Transfer planning method, system and equipment based on multiple public transport modes and medium

Abstract

The invention discloses a transfer planning method, system, equipment and medium based on multiple public transport modes, and the method comprises the steps: dividing a historical time period of a target city to obtain a plurality of historical time sub-segments, and classifying each time sub-segment; determining an outer circle layer and an inner circle layer of the target city; the hour connection sharing rate of each subway station under each life type is determined; training a to-be-trained neural network model by using the data set to obtain a people flow bearing degree prediction model; determining a plurality of subway taking paths according to the initial position and the final position; and carrying out prediction by using a people flow bearing degree prediction model, and determining a subway transfer station and a target subway taking path from the plurality of subway taking paths according to a prediction result. The invention belongs to the field of subway transfer. According to the invention, a most comfortable subway transfer route can be provided.

Description

Technical Field

[0001] The present invention relates to the field of subway transfers, and in particular to a transfer planning method, system, equipment and medium based on multiple public transportation modes. Background Art

[0002] As cities develop, travel options are becoming increasingly diverse, including subways, buses, shared bikes, walking, and private cars. In economically developed regions (such as Beijing, Shanghai, Chengdu, Wuhan, and Xi'an), subways are the most popular mode of transportation.

[0003] Cities with pie-shaped development and mature infrastructure, such as Beijing and Chengdu, are typically divided into inner and outer rings. Both rings are served by numerous subway lines, crisscrossing and connecting the inner and outer rings. For work or daily life, some people first travel to a nearby subway station by bus, shared bike, walking, or private car. Then, they take the subway from the outer ring to the inner ring, or vice versa, requiring multiple transfers before finally reaching a subway station near their destination.

[0004] Currently, major subway line apps usually recommend the shortest route, and some apps also reflect the real-time congestion status of the line. However, for passengers with long spans and many transfer points, how to more accurately predict easier transfer routes for them is an urgent problem to be solved. Summary of the Invention

[0005] The present invention solves the technical problem in the prior art of how to more accurately predict easier transfer routes for people with long spans and many transfer points by providing a transfer planning method, system, equipment and medium based on multiple public transportation modes, thereby achieving the technical effect of providing easier transfer routes.

[0006] In a first aspect, the present invention provides a transfer planning method based on multiple public transportation modes, comprising: Divide the historical time period of the target city into several historical time sub-segments, and classify each time sub-segment into a life type, including holiday type, workday type, and rest day type. Identify the outer and inner circles of the target city, where each circle includes several subway stations, bus stops, and shared bike stations; Using days as the maximum time unit and hours as the division unit, the historical time sub-segments under each lifestyle type are divided, and the hourly connection share of each subway station under each lifestyle type is determined; A data set is constructed based on lifestyle, subway station, hourly connection share, subway station's circle, and subway station's hourly subway passenger flow. The trained neural network model is trained with this data set to obtain a passenger flow carrying capacity prediction model. The trained neural network model is used to predict the first passenger flow carrying capacity of the subway station. Obtain the target's departure time node, starting location, and end location, and determine several subway routes based on the starting location and end location; The passenger flow carrying capacity prediction model is used to predict the first passenger flow carrying capacity of the subway station on the subway riding path at the target departure time node, and the subway transfer station and the target subway riding path are determined from several subway riding paths based on the prediction results.

[0007] Furthermore, for each subway transfer station, it also includes: Determine the circle where the subway transfer station is located; Determine the connecting area of ​​the subway transfer station based on the circle where the subway transfer station is located; Determine whether the docking area of ​​any adjacent subway station overlaps with the docking area of ​​a subway transfer station; If so, determine the second passenger flow carrying capacity of the subway transfer station at the target departure time node based on the population information and business information of the connecting area of ​​the subway transfer station; If not, then the connecting area of ​​the subway transfer station is re-divided based on the location relationship between the adjacent subway stations and the subway transfer station. The population and business information of the re-divided connecting area of ​​the subway transfer station is used to determine the second passenger flow carrying capacity of the subway transfer station at the target departure time node; According to the second passenger flow carrying capacity and the first passenger flow carrying capacity of the subway transfer station, it is determined whether to change the target subway riding route.

