A passenger flow accurate analysis method and system based on mobile phone users

Abstract

The application relates to the technical field of passenger flow analysis, and discloses a passenger flow accurate analysis method and system based on mobile phone users, which comprises the following steps: collecting user trajectory data of users in a scenic area and performing pretreatment; performing path matching on the pretreated user trajectory data and road network data in the scenic area; identifying the passenger trajectory data, performing time period statistics of the passenger trajectory data according to scenic landscape areas; calculating seasonal influence factors and scenic activity factors of the scenic landscape areas by using a passenger flow optimization model, optimizing and adjusting passenger number statistical results in combination with passenger heat values, and converting the passenger number statistical results into statistical charts and tables. The application maps and converts mobile phone communication positioning coordinates and scenic roads, performs positioning matching on passenger trajectories based on a limited number of mobile phone communication positioning coordinates, performs statistics of the passenger trajectories in different time periods, and adjusts the statistical results in combination with seasonal information and scenic activity information, so that the passenger number in the scenic area can be summarized and counted.

Description

Technical Field

[0001] This invention relates to the field of passenger flow analysis, and in particular to a method and system for accurate passenger flow analysis based on mobile phone users. Background Technology

[0002] In recent years, with sustained economic growth and improved living standards, the tourism industry, as an important component of the global economy, has developed rapidly. According to statistics from the World Tourism Organization (UNWTO), the number of international tourists has increased year by year, and tourism spending has also been rising. As one of the world's largest tourism markets, China's tourism development has not only boosted local economic growth but also promoted cultural exchange and social development. However, the rapid development of the tourism industry has also brought many challenges, especially in terms of visitor flow management and resource allocation. During peak tourist seasons, scenic spots often face overcrowding, leading to a decline in visitor experience, increased environmental pollution, and increased safety hazards. Effective visitor flow management can not only improve visitor satisfaction but also optimize resource allocation and reduce operating costs. Therefore, how to accurately analyze and measure visitor numbers in different areas of a scenic spot has become an urgent problem for tourism managers to solve. Summary of the Invention

[0003] In view of this, the present invention provides a method and system for accurate passenger flow analysis based on mobile phone users. By collecting and analyzing information such as the movement trajectory and dwell time of mobile phone users in scenic spots, it provides data support for passenger flow analysis and supports real-time monitoring of passenger flow in scenic spots.

[0004] To achieve the above objectives, the present invention provides a method for accurate passenger flow analysis based on mobile phone users, comprising the following steps:

[0005] S1: Collect user trajectory data within the scenic area and preprocess it to obtain preprocessed user trajectory data;

[0006] S2: Match the preprocessed user trajectory data with the road network data within the scenic area to obtain the user's actual road network trajectory data, wherein the trajectory similarity metric is the implementation method of the path matching;

[0007] S3: Identify tourist trajectory data from the user's actual road network trajectory data, and perform time-segmented statistics on tourist trajectory data according to scenic area to obtain the tourist number statistics for different scenic areas at different times;

[0008] S4: Min the tourist trajectory patterns within the scenic area from the tourist trajectory data to obtain the tourist popularity value of the scenic area.

[0009] S5: Construct a visitor flow optimization model, use the visitor flow optimization model to calculate the seasonal influencing factors of the scenic area and the activity factors of the scenic area, combine the visitor popularity value to optimize and adjust the visitor number statistics, and convert the optimized and adjusted visitor number statistics into statistical charts for display.

[0010] As a further improvement of the present invention:

[0011] Optionally, the user trajectory data collected in step S1 within the scenic area includes:

[0012] Collect user trajectory data within the scenic area:

[0013] e= { e n =( e n 1 , e n 2 ,..., e n i ,..., e n num n |n∈[1,N]} ;

[0014] in:

[0015] This represents the user trajectory sequence of the nth user within the scenic area;

[0016] Represents user trajectory sequence middle A sequence of mobile phone signaling data, among which Represents user trajectory sequence The i-th mobile signaling data in the middle, Represents user trajectory sequence The total number of mobile phone signaling data is provided by the mobile operator in this embodiment of the invention.

[0017] e n i = ( dis n i , time n i ),i ∈ [1, num n ] , Indicates mobile phone signaling data Distance information in the middle, Indicates mobile phone signaling data The time of generation, including distance information For the nth user's mobile phone at time The distance between the mobile phone and the three base stations within the scenic area; in this embodiment of the invention, if the mobile phone communicates with the base stations within the scenic area, mobile phone signaling data is generated;

[0018] The user trajectory data e is preprocessed to obtain preprocessed user trajectory data.

[0019] Optionally, the user trajectory data is preprocessed to obtain preprocessed user trajectory data, including:

[0020] Preprocess the user trajectory data e, where user trajectory data e contains user trajectory sequences. The preprocessing procedure is as follows:

[0021] S11: Obtain the coordinates of three base stations A, B, and C within the scenic area:

[0022] ;

[0023] in:

[0024] The coordinates of three base stations A, B, and C within the scenic area are shown in that order. Let A, B, and C be the coordinates of the three base stations in the east-west direction. Let A, B, and C be the coordinates of the three base stations in the north-south direction, with the center of the scenic area as the origin.

