Transfer planning method, system, device and medium based on multiple public transportation modes

Abstract

The application discloses a transfer planning method, system, equipment and medium based on multiple public transport modes, and belongs to the field of metro transfer. The application can provide a most comfortable metro transfer route.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of subway transfer, and in particular to a transfer planning method, system, device and medium based on multiple public transportation modes. BACKGROUND

[0002] With the development of cities, there are more and more choices for travel, such as subways, buses, shared bicycles, walking and private cars. In economically developed regions (such as Beijing, Shanghai, Chengdu, Wuhan and Xi'an), subway travel is the most selected mode.

[0003] Cities that develop in a pie shape and are well supported (such as Beijing and Chengdu) are usually divided into inner and outer rings, and both the inner and outer rings are distributed with several subway lines that interweave vertically and horizontally to connect the inner and outer ring areas. Some people need to travel to a nearby subway station by bus, shared bicycle, walking or private car due to work or living needs, and then take the subway to cross from the inner ring to the outer ring or from the outer ring to the inner ring, and need to transfer several times along the way, and finally arrive at a subway station near the destination.

[0004] Currently, major subway line apps usually recommend the route with the shortest time, and some apps also reflect the real-time congestion status of the line, but for people with long spans and multiple transfer points, how to more accurately predict an easier transfer route is a problem to be solved. SUMMARY

[0005] The present application provides a transfer planning method, system, device and medium based on multiple public transportation modes, which solves the technical problem of how to more accurately predict an easier transfer route for people with long spans and multiple transfer points in the prior art, and achieves the technical effect of providing an easier transfer route.

[0006] In a first aspect, the present application provides a transfer planning method based on multiple public transportation modes, comprising:

[0007] Divide the historical time period of the target city into several historical time sub-periods, and classify each time sub-period, wherein each time sub-period belongs to a life type, and the life type includes a holiday type, a weekday type and a rest day type;

[0008] Determine the outer circle layer and the inner circle layer of the target city, wherein the outer circle layer and the inner circle layer each contain several subway stations, bus stations and shared bicycle stations;

[0009] Divide the historical time sub-periods under each life type into time units with a maximum time unit of day and a division unit of hour, and determine the hourly transfer sharing rate of each subway station under each life type;

[0010] The data set is constructed according to the life type, the subway station, the hourly transfer sharing rate, the circle layer where the subway station is located, and the hourly subway passenger flow of the subway station, and the data set is used to train the neural network model to obtain a passenger flow carrying capacity prediction model, wherein the neural network model is used to predict the first passenger flow carrying capacity of the subway station;

[0011] The starting time node, the starting position, and the terminal position of the target are obtained, and a plurality of subway riding paths are determined according to the starting position and the terminal position;

[0012] The first passenger flow carrying capacity of the subway station on the subway riding path of the target at the starting time node is predicted by the passenger flow carrying capacity prediction model, and the subway transfer station and the target subway riding path are determined from the plurality of subway riding paths according to the prediction result.

[0013] Further, for each subway transfer station, further comprising:

[0014] The circle layer where the subway transfer station is located is determined;

[0015] The transfer area of the subway transfer station is determined according to the circle layer where the subway transfer station is located;

[0016] It is judged whether the transfer area of any adjacent subway station overlaps with the transfer area of the subway transfer station;

[0017] If yes, the second passenger flow carrying capacity of the subway transfer station at the starting time node of the target is determined according to the population information and the commercial information of the transfer area of the subway transfer station;

[0018] If no, the transfer area of the subway transfer station is re-divided according to the positional relationship between the adjacent subway station and the subway transfer station, and the second passenger flow carrying capacity of the subway transfer station at the starting time node of the target is determined according to the population information and the commercial information of the re-divided transfer area of the subway transfer station;

[0019] According to the second passenger flow carrying capacity and the first passenger flow carrying capacity of the subway transfer station, it is judged whether to change the target subway riding path of the target.

[0020] Further, the transfer area of the subway transfer station is re-divided according to the positional relationship between the adjacent subway station and the subway transfer station, comprising:

[0021] It is judged whether there is a commercial body or a residential area in the overlapping transfer area;

[0022] If not, the overlapping transfer area is equally divided to obtain the re-divided transfer area of the subway transfer station;

[0023] If the overlapping transfer area exists, a regional division ratio is determined according to the travel preference of the commercial body or the residential area, and the overlapping transfer area is divided according to the regional division ratio to obtain the transfer area of the subway transfer station after re-division.