[0008] Furthermore, based on the location 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 or residential areas within the overlapping connection areas; If it does not exist, the overlapping connecting areas are divided equally to obtain the connecting areas of the re-divided subway transfer stations; If so, the regional division ratio is determined based on the travel preferences of commercial entities or residential areas, and the overlapping connecting areas are divided according to the regional division ratio to obtain the connecting areas of the re-divided subway transfer stations.

[0009] Furthermore, judging whether to change the target subway travel route according to the second passenger flow carrying capacity and the first passenger flow carrying capacity of the subway transfer station includes: If the difference between the sum of the second passenger flow carrying capacity of several subway transfer stations and the sum of the first passenger flow carrying capacity is greater than the first threshold, or the difference between the second passenger flow carrying capacity of any subway transfer station and the first passenger flow carrying capacity is greater than the second threshold, the target subway riding route is changed; otherwise, it is not changed.

[0010] Furthermore, a subway transfer station and a target subway riding route are determined from the plurality of subway riding routes based on the prediction results, including: Determine the sum of the first passenger flow carrying capacity of each subway route; The subway riding route with the lowest sum of the first passenger flow carrying factors is used as the target subway riding route, and subway transfer stations are determined in the target subway riding route.

[0011] Furthermore, the outer and inner circles of the target city are determined, including: The target city is divided according to its urban planning to obtain the outer circle and inner circle of the target city.

[0012] Furthermore, several subway routes are determined based on the starting location and the ending location, including: Determine the starting subway station according to the starting position, where the number of the starting subway station is greater than or equal to 1; According to the terminal location, determine the subway station of the terminal, and the number of subway stations of the terminal is greater than or equal to 1; According to the starting subway station and the ending subway station, several subway routes are planned.

[0013] In a second aspect, the present invention provides a transfer planning system based on multiple public transportation modes, comprising: The time division module is used to divide the historical time period of the target city into several historical time sub-segments and classify each time sub-segment, where each time sub-segment belongs to a life type, including holiday type, workday type and rest day type; The circle division module is used to determine the outer and inner circles of the target city, where both the outer and inner circles include several subway stations, bus stations, and shared bicycle stations; The sharing rate determination module is used to divide the historical time sub-segments under each lifestyle type into days as the maximum time unit and hours as the segmentation unit, and determine the hourly connection sharing rate of each subway station under each lifestyle type; A neural network training module is used to construct a data set based on lifestyle, subway station, hourly connection share, subway station circle, and hourly subway passenger flow at the subway station, and train a to-be-trained neural network model using the data set 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; The path screening module is used to obtain the target's departure time node, starting location and end location, and determine several subway routes based on the starting location and end location; The path determination module is used to predict the first passenger flow carrying capacity of the subway station on the subway riding path at the target departure time node using the passenger flow carrying capacity prediction model, and determine the subway transfer station and the target subway riding path from several subway riding paths based on the prediction results.

[0014] In a third aspect, the present invention provides an electronic device, comprising: processor; a memory for storing processor-executable instructions; The processor is configured to execute to implement the transfer planning method based on multiple public transportation modes as provided in the first aspect.

[0015] In a fourth aspect, the present invention provides a non-temporary computer-readable storage medium. When the instructions in the non-temporary computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement the transfer planning method based on multiple public transportation modes as provided in the first aspect.

[0016] One or more technical solutions provided in the present invention have at least the following technical effects or advantages: The present invention uses subway stations as anchor points, binds the hourly connection share rate of the subway station every hour of every day, the life type of the subway station on that day, the circle where the subway station is located, and the subway passenger flow of the subway station in that hour into a data group, and trains based on the data group to obtain a passenger flow carrying capacity prediction model. Based on the passenger flow carrying capacity prediction model, the sum of the first passenger flow carrying capacity of each station on each path is obtained. Based on the sum of the first passenger flow carrying capacity, a target subway riding route that is most comfortable and balanced in time and number of stations can be provided for cross-region customers.

[0017] This invention takes into account the density of pedestrian flow at each station along the route, effectively avoiding the travel inconvenience and delay risks caused by peak hours or high-load stations. On the other hand, by determining the sum of the carrying capacity of the entire route, it avoids the deviation caused by relying solely on the number of stations or path length, making the route selection closer to the actual travel experience. It also combines the division of life types and time periods to make the prediction results more scenario-adaptive, improve the intelligence and personalization level of route planning, help alleviate local congestion in the subway system, and optimize urban traffic operation efficiency.

