A station user travel route recommendation method and device, and a storage medium

Abstract

A station user travel route recommendation method and device, and a storage medium, the station user travel route recommendation method comprising: acquiring user data and determining user habits; determining key areas in the station, determining the crowdedness of the key areas, determining the travel time of the key areas according to a predetermined relationship between crowdedness and travel time; determining a route from a starting point to a destination, dividing the route into route segments by taking the key areas included in the route as division nodes, determining the recommendation value of each route segment, the recommendation value of the route segment being negatively related to the distance from the start to the end of the route segment, the crowdedness tolerance of the user, and the travel time of the key areas included in the route segment, and positively related to the step frequency of the user; determining the recommendation value of the route according to the recommendation value of all route segments included in the same route; and recommending the route to the user according to the recommendation value of the route. The scheme provided in the embodiment can recommend a route that is more in line with user habits, thereby improving user experience.

Description

Technical Field

[0001] This article relates to route recommendation technology, and more particularly to a method, device, and storage medium for recommending user travel routes within a station. Background Technology

[0002] Currently, with the development of tourism, train stations and airports have become important transportation hubs for people transferring between different cities. Simultaneously, with the improvement of the country's economic development level and infrastructure construction, transportation hubs are becoming increasingly large in size, often accompanied by multi-level underground transportation hubs and multiple entrances on the ground. The complex structure poses considerable difficulties for people unfamiliar with the area's layout, and the inability to fully utilize multiple passageways leads to a waste of public resources. With the rapid development of intelligent information technology, people are no longer satisfied with just ground-level travel needs; internal station access has become particularly important, thus necessitating solutions for internal station access. Summary of the Invention

[0003] This application provides a method, apparatus, and storage medium for recommending user routes within a station, thereby improving user experience.

[0004] This application provides a method for recommending user routes within a station, including:

[0005] Acquire user data and determine user habits based on the user data, including the user's crowd tolerance and user cadence information;

[0006] Identify key areas within the station, determine the congestion level of these key areas, and determine the travel time for these key areas based on a pre-determined relationship between congestion level and travel time.

[0007] The route from the origin to the destination is determined. The route is divided into segments by using key areas as dividing nodes. The recommended value of each segment is determined. The recommended value of a segment is negatively correlated with the distance from the beginning to the end of the segment, the user's congestion tolerance, and the travel time in the key areas included in the segment, and positively correlated with the user's step frequency. The recommended value of the route is determined based on the recommended values ​​of all segments included in the same route.

[0008] Recommend routes to users based on their recommendation value.

[0009] In one exemplary embodiment, determining the key area includes: designating areas with a pedestrian flow exceeding a preset threshold within a preset time period as key areas.

[0010] In an exemplary embodiment, determining the congestion level of the key area includes:

[0011] Obtain the area S and the number of people N in the key area, and determine the population density ρ = N / S;

[0012] Determine the congestion level of the key area m = ρ / ρ max , where ρ max The maximum pedestrian density in the key area;

[0013] The relationship between congestion level and travel time is determined as follows: multiple sets of congestion level and travel time are obtained, and the relationship between congestion level and travel time is obtained by fitting using the least squares method.

[0014] In one exemplary embodiment, acquiring user data includes: acquiring stored historical user data, or sending survey information to users and receiving user feedback as user data, wherein the survey information is displayed in an augmented reality or virtual reality manner.

[0015] In one exemplary embodiment, the user data includes:

[0016] The maximum acceptable travel time for users under different levels of congestion;

[0017] The maximum level of congestion that users can tolerate is called the second level of congestion.

[0018] The level of congestion when users may choose other routes is called the first level of congestion, and the first level of congestion is less than or equal to the second level of congestion.

[0019] The step of determining user habits based on the user data includes:

[0020] When users can fully accept the delay caused by congestion, that is, when the first level of congestion is 1, the congestion tolerance is 1.

[0021] When users cannot tolerate the delay caused by congestion at all, that is, when the second level of congestion is 0, the congestion tolerance approaches 0 infinitely.

[0022] When the first congestion level is less than 1, the second congestion level is greater than 0, and the congestion level is between the first and second congestion levels, the congestion tolerance level is 1 if the travel time in the critical area is less than or equal to the maximum acceptable travel time for users; otherwise, the congestion tolerance level is 1. Where T is the travel time in the critical area; Fm is the maximum travel time that users can accept under the congestion level of the critical area.

