Method and system for analyzing travel habits of key passengers based on multi-dimensional space-time characteristics

Abstract

The present application relates to the technical field of intelligent supervision and data analysis, in particular to a method and system for analyzing the passing habits of key passengers based on multi-dimensional space-time characteristics; the method comprises: obtaining the passing records, inspection records and seizure records of key passengers; obtaining the scheduling table data of each port inspection department; receiving the analysis parameters set by the user, including the statistical date interval, statistical time period, port, shift, key passenger type and concentration threshold; performing multi-dimensional cross statistics on the passing data of key passengers from the time dimension, port dimension and shift dimension to obtain the passing data distribution statistical result; performing correlation analysis on the inspection records, seizure records and passing data to identify the passing rules of irregular passengers; identifying the key passengers with high concentration and their concentrated time range according to the concentration threshold, generating a concentration analysis report and outputting, the present application solves the technical problems of single analysis dimension and inability to fully capture the differentiated behavior patterns of passengers in the prior art.

Description

Technical Field

[0001] This invention relates to the field of intelligent supervision and data analysis technology, and in particular to a method and system for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics. Background Technology

[0002] In port passenger management, key passengers refer to those who have been placed on a key monitoring list due to repeated violations, the discovery of prohibited items, or other risky behaviors. Continuous tracking and analysis of the travel behavior of key passengers is a crucial aspect of port risk prevention and control. In-depth analysis of key passenger travel data can reveal their travel patterns and anomalies, providing a basis for precise deployment and inspection decisions.

[0003] Existing technologies have the following technical problems when analyzing the travel habits of key passengers:

[0004] Existing technologies primarily focus on passenger clearance frequency, such as counting the number of times a passenger enters or leaves the country within a certain period. They lack comprehensive statistics on multi-dimensional spatiotemporal characteristics, including the distribution of travel time, ports of entry, and flight schedules. Different passengers' travel habits may manifest in different ways; some passengers prefer to travel during specific times, some concentrate their activities at specific ports, and some are associated with specific flight schedules. Single-dimensional statistics cannot fully capture these differentiated behavioral patterns.

[0005] In addition, the port passenger inspection work implements a shift rotation system, and there are differences in the allocation of regulatory resources and inspection intensity among different shifts. Some key passengers may take advantage of shift handover or weak links in the supervision of specific shifts to pass through customs. However, the existing technology cannot correlate passenger passage time with departmental shift schedule data for analysis, and cannot identify whether key passengers are concentrated in specific shift types. Summary of the Invention

[0006] The purpose of this invention is to propose a method and system for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics, thereby solving at least one of the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] The first aspect of this invention proposes a method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics, comprising the following steps:

[0009] Obtain the travel records, inspection records, and seizure records of key passengers;

[0010] Obtain the shift schedule data of the passenger inspection departments at each port;

[0011] The system receives user-defined analysis parameters, including statistical date range, statistical time period, port of entry, flight number, key passenger type, and concentration threshold.

[0012] Based on the analysis parameters, multidimensional cross-statistics are performed on the passage data of the key passengers from the dimensions of time, port, and flight to obtain the statistical results of passage data distribution.

[0013] The inspection records and seizure records are correlated with the passage data to identify the passage patterns of passengers who violate regulations.

[0014] Based on the concentration threshold, identify key passengers with high concentration and their concentrated time range, generate a concentration analysis report and output it.

[0015] A further improvement lies in the specific method for performing multi-dimensional cross-statistics on the travel data of key passengers from the dimensions of time, port, and flight number, which includes:

[0016] The number of passages for each key passenger group was counted by hour, day, week, and month to obtain time-dimension distribution data.

[0017] Statistics were compiled on the number of times and percentage of key passengers passed through each port to obtain port-level distribution data.

[0018] Based on the schedule data, the travel time of each key passenger is matched to the corresponding train, and the number of times and percentage of each key passenger travels under each train type are counted to obtain the train-specific distribution data.

[0019] A further improvement is that the specific method for matching the travel time of each key passenger to the corresponding train / bus based on the schedule data includes:

[0020] For the passage time in each passage record, find the shift to which that time belongs in the schedule data;

[0021] When the passage time falls between the start and end time of a certain shift, the passage record is marked as that shift type;

[0022] When the passage time falls within the shift change period, a shift change marker is simultaneously displayed.

