A method and system for measuring global passenger flow based on mobile signaling data

Abstract

This invention relates to a method and system for calculating overall passenger flow based on mobile signaling data. The method includes: using a preset dynamic weighting model and mobile signaling data to obtain the permanent residence identification result for each user; identifying and classifying all users to obtain overall passenger identification and classification results; filtering the overall passenger identification and classification results for transit passengers based on a preset minimum stay duration calculation model for cities to obtain a first overall passenger result; identifying and eliminating atypical tourists from the first overall passenger result based on a preset special user group identification model to obtain a second overall passenger result; expanding the second overall passenger result based on the market share of the target operator to generate overall passenger flow analysis results. By introducing a dynamic weighting model to identify permanent residence and identifying and filtering transit passengers and atypical tourists, the method achieves accurate elimination of non-tourism behaviors, improving the purity and accuracy of tourism passenger flow statistics.

Description

Technical Field

[0001] This invention belongs to the field of data analysis and data mining technology, and in particular relates to a method and system for calculating the overall passenger flow based on mobile signaling data. Background Technology

[0002] With the rapid development of the social economy and the improvement of residents' living standards, the tourism industry has become an important pillar of the national economy. Accurate, real-time, and comprehensive passenger flow and tourism statistics are of irreplaceable value for optimizing the allocation of tourism resources, planning public service facilities, making decisions on regional economic development, and managing emergencies. According to the current definition of the tourism industry, tourists are generally defined as people who leave their usual place of residence, travel a distance of more than 10 kilometers, spend more than 6 hours on the trip, and whose purpose of travel is not to obtain remuneration.

[0003] Traditional methods of visitor flow statistics, such as scenic spot ticket gate systems, fixed-point manual questionnaire surveys, and hotel check-in registration, have many inherent flaws. Not only are they costly and require huge manpower, but more importantly, their data coverage is limited to specific physical spaces (e.g., scenic spots and hotels), failing to capture the complete movement trajectory of tourists across the entire area, resulting in a serious "information silo" effect.

[0004] In recent years, with the popularization of mobile communication technology, using signaling big data from mobile terminals for passenger flow analysis has become a promising emerging technology path. Mobile signaling data can record users' spatiotemporal locations at low cost and high frequency, naturally possessing advantages such as full coverage, real-time continuity, and huge sample size, providing a possibility for breaking through the bottlenecks of traditional statistical methods. However, current passenger flow identification technology based on mobile signaling is still in its early stages of development. Existing technical solutions have significant shortcomings in the rigor of identification logic and the ability to handle complex scenarios, resulting in a significant reduction in the accuracy and scientific validity of statistical results. A common problem with existing technical solutions is that their identification models are relatively crude, mostly relying on single-dimensional static rules or fixed thresholds for judgment. For example, some methods simply distinguish between residents and tourists based on the length of time users stay in a certain area. This "one-size-fits-all" association rule-based classification does not strictly follow the core definitions of "habitual environment" and "travel purpose" in the definition of tourism, and is prone to misjudgment.

[0005] A more serious challenge lies in the extreme complexity of real-world population flows. Various non-tourism travel behaviors exhibit highly similar spatiotemporal characteristics to tourism behaviors, and existing technologies lack effective identification and filtering mechanisms, resulting in severe "noise" contamination of statistical data. The shortcomings of existing technologies are concentrated in the following aspects:

[0006] Misjudgment of "passenger flow": Many passengers on long-distance intercity trips may only stop briefly in a certain city. Their spatiotemporal trajectories may meet simple tourist identification rules, making it difficult to effectively identify and exclude "passing" behavior. This exaggerates the number of tourists passing through the cities and causes passenger flow data to be inflated.

[0007] Confusion of large-scale "student mobility": During specific periods such as winter and summer vacations, large-scale student migrations back to their hometowns or schools often match the basic definition of tourists in terms of travel distance and duration. Due to a lack of effective identification of student groups, they are often misjudged as tourist traffic, leading to abnormal fluctuations and distortions in the number of tourists at specific time points.

[0008] Interference from highly mobile "professional behavior": With the rise of the platform economy, the mobility patterns of new business practitioners such as ride-hailing drivers, food delivery riders, and chauffeur drivers are characterized by high frequency, wide range, and long time periods. It is impossible to effectively distinguish between professional mobility and real leisure tourism behavior, thus incorrectly including a large number of professional trajectories in tourist statistics.

[0009] In summary, existing technologies for passenger flow calculation using mobile signaling face multiple technical bottlenecks, such as the vague definition of users' "habitual environment" and the lack of accurate identification methods for various typical non-tourism travel scenarios, resulting in inaccurate passenger flow calculations. Summary of the Invention

[0010] To address the aforementioned technical problems, this invention provides a method and system for calculating passenger flow across the entire region based on mobile signaling data.

[0011] The technical solution adopted in this invention is:

[0012] Firstly, a method for calculating overall passenger flow based on mobile signaling data is provided, including:

[0013] Obtain mobile signaling data from multiple users within the target province, and use a preset dynamic weighting model and mobile signaling data to obtain the permanent residence identification result for each user;

[0014] Using a pre-set global passenger identification and classification model and the results of permanent residence identification, all users are identified and classified to obtain the global passenger identification and classification results.

[0015] Based on the preset minimum stay duration calculation model for cities, the results of the identification and classification of passengers across the entire region are filtered for transit passengers to obtain the first result of passengers across the entire region.

[0016] Based on a pre-set special user group identification model, atypical tourists are identified and eliminated from the first overall passenger results to obtain the second overall passenger results.

[0017] Based on the market share of the target operator, the second-level all-for-one tourism results are expanded and calculated to generate all-for-one passenger flow analysis results.

[0018] Furthermore, the expression for the preset dynamic weighted model is:

[0019] ;

[0020] in, This represents the score of user A's permanent presence at a specific base station B on day t. This represents the duration of user A's stay at a specific base station B on day t. Represents the normalized baseline total duration; These are preset normalization coefficients; This represents the historical score that user A has accumulated at a specific base station B on day t-1. This is the preset time decay factor.