[0023] In one exemplary embodiment, the user data includes: the user's maximum acceptable cadence and the user's normal cadence;

[0024] The step of determining user habits based on the user data includes: when the user wants to reduce route time, selecting the maximum acceptable step frequency as the user's step frequency; otherwise, selecting the user's normal step frequency as the user's step frequency.

[0025] In an exemplary embodiment, before summing the recommended values ​​of all road segments included in the same route to obtain the recommended value of the route, the method further includes:

[0026] Obtain the latest arrival time expected by the user to reach the destination, and determine the travel time threshold based on the latest arrival time;

[0027] Obtain the estimated travel time for each road segment. When a road segment includes a critical area, the estimated travel time for that road segment is [increased / decreased]. When the road segment does not include critical areas, the estimated travel time of the road segment. Where T is the travel time of the key area included in the road segment, P is the distance from the beginning to the end of the road segment, and δ is the user's step frequency;

[0028] For any given route, the estimated travel time of the route is obtained by adding up the estimated travel times of the segments included in the route.

[0029] The recommended value of a route is obtained by summing the recommended values ​​of all segments included in the same route.

[0030] A target route with an estimated travel time less than or equal to the travel time threshold is identified, and the recommended value of the target route is obtained by summing the recommended values ​​of all segments of the target route.

[0031] In one exemplary embodiment, determining the recommended value for each road segment includes:

[0032] Recommended value of road sections

[0033] Where β is the user's congestion tolerance, T is the travel time of the key areas included in the road segment, P is the distance from the beginning to the end of the road segment, and δ is the user's walking frequency.

[0034] This disclosure provides a device for recommending user routes within a station, including a memory and a processor. The memory stores a program, which, when read and executed by the processor, implements any of the aforementioned methods for recommending user routes within a station.

[0035] This disclosure provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the site user route recommendation method described in any of the above embodiments.

[0036] Compared with related technologies, this application includes a method and apparatus for recommending user routes within a station, as well as a storage medium. The method for recommending user routes within a station includes: acquiring user data; determining user habits based on the user data, the user habits including the user's congestion tolerance and step frequency information; determining key areas within the station; determining the congestion level of the key areas; determining the travel time of the key areas based on a predetermined relationship between congestion level and travel time; determining a route from the starting point to the destination; dividing the route into segments using the key areas included in the route as dividing nodes; determining the recommendation value of each segment, the recommendation value of which is negatively correlated with the distance from the beginning to the end of the segment, the user's congestion tolerance, and the travel time of the key areas included in the segment, and positively correlated with the user's step frequency; determining the recommendation value of the route based on the recommendation values ​​of all segments included in the same route; and recommending routes to users based on the recommendation value of the routes. The solution provided in this embodiment can determine the recommendation value based on user habits, the travel time of key areas, and the distance of segments, and recommend routes based on the recommendation value, which can recommend routes that are more in line with user habits and improve user experience.

[0037] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the application. Other advantages of this application can be realized and obtained by means of the solutions described in the description and the accompanying drawings. Attached Figure Description

[0038] The accompanying drawings are used to provide an understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0039] Figure 1 A flowchart of a method for recommending user routes within a station, as provided in this embodiment of the disclosure;

[0040] Figure 2 Flowchart of a method for recommending user routes within a station, as provided in an exemplary embodiment;

[0041] Figure 3 A crowding habit curve is provided for an exemplary embodiment;

[0042] Figure 4 A schematic diagram of a key area provided for an exemplary embodiment;

[0043] Figure 5 A schematic diagram of a road segment is provided for an exemplary embodiment;

[0044] Figure 6 A route diagram provided for an exemplary embodiment;

[0045] Figure 7 A schematic diagram of a station user route recommendation device provided as an exemplary embodiment. Detailed Implementation

[0046] This application describes several embodiments, but these descriptions are exemplary and not restrictive, and it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with, or may replace, any feature or element of any other embodiment.

[0047] This application includes and contemplates combinations of features and elements known to those skilled in the art. The embodiments, features, and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive scheme as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive schemes to form another unique inventive scheme as defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in this application may be implemented individually or in any suitable combination. Therefore, the embodiments are not limited except by the limitations imposed by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.