[0025] S12: Extract distance information from mobile phone signaling data, construct a system of equations corresponding to the location coordinates based on base station coordinates, solve the system of equations to obtain the location coordinates corresponding to any mobile phone signaling data; where mobile phone signaling data The corresponding positioning coordinates are , These represent the coordinates in the east-west and north-south directions, respectively; the distance information... The system of equations corresponding to the positioning coordinates is as follows:

[0026] ;

[0027] ;

[0028] in:

[0029] These represent the times of the mobile phone held by the nth user. Distances between the scenic area and three base stations A, B, and C;

[0030] Representing distance information The corresponding location coordinates, that is, the nth user at time The positioning coordinates;

[0031] S13: Construct a user positioning coordinate sequence from all the positioning coordinates. :

[0032] ;

[0033] S14: Calculate the user's location coordinate sequence Abnormal index Among them, the abnormal index The calculation formula is:

[0034] ;

[0035] ;

[0036] in:

[0037] This represents a preset distance threshold between adjacent positioning coordinates;

[0038] Represents positioning coordinates The distance between them;

[0039] S15: If the abnormal index If the value exceeds the preset abnormal threshold, it indicates a user location coordinate sequence. There is a significant positioning error in the user's positioning coordinate sequence. and user trajectory sequences Perform cleaning treatment;

[0040] Otherwise, it constitutes a user trajectory sequence. Preprocessing results :

[0041] ;

[0042] ;

[0043] in:

[0044] Indicates mobile phone signaling data The processing results;

[0045] Preprocessing results This is the g-th preprocessed user trajectory sequence in the preprocessed user trajectory data E, where g represents the number of the current preprocessed user trajectory sequences, and the initial value of g is 1.

[0046] All preprocessed user trajectory sequences constitute preprocessed user trajectory data. :

[0047] E={ E m =( E m 1 , E m 2 ,..., E m i ,..., E m num m |m∈[1,M]} ;

[0048] ;

[0049] in:

[0050] M represents the total number of preprocessed user trajectory sequences. This represents the preprocessed user trajectory sequence of the m-th group. Represents user trajectory sequence The processing result of the i-th mobile signaling data. Represents user trajectory sequence The total number of processing results for mobile phone signaling data.

[0051] Optionally, in step S2, the preprocessed user trajectory data is matched with the road network data within the scenic area to obtain the user's actual road network trajectory data, including:

[0052] The preprocessed user trajectory data is matched with the road network data within the scenic area to obtain the user's actual road network trajectory data, where the m-th preprocessed user trajectory sequence is... The path matching process is as follows:

[0053] S21: Constructing road network data within the scenic area ,in G represents the set of vertex coordinates of road turning points or road intersections within the scenic area. G represents the set of roads within the scenic area. Roads include the starting point, the ending point, and the intermediate point of the road. The coordinates of the starting point, the ending point, and the intermediate point of the road all belong to the set of vertex coordinates.

[0054] S22: Data from the road network within the scenic area Extract user trajectory sequences from the roads. The set of candidate roads with arbitrary location coordinates, where the location coordinates are... The candidate road extraction method is as follows:

[0055] Using positioning coordinates Construct a circular region with center R and radius R, and use the roads contained within or intersecting within the circular region as positioning coordinates. Candidate roads; the resulting positioning coordinates The candidate road set is , Q m i = { Q m i (j)|j∈[1,J]} , Represents the set of candidate roads The j-th candidate road in the set, where J represents the set of candidate roads. Total number of candidate roads;

[0056] S23: Calculate the road direction of any candidate road in the candidate road set; where the candidate roads The road direction is:

[0057] ;

[0058] in:

[0059] Indicate candidate roads The direction of the road;

[0060] Indicate candidate roads The coordinates of the road's endpoint;

[0061] Indicate candidate roads The coordinates of the starting point of the road;

[0062] S24: Combining the road directions of the candidate roads, calculate the probability of any candidate road being used as the actual road network trajectory; where the candidate roads... As positioning coordinates The trajectory probability of the associated actual road network trajectory is:

[0063] ;

[0064] ;

[0065] ;

[0066] ;

[0067] ;

[0068] in:

[0069] Indicate candidate roads As positioning coordinates The trajectory probability of the associated actual road network trajectory;

[0070] Represents an exponential function with the natural constant as its base;

[0071] Represents positioning coordinates The distance between them;

[0072] Represents positioning coordinates The coordinate values ​​in the middle;

[0073] Indicates the location coordinates Projected onto candidate roads The projection distance;

[0074] Indicates probability control parameters;

[0075] Indicate candidate roads The similarity of the road trajectory directions; Indicate candidate roads Road projection distance similarity; Indicate candidate roads The actual road network trajectory transfer probability, i.e., the positioning coordinates The road between them was moved to the candidate road. The probability of;

[0076] S25: Select the candidate road with the highest trajectory probability as... The actual road network trajectory corresponding to the mid-position coordinates; constitutes the user trajectory sequence. Corresponding actual user road network trajectory:

[0077] ;

[0078] in:

[0079] Represents user trajectory sequence Mid-position coordinates The corresponding actual road network trajectory, and As actual road network trajectory The trajectory time.

[0080] Optionally, the step S3, which involves identifying tourist trajectory data from the user's actual road network trajectory data, includes:

[0081] Tourist trajectory data is obtained by identifying actual user road network trajectory data. The process for identifying tourist trajectory data is as follows:

[0082] S31: Calculate the trajectory length of the user's actual road network trajectory; where the user's actual road network trajectory The trajectory length is:

[0083] ;

[0084] in:

[0085] Indicates the user's actual road network trajectory The length of the trajectory;

[0086] Represents the actual road network trajectory The length of the road;

[0087] S32: Calculate the trajectory time of the user's actual road network trajectory; where the user's actual road network trajectory The trajectory time is:

[0088] ;

[0089] in:

[0090] Indicates the user's actual road network trajectory The trajectory time;

[0091] S33: Calculate the area of ​​the smallest bounding rectangle containing the user's actual road network trajectory, and use this area as the scenic area coverage of the user's actual road network trajectory; where the user's actual road network trajectory... The coverage of scenic spots is ;

[0092] S34: Calculate the probability coefficient that the user's actual road network trajectory is the tourist trajectory, where the user's actual road network trajectory The probability coefficient of the tourist trajectory is :

[0093] ;

[0094] in:

[0095] Represents an exponential function with the natural constant as its base;

[0096] If the probability coefficient is greater than the preset probability threshold, the user's actual road network trajectory will be marked as a tourist trajectory, and all tourist trajectories will constitute tourist trajectory data.

