Layout method of electric bicycle public charging station

Abstract

The invention discloses a layout method of an electric bicycle public charging station, and relates to the field of urban construction. The method comprises the following steps: firstly, training each basic site selection planning model of the mixed site selection planning model, and carrying out performance evaluation on a calculation result of each model; thirdly, comparing comprehensive evaluation results of the mixed site selection planning model and the plurality of basic models, and when the mixed site selection planning model is best in performance, determining an optimal decision threshold value of the mixed site selection planning model; then, inputting the raster data of the to-be-planned area into the mixed site selection planning model, and determining a preliminary screening result of the to-be-planned area according to a model calculation result and the optimal decision threshold; and finally, further screening the preliminary screening result based on the convenience and safety requirements of the electric bicycle rider, and determining a proper site selection layout area of the electric bicycle charging station.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly to a layout method for public charging stations of electric bicycles. Background Art

[0002] With the continuous deepening of the modern urban process, the continuous increase in urban area and various infrastructure, while bringing great convenience to the lives of urban residents, it also brings adverse factors such as increased commuting distance, increased cost, and increased time. In order to cope with the changing living environment, electric bicycles have gradually become the main short-distance transportation means for the people. At the same time, problems such as "difficult charging and few stations" and uneven charging demands have emerged, which not only affect the user experience of riders but also reduce the purchase willingness of consumers.

[0003] Most of the existing research on the site selection of electric bicycle charging stations is "oriented by charging demand", and solves and analyzes the site selection and planning problems of charging stations and battery swapping stations. The entry point for solving problems is usually limited to alleviating charging demand, and the methods and technical means used are also relatively single. This not only results in the lack of detailed and diverse site selection suggestions in the site selection results but also is out of touch with the actual environmental conditions, making it difficult to provide effective decision-making support for the site selection work of charging stations.

[0004] Therefore, optimizing the existing layout method for public charging stations of electric bicycles, constructing a reasonable site selection model, and providing more effective decision-making support for the site selection work have become urgent problems to be solved. Summary of the Invention

[0005] Based on this, it is necessary to provide a layout method for public charging stations of electric bicycles to solve the above technical problems, and this method can optimize the layout of public charging stations of electric bicycles.

[0006] The present invention adopts the following technical solutions: The present invention provides a layout method for public charging stations of electric bicycles, including: Comprehensively evaluating multiple trained basic site selection and planning models respectively through a test grid dataset to obtain the comprehensive evaluation results of each basic site selection and planning model; each grid data includes different numbers of points of interest; the points of interest include name, category, and address; Inputting the test grid dataset into a hybrid site selection and planning model to obtain the test results of each test grid, extracting the discretized eigenvalue in the test results as the optional decision threshold of the hybrid site selection and planning model, and comprehensively evaluating the hybrid site selection and planning model based on the optional decision threshold and the test results to obtain the comprehensive evaluation results of the hybrid site selection and planning model under different optional decision thresholds; the hybrid site selection and planning model is integrated by multiple basic site selection and planning models; By comparing the comprehensive evaluation results of multiple basic site selection planning models with those of the hybrid site selection planning model at different optional decision thresholds, determine the optimal decision threshold of the hybrid site selection planning model; Perform rasterization processing on the area to be planned to obtain raster data; Input the raster data of the area to be planned into the hybrid site selection planning model to obtain the preliminary planning results of each raster in the area to be planned. According to the preliminary planning results and the optimal decision threshold, determine the preliminary screening results of the area to be planned; Based on considerations of rider convenience and safety, screen the preliminary screening results to obtain the second screening results of the area to be planned, and determine the second screening results as the layout area of electric bicycle public charging stations in the area to be planned.

[0007] Preferably, in the calculation results of the hybrid site selection planning model, the values greater than or equal to the optimal decision threshold include low-confidence positive classes, medium-confidence positive classes, medium-high-confidence positive classes, and high-confidence positive classes; the preliminary screening results include setting the raster as not building a charging station, not suitable for building a charging station, suitable for building a charging station, more suitable for building a charging station, and most suitable for building a charging station, and marking the corresponding graphics; according to the preliminary planning results and the optimal decision threshold, determine the preliminary screening results, specifically including: Set the raster with a value less than or equal to the optimal decision threshold in the calculation results as not building a charging station; Set the raster with a value greater than the optimal decision threshold and less than or equal to the low-confidence positive class in the calculation results as not suitable for building a charging station, and mark it as the first setting graphic; Set the raster with a value greater than the low-confidence positive class and less than or equal to the medium-confidence positive class in the calculation results as suitable for building a charging station, and mark it as the second setting graphic; Set the raster with a value greater than the medium-confidence positive class and less than or equal to the medium-high-confidence positive class in the calculation results as more suitable for building a charging station, and mark it as the third setting graphic; Set the raster with a value greater than the medium-high-confidence positive class and less than or equal to the high-confidence positive class in the calculation results as most suitable for building a charging station, and mark it as the fourth setting graphic.