[0021] Furthermore, mobile signaling data from multiple users within the target province is acquired, and a preset dynamic weighted model is used to obtain the permanent residence identification result for each user based on the mobile signaling data, including:

[0022] Acquire mobile signaling data from multiple users within a target province;

[0023] Based on mobile signaling data, obtain the historical dwell data of all users at different base stations under the target operator;

[0024] The current dwell time of different users at different base stations on the same day is obtained based on historical dwell data;

[0025] Input the current dwell time into the preset dynamic weighted model to calculate the dwell score of different users on different base stations;

[0026] The resident score is compared with the preset resident determination threshold to identify the resident base station of each user, and the resident base station is used as the resident location identification result.

[0027] Furthermore, the pre-defined overall tourist identification and classification model includes sub-models for determining tourists from within and outside the province, as well as sub-models for classifying overnight and day-trip tourists.

[0028] Using a pre-defined global passenger identification and classification model and the results of permanent residence identification, all users are identified and classified to obtain global passenger identification and classification results, including:

[0029] Based on the sub-model for determining tourists from within and outside the province and the results of the permanent residence identification, tourists from within and outside the province are identified.

[0030] Based on the classification sub-models for overnight and day-trip tourists and the results of permanent residence identification, overnight and day-trip tourists among tourists from within and outside the province are identified, resulting in the overall tourist identification and classification results.

[0031] Furthermore, based on the sub-model for determining tourists from within and outside the province and the results of the permanent residence identification, tourists from within and outside the province are identified, including:

[0032] Based on the sub-model for determining tourists from within and outside the province and the results of permanent residence identification, users without permanent base stations in the target province are identified as candidates from outside the province, and users with permanent base stations are identified as users from within the province.

[0033] Determine whether the first cumulative travel time of the candidate user from outside the province within the target province is not less than a preset time threshold; if the first cumulative travel time is not less than the preset time threshold, then determine that the candidate user from outside the province is a tourist from outside the province; if the first cumulative travel time is less than the preset time threshold, then determine that the candidate user from outside the province is not a tourist.

[0034] Determine whether the travel distance of users within the province is not less than a preset spatial distance threshold, and whether the second cumulative travel time is not less than a preset duration threshold. The travel distance is the straight-line spatial distance of users within the province from their permanent base station, and the second cumulative travel time is the cumulative duration during which the travel distance of users within the province is not less than the preset spatial distance threshold.

[0035] If the travel distance is not less than the preset spatial distance threshold and the second cumulative travel time is not less than the preset time threshold, then the user within the province is determined to be a tourist within the province.

[0036] If the travel distance is less than the preset spatial distance threshold and / or the second cumulative travel time is less than the preset time threshold, then users within the province are determined to be non-tourists.

[0037] Furthermore, based on the classification sub-models for overnight and day-trip tourists and the results of permanent residence identification, overnight and day-trip tourists among tourists from within and outside the province are identified, resulting in the overall tourist identification and classification results, including:

[0038] Based on the classification sub-models of overnight and day-trip tourists and the results of permanent residence identification, the first cumulative stay time of tourists from outside the province in the tourist destination area within the target province within the preset nighttime time window, and the second cumulative stay time of tourists from within the province at the nighttime base station within the preset nighttime time window are obtained.

[0039] Determine whether the first cumulative stay duration of out-of-province tourists is not less than the preset nighttime stay duration threshold;

[0040] If the first cumulative stay is not less than the preset overnight stay threshold, then tourists from outside the province are determined to be overnight tourists from outside the province.

[0041] If the first cumulative stay of tourists from outside the province is less than the preset overnight stay threshold, then the tourists from outside the province are determined to be day-trip tourists from outside the province.

[0042] Determine whether the second cumulative stay duration of tourists within the province is not less than the preset nighttime stay duration threshold, and whether the straight-line spatial distance between the nighttime base station and any permanent base station is not less than the preset spatial distance threshold.

[0043] If the second cumulative stay duration is not less than the preset nighttime stay duration threshold, and the straight-line spatial distance between the nighttime base station and any permanent base station is not less than the preset spatial distance threshold, then the tourist within the province is determined to be an overnight tourist within the province.

[0044] If the second cumulative dwell time is less than the preset nighttime dwell time threshold and / or the straight-line spatial distance between the nighttime dwell base station and any permanent base station is less than the preset spatial distance threshold, then the tourist within the province is determined to be a one-day tourist within the province.

[0045] Based on the determination results of overnight tourists and day-trip tourists corresponding to tourists from outside the province and tourists from within the province, the identification and classification results of tourists across the entire region are obtained.

[0046] Furthermore, based on the preset minimum stay duration calculation model for prefecture-level cities, the passenger identification and classification results for the entire region are filtered for transit passengers to obtain the first passenger result for the entire region, including:

[0047] Based on the results of the overall tourist identification and classification, the intra-provincial travel trajectory of each tourist among multiple cities in the target province is determined;

[0048] Identify intermediate cities that serve as transit points or short-term stops from the travel routes within the province, and collect data on the length of stay in these intermediate cities.

[0049] Visual analysis of dwell time data was performed to verify whether it exhibited a bimodal distribution statistical characteristic. In the bimodal distribution statistical characteristic, one peak corresponds to the short-term dwell time of transit passengers, and the other peak corresponds to the longer-term dwell time of non-transit passengers.

[0050] Using statistical or machine learning algorithms, we automatically find and determine the critical point that best segments the bimodal distribution statistical features, and use the duration value corresponding to the critical point as the minimum dwell time threshold for intermediate cities.

[0051] The minimum stay time calculation model of the pre-set city is used to filter the transit passengers of each city in the whole area passenger identification and classification results, and the first whole area passenger results are obtained.

[0052] Furthermore, the pre-defined special user group identification model includes a campus student identification sub-model and a professional user identification sub-model.