[0048] Furthermore, in describing representative embodiments, the specification may have presented methods and / or processes as a specific sequence of steps. However, the method or process should not be limited to the specific order of steps described herein, to the extent that it does not depend on such a specific order. As will be understood by those skilled in the art, other sequences of steps are also possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation of the claims. Moreover, the claims concerning the method and / or process should not be limited to the steps performed in the written order, and those skilled in the art will readily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.

[0049] In one technical solution, a recommended route and estimated travel time are provided to the user based on the system's preset default route. This solution has the following drawbacks:

[0050] 1. The route planning is too simplistic and does not make full use of the advantages of each node in the route for arrangement and combination.

[0051] 2. The system fails to fully utilize its internal resources and guide user flow through routes.

[0052] 3. Poor user experience.

[0053] This disclosure proposes a method for recommending user routes within a station, which can provide more reasonable route options for users in large station areas containing multi-level underground transportation hubs and multiple entrances and exits. When calculating routes, it fully considers user habits, travel time in various key areas, and distance between key areas and users, and recommends routes to users by calculating the recommendation value of the routes. Alternatively, it can display the differences between various routes for users to choose from.

[0054] Figure 1 This is a flowchart illustrating a method for recommending user routes within a station, as provided in an embodiment of this disclosure. Figure 1 As shown, the method for recommending user routes within the station provided in this embodiment includes:

[0055] Step 101: Obtain user data and determine user habits based on the user data. The user habits include the user's crowd tolerance and user cadence information. The crowd tolerance is the user's degree of acceptance of crowding.

[0056] Step 102: Identify key areas within the station, determine the congestion level of the key areas, and determine the passage time for the key areas based on the predetermined relationship between congestion level and passage time.

[0057] Step 103: Determine the route from the starting point to the destination. Divide the route into segments by using key areas as dividing nodes. Determine the recommended value of each segment. The recommended value of a segment is negatively correlated with the distance from the beginning to the end of the segment, the user's congestion tolerance, and the travel time in the key areas included in the segment, and positively correlated with the user's step frequency. Determine the recommended value of the route based on the recommended values ​​of all segments included in the same route. Summate the recommended values ​​of all segments included in the same route to obtain the recommended value of the route.

[0058] Step 104: Recommend routes to users based on their recommendation value.

[0059] The solution provided in this embodiment can determine the recommendation value based on user habits, travel time in key areas, and distance of road segments. Based on the recommendation value, route recommendations can be made to recommend routes that are more in line with user habits, thereby improving the user experience.

[0060] In one exemplary embodiment, determining the key area includes: designating areas with pedestrian traffic exceeding a preset threshold within a preset time period as key areas. This can be achieved by statistically analyzing pedestrian traffic within the station and determining the key areas based on the statistical results. However, this embodiment is not limited to this; certain areas within the station can be directly designated as key areas, such as areas frequently observed to be congested. Key areas can also be areas with surveillance cameras, allowing for real-time acquisition of personnel numbers and pedestrian traffic data through monitoring information.

[0061] A large number of cameras are typically deployed within the station to capture images of specific areas. Each camera has a limited capture range, commonly referred to as the visible field of view. Each visible field experiences varying pedestrian traffic at different times of the day, with a daily pedestrian traffic volume of L. The maximum number of people passing through each visible field per second is calculated and used as the maximum limit for pedestrian traffic flow within that visible field. That is, it is used as a preset threshold.

[0062] A visible area is designated as a critical area only when the daily pedestrian flow exceeds the maximum limit; that is, the area experiences peak pedestrian flow and congestion at a specific time of day. In other words, the maximum daily pedestrian flow L of the visible area is defined as... max A visible area can be designated as a critical area if the following conditions are met: Key areas could be, for example, turnstile areas that are usually congested.

[0063] In an exemplary embodiment, determining the recommended value of a route based on the recommended values ​​of all road segments included in the same route includes:

[0064] The recommended value of a route is obtained by summing the recommended values ​​of all road segments included in the same route. However, this embodiment of the present disclosure is not limited to this; the recommended values ​​of the road segments can be weighted and then summed to obtain the recommended value of the route.

[0065] In an exemplary embodiment, determining the congestion level of the key area includes:

[0066] Obtain the area S and the number of people N of the key area, and determine the population density ρ = N / S of the key area; wherein, the area S of the key area can be pre-configured, and the number of people N can be determined based on the monitoring images of the key area; N is [0, N...]. max ];

[0067] Determine the congestion level of the key area m = ρ / ρ max , where ρ maxThe maximum pedestrian density in the key area is defined as m. In this embodiment, the pedestrian density is normalized to obtain the congestion level. It can be seen that the congestion level m ranges from [0,1].