[0097] Tourist trajectory data is statistically analyzed by region and time period to obtain the tourist number statistics for different regions at different times.

[0098] Optionally, the step of statistically analyzing tourist trajectory data by time period according to scenic area to obtain tourist number statistics for different scenic areas at different times includes:

[0099] The scenic area is divided into K scenic landscape areas. Based on several tourist trajectories in the tourist trajectory data, if the actual road network trajectory in a tourist trajectory belongs to the t-th time period and overlaps with the k-th scenic landscape area, then this tourist trajectory increases the number of tourists in the k-th scenic landscape area by one in the t-th time period. Thus, the number of tourists in each scenic landscape area at different time periods is calculated, where the number of tourists in the k-th scenic landscape area in the t-th time period is... , t ∈[1,24] Each time slot lasts for 1 hour. k ∈[1,K] .

[0100] Optionally, step S4 involves mining tourist trajectory patterns within the scenic area from the tourist trajectory data, including:

[0101] Tourist trajectory pattern mining is performed on tourist trajectory data within the scenic area to obtain tourist popularity values ​​for different scenic areas. The process of tourist trajectory pattern mining within the scenic area is as follows:

[0102] S41: Extract the vertex coordinate sequence of the tourist trajectory from the tourist trajectory data, and extract the trajectory time corresponding to the actual road network trajectory with the vertex coordinate as the road starting point in the tourist trajectory to form a trajectory time series;

[0103] S42: According to the trajectory time associated with the vertex coordinates, if the trajectory time belongs to the t-th time period, then the vertex coordinates are assigned to the t-th time period, resulting in a set of vertex coordinates for 24 time periods;

[0104] S43: Calculate the density information of K scenic areas at any given time period; where the density information of the kth scenic area at the tth time period is:

[0105] ;

[0106] in:

[0107] This represents the density information of the k-th scenic area in the t-th time period;

[0108] This represents the density information of the k-th scenic area.

[0109] Let Y represent the set of Y vertices in the set of vertex coordinates for the t-th time period that are closest to the k-th scenic area. c represents the set of coordinates The coordinates of any vertex in the array;

[0110] This represents the density control parameter; in this embodiment of the invention, it will be... Set to 2;

[0111] S44: Convert density information into visitor popularity values ​​for scenic areas at any given time period, where the visitor popularity value for the k-th scenic area at the t-th time period is:

[0112] ;

[0113] in:

[0114] This represents the visitor popularity value of the k-th scenic area during the t-th time period.

[0115] Optionally, in step S5, a visitor flow optimization model is constructed. This model is used to calculate seasonal influencing factors and activity factors within the scenic area, and the visitor number statistics are optimized and adjusted based on visitor popularity values. This includes:

[0116] A visitor flow optimization model is constructed, which calculates seasonal influencing factors and scenic area activity factors. The model takes the visitor popularity value of the scenic area, seasonal influencing factors, scenic area activity factors, and visitor number statistics as inputs, and outputs the optimized visitor number statistics. The optimization process for the visitor number statistics is as follows:

[0117] S51: The seasonal influencing factors of different scenic areas are calculated using the passenger flow optimization model; the seasonal influencing factor of the kth scenic area is:

[0118] ;

[0119] in:

[0120] This represents the seasonal influencing factor of the k-th scenic area.

[0121] This represents the average number of visitors to the k-th scenic area during the current season; This represents the average number of tourists visiting the k-th scenic area across all seasons; in this embodiment of the invention, the seasonality factor is calculated using unoptimized tourist number statistics.

[0122] This represents the average number of visitors to the entire scenic area during the current season.

[0123] S52: The visitor flow optimization model calculates the scenic activity factors for different scenic areas; where the scenic activity factor for the kth scenic area is:

[0124] ;

[0125] in:

[0126] This represents the activity factor of the k-th scenic area in the t-th time period. A binary variable representing whether the k-th scenic area holds a special event in the t-th time period. , This indicates that no special event was held in the k-th scenic area during the t-th time period. This indicates that a special event will be held in the k-th scenic area during the t-th time period;

[0127] S53: Using the tourist popularity value, seasonality factor, scenic area activity factor, and tourist number statistics of the scenic area as inputs, calculate the optimized tourist number statistics, where the optimized tourist number of the k-th scenic area in the t-th time period is... :

[0128] S k t = s k t [ (1+ γ k 2 (t) ) H k t h 2 ] γ k 1 h 1 ;

[0129] in:

[0130] The parameters representing the seasonal influencing factors and the scenic area activity factors are respectively:

[0131] The optimized and adjusted tourist number statistics will be converted into statistical charts for display, and the results will be submitted to relevant personnel such as scenic area managers. The statistical charts include bar charts of tourist numbers in different scenic areas over 24 time periods, as well as year-on-year and month-on-month change rates, and pie charts of total tourist numbers in different scenic areas, as well as year-on-year and month-on-month change rates.

[0132] To address the aforementioned problems, this invention provides a precise passenger flow analysis system based on mobile phone users, the system comprising:

[0133] The data acquisition and processing module is used to collect user trajectory data within the scenic area and perform preprocessing to obtain preprocessed user trajectory data.

[0134] The tourist statistics module is used to match the preprocessed user trajectory data with the road network data within the scenic area to obtain the user's actual road network trajectory data. It then identifies the tourist trajectory data from the user's actual road network trajectory data and performs time-segmented statistics on the tourist trajectory data according to the scenic area to obtain the tourist number statistics for different scenic areas at different times.

[0135] The results display device is used to mine tourist trajectory patterns within the scenic area from tourist trajectory data, obtain tourist popularity values ​​for scenic areas, calculate seasonal influencing factors and scenic activity factors for scenic areas using a visitor flow optimization model, optimize and adjust tourist number statistics based on tourist popularity values, and convert the optimized and adjusted tourist number statistics into statistical charts for display.

