether the user obtains effective charging service; Filter the plurality of historical arriving vehicles based on the historical feedback information to obtain the historical arriving battery swapping vehicles after filtering for the battery swapping station points to be balanced; Based on the mean value of the filtered historical arriving battery swapping vehicles, determine the number of maintainable arriving battery swapping vehicles corresponding to the battery swapping station point; If it is determined that the number of maintainable arriving battery swapping vehicles is less than the number of arriving battery swapping vehicles, perform exposure adjustment on each battery swapping station point based on the difference between the number of arriving battery swapping vehicles and the number of maintainable arriving battery swapping vehicles; Preferably, the exposure adjustment of each battery swapping station point based on the difference between the number of arriving battery swapping vehicles and the number of maintainable arriving battery swapping vehicles specifically includes: Determine the difference between the number of arriving battery swapping vehicles and the number of maintainable arriving battery swapping vehicles, so as to determine the downward adjustment value of the exposure rate of the battery swapping station point based on the magnitude of the difference of each battery swapping station point; Update the exposure of the battery swapping station point through the downward adjustment value of the exposure rate to determine the current exposure position of the battery swapping station point; And / or, determine the difference between the number of arriving battery swapping vehicles and the number of maintainable arriving battery swapping vehicles, so as to determine the search difficulty value of the battery swapping station point based on the magnitude of the difference; Update the sorting of the search positions of the battery swapping station points through the search difficulty value to determine the current search position of the battery swapping station point; And / or, determine the difference between the number of arriving battery swapping vehicles and the number of maintainable arriving battery swapping vehicles to obtain the comparison result between the difference and the preset threshold; Determine whether to add a reminder pop-up window for off-peak according to the comparison result at the current exposure position corresponding to the battery swapping station site.

9. A user diversion device for a battery swapping station, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: execute the user diversion method of the battery swapping station site according to any one of claims 1-8 above.

10. A non-volatile storage medium stores computer-executable instructions, characterized in that, The computer-executable instructions can: execute the user diversion method of the battery swapping station site according to any one of claims 1-8 above.

Images