[0023] A further improvement lies in the method of correlating and analyzing the inspection records and seizure records with passage data to identify the passage patterns of violating passengers, including:

[0024] The inspection records and passage records of key passengers are linked according to passenger identification and time sequence to generate a time series containing passage time and inspection results;

[0025] Based on the aforementioned time series statistics, the number of inspections, seizures, and smuggling transfers for each key passenger were recorded.

[0026] Based on the statistically obtained number of inspections, seizures, and smuggling transfers, the travel distribution characteristics of key passengers with abnormal inspection results are identified in terms of time, port, and flight number dimensions, and these travel distribution characteristics are used as the travel patterns of passengers violating regulations.

[0027] A further improvement is that the concentration threshold includes a time interval and a frequency threshold; the specific method for identifying key passengers with high concentration and their concentrated time range based on the concentration threshold includes: according to the statistical results of the passage data distribution, counting the passage frequency of each key passenger within the time interval; when the passage frequency of a key passenger within the time interval reaches or exceeds the frequency threshold, identifying the key passenger as a key passenger with high concentration, and recording the time range of the key passenger's concentrated passage.

[0028] A further improvement is that the concentration threshold also includes a proportion threshold; the specific method for identifying key passengers with high concentration and their concentrated time range based on the concentration threshold further includes: calculating the proportion of each key passenger's passage frequency within the time interval to their total passage frequency, and when the proportion reaches or exceeds the proportion threshold, identifying the key passenger as a key passenger with high concentration.

[0029] A further improvement is that the method also includes: when a high concentration of key passengers is identified, a concentration warning prompt is generated and pushed to the regulatory end; the concentration warning prompt includes at least the passenger identifier, the time range of concentrated passage, and the concentration index value.

[0030] A further improvement is that the method also includes: generating a travel habit profile for each key passenger based on the statistical results of the travel data distribution and the travel patterns of the violating passengers; the travel habit profile includes at least travel time preference, port preference, flight preference and inspection result correlation features.

[0031] A further improvement is that the method further includes: calculating a risk score for each key passenger based on the travel habit profile; the risk score is calculated by weighting at least three dimensions: abnormality of travel frequency, concentration of time period, concentration of flight number, abnormality rate of inspection, and records of discovery; when the risk score exceeds a preset risk threshold, the corresponding key passenger is marked as a high-risk passenger.

[0032] The second aspect of this invention proposes a method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics, comprising:

[0033] The data acquisition module is used to acquire the passage records, inspection records, and seizure records of key passengers, as well as the shift schedule data of the passenger inspection departments at various ports;

[0034] The parameter configuration module is used to receive analysis parameters set by the user. The analysis parameters include statistical date interval, statistical time period, port, flight number, key passenger type and concentration threshold.

[0035] The statistics module is used to perform multi-dimensional cross-statistics on the passage data of the key passengers from the dimensions of time, port, and flight number, based on the analysis parameters, to obtain the statistical results of the passage data distribution.

[0036] The correlation analysis module is used to perform correlation analysis between the inspection records and the seizure records and the passage data to identify the passage patterns of passengers who violate regulations;

[0037] The concentration analysis module is used to identify key passengers with high concentration and their concentrated time range based on the concentration threshold, generate a concentration analysis report and output it.

[0038] The beneficial effects of this invention are as follows:

[0039] This invention receives user-defined analysis parameters and performs multi-dimensional cross-statistics on the travel data of key passengers from the dimensions of time, port, and flight, achieving a comprehensive analysis of the travel habits of key passengers. This solves the technical problem of existing technologies having a single analysis dimension and being unable to fully capture the differentiated behavioral patterns of passengers.

[0040] This invention obtains the schedule data of passenger inspection departments at various ports, matches the passage time of key passengers to the corresponding shifts, obtains the passage distribution of key passengers under each shift type, realizes the correlation analysis between passage behavior and duty arrangement, and can identify whether key passengers have a concentrated passage phenomenon under a specific shift type. This solves the technical problem that existing technologies cannot detect behaviors that use duty patterns to evade supervision.

