Passenger flow information acquisition system and method based on multiple scenes

Abstract

The invention relates to the technical field of passenger flow information acquisition, and discloses a passenger flow information acquisition system and method based on multiple scenes, and the method comprises the steps of data acquisition, user classification, real-time analysis, regional analysis and information display.In the aspect of crowd flow analysis, mobile signaling data are accurately acquired, and timestamps and base station information are combined, so that the crowd flow analysis efficiency is improved; high-temporal-spatial-resolution analysis is realized, a crowd real-time flow diagram can be accurately generated, and urban traffic planning, large-scale activity security and the like are assisted; and in area evaluation, key inflow and normal flow areas are determined, a key area map is generated, and a basis is provided for commercial layout and public facility construction. User classification is accurate, and tourism management and local public service optimization are facilitated. An analysis result is visually presented through visual display, scientific decision making is assisted, and the method is suitable for multiple fields such as urban emergency management; a real-time updating mechanism ensures the timeliness of data, and improves the flexibility of city management and the capability of dealing with emergencies.

Description

Technical Field

[0001] The present invention relates to the technical field of passenger flow information collection, and in particular to a passenger flow information collection system and method based on multiple scenarios. Background Art

[0002] In modern society, with the development of cities and the growth of population, passenger flow information collection and analysis have become increasingly important for urban planning, traffic management, commercial operations and other fields. Traditional passenger flow information collection methods, such as questionnaires, manual counting and video surveillance, have many limitations. Questionnaires rely on subjective answers, and accuracy and completeness are difficult to guarantee. They are time-consuming and slow to update data. Manual counting can only cover limited areas and time periods, with high labor costs and large errors. Although video surveillance can be observed intuitively, it has high deployment costs and complex data processing. Its application in privacy-sensitive areas is limited. In addition, these traditional methods are difficult to conduct comprehensive and detailed spatial analysis of large areas, and cannot meet the needs of urban-level crowd flow research for spatial refinement analysis. At the same time, in the face of large-scale data, traditional methods are inefficient in processing and difficult to conduct long-term and continuous collection and analysis. However, urban development management urgently needs to grasp the long-term trends and laws of crowd flow.

[0003] In this context, mobile signaling data came into being. Mobile signaling is a control signal automatically transmitted between mobile phones and base stations. It contains rich information such as timestamp, mobile phone number, base station unique identifier, and base station latitude and longitude. It can reflect user location and behavior changes in real time. With the popularization of mobile communication users, its data volume is huge, and it can continuously record user movement trajectories, showing great application potential in the field of passenger flow information collection technology. Summary of the invention

[0004] The purpose of the present invention is to provide a passenger flow information collection system and method based on multiple scenarios, which solves the technical problems raised in the background technology.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] The passenger flow information collection method based on multiple scenarios includes the following steps:

[0007] Step 1: Data acquisition:

[0008] Obtain the geographic spatial information of the target collection area, and at the same time obtain the mobile signaling data in multiple time periods within the specified period at a specified time interval; wherein the mobile signaling data includes timestamp, mobile phone number, base station unique identifier and base station latitude and longitude;

[0009] Step 2: Real-time analysis:

[0010] The target collection area is divided into grids in geographical space according to preset rules, and at the same time, a real-time flow map of the crowd is determined by the longitude and latitude of the base stations in the mobile signaling data;

[0011] It also conducts analysis of individual user travel cycles and group travel pattern periodicity based on the geospatial information of the target collection area and the user's mobile signaling data;

[0012] Step 3: Regional Analysis:

[0013] In each grid, the difference in the number of users in each adjacent analysis period is combined to generate a real-time crowd flow map;

[0014] Step 4: Information display:

[0015] The analysis results corresponding to the real-time analysis in step 2 and the regional analysis in step 3 are displayed in a visual manner.

[0016] As a further solution of the present invention, the grid division method is to divide the target acquisition area into multiple target-sized grids through GPS coordinate grids;

[0017] At the same time, each grid is assigned a unique identifier;

[0018] The identifier of the grid is represented by [i, j], and i=1...n, j=1...m, and n and m represent the vertical and horizontal numbers of the grids respectively.

[0019] As a further solution of the present invention, the crowd flow map is determined as follows:

[0020] Step 1.1, determine the grid to which the data location belongs:

[0021] Determine the grid to which the location information of each mobile signaling data belongs by using the latitude and longitude of the base station in the mobile signaling data;

[0022] Step 1.2, mark the analysis period:

[0023] According to the time trend, multiple time periods in the specified period are marked in sequence as analysis period 1, analysis period 2, ..., analysis period e;

[0024] Then, the analysis period to which the location information of each mobile signaling data belongs is determined through the timestamp in the mobile signaling data;

[0025] Step 1.3, count the number of users in each grid at each time period:

[0026] Count the number of users in each grid corresponding to each analysis period and mark it as S k，i，j; Wherein, k represents the number of analysis time periods, k = 1, 2, ... e, and e represents the number of time periods;

[0027] Step 1.4, extract the number of grid users in adjacent time periods:

[0028] In two adjacent analysis periods k and k+1, extract the number of users S of each grid k，i，j and S k+1，i，j ;

[0029] Then through Calculate the difference in the number of users between the two adjacent analysis periods

[0030] Step 1.5, determine the direction of crowd flow:

[0031] According to the difference between the two adjacent analysis time periods, the crowd flow direction between the two adjacent analysis time periods is determined;

[0032] like If it is greater than 0, it means that the number of users in the corresponding grid [i, j] increases, that is, people flow into the corresponding grid [i, j];

[0033] like If it is less than 0, it means that the number of users in the corresponding grid [i, j] decreases, that is, people flow out of the corresponding grid [i, j];

[0034] like If it is equal to 0, it means that the number of users in the corresponding grid [i, j] has not changed, that is, there is no crowd flow in the corresponding grid [i, j];

[0035] Step 1.6, Generate real-time crowd flow map:

[0036] According to the crowd flow direction in the two adjacent analysis periods and combined with geographic space information, a real-time crowd flow map is generated.