[0008] Preferably, the convenience consideration is to select the pre-site selection area along the highway, and the safety consideration is to exclude the pre-site selection areas containing expressways, first-class highways, and national highways. Based on considerations of rider convenience and safety, screen the preliminary screening results to obtain the second screening results of the area to be planned, specifically including: Based on the preliminary screening results, select the pre-site selection area along the highway to obtain the first pre-site selection area; For the first pre-site selection area, exclude the pre-site selection areas containing expressways, first-class highways, and national highways to obtain the second pre-site selection area; For the second pre-site selection area, exclude the pre-site selection areas containing intersections to obtain the second screening result.

[0009] Preferably, the construction process of the hybrid site selection planning model specifically includes: Construct basic site selection planning models through decision trees, random forests, backpropagation neural networks, and long short-term memory networks respectively; For each basic site selection planning model, use the training grid dataset to train the basic site selection planning model; Calculate the evaluation indicators of multiple basic site selection planning models respectively; the evaluation indicators include accuracy, precision, recall, and F1 score; For each basic site selection planning model, determine the weight of the basic site selection planning model in constructing the hybrid site selection planning model as the ratio of the accuracy of the basic site selection planning model to the sum of the accuracies of multiple basic site selection planning models; Construct a hybrid site selection planning model based on the weights of the basic site selection planning models.

[0010] Preferably, the calculation method of the weight of the basic site selection planning model is: ; where is the weight of the n th basic site selection planning model, is the accuracy of the n th basic site selection planning model.

[0011] Preferably, by comparing the comprehensive evaluation results of multiple basic site selection planning models and the hybrid site selection planning model under different optional decision thresholds, determine the best decision threshold of the hybrid site selection planning model, specifically including: When the comprehensive evaluation result of the hybrid site selection planning model is greater than the comprehensive evaluation results of each basic site selection planning model, if there are multiple optional decision thresholds, then determine the optional decision threshold corresponding to the maximum comprehensive evaluation result of the hybrid site selection planning model as the best decision threshold of the hybrid site selection planning model; When the comprehensive evaluation result of the hybrid site selection planning model is greater than the comprehensive evaluation results of each basic site selection planning model, if there is a unique optional decision threshold, then determine the unique optional decision threshold as the best decision threshold of the hybrid site selection planning model.

[0012] Preferably, the calculation result of each grid in the area to be planned is: ; where Nis the calculation result for each grid in the area to be planned, is the weight of the n th basic site selection planning model, is the calculation result of the n th basic site selection planning model for each grid in the area to be planned.

[0013] Preferably, the calculation method of the comprehensive evaluation result of the hybrid site selection planning model is: ; wherein, is the comprehensive evaluation result of the hybrid site selection planning model when the optional decision threshold is , is the weight of the th evaluation index, is the value of the th evaluation index after the hybrid model is given the optional decision threshold ; The calculation method of the comprehensive evaluation result of the basic site selection planning model is: ; wherein, is the comprehensive evaluation result of the st basic site selection planning model, is the weight of the th evaluation index, is the value of the th basic site selection planning model under the th evaluation index.

[0014] The present invention provides a layout device for an electric bicycle public charging station, comprising: A first evaluation module, configured to comprehensively evaluate multiple trained basic site selection planning models respectively through a test grid data set, and obtain the comprehensive evaluation result of each basic site selection planning model; each grid data includes different numbers of points of interest; the points of interest include name, category and address; A second evaluation module, configured to input the test grid data set into the hybrid site selection planning model, obtain the test result of each test grid, extract the discretized feature value in the test result as the optional decision threshold of the hybrid site selection planning model, and comprehensively evaluate the hybrid site selection planning model based on the optional decision threshold and the test result to obtain the comprehensive evaluation result of the hybrid site selection planning model under different optional decision thresholds; the hybrid site selection planning model is integrated from multiple basic site selection planning models; A first determination module, configured to determine the optimal decision threshold of the hybrid site selection planning model by comparing the comprehensive evaluation results of multiple basic site selection planning models and the hybrid site selection planning model under different optional decision thresholds.

[0015] A rasterization module, configured to rasterize the area to be planned to obtain raster data.

[0016] A second determination module, configured to input the raster data of the area to be planned into the hybrid site selection planning model, obtain the preliminary planning results of each raster in the area to be planned, and determine the preliminary screening results of the area to be planned according to the preliminary planning results and the optimal decision threshold.

[0017] A third determination module, configured to screen the preliminary screening results based on the convenience and safety considerations of riders, obtain the second screening results of the area to be planned, and determine the second screening results as the layout area of the electric bicycle public charging stations in the area to be planned.

[0018] The present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned layout method of electric bicycle public charging stations is implemented.

[0019] The present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the above-mentioned layout method of electric bicycle public charging stations is implemented.