[0053] Based on a pre-defined special user group identification model, atypical tourists are identified and eliminated from the first overall passenger data to obtain the second overall passenger data, including:

[0054] The permanent base station locations of each tourist in the first global passenger results are matched with the pre-set list of geographical information of university base stations in the province; tourists whose permanent base station locations are in the pre-set list of geographical information of university base stations in the province are identified as potential students; real-name age information, campus-exclusive communication package application information and DPI data of potential students are obtained, and the student identity of potential students is cross-verified in multiple dimensions to identify the campus student group.

[0055] Obtain the average daily usage time and monthly active days of occupational applications for each tourist in the first global passenger results, and mark those whose average daily usage time and monthly active days both reach the corresponding thresholds as occupational users; determine whether the travel trajectory of occupational users meets the spatiotemporal conditions of passengers. If it does, they are determined to be occupational user passengers; if it does not, they are determined to be occupational user non-passengers.

[0056] By removing campus students and non-professional travelers from the first overall traveler results, we obtain the second overall traveler results.

[0057] Secondly, a system for calculating the overall passenger flow based on mobile signaling data is provided, including:

[0058] The permanent residence identification module is used to obtain mobile signaling data of multiple users within the target province, and uses a preset dynamic weighting model and mobile signaling data to obtain the permanent residence identification result of each user;

[0059] The whole-domain passenger identification and classification module is used to identify and classify all users using a preset whole-domain passenger identification and classification model and the permanent residence identification results, and to obtain the whole-domain passenger identification and classification results.

[0060] The transit passenger filtering module is used to filter transit passengers based on the preset city minimum stay duration calculation model to obtain the first overall passenger result.

[0061] The atypical passenger identification module is used to identify and remove atypical tourists from the first overall passenger results based on a preset special user group identification model, so as to obtain the second overall passenger results.

[0062] The expansion calculation module is used to expand the second-level all-area tourism results based on the market share of the target operator and statistically generate all-area passenger flow analysis results.

[0063] The beneficial effects achieved by this invention are as follows:

[0064] The system acquires mobile signaling data from multiple users within the target province. A pre-defined dynamic weighting model and the mobile signaling data are used to identify the permanent residence of each user. A pre-defined province-wide passenger identification and classification model, along with the permanent residence identification results, are used to identify and classify all users, resulting in province-wide passenger identification and classification results. Based on a pre-defined minimum stay duration calculation model for each city, the province-wide passenger identification and classification results are filtered for transit passengers, yielding the first province-wide passenger result. Based on a pre-defined special user group identification model, the first province-wide passenger result is used to identify and remove atypical tourists, yielding the second province-wide passenger result. The second province-wide tourism result is then expanded based on the target operator's market share, generating a province-wide passenger flow analysis result. By introducing a dynamic weighting model to identify permanent residence and identifying and filtering transit passengers and atypical tourists, the system achieves precise removal of non-tourism behaviors, improving the purity and accuracy of tourism passenger flow statistics. Attached Figure Description

[0065] Figure 1 This is a flowchart of the method for calculating the overall passenger flow based on mobile signaling data according to the present invention;

[0066] Figure 2 This is a structural diagram of the system for calculating passenger flow across the entire region based on mobile signaling data, as per the present invention. Detailed Implementation

[0067] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0068] like Figure 1 As shown, this embodiment of the invention provides a method for calculating the overall passenger flow based on mobile signaling data, including:

[0069] 101. Obtain mobile signaling data of multiple users within the target province, and use a preset dynamic weighting model and mobile signaling data to obtain the permanent residence identification result of each user;

[0070] In this embodiment, the core data is the mobile signaling data of all users in the target province and the target operator, which includes key information such as the user's anonymized ID, the latitude and longitude of the connected base station, and timestamps. This data forms the basis for constructing the user's high-precision spatiotemporal trajectory. Based on the mobile signaling data, the historical dwell time data of all users at different base stations under the target operator is obtained. By analyzing the historical dwell time data, the current dwell time of different users at different base stations on the same day can be obtained. Combined with the latitude and longitude of the connected base station, the activity trajectory of each user can be determined.

[0071] The auxiliary data includes a list of university base stations, DPI data, number segment dimension table and IMSI country code, and real-name registration table;

[0072] University Base Station List: A list that accurately marks the geographical locations of base stations within universities across the province (such as teaching buildings, dormitories, libraries, and canteens), serving as a key geofencing basis for the campus student identification sub-model;

[0073] DPI data: Deep Packet Inspection data, which can record users' usage behavior of specific applications (APPs), such as usage duration, active periods, and specific function pages visited. It is a powerful tool for accurately identifying professional users (such as driver-side APPs) and assisting in verifying student identities (such as learning APPs).

[0074] Number segment dimension table and IMSI country code: The number segment dimension table stores the precise mapping relationship between the first 7 digits of a mobile phone number and its province of origin; the country code in the IMSI (International Mobile Subscriber Identity) ("460" for domestic users) is used to directly and efficiently distinguish between domestic and overseas users. Together, they provide an authoritative basis for determining the origin of tourists from outside the province and overseas.

[0075] Real-name registration table: It links the user's age, account opening location and other de-identified information registered with the operator, which provides important support for age filtering (e.g., 17-28 years old) and cross-validation of permanent residence determination for campus student models;

[0076] Since raw signaling data inevitably contains various types of noise, if it is not effectively processed, it will seriously affect the accuracy of subsequent trajectory analysis and behavior recognition. Therefore, data preprocessing is also required. The specific steps include:

[0077] (a) Basic cleaning: Delete records with missing key fields (such as user ID, timestamp, base station location), and efficiently deduplicate duplicate records generated continuously by the same user at the same base station without location changes;

[0078] (ii) Drift data filtering: Identify and remove "drift points" caused by abnormal base station signals or inter-regional handover delays. Drift points are manifested in the data as users undergoing long-distance displacements that are geographically impossible in a very short period of time (i.e., instantaneous speeds far exceeding the physical limits of normal transportation). By setting dynamic speed and distance dual thresholds, such severely distorted erroneous data can be effectively filtered.