[0037] As a further solution of the present invention, when the generation time of the real-time crowd flow map exceeds the corresponding preset time interval, the number of users corresponding to an analysis period adjacent to the subsequent analysis period in the adjacent analysis period in Step 1.5 is obtained, and then a new real-time crowd flow map is generated and the original real-time crowd flow map is updated in accordance with the method from Step 1.4 to Step 1.5.

[0038] As a further solution of the present invention, the method of regional analysis is as follows:

[0039] A grid is selected, and the difference in the number of users in multiple adjacent analysis periods within a specified period is obtained in the grid, and then the average value is calculated, and the average value is marked as the regional evaluation value;

[0040] Then the regional evaluation value is compared with the preset regional evaluation threshold, and the regional mark of the grid is determined based on the comparison result:

[0041] Area markings include: key inflow areas and normal flow areas;

[0042] If the regional evaluation value is greater than the regional evaluation threshold, it means that the inflow of people in the grid is large, and the grid is marked as a key inflow area. Otherwise, the grid is marked as a normal flow area.

[0043] And so on, determine the area mark corresponding to each grid;

[0044] Then the key inflow areas and normal flow areas are combined with geospatial information to generate a key area map;

[0045] As a further solution of the present invention, in the key area map, the key inflow area is marked by a red block at the corresponding grid.

[0046] As a further solution of the present invention, the steps are also included: User classification:

[0047] According to the mobile phone numbers in all mobile signaling data, the users in the target collection area are classified and processed, and the users in the target collection area are divided into two clusters according to the classification results;

[0048] The two clusters are respectively corresponding to local users and foreign users.

[0049] As a further solution of the present invention: the analysis and processing method is also included as follows:

[0050] According to the mobile phone numbers in all mobile signaling data in each area, the location of each mobile phone number is counted;

[0051] Users in the target collection area are divided into local users and non-local users according to the location of their mobile phone numbers;

[0052] The specific distinction is as follows:

[0053] First, extract and pre-establish a mobile phone number location database;

[0054] Among them, the database contains the mapping relationship between each mobile phone number segment and the corresponding location;

[0055] Then, for each mobile phone number, its location is determined by querying the database;

[0056] If the location is consistent with the location of the target collection area, the user is marked as a local user; otherwise, it is marked as a foreign user.

[0057] As a further solution of the present invention: by extracting all non-local users and combining the real-time analysis of step 2 and the regional analysis of step 3, a real-time flow map of the crowd and a key area map for non-local users are obtained respectively;

[0058] At the same time, by extracting all local users and combining the real-time analysis in step two and the regional analysis in step three, a real-time flow map of the population and a map of key areas for local users are obtained respectively.

[0059] As a further solution of the present invention: the method for analyzing the individual travel cycle of a user is as follows:

[0060] Step K1.1. For each user, determine the date and time of their first appearance and the date and time of their last appearance based on their activity records in the target collection area, and mark them as T respectively. start and T end ;

[0061] Step K1.2, through: T total =T end -T start ;

[0062] Calculate the total activity time T of the user in the collection area total ;

[0063] Step K1.3: During the observation period, count the number of times a user appears in different periods and multiple different time intervals in different periods, and mark it as W. gt ;

[0064] Among them, g = 1, 2, ... u, t = 1, 2, ... v, u represents the number of different periods in the observation period, and v represents the number of multiple different time intervals in different periods;

[0065] Moreover, different periods are divided within the observation period, and different time intervals are divided within different periods;

[0066] Step K1.4, through:

[0067] Calculate the user's appearance frequency FL in each time period gt :

[0068] As a further solution of the present invention: the periodic analysis method of group travel rules is as follows:

[0069] Step K2.1, aggregate and average the appearance frequencies of all users in different periods and multiple different time intervals within different periods to obtain the travel frequency distribution of the group in different weeks and time periods;

[0070] The method is:

[0071] The frequency of each user in the group in different periods and multiple different time intervals in different periods is marked as FL gth ;

[0072] Where h = 1, 2, ..., e, e represents the number of all users in the group;

[0073] Then through:

[0074] The average frequency of occurrence of FLP in a population at different times and in multiple time intervals within different times gt ;

[0075] Step K2.1. Determine the peak and trough time periods based on the travel frequency distribution of the group;

[0076] The method is:

[0077] The average frequency FLP of the group in different periods and multiple different time intervals in different periods gt Compare with the preset frequency thresholds FLPy1 and FLPy2:

[0078] Among them, FLPy1<FLPy2;

[0079] When FLP gt >FLPy2, the corresponding time period is regarded as the travel peak time period;

[0080] When FLP gt When <FLPy1, it is regarded as the travel low period;

[0081] When FLPy2 ≥ FLP gt When ≥FLPy1, it is regarded as the normal travel time period.

[0082] A passenger flow information collection system based on multiple scenarios, the system is implemented by a passenger flow information collection method based on multiple scenarios, and the system includes:

[0083] A data acquisition unit, which acquires geographic spatial information of a target acquisition area and simultaneously acquires mobile signaling data within multiple time periods within a specified period at specified time intervals;

[0084] A real-time analysis unit is used to divide the target collection area into grids in geographic space according to preset rules, and determine the real-time flow map of the crowd through the longitude and latitude of the base station in the mobile signaling data; and to perform individual user travel cycle analysis and group travel regularity periodicity analysis based on the geographic space information of the target collection area and the mobile signaling data of the user;

[0085] The regional analysis unit is used to generate a real-time crowd flow diagram in each grid by combining the difference of the number of users in each adjacent analysis period;

[0086] Information display is used to display the analysis results corresponding to the real-time analysis unit and the regional analysis unit in a visual manner.