[0018] The present invention determines the area division ratio according to the travel preferences of commercial entities or residential areas, which can improve the rationality of the connection area division.

[0019] The present invention compares the difference between the second passenger flow carrying capacity and the first passenger flow carrying capacity of a subway transfer station, sets a threshold judgment condition to decide whether to change the target subway route, and can achieve dynamic optimization of the travel route.

[0020] The present invention corrects the target subway riding route based on the second passenger flow carrying capacity of the subway transfer station, thereby improving the rationality of route determination.

[0021] The present invention divides time periods according to lifestyle types, which can improve the accuracy of pedestrian flow carrying capacity prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A flow chart of a transfer planning method based on multiple public transportation modes provided by the present invention; Figure 2 Schematic diagram of the docking area provided by the present invention. DETAILED DESCRIPTION

[0024] The embodiment of the present invention solves the technical problem in the prior art of how to more accurately predict easier transfer routes for people with long spans and many transfer points by providing a transfer planning method based on multiple public transportation modes.

[0025] The technical solution of the present invention is to solve the above technical problems, and the overall idea is as follows: The transfer planning method based on multiple public transportation modes includes: dividing the historical time period of the target city to obtain several historical time sub-segments, and classifying each time sub-segment, wherein each time sub-segment belongs to a life type, and the life type includes a holiday type, a workday type, and a rest day type; determining the outer circle and the inner circle of the target city, wherein the outer circle and the inner circle both include several subway stations, bus stations, and shared bicycle stations; using the day as the maximum time unit and the hour as the division unit, dividing the historical time sub-segments under each life type, and determining the hourly connection share rate of each subway station under each life type; and dividing the historical time sub-segments under each life type by life type, subway station, hourly connection rate, and so on. A data set is constructed based on the sharing rate, the circle 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 to be trained is used to predict the first passenger flow carrying capacity of the subway station; the departure time node, starting position and end position of the target are obtained, and several subway riding routes are determined according to the starting position and the end position; the passenger flow carrying capacity prediction model is used to predict the first passenger flow carrying capacity of the subway station in the subway riding route at the departure time node of the target, and the subway transfer station and the target subway riding route are determined from the several subway riding routes according to the prediction results.

[0026] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0027] First, the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0028] The present invention can provide an alternative subway ride for people in cities that have experienced pie-shaped development and mature supporting facilities. Cities that have experienced pie-shaped development and mature supporting facilities may include Beijing, Shanghai, Guangzhou, Shenzhen, Chengdu, Chongqing, Hangzhou, Nanjing, Wuhan, Xi'an, London, New York, Tokyo, Singapore, Sydney, and Paris.

[0029] Cities that develop in a pie-shaped pattern are usually divided into an inner ring and an outer ring. Both the inner ring and the outer ring contain several subway lines, which connect the inner and outer rings in series.

[0030] The present invention can mainly provide another riding mode for people who take the subway from the outer side of the inner ring to the outer ring, or from the inner side of the outer ring to the inner ring, and need to transfer several times on the way.

[0031] The present invention provides Figure 1 The transfer planning method based on multiple public transportation modes shown includes steps S11-S16: Step S11, divide the historical time period of the target city into several historical time sub-segments, and classify each time sub-segment, wherein each time sub-segment belongs to a life type, and the life type includes a holiday type, a workday type, and a rest day type.

[0032] Target cities can be those that exhibit pie-shaped development and have mature supporting facilities. The historical period is typically 365 days or longer. To improve accuracy, data from the last three years can be used.

[0033] The historical time period is divided into several historical time sub-segments according to the life type. For example, 2024.5.1-2024.5.15 (only 15 days are selected for the sake of ease of explanation), among which 2024.5.1-2024.5.5 is a historical time sub-segment, and the life type of this time sub-segment is the holiday type; 2024.5.6-2024.5.10 is a historical time sub-segment, and the life type of this time sub-segment is the weekday type; 2024.5.11-2024.5.12 is a historical time sub-segment, and the life type of this time sub-segment is the rest day type; 2024.5.13-2024.5.15 is a historical time sub-segment, and the life type of this time sub-segment is the weekday type.