[0079] (III) Ping-Pong Handover Data Elimination: Ping-pong handover refers to the short-term, high-frequency, back-and-forth handover between two or more adjacent base station signal coverage areas when a user is in order to maintain the best communication quality. This phenomenon generates a large number of false movement trajectory points. The elimination algorithm is as follows:

[0080] Set a fine-grained time window threshold (e.g., 30 seconds or 1 minute) to detect local trajectory sequences;

[0081] Within this time window, detect whether there is a sequence pattern (such as ABA or ABCA) in which a reference base station is repeatedly accessed.

[0082] If such a ping-pong sequence is detected, an equivalent geographic center location is calculated using a dwell time-weighted average method. This single, closer equivalent location to the user's actual dwell center is then used to replace the entire ping-pong sequence. The formula for calculating its equivalent latitude and longitude is as follows:

[0083] ;

[0084] ;

[0085] In the formula, This represents the longitude-weighted average. This represents the latitude-weighted average. Refers to the first The dwell time of each signaling point It is the first The longitude of each signaling point It is the first The latitude of each signaling point;

[0086] The preset dynamic weighted model aims to accurately and dynamically identify users' "habitual environment" (i.e., permanent residence), thereby effectively distinguishing local residents from visitors. It is the basis for all subsequent analyses. Its core is the innovative dynamic weighted scoring algorithm for permanent base stations. Unlike traditional methods that only statically count the frequency or duration of occurrence, this algorithm introduces a time decay mechanism, giving the model the ability to dynamically adapt to changes in user behavior patterns.

[0087] The default expression for the dynamic weighted model is:

[0088] ;

[0089] in, This represents the score of user A's permanent presence at a specific base station B on day t. This represents the duration of user A's stay at a specific base station B on day t. This represents the normalized baseline total duration, for example, the nighttime period from 0:00 to 6:00. It is 6 hours, used to normalize the daily residency contribution; This is a preset normalization coefficient used to adjust the weight of the influence of the dwell time on the total score. It is generally set to 0.8 by default. This represents the historical score that user A has accumulated at a specific base station B on day t-1. As a preset time decay factor, The existence of this ensures that historical scores decay exponentially over time, meaning that recent behaviors (such as yesterday's stay) have a higher weight than distant behaviors (such as a stay a month ago). This allows the model to update its permanent residence judgment more quickly when users change their lifestyle (such as moving or changing workplaces), effectively avoiding the excessive influence of historical "old" data and greatly improving the model's sensitivity and realism.

[0090] The resident score is compared with the preset resident determination threshold to identify the resident base station of each user, and the resident base station is used as the resident location identification result.

[0091] The determination of permanent residence mainly falls into three categories:

[0092] Residence determination: Select the user's mobile signaling data for the most recent 45 days, specifically analyze the trajectory during the nighttime rest period from 0:00 to 6:00 every day, and use the expression of a preset dynamic weighted model to iteratively calculate the resident score of each base station that appears; for residence, the preset resident determination threshold is the residence threshold; for workplace, the preset resident determination threshold is the workplace threshold; generally, the residence is where the user's trajectory is most concentrated, so the residence threshold should be greater than the workplace threshold; if the resident score of a base station exceeds the residence threshold (e.g., 300 points), then the base station with the highest score among all base stations whose resident scores exceed the residence threshold is determined to be the user's resident base station;

[0093] Work location determination: Similarly, select the mobile signaling data of the most recent 45 days and analyze the typical work time trajectory from 9:00 to 11:00 and from 14:00 to 17:00 every day. If the permanent score of a certain base station exceeds the work location threshold (e.g., 200 points), the base station with the highest score is determined as the user's permanent work location base station.

[0094] Third permanent residence determination: In order to more comprehensively depict the user's "habitual environment", in addition to the determination of the permanent residence of the workplace and residence, further analyze the user's trajectory on weekends and statutory holidays, and find other regular activity locations (such as parents' home, couple's residence, etc.) with high scores and geographical distances greater than 10 kilometers from the former two, in addition to the residence and workplace, as the user's third permanent residence base.

[0095] The determination results of the above residential permanent base stations, workplace permanent base stations and third permanent base stations are integrated to form the permanent location identification result for each user.

[0096] Since passenger flow calculation targets all users within the current target province, users who have only recently appeared in the target province have very little or no historical data on their stay within the target province, making it impossible for them to have permanent base stations.

[0097] 102. Using a pre-set global passenger identification and classification model and the results of permanent residence identification, all users are identified and classified to obtain global passenger identification and classification results.

[0098] In this embodiment, the preset global passenger identification and classification model includes a sub-model for determining tourists from within and outside the province, and a sub-model for classifying overnight and day-trip tourists.

[0099] The process for determining whether a tourist is from within or outside the province is as follows:

[0100] Based on the sub-model for determining tourists from within and outside the province and the results of permanent residence identification, users without permanent base stations in the target province are identified as candidates from outside the province, while users with permanent base stations are identified as users from within the province; this is the first hurdle to distinguish between local residents and tourists from other places.

[0101] The system determines whether the first cumulative travel time of out-of-province candidate users within the target province is not less than a preset time threshold (specifically set to 6 hours). The first cumulative travel time is calculated by summing the current dwell time of out-of-province candidate users at different base stations within the target province on the same day. If the first cumulative travel time is not less than the preset time threshold, the out-of-province candidate user is determined to be an out-of-province tourist; if the first cumulative travel time is less than the preset time threshold, the out-of-province candidate user is determined to be a non-tourist. The purpose is to filter out short-term transit or short stays for non-tourism purposes.

[0102] The system determines whether the travel distance of a user within the province is not less than a preset spatial distance threshold and whether the second cumulative travel time is not less than a preset duration threshold. The travel distance is the straight-line spatial distance of the user within the province from the permanent base station, and the second cumulative travel time is the cumulative duration during which the user's travel distance is not less than the preset spatial distance threshold. The preset spatial distance threshold and the preset duration threshold are the spatiotemporal conditions for traveler behavior. For example, if a user leaves the permanent base station for more than 10 kilometers and the time exceeds 6 hours, it is considered tourism.

[0103] If the travel distance is not less than the preset spatial distance threshold and the second cumulative travel time is not less than the preset time threshold, then the user within the province is determined to be a tourist within the province.