[0087] Beneficial effects of the present invention:

[0088] Comprehensive use of multi-source data: By acquiring the geographic spatial information of the target collection area and the mobile signaling data of multiple time periods within a specified period, it is possible to fully grasp various basic data related to passenger flow, providing rich data support for subsequent in-depth and multi-dimensional analysis, and avoiding the problem of one-sided analysis results due to missing data.

[0089] Multi-dimensional analysis perspective: not only real-time analysis is carried out, including determining the real-time flow map of the crowd based on the geographic space division grid, but also individual user travel cycle analysis and group travel pattern periodic analysis are carried out. From the individual and group levels, as well as the real-time spatial flow perspective, the characteristics and patterns of passenger flow are fully understood, making the grasp of passenger flow information more in-depth and detailed.

[0090] Precise regional insights: In regional analysis, by calculating the average difference in the number of users in adjacent analysis periods in each grid and comparing it with the preset threshold, key inflow areas and normal flow areas are divided. This can accurately locate areas with different flow characteristics, help to understand the passenger flow gathering or evacuation situation in different grid areas in a targeted manner, and has important guiding significance for resource allocation, management decision-making and other aspects.

[0091] Visual and intuitive display: The results of real-time analysis and regional analysis are displayed in a visual way. Whether it is a real-time crowd flow map or a key area map, etc., relevant personnel can understand passenger flow information more intuitively and clearly, reducing the difficulty of information interpretation and facilitating rapid response strategies based on passenger flow conditions.

[0092] User classification refinement: Users can be classified according to their mobile phone numbers, and local users and non-local users can be distinguished. On this basis, real-time crowd flow maps and key area maps for local users and non-local users can be obtained respectively, which further refines the dimensions of passenger flow analysis and enables managers to formulate corresponding services, management and other measures according to the flow characteristics of users from different sources.

[0093] Clear individual travel patterns: By analyzing the user's individual travel cycle, calculating the total duration of their activities and the frequency of occurrence in different periods and time intervals, it is helpful to understand the individual's activity patterns and habits in the target collection area. For example, the travel preferences of specific individuals such as frequent travelers can be analyzed based on this, providing a basis for personalized services.

[0094] Insights into group travel patterns: Periodic analysis of group travel patterns can determine travel peaks, troughs, and normal travel time periods, which has important reference value for resource allocation and operational planning in many scenarios such as public transportation operations, business hours scheduling in commercial venues, and organization of large-scale events, so that it can better match passenger flow peaks and troughs and improve service quality and operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] The present invention will be further described below in conjunction with the accompanying drawings.

[0096] Figure 1 It is a flow chart of the passenger flow information collection system and method based on multiple scenarios of the present invention.

[0097] Figure 2 It is a flowchart of real-time analysis in the passenger flow information collection system and method based on multiple scenarios of the present invention. DETAILED DESCRIPTION

[0098] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0099] Embodiment 1

[0100] See also Figure 1 and Figure 2 As shown, the present invention is a passenger flow information collection method based on multiple scenarios, comprising the following steps:

[0101] Step 1: Data acquisition:

[0102] Obtain geospatial information of the target collection area;

[0103] Acquire mobile signaling data in multiple time periods within a specified period at specified time intervals;

[0104] Among them, mobile signaling data includes timestamp, mobile phone number, base station unique identifier and base station latitude and longitude;

[0105] Step 2: Real-time analysis:

[0106] The target collection area is divided into grids in geographical space according to preset rules, and at the same time, a real-time flow map of the crowd is determined by the longitude and latitude of the base stations in the mobile signaling data;

[0107] Wherein, the grid division method is to divide the target acquisition area into multiple target-sized grids through GPS coordinate grids;

[0108] At the same time, each grid is assigned a unique identifier;

[0109] The identifier of the grid is represented by [i, j], and i=1...n, j=1...m, and n and m represent the vertical and horizontal numbers of the grids respectively;

[0110] The crowd flow map is determined as follows:

[0111] Step 1.1, determine the grid to which the location information of each mobile signaling data belongs through the base station longitude and latitude in the mobile signaling data;

[0112] Step 1.2, according to the time trend, mark multiple time periods in the specified period as analysis period 1, analysis period 2, ... analysis period e;

[0113] Then, the analysis period to which the location information of each mobile signaling data belongs is determined through the timestamp in the mobile signaling data;

[0114] Step 1.3: Count the number of users in each grid corresponding to each analysis period and mark it as S k，i，j ; Wherein, k represents the number of analysis time periods, k = 1, 2, ... e, and e represents the number of time periods;

[0115] Step 1.4: In two adjacent analysis periods k and k+1, extract the number of users S in each grid k，i，j and S k+1，i，j ;

[0116] Then through Calculate the difference in the number of users between the two adjacent analysis periods

[0117] Step 1.5, according to the difference between the two adjacent analysis periods, determine the crowd flow direction of the two adjacent analysis periods;

[0118] like If it is greater than 0, it means that the number of users in the corresponding grid [i, j] increases, that is, people flow into the corresponding grid [i, j];

[0119] like If it is less than 0, it means that the number of users in the corresponding grid [i, j] decreases, that is, people flow out of the corresponding grid [i, j];

[0120] like If it is equal to 0, it means that the number of users in the corresponding grid [i, j] has not changed, that is, there is no crowd flow in the corresponding grid [i, j];

[0121] Step 1.6, based on the crowd flow direction of the two adjacent analysis periods and combined with geographic space information, a real-time crowd flow map is generated;

[0122] When the crowd real-time flow map generation time exceeds the corresponding preset time interval, the number of users corresponding to an analysis period adjacent to the next analysis period in the adjacent analysis period in Step 1.5 is obtained, and then a new crowd real-time flow map is generated and the original crowd real-time flow map is updated according to the method from Step 1.4 to Step 1.5;

[0123] In this embodiment, such a process design is intended to ensure that the real-time crowd flow map can reflect the actual situation in a timely manner, so that relevant personnel can analyze and make decisions based on accurate data, and improve the efficiency of collecting and managing crowd flow. Whether in the fields of traffic planning, event organization or security, such accurate and timely crowd flow information is of great significance, which can help relevant parties better allocate resources and optimize layout, thereby ensuring the smooth progress of various activities and the maintenance of public safety;

[0124] Step 3: Information display:

[0125] The analysis results corresponding to the real-time analysis are displayed in a visual manner.