[0024] Further, whether the target subway riding path is replaced is determined according to the second passenger flow carrying degree and the first passenger flow carrying degree of the subway transfer station, including:

[0025] If the difference between the sum of the second passenger flow carrying degrees and the sum of the first passenger flow carrying degrees of the subway transfer stations is greater than a first threshold, or the difference between the second passenger flow carrying degree and the first passenger flow carrying degree of any subway transfer station is greater than a second threshold, the target subway riding path is replaced; otherwise, the target subway riding path is not replaced.

[0026] Further, the subway transfer station and the target subway riding path are determined from the plurality of subway riding paths according to the prediction result, including:

[0027] The sum of the first passenger flow carrying degrees of each subway riding path is determined.

[0028] The subway riding path with the lowest sum of the first passenger flow carrying degrees is taken as the target subway riding path, and the subway transfer station is determined in the target subway riding path.

[0029] Further, the outer circle layer and the inner circle layer of the target city are determined, including:

[0030] The target city is divided according to the urban planning of the target city to obtain the outer circle layer and the inner circle layer of the target city.

[0031] Further, the plurality of subway riding paths are determined according to the starting position and the terminal position, including:

[0032] The starting subway station is determined according to the starting position, and the number of the starting subway stations is greater than or equal to 1.

[0033] The terminal subway station is determined according to the terminal position, and the number of the terminal subway stations is greater than or equal to 1.

[0034] The plurality of subway riding paths are planned according to the starting subway station and the terminal subway station.

[0035] In a second aspect, the present application provides a transfer planning system based on multiple public transportation modes, including:

[0036] The time division module is configured to divide the historical time period of the target city to obtain a plurality of historical time sub-periods, and classify each time sub-period, wherein each time sub-period belongs to a life type, and the life type includes a holiday type, a weekday type and a rest day type.

[0037] The circle layer division module is configured to determine an outer circle layer and an inner circle layer of the target city, wherein the outer circle layer and the inner circle layer each contain a plurality of subway stations, bus stations and shared bicycle stations;

[0038] The sharing rate determination module is configured to divide the historical time segments under each life type into time units of day and time units of hour, and determine the hourly transfer sharing rate of each subway station under each life type;

[0039] The neural network training module is configured to construct a data group by using the life type, the subway station, the hourly transfer sharing rate, the circle layer where the subway station is located and the hourly subway passenger flow of the subway station, train a to-be-trained neural network model by using the data group, and obtain a passenger flow carrying capacity prediction model, wherein the to-be-trained neural network model is used to predict the first passenger flow carrying capacity of the subway station;

[0040] The path screening module is configured to obtain a departure time node, a starting position and a terminal position of the target, and determine a plurality of subway riding paths according to the starting position and the terminal position;

[0041] The path determination module is configured to predict the first passenger flow carrying capacity of the subway station of the subway riding path under the departure time node of the target by using the passenger flow carrying capacity prediction model, and determine the subway transfer station and the target subway riding path from the plurality of subway riding paths according to the prediction result.

[0042] In a third aspect, the present application provides an electronic device, comprising:

[0043] a processor;

[0044] a memory for storing processor-executable instructions;

[0045] The processor is configured to execute to realize the transfer planning method based on multiple public transportation modes as provided in the first aspect.

[0046] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, when the instructions in the non-transitory computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the realization of the transfer planning method based on multiple public transportation modes as provided in the first aspect.

[0047] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0048] The present application binds the hourly transfer sharing rate of each hour in the day of the subway station, the life type of the subway station in the day, the circle layer where the subway station is located, and the hourly subway passenger flow of the subway station as a data group, and obtains the sum of the first passenger flow carrying degrees of each station of each path based on the passenger flow carrying degree prediction model, so as to provide a target subway riding path that is most comfortable and balanced in time and station quantity for cross-region customers.

[0049] The present application considers the passenger flow density of each station in the path, effectively avoids the travel inconvenience and delay risk caused by the peak period or high-load station, on the other hand, by determining the sum of the carrying degrees of the whole path, avoids the deviation caused by simply relying on the number of stations or the length of the path, makes the path selection closer to the actual travel experience, and combines the division of life type and time period, makes the prediction result more scene-adaptive, improves the intelligentization and personalization level of path planning, helps to relieve the local congestion of the subway system, and optimizes the urban traffic operation efficiency.

[0050] The present application can improve the rationality of the transfer area division by determining the regional division proportion according to the travel preferences of commercial bodies or residential areas.

[0051] The present application can realize dynamic optimization of the travel path by comparing the difference between the second passenger flow carrying degree and the first passenger flow carrying degree of the subway transfer station, and setting a threshold judgment condition to determine whether to replace the target subway path.