[0034] The present invention divides time periods according to lifestyle types, which can improve the accuracy of pedestrian flow carrying capacity prediction.

[0035] It's understandable that different lifestyles correspond to different types of travelers. For example, holidays are dominated by tourists, while weekdays are dominated by workers, and their travel times also vary. Therefore, different lifestyles have distinct travel characteristics. This invention uses lifestyles as a reference for predicting passenger flow carrying capacity, which can improve prediction accuracy.

[0036] After determining the life type of each historical time sub-segment, the life type of each historical time sub-segment is classified to obtain a number of historical time sub-segments under each life type.

[0037] Step S12: determine the outer and inner circles of the target city, where both the outer and inner circles include several subway stations, bus stations, and shared bicycle stations.

[0038] Determining the outer and inner circles of the target city includes: dividing the target city according to the urban planning of the target city to obtain the outer and inner circles of the target city.

[0039] After clarifying the historical time division of the target city, the spatial structure of the city can be divided into circles, that is, the city can be divided into two areas: the outer circle and the inner circle.

[0040] Since this invention primarily targets pie-shaped cities, pie-shaped cities can typically be naturally divided into inner and outer rings. For example, Chengdu's inner ring is within the Third Ring Road, while the outer ring is outside the Third Ring Road. Another example is Beijing's inner ring is within the Fifth Ring Road, while the outer ring is outside the Fifth Ring Road. Other cities can determine their own rings based on their own urban planning, and this is not a limitation. It is understood that both the inner and outer rings contain several subway stations, bus stops, and shared bike stations.

[0041] Step S13 , using day as the maximum time unit and hour as the division unit, divides the historical time sub-segments under each lifestyle type, and determines the hourly connection share rate of each subway station under each lifestyle type.

[0042] The connection share rate is the ratio of the number of people using transportation to or from a metro station during a specific time period to the total number of people using that metro station. Transportation options for reaching a metro station include walking, cycling, public transportation, driving, or traveling from other metro stations.

[0043] Using day as the largest time unit means dividing time into days first, and using hour as the division unit means dividing each day into 24 hours.

[0044] Taking into account the actual subway operation situation, the present invention only takes 6:00-23:00 as the effective hours. In other words, the hourly connection sharing rate in the following text also only includes 6:00-23:00.

[0045] After segmenting by day and hour, based on the subway station data from 6:00 to 23:00 under each lifestyle type, the connection share rate in fixed time periods of several historical time subsegments under the same lifestyle type is calculated, and this is used as the hourly connection share rate for that time period on that day.

[0046] For ease of understanding, Table 1 is provided. Table 1 shows the hourly connection share rate of a subway station A in a certain city on May 1, 2023, when the life type is holiday type.

[0047]

[0048] It is understandable that, for the convenience of calculation, the present invention combines the connection share rates of arriving at and leaving the subway station by choosing the same mode of transportation. That is, the present invention does not distinguish whether arriving at or leaving the subway station, but only distinguishes the mode of arrival and departure.

[0049] Taking 7:00-8:00 on May 1, 2023 as an example, the number of people entering subway station A is 100, and the number of people leaving subway station A is 50, so the total passenger flow is 150. Among them, the number of people who choose to enter subway station A by car is 5, and the number of people who choose to leave subway station A by car is 10. The hourly connection share rate of car as a means of transportation is 10%.

[0050] Step S14, construct a data group based on lifestyle type, subway station, hourly connection share, the circle where the subway station is located, and the hourly subway passenger flow of the subway station, and use the data group to train the neural network model to obtain a passenger flow carrying capacity prediction model, wherein the neural network model to be trained is used to predict the first passenger flow carrying capacity of the subway station.

[0051] Using a subway station as an anchor, we combined the station's hourly connection share, the daily lifestyle, the area it's located in, and the subway passenger flow at that station for that hour into a single data set. This yielded several data sets in total. The passenger flow capacity refers to the ratio of a station's current passenger flow to its maximum capacity.

[0052] Several data groups are input into the neural network model to be trained, 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 neural network model to be trained is output and used as a pedestrian flow carrying capacity prediction model.

[0053] It is understandable that training a neural network model based on a data set is a conventional process and will not be described in detail here.

[0054] Step S15: Obtain the departure time node, starting position and end position of the target, and determine several subway riding routes according to the starting position and the end position.