[0126] This embodiment divides the target collection area into grids and determines the real-time crowd flow map in combination with the base station longitude and latitude in the mobile signaling data, which can accurately reflect the crowd flow in different areas and provide detailed crowd dynamic information for relevant personnel; it marks multiple time periods according to the time trend, counts the number of users in each grid and calculates the difference between adjacent time periods to determine the direction of crowd flow, which helps to timely grasp the changing trend of crowd flow and improve the collection and management efficiency of crowd flow; when the generation time of the real-time crowd flow map exceeds the corresponding preset time interval, the real-time crowd flow map is updated in time to ensure that the displayed information can accurately reflect the actual situation, provide important data support for fields such as traffic planning, event organization and security, and help relevant parties better allocate resources, optimize layout, and ensure the smooth progress of various activities and the maintenance of public safety.

[0127] For example:

[0128] Suppose we want to collect and analyze crowd flow in the downtown area of ​​a city, which is the target collection area.

[0129] First, we acquired data. We obtained the geographic spatial information of the city's downtown area, such as the boundary range of the area, the distribution of main streets, etc.

[0130] Then, at hourly intervals, we obtained mobile signaling data for each time period of each day of the week (e.g., 7:00-9:00 a.m., 12:00-14:00 p.m., 18:00-20:00 p.m., etc.);

[0131] The data includes information such as timestamp, mobile phone number, base station unique identifier, and base station latitude and longitude;

[0132] Then, real-time analysis is performed to divide the downtown area into 100 (n=10, m=10) grids of equal size using GPS coordinate grids, and each grid is assigned a unique identifier, such as [1,1], [1,2], ... [10,10];

[0133] Determine the grid to which each mobile signaling data belongs and the analysis period through the latitude and longitude of the base station;

[0134] For example, during the analysis period of 8:00-9:00 a.m., the number of users in the statistical grid [3,5] is 200, marked as S. 1,3,5 (assuming this is the first analysis period);

[0135] In the adjacent analysis period of 9:00-10:00 in the morning, the number of users in grid [3,5] becomes 250, S 2,3,5 =250;

[0136] By calculating the difference, we know that 50 people flow into the grid [3,5] during this period, and the crowd flow direction is inflow. Combining geographic spatial information, a real-time crowd flow map is generated;

[0137] If the crowd flow map generation time exceeds the preset time interval per hour, the data of the next adjacent analysis period (such as 10 am to 11 am) is obtained and the crowd flow map is updated in the same way;

[0138] In this way, relevant personnel can timely understand the crowd flow in different grids in the city center. For example, the traffic management department can adjust the duration of traffic lights and optimize bus routes according to the crowd flow, thereby improving the efficiency of urban traffic operation.

[0139] Embodiment 2

[0140] As the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of the present embodiment is different from the first embodiment only in that the present embodiment further includes the following steps: Regional analysis:

[0141] In each grid, the difference in the number of users in each adjacent analysis period is combined to generate a real-time crowd flow map;

[0142] The specific method is as follows:

[0143] A grid is selected, and the difference in the number of users in multiple adjacent analysis periods within a specified period is obtained in the grid, and then the average value is calculated, and the average value is marked as the regional evaluation value;

[0144] Then the regional evaluation value is compared with the preset regional evaluation threshold, and the regional mark of the grid is determined based on the comparison result:

[0145] Area markings include: key inflow areas and normal flow areas;

[0146] If the regional evaluation value is greater than the regional evaluation threshold, it means that the inflow of people in the grid is large, and the grid is marked as a key inflow area. Otherwise, the grid is marked as a normal flow area.

[0147] And so on, determine the area mark corresponding to each grid;

[0148] Then the key inflow areas and normal flow areas are combined with geospatial information to generate a key area map;

[0149] In this embodiment, in the key area map, the key inflow area is marked by a red block at the corresponding grid;

[0150] The information display step is also used to display the analysis results corresponding to the regional analysis in a visual manner.

[0151] This embodiment not only generates a real-time crowd flow map in each grid by combining the difference in the number of users in each adjacent analysis period, but also determines the regional mark of the grid by calculating the average value and comparing it with the preset regional assessment threshold, thereby further distinguishing between key inflow areas and normal flow areas; the generated key area map can allow relevant personnel to more intuitively understand which areas have a large influx of people, so as to carry out targeted resource allocation and management, improve management efficiency and service quality; key inflow areas are marked with red blocks in the key area map, so that the information display is clearer and easier to quickly identify key areas.

[0152] For example:

[0153] Taking the city center area as an example, regional analysis is performed based on Example 1;

[0154] In each grid, we calculate the difference in the number of users in each adjacent analysis period;

[0155] For example, for grid [4,7], the difference in the number of users in the same time period every day of the week (such as 10am-11am and 11am-12pm) is 30, 40, 20, 35, 45, 38, and 22 respectively. Then the average value is (30+40+20+35+45+38+22)÷7=32;

[0156] Assume that the regional assessment threshold is 30;

[0157] Since the average value is greater than the regional assessment threshold, the grid [4,7] is marked as the key inflow area. The other grids are calculated and marked in the same way, and finally the regional marks corresponding to each grid are determined to generate the key area map;

[0158] In the key area map, key inflow areas such as grid [4,7] are marked with red blocks at the corresponding grids;

[0159] Merchants can open more stores or hold promotional activities in key inflow areas based on the key area map to attract more customers and improve business efficiency.