[0052] The present application can improve the rationality of route determination by correcting the target subway riding path based on the second passenger flow carrying degree of the subway transfer station.

[0053] The present application can improve the accuracy of passenger flow carrying degree prediction by dividing the time period according to the life type. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0055] Figure 1 The flowchart of the transfer planning method based on multiple public transportation modes provided by the present application is shown.

[0056] Figure 2 The schematic diagram of the transfer area provided by the present application is shown. DETAILED DESCRIPTION

[0057] The embodiment of the present application provides a transfer planning method based on multiple public transport modes, and solves the technical problem of how to more accurately predict a more relaxed transfer route for personnel with long span and multiple transfer points in the prior art.

[0058] The technical solution of the present application is to solve the above technical problems, and the general idea is as follows:

[0059] The transfer planning method based on multiple public transport modes comprises the following steps: dividing a historical time period of a target city to obtain a plurality of historical time sub-periods, and classifying each time sub-period, wherein each time sub-period belongs to a life type, and the life type comprises a holiday type, a weekday type, and a rest day type; determining an outer circle layer and an inner circle layer of the target city, wherein the outer circle layer and the inner circle layer each comprise a plurality of subway stations, bus stations, and shared bicycle stations; dividing the historical time sub-periods under each life type into segments with days as the maximum time unit and hours as the segmentation unit, and determining the hourly transfer sharing rate of each subway station under each life type; constructing a data group based on the life type, the subway station, the hourly transfer sharing rate, the circle layer where the subway station is located, and the hourly subway passenger flow of the subway station, and training a to-be-trained neural network model based on the data group to obtain a passenger flow carrying capacity prediction model, wherein the to-be-trained neural network model is used to predict the first passenger flow carrying capacity of the subway station; obtaining a target departure time node, a starting position, and a terminal position, and determining a plurality of subway riding paths according to the starting position and the terminal position; predicting the first passenger flow carrying capacity of the subway station of the subway riding path under the target departure time node based on the passenger flow carrying capacity prediction model, and determining the subway transfer station and the target subway riding path from the plurality of subway riding paths according to the prediction result.

[0060] In order to better understand the above technical solution, the above technical solution will be described in detail in combination with the drawings of the specification and the specific embodiments.

[0061] First of all, the term "and / or" appearing in this paper is only to describe the association relationship of the associated objects, which means that there are three kinds of relationships, for example, A and / or B, which means that there are three kinds of situations, such as A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents an "or" relationship between the front and rear associated objects.

[0062] The present application can mainly provide another subway riding mode for personnel in a city that develops in a pie shape and is equipped with mature supporting facilities. The city that develops in a pie shape and is equipped with mature supporting facilities can include Beijing, Shanghai, Guangzhou, Shenzhen, Chengdu, Chongqing, Hangzhou, Nanjing, Wuhan, Xi'an, London, New York, Tokyo, Singapore, Sydney, and Paris.

[0063] The city presenting a pie-shaped development is usually divided into an inner ring and an outer ring, and the inner ring and the outer ring each contain a plurality of subway lines connecting the inner ring and the outer ring.

[0064] The present application can provide another mode of transportation for personnel who need to transfer several times on the way from the inner ring to the outer ring or from the outer ring to the inner ring by taking the subway.

[0065] The present application provides a transfer planning method based on multiple public transportation modes as shown in Figure 1 The transfer planning method based on multiple public transportation modes includes steps S11-S16.

[0066] Step S11: dividing a historical time period of a target city to obtain a plurality of historical time sub-periods, and classifying each time sub-period, wherein each time sub-period belongs to a life type, and the life type includes a holiday type, a weekday type, and a rest day type.

[0067] The target city can be a city presenting a pie-shaped development and supporting mature facilities. The length of the historical time period is usually selected to be 365 days or more. To improve accuracy, data from the last 3 years can be selected.

[0068] The historical time period is divided into a plurality of historical time sub-periods according to the life type, for example, 2024.5.1-2024.5.15 (only 15 days are selected for convenience of explanation), wherein 2024.5.1-2024.5.5 is a historical time sub-period, the life type of the time sub-period is a holiday type; 2024.5.6-2024.5.10 is a historical time sub-period, the life type of the time sub-period is a weekday type; 2024.5.11-2024.5.12 is a historical time sub-period, the life type of the time sub-period is a rest day type; and 2024.5.13-2024.5.15 is a historical time sub-period, the life type of the time sub-period is a weekday type.

[0069] The present application divides the time period according to the life type, which can improve the accuracy of the people flow carrying capacity prediction.