[0055] Specifically, it includes: determining the starting subway station according to the starting position, and the number of the starting subway station is greater than or equal to 1; determining the ending subway station according to the ending position, and the number of the ending subway station is greater than or equal to 1; and planning several subway routes according to the starting subway station and the ending subway station.

[0056] It is understandable that there may be one or more subway stations near the starting location. At this time, the starting subway station can be selected according to the actual situation and the mode of travel. For example, if traveling by car, you can consider a subway station within a radius of 3 kilometers as the starting subway station. If walking, choose a subway station within a radius of 1 kilometer as the starting subway station. The same applies to the ending subway station.

[0057] After determining the starting and ending subway stations, several subway routes can be planned.

[0058] Step S16, using the passenger flow carrying capacity prediction model to predict the first passenger flow carrying capacity of the subway station at the departure time node under the target departure time node, and determine the subway transfer station and the target subway riding route from several subway riding routes based on the prediction results.

[0059] Determine subway transfer stations and a target subway route from a plurality of subway routes based on the prediction results, including: determining the sum of the first passenger flow carrying capacity of each subway route; taking the subway route with the lowest sum of the first passenger flow carrying capacity as the target subway route, and determining subway transfer stations in the target subway route.

[0060] Determining the departure time node means that the type of life on that day is determined and the time period in which the departure time node is located is determined.

[0061] It's understandable that every subway station on every subway route has a primary passenger flow capacity. A lower sum of primary passenger flow capacity not only indicates a lower overall passenger flow trend for that subway route, but also means that the route passes through fewer subway stations, resulting in a shorter transit time. (If all primary passenger flow capacity values ​​along a subway route are low, but the number of stations passed is high, the sum of the primary passenger flow capacity values ​​can also be high.)

[0062] Subway transfer stations refer to subway stations where transfers are required along the route.

[0063] In view of this, the present invention uses the subway station as an anchor point, binds the hourly connection share rate of the subway station every hour of every day, the life type of the subway station on that day, the circle where the subway station is located, and the subway passenger flow of the subway station in that hour into a data group, and trains based on the data group to obtain a passenger flow carrying capacity prediction model. Based on the passenger flow carrying capacity prediction model, the sum of the first passenger flow carrying capacity of each station on each path is obtained. Based on the sum of the first passenger flow carrying capacity, a target subway riding route that is most comfortable and balanced in time and number of stations can be provided for cross-region customers.

[0064] This invention takes into account the density of pedestrian flow at each station along the route, effectively avoiding the travel inconvenience and delay risks caused by peak hours or high-load stations. On the other hand, by determining the sum of the carrying capacity of the entire route, it avoids the deviation caused by relying solely on the number of stations or path length, making the route selection closer to the actual travel experience. It also combines the division of life types and time periods to make the prediction results more scenario-adaptive, improve the intelligence and personalization level of route planning, help alleviate local congestion in the subway system, and optimize urban traffic operation efficiency.

[0065] In addition, for each subway transfer station (transfers are only made at subway transfer stations, which provide the lowest safety and comfort, so this invention only considers subway transfer stations), the following are also included: Determine the circle where the subway transfer station is located.

[0066] Determine the connecting area of ​​the subway transfer station based on the circle where the subway transfer station is located.

[0067] It is understandable that the sizes of the docking areas in different circles are different. Usually the docking area of ​​the inner circle is smaller than that of the outer circle (because the stations in the outer circle are sparser than those in the inner circle). For example, the connection area of ​​the subway station in the outer circle of city B is the area formed by 9KM, and the connection area of ​​the subway station in the inner circle of city B is the area formed by 5KM. The specific area can be determined according to each city.

[0068] Determine whether the docking area of ​​any adjacent subway station overlaps with the docking area of ​​a subway transfer station.

[0069] If so, the second passenger flow carrying capacity of the subway transfer station at the target departure time node is determined based on the population information and business information of the connecting area of ​​the subway transfer station.

[0070] Population information represents the permanent population within the connection area of ​​a subway transfer station, while commercial information includes the floating population within the connection area. These correlation coefficients can usually be calculated by compiling historical data. Table 2 shows the coefficients for subway transfer station C. These coefficients reflect the probability that a floating or fixed population will enter or leave subway transfer station C during that time period.