[0104] If the travel distance is less than the preset spatial distance threshold and / or the second cumulative travel time is less than the preset time threshold, then users within the province are determined to be non-tourists.

[0105] After distinguishing between in-province and out-of-province users as tourists / non-tourists, the further analysis of in-province and out-of-province tourists, and the process of classifying overnight and day-trip tourists within the target province's tourist destination area, is as follows:

[0106] The sub-model for classifying overnight and day-trip tourists aims to further categorize tourists' stay behavior and provide key data support for in-depth analysis of tourism consumption potential and accommodation demand. The core rule is based on a refined analysis of users' nighttime spatiotemporal behavior and adopts differentiated logic for tourists from within and outside the province.

[0107] Based on the classification sub-models of overnight and day-trip tourists and the results of permanent residence identification, the first cumulative stay duration of tourists from outside the province within the target province during the preset nighttime time window and the second cumulative stay duration of tourists from within the province at the nighttime base station during the preset nighttime time window are obtained.

[0108] The system determines whether the first cumulative stay duration of out-of-province tourists is not less than a preset nighttime stay duration threshold. If the first cumulative stay duration is not less than the preset nighttime stay duration threshold, they are identified as overnight tourists from out of province. If the first cumulative stay duration is less than the preset nighttime stay duration threshold, they are identified as day-trip tourists from out of province. Specifically, since out-of-province tourists naturally meet the requirement of "leaving their usual environment" at a long distance, the determination logic is relatively straightforward: if they have a record of staying for 5 consecutive hours or more in the tourist destination area during the nighttime period (0:00-7:00), they are identified as "overnight tourists"; otherwise, they are identified as "day-trip tourists".

[0109] The system determines whether the second cumulative stay duration of tourists from within the province is not less than a preset nighttime stay duration threshold, and whether the straight-line spatial distance between the nighttime base station and any permanent base station is not less than a preset spatial distance threshold. If the second cumulative stay duration is not less than the preset nighttime stay duration threshold, and the straight-line spatial distance between the nighttime base station and any permanent base station is not less than the preset spatial distance threshold, then the tourist is identified as an overnight tourist from within the province. If the second cumulative stay duration is less than the preset nighttime stay duration threshold and / or the straight-line spatial distance between the nighttime base station and any permanent base station is less than the preset spatial distance threshold, then the tourist is identified as a day-trip tourist from within the province. Specifically, for tourists from within the province, to avoid... Local residents' late-night social and entertainment activities were mistakenly classified as overnight tourism. To address this, stricter dual constraints were imposed. First, the base station where they stayed overnight must be at least 10 kilometers away from all their identified permanent locations (residence, workplace, and third permanent location) to ensure their travel truly deviates from their daily "habitual environment." Second, at these locations meeting the distance requirement, they must also meet the requirement of staying continuously for 5 hours or more overnight. Only when both of these spatiotemporal conditions are met can they be classified as "overnight tourists"; otherwise, they are categorized as "day-trip tourists." This differentiated and rigorous logic significantly improves the accuracy of the classification.

[0110] Based on the determination results of overnight tourists and day-trip tourists from outside the province and within the province, the overall tourist identification and classification results are obtained.

[0111] 103. Based on the preset minimum stay duration calculation model for cities, the results of passenger identification and classification across the entire region are filtered for transit passengers to obtain the first result of passenger identification across the entire region.

[0112] In this embodiment, the preset minimum dwell time calculation model for cities is a core innovative solution proposed to address the industry pain point of misjudging "passenger flow";

[0113] The core idea is to abandon the nationally unified static filtering rules and dynamically calculate a "minimum stay duration" threshold for each city. Tourists whose total stay in a city is less than this threshold are considered passersby rather than real tourists and are therefore excluded. Furthermore, the minimum stay duration threshold is dynamic, generated based on the transportation hub status, tourism resources, and data distribution of different time periods (holidays / weekends / weekdays) of different cities. This allows the method to accurately analyze passenger flow patterns during specific holidays and output the distribution of tourists during that period.

[0114] Based on the results of the overall tourist identification and classification, the intra-provincial travel trajectory of each tourist in multiple cities within the target province was determined;

[0115] Identify intermediate cities that serve as transit points or short-term stops from the tourist routes within the province, and determine the length of stay of tourists in intermediate cities through historical stay data;

[0116] Visual analysis of the dwell time data was performed to verify whether it exhibited a bimodal distribution statistical characteristic. In the bimodal distribution statistical characteristic, one peak corresponds to the short dwell time of passing passengers, and the other peak corresponds to the longer dwell time of non-passing passengers.

[0117] Statistical or machine learning algorithms are used to automatically find and determine the critical point that can best segment the bimodal distribution, and the duration value corresponding to the critical point is used as the minimum dwell time threshold for intermediate cities. There are two methods for calculating the minimum dwell time threshold: ANOVA to maximize the difference between groups and K-Means cluster analysis, which will be explained below.

[0118] The method for maximizing between-group differences in analysis of variance employs a sliding window scanning strategy to find an optimal split point that maximizes the difference between the two groups (transit passengers and multi-city tourists). Specifically, it iterates through all possible duration split points, calculates the sum of squares (SSB) between the groups, and identifies the split point with the largest SSB as the optimal threshold. Its objective function is:

[0119] ;

[0120] in, and The sample size for the two groups before and after the split point. and This represents the mean of the corresponding group.

[0121] K-Means Clustering Analysis Method: This method employs the classic K-Means unsupervised clustering algorithm (setting K=2) to automatically cluster the dwell time data into two classes. The upper boundary of the cluster representing "passing travelers" (with smaller center values) serves as the other candidate threshold. ;

[0122] Threshold fusion: To balance the emphasis of the two methods and enhance the stability of the results, the final minimum stay duration threshold for cities is the average of the two methods. ;

[0123] The minimum stay time calculation model of the pre-set city is used to filter the transit passengers of each city in the whole area passenger identification and classification results, and the first whole area passenger results are obtained.