[0070] It can be understood that the personnel corresponding to different life types are different, for example, tourists are mainly in holidays, and workers are mainly in weekdays, and the travel time is also different. Therefore, different life types have their own obvious travel characteristics, and the present application provides a reference for people flow carrying capacity prediction according to the life type, which can improve the accuracy of the prediction.

[0071] After determining the life type of each historical time sub-period, the life types of the historical time sub-periods are classified to obtain a plurality of historical time sub-periods under each life type.

[0072] Step S12, determining the outer ring layer and the inner ring layer of the target city, wherein the outer ring layer and the inner ring layer each contain a plurality of subway stations, bus stations and shared bicycle stations.

[0073] Determining the outer ring layer and the inner ring layer of the target city comprises: dividing the target city according to the city planning of the target city to obtain the outer ring layer and the inner ring layer of the target city.

[0074] After the historical time division of the target city is determined, the spatial structure of the city can be divided into ring layers, i.e. the city is divided into two regions of the outer ring layer and the inner ring layer.

[0075] Since the present application mainly aims at pie-shaped cities, the pie-shaped cities can be naturally divided into inner and outer rings, for example, the area within the third ring of Chengdu is the inner ring, and the area outside the third ring is the outer ring, for another example, the area within the fifth ring of Beijing is the inner ring, and the area outside the fifth ring is the outer ring, and the rest of the cities can be determined according to their own city planning, which is not limited here. It can be understood that whether it is an inner ring or an outer ring, there are a plurality of subway stations, bus stations and shared bicycle stations.

[0076] Step S13, dividing each historical time sub-section under each life type by day as the maximum time unit and by hour as the division unit, and determining the hourly transfer sharing rate of each subway station under each life type.

[0077] The transfer sharing rate refers to the proportion of the number of people using the transportation mode to or from the subway station to the total number of trips at the subway station in a certain time period. The transportation mode to the subway station includes walking, cycling, taking the bus, driving or arriving from other subway stations.

[0078] Taking day as the maximum time unit means dividing the time into each day first, and taking hour as the division unit means dividing each day after division into 24 hours.

[0079] Considering the actual subway operation, the present application only extracts 6.00-23.00 as the effective hour, and the hourly transfer sharing rate in the subsequent text also only contains 6.00-23.00.

[0080] According to the number of days and hours, according to the subway station data of 6.00-23.00 under each life type, the transfer sharing rate of a plurality of historical time sub-sections under the same life type in a fixed period is counted as the hourly transfer sharing rate of the period of the day.

[0081] For ease of understanding, Table 1 is provided, which is the hourly transfer sharing rate of a certain subway station A of a certain city on 2023.5.1, and the life type is the holiday type.

[0082]

[0083] It can be understood that, in order to facilitate calculation, the transfer sharing rates of the same traffic mode to arrive and leave the subway station are combined, that is, the application does not distinguish whether to arrive or leave the subway station, but only distinguishes the mode of arrival and departure.

[0084] Taking 7:00-8:00 on May 1, 2023 as an example, the number of people entering the subway station A is 100, and the number of people leaving the subway station A is 50, so the total flow is 150, wherein the number of people choosing to enter the subway station A by car is 5, and the number of people choosing to leave the subway station A by car is 10, so the hourly transfer sharing rate of car as the traffic mode is 10%.

[0085] Step S14, constructing a data group with the life type, the subway station, the hourly transfer sharing rate, the circle layer where the subway station is located, and the hourly subway passenger flow of the subway station, and training the to-be-trained neural network model with the data group to obtain a passenger flow carrying capacity prediction model, wherein the to-be-trained neural network model is used to predict the first passenger flow carrying capacity of the subway station.

[0086] Taking the subway station as an anchor point, the hourly transfer sharing rate of each hour of the subway station in a day, the life type of the subway station on the day, the circle layer where the subway station is located, and the hourly subway passenger flow of the subway station are bound into a data group, and a plurality of data groups are obtained. The passenger flow carrying capacity refers to the ratio of the current passenger flow to the maximum carrying capacity of the subway station.

[0087] The plurality of data groups are input into the to-be-trained neural network model for training, and the neural network parameters are adjusted according to the results. When the preset training requirements are met or the maximum number of training times is met, the to-be-trained neural network model is output, and the model is used as the passenger flow carrying capacity prediction model.

[0088] It can be understood that, based on the data group, the to-be-trained neural network model is a conventional process, which is not described here.

[0089] Step S15, obtaining the departure time node, the starting position and the terminal position of the target, and determining a plurality of subway riding paths according to the starting position and the terminal position.

[0090] Specifically, it includes: determining the starting subway station according to the starting position, and the number of starting subway stations is greater than or equal to 1; determining the terminal subway station according to the terminal position, and the number of terminal subway stations is greater than or equal to 1; and planning a plurality of subway riding paths according to the starting subway station and the terminal subway station.