[0071]

[0072] Taking 7:00-8:00 as an example, the permanent population (population information) of the connecting area of ​​subway transfer station C is 70,000 and the floating population is 50,000 (commercial information). The number of people entering or leaving between 7:00 and 8:00 is 70,000*0.0012+50,000*0.0007=119 people. The maximum hourly load of subway transfer station C is 1,000. The second passenger flow load between 7:00 and 8:00 is 0.119.

[0073] If not, the connecting area of ​​the subway transfer station will be redivided according to the location relationship between the adjacent subway stations and the subway transfer station, and the second passenger flow carrying capacity of the subway transfer station at the target departure time node will be determined based on the population information and commercial information of the redivided connecting area of ​​the subway transfer station.

[0074] include: Determine whether there are commercial or residential areas within the overlapping connection areas.

[0075] If it does not exist, the overlapping connecting areas are divided equally to obtain the connecting areas of the re-divided subway transfer stations.

[0076] like Figure 2 As shown, D is the docking area of ​​subway transfer station d, and E is the docking area of ​​subway transfer station e. The two overlap to form F. If there is no commercial entity or residential area in the overlapping docking area, then subway transfer station d and subway transfer station e will divide F equally.

[0077] If so, the regional division ratio is determined based on the travel preferences of commercial entities or residential areas, and the overlapping connecting areas are divided according to the regional division ratio to obtain the connecting areas of the re-divided subway transfer stations.

[0078] According to the travel preferences of people in commercial buildings or residential areas, if the travel preferences of people in commercial buildings or residential areas are more inclined to subway transfer station d, it means that the proportion of regional divisions that favor subway transfer station d should be higher.

[0079] For example, the travel preferences of people in commercial or residential areas are: If subway transfer station d: subway transfer station e=6:4, then the area division ratio can be 6:4.

[0080] The present invention determines the area division ratio according to the travel preferences of commercial entities or residential areas, which can improve the rationality of the connection area division.

[0081] According to the second passenger flow carrying capacity and the first passenger flow carrying capacity of the subway transfer station, it is determined whether to change the target subway riding route.

[0082] Including: if the difference between the sum of the second passenger flow carrying capacity of several subway transfer stations and the sum of the first passenger flow carrying capacity is greater than a first threshold, or the difference between the second passenger flow carrying capacity of any subway transfer station and the first passenger flow carrying capacity is greater than a second threshold, then the target subway riding route is changed; otherwise, it is not changed.

[0083] If the difference between the sum of the second passenger flow carrying capacity and the sum of the first passenger flow carrying capacity is greater than the first threshold, or the difference between the second passenger flow carrying capacity and the first passenger flow carrying capacity of any subway transfer station is greater than the second threshold, it means that the deviation is too large. If there is a deviation in the prediction, the target subway riding route can be reset in the shortest time.

[0084] This invention compares the difference between the second and first passenger flow capacity at a subway transfer station and sets a threshold judgment condition to determine whether to change the target subway route, thereby achieving dynamic optimization of travel routes. This invention uses the second passenger flow capacity of the subway transfer station to correct the target subway route, thereby improving the rationality of route determination.