[0068] In an exemplary embodiment, ρ max This can be determined through pre-testing. When there are no people in the critical area, the number of people in the critical area is 0, and the area of ​​the critical area is S. At this time, the population density ρ in the critical area is 0. When the number of people in the critical area reaches saturation (this can be determined by referring to the design parameters of the relevant building, which can be used as the maximum number of people that the critical area can accommodate during the design phase, or by determining the saturation number based on operational needs), that is, when all areas in the critical area are occupied by people, the number of people in the critical area is N. max The maximum population density in the key area can be obtained as ρ. max That is, the maximum population density can be obtained directly by dividing the maximum number of people in the key area by the area S of the key area during the building design.

[0069] In another exemplary embodiment, the maximum crowd density ρ max It can be set to a fixed value, and the maximum crowd density can be set according to relevant fire safety requirements. It can monitor the crowd density and limit the flow when the preset maximum crowd density is reached, thereby preventing the crowd density from exceeding the maximum crowd density.

[0070] In an exemplary embodiment, the maximum crowd density ρ max For example, it can be set to 0.3 people / m 2 Up to 1 person / m 2 .

[0071] The relationship between congestion level and travel time is determined as follows: Multiple sets of congestion levels and travel times are obtained, and the relationship is fitted using the least squares method. Assume the time it takes for a user to pass through the area is t. Multiple sets of data (m1, t1), (m2, t2), (m3, t3)... for the key area can be used to fit these data sets, and the travel time T for the key area can be calculated based on the fitted polynomial. For example, the least squares method can be used for polynomial fitting.

[0072] In one exemplary embodiment, acquiring user data includes: acquiring stored historical user data, or sending survey information to users and receiving user feedback as user data, wherein the survey information is displayed in an augmented reality or virtual reality manner.

[0073] In one exemplary embodiment, the user data includes:

[0074] The maximum acceptable travel time for users under different levels of congestion;

[0075] The maximum level of congestion that users can tolerate is called the second level of congestion.

[0076] The level of congestion when users may choose other routes is called the first level of congestion, and the first level of congestion is less than or equal to the second level of congestion.

[0077] The step of determining user habits based on the user data includes:

[0078] When users can fully accept the delay caused by congestion, that is, when the first level of congestion is 1, the congestion tolerance is 1.

[0079] When users cannot tolerate the delay caused by congestion at all, that is, when the second level of congestion is 0, the congestion tolerance approaches 0 infinitely.

[0080] When the first congestion level is less than 1, the second congestion level is greater than 0, and the congestion level is between the first and second congestion levels, the congestion tolerance level is 1 if the travel time in the critical area is less than or equal to the maximum acceptable travel time for users; otherwise, the congestion tolerance level is 1. Where T is the current travel time in the critical area; Fm is the maximum travel time that users can accept under the congestion level of the critical area.

[0081] The above method for calculating crowd tolerance is just an example. Crowd tolerance can be generated in other ways as needed, as long as it reflects the user's acceptance of crowding.

[0082] In one exemplary embodiment, the user data may include: the user's maximum acceptable cadence, and the user's normal cadence;

[0083] The step of determining user habits based on the user data includes: when the user wants to reduce route time, selecting the maximum acceptable step frequency as the user's step frequency; otherwise, selecting the user's normal step frequency as the user's step frequency.

[0084] In an exemplary embodiment, before summing the recommended values ​​of all road segments included in the same route to obtain the recommended value of the route, the method further includes:

[0085] Obtain the latest arrival time expected by the user to reach the destination, and determine the travel time threshold based on the latest arrival time;

[0086] Obtain the estimated travel time for each road segment. When a road segment includes a critical area, the estimated travel time for that road segment is [increased / decreased]. When the road segment does not include critical areas, the estimated travel time of the road segment. Where T is the travel time of the key area included in the road segment, P is the distance from the beginning to the end of the road segment, and δ is the user's step frequency;

[0087] For any given route, the estimated travel time of the route is obtained by adding up the estimated travel times of the segments included in the route.

[0088] The recommended value of a route is obtained by summing the recommended values ​​of all segments included in the same route.

[0089] A target route with an estimated travel time less than or equal to the travel time threshold is identified, and the recommended value of the target route is obtained by summing the recommended values ​​of all segments of the target route.