[0091] It can be understood that there can be one or more subway stations near the starting position, and the starting subway station can be selected according to the actual situation. For example, for car travel, a subway station within 3 kilometers can be selected as the starting subway station, and for walking, a subway station within 1 kilometer can be selected as the starting subway station. The end subway station is the same.

[0092] After determining the starting subway station and the end subway station, a plurality of subway riding paths can be planned.

[0093] In step S16, the first passenger flow carrying degree of the starting time node of the starting time node of the target is predicted by the passenger flow carrying degree prediction model, and the subway transfer station and the target subway riding path are determined from the plurality of subway riding paths according to the prediction result.

[0094] According to the prediction result, the subway transfer station and the target subway riding path are determined from the plurality of subway riding paths, including: determining the sum of the first passenger flow carrying degree of each subway riding path; the subway riding path with the lowest sum of the first passenger flow carrying degree is taken as the target subway riding path, and the subway transfer station is determined in the target subway riding path.

[0095] The starting time node means that the life type of the day is determined, and the time period in which the starting time node is located is determined.

[0096] It can be understood that each subway station in each subway riding path has a first passenger flow carrying degree. The lower the sum of the first passenger flow carrying degree, the smaller the overall passenger flow trend of the subway riding path, and the fewer the subway stations passed through and the shorter the time taken.

[0097] The subway transfer station refers to the subway station that needs to be transferred in the path.

[0098] Therefore, the present application binds the hourly transfer sharing rate of each hour of the subway station in the day, the life type of the subway station in the day, the circle layer of the subway station, and the hourly subway passenger flow of the subway station as a data group, and trains the data group to obtain a passenger flow carrying degree prediction model. Based on the passenger flow carrying degree prediction model, the sum of the first passenger flow carrying degree of each station of each path is obtained, and based on the sum of the first passenger flow carrying degree, a target subway riding path that is most comfortable to ride and balanced in time and number of stations can be provided for cross-zone customers.

[0099] The application considers the crowd density of each station in the path, effectively avoids the travel inconvenience and delay risk brought by the peak period or high-load station; on the other hand, by determining the sum of the carrying degree of the entire path, the deviation brought by simply relying on the number of stations or the length of the path is avoided, so that the path selection is closer to the actual travel experience, and the prediction result is more scene-adaptive by combining the division of life types and time periods, the intelligentization and personalization level of path planning is improved, which helps to relieve the local congestion of the subway system and optimize the urban traffic operation efficiency.

[0100] In addition, for each subway transfer station (only at the subway transfer station can transfer, the safety is the lowest and the comfort is the lowest when transferring, so the application only considers the subway transfer station), it also includes:

[0101] Determine the circle layer where the subway transfer station is located.

[0102] According to the circle layer where the subway transfer station is located, determine the connection area of the subway transfer station.

[0103] It can be understood that the sizes of the connection areas of different circle layers are different, and usually the size of the connection area of the inner circle layer is smaller than that of the outer circle layer (because the station setting of the outer circle layer is sparser than that of the inner circle layer)

[0104] For example, the connection area of the subway station of the outer circle layer of B city is the area formed by 9KM, and the connection area of the subway station of the inner circle layer of B city is the area formed by 5KM, which can be determined according to each city.

[0105] Determine whether the connection area of any adjacent subway station overlaps with the connection area of the subway transfer station.

[0106] If so, according to the population information and commercial information of the connection area of the subway transfer station, determine the second passenger flow carrying degree of the subway transfer station at the target departure time node.

[0107] The population information represents the resident population in the connection area of the subway transfer station, and the commercial information contains the floating population in the connection area of the subway transfer station, which can usually be obtained by statistical data in recent years. Table 2 is the coefficient of subway transfer station C, which reflects the probability of floating population or fixed population entering or leaving subway transfer station C in this period.

[0108]

[0109] Taking 7.00-8.00 as an example, the resident population (population information) of the transfer area of the subway transfer station C is 7w, and the floating population (business information) is 5w, so the number of people entering or leaving at 7.00-8.00 is 70000*0.0012+50000*0.0007=119, and the maximum carrying capacity of the subway transfer station C is 1000, so the second traffic carrying degree of 7.00-8.00 is 0.119.

[0110] If not, according to the positional relationship between the adjacent subway station and the subway transfer station, the transfer area of the subway transfer station is re-divided, and the second traffic carrying degree of the subway transfer station at the target departure time node is determined according to the population information and business information of the re-divided transfer area of the subway transfer station.