[0136] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0137] Memory, storing at least one instruction;

[0138] Communication interfaces enable communication between electronic devices; and

[0139] The processor executes the instructions stored in the memory to implement the above-described method for accurate passenger flow analysis based on mobile phone users.

[0140] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned method for accurate passenger flow analysis based on mobile phone users.

[0141] Compared with existing technologies, this invention proposes a method and system for accurate passenger flow analysis based on mobile phone users, which has the following advantages:

[0142] First, this solution proposes a tourist trajectory positioning and matching method based on base stations and mobile phone communication. The method locates the mobile phone based on the distance between the phone and the base station, obtaining a user trajectory sequence containing the phone's location and positioning time. An anomaly index is calculated based on the magnitude of changes in phone location and positioning time; a higher anomaly index indicates a significant change in phone location within a short period. Trajectories with excessively high anomaly indices are filtered out. A road mapping method is used to extract nearby scenic roads from any location coordinate in the user trajectory sequence as candidate roads. Based on the distance between the candidate road and the location coordinate, and the road direction, the similarity of the candidate road's trajectory direction, the similarity of its projected distance, and the probability of actual road network trajectory transfer are calculated. This constructs the trajectory probability of the candidate road as the actual road network trajectory associated with the location coordinate, realizing the mapping and conversion between the location coordinate and scenic roads, and achieving tourist trajectory positioning and matching based on a limited number of mobile phone communication location coordinates.

[0143] Meanwhile, this solution proposes a method for statistical analysis of tourist flow in scenic areas. Based on the trajectory length, trajectory time, and scenic area coverage of users' actual road network trajectories, it selects trajectories with shorter trajectories, longer trajectories, and smaller scenic area coverage as the trajectories of scenic area staff. This enables the filtering and processing of tourist trajectories within the scenic area. Based on the time information of the tourist trajectories, it obtains the number of tourists in different scenic areas at different times. Furthermore, based on the distance from the location coordinates in the tourist trajectory to different scenic areas, it calculates the density information of each scenic area and converts it into a popularity value. A tourist flow optimization model is used to calculate seasonal influencing factors and scenic area activity factors. Using the tourist popularity value, seasonal influencing factors, scenic area activity factors, and tourist number statistics as inputs, the tourist number statistics are optimized and adjusted. The calculation formulas for seasonal influencing factors and scenic area activity factors are continuously updated using new data to improve the accuracy and reliability of the statistics. Attached Figure Description

[0144] Figure 1 A flowchart illustrating a method for precise passenger flow analysis based on mobile phone users, provided in an embodiment of the present invention;

[0145] Figure 2 This is a functional module diagram of a mobile phone user-based passenger flow precision analysis system provided in an embodiment of the present invention;

[0146] Figure 2 In the middle: 100. A precise passenger flow analysis system based on mobile phone users; 101. A data acquisition and processing module; 102. A tourist statistics module; 103. A results display device.

[0147] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0148] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0149] This application provides a method for precise passenger flow analysis based on mobile phone users. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for precise passenger flow analysis based on mobile phone users can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0150] Example 1:

[0151] S1: Collect user trajectory data within the scenic area and preprocess it to obtain preprocessed user trajectory data.

[0152] The user trajectory data collected in step S1 within the scenic area includes:

[0153] Collect user trajectory data within the scenic area:

[0154] e= { e n =( e n 1 , e n 2 ,..., e n i ,..., e n num n |n∈[1,N]} ;

[0155] in:

[0156] This represents the user trajectory sequence of the nth user within the scenic area;

[0157] Represents user trajectory sequence middle A sequence of mobile phone signaling data, among which Represents user trajectory sequence The i-th mobile signaling data in the middle, Represents user trajectory sequence The total number of mobile phone signaling data is provided by the mobile operator in this embodiment of the invention.

[0158] e n i = ( dis n i , time n i ),i ∈ [1, num n ] , Indicates mobile phone signaling data Distance information in the middle, Indicates mobile phone signaling data The time of generation, including distance information For the nth user's mobile phone at time The distance between the mobile phone and the three base stations within the scenic area; in this embodiment of the invention, if the mobile phone communicates with the base stations within the scenic area, mobile phone signaling data is generated;

[0159] The user trajectory data e is preprocessed to obtain preprocessed user trajectory data.

[0160] The user trajectory data is preprocessed to obtain preprocessed user trajectory data, including:

[0161] Preprocess the user trajectory data e, where user trajectory data e contains user trajectory sequences. The preprocessing procedure is as follows:

[0162] S11: Obtain the coordinates of three base stations A, B, and C within the scenic area:

[0163] ;

[0164] in:

[0165] The coordinates of three base stations A, B, and C within the scenic area are shown in that order. Let A, B, and C be the coordinates of the three base stations in the east-west direction. Let A, B, and C be the coordinates of the three base stations in the north-south direction, with the center of the scenic area as the origin.

[0166] S12: Extract distance information from mobile phone signaling data, construct a system of equations corresponding to the location coordinates based on base station coordinates, solve the system of equations to obtain the location coordinates corresponding to any mobile phone signaling data; where mobile phone signaling data The corresponding positioning coordinates are , These represent the coordinates in the east-west and north-south directions, respectively; the distance information... The system of equations corresponding to the positioning coordinates is as follows:

[0167] ;

[0168] ;

[0169] in:

[0170] These represent the times of the mobile phone held by the nth user. Distances between the scenic area and three base stations A, B, and C;

[0171] Representing distance information The corresponding location coordinates, that is, the nth user at time The positioning coordinates;

[0172] S13: Construct a user positioning coordinate sequence from all the positioning coordinates. :

[0173]

[0174] S14: Calculate the user's location coordinate sequence Abnormal index Among them, the abnormal index The calculation formula is:

[0175] ;

[0176] ;

[0177] in:

[0178] This represents a preset distance threshold between adjacent positioning coordinates;

[0179] Represents positioning coordinates The distance between them;

[0180] S15: If the abnormal index If the value exceeds the preset abnormal threshold, it indicates a user location coordinate sequence. There is a significant positioning error in the user's positioning coordinate sequence. and user trajectory sequences Perform cleaning treatment;

[0181] Otherwise, it constitutes a user trajectory sequence. Preprocessing results :

[0182] ;

[0183] ;

[0184] in:

[0185] Indicates mobile phone signaling data The processing results;

[0186] Preprocessing results This is the g-th preprocessed user trajectory sequence in the preprocessed user trajectory data E, where g represents the number of the current preprocessed user trajectory sequences, and the initial value of g is 1.