[0090] In this embodiment, the target route may include multiple routes. This embodiment also calculates the estimated travel time of the routes, excluding routes whose estimated travel time exceeds a travel time threshold. The recommended value of the excluded routes is not calculated, and the excluded routes are not recommended. This improves the user experience, eliminating the need for users to manually exclude routes and reducing the number of routes requiring recommended value calculation. However, this embodiment is not limited to this; routes whose estimated travel time exceeds the travel time threshold may not be excluded, and the recommended value of all routes may be calculated.

[0091] In one exemplary embodiment, determining the recommended value for each road segment may include:

[0092] Recommended value of road sections

[0093] Where β represents the user's congestion tolerance, T represents the travel time to the key areas included in the road segment, P represents the distance from the beginning to the end of the road segment, and δ represents the user's step frequency. The method for calculating the recommendation value provided in this embodiment is only an example. The recommendation value can be calculated in other ways, such that the recommendation value of the road segment is negatively correlated with the distance from the beginning to the end of the road segment, the user's congestion tolerance, and the travel time to the key areas included in the road segment, and positively correlated with the user's step frequency.

[0094] In the above embodiments, user habits from two dimensions are collected to calculate the recommendation value. In another exemplary embodiment, more user habits can be introduced to calculate the recommendation value, such as three-dimensional, four-dimensional, or even higher-dimensional vectors to calculate the route recommendation value. Let the user habits of each dimension be V1, V2, V3, ..., then the recommendation value of the route segment is:

[0095]

[0096] In one exemplary embodiment, recommending routes to the user based on their recommendation value includes: recommending the route with the highest recommendation value to the user; or, recommending a group of routes to the user, where the recommendation value of each route in the group is greater than or equal to the recommendation value of any unrecommended route. For example, recommending the top three routes by recommendation value is just an example; more or fewer routes can be recommended as needed. For instance, recommendations can be based on the number of routes set by the user; if the user sets two routes to be recommended, then the two routes with the highest recommendation value will be displayed. Alternatively, all routes and their recommendation values ​​can be displayed for the user to choose from. The recommended routes can also display the advantages and disadvantages of each route for the user to select from.

[0097] The technical solution of the present disclosure embodiment will be further illustrated by an example below.

[0098] In this embodiment of the disclosure, the route is atomized, that is, the entire route is divided into multiple segments, with key areas as dividing nodes. By evaluating the distance to the key area, the estimated travel time to the key area, and taking into account user habits, namely preferences and walking frequency, the travel route is optimized to make the route more reasonable.

[0099] like Figure 2 As shown, this embodiment provides a method for recommending user routes within a station, including:

[0100] Step 201: Determine if there is user data. If there is, proceed to step 203; otherwise, proceed to step 202.

[0101] Step 202: Distribute survey information, receive user feedback information to generate user data, and proceed to step 204;

[0102] Step 203: Reuse existing user data;

[0103] Step 204: Generate user habits based on user data;

[0104] Step 205: Determine the passage time for key areas;

[0105] Step 206: Determine the distance of the road segment;

[0106] Step 207: Calculate the recommended value of the route;

[0107] Step 208: Compare the recommendation value of each route and recommend a route to the user;

[0108] Step 209: Determine the route actually selected by the user;

[0109] The route can be obtained through user input or by detecting the user's trajectory.

[0110] Step 210: Collect user data based on the actual route selected by the user, then end.

[0111] For example, it records the congestion level of the route actually selected by the user and updates the maximum congestion level that the user can accept; it also records the user's step frequency information.

[0112] In step 204, the user habit focus is on the user's preference for route selection and the user's walking frequency in the station under no congestion conditions, which can collect the user's congestion tolerance and the user's normal walking frequency range.

[0113] From the perspective of congestion tolerance, the higher the user's tolerance for congestion, the smaller the impact of the extended travel time caused by congestion on the user. Let the user's tolerance for congestion be β.

[0114] The following surveys can be conducted with users:

[0115] 1. Investigate crowding tolerance

[0116] 1) Ask the user for the longest travel time F under different levels of congestion in the key area that they can tolerate.

[0117] Animation can be incorporated when asking users questions. Virtual Reality (VR) or Augmented Reality (AR) videos can be used to provide users with various simulated scenarios, allowing them to experience and respond to the corresponding levels of congestion. For example, users can be offered multiple choices (e.g., three) regarding the maximum acceptable travel time in a fixed-area area with congestion levels of 30%, 50%, and 80%. This can be used as the primary factor in assessing a user's tolerance for congestion. This factor can be used to create a curve with congestion level on the horizontal axis and maximum travel time F on the vertical axis, as shown below. Figure 3 The curve L1 shown.