[0111] Comprising:

[0112] Judging whether there is a commercial body or a residential area in the overlapping transfer area.

[0113] If not, the overlapping transfer area is equally divided to obtain the re-divided transfer area of the subway transfer station.

[0114] As shown in Figure 2 , D is the transfer area of the subway transfer station d, E is the transfer area of the subway transfer station e, and F is the overlapping area of D and E. If there is no commercial body or residential area in the overlapping transfer area, the subway transfer station d and the subway transfer station e divide F equally.

[0115] If there is, the regional division ratio is determined according to the travel preference of the commercial body or the residential area, and the overlapping transfer area is divided according to the regional division ratio to obtain the re-divided transfer area of the subway transfer station.

[0116] According to the travel preference of the personnel of the commercial body or the residential area, if the travel preference of the personnel of the commercial body or the residential area is more biased towards the subway transfer station d, it means that the bias towards the subway transfer station d should be more in the regional division ratio.

[0117] For example, the travel preference of the personnel of the commercial body or the residential area is:

[0118] Subway transfer station d: subway transfer station e=6:4, so the regional division ratio can be 6:4.

[0119] The application determines the regional division ratio according to the travel preference of the commercial body or the residential area, which can improve the rationality of the division of the transfer area.

[0120] According to the second traffic carrying degree and the first traffic carrying degree of the subway transfer station, it is judged whether to replace the target subway riding path of the target.

[0121] If the difference between the sum of the second passenger flow carrying degrees of the several subway transfer stations and the sum of the first passenger flow carrying degrees is greater than a first threshold value, or the difference between the second passenger flow carrying degree and the first passenger flow carrying degree of any subway transfer station is greater than a second threshold value, the target subway riding path is replaced; otherwise, the target subway riding path is not replaced.

[0122] The difference between the sum of the second passenger flow carrying degrees and the sum of the first passenger flow carrying degrees being greater than the first threshold value or the difference between the second passenger flow carrying degree and the first passenger flow carrying degree of any subway transfer station being greater than the second threshold value indicates that the deviation is too large, the prediction deviates from the situation, and the target subway riding path can be reset with the shortest time.

[0123] The application can realize dynamic optimization of the travel path by comparing the difference between the second passenger flow carrying degree and the first passenger flow carrying degree of the subway transfer station, setting a threshold value judgment condition to determine whether to replace the target subway path, and can improve the rationality of route determination.

[0124] In summary, the present application provides a transfer planning method based on multiple public transportation modes, comprising: dividing a historical time period of a target city to obtain a plurality of historical time sub-periods, and classifying each time sub-period; determining an outer circle layer and an inner circle layer of the target city; dividing the historical time sub-periods under each life type into segments with a maximum time unit of day and a segmentation unit of hour, and determining the hourly transfer sharing rate of each subway station under each life type; constructing a data group based on the life type, the subway station, the hourly transfer sharing rate, the circle layer where the subway station is located, and the hourly subway passenger flow of the subway station, and training a neural network model to be trained based on the data group to obtain a passenger flow carrying capacity prediction model; obtaining a target departure time node, a starting position and a terminal position, and determining a plurality of subway riding paths based on the starting position and the terminal position; predicting the first passenger flow carrying capacity of the subway station of the subway riding path under the target departure time node based on the passenger flow carrying capacity prediction model, and determining the subway transfer station and the target subway riding path from the plurality of subway riding paths based on the prediction result. The present application divides the time period based on the life type, which can improve the accuracy of the passenger flow carrying capacity prediction. The present application binds the hourly transfer sharing rate of the subway station in each hour of the day, the life type of the subway station on the day, the circle layer where the subway station is located, the hourly subway passenger flow of the subway station into a data group based on the subway station as an anchor point, and trains the passenger flow carrying capacity prediction model based on the data group. Based on the passenger flow carrying capacity prediction model, the sum of the first passenger flow carrying capacity of each station of each path is obtained. Based on the sum of the first passenger flow carrying capacity, a target subway riding path that is most comfortable to ride and balanced in time and number of stations can be provided for cross-zone customers. The present application considers the passenger flow density of each station in the path, effectively avoiding the inconvenience and delay risk caused by peak hours or high-load stations; on the other hand, by determining the sum of the carrying capacity of the entire path, the deviation caused by simply relying on the number of stations or the length of the path is avoided, making the path selection more close to the actual travel experience. In combination with the division of life type and time period, the prediction result is more scene-adaptive, improving the intelligence and personalization level of path planning, which helps to alleviate the local congestion of the subway system and optimize the efficiency of urban traffic operation. The present application determines the regional division proportion through the travel preferences of commercial bodies or residential areas, which can improve the rationality of the transfer area division. The present application compares the difference between the second passenger flow carrying capacity and the first passenger flow carrying capacity of the subway transfer station, sets a threshold judgment condition to determine whether to replace the target subway path, which can realize dynamic optimization of the travel path. The present application uses the second passenger flow carrying capacity of the subway transfer station to correct the target subway riding path, which can improve the rationality of route determination.