[0124] 104. Based on the preset special user group identification model, atypical tourists are identified and eliminated from the first overall passenger results to obtain the second overall passenger results.

[0125] In this embodiment, considering the systematic interference caused by the regular large-scale movement of students during holidays such as winter and summer vacations on tourism flow statistics, as well as the difficulty in distinguishing the work behavior and real tourism behavior of highly mobile occupational groups (such as ride-hailing drivers and food delivery riders), a special user group identification model is used to identify and eliminate atypical tourists.

[0126] The pre-defined special user group identification model includes a campus student identification sub-model and a professional user identification sub-model.

[0127] The location of each tourist's permanent base station in the first global passenger results is matched with a pre-set list of geographical information of university base stations in the province; tourists whose permanent base station locations are in the pre-set list of geographical information of university base stations in the province are identified as potential students.

[0128] The system obtains real-name age information, campus-exclusive communication package subscription information, and DPI data of potential students to conduct multi-dimensional cross-verification of their student identities and identify the campus student group. Specifically, it filters users aged 17-28, covering the main age groups of undergraduates, master's students, and doctoral students, excluding faculty, staff, family members, and surrounding residents who do not meet the age requirement. Through operator business data, it accurately identifies users who have subscribed to campus-exclusive packages (such as the M-Zone campus card) or special data discount packages for winter and summer vacations. Through DPI data, it identifies users who frequently use specific learning apps (such as Chaoxing, CNKI, Xuexitong, Yu Classroom, etc.) to corroborate their student identities from a behavioral perspective. It can also add social circle supplementary identification, that is, to recall some students with less obvious characteristics (such as those who have not used campus packages). If a user has frequent communication records with multiple (e.g., ≥3) potential students identified in the previous steps, they are also listed as potential students for further verification.

[0129] Obtain the average daily usage time and monthly active days of occupational apps for each tourist in the first overall tourist results. Using DPI data, label users who use specific occupational apps frequently and intensively as "occupational users". The judgment threshold is dynamic and conforms to industry characteristics. For example, the average daily usage time of the driver / rider app order-taking page is ≥1 hour and the monthly active days are ≥20 days.

[0130] To determine whether the travel trajectory of a professional user meets the spatiotemporal conditions of a passenger, the spatiotemporal conditions are that the passenger is more than 10 kilometers away from the permanent base station and the travel time is more than 6 hours.

[0131] To conduct further verification, it is also necessary to check the usage time of the professional user's professional APP on the day of travel. If the usage time is extremely low (e.g., <1 hour), it can be preliminarily judged that the user may be in a rest or vacation state that day, and there is a possibility of travel.

[0132] The user's length of stay at the destination is compared with the minimum length of stay threshold dynamically calculated for that city. If the length of stay is greater than or equal to the threshold, the user's trip is determined to be a genuine tourist activity and the user is classified as a professional tourist. Otherwise, it is still considered a professional activity or a transit activity and the user is classified as a professional non-tourist.

[0133] It should be noted that the method system of the present invention has a high degree of dynamic adaptability. For example, during major holidays such as Spring Festival and National Day, the thresholds of some models can be automatically or manually adjusted by experts to adapt to abnormal behavior patterns. For example, the usage time threshold of professional APP in the professional user identification sub-model can be appropriately relaxed (from 1 hour to 1.5 hours) to cope with the short-term impact of order fluctuations on drivers' work patterns during holidays and ensure the robustness of the model.

[0134] By removing campus students and non-professional travelers from the first overall traveler results, we obtain the second overall traveler results.

[0135] 105. Based on the market share of the target operator, the second all-for-one tourism results are expanded and calculated to generate all-for-one passenger flow analysis results.

[0136] In this embodiment, to fundamentally solve the problem of inaccurate statistics on tourist origins, a more scientific method of province-specific differentiated sampling is adopted. The specific steps are as follows:

[0137] Data preparation: Obtain the latest authoritative data on the market share of mobile operators in all provinces across the country;

[0138] Provincial Expansion Calculation: For tourist sample sizes from different provinces, instead of using a uniform national market share, the specific market share of each province of origin is used for expansion. The formula for calculating the total number of tourists in province O is as follows:

[0139] ;

[0140] Total National Tourist Volume: By precisely summing the expanded sample results from all provinces, the total tourist volume for the entire region is obtained.

[0141] ;

[0142] in: Index of tourist origin provinces This indicates the mobile market share of province O.

[0143] After the refined processing, identification, filtering, and calculation in steps 101-105 above, a series of rich, in-depth, and highly timely analytical products can be generated at the result output layer. These include not only macro-level statistics on the total number of tourists in the entire region, the composition of tourists from within and outside the province, and the ratio of overnight to day-trip tourists, but also in-depth analytical reports on specific time dimensions based on specific needs. These include: annual tourist analysis reports, monthly passenger flow monitoring reports, holiday-themed analysis reports, and multi-dimensional visualization charts.

[0144] Annual tourist analysis reports provide a macro-level view of annual tourist flow trends and the distribution of hotspots within the province; monthly tourist flow monitoring reports provide data support for monthly marketing and transportation capacity allocation; holiday-themed analysis reports accurately output the distribution of tourist origins and destinations for specific holidays, providing decision-making basis for holiday tourism management and emergency response; multi-dimensional visualization charts, including but not limited to city-level tourist flow heat maps and charts showing the proportion of students and professionals among tourists, provide intuitive and multi-dimensional decision support for cultural and tourism management departments and related industries.

[0145] The beneficial effects achieved by the embodiments of the present invention are as follows:

[0146] By introducing a dynamic weighted scoring model with time decay to identify permanent residences, it is more scientific and sensitive than the traditional static frequency statistics method. It can adapt to changes in user behavior. For various typical noise scenarios such as passing passenger flow, student flow, and professional behavior, a special filtering model with multi-dimensional feature fusion has been constructed to achieve accurate elimination of non-tourism behavior, fundamentally improving the purity and accuracy of tourism passenger flow statistics.