[0041] This invention automatically identifies the travel distribution characteristics of violators in terms of time, port, and flight by performing correlation analysis between inspection records, seizure records, and passage data, and uncovers the travel patterns of violators. This solves the technical problem of lacking correlation analysis between passage records and inspection records and being unable to extract risk features from historical inspection data. Attached Figure Description

[0042] Figure 1 This is a flowchart of a method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics, according to the present invention.

[0043] Figure 2The flowchart illustrates a method for performing multidimensional cross-statistics on the travel data of key passengers from the perspectives of time, port of entry, and flight frequency, based on the aforementioned analysis parameters.

[0044] Figure 3 This is an architecture diagram of a key passenger travel habit analysis system based on multi-dimensional spatiotemporal features, according to the present invention. Detailed Implementation

[0045] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. The described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0046] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0047] Please refer to the attached document. Figure 1 The first aspect of this invention proposes a method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics, which is applied to a port passenger data management platform. The platform is connected to multiple data sources such as the travel pass system, the key passenger database, the inspection management system, and the scheduling management system.

[0048] The system comprises several components: the Passenger Clearance System, a port passenger clearance information management system that records passenger travel time, port of entry, and direction of travel; the Key Passenger Database, a database maintaining a list of high-risk passengers and records of seized items and violations, with key passengers being those listed for priority monitoring due to repeated violations, seizure of prohibited items, or other risky behavior; the Inspection Management System, a business system recording the passenger inspection process and results, including inspection time, results, seizures, and anti-smuggling transfer results; and the Scheduling Management System, a duty scheduling management system for port passenger inspection departments, recording shift times, shift types, and other scheduling data for each department.

[0049] The method includes the following steps:

[0050] Step S1: Obtain the passage records, inspection records, and seizure records of key passengers.

[0051] Step S2: Obtain the shift schedule data of the passenger inspection departments at each port.

[0052] Step S3: Receive the analysis parameters set by the user. The analysis parameters include the statistical date range, statistical time period, port, flight number, key passenger type and concentration threshold.

[0053] Step S4: Based on the analysis parameters, perform multidimensional cross-statistics on the passage data of the key passengers from the dimensions of time, port, and flight to obtain the passage data distribution statistics results.

[0054] Step S5: Perform correlation analysis between the inspection records and the seizure records and the passage data to identify the passage patterns of passengers who violate regulations.

[0055] Step S6: Identify key passengers with high concentration and their concentrated time range based on the concentration threshold, generate a concentration analysis report and output it.

[0056] The method steps of the present invention will be described in detail below:

[0057] Specifically, in step S1, the passage records, inspection records, and seizure records of key passengers are obtained. The passage records originate from the travel information system, and each record includes at least the passenger identifier, passage time, port of entry / exit, and direction of entry / exit. The passenger identifier is a unique identifier assigned to each passenger by the system, used to link the data of the same passenger across different data sources. The inspection records originate from the inspection management system, and each record includes at least the inspection time and inspection result, which includes two types: normal release and abnormal handling. The seizure records originate from the inspection management system, and each record includes at least the seizure time, type of item, and handling result.

[0058] Understandably, obtaining passage records, inspection records, and seizure records is the data foundation for analyzing the travel habits of key passengers. Specifically, passage records provide spatiotemporal information about passenger clearance, serving as core data for analyzing passage distribution; while inspection records and seizure records provide information on passenger violations, key data for identifying patterns of illegal passage.

[0059] Specifically, in step S2, the shift schedule data of each port passenger inspection department is obtained. The shift schedule data comes from the port passenger inspection department's shift management system, and each shift record includes at least the department identifier, shift time, and shift type. The shift types include morning shift, afternoon shift, evening shift, and shift handover, and different types of shifts correspond to different working time periods.

[0060] Understandably, schedule data is the foundation for analyzing the shift dimensions. By matching passenger travel times with schedule data, it is possible to identify whether passenger travel behavior is associated with a specific shift type.

[0061] Specifically, in step S3, the analysis parameters set by the user are received. The analysis parameters include the statistical date range, statistical time period, port of entry, flight number, key passenger type, and concentration threshold; these parameters are customized by the user through the settings interface.