[0125] Based on the same inventive concept, the present application provides a transfer planning system based on multiple public transportation modes, comprising:

[0126] a time division module, configured to divide a historical time period of a target city to obtain a plurality of historical time sub-periods, and classify each of the historical time sub-periods, wherein each of the historical time sub-periods belongs to a life type, and the life type includes a holiday type, a weekday type, and a rest day type;

[0127] a circle layer division module, configured to determine an outer circle layer and an inner circle layer of the target city, wherein the outer circle layer and the inner circle layer each include a plurality of subway stations, bus stations, and shared bicycle stations;

[0128] a sharing rate determination module, configured to divide the historical time sub-periods under each life type by taking a day as a maximum time unit and an hour as a division unit, and determine an hourly transfer sharing rate of each subway station under each life type;

[0129] a neural network training module, configured to construct a data group by taking a life type, a subway station, an hourly transfer sharing rate, a circle layer where the subway station is located, and an hourly subway passenger flow of the subway station, train a to-be-trained neural network model by taking the data group, and obtain a passenger flow carrying capacity prediction model, wherein the to-be-trained neural network model is used to predict a first passenger flow carrying capacity of the subway station;

[0130] a path screening module, configured to obtain a departure time node, a starting position, and a terminal position of a target, and determine a plurality of subway riding paths according to the starting position and the terminal position;

[0131] a path determination module, configured to predict a first passenger flow carrying capacity of a subway station of a subway riding path of the target at the departure time node by taking the passenger flow carrying capacity prediction model, and determine a subway transfer station and the target subway riding path from the plurality of subway riding paths according to a prediction result.

[0132] Based on the same inventive concept, the present application also provides an electronic device, comprising:

[0133] a processor;

[0134] a memory for storing processor-executable instructions;

[0135] wherein the processor is configured to execute to implement the transfer planning method based on multiple public transportation modes as provided in the foregoing.

[0136] Based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the transfer planning method based on multiple public transportation modes as provided in the foregoing.

[0137] Since the electronic device introduced in the embodiment is the electronic device used for implementing the method for processing information in the embodiment of the present application, based on the method for processing information introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device in the embodiment and various changes thereof, so how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the electronic device used for implementing the method for processing information in the embodiment of the present application is implemented by those skilled in the art, it belongs to the scope of the present application.

[0138] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer-readable program code.

[0139] The present application is described in relation to flowcharts and / or block diagrams that illustrate the methodology, apparatus (system) and computer program product according to embodiments of the present application. It is understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations 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 a processor of a general purpose computer, a special purpose computer, an embedded processor or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, create means for implementing the functions specified in the flowcharts and / or block diagrams block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified by the flow or flows and / or block or blocks.

[0140] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions means which implement the function specified in the flowcharts and / or block diagrams flow or flows and / or block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified by the flow or flows and / or block or blocks.

[0141] These computer program instructions can also be loaded onto a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer implemented process such that the instructions which execute on the computer or other programmable device provide steps for implementing the functions specified in the flowcharts and / or block diagrams flow or flows and / or block or blocks. Figure 1 one or more flows and / or blocks Figure 1steps of the functions specified in the block or blocks.

[0142] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to encompass within their scope all such variations and modifications as are included within the scope of the application.

[0143] It is apparent that those skilled in the art can, without departing from the spirit and scope of the application, make various changes and modifications of the application. Thus, it is intended that the present application cover all such changes and modifications that are within the scope of this application, along with all equivalents thereof.