[0147] It can not only identify tourists, but also create multi-dimensional profiles of them, such as accurately distinguishing between tourists from within and outside the province, overnight / day trips, and effectively identifying genuine tourism behavior from special groups such as students and professional drivers;

[0148] The minimum dwell time threshold for cities is dynamically calculated based on local, real-time massive data distribution and can be adaptively adjusted according to different scenarios such as holidays and weekdays. It can flexibly adapt to changes in passenger flow patterns in different regions and at different times, and has stronger scientificity, robustness and universality.

[0149] By using provincial market share for differentiated sample expansion, the problem of distortion in the source area structure caused by traditional single expansion factors is solved, making the analysis results of tourist source areas closer to the real market situation.

[0150] Based on the method for calculating the overall passenger flow based on mobile signaling data described in the above embodiments, the system for calculating the overall passenger flow based on mobile signaling data will be described below through embodiments.

[0151] like Figure 2 As shown, this embodiment of the invention provides a system for calculating the overall passenger flow based on mobile signaling data, including:

[0152] The permanent residence identification module 201 is used to acquire mobile signaling data of multiple users in the target province and obtain the permanent residence identification result of each user by using a preset dynamic weighting model and mobile signaling data.

[0153] The whole-domain passenger identification and classification module 202 is used to identify and classify all users using a preset whole-domain passenger identification and classification model and the permanent residence identification results, and to obtain the whole-domain passenger identification and classification results.

[0154] The transit passenger filtering module 203 is used to filter transit passengers based on the preset city minimum stay duration calculation model to obtain the first city passenger result.

[0155] The atypical passenger identification module 204 is used to identify and remove atypical tourists from the first overall passenger result based on a preset special user group identification model to obtain the second overall passenger result.

[0156] The expansion calculation module 205 is used to expand the second all-area tourism results based on the market share of the target operator and statistically generate all-area passenger flow analysis results.

[0157] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0159] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0160] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0161] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of the claims of the present invention pending approval.

Claims

1. A method for calculating passenger flow across an entire region based on mobile signaling data, characterized in that, include: Obtain mobile signaling data of multiple users within the target province, and use a preset dynamic weighting model and the mobile signaling data to obtain the permanent residence identification result of each user; Using a pre-defined global passenger identification and classification model and the permanent residence identification results, all users are identified and classified to obtain global passenger identification and classification results. Based on the preset minimum stay duration calculation model for cities, the transit passenger filtering process is applied to the overall passenger identification and classification results to obtain the first overall passenger result. Based on a preset special user group identification model, atypical tourists are identified and eliminated from the first overall passenger results to obtain the second overall passenger results; the preset special user group identification model includes a campus student identification sub-model and a professional user identification sub-model. Based on the market share of the target operator, the second all-for-one tourism results are expanded and calculated to generate all-for-one passenger flow analysis results. The expression for the preset dynamic weighted model is: ； Among them, the This represents the score of user A's permanent presence at a specific base station B on day t; This represents the duration of user A's stay at the specific base station B on day t; The reference total duration is the normalized baseline; The preset normalization coefficients; This represents the historical score value that user A has accumulated at the specific base station B on day t-1. This is a preset time decay factor; The step of identifying and eliminating atypical tourists based on a preset special user group identification model to obtain a second set of overall passenger results includes: The permanent base station locations of each tourist in the first global passenger results are matched with a pre-set list of geographical information of university base stations in the province; tourists whose permanent base station locations are in the pre-set list of geographical information of university base stations in the province are identified as potential students; the real-name age information, campus-exclusive communication package application information and DPI data of the potential students are obtained, and the student identity of the potential students is cross-verified in multiple dimensions to identify the campus student group. Obtain the average daily usage time and monthly active days of each tourist's occupational application in the first global passenger results, and mark those whose average daily usage time and monthly active days both reach the corresponding threshold as occupational users; determine whether the travel trajectory of the occupational user meets the spatiotemporal conditions of a passenger. If it does, determine that the user is an occupational user passenger; if it does not, determine that the user is an occupational user non-passenger. The campus student group and the professional users who are not passengers are removed from the first global passenger result to obtain the second global passenger result.

2. The method for calculating the entire area passenger flow based on mobile signaling data according to claim 1, characterized in that, The process of acquiring mobile signaling data from multiple users within a target province, and using a preset dynamic weighting model and the mobile signaling data to obtain the permanent residence identification result for each user, includes: Acquire mobile signaling data from multiple users within a target province; Based on the mobile signaling data, historical dwell data of all users at different base stations under the target operator are obtained; Based on the historical dwell time data, the current dwell time of different users at different base stations within the same day can be obtained; The current dwell time is input into the preset dynamic weighted model to calculate the dwell score of different users on different base stations; The resident score is compared with a preset resident determination threshold to identify the resident base station of each user, and the resident base station is used as the resident location identification result.

3. The method for calculating the entire area passenger flow based on mobile signaling data according to claim 2, characterized in that, The preset global tourist identification and classification model includes sub-models for determining tourists from within and outside the province, as well as sub-models for classifying overnight and day-trip tourists. The process employs a pre-defined global passenger identification and classification model and the results of the permanent residence identification to identify and classify all users, resulting in global passenger identification and classification results, including: Based on the sub-model for determining tourists from within and outside the province and the results of the permanent residence identification, tourists from within and outside the province are identified. Based on the overnight and day-trip tourist classification sub-model and the permanent residence identification results, overnight tourists and day-trip tourists among the tourists within the province and the tourists outside the province are identified, and the overall tourist identification and classification results are obtained.