[0062] The statistical date range specifies the time frame for analysis, allowing users to set specific start and end dates, such as "May 1, 2026 to May 31, 2026". The statistical time period specifies the time granularity of the analysis, such as by hour, day, week, or month. The port of entry specifies the range of ports to be analyzed; users can select a single port or a combination of ports. The flight schedule specifies the flight type to be analyzed; users can select morning, afternoon, evening, or all flights. The key passenger type specifies the key passenger category to be analyzed; users can filter based on risk level or other classification criteria. The concentration threshold is used for subsequent concentration identification, including parameters such as time range, frequency threshold, and percentage threshold.

[0063] Understandably, since the time range and statistical granularity required to be focused on vary in different regulatory scenarios, fixed parameters cannot meet the needs of all scenarios. Giving users the right to configure parameters can flexibly adapt to diverse business needs.

[0064] Specifically, in step S4, based on the analysis parameters, the passage data of the key passengers are subjected to multi-dimensional cross-statistics from the time dimension, port dimension, and flight number dimension to obtain the passage data distribution statistics results.

[0065] like Figure 2 As shown, the specific method for performing multi-dimensional cross-statistics on the travel data of key passengers from the dimensions of time, port, and flight number includes:

[0066] Step S41: Count the number of passages of each key passenger in terms of hour, day, week and month to obtain the time dimension distribution data.

[0067] Specifically, the hourly statistics on the number of trips for key passengers are as follows: the analysis period is divided into 24 hourly time slots. For each key passenger, the number of trips within each hourly time slot is counted, generating 24-hour travel distribution data. This hourly statistics are used to identify passenger travel preferences. For example, if 80% of a passenger's travel records are concentrated between 22:00 and 06:00 the next day, it indicates that the passenger prefers nighttime travel.

[0068] The daily statistics on the number of trips for key passengers are as follows: The analysis period is divided into multiple days, and for each key passenger, the number of trips on each day is counted to generate daily travel distribution data. Understandably, the daily statistics are used to identify passenger preferences for travel dates. For example, if a passenger's trips are concentrated on Fridays and Saturdays, it indicates a weekend travel pattern.

[0069] The weekly statistics on the number of passages for key passengers are as follows: The analysis period is divided into multiple natural weeks. For each key passenger, the number of passages in each week is counted to generate weekly passage distribution data. It can be understood that weekly statistics are used to identify weekly passage patterns of passengers. For example, if a passenger's passage frequency suddenly increases in a certain week, it indicates an abnormal change in their passage behavior during that week.

[0070] The monthly statistics on the number of passages for key passengers are as follows: the analysis period is divided into multiple natural months, and for each key passenger, the number of passages in each month is counted to generate monthly passage distribution data. Understandably, monthly statistics are used to identify monthly passage trends for passengers. For example, if a passenger's passage frequency shows an increasing trend month by month, it indicates that their activity frequency is continuously increasing.

[0071] Step S42: Calculate the number of times and percentage of key passengers passing through each port to obtain port-level distribution data.

[0072] Specifically, the entire travel record of each key passenger is traversed, the number of times they pass through each port is counted, and the proportion of the number of times they pass through each port to the total number of times they pass through is calculated. It can be understood that step S42 is used to identify the ports of passage preferred by passengers. For example, if 90% of a passenger's travel records are concentrated at port A, it indicates that they mainly operate at port A.

[0073] Step S43: Match the travel time of each key passenger to the corresponding train or bus based on the schedule data, and count the number of times and percentage of each key passenger travels under each train or bus type to obtain the train or bus dimension distribution data.

[0074] Specifically, the method for matching the travel time of each key passenger to the corresponding bus or train based on the schedule data is as follows:

[0075] For each passage record, the passage time is searched in the schedule data to find the shift to which that time belongs.

[0076] When the passage time falls between the start and end time of a certain shift, the passage record is marked as that shift type.

[0077] When the passage time falls within the shift change period, a shift change marker is simultaneously displayed.

[0078] It should be understood that the shift handover period refers to the time between the morning shift and the afternoon shift, and between the afternoon shift and the evening shift, which is usually 15 to 30 minutes. The shift types include morning shift, afternoon shift, evening shift, and shift handover.