Claims

1. A transfer planning method based on multiple public transportation modes, characterized in that, include: The historical time period of the target city is divided into several historical time segments, and each time segment is classified. Each time segment belongs to a type of lifestyle, including holiday type, weekday type, and rest day type. Determine the outer and inner rings of the target city, each of which includes several subway stations, bus stops, and shared bicycle stations; Using days as the largest time unit and hours as the dividing unit, the historical time segments under each lifestyle type are divided, and the hourly connection share rate of each subway station under each lifestyle type is determined. A data set was constructed based on lifestyle type, subway station, hourly connection modal share, the area where the subway station is located, and the hourly subway passenger flow at the subway station. The data set was used to train the neural network model to obtain a passenger flow carrying capacity prediction model. The neural network model to be trained was used to predict the first passenger flow carrying capacity of the subway station. Obtain the departure time, starting location, and ending location of the target, and determine several subway routes based on the starting and ending locations; The passenger flow carrying capacity prediction model is used to predict the first passenger flow carrying capacity of the subway stations along the subway travel route at the departure time node of the target, and the subway transfer stations and the target subway travel route are determined from several subway travel routes based on the prediction results. Also includes: Determine the district / zone where the subway transfer station is located; Determine the connection area of ​​the subway transfer station based on the ring road where the subway transfer station is located; Determine whether the connection area of ​​any adjacent subway station overlaps with the connection area of ​​a subway transfer station; If so, then based on the population and commercial information of the connecting area of ​​the subway transfer station, determine the second passenger flow carrying capacity of the subway transfer station at the departure time of the target. If not, the connection area of ​​the metro transfer station is re-divided according to the location relationship between the adjacent metro stations and the metro transfer station, and the second passenger flow carrying capacity of the metro transfer station at the departure time node is determined based on the population and commercial information of the re-divided connection area of ​​the metro transfer station. Based on the locational relationship between adjacent subway stations and subway transfer stations, the connection areas of subway transfer stations are re-divided, including: Determine whether there are commercial buildings or residential areas within the overlapping connection areas; If it does not exist, the overlapping connection areas are divided equally to obtain the connection areas of the subway transfer stations after re-division. If they exist, the area division ratio is determined based on the travel preferences of commercial areas or residential areas, and the overlapping connection areas are divided according to the area division ratio to obtain the connection areas of the re-divided subway transfer stations. Based on the second and first passenger flow capacity of the subway transfer station, determine whether to change the target subway route, specifically including: If the difference between the sum of the second passenger flow capacity and the sum of the first passenger flow capacity of several subway transfer stations is greater than the first threshold, or if the difference between the second passenger flow capacity and the first passenger flow capacity of any subway transfer station is greater than the second threshold, then the target subway route will be changed; otherwise, it will not be changed.

2. The transfer planning method based on multiple public transportation modes as described in claim 1, characterized in that, Based on the prediction results, subway transfer stations and target subway routes are determined from several subway travel routes, including: Determine the sum of the first passenger flow carrying capacity for each subway route; The subway route with the lowest sum of passenger flow capacity is selected as the target subway route, and the subway transfer stations are determined within the target subway route.

3. The transfer planning method based on multiple public transportation modes as described in claim 1, characterized in that, Determine the outer and inner concentric layers of the target city, including: The target city is divided into outer and inner layers based on its urban planning.

4. The transfer planning method based on multiple public transportation modes as described in claim 1, characterized in that, Several subway routes are determined based on the starting and ending points, including: Determine the starting subway station based on the starting location; the number of starting subway stations is greater than or equal to 1. Based on the destination location, determine the subway station of the destination. The number of subway stations of the destination is greater than or equal to 1. Based on the starting and ending subway stations, several subway travel routes are planned.

5. A transfer planning system based on multiple public transportation modes, characterized in that, The transfer planning system based on multiple public transport modes, as described in any one of claims 1-4, comprises: The time segmentation module is used to divide the historical time period of the target city into several historical time segments, and to classify each time segment into a type of lifestyle, including holiday type, weekday type, and rest day type. The concentric circle segmentation module is used to determine the outer and inner concentric circles of the target city. Both the outer and inner concentric circles include several subway stations, bus stops, and shared bicycle stations. The modal share determination module is used to divide the historical time segments under each type of lifestyle into segments with days as the maximum time unit and hours as the segmentation unit, and to determine the hourly modal share of each subway station under each type of lifestyle. The neural network training module is used to construct a data set based on lifestyle type, subway station, hourly connection modal share, the area where the subway station is located, and the hourly subway passenger flow of the subway station. The neural network model to be trained is then used to train the model to obtain a passenger flow carrying capacity prediction model. The neural network model to be trained is used to predict the first passenger flow carrying capacity of the subway station. The route filtering module is used to obtain the departure time, starting location, and ending location of the target, and to determine several subway travel routes based on the starting location and ending location. The route determination module is used to predict the first passenger flow capacity of the subway stations along the subway route at the departure time node of the target using a passenger flow capacity prediction model, and to determine the subway transfer stations and the target subway route from several subway routes based on the prediction results.

6. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the transfer planning method based on multiple public transport modes as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the non-transitory computer-readable storage medium are executed by the processor of the electronic device, the electronic device is enabled to perform the transfer planning method based on multiple public transport modes as described in any one of claims 1 to 4.

Images