[0020] The above-mentioned at least one technical solution adopted by the present invention can achieve the following beneficial effects: Collect evaluation indicators of multiple basic site selection planning models and hybrid site selection planning models under different optional decision thresholds; respectively evaluate the comprehensive performance of multiple basic site selection planning models and hybrid site selection planning models under different optional decision thresholds, and conduct comparative analysis; if the comprehensive evaluation result of the hybrid site selection planning model is better than the comprehensive evaluation result of each basic site selection planning model, then determine the optional decision threshold corresponding to the maximum comprehensive evaluation result of the hybrid site selection planning model as the optimal decision threshold. When determining the preliminary screening results of the area to be planned according to the hybrid site selection planning model, using this optimal decision threshold can improve the site selection reliability of electric bicycle charging stations.

[0021] Input the grid data of the area to be planned into the hybrid site selection planning model to obtain the preliminary planning results of each grid in the area to be planned. According to the preliminary planning results and the optimal decision threshold, determine the preliminary screening results of the area to be planned. Screening according to the preliminary planning results combined with the optimal decision threshold can not only significantly improve the reliability of the site selection of electric bicycle charging stations, but also provide a more flexible and diverse selection space for decision-makers; based on the convenience and safety of electric bicycle use, conduct a secondary screening of the preliminary screening results to obtain the second screening results of the area to be planned, which can not only optimize the site selection layout of electric bicycle charging stations, improve the user experience, reduce the riding safety risk, etc., but also provide a scientific basis for urban planning.

[0022] This method can optimize the site distribution of electric bicycle charging stations, provide scientific, efficient and diverse decision-making support for the actual site selection work, and improve the rationality and operability of site selection. Brief Description of the Drawings

[0023] The drawings described herein are used to provide a further understanding of the present invention and form a part of the present invention. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0024] Figure 1 It is a schematic flow chart of a layout method for a public charging station of electric bicycles provided by the present invention; Figure 2 It is a schematic diagram of the training process of the hybrid site selection planning model provided by the present invention; Figure 3 It is a schematic diagram of the preliminary screening results of the hybrid site selection planning model provided by the present invention; Figure 4 It is a road network information map of the area to be planned provided by the present invention; Figure 5 Schematic diagram of highways, first-class highways and national highways in the area to be planned provided by the present invention; Figure 6 It is a schematic diagram of large intersections in the area to be planned provided by the present invention; Figure 7 It is a schematic diagram of the second screening results of the hybrid site selection planning model provided by the present invention; Figure 8 It is a working flow chart of a layout method for a public charging station of electric bicycles provided by the present invention; Figure 9 It is a schematic diagram of a layout device for a public charging station of electric bicycles provided by the present invention; Figure 10 It is a schematic diagram of a computer device for implementing a layout method for a public charging station of electric bicycles provided by the present invention. Detailed Embodiments

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] Electric bicycles have gradually become one of the most important short-distance transportation tools for the people. my country is a major producer and consumer of electric bicycles, with a total of 350 million electric bicycles. In a certain place alone, the number of electric bicycles reached 1.6831 million in 2021. At the same time, there are also problems of uneven charging demand, such as "difficult charging and few stations", which not only affects the riders' experience but also reduces consumers' willingness to buy.

[0027] In the existing technology, some studies are guided by the charging demand of electric bicycles, and through machine learning and big data, mathematical models are established and solved to optimize the location selection problem of electric bicycle charging stations. For example, based on the battery swapping data of a large domestic battery swapping company, point of interest (POI) data and some takeaway demand data of a certain place, researchers used linear regression analysis methods and K-means clustering algorithms to study the relationship between the battery swapping order demand of the battery swapping cabinet and the surrounding POI density, and proposed a location selection strategy for the battery swapping cabinet of electric bicycles. Drawing on the relevant results of the layout of electric vehicle charging stations, the researchers determined the starting and ending points of takeaway delivery by clustering POI data, and simulated the delivery route of the riders to predict the spatiotemporal distribution of the battery swapping demand of electric bicycles, and constructed a multi-objective battery swapping cabinet location and capacity determination model with the lowest total cost for operators and the highest user satisfaction.

[0028] However, the existing site selection planning of electric bicycle charging stations and battery swap stations is usually simple and isolated, with "alleviating charging demand" as the main entry point, and the research method is relatively single. The site selection results ignore the on-site environment and lack detailed and diverse suggestions, making it difficult to provide effective decision support for the site selection of charging stations. The present invention discloses a hybrid site selection planning model for electric bicycle charging stations (Electric Bicycle Charging Station, EBCS) based on the distribution of facilities in a certain urban area, combining the use characteristics of electric bicycles themselves and multi-dimensional information such as highway levels, and providing diversified choices for site selection workers on the basis of realizing the reasonable layout of charging stations in the planned area.