[0160] Embodiment 3

[0161] As the third embodiment of the present invention, when the present application is implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments, and the difference between the technical solution of this embodiment and the first and second embodiments is that in this embodiment, it also includes the steps of: user classification

[0162] Classify users in the target collection area based on the mobile phone numbers in all mobile signaling data;

[0163] The analysis and processing methods are as follows:

[0164] According to the mobile phone numbers in all mobile signaling data in each area, the location of each mobile phone number is counted;

[0165] Users in the target collection area are divided into local users and non-local users according to the location of their mobile phone numbers;

[0166] The specific distinction is as follows:

[0167] First, extract and pre-establish a mobile phone number location database;

[0168] Among them, the database contains the mapping relationship between each mobile phone number segment and the corresponding location;

[0169] Then, for each mobile phone number, its location is determined by querying the database;

[0170] If the location is consistent with the location of the target collection area, the user is marked as a local user; otherwise, the user is marked as a foreign user;

[0171] In this embodiment, by extracting all non-local users and combining the real-time analysis in step 2 and the regional analysis in step 3, a real-time flow map of non-local users and a map of key areas can be obtained respectively;

[0172] At the same time, by extracting all local users and combining the real-time analysis in step 2 and the regional analysis in step 3, a real-time flow map of the crowd and a map of key areas for local users can be obtained respectively;

[0173] In the embodiments, signaling data is data used in a communication network to control processes such as establishing, maintaining, and releasing communication connections; a mobile phone number, as an identifier of a communication device, appears in many signaling interaction processes; when a mobile phone initiates a call, the initial signaling message for call establishment will include the calling user's mobile phone number, which is used to route the call in the network to determine the location of the called user and establish a connection; similarly, the signaling process for services such as text message sending will also include the sender and receiver's mobile phone numbers so that the network can accurately transmit information; although signaling data includes mobile phone numbers, entities that own the data, such as communication operators, are subject to strict privacy regulations and internal security policies, and they provide mobile phone number-related content in an identifiable form such as plain text with the user's consent or under specific circumstances required by law.

[0174] This embodiment classifies users in the target collection area according to their mobile phone numbers, and divides users into local users and non-local users, which can meet the analysis needs of specific user groups in different scenarios; real-time crowd flow maps and key area maps for non-local users and local users are obtained respectively, which helps to have a deeper understanding of the flow characteristics and behavior patterns of different user groups, and provide a basis for formulating more accurate policies and services; combined with the solutions of embodiment one and embodiment two, on the basis of providing comprehensive crowd flow information, user classification is further refined, the analysis dimension is enriched, and the accuracy and pertinence of the analysis are improved.

[0175] For example:

[0176] Still taking the city center area as an example, user classification is performed on the basis of the first and second embodiments.

[0177] First, based on the mobile phone numbers in all mobile signaling data, through the pre-established mobile phone number location database;

[0178] Among them, the database contains the mapping relationship between each mobile phone number segment and the corresponding location;

[0179] Then, the users in the target collection area are classified;

[0180] For example, if the number is 1385678, and the database is queried to know that its location is this city, then the user is marked as a local user;

[0181] The number 1368910, whose place of origin is other cities, will be marked as a non-local user.

[0182] By extracting all non-local users and combining real-time analysis with regional analysis, we can obtain a real-time flow map of non-local users and a map of key areas.

[0183] For example, it was found that during the tourist season, out-of-town users were located in grids around certain scenic spots in the city center, such as [6,3], [7,4], etc.;

[0184] During certain time periods, the influx of people is large, such as from 14:00 to 16:00 in the afternoon, forming a key influx area for out-of-town users;

[0185] Similarly, similar analysis can be performed for local users. Urban planning departments can formulate different planning strategies based on the different flow of local and non-local users, such as increasing the layout of community public facilities for local residents and optimizing service facilities around tourist attractions for non-local tourists.

[0186] Embodiment 4

[0187] As the fourth embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the second embodiment and the third embodiment, the difference between the present embodiment and the first embodiment, the second embodiment and the third embodiment is only that in the present embodiment,

[0188] It also conducts analysis of individual user travel cycles and group travel pattern periodicity based on the geospatial information of the target collection area and the user's mobile signaling data;

[0189] Step K1: The analysis method of individual user travel cycle is as follows:

[0190] Step K1.1. For each user, determine the date and time of their first appearance and the date and time of their last appearance based on their activity records in the target collection area, and mark them as T respectively. start and T end ;

[0191] Step K1.2, through: T total =T end -T start ;

[0192] Calculate the total activity time T of the user in the collection area total ;

[0193] Step K1.3: During the observation period, count the number of times a user appears in different periods and multiple different time intervals in different periods, and mark it as W. gt ;

[0194] Among them, g = 1, 2, ... u, t = 1, 2, ... v, u represents the number of different periods in the observation period, and v represents the number of multiple different time intervals in different periods;

[0195] Moreover, different periods are divided within the observation period, and different time intervals are divided within different periods;

[0196] For example, taking one week as the observation period, count the number of times each user appears in different time periods from Monday to Sunday, such as 0-6 o'clock, 6-12 o'clock, 12-18 o'clock, and 18-24 o'clock, where g represents the day of the week, and i = 1, 2, ... 7, representing time periods t = 1, 2, 3, 4;

[0197] Step K1.4, through:

[0198] Calculate the user's appearance frequency FL in each time period gt :

[0199] Step K2: The periodic analysis method of group travel rules is as follows:

[0200] Step K2.1, aggregate and average the appearance frequencies of all users in different periods and multiple different time intervals within different periods to obtain the travel frequency distribution of the group in different weeks and time periods;

[0201] The method is:

[0202] The frequency of each user in the group in different periods and multiple different time intervals in different periods is marked as FL gth ;