[0085] In summary, the present invention provides a transfer planning method based on multiple public transportation modes, including: dividing the historical time period of the target city to obtain several historical time sub-segments, and classifying each time sub-segment; determining the outer circle and inner circle of the target city; dividing the historical time sub-segments under each life type with days as the maximum time unit and hours as the segmentation unit, and determining the hourly connection share rate of each subway station under each life type; constructing a data group based on life type, subway station, hourly connection share rate, the circle 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 with the data group to obtain a passenger flow carrying capacity prediction model; obtaining the departure time node, starting position and end position of the target, and determining several subway riding paths according to the starting position and the end position; using the passenger flow carrying capacity prediction model to predict the first passenger flow carrying capacity of the subway station of the subway riding path under the target departure time node, and determining the subway transfer station and the target subway riding path from the several subway riding paths according to the prediction results. The present invention divides the time period by life type, which can improve the accuracy of passenger flow carrying capacity prediction. The present invention uses subway stations as anchor points, binds the hourly connection share rate of each subway station every hour of each day, the lifestyle of the subway station on that day, the circle in which the subway station is located, and the subway passenger flow of the subway station in that hour into a data set, and trains based on the data set to obtain a passenger flow carrying capacity prediction model. Based on the passenger flow carrying capacity prediction model, the sum of the first passenger flow carrying capacity of each station on each path is obtained. Based on the sum of the first passenger flow carrying capacity, a target subway travel route that is most comfortable and balanced in terms of time and number of stations can be provided for cross-region customers. The present invention takes into account the passenger flow density of each station in the route, effectively avoiding the inconvenience and delay risks caused by peak hours or high-load stations. On the other hand, by determining the sum of the carrying capacity of the entire route, the deviation caused by relying solely on the number of stations or route length is avoided, making the route selection more close to the actual travel experience. In addition, the combination of lifestyle and time period division makes the prediction result more scenario-adaptive, improves the intelligence and personalization level of route planning, helps to alleviate local congestion in the subway system, and optimizes the efficiency of urban transportation operation. The present invention determines the regional division ratio based on the travel preferences of commercial entities or residential areas, which can improve the rationality of the connection area division. The present invention 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 change the target subway route, and can achieve dynamic optimization of the travel route. The present invention corrects the target subway riding route based on the second passenger flow carrying capacity of the subway transfer station, which can improve the rationality of the route determination.

[0086] Based on the same inventive concept, the present invention provides a transfer planning system based on multiple public transportation modes, including: The time division module is used to divide the historical time period of the target city into several historical time sub-segments and classify each time sub-segment, where each time sub-segment belongs to a life type, including holiday type, workday type and rest day type; The circle division module is used to determine the outer and inner circles of the target city, where both the outer and inner circles include several subway stations, bus stations, and shared bicycle stations; The sharing rate determination module is used to divide the historical time sub-segments under each lifestyle type into days as the maximum time unit and hours as the segmentation unit, and determine the hourly connection sharing rate of each subway station under each lifestyle type; A neural network training module is used to construct a data set based on lifestyle, subway station, hourly connection share, subway station circle, and hourly subway passenger flow at the subway station, and train a to-be-trained neural network model using the data set 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; The path screening module is used to obtain the target's departure time node, starting location and end location, and determine several subway routes based on the starting location and end location; The path determination module is used to predict the first passenger flow carrying capacity of the subway station on the subway riding path at the target departure time node using the passenger flow carrying capacity prediction model, and determine the subway transfer station and the target subway riding path from several subway riding paths based on the prediction results.

[0087] Based on the same inventive concept, the present invention further provides an electronic device, comprising: processor; a memory for storing processor-executable instructions; The processor is configured to execute to implement the transfer planning method based on multiple public transportation modes as provided above.

[0088] Based on the same inventive concept, the present invention also provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by the processor of an electronic device, the electronic device can execute the transfer planning method based on multiple public transportation modes as provided above.

[0089] Since the electronic device described in this embodiment is an electronic device used to implement the information processing method in the embodiment of the present invention, based on the information processing method described in the embodiment of the present invention, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present invention will not be described in detail here. As long as the electronic device used by those skilled in the art to implement the information processing method in the embodiment of the present invention falls within the scope of protection of the present invention.

[0090] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes 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, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1A step that specifies a function in one or more boxes.

[0094] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0095] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A transfer planning method based on multiple public transportation modes, characterized by: include: Divide the historical time period of the target city into several historical time sub-segments, and classify each time sub-segment into a life type, including holiday type, workday type, and rest day type. Identify the outer and inner circles of the target city, where each circle includes several subway stations, bus stops, and shared bike stations; Using days as the maximum time unit and hours as the division unit, the historical time sub-segments under each lifestyle type are divided, and the hourly connection share of each subway station under each lifestyle type is determined; A data set is constructed based on lifestyle, subway station, hourly connection share, subway station's circle, and subway station's hourly subway passenger flow. The trained neural network model is trained with this data set to obtain a passenger flow carrying capacity prediction model. The trained neural network model is used to predict the first passenger flow carrying capacity of the subway station. Obtain the target's departure time node, starting location, and end location, and determine several subway routes based on the starting location and end location; The passenger flow carrying capacity prediction model is used to predict the first passenger flow carrying capacity of the subway station on the subway riding path at the target departure time node, and the subway transfer station and the target subway riding path are determined from several subway riding paths based on the prediction results.