[0029] Devices such as desktop computers, servers, and laptops that execute the solution of the present invention. For the sake of convenience in description, only servers will be used as the execution entity for illustration below.

[0030] The following will, in conjunction with the accompanying drawings, elaborate on the technical solutions provided by various embodiments of the present invention.

[0031] Figure 1 It is a schematic flowchart of the layout method for a public charging station of an electric bicycle in the present invention, specifically including the following steps: S101: Use the test grid dataset to comprehensively evaluate multiple trained basic site selection and planning models respectively, and obtain the comprehensive evaluation results of each basic site selection and planning model; each grid data includes different numbers of points of interest; a point of interest includes a name, a category, and an address.

[0032] The site selection and planning of EBCS are affected and restricted by the distribution of various surrounding facilities. POI data records the key information of each important facility and is suitable for environmental feature analysis. The POI data adopted in the present invention all comes from the navigation open platform. The point of interest data includes a name, a category, and an address. The category includes a major category and a minor category. The address includes longitude, latitude, and detailed address, etc. The present invention uses rasterized POI data as grid data, and each grid data includes different numbers of point of interest data.

[0033] Use the decision tree (DT), random forest (RF), BP neural network (BP), and long short-term memory network (LSTM) to construct four basic site selection and planning models respectively; use the training grid dataset to train the four basic planning models.

[0034] Specifically, in the present invention, the basic site selection and planning models include DT, RF, BP, and LSTM. Input the test grid dataset into DT, RF, BP, and LSTM respectively to obtain the test results of the DT, RF, BP, and LSTM models. According to the test results and various evaluation indicators, conduct a comprehensive evaluation of DT, RF, BP, and LSTM. The calculation method of the comprehensive evaluation results of the basic site selection and planning models is shown in formula (1):

[0035] (1); Where is the comprehensive evaluation result of the th basic site selection and planning model, is the weight of different evaluation indicators, is the value under different evaluation indicators.

[0036] S102: Input the test grid dataset into the hybrid site selection planning model to obtain the test results of each test grid, extract the discretized feature values in the test results as the optional decision thresholds of the hybrid site selection planning model, and comprehensively evaluate the hybrid site selection planning model based on the optional decision thresholds and the test results to obtain the comprehensive evaluation results of the hybrid site selection planning model under different optional decision thresholds; the hybrid site selection planning model is obtained by integrating multiple basic site selection planning models.

[0037] Specifically, first, use the training grid dataset to train each basic site selection planning model in the hybrid site selection planning model to obtain multiple trained basic site selection planning models, and determine the weights of the corresponding basic site selection planning models according to the evaluation indicators of the basic site selection planning models; then, construct the hybrid site selection planning model according to the multiple trained basic site selection planning models and their weights; next, input the test grid dataset into the hybrid site selection planning model to obtain the test results of the hybrid site selection planning model, and extract the discretized feature values in the test results as the optional decision thresholds; finally, determine the comprehensive evaluation results of the hybrid site selection planning model under different optional decision thresholds according to the optional decision thresholds and the test results of the hybrid site selection planning model.

[0038] In an exemplary embodiment, the construction process of the hybrid site selection planning model specifically includes: constructing basic site selection planning models through decision trees, random forests, backpropagation neural networks, and long short-term memory networks respectively; for each basic site selection planning model, use the training grid dataset to train the basic site selection planning model; calculate the evaluation indicators of the multiple basic site selection planning models respectively; the evaluation indicators include accuracy, precision, recall, and F1 score; for each basic site selection planning model, determine the ratio of the accuracy of the basic site selection planning model to the sum of the accuracies of the multiple basic site selection planning models as the weight of the basic site selection planning model when constructing the hybrid site selection planning model; based on the weights of the basic site selection planning models, perform weighted summation and normalization on the calculation results of the four basic site selection planning models to construct the hybrid site selection planning model.

[0039] Specifically, as Figure 2The training process of the hybrid site selection planning model is shown as follows. First, the data is preprocessed, and some of the preprocessed raster data is divided into a training raster dataset and a test raster dataset. Secondly, multiple basic site selection planning models are trained. Then, the performance of these basic models is evaluated. According to the evaluation results, the weights of each basic model are calculated, and weighted summation and normalization processing are performed to construct the hybrid site selection planning model. After that, the test raster dataset is input into the hybrid site selection planning model, and the optional decision thresholds are determined according to the discretized feature values in the test results. The comprehensive evaluation results of each basic site selection planning model and the hybrid site selection planning model under different optional decision thresholds are calculated respectively. If the comprehensive evaluation result of the hybrid model under a certain decision threshold is better than all basic models, the optional decision threshold corresponding to the maximum comprehensive evaluation result of the hybrid site selection planning model is determined as the optimal decision threshold. If there is no optimal threshold after the comprehensive evaluation of the hybrid site selection planning model, the hybrid site selection planning model is retrained.