[0203] Where h = 1, 2, ..., e, e represents the number of all users in the group;

[0204] Then through:

[0205] The average frequency of occurrence of FLP in a population at different times and in multiple time intervals within different times gt ;

[0206] Step K2.1. Determine the peak and trough time periods based on the travel frequency distribution of the group;

[0207] The method is:

[0208] The average frequency FLP of the group in different periods and multiple different time intervals in different periods gt Compare with the preset frequency thresholds FLPy1 and FLPy2:

[0209] Among them, FLPy1<FLPy2;

[0210] When FLP gt >FLPy2, the corresponding time period is regarded as the travel peak time period;

[0211] When FLP gt When <FLPy1, it is regarded as the travel low period;

[0212] When FLPy2 ≥ FLP gt When ≥FLPy1, it is regarded as the normal travel time period;

[0213] In this embodiment, the periodic information of group travel patterns, including travel frequency distribution in different weeks and time periods, and travel peak and valley time periods, are displayed in a visual manner;

[0214] Among them, a bar chart can be used to show the travel frequency distribution.

[0215] Relevant departments can carry out resource allocation and planning based on these analysis results;

[0216] For example, the transportation department can increase public transportation capacity or optimize traffic light settings during peak travel times; the commercial department can reasonably arrange store opening hours and promotional activities according to the distribution of people in different cycle stages.

[0217] This embodiment conducts individual user travel cycle analysis and group travel pattern periodicity analysis based on the target collection area's geographic spatial information and mobile signaling data. Individual travel cycle analysis can determine the total duration of users' activities in the collection area, the number and frequency of occurrences in different periods and time intervals, and help to gain a deeper understanding of individual behavior patterns. Group travel pattern periodicity analysis can summarize the average frequency of all users to obtain the group travel frequency distribution, and determine the peak, trough and normal time periods for travel. Relevant departments can use this to conduct precise resource allocation and planning, such as the transportation department optimizing the capacity and signal light settings, and the commercial department reasonably arranging business hours and promotional activities, improving urban operation efficiency and service quality, making resource utilization more reasonable, and services more in line with people's travel needs.

[0218] Embodiment 5

[0219] As the fifth embodiment of the present invention, when the present application is specifically implemented, compared with the first, second, third and fourth embodiments, the technical solution of this embodiment is to combine and implement the solutions of the above-mentioned first, second, third and fourth embodiments.

[0220] This embodiment integrates all the functions and analyses of embodiments one to four. It can comprehensively and accurately grasp the flow of people in different grids and time periods, determine key inflow areas and normal flow areas, distinguish the flow characteristics of local and non-local users, and generate corresponding real-time flow maps and key area maps for the crowd. It can also deeply analyze the travel patterns of individuals and groups. Relevant departments can comprehensively coordinate resource allocation and management based on rich and detailed analysis results. The transportation department can ensure smooth commuting for different users, the security department can accurately deploy forces to ensure safety, and the commercial department can carry out targeted marketing, comprehensively improving the overall operation efficiency, service quality, and event organization and security level of the city, fully meeting the city's multi-faceted management and operation needs, and enhancing the refinement and adaptability of urban management.

[0221] For example:

[0222] Embodiment 5 combines the solutions of Embodiment 1, Embodiment 2, and Embodiment 3, integrating all the above functions and analyses; still taking the city center area as an example, after fully acquiring the data, not only the flow of people in different grids and time periods is analyzed in real time to generate a real-time crowd flow map; regional analysis is also performed to determine key inflow areas and normal flow areas, and generate a key area map; at the same time, users are classified to obtain real-time crowd flow maps and key area maps for local users and non-local users respectively.

[0223] For example, during a large-scale event, comprehensive analysis shows that the grids around the event venue are the key inflow areas for out-of-town users during a specific period of time before and after the event, while local users may be more concentrated on the path grid between the event venue and their residence during the event;

[0224] Relevant departments can comprehensively allocate and manage resources based on these detailed analysis results; the transportation department can add bus routes and guide signs to the event venues for out-of-town tourists, while ensuring smooth daily commuting for local residents; the security department can strengthen security forces in key inflow areas to ensure the safety of activities; the commercial department can carry out targeted marketing activities in corresponding areas for different user groups, etc. In this way, the people in the central area of ​​the city can be managed and served more efficiently and accurately, and the overall operation efficiency and service quality of the city can be improved.

[0225] In traffic planning scenarios: By dividing the target collection area into grids, combined with the base station longitude and latitude and timestamps in the mobile signaling data, the flow direction and number of people in different grid areas can be determined in real time; this is of great significance to urban traffic planning. For example, the traffic management department can adjust the duration of traffic lights and optimize bus routes in traffic congestion areas in a timely manner based on the real-time flow map of the crowd, thereby improving the efficiency of urban traffic operation;

[0226] In the event organization scenario: When holding large-scale events, such as concerts and sports events, this analysis helps organizers understand the real-time dynamics of the crowd at the event site and surrounding areas; for example, they can clearly understand the crowd gathering and evacuation in different areas when the audience enters and leaves the venue, so as to reasonably arrange on-site guides and set up safe passages to ensure that the event is carried out safely and orderly;

[0227] In the tourism management scenario: users are divided into local users and non-local users according to the location of their mobile phone numbers, and non-local users are analyzed; in tourist cities, the flow patterns of non-local tourists in tourist attractions, hotels, commercial streets and other areas can be deeply understood. For example, through the real-time flow map of non-local users, the tourism management department can determine the scenic spots and time periods where tourists are concentrated, and reasonably arrange tourism resources, such as adding service facilities in scenic spots and optimizing tourist routes; tourism businesses can also carry out precise marketing activities in areas with dense tourist concentrations to increase tourism revenue;

[0228] In the local public service optimization scenario: Analysis of local users helps to understand the daily activities and travel patterns of local residents. Urban planning departments can optimize the layout of community public facilities based on this information, such as adding parks and fitness facilities in areas where residents frequently move around. Public transportation departments can also reasonably plan bus routes and operating hours based on the peak travel hours and frequented locations of local residents, thereby improving the convenience of local residents' lives.