[0118] 2) Ask the user the maximum level of congestion they can accept, which is called the second level of congestion M2.

[0119] We present users with various user models to determine their maximum acceptable level of congestion. For example, when the congestion in a certain area reaches a certain threshold, the user will find it completely intolerable. These factors are considered as secondary factors in route recommendations. This results in a straight line L2 with the user's maximum acceptable level of congestion on the horizontal axis, where the horizontal axis value is M2.

[0120] 3) For the preference of users in more distant areas with low congestion, determine the user's preference for choosing other routes when the congestion level reaches a certain level M1.

[0121] Multiple simulated route options are presented to users for them to choose from, in order to obtain user preference values ​​in advance, serving as a third factor in assessing users' tolerance for congestion. This factor allows us to determine users' preferences for choosing other routes when congestion reaches a certain level; that is, the horizontal axis represents the level of congestion when users intentionally choose other routes, represented by the straight line L3, with the horizontal axis value being the first level of congestion, M1.

[0122] The user's congestion level habit curve is established from three aspects. Figure 3 It can be seen that the curve segment L1 located between the straight lines L2 and L3 is the curve representing the user's habitual level of congestion.

[0123] When users can fully accept the delay caused by congestion, the level of acceptance of congestion reaches its maximum at β = 1.

[0124] When users can no longer accept the delay caused by congestion, their tolerance for congestion reaches a minimum of β, which approaches 0 infinitely.

[0125] When the congestion level is between (M1, M2), and the current actual travel time T in the critical area is less than or equal to the maximum acceptable travel time Fm for the user under the current congestion level, β is 1; when the actual travel time T is greater than the maximum acceptable travel time Fm for the user under the current congestion level, the value of β is as follows:

[0126]

[0127] Therefore, the range of β is (0,1).

[0128] II. Survey users' step frequency

[0129] From the perspective of cadence range, users' cadence will vary due to factors such as age and occupation. For example, the cadence of the elderly is slightly slower than that of the younger generation, meaning that long distances have a greater impact on their choices. Here, we set the user's cadence as δ, where δ>0.

[0130] 1) Ask the user the maximum acceptable cadence δ1 to assess the user's maximum walking speed;

[0131] 2) Ask the user about their cadence δ2 under normal circumstances; or, combine big data analysis, such as for office workers, analyze the average cadence of this type of user as the cadence δ2 under normal circumstances, based on the local city and working hours; or, determine the user's normal cadence δ2 by recording the user's cadence information.

[0132] 3) For areas that are far away but have low congestion, the selection bias is δ3. This is used to assess whether an area will no longer be recommended to the user when the distance exceeds a certain threshold.

[0133] The user's cadence is analyzed from three aspects to generate the user's cadence information δ, which represents the user's acceptance level in long-distance key areas. Generally, δ = δ².

[0134] When a user's cadence is slow, such as when the user is in a wheelchair or is elderly, the distance from the key area to the user has a greater impact on their cadence. When a user's cadence is fast, such as when the user is an office worker or a young person, the distance from the key area to the user has a smaller impact on their cadence.

[0135] When users have high time requirements during use, that is, users want to compress route time as much as possible, the user's maximum step frequency δ1 will be used as the user's step frequency to calculate the route, that is, δ = δ1.

[0136] In one exemplary embodiment, when querying usage patterns, the latest arrival time expected by the user to reach their destination (which could be the departure time of public transportation) is collected.

[0137] In step 206, the distance of the road segment is determined. Taking a route that includes only one road segment as an example, the road segment distance is the actual distance between the key area and the user's starting point.

[0138] by Figure 4 For example, by Figure 4 As you can see, Figure 4 The user is located at the corner of the entrance to the station. The underground station building includes four key areas: key area 1, key area 2, key area 3, and key area 4.

[0139] Depend on Figure 5 As can be seen, based on the pre-drawn road network distribution within the station, the actual distance between the user's current location and each key area can be obtained (this could be the distance to the midpoint of the key area, but this embodiment is not limited to this; it could be the distance to the start or end point of the key area, or the distance between points between the start and end points). Based on the road network drawing, the distance P from the user's current location (starting point) to the key area is determined, which is the distance from the beginning to the end of the road segment.