[0040] Specifically, the evaluation indicators of four basic site selection planning models are calculated. Common binary classification evaluation indicators include: Accuracy (Accuracy, ), Precision (Precision, ), Recall (Recall, ), F1Score (F1Score, ), and AUC (Area Under Curve, ), etc. The present invention selects , , , and as evaluation indicators. The calculation method of Accuracy is shown in formula (2): (2); Among them, is Accuracy, is the true positive sample, is the true negative sample, is the sample that is actually negative but the output is positive, is the sample that is actually positive but the output is negative.

[0041] Specifically, the calculation method of Precision is shown in formula (3): (3); Among them, is Precision, is the true positive sample, is the sample that is actually negative but the output is positive.

[0042] Specifically, the recall rate is calculated as shown in formula (4): (4); wherein is the recall rate, is the true positive sample, is the sample that is actually positive but output as negative.

[0043] Specifically, is calculated as shown in formula (5): (5); wherein is the score, is the accuracy rate, is the recall rate.

[0044] Specifically, the accuracy rate of each basic site selection planning model is divided by the sum of the accuracy rates of the four models as the weight of the model. The calculation method of the weight of the basic site selection planning model is shown in formula (6): (6); wherein is the weight of the n th basic site selection planning model, is the n th basic site selection planning model's accuracy rate.

[0045] Specifically, the value range of the discretized eigenvalue k is all the test results of the test grid. Taking a certain discretized eigenvalue k in the test results of the mixed site selection planning model as the optional decision threshold to adjust the decision-making conditions of the mixed site selection planning model, and then determining the overall performance and performance of the model. The decision-making condition is the critical value for setting the grid as not building a charging station. When the calculation result of the grid obtained by the mixed site selection planning model is less than the critical value, the grid is set as not building a charging station; The present invention introduces evaluation indicators such as Acc and Prec, and uses the methods of weighted summation and normalization to determine the comprehensive evaluation result of the mixed site selection planning model. The calculation method of the comprehensive evaluation result of the mixed site selection planning model is shown in formula (7): (7); wherein is the comprehensive evaluation result of the mixed site selection planning model when the optional decision threshold is , is the weight of different evaluation indicators, is the value of different evaluation indicators after the mixed model gives the optional decision threshold .

[0046] S103: Determine the optimal decision threshold of the hybrid site selection planning model by comparing the comprehensive evaluation results of multiple basic site selection planning models with those of the hybrid site selection planning model under different optional decision thresholds.

[0047] In an exemplary embodiment, determining the optimal decision threshold of the hybrid site selection planning model by comparing the comprehensive evaluation results of multiple basic site selection planning models with those of the hybrid site selection planning model under different optional decision thresholds specifically includes: when the comprehensive evaluation result of the hybrid site selection planning model is greater than the comprehensive evaluation results of each basic site selection planning model, if there are multiple optional decision thresholds, then determine the optional decision threshold corresponding to the maximum comprehensive evaluation result of the hybrid site selection planning model as the optimal decision threshold of the hybrid site selection planning model; when the comprehensive evaluation result of the hybrid site selection planning model is greater than the comprehensive evaluation results of each basic site selection planning model, if there is a unique optional decision threshold, then determine the unique optional decision threshold as the optimal decision threshold of the hybrid site selection planning model.

[0048] Specifically, for example, when the optional decision threshold is 0.6, if the comprehensive evaluation result of the hybrid site selection planning model is better than the four basic site selection planning models and is optimal in terms of performance compared to other thresholds (0.5, 0.7, 0.8, 0.9, 1), determine the decision threshold as 0.6.

[0049] S104: Perform rasterization processing on the area to be planned to obtain raster data.

[0050] In the present invention, rasterize the area to be planned to obtain raster data, and the electric bicycle charging stations are arranged on the grids that need to be arranged with charging stations screened by the present invention. The POI data used in the present invention is sourced from the navigation open platform, and the data content includes name, major category, minor category, longitude, latitude, detailed address, etc.

[0051] S105: Input the raster data of the area to be planned into the hybrid site selection planning model to obtain the preliminary planning results of each grid in the area to be planned, and determine the preliminary screening results of the area to be planned according to the preliminary planning results and the optimal decision threshold.

[0052] In an exemplary embodiment, the calculation result of each grid in the area to be planned is shown in formula (8): (8); Wherein, N is the calculation result of each grid in the area to be planned, is the weight of the n th basic site selection planning model, is the calculation result of the n th basic site selection planning model for calculating each grid in the area to be planned.

[0053] Specifically, according to the calculation results and weights of the nth basic site selection planning model, the calculation results of each grid in the area to be planned are determined after weighted summation and normalization processing.