[0229] In the commercial layout scenario: calculate the evaluation value of each grid area and compare it with the threshold to determine the key inflow area and normal flow area, and generate a key area map; in the commercial field, merchants can open more stores and hold promotional activities in areas with large inflow of people, such as urban commercial centers and emerging commercial areas, based on the key area map, to attract more consumers and improve business efficiency; at the same time, it also helps commercial real estate developers determine the location of new commercial projects, so that the commercial layout is more in line with the flow trend of people;

[0230] In the public facilities construction scenario: government departments can rationally plan the construction of public facilities in key inflow areas based on the results of regional analysis, such as increasing the number of public toilets, parking lots and other facilities in densely populated areas with frequent mobility, optimizing the allocation of public service resources and improving the overall service level of the city;

[0231] In the personalized service scenario: calculating the total time of users' activities in the collection area and the frequency of their appearance in different periods and time intervals can provide a deep understanding of individual behavior patterns; for example, hotels can prepare personalized services in advance based on the travel cycles of frequent travelers, such as preparing specific room types and preferred items during their regular check-in times; travel service providers can also recommend personalized travel itineraries for tourists based on their individual travel patterns;

[0232] In the research scenario of specific populations: It is also of great significance to study the activity patterns of specific populations, such as office workers and students. Taking the study of office workers as an example, by analyzing their travel cycles on weekdays and non-working days, we can understand their commuting patterns, activity patterns near their workplaces, etc., and provide data support for urban functional area planning, such as the reasonable layout of business districts and residential areas.

[0233] In public transportation operation scenarios: determine the peak and off-peak time periods for group travel. The transportation department can increase public transportation capacity during peak travel periods, such as increasing bus trips and subway departure frequencies, optimizing traffic signal settings, improving traffic operation efficiency, and alleviating traffic congestion; reasonably arrange vehicle maintenance and driver rest during off-peak time periods to reduce operating costs;

[0234] Commercial operation scenarios: Commercial departments can reasonably arrange store opening hours and promotional activities according to the travel patterns of groups; for example, during peak travel periods, they can extend business hours and increase promotion efforts to attract more customers to consume; during off-peak periods, they can arrange internal work such as employee training and store tidying up to improve operational management efficiency.

[0235] The present invention also provides: a passenger flow information collection system based on multiple scenarios, the system is implemented by a passenger flow information collection method based on multiple scenarios, and the system includes:

[0236] A data acquisition unit, which acquires geographic spatial information of a target acquisition area and simultaneously acquires mobile signaling data within multiple time periods within a specified period at specified time intervals;

[0237] A real-time analysis unit is used to divide the target collection area into grids in geographic space according to preset rules, and determine the real-time flow map of the crowd through the longitude and latitude of the base station in the mobile signaling data; and to perform individual user travel cycle analysis and group travel regularity periodicity analysis based on the geographic space information of the target collection area and the mobile signaling data of the user;

[0238] The regional analysis unit is used to generate a real-time crowd flow diagram in each grid by combining the difference of the number of users in each adjacent analysis period;

[0239] Information display is used to display the analysis results corresponding to the real-time analysis unit and the regional analysis unit in a visual manner.

[0240] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0241] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A passenger flow information collection method based on multiple scenarios, characterized in that: The following steps are involved: Step 1: Obtain the geographic spatial information of the target collection area, and simultaneously obtain the mobile signaling data in multiple time periods within a specified period at a specified time interval; wherein the mobile signaling data includes a timestamp, a mobile phone number, a base station unique identifier, and the latitude and longitude of the base station; Step 2: The target collection area is divided into grids in geographic space according to preset rules. At the same time, the real-time flow map of the crowd is determined by the longitude and latitude of the base station in the mobile signaling data. The individual travel cycle analysis of the user and the periodic analysis of the group travel rules are also performed based on the geographic space information of the target collection area and the mobile signaling data of the user; Step 3: In each grid, a real-time crowd flow diagram is generated by combining the difference in the number of users in each adjacent analysis period; Step 4: Display the analysis results corresponding to step 2 and step 3 in a visual way.

2. The method for collecting passenger flow information based on multiple scenarios according to claim 1 is characterized in that: In step 2, the grid division method is to divide the target acquisition area into multiple target-sized grids through GPS coordinate grids; At the same time, each grid is assigned a unique identifier; The identifier of the grid is represented by [i, j], and i=1...n, j=1...m, and n and m represent the vertical and horizontal numbers of the grids respectively.

3. The method for collecting passenger flow information based on multiple scenarios according to claim 2 is characterized in that: In step 2, the crowd flow map is determined as follows: Step 1.1, determine the grid to which the location information of each mobile signaling data belongs through the base station longitude and latitude in the mobile signaling data; Step 1.2, according to the time trend, mark multiple time periods in the specified period as analysis period 1, analysis period 2, ... analysis period e; Then, the analysis period to which the location information of each mobile signaling data belongs is determined through the timestamp in the mobile signaling data; Step 1.3: Count the number of users in each grid corresponding to each analysis period and mark it as S k，i，j ; Wherein, k represents the number of analysis time periods, k = 1, 2, ... e, and e represents the number of time periods; Step 1.4: In two adjacent analysis periods k and k+1, extract the number of users S in each grid k，i，j and S k+1，i，j ; Then through Calculate the difference in the number of users between the two adjacent analysis periods Step 1.5, according to the difference between the two adjacent analysis periods, determine the crowd flow direction of the two adjacent analysis periods; like If it is greater than 0, it means that the number of users in the corresponding grid [i, j] increases, that is, people flow into the corresponding grid [i, j]; like If it is less than 0, it means that the number of users in the corresponding grid [i, j] decreases, that is, people flow out of the corresponding grid [i, j]; like If it is equal to 0, it means that the number of users in the corresponding grid [i, j] has not changed, that is, there is no crowd flow in the corresponding grid [i, j]; Step 1.6: Generate a real-time crowd flow map based on the crowd flow direction in the two adjacent analysis periods and in combination with geographic spatial information.