[0079] This invention utilizes multidimensional cross-statistics to comprehensively characterize the travel characteristics of key passengers from different perspectives. These different dimensions reflect various aspects of passenger behavior: the time dimension reveals temporal patterns of travel, the port dimension reveals spatial distribution of travel, and the flight / bus dimension reveals the correlation between travel and operational arrangements. By synthesizing the statistical results from these three dimensions, a comprehensive understanding of passenger travel behavior can be obtained.

[0080] Specifically, in step S5, the method for correlating and analyzing the inspection records and the seizure records with the passage data to identify the passage patterns of violating passengers includes:

[0081] Step S51: Associate the inspection records and passage records of each key passenger according to passenger identification and time sequence to generate a time series including passage time and inspection results.

[0082] Specifically, using the passenger identifier as the association key, for each key passenger, all their inspection records and passage records are arranged in chronological order to generate a time series including passage time and inspection results. The time series reflects whether the passenger was inspected each time they passed through and the inspection results.

[0083] Step S52: Based on the time series, count the number of inspections, seizures, and smuggling transfers of each key passenger.

[0084] Specifically, the analysis counts the total number of times the passenger was inspected, the total number of times prohibited items were seized, and the total number of times the passenger was transferred to the anti-smuggling department for suspected illegal activities during the analysis period.

[0085] Step S53: Based on the statistically obtained number of inspections, number of seizures, and number of cases transferred for smuggling, identify the travel distribution characteristics of key passengers with abnormal inspection results in terms of time, port, and flight number dimensions.

[0086] Specifically, passage records with abnormal inspection results (such as seizures or transfers for smuggling) are extracted separately, and their distribution across hourly, daily, weekly, port, and flight dimensions is statistically analyzed to identify their distributional differences relative to normal passage. For example, if 80% of a passenger's abnormal passage records are concentrated at night, 70% at Port A, and 60% on evening flights, while the passenger's normal passage records are more evenly distributed across time periods, ports, and flights, these characteristics are identified as the passenger's violation pattern, i.e., "nighttime, Port A, evening flights" are the main spatiotemporal characteristics of their violation.

[0087] Understandably, through the above correlation analysis, the passage patterns of passengers who violate regulations can be automatically extracted from historical inspection data, providing a reference for subsequent risk identification.

[0088] Specifically, in step S6, the concentration threshold includes a time interval and a frequency threshold. The specific method for identifying high-concentration key passengers and their concentrated time ranges based on the concentration threshold includes:

[0089] Based on the statistical results of the passage data distribution, the passage frequency of each key passenger within the specified time interval is calculated. The time interval is an analysis window set by the user, such as "the last 7 days" or "June 1, 2026 to June 7, 2026". For each key passenger, the total number of passages within this time interval is calculated.

[0090] When the frequency of passage of a key passenger within the time interval reaches or exceeds the frequency threshold, the key passenger is identified as a key passenger with high concentration, and the time range of concentrated passage of the key passenger is recorded.

[0091] For example, if a frequency threshold of 5 times is set and the time range is the most recent 7 days, and a key passenger passes through 8 times in the most recent 7 days, exceeding the frequency threshold, the passenger will be identified as a key passenger with high concentration, and the time range of their concentrated passage will be recorded.

[0092] In a preferred embodiment of the present invention, the concentration threshold further includes a proportion threshold. The specific method for identifying high-concentration key passengers and their concentrated time ranges based on the concentration threshold further includes: calculating the proportion of each key passenger's passage frequency within the time interval to their total passage frequency; when the proportion reaches or exceeds the proportion threshold, the key passenger is identified as a high-concentration key passenger.

[0093] For example, a threshold of 50% is set, with the time range being the most recent 7 days. A key passenger has traveled 3 times in the most recent 7 days. This passenger's total number of travels within the analysis period is 4. The number of travels in the most recent 7 days accounts for 75% of the total number of travels, exceeding the threshold. Therefore, this passenger is identified as a key passenger with high concentration.