[0054] In an exemplary embodiment, among the calculation results of the hybrid site selection planning model, the values greater than or equal to the optimal decision threshold include low-confidence positive classes, medium-confidence positive classes, medium-high-confidence positive classes, and high-confidence positive classes; the preliminary screening results include setting the grids as not building charging stations, not suitable for building charging stations, suitable for building charging stations, more suitable for building charging stations, and most suitable for building charging stations, and marking the corresponding graphics; according to the preliminary planning results and the optimal decision threshold, the preliminary screening results are determined, specifically including: setting the grids with values less than or equal to the optimal decision threshold in the calculation results as not building charging stations; setting the grids with values greater than the optimal decision threshold and less than or equal to the low-confidence positive class in the calculation results as not suitable for building charging stations and marking them with the first setting graphic; setting the grids with values greater than the low-confidence positive class and less than or equal to the medium-confidence positive class in the calculation results as suitable for building charging stations and marking them with the second setting graphic; setting the grids with values greater than the medium-confidence positive class and less than or equal to the medium-high-confidence positive class in the calculation results as more suitable for building charging stations and marking them with the third setting graphic; setting the grids with values greater than the medium-high-confidence positive class and less than or equal to the high-confidence positive class in the calculation results as most suitable for building charging stations and marking them with the fourth setting graphic.

[0055] Specifically, according to the comparison of the calculation results of each grid in the area to be planned with the optimal decision threshold, low-confidence positive class, medium-confidence positive class, relatively high-confidence positive class, and high-confidence positive class, the grids are determined to be marked as most suitable for building charging stations, more suitable for building charging stations, suitable for building charging stations, not suitable for building charging stations, and not building charging stations. In the present invention, according to different marking types of the grids, the grids are marked with different graphics, and the present invention does not limit this. For example, the grids can also be marked with different colors according to different marking types. According to the marking results, the preliminary screening results of the area to be planned are determined.

[0056] In the present invention, the first setting graphic is a triangle, the second setting graphic is a rhombus, the third setting graphic is a circle, and the fourth setting graphic is a square. As Figure 3 Shown is the preliminary screening result of the hybrid site selection planning model. Among them, the grids marked with squares indicate the most suitable for building charging stations, the grids marked with circles indicate more suitable for building charging stations, the grids marked with rhombuses indicate suitable for building charging stations, and the grids marked with triangles indicate not suitable for building charging stations.

[0057] S106: Considering the convenience and safety of riders, screen the preliminary screening results to obtain the second screening results of the area to be planned, and determine the second screening results as the layout area of the public charging stations for electric bicycles in the area to be planned.

[0058] In an exemplary embodiment, the convenience consideration is to select pre-site areas along the road, and the safety consideration is to exclude pre-site areas containing expressways, first-class highways, and national highways. Considering the convenience and safety of electric bicycle riders, screen the preliminary screening results to obtain the second screening results of the area to be planned, specifically including: based on the preliminary screening results, select pre-site areas along the road to obtain the first pre-site area; for the first pre-site area, exclude pre-site areas containing expressways, first-class highways, and national highways to obtain the second pre-site area; for the second pre-site area, exclude pre-site areas containing intersections to obtain the second screening results, and determine the second screening results as the layout area of the public charging stations for electric bicycles in the area to be planned.

[0059] Specifically, the EBCS is a charging station for electric bicycles and also a gathering place for a large number of electric bicycles, so convenience and safety must be given top priority.

[0060] As Figure 4 shown, it is the road network information map of the area to be planned provided by the present invention. Setting the location of the EBCS on both sides of the road to obtain the first pre-site area not only increases the usage frequency of the EBCS but also makes the riders of electric bicycles feel more convenient when using it.

[0061] As Figure 5As shown in the figure, the high-speed, first-class highways and national highways within the area to be planned are provided by the present invention. The research results show that there is a clear relationship between the collision speed of electric bicycle riders and the severity of injuries. When the collision speed between a vehicle and an electric bicycle is 30 km / h, the death risk of the electric bicycle rider is 2.9%; when the collision speed between a vehicle and an electric bicycle is 50 km / h, the death risk of the electric bicycle rider is 23%; when the collision speed between a vehicle and an electric bicycle is 60 km / h, the death risk of the electric bicycle rider is 50%; when the collision speed between a vehicle and an electric bicycle is 80 km / h, the death risk of the electric bicycle rider is 90%. According to the highway design specifications, for the first-class highway used for distribution, the design speed is 80 km / h, while for the second-class highway used for distribution, the design speed is 60 km / h. When restricted by conditions such as terrain and geology, they are adjusted to 60 km / h and 40 km / h respectively. Therefore, the EBCS near the second-class and lower-class highways is safer. As a national-level trunk highway, the national highway connects the important political and economic centers and transportation hubs of the country. It undertakes a large transportation capacity and has a large number of passing vehicles. The areas on both sides and adjacent to the national highway are not suitable for planning and constructing EBCS. Excluding the EBCS pre-selection areas containing high-speed, first-class highways and national highways from the first pre-selection area, the second pre-selection area is obtained.