4. The method for collecting passenger flow information based on multiple scenarios according to claim 3 is characterized in that: When the generation time of the real-time crowd flow map exceeds the corresponding preset time interval, the number of users corresponding to an analysis period adjacent to the next analysis period in the adjacent analysis period in Step 1.5 is obtained, and then a new real-time crowd flow map is generated and the original real-time crowd flow map is updated according to the method from Step 1.4 to Step 1.

5.

5. The method for collecting passenger flow information based on multiple scenarios according to claim 1 is characterized in that: In step 3, the key area map is generated as follows: A grid is selected, and the difference in the number of users in multiple adjacent analysis periods within a specified period is obtained in the grid, and then the average value is calculated, and the average value is marked as the regional evaluation value; Then, the regional evaluation value is compared with a preset regional evaluation threshold, and the regional mark of the grid is determined according to the comparison result, wherein the regional mark includes: a key inflow area and a normal flow area; If the regional evaluation value is greater than the regional evaluation threshold, it means that the inflow of people in the grid is large, and the grid is marked as a key inflow area. Otherwise, the grid is marked as a normal flow area. And so on, determine the area mark corresponding to each grid; Then the key inflow areas and normal flow areas are combined with geospatial information to generate a key area map; In the key area map, the key inflow areas are marked by red blocks at the corresponding grids.

6. The method for collecting passenger flow information based on multiple scenarios according to claim 1, characterized in that: The analysis method of individual user travel cycle is as follows: Step K1.

1. For each user, determine the date and time of their first appearance and the date and time of their last appearance based on their activity records in the target collection area, and mark them as T respectively. start and T end ; Step K1.2, through: T total =T end -T start ; Calculate the total activity time T of the user in the collection area total ; Step K1.3: During the observation period, count the number of times a user appears in different periods and multiple different time intervals in different periods, and mark it as W. gt ; Among them, g = 1, 2, ... u, t = 1, 2, ... v, u represents the number of different periods in the observation period, and v represents the number of multiple different time intervals in different periods; Moreover, different periods are divided within the observation period, and different time intervals are divided within different periods; Step K1.4, through: Calculate the user's appearance frequency FL in each time period gt : The periodic analysis method of group travel rules is as follows: Step K2.1, aggregate and average the appearance frequencies of all users in different periods and multiple different time intervals within different periods to obtain the travel frequency distribution of the group in different weeks and time periods; The method is: mark the frequency of each user in the group in different periods and multiple different time intervals in different periods as FL gth ; Where h = 1, 2, ..., e, e represents the number of all users in the group; Then through: The average frequency of occurrence of FLP in a population at different times and in multiple time intervals within different times gt ; Step K2.

1. Determine the peak and trough time periods based on the travel frequency distribution of the group; The method is to calculate the average frequency FLP of the group in different periods and multiple different time intervals in different periods gt Compare with the preset frequency thresholds FLPy1 and FLPy2: Among them, FLPy1<FLPy2; When FLP gt >FLPy2, the corresponding time period is regarded as the travel peak time period; When FLP gt When <FLPy1, it is regarded as the travel low period; When FLPy2 ≥ FLP gt When ≥FLPy1, it is regarded as the normal travel time period.

7. The method for collecting passenger flow information based on multiple scenarios according to claim 1 is characterized in that: It also includes the steps: User classification: According to the mobile phone numbers in all mobile signaling data, the users in the target collection area are classified and processed, and the users in the target collection area are divided into two clusters according to the classification results; The two clusters are respectively corresponding to local users and foreign users.

8. The method for collecting passenger flow information based on multiple scenarios according to claim 7 is characterized in that: The analysis and processing methods are as follows: According to the mobile phone numbers in all mobile signaling data in each area, the location of each mobile phone number is counted; Users in the target collection area are divided into local users and non-local users according to the location of their mobile phone numbers. The user differentiation method is as follows: First, extract and pre-establish a mobile phone number location database; Among them, the database contains the mapping relationship between each mobile phone number segment and the corresponding location; Then, for each mobile phone number, its location is determined by querying the database; If the location is consistent with the location of the target collection area, the user is marked as a local user; otherwise, it is marked as a foreign user.

9. The method for collecting passenger flow information based on multiple scenarios according to claim 7, characterized in that: By extracting all non-local users and combining the analysis methods in step 2 and step 3, a real-time flow map of non-local users and a map of key areas are obtained respectively; At the same time, by extracting all local users and combining the real-time analysis in step two and the regional analysis in step three, a real-time flow map of the population and a map of key areas for local users are obtained respectively.

10. A passenger flow information collection system based on multiple scenarios, the system being implemented by the passenger flow information collection method based on multiple scenarios according to any one of claims 1 to 9, characterized in that: The system includes: A data acquisition unit, which acquires geographic spatial information of a target acquisition area and simultaneously acquires mobile signaling data within multiple time periods within a specified period at specified time intervals; A real-time analysis unit is used to divide the target collection area into grids in geographic space according to preset rules, and determine the real-time flow map of the crowd through the longitude and latitude of the base station in the mobile signaling data; and to perform individual user travel cycle analysis and group travel regularity periodicity analysis based on the geographic space information of the target collection area and the mobile signaling data of the user; The regional analysis unit is used to generate a real-time crowd flow diagram in each grid by combining the difference of the number of users in each adjacent analysis period; Information display is used to display the analysis results corresponding to the real-time analysis unit and the regional analysis unit.

Images