4. The method for calculating the entire area passenger flow based on mobile signaling data according to claim 3, characterized in that, The identification of tourists from within and outside the province based on the provincial and out-of-province tourist determination sub-model and the permanent residence identification results includes: Based on the provincial and out-of-province tourist determination sub-model and the permanent residence identification results, users without permanent base stations in the target province are identified as out-of-province candidate users, and users with permanent base stations are identified as in-province users. Determine whether the first cumulative travel time of the candidate user from outside the province within the target province is not less than a preset time threshold; If the first cumulative travel time is not less than the preset time threshold, then the candidate user from outside the province is determined to be a tourist from outside the province. If the first cumulative travel time is less than the preset time threshold, then the candidate user from outside the province is determined to be a non-tourist. Determine whether the travel distance of the user within the province is not less than a preset spatial distance threshold, and whether the second cumulative travel time is not less than the preset time threshold. The travel distance is the straight-line spatial distance of the user within the province from the permanent base station, and the second cumulative travel time is the cumulative duration during which the travel distance of the user within the province is not less than the preset spatial distance threshold. If the travel distance is not less than the preset spatial distance threshold and the second cumulative travel time is not less than the preset time threshold, then the user within the province is determined to be a tourist within the province. If the travel distance is less than the preset spatial distance threshold and / or the second cumulative travel time is less than the preset duration threshold, then the user within the province is determined to be a non-tourist.

5. The method for calculating the entire area passenger flow based on mobile signaling data according to claim 4, characterized in that, Based on the overnight and day-trip tourist classification sub-model and the permanent residence identification results, overnight and day-trip tourists are identified among tourists from within the province and tourists from outside the province, resulting in a comprehensive tourist identification and classification result, including: Based on the overnight and day-trip tourist classification sub-model and the permanent residence identification results, the first cumulative stay duration of the out-of-province tourist in the tourist destination area within the target province within the preset nighttime time window, and the second cumulative stay duration of the in-province tourist at the nighttime base station within the preset nighttime time window are obtained. Determine whether the first cumulative stay duration of the out-of-province tourist is not less than a preset nighttime stay duration threshold; If the first cumulative stay duration is not less than the preset nighttime stay duration threshold, then the out-of-province tourist is determined to be an out-of-province overnight tourist; If the first cumulative stay duration of the out-of-province tourist is less than the preset nighttime stay duration threshold, then the out-of-province tourist is determined to be a one-day out-of-province tourist. Determine whether the second cumulative stay duration of the tourists within the province is not less than the preset nighttime stay duration threshold, and whether the straight-line spatial distance between the nighttime base station and any of the permanent base stations is not less than the preset spatial distance threshold; If the second cumulative stay duration is not less than the preset nighttime stay duration threshold, and the straight-line spatial distance between the nighttime base station and any of the permanent base stations is not less than the preset spatial distance threshold, then the tourist from within the province is determined to be an overnight tourist from within the province. If the second cumulative stay time is less than the preset night stay time threshold and / or the straight-line spatial distance between the night stay base station and any of the permanent base stations is less than the preset spatial distance threshold, then the tourist from within the province is determined to be a tourist on a one-day tour within the province. Based on the determination results of overnight tourists and day-trip tourists corresponding to tourists from outside the province and tourists from within the province, the identification and classification results of tourists across the entire region are obtained.

6. The method for calculating the entire area passenger flow based on mobile signaling data according to claim 5, characterized in that, The transit passenger filtering process is applied to the overall passenger identification and classification results based on the preset minimum stay duration calculation model for prefecture-level cities to obtain the first overall passenger result, including: Based on the overall passenger identification and classification results, determine the intra-provincial travel trajectory of each tourist among multiple cities in the target province; Identify intermediate cities that serve as transit points or short-term stops from the travel routes within the province, and collect data on the length of stay in these intermediate cities. Visual analysis of the dwell time data is performed to verify whether it exhibits a bimodal distribution statistical characteristic, in which one peak corresponds to the short dwell time of passing passengers and the other peak corresponds to the longer dwell time of non-passing passengers. Using statistical or machine learning algorithms, the critical point that best segments the bimodal distribution statistical features is automatically found and determined, and the duration value corresponding to the critical point is used as the minimum residence duration threshold of the intermediate city. The minimum stay duration calculation model for each city is used to filter the transit passengers in each city based on the minimum stay duration threshold of the whole region passenger identification and classification results, so as to obtain the first whole region passenger result.

7. A system for calculating passenger flow across an entire region based on mobile signaling data, characterized in that, include: The permanent residence identification module is used to acquire mobile signaling data of multiple users within the target province, and to obtain the permanent residence identification result of each user by using a preset dynamic weighting model and the mobile signaling data. The whole-domain passenger identification and classification module is used to identify and classify all users using a preset whole-domain passenger identification and classification model and the permanent residence identification results, and to obtain the whole-domain passenger identification and classification results. The transit passenger filtering module is used to perform transit passenger filtering on the whole-area passenger identification and classification results based on a preset city minimum stay duration calculation model to obtain the first whole-area passenger result. The atypical passenger identification module is used to identify and remove atypical tourists from the first overall passenger results based on a preset special user group identification model to obtain the second overall passenger results; the preset special user group identification model includes a campus student identification sub-model and a professional user identification sub-model. The expansion calculation module is used to expand the second all-area tourism results based on the market share of the target operator and statistically generate all-area passenger flow analysis results. The expression for the preset dynamic weighted model is: ； Among them, the This represents the score of user A's permanent presence at a specific base station B on day t; This represents the duration of user A's stay at the specific base station B on day t; The reference total duration is the normalized baseline; The preset normalization coefficients; This represents the historical score value that user A has accumulated at the specific base station B on day t-1. This is a preset time decay factor; The atypical passenger identification module is specifically used to match the permanent base station location of each tourist in the first global passenger result with a pre-set geographical information list of university base stations in the province; and to identify tourists whose permanent base station location is in the pre-set geographical information list of university base stations in the province as potential students. The system obtains the real-name age information, campus-exclusive communication package subscription information, and DPI data of the potential students, and performs multi-dimensional cross-verification of their student identities to identify the campus student group. It also obtains the average daily usage time and monthly active days of occupational applications for each tourist in the first overall passenger result, marking those whose average daily usage time and monthly active days both reach the corresponding thresholds as occupational users. The system determines whether the travel trajectory of the occupational users meets the passenger spatiotemporal conditions; if it does, they are determined to be occupational user passengers; otherwise, they are determined to be occupational user non-passengers. Finally, the system removes the campus student group and the occupational user non-passengers from the first overall passenger result to obtain the second overall passenger result.

Images