[0062] As Figure 6 shown, it is a large intersection within the area to be planned. As a convergence point of various vehicles, the large intersection is one of the most complex road conditions. For intersections formed by second-class or higher-class highways, due to the relatively high design vehicle speed and a large number of mixed vehicles, therefore, excluding the grid areas containing large intersections within the second pre-selection area, the second screening result is obtained. The second screening result is as Figure 7 shown, where the square indicates the most suitable area for building a charging station, the circle indicates a more suitable area for building a charging station, the rhombus indicates a suitable area for building a charging station, and the triangle indicates an unsuitable area for building a charging station. The second screening result is determined as the suitable site layout area for the electric bicycle public charging station within the area to be planned.

[0063] In an exemplary embodiment, the present invention provides a Figure 8 working flow chart of the layout method of an electric bicycle public charging station as shown. First, obtain the point-of-interest data from the geographic information system, rasterize the point-of-interest data to obtain the point-of-interest raster data. Secondly, process the point-of-interest raster data through a mixed site selection planning model to obtain the preliminary screening result of the area to be planned. Then, process the preliminary screening result through multi-dimensional information such as the usage characteristics of electric bicycles and the highway level to obtain the second screening result.

[0064] When applying the layout method of an electric bicycle public charging station provided by the present invention, it is not necessary to execute according to the order of the steps shown in Figure 1 . The specific execution order of each step can be determined according to needs, and the present invention does not limit this.

[0065] The above is a layout method of an electric bicycle public charging station provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding layout device of an electric bicycle public charging station, as shown in Figure 9 .

[0066] Figure 9 It is a schematic diagram of a layout device of an electric bicycle public charging station provided by the present invention, including: A first evaluation module 901, configured to comprehensively evaluate multiple trained basic site selection planning models through a test grid dataset respectively, and obtain the comprehensive evaluation results of each basic site selection planning model; each grid data includes different numbers of points of interest; the points of interest include name, major category, minor category, longitude, latitude, and detailed address.

[0067] A second evaluation module 902, configured to input the test grid dataset into the hybrid site selection planning model to obtain the test results of each test grid. Extract the discretized eigenvalue in the result as the optional decision threshold of the hybrid site selection planning model. Based on the optional decision threshold and the test results, comprehensively evaluate the hybrid site selection planning model to obtain the comprehensive evaluation results of the hybrid site selection planning model under different optional decision thresholds; the hybrid site selection planning model is obtained by integrating multiple basic site selection planning models.

[0068] A first determination module 903, configured to determine the optimal decision threshold of the hybrid site selection planning model by comparing the comprehensive evaluation results of multiple basic site selection planning models and the hybrid site selection planning model under different optional decision thresholds.

[0069] A rasterization module 904, configured to rasterize the area to be planned to obtain grid data.

[0070] A second determination module 905, configured to input the grid data of the area to be planned into the hybrid site selection planning model to obtain the preliminary planning results of each grid in the area to be planned, and determine the preliminary screening results of the area to be planned according to the preliminary planning results and the optimal decision threshold.

[0071] A third determination module 906, configured to screen the preliminary screening results based on the convenience and safety considerations of riders to obtain the second screening results of the area to be planned, and determine the second screening results as the layout area of the electric bicycle public charging station in the area to be planned.

[0072] For the specific limitations of a layout device for an electric bicycle public charging station, reference can be made to the limitations of the layout method for an electric bicycle public charging station in the above text, which will not be elaborated here. Each module in the above layout device for an electric bicycle public charging station can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of the processor in a computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0073] The present invention also provides a computer-readable storage medium storing a computer program, which can be used to execute the Figure 1 layout method for an electric bicycle public charging station provided above.

[0074] The present invention also provides Figure 10 a schematic structural diagram of the computer device shown in, as Figure 10 shown, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, there may also be other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the Figure 1 layout method for an electric bicycle public charging station provided above.

[0075] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memories. The non-volatile memory can include a read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0076] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present invention.

Claims

1. A method for laying out public charging stations for electric bicycles, characterized in that: include: Through the test grid data set, the trained multiple basic site selection planning models are comprehensively evaluated to obtain the comprehensive evaluation results of each basic site selection planning model; each grid data includes a different number of points of interest; the points of interest include name, category and address; Input the test grid dataset into the hybrid site planning model, obtain the test result of each test grid, extract the discretized characteristic value in the test result as the optional decision threshold of the hybrid site planning model, conduct a comprehensive evaluation of the hybrid site planning model based on the optional decision threshold and the test result, and obtain the comprehensive evaluation results of the hybrid site planning model under different optional decision thresholds; the hybrid site planning model is obtained by integrating multiple basic site planning models; By comparing the comprehensive evaluation results of multiple basic site selection planning models and the hybrid site selection planning model under different optional decision thresholds, the optimal decision threshold of the hybrid site selection planning model is determined; Perform rasterization processing on the planned area to obtain raster data; Input the grid data of the area to be planned into the hybrid site selection planning model to obtain the preliminary planning results of each grid in the area to be planned, and determine the preliminary screening results of the area to be planned based on the preliminary planning results and the optimal decision threshold; Based on the convenience and safety of riders, the preliminary screening results are screened to obtain the second screening results of the area to be planned, and the second screening results are determined as the layout area of ​​public charging stations for electric bicycles in the area to be planned.