[0094] Understandably, relying solely on frequency thresholds may miss passengers who pass through in small numbers but in concentrated periods of time. However, by introducing a percentage threshold, it is possible to capture both types of anomalies: high absolute frequency and high relative concentration.

[0095] In a preferred embodiment of the present invention, the method further includes: when a high concentration of key passengers is identified, generating a concentration warning and pushing it to the regulatory end, so that regulatory personnel can be aware of the abnormal passage of key passengers as soon as possible and promptly deploy targeted inspection measures. The concentration warning includes at least a passenger identifier, a time range of concentrated passage, and a concentration index value, wherein the concentration index value is the frequency or percentage of passage of the passenger within the time range.

[0096] In a preferred embodiment of the present invention, the method further includes: generating a travel habit profile for each key passenger based on the statistical results of the travel data distribution and the travel patterns of the violating passengers. The travel habit profile includes at least travel time preference, port preference, flight preference, and features related to inspection results.

[0097] Specifically, the travel time preference is generated based on hourly travel distribution data, such as "preferring nighttime travel (22:00-06:00, accounting for 80%)". The port preference is generated based on port-level travel distribution data, such as "preferring Port A (accounting for 90%)". The shift preference is generated based on shift-level travel distribution data, such as "preferring evening shifts (accounting for 70%)". The inspection result correlation characteristics are generated based on the correlation analysis results of step S5, such as "abnormal travel is concentrated in nighttime hours and evening shifts".

[0098] Understandably, travel habit profiles are structured descriptions of the travel behavior of key passengers, integrating scattered statistical data and correlation analysis results into a set of passenger behavior characteristics that can be intuitively understood by regulators.

[0099] In a preferred embodiment of the present invention, the method further includes: calculating a risk score for each key passenger based on the travel habit profile, wherein the risk score is calculated by weighting at least three dimensions: abnormality of travel frequency, concentration of time period, concentration of flight number, abnormality rate of inspection, and records of discovery.

[0100] Specifically, the calculation methods for each dimension are as follows:

[0101] The frequency anomaly score reflects whether the frequency of passage for key passengers during the analysis period is significantly higher than their historical normal level or the average level of passengers at the same port. The specific calculation method is as follows: For each key passenger, calculate their average daily passage frequency during the analysis period, and their average daily passage frequency during the same historical period (e.g., the same period last year or the same period last quarter). Divide the current average daily passage frequency by the historical average daily passage frequency to obtain the frequency change ratio; alternatively, compare the passenger's average daily passage frequency during the analysis period with the average average daily passage frequency of all passengers at the same port during the same time period, and calculate the ratio between the two. When the frequency change ratio exceeds the upper limit of the preset normal range, the frequency anomaly score is increased accordingly.

[0102] Time-segment concentration reflects the degree to which the travel time of key passengers is concentrated throughout the day. The specific calculation method is as follows: the day is divided into 24 time periods by hour, the number of times each key passenger travels in each time period is counted, and the proportion of the number of times traveled in each time period to the total number of times traveled is calculated; information entropy or concentration index is used to measure the degree of concentration of time-segment distribution. The higher the concentration, the more concentrated the passenger's travel behavior is in a specific time period.

[0103] Flight frequency concentration reflects whether the passage of key passengers is concentrated under a specific flight frequency type. The specific calculation method is as follows: based on the flight frequency dimension distribution data obtained in step S4, the percentage of passage times of each key passenger under each flight frequency type is counted, and the degree of concentration of flight frequency distribution is calculated. For example, the proportion of the flight with the highest percentage is used as the flight frequency concentration index.

[0104] The inspection anomaly rate reflects the proportion of key passengers whose inspection results are abnormal. The specific calculation method is as follows: divide the number of inspections of key passengers with abnormal results (such as being seized or transferred by anti-smuggling authorities) by the total number of inspections to obtain the inspection anomaly rate.

[0105] The seizure record dimension reflects whether key passengers have a history of being found with prohibited items and the severity of the seizures. The specific calculation method is as follows: based on the key passengers' historical seizure records, the number of seizures and the types of items seized are counted, and corresponding risk scores are assigned according to the number of seizures and the risk level of the items. For example, high-risk prohibited items are assigned higher scores, and the more seizures, the higher the score.