[0140] Based on user habits, it can be seen that user habits are quite important in users' route selection. Therefore, when recommending routes to users, user habits should be taken into account when calculating route recommendations.

[0141] Before calculating the recommended value of a route, the estimated travel time for each road segment is calculated based on the collected information.

[0142] The estimated travel time of the route is determined based on the estimated travel time of each segment of the route.

[0143] For any route, before calculating the recommended value of the route, it is determined whether the current time plus the estimated travel time of the route is earlier than the latest arrival time. If it is earlier, the recommended value of the route is calculated; otherwise, the recommended value of the route is not calculated.

[0144] Given that the estimated time for a user to traverse a critical area is T, the distance from the user's location to the critical area is P (i.e., the distance of the road segment), the user's tolerance for congestion is β, and the user's normal walking frequency is δ.

[0145] Then, the actual impact of the travel time in the critical area on the user is T / β, and the actual impact of the distance from the user's location to the critical area on the user is P / δ.

[0146] The greater the actual impact of travel time and distance to key areas on users, the lower the recommendation value of that road segment.

[0147] Figure 6 A route diagram provided for an exemplary embodiment. (e.g.) Figure 6 As shown, the route from the starting point (origin) to the destination includes multiple routes. For example, a route might be: Starting Point → A1 → A1-1 → A1-1-1 → Destination. This route can be divided into several segments: Segment 1: Starting Point → A1, Segment 2: A1 → A1-1, Segment 3: A1-1 → A1-1-1, Segment 4: A1-1-1 → Destination. Segment 1 includes the key area A1, Segment 2 includes the key area A1-1 but excludes the key area A1 (assuming the user has already passed through key area A1), Segment 3 includes the key area A1-1-1 but excludes the key area A1-1, and Segment 4 has no key area. The recommendation value of each segment is calculated separately. The recommendation values ​​of all segments on the same route are added together to determine the total recommendation value of the route. The route with the highest recommendation value is then recommended to the user. For example, if the route Starting Point → B1 → B1-3 → B1-3-2 → Destination has the highest recommendation value, that route is recommended to the user.

[0148] In an exemplary embodiment, when there are multiple layers within the station, the user can be selected from the road segments with the highest recommended value in each layer. After selecting the optimal road segments in each layer, the overall optimal route is recommended to the user.

[0149] In an exemplary embodiment, when a user uses the system for the first time, the system evaluates the user's habits according to survey questions, and then recommends a suitable route for the user. However, during the user's use, the user's environment or usage habits may change dynamically. Therefore, when the user uses the recommended solution, the system will collect the user's data, such as the three-dimensional data collected in the survey questions in the foregoing embodiments (taking crowd tolerance as an example, the maximum passing time acceptable to the user under different crowd levels, the first crowd level and the second crowd level can be re-collected), to recalculate and generate new user habits.

[0150] Suppose the user's existing crowd tolerance is β, and the user's crowd tolerance recalculated according to the collected real data is β 新 , a crowd tolerance threshold is set as c. When |β-β 新 |≥c, user data is re-collected to generate user habits; that is, when |β-β 新 |<c, the existing user habits continue to be used.

[0151] Similarly, suppose the user's original conventional cadence parameter is δ, and the cadence parameter recalculated according to the collected real data is δ 新 , a cadence parameter threshold is set as d. Only when the difference between the data calculated from the actual data and the original data meets the threshold, the new data will be selected to recalculate user habits. That is, when |δ-δ 新 |≥d, new user data is collected to regenerate user habits; when |δ-δ 新 |<d, the original user habits are used.

[0152] The solution provided in this embodiment is sufficiently detailed in route selection, and fully considers the advantages and disadvantages of each node; it fully combines user habits, introduces user habits as a variable into the calculation of the route recommendation solution, can recommend routes that better meet user needs, and improves user experience; in addition, routes are recommended based on the recommendation value of the route, rather than simply based on time, which has richer dimensions and can better reflect user needs.

[0153] As Figure 7 shown, an embodiment of the present disclosure provides an in-station user passage route recommendation apparatus 70, comprising a memory 710 and a processor 720, wherein the memory 710 stores a program, and when the program is read and executed by the processor 720, the in-station user passage route recommendation method according to any of the foregoing embodiments is implemented.

[0154] An embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the in-station user passage route recommendation method according to any of the foregoing embodiments.