[0187] All preprocessed user trajectory sequences constitute preprocessed user trajectory data. :

[0188] E={ E m =( E m 1 , E m 2 ,..., E m i ,..., E m num m |m∈[1,M]} ;

[0189] ;

[0190] in:

[0191] M represents the total number of preprocessed user trajectory sequences. This represents the preprocessed user trajectory sequence of the m-th group. Represents user trajectory sequence The processing result of the i-th mobile signaling data. Represents user trajectory sequence The total number of processing results for mobile phone signaling data.

[0192] S2: Match the preprocessed user trajectory data with the road network data within the scenic area to obtain the user's actual road network trajectory data.

[0193] In step S2, the preprocessed user trajectory data is matched with the road network data within the scenic area to obtain the user's actual road network trajectory data, including:

[0194] The preprocessed user trajectory data is matched with the road network data within the scenic area to obtain the user's actual road network trajectory data, where the m-th preprocessed user trajectory sequence is... The path matching process is as follows:

[0195] S21: Constructing road network data within the scenic area ,in G represents the set of vertex coordinates of road turning points or road intersections within the scenic area. G represents the set of roads within the scenic area. Roads include the starting point, the ending point, and the intermediate point of the road. The coordinates of the starting point, the ending point, and the intermediate point of the road all belong to the set of vertex coordinates.

[0196] S22: Data from the road network within the scenic area Extract user trajectory sequences from the roads. The set of candidate roads with arbitrary location coordinates, where the location coordinates are... The candidate road extraction method is as follows:

[0197] Using positioning coordinates Construct a circular region with center R and radius R, and use the roads contained within or intersecting within the circular region as positioning coordinates. Candidate roads; the resulting positioning coordinates The candidate road set is , Q m i = { Q m i (j)|j∈[1,J]} , Represents the set of candidate roads The j-th candidate road in the set, where J represents the set of candidate roads. Total number of candidate roads;

[0198] S23: Calculate the road direction of any candidate road in the candidate road set; where the candidate roads The road direction is:

[0199] ;

[0200] in:

[0201] Indicate candidate roads The direction of the road;

[0202] Indicate candidate roads The coordinates of the road's endpoint;

[0203] Indicate candidate roads The coordinates of the starting point of the road;

[0204] S24: Combining the road directions of the candidate roads, calculate the probability of any candidate road being used as the actual road network trajectory; where the candidate roads... As positioning coordinates The trajectory probability of the associated actual road network trajectory is:

[0205] ;

[0206] ;

[0207] ;

[0208] ;

[0209] ;

[0210] in:

[0211] Indicate candidate roads As positioning coordinates The trajectory probability of the associated actual road network trajectory;

[0212] Represents an exponential function with the natural constant as its base;

[0213] Represents positioning coordinates The distance between them;

[0214] Represents positioning coordinates The coordinate values ​​in the middle;

[0215] Indicates the location coordinates Projected onto candidate roads The projection distance;

[0216] Indicates probability control parameters;

[0217] Indicate candidate roads The similarity of the road trajectory directions; Indicate candidate roads Road projection distance similarity; Indicate candidate roads The actual road network trajectory transfer probability, i.e., the positioning coordinates The road between them was moved to the candidate road. The probability of;

[0218] S25: Select the candidate road with the highest trajectory probability as... The actual road network trajectory corresponding to the mid-position coordinates; constitutes the user trajectory sequence. Corresponding actual user road network trajectory:

[0219] ;

[0220] in:

[0221] Represents user trajectory sequence Mid-position coordinates The corresponding actual road network trajectory, and As actual road network trajectory The trajectory time.

[0222] S3: Identify tourist trajectory data from the user's actual road network trajectory data, and perform time-segmented statistics on tourist trajectory data according to scenic area, to obtain the tourist number statistics for different scenic areas at different times.

[0223] The tourist trajectory data identified from the user's actual road network trajectory data in step S3 includes:

[0224] Tourist trajectory data is obtained by identifying actual user road network trajectory data. The process for identifying tourist trajectory data is as follows:

[0225] S31: Calculate the trajectory length of the user's actual road network trajectory; where the user's actual road network trajectory The trajectory length is:

[0226] ;

[0227] in:

[0228] Indicates the user's actual road network trajectory The length of the trajectory;

[0229] Represents the actual road network trajectory The length of the road;

[0230] S32: Calculate the trajectory time of the user's actual road network trajectory; where the user's actual road network trajectory The trajectory time is:

[0231] ;

[0232] in:

[0233] Indicates the user's actual road network trajectory The trajectory time;

[0234] S33: Calculate the area of ​​the smallest bounding rectangle containing the user's actual road network trajectory, and use this area as the scenic area coverage of the user's actual road network trajectory; where the user's actual road network trajectory... The coverage of scenic spots is ;

[0235] S34: Calculate the probability coefficient that the user's actual road network trajectory is the tourist trajectory, where the user's actual road network trajectory The probability coefficient of the tourist trajectory is :

[0236] ;

[0237] in:

[0238] Represents an exponential function with the natural constant as its base;

[0239] If the probability coefficient is greater than the preset probability threshold, the user's actual road network trajectory will be marked as a tourist trajectory, and all tourist trajectories will constitute tourist trajectory data.