2. The method according to claim 1, characterized in that In the calculation results of the hybrid site selection planning model, the values ​​greater than or equal to the optimal decision threshold include low confidence positive class, medium confidence positive class, medium-high confidence positive class, and high confidence positive class; the preliminary screening results include setting the grid to not build a charging station, not suitable for building a charging station, suitable for building a charging station, more suitable for building a charging station, and most suitable for building a charging station, and marking the corresponding graphics; Based on the preliminary planning results and the optimal decision threshold, the preliminary screening results are determined, including: The grids whose values ​​in the calculation results are less than or equal to the optimal decision threshold are set as not to build charging stations; The grids whose values ​​in the calculation results are greater than the optimal decision threshold and less than or equal to the low confidence positive class are set as unsuitable for building charging stations and marked as the first setting graphic; The grids whose values ​​in the calculation results are greater than the low confidence positive class and less than or equal to the medium confidence positive class are set as suitable for building charging stations and marked as the second setting graphic; The grids whose values ​​in the calculation results are greater than the medium confidence positive class and less than or equal to the medium-high confidence positive class are set as more suitable for building charging stations and marked as the third setting graphic; The grids whose values ​​in the calculation results are greater than the medium-high confidence positive class and less than or equal to the high confidence positive class are set as the most suitable for building a charging station and are marked as the fourth setting graphic.

3. The method according to claim 1, characterized in that The convenience consideration is to select the pre-selected area along the highway, and the safety consideration is to exclude the pre-selected area containing expressways, first-class highways and national highways. Based on the convenience and safety considerations of riders, the preliminary screening results are screened to obtain the second screening results of the areas to be planned, including: Based on the preliminary screening results, pre-selected areas are selected along the highway to obtain the first pre-selected area; For the first pre-selected site area, the pre-selected site area containing expressways, first-class highways and national roads is excluded to obtain the second pre-selected site area; For the second pre-selected area, the pre-selected area containing the intersection is excluded to obtain the second screening result.

4. The method according to claim 1, characterized in that The construction process of the hybrid site planning model includes: The basic site selection planning models are constructed through decision trees, random forests, back propagation neural networks and long short-term memory networks; For each basic site planning model, the basic site planning model is trained using a training raster dataset; Calculate the evaluation indicators of multiple basic site planning models respectively; the evaluation indicators include accuracy, precision, recall and F1 score; For each basic site selection planning model, the ratio of the accuracy of the basic site selection planning model to the sum of the accuracy of multiple basic site selection planning models is determined as the weight of the basic site selection planning model when constructing the hybrid site selection planning model; Based on the weights of the basic site selection planning models, the calculation results of the four basic site selection planning models are weighted summed and normalized to construct a hybrid site selection planning model.

5. The method according to claim 4, characterized in that The weights of the basic site planning model are calculated as follows: ； in, For the n The weights of the basic site planning model, For the n The accuracy of the basic site selection planning model.

6. The method according to claim 1, characterized in that By comparing the comprehensive evaluation results of multiple basic site selection planning models and the hybrid site selection planning model under different optional decision thresholds, the optimal decision threshold of the hybrid site selection planning model is determined, including: When the comprehensive evaluation result of the hybrid site planning model is greater than the comprehensive evaluation result of each basic site planning model, if there are multiple optional decision thresholds, the optional decision threshold corresponding to the maximum comprehensive evaluation result of the hybrid site planning model is determined as the optimal decision threshold of the hybrid site planning model; When the comprehensive evaluation result of the hybrid site planning model is greater than the comprehensive evaluation result of each basic site planning model, if there is a unique optional decision threshold, the unique optional decision threshold is determined as the optimal decision threshold of the hybrid site planning model.

7. The method of claim 1, wherein: The calculation results of each grid in the area to be planned are: ； in, N is the calculation result of each grid in the area to be planned, For the n The weight of the basic site planning model, For the n A basic site planning model calculates the calculation results of each grid in the area to be planned.

8. The method of claim 1, wherein: The comprehensive evaluation results of the hybrid site planning model are calculated as follows: ； in, The optional decision threshold is When the comprehensive evaluation results of the hybrid site planning model are For the The weight of the evaluation index, Give an optional decision threshold to the hybrid model After The value of the evaluation index; The calculation method of the comprehensive evaluation results of the basic site planning model is: ； in, For the Comprehensive evaluation results of the basic site selection planning models, For the The weight of the evaluation index, For the A basic site planning model The value of the evaluation index.

Images