2. The transfer planning method based on multiple public transportation modes according to claim 1, characterized in that: For each subway transfer station, it also includes: Determine the circle where the subway transfer station is located; Determine the connecting area of ​​the subway transfer station based on the circle where the subway transfer station is located; Determine whether the docking area of ​​any adjacent subway station overlaps with the docking area of ​​a subway transfer station; If so, determine the second passenger flow carrying capacity of the subway transfer station at the target departure time node based on the population information and business information of the connecting area of ​​the subway transfer station; If not, then the connecting area of ​​the subway transfer station is re-divided based on the location relationship between the adjacent subway stations and the subway transfer station. The population and business information of the re-divided connecting area of ​​the subway transfer station is used to determine the second passenger flow carrying capacity of the subway transfer station at the target departure time node; According to the second passenger flow carrying capacity and the first passenger flow carrying capacity of the subway transfer station, it is determined whether to change the target subway riding route.

3. The transfer planning method based on multiple public transportation modes according to claim 2, characterized in that: Based on the location relationship between adjacent subway stations and subway transfer stations, the connection area of ​​subway transfer stations is re-divided, including: Determine whether there are commercial or residential areas within the overlapping connection areas; If it does not exist, the overlapping connecting areas are divided equally to obtain the connecting areas of the re-divided subway transfer stations; If so, the regional division ratio is determined based on the travel preferences of commercial entities or residential areas, and the overlapping connecting areas are divided according to the regional division ratio to obtain the connecting areas of the re-divided subway transfer stations.

4. The transfer planning method based on multiple public transportation modes according to claim 2, characterized in that: Determining whether to change the target subway route based on the second passenger flow carrying capacity and the first passenger flow carrying capacity of the subway transfer station includes: If the difference between the sum of the second passenger flow carrying capacity of several subway transfer stations and the sum of the first passenger flow carrying capacity is greater than the first threshold, or the difference between the second passenger flow carrying capacity of any subway transfer station and the first passenger flow carrying capacity is greater than the second threshold, the target subway riding route is changed; otherwise, it is not changed.

5. The transfer planning method based on multiple public transportation modes according to claim 1, characterized in that: Based on the prediction results, the subway transfer station and the target subway route are determined from a number of subway routes, including: Determine the sum of the first passenger flow carrying capacity of each subway route; The subway riding route with the lowest sum of the first passenger flow carrying factors is used as the target subway riding route, and subway transfer stations are determined in the target subway riding route.

6. The transfer planning method based on multiple public transportation modes according to claim 1, characterized in that: Identify the outer and inner circles of the target city, including: The target city is divided according to its urban planning to obtain the outer circle and inner circle of the target city.

7. The transfer planning method based on multiple public transportation modes according to claim 1, characterized in that: Several subway routes are determined based on the starting and ending locations, including: Determine the starting subway station according to the starting position, where the number of the starting subway station is greater than or equal to 1; According to the terminal location, determine the subway station of the terminal, and the number of subway stations of the terminal is greater than or equal to 1; According to the starting subway station and the ending subway station, several subway routes are planned.

8. A transfer planning system based on multiple public transportation modes, characterized by: include: The time division module is used to divide the historical time period of the target city into several historical time sub-segments and classify each time sub-segment, where each time sub-segment belongs to a life type, including holiday type, workday type and rest day type; The circle division module is used to determine the outer and inner circles of the target city, where both the outer and inner circles include several subway stations, bus stations, and shared bicycle stations; The sharing rate determination module is used to divide the historical time sub-segments under each lifestyle type into days as the maximum time unit and hours as the segmentation unit, and determine the hourly connection sharing rate of each subway station under each lifestyle type; A neural network training module is used to construct a data set based on lifestyle, subway station, hourly connection share, subway station circle, and hourly subway passenger flow at the subway station, and train a to-be-trained neural network model using the data set 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; The path screening module is used to obtain the target's departure time node, starting location and end location, and determine several subway routes based on the starting location and end location; The path determination module is used to predict the first passenger flow carrying capacity of the subway station on the subway riding path at the target departure time node using the passenger flow carrying capacity prediction model, and determine the subway transfer station and the target subway riding path from several subway riding paths based on the prediction results.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute to implement the transfer planning method based on multiple public transportation modes as described in any one of claims 1 to 7.

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

Images