[0240] Tourist trajectory data is statistically analyzed by region and time period to obtain the tourist number statistics for different regions at different times.

[0241] The process of statistically analyzing tourist trajectory data by time period according to scenic area to obtain tourist number statistics for different scenic areas at different times includes:

[0242] The scenic area is divided into K scenic landscape areas. Based on several tourist trajectories in the tourist trajectory data, if the actual road network trajectory in a tourist trajectory belongs to the t-th time period and overlaps with the k-th scenic landscape area, then this tourist trajectory increases the number of tourists in the k-th scenic landscape area by one in the t-th time period. Thus, the number of tourists in each scenic landscape area at different time periods is calculated, where the number of tourists in the k-th scenic landscape area in the t-th time period is... , t ∈[1,24] Each time slot lasts for 1 hour. k ∈[1,K] .

[0243] S4: Min the tourist trajectory patterns within the scenic area using tourist trajectory data to obtain the tourist popularity value of the scenic area.

[0244] Step S4 involves mining tourist trajectory patterns within the scenic area from the tourist trajectory data, including:

[0245] Tourist trajectory pattern mining is performed on tourist trajectory data within the scenic area to obtain tourist popularity values ​​for different scenic areas. The process of tourist trajectory pattern mining within the scenic area is as follows:

[0246] S41: Extract the vertex coordinate sequence of the tourist trajectory from the tourist trajectory data, and extract the trajectory time corresponding to the actual road network trajectory with the vertex coordinate as the road starting point in the tourist trajectory to form a trajectory time series;

[0247] S42: According to the trajectory time associated with the vertex coordinates, if the trajectory time belongs to the t-th time period, then the vertex coordinates are assigned to the t-th time period, resulting in a set of vertex coordinates for 24 time periods;

[0248] S43: Calculate the density information of K scenic areas at any given time period; where the density information of the kth scenic area at the tth time period is:

[0249] ;

[0250] in:

[0251] This represents the density information of the k-th scenic area in the t-th time period;

[0252] This represents the density information of the k-th scenic area.

[0253] Let Y represent the set of Y vertices in the set of vertex coordinates for the t-th time period that are closest to the k-th scenic area. c represents the set of coordinates The coordinates of any vertex in the array;

[0254] This represents the density control parameter; in this embodiment of the invention, it will be... Set to 2;

[0255] S44: Convert density information into visitor popularity values ​​for scenic areas at any given time period, where the visitor popularity value for the k-th scenic area at the t-th time period is:

[0256] ;

[0257] in:

[0258] This represents the visitor popularity value of the k-th scenic area during the t-th time period.

[0259] S5: Construct a visitor flow optimization model, use the visitor flow optimization model to calculate the seasonal influencing factors of the scenic area and the activity factors of the scenic area, combine the visitor popularity value to optimize and adjust the visitor number statistics, and convert the optimized and adjusted visitor number statistics into statistical charts for display.

[0260] Step S5 involves constructing a visitor flow optimization model, using this model to calculate seasonal influencing factors and activity factors within the scenic area, and optimizing the visitor number statistics based on visitor popularity values. This includes:

[0261] A visitor flow optimization model is constructed, which calculates seasonal influencing factors and scenic area activity factors. The model takes the visitor popularity value of the scenic area, seasonal influencing factors, scenic area activity factors, and visitor number statistics as inputs, and outputs the optimized visitor number statistics. The optimization process for the visitor number statistics is as follows:

[0262] S51: The seasonal influencing factors of different scenic areas are calculated using the passenger flow optimization model; the seasonal influencing factor of the kth scenic area is:

[0263] ;

[0264] in:

[0265] This represents the seasonal influencing factor of the k-th scenic area.

[0266] This represents the average number of visitors to the k-th scenic area during the current season; This represents the average number of tourists visiting the k-th scenic area across all seasons; in this embodiment of the invention, the seasonality factor is calculated using unoptimized tourist number statistics.

[0267] This represents the average number of visitors to the entire scenic area during the current season.

[0268] S52: The visitor flow optimization model calculates the scenic activity factors for different scenic areas; where the scenic activity factor for the kth scenic area is:

[0269] ;

[0270] in:

[0271] This represents the activity factor of the k-th scenic area in the t-th time period. A binary variable representing whether the k-th scenic area holds a special event in the t-th time period. , This indicates that no special event was held in the k-th scenic area during the t-th time period. This indicates that a special event will be held in the k-th scenic area during the t-th time period;

[0272] S53: Using the tourist popularity value, seasonality factor, scenic area activity factor, and tourist number statistics of the scenic area as inputs, calculate the optimized tourist number statistics, where the optimized tourist number of the k-th scenic area in the t-th time period is... :

[0273] S k t = s k t [ (1+ γ k 2 (t) ) H k t h 2 ] γ k 1 h 1 ;

[0274] in:

[0275] The parameters representing the seasonal influencing factors and the scenic area activity factors are respectively:

[0276] The optimized and adjusted tourist number statistics will be converted into statistical charts for display, and the results will be submitted to relevant personnel such as scenic area managers. The statistical charts include bar charts of tourist numbers in different scenic areas over 24 time periods, as well as year-on-year and month-on-month change rates, and pie charts of total tourist numbers in different scenic areas, as well as year-on-year and month-on-month change rates.

[0277] Example 2:

[0278] like Figure 2 The diagram shown is a functional block diagram of a mobile phone user-based passenger flow precision analysis system 100 provided in an embodiment of the present invention, which can implement the mobile phone user-based passenger flow precision analysis method in embodiment 1.

[0279] Depending on the functions implemented, the mobile phone user-based precise passenger flow analysis system may include a data acquisition and processing module 101, a tourist statistics module 102, and a result display device 103. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and perform a fixed function.

[0280] The data acquisition and processing module 101 is used to collect user trajectory data of users in the scenic area and perform preprocessing to obtain preprocessed user trajectory data.