[0106] After normalization of each dimension, a weighted sum is calculated according to preset weights to obtain a risk score, ranging from 0 to 100. The specific normalization process is as follows: for each dimension, based on the value distribution of that dimension among all key passengers, a maximum-minimum normalization or percentile ranking method is used to map the original value of that dimension to a normalized score between 0 and 100. For example, for the frequency anomaly dimension, the highest frequency change ratio among all key passengers is taken as the maximum reference value. The frequency change ratio of each passenger is divided by this maximum reference value and then multiplied by 100 to obtain the normalized score. For the time-period concentration dimension, the maximum possible value of the concentration index is used as a reference value for normalization.

[0107] The preset weights for each dimension are configurable parameters. The system provides default weight configurations, such as a weight of 30% for passage frequency anomaly, 20% for time period concentration, 15% for shift concentration, 25% for inspection anomaly rate, and 10% for record retrieval, with the sum of all weights being 100%. In addition, users can adjust the weight values ​​of each dimension through the settings interface according to actual business needs.

[0108] When the risk score exceeds the preset risk threshold, the corresponding key passenger will be marked as a high-risk passenger.

[0109] For example, if the preset risk threshold is 75 points, and a key passenger's normalized scores for abnormal passage frequency are 85, time period concentration is 70, flight frequency concentration is 65, inspection anomaly rate is 80, and record retrieval is 55, then the weighted average score calculated using the default weights is: 85×30%+70×20%+65×15%+80×25%+55×10%=74.75 points. This score does not meet the preset risk threshold and the passenger is not marked as a high-risk passenger. However, if a passenger's normalized scores for each dimension are 95, 85, 80, 90, and 70, the weighted average score is 87 points, exceeding the preset risk threshold, and the passenger is then marked as a high-risk passenger.

[0110] like Figure 3 As shown, the second aspect of this embodiment proposes a key passenger travel habit analysis system based on multi-dimensional spatiotemporal features, which corresponds to the key passenger travel habit analysis method based on multi-dimensional spatiotemporal features provided in the above embodiment of this invention. Since the key passenger travel habit analysis system based on multi-dimensional spatiotemporal features provided in this embodiment corresponds to the key passenger travel habit analysis method based on multi-dimensional spatiotemporal features provided in the above embodiment of this invention, the implementation method of the aforementioned key passenger travel habit analysis method based on multi-dimensional spatiotemporal features is also applicable to the key passenger travel habit analysis system based on multi-dimensional spatiotemporal features provided in this embodiment.

[0111] Specifically, the system includes the following modules:

[0112] The data acquisition module is used to acquire the passage records, inspection records, and seizure records of key passengers, as well as the shift schedule data of the passenger inspection departments at various ports;

[0113] The parameter configuration module is used to receive analysis parameters set by the user. The analysis parameters include statistical date interval, statistical time period, port, flight number, key passenger type and concentration threshold.

[0114] The statistics module is used to perform multi-dimensional cross-statistics on the passage data of the key passengers from the dimensions of time, port, and flight number, based on the analysis parameters, to obtain the statistical results of the passage data distribution.

[0115] The correlation analysis module is used to perform correlation analysis between the inspection records and the seizure records and the passage data to identify the passage patterns of passengers who violate regulations;

[0116] The concentration analysis module is used to identify key passengers with high concentration and their concentrated time range based on the concentration threshold, generate a concentration analysis report and output it.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics, characterized in that, Includes the following steps: Obtain the travel records, inspection records, and seizure records of key passengers; Obtain the shift schedule data of the passenger inspection departments at each port; The system receives user-defined analysis parameters, including statistical date range, statistical time period, port of entry, flight number, key passenger type, and concentration threshold. Based on the analysis parameters, multidimensional cross-statistics are performed on the passage data of the key passengers from the dimensions of time, port, and flight to obtain the statistical results of passage data distribution. The inspection records and seizure records are correlated with the passage data to identify the passage patterns of passengers who violate regulations. Based on the concentration threshold, identify key passengers with high concentration and their concentrated time range, generate a concentration analysis report and output it.