[0155] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

Claims

1. A method for recommending user routes within a station, characterized in that, include: Acquire user data and determine user habits based on the user data, including the user's crowd tolerance and user cadence information; Identify key areas within the station, determine the congestion level of these key areas, and determine the travel time for these key areas based on a pre-determined relationship between congestion level and travel time. The route from the origin to the destination is determined. The route is divided into segments by using key areas as dividing nodes. The recommended value of each segment is determined. The recommended value of a segment is negatively correlated with the distance from the beginning to the end of the segment and the travel time in the key areas included in the segment, and positively correlated with the user's congestion tolerance and the user's step frequency. The recommended value of the route is determined based on the recommended values ​​of all segments included in the same route. Recommend routes to users based on their recommendation value; The user data includes: The maximum acceptable travel time for users under different levels of congestion; The maximum level of congestion that users can tolerate is called the second level of congestion. The level of congestion when users may choose other routes is called the first level of congestion, and the first level of congestion is less than or equal to the second level of congestion. The step of determining user habits based on the user data includes: When users can fully accept the delay caused by congestion, that is, when the first level of congestion is 1, the congestion tolerance is 1. When users cannot tolerate the delay caused by congestion at all, that is, when the second level of congestion is 0, the congestion tolerance approaches 0 infinitely. When the first congestion level is less than 1, the second congestion level is greater than 0, and the congestion level is between the first and second congestion levels, the congestion tolerance level is 1 if the travel time in the critical area is less than or equal to the maximum acceptable travel time for users; otherwise, the congestion tolerance level is 1. Where T is the travel time for the critical area; This represents the maximum acceptable travel time for users under congestion levels in key areas.

2. The method for recommending user routes within a station according to claim 1, characterized in that, The determination of key areas includes: designating areas with a pedestrian flow exceeding a preset threshold within a preset time period as key areas.

3. The method for recommending user routes within a station according to claim 1, characterized in that, Determining the congestion level of the key area includes: Obtain the area S and the number of people N in the key area to determine the crowd density. =N / S; Determine the level of congestion in the key areas. ,in, The maximum pedestrian density in the key area; The relationship between congestion level and travel time is determined as follows: multiple sets of congestion level and travel time are obtained, and the relationship between congestion level and travel time is obtained by fitting using the least squares method.

4. The method for recommending user routes within a station according to claim 1, characterized in that, The acquisition of user data includes: acquiring stored historical user data, or sending survey information to users and receiving user feedback as user data, and the survey information is displayed in the form of augmented reality or virtual reality.

5. The method for recommending user routes within a station according to claim 1, characterized in that, The user data also includes: the user's maximum acceptable step frequency, and the user's normal step frequency; The step of determining user habits based on the user data further includes: when the user wants to reduce route time, selecting the maximum acceptable step frequency as the user's step frequency; otherwise, selecting the user's normal step frequency as the user's step frequency.

6. The method for recommending user routes within a station according to claim 1, characterized in that, Before summing the recommended values ​​of all segments included in the same route to obtain the recommended value of the route, the following steps are also included: Obtain the latest arrival time expected by the user to reach the destination, and determine the travel time threshold based on the latest arrival time; Obtain the estimated travel time for each road segment. When a road segment includes a critical area, the estimated travel time for that road segment is [increased / decreased]. When the road segment does not include critical areas, the estimated travel time of the road segment is... Where T is the travel time to the key areas included in the road segment, and P is the distance from the beginning to the end of the road segment. For the user's step frequency; For any given route, the estimated travel time of the route is obtained by adding up the estimated travel times of the segments included in the route. The recommended value of a route is obtained by summing the recommended values ​​of all segments included in the same route. A target route with an estimated travel time less than or equal to the travel time threshold is identified, and the recommended value of the target route is obtained by summing the recommended values ​​of all segments of the target route.

7. The method for recommending user routes within a station according to claim 1, characterized in that, The determination of the recommended value for each road segment includes: Recommended value of road sections in, For users' congestion tolerance, T is the travel time to the key areas included in the road segment, and P is the distance from the beginning to the end of the road segment. This refers to the user's step frequency.

8. A device for recommending user routes within a station, characterized in that, It includes a memory and a processor, wherein the memory stores a program that, when read and executed by the processor, implements the in-station user route recommendation method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the in-station user route recommendation method as described in any one of claims 1 to 7.

Images