[0281] The tourist statistics module 102 is used to match the preprocessed user trajectory data with the road network data in the scenic area to obtain the actual road network trajectory data of the user, identify the tourist trajectory data from the actual road network trajectory data of the user, and perform time-segmented statistics on the tourist trajectory data according to the scenic area to obtain the tourist number statistics results of different scenic areas at different times.

[0282] The results display device 103 is used to mine tourist trajectory patterns within the scenic area from tourist trajectory data, obtain tourist popularity values ​​for scenic areas, calculate seasonal influencing factors and scenic activity factors for scenic areas using a visitor flow optimization model, and optimize and adjust the tourist number statistics based on the tourist popularity values.

[0283] In detail, the modules in the mobile phone user-based precise passenger flow analysis system 100 described in this embodiment of the invention employ the same methods as described above. Figure 1 The method used is the same as the precise passenger flow analysis method based on mobile phone users described above, and it can produce the same technical effect, so it will not be repeated here.

[0284] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0285] It should be noted that the sequence numbers of the above embodiments of the present invention are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0286] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0287] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for precise analysis of passenger flow based on mobile phone users, characterized in that, The method comprises: S1: collecting user trajectory data of users in the scenic area and preprocessing to obtain preprocessed user trajectory data; S2: path matching the preprocessed user trajectory data with road network data in the scenic area to obtain user actual road network trajectory data; wherein the m-th group of pre-processed user trajectory sequences The path matching procedure is as follows: S21: constructing the road network data in the scenic area wherein the vertex coordinate set representing the inflection point or the intersection point of the road in the scenic area, G represents the road set in the scenic area, the road including the road start point, the road end point and the road intermediate point, wherein the coordinates of the road start point, the road end point and the road intermediate point all belong to the vertex coordinate set; S22: Extracting a candidate road set of any positioning coordinates in the user trajectory sequence from the road in the scenic spot road network data S23: Extracting a candidate road set of any positioning coordinates in the user trajectory sequence from the road in the scenic spot road network data S24: Extracting a candidate road set of any positioning coordinates in the user trajectory sequence from the road in the scenic spot road network data The candidate road extraction manner is as follows: The positioning coordinates are constructed by taking the center of the circle as the positioning coordinates and the radius R as the radius of the circle The candidate roads included in or intersecting the circular area are taken as the positioning coordinates The candidate road set constructed by the positioning coordinates is , , The jth candidate road in the candidate road set is represented by , and J represents the total number of candidate roads in the candidate road set . S23: calculating the road direction of any candidate road in the candidate road set; S24: combining the road direction of the candidate road, calculating the trajectory probability of any candidate road as the actual road network trajectory; S25: select the candidate road with the highest trajectory probability as The actual road network trajectory corresponding to the positioning coordinate S3: identifying the tourist trajectory data from the user actual road network trajectory data, and performing time period statistics on the tourist trajectory data according to the scenic landscape area to obtain the tourist number statistical result of different scenic landscape areas in different time periods; The identification process of the tourist trajectory data is as follows: S31: calculating the trajectory length of the user actual road network trajectory; S32: calculating the trajectory time of the user actual road network trajectory; S33: calculate the area of the minimum circumscribed rectangle containing the actual road network trajectory of the user as the scenic coverage degree of the actual road network trajectory of the user; wherein the scenic coverage degree of the actual road network trajectory of the user is . ; S34: calculating the probability coefficient of the user actual road network trajectory being a tourist trajectory; If the probability coefficient is greater than a preset probability threshold, the user actual road network trajectory is marked as a tourist trajectory, and all tourist trajectories constitute the tourist trajectory data; The tourist trajectory data is subjected to time period statistics according to the area to obtain the tourist number statistical result of different areas in different time periods; S4: performing scenic tourist trajectory pattern mining on the tourist trajectory data to obtain the tourist heat value of the scenic landscape area; S5: constructing a passenger flow optimization model, calculating the seasonal influence factor and the scenic activity factor of the scenic landscape area by using the passenger flow optimization model, optimizing and adjusting the tourist number statistical result in combination with the tourist heat value, and converting the optimized and adjusted tourist number statistical result into a statistical chart for display.

2. The method of claim 1, wherein the method comprises: The S1 step of collecting user trajectory data of users in the scenic area comprises: Collecting user trajectory data e of users in the scenic area: ； Wherein: a user trajectory sequence representing an nth user in the scenic area; denotes a sequence of user trajectories in a sequence of mobile phone signaling data, wherein denotes a sequence of user trajectories the i-th mobile phone signaling data in denotes a sequence of user trajectories the total number of mobile phone signaling data in , represents the distance information in the mobile phone signaling data , represents the distance information in the mobile phone signaling data generated time, wherein the distance information is the distance between the mobile phone held by the nth user and the three base stations in the scenic area at time ; The user trajectory data e is preprocessed to obtain preprocessed user trajectory data.

3. The method of claim 1, wherein the method comprises: The user trajectory data is preprocessed to obtain preprocessed user trajectory data, which comprises: The user trajectory data e is preprocessed, wherein the preprocessing procedure of the user trajectory sequence in the user trajectory data e is as follows: The preprocessing procedure of the user trajectory sequence in the user trajectory data e is as follows: S11: Obtain the base station coordinates of three base stations A, B, and C in the scenic area ; S12: extract the distance information in the mobile phone signaling data, combine the base station coordinates to construct an equation group corresponding to the positioning coordinates of the distance information, solve the equation group, and obtain the positioning coordinates corresponding to any mobile phone signaling data; wherein the mobile phone signaling data corresponding to the positioning coordinates is ; S13: Forming all positioning coordinates into a user positioning coordinate sequence : ； S14: Calculate the user positioning coordinate sequence abnormal index ; S15: If the anomaly index is higher than a preset anomaly threshold, it indicates that the user positioning coordinate sequence has obvious positioning errors, and the user positioning coordinate sequence and the user trajectory sequence are cleaned up; Otherwise constitutes a user trajectory sequence Preprocessing result : ； ； Wherein: representing the processing results of the mobile phone signaling data representing the processing results of the mobile phone signaling data The pre-processing result is the gth pre-processed user trajectory sequence in the pre-processed user trajectory data E, where g represents the number of the current pre-processed user trajectory sequence, and the initial value of g is 1. constructing pre-processed user trajectory data from all pre-processed user trajectory sequences : ； ； Wherein: M represents the total number of preprocessed user trajectory sequences, represents the mth preprocessed user trajectory sequence, represents the user trajectory sequence the processing result of the ith mobile phone signaling data in the user trajectory sequence, represents the user trajectory sequence the total number of processing results of mobile phone signaling data in the user trajectory sequence.