2. The method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics according to claim 1, characterized in that, The specific method for performing multidimensional cross-statistics on the travel data of key passengers from the dimensions of time, port, and flight number includes: The number of passages for each key passenger group was counted by hour, day, week, and month to obtain time-dimension distribution data; Statistics were compiled on the number of times and percentage of key passengers passed through each port to obtain port-level distribution data. Based on the schedule data, the travel time of each key passenger is matched to the corresponding train, and the number of times and percentage of each key passenger travels under each train type are counted to obtain the train-specific distribution data.

3. The method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics according to claim 2, characterized in that, The specific method for matching the travel time of each key passenger to the corresponding train or bus based on the schedule data includes: For the passage time in each passage record, find the shift to which that time belongs in the schedule data; When the passage time falls between the start and end time of a certain shift, the passage record is marked as that shift type; When the passage time falls within the shift change period, a shift change marker is simultaneously displayed.

4. The method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics according to claim 1, characterized in that, The specific methods for identifying the travel patterns of violating passengers by correlating and analyzing the inspection records and seizure records with travel data include: The inspection records and passage records of key passengers are linked according to passenger identification and time sequence to generate a time series containing passage time and inspection results; Based on the aforementioned time series statistics, the number of inspections, seizures, and smuggling transfers for each key passenger were recorded. Based on the statistically obtained number of inspections, seizures, and smuggling transfers, the travel distribution characteristics of key passengers with abnormal inspection results are identified in terms of time, port, and flight number dimensions, and these travel distribution characteristics are used as the travel patterns of passengers violating regulations.

5. The method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics according to claim 1, characterized in that, The concentration threshold includes a time interval and a frequency threshold; the specific method for identifying key passengers with high concentration and their concentrated time range based on the concentration threshold includes: according to the statistical results of the passage data distribution, counting the passage frequency of each key passenger within the time interval; when the passage frequency of a key passenger within the time interval reaches or exceeds the frequency threshold, identifying the key passenger as a key passenger with high concentration, and recording the time range of the key passenger's concentrated passage.

6. The method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics according to claim 5, characterized in that, The concentration threshold also includes a proportion threshold; the specific method for identifying key passengers with high concentration and their concentrated time range based on the concentration threshold further includes: calculating the proportion of each key passenger's passage frequency within the time interval to their total passage frequency, and when the proportion reaches or exceeds the proportion threshold, identifying the key passenger as a key passenger with high concentration.

7. A method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics according to any one of claims 1-6, characterized in that, The method further includes: when identifying key passengers with high concentration, generating a concentration warning and pushing it to the regulatory end; the concentration warning includes at least the passenger identifier, the time range of concentrated passage, and the concentration index value.

8. A method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics according to any one of claims 1-6, characterized in that, The method further includes: generating a travel habit profile for each key passenger based on the statistical results of the travel data distribution and the travel patterns of the violating passengers; the travel habit profile includes at least travel time preference, port preference, flight preference and inspection result correlation features.

9. The method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics according to claim 8, characterized in that, The method further includes: calculating a risk score for each key passenger based on the travel habit profile; the risk score is calculated by weighting at least three dimensions, including abnormality in travel frequency, concentration in time period, concentration in flight frequency, abnormality rate in inspection, and records of discovery; when the risk score exceeds a preset risk threshold, the corresponding key passenger is marked as a high-risk passenger.

10. A method for analyzing the travel habits of key passengers based on multi-dimensional spatiotemporal characteristics, characterized in that, include: The data acquisition module is used to acquire the passage records, inspection records, and seizure records of key passengers, as well as the shift schedule data of the passenger inspection departments at various ports; The parameter configuration module is used to receive analysis parameters set by the user. The analysis parameters include statistical date interval, statistical time period, port, flight number, key passenger type and concentration threshold. The statistics module is used to perform multi-dimensional cross-statistics on the passage data of the key passengers from the dimensions of time, port, and flight number, based on the analysis parameters, to obtain the statistical results of the passage data distribution. The correlation analysis module is used to perform correlation analysis between the inspection records and the seizure records and the passage data to identify the passage patterns of passengers who violate regulations; The concentration analysis module is used to identify key passengers with high concentration and their concentrated time range based on the concentration threshold, generate a concentration analysis report and output it.

Images