4. The method of claim 1, wherein the method comprises: The tourist trajectory data is subjected to time period statistics according to the scenic landscape area to obtain the tourist number statistical result of different scenic landscape areas in different time periods, which comprises: The scenic area is divided into K scenic landscape regions, according to a plurality of tourist trajectories in the tourist trajectory data, if the trajectory time of the actual road network trajectory in the tourist trajectory belongs to the t th time period, and the actual road network trajectory and the k th scenic landscape region exist overlap, then the tourist trajectory makes the number of tourists of the k th scenic landscape region in the t th time period plus one; thereby the number of tourists of each scenic landscape region in different time periods is calculated, wherein the number of tourists of the k th scenic landscape region in the t th time period is , , the time length of each time period is 1 hour, .

5. The method of claim 4, wherein the method comprises: The step S4 of performing scenic tourist trajectory pattern mining on the tourist trajectory data comprises: The scenic tourist trajectory pattern mining process of the tourist trajectory data is as follows: S41: extracting the vertex coordinate sequence of the tourist trajectory in the tourist trajectory data, extracting the trajectory time corresponding to the actual road network trajectory with the vertex coordinate as the road starting point in the tourist trajectory, and constructing a trajectory time sequence; S42: according to the trajectory time associated with the vertex coordinate, if the trajectory time belongs to the t th time period, the vertex coordinate is divided into the t th time period to obtain 24 time period vertex coordinate sets; S43: calculate the density information of the K scenic spot landscape regions in any period; wherein the density information of the kth scenic spot landscape region in the tth period is ; S44: converting the density information into the tourist heat value of the scenic landscape area in any time period, wherein the tourist heat value of the k th scenic landscape area in the t th time period is: ； Wherein: represents the tourist heat value of the kth scenic spot landscape region in the tth time period.

6. The method of claim 1, wherein the method comprises: The S5 step constructs a passenger flow optimization model. The passenger flow optimization model is used to calculate a seasonal influence factor of the scenic landscape area and a scenic activity factor. The passenger flow optimization model is combined with the tourist heat value to optimize and adjust the passenger number statistical result, including: The passenger flow optimization model is constructed. The passenger flow optimization model calculates a seasonal influence factor and a scenic activity factor. The scenic landscape area tourist heat value, the seasonal influence factor, the scenic activity factor, and the passenger number statistical result are input. The optimized and adjusted passenger number statistical result is output. The optimization and adjustment process of the passenger number statistical result is as follows: S51: The passenger flow optimization model calculates a seasonal influence factor of different scenic landscape areas. The seasonal influence factor of the kth scenic landscape area is as follows: ； Wherein: a seasonal influence factor representing the kth scenic area landscape region; represents the average number of visitors of the kth scenic spot landscape area in the current season; represents the average number of visitors of the kth scenic spot landscape area in all seasons; represents the average number of visitors in the entire scenic area in the current season; S52: The passenger flow optimization model calculates a scenic activity factor of different scenic landscape areas. The scenic activity factor of the kth scenic landscape area is as follows: ； Wherein: Yktrepresents the scenic activity factor of the kth scenic landscape area in the tth time period, Yktrepresents the binary variable of whether the kth scenic landscape area holds special activities in the tth time period, , Yktrepresents that the kth scenic landscape area does not hold special activities in the tth time period, Yktrepresents that the kth scenic landscape area holds special activities in the tth time period; S53: taking the tourist heat value of the scenic landscape area, the seasonal influence factor, the scenic activity factor and the tourist number statistical result as inputs, calculating to obtain the optimized and adjusted tourist number statistical result, wherein the optimized and adjusted tourist number of the kth scenic landscape area in the tth time period is : ； Wherein: denotes the factor regulation parameter of seasonal influence factor and scenic activity factor in turn; The optimized and adjusted passenger number statistical result is converted into a statistical chart for display. The statistical chart includes a column chart of the passenger number of different scenic landscape areas in 24 time periods and a same period and a period change rate. A pie chart of the total passenger number of different scenic landscape areas and a same period and a period change rate.

7. A passenger flow precision analysis system based on mobile phone users, characterized in that, The system includes: A data acquisition and processing module that acquires and pre-processes user trajectory data of users in the scenic area to obtain pre-processed user trajectory data; A tourist statistical module that matches the pre-processed user trajectory data with road network data in the scenic area to obtain actual road network trajectory data of users. The tourist trajectory data is identified from the actual road network trajectory data of users. The tourist trajectory data is statistically divided by time period according to scenic landscape areas to obtain passenger number statistical results of different scenic landscape areas in different time periods; A result display device that mines tourist trajectory patterns in the scenic area based on the tourist trajectory data to obtain a scenic landscape area tourist heat value. A passenger flow optimization model is used to calculate a seasonal influence factor of the scenic landscape area and a scenic activity factor. The passenger flow optimization model is combined with the tourist heat value to optimize and adjust the passenger number statistical result. The optimized and adjusted passenger number statistical result is converted into a statistical chart for display. The method realizes a passenger flow precision analysis method based on mobile phone users according to any one of claims 1-6.

Images