Aviation passenger identification method and device based on mobile phone signaling and electronic equipment

Abstract

The invention provides an aviation passenger identification method and device based on mobile phone signaling and electronic equipment, and the method comprises the steps: determining a resident user set of the current day for each airport, and obtaining all resident data of each resident user of the current day; the resident data is an aggregation result obtained by processing multiple pieces of signaling data through space-time aggregation; for a certain resident user, identifying and combining resident data which are in the same airport area and are continuous in time, and then integrating the combined resident data with the uncombined resident data to obtain a resident data set of the resident user; and based on the resident data set of each resident user, determining the travel characteristics of the resident user, and according to the travel characteristics of the resident user, determining whether the resident user is an aviation passenger by applying a preset classification rule. According to the method, the aviation flight characteristics and the travel characteristics displayed by the mobile phone signaling data in the aviation travel process are comprehensively considered, and the aviation passengers can be accurately and efficiently identified through deep fusion of the multi-dimensional information.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to an airline passenger identification method, device and electronic equipment based on mobile phone signaling. Background Art

[0002] At present, the transportation industry has achieved remarkable development, forming a comprehensive transportation network system including civil aviation, railways, roads and waterways, improving the level of infrastructure and transportation services, and enhancing users' sense of happiness.

[0003] As a key component, airports play an indispensable role in the transportation system and have become the main mode of transportation for residents to travel with high quality. The complete travel data of airport passengers plays an important supporting role in in-depth research on the travel characteristics of air passengers, airport planning, and intermodal analysis.

[0004] In the existing technology, air passenger travel data is obtained by purchasing ticketing data from airlines, conducting traditional questionnaire surveys, and jointly modeling based on the spatial scope of one end airport and mobile phone signaling. However, these methods are costly and their efficiency and accuracy are difficult to guarantee. Summary of the invention

[0005] In view of this, the object of the present invention is to provide an airline passenger identification method, device and electronic equipment based on mobile phone signaling to improve the accuracy of airline passenger identification, reduce the time cost of identification, and improve efficiency.

[0006] In a first aspect, the present invention provides an airline passenger identification method based on mobile phone signaling, the method comprising: for each airport, determining a set of resident users on the day, and obtaining all resident data of each resident user on the day; wherein the resident data is an aggregation result obtained by performing spatiotemporal aggregation processing on multiple signaling data; for each of the resident users, identifying and merging the resident data that are temporally continuous in the same airport area, and then integrating the merged resident data with the unmerged resident data to obtain a resident data set of the resident user; based on the resident data set of each of the resident users, determining the travel characteristics of the resident user, and applying preset classification rules to determine whether the resident user is an airline passenger according to the travel characteristics of the resident user.

[0007] In a second aspect, the present invention provides an aviation passenger identification device based on mobile phone signaling, comprising: a determination module, for determining the set of resident users of the day for each airport; an acquisition module, for acquiring all resident data of each resident user; wherein the resident data is an aggregation result obtained by performing spatiotemporal aggregation processing on multiple signaling data; an aggregation module, for identifying and merging, for each of the resident users, resident data that are continuous in time within the same airport area, and then integrating the merged resident data with the unmerged resident data to obtain a resident data set of the resident user; an identification module, for determining the travel characteristics of the resident user based on the resident data set of each resident user, and applying preset classification rules to determine whether the resident user is an aviation passenger based on the travel characteristics of the resident user.

[0008] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the method for airline passenger identification based on mobile phone signaling as described in any one of the aforementioned implementation modes.

[0009] The method, device and electronic device for identifying airline passengers based on mobile phone signaling provided in the embodiment of the present invention first collect data for each airport, determine the set of resident users on the day, and obtain all the resident data of these users. Then, for a certain resident user, identify the resident data that are continuous in time in the same airport area and merge them, which helps to track the user's behavior trajectory at the airport more accurately. The merged resident data are integrated with the unmerged resident data. Finally, the user's travel characteristics are determined based on the resident data set of each user. According to these travel characteristics, the preset classification rules are applied to determine whether the user meets the characteristics of airline passengers, and airline passengers can be accurately identified from a large number of users. In general, the embodiment of the present invention comprehensively considers the travel behavior characteristics of airline passengers and the travel mode displayed by mobile phone signaling data during air travel. Through the deep integration of these multi-dimensional information, the airline passenger group can be accurately and efficiently identified.

[0010] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 is a schematic flow chart of an airline passenger identification method based on mobile phone signaling provided in an embodiment of the present invention;

[0013] Figure 2 is a schematic diagram of resident data aggregation provided by an embodiment of the present invention;

[0014] Figure 3 It is a functional module diagram of an aviation passenger identification device based on mobile phone signaling provided by an embodiment of the present invention;

[0015] Figure 4 A structural block diagram of an electronic device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0017] Currently, there are several main ways to obtain air passenger travel data, including purchasing ticket data from airlines, conducting traditional questionnaires, and using the spatial scope of a single airport and mobile phone signaling data for joint modeling. However, each of these methods has some limitations. Specifically:

[0018] As for the way airlines purchase ticketing data, since this data is scattered within each airline and the procurement channels are complex, this makes data collection complicated and costly.

[0019] The shortcomings of the traditional questionnaire survey method in the implementation process are: (1) The questionnaire survey method is applicable to a limited research space scale and is only suitable for small-scale research. Due to the limitations of manpower and time costs, it is difficult to use the questionnaire survey method for large-scale research. (2) Questionnaire surveys involve multiple processes such as designing, distributing, collecting and analyzing questionnaires. Each process requires a lot of time and manpower costs, which determines that the questionnaire survey cycle is relatively long and the cost is relatively high. For research scenarios with high effectiveness requirements, traditional questionnaire surveys have certain limitations in flexibility and timely response. (3) The sample and quality of the questionnaire survey are closely related to the personal wishes of the respondents. It is difficult for the questionnaire distributor to control the sample and quality of the questionnaire survey. Different respondents may have different understandings of the questions, resulting in inconsistent answers; respondents may answer questions based on social expectations, which may not be the true thoughts of the feedback.

[0020] The joint modeling method based on the spatial scope of one-end airport and mobile phone signaling has, to a certain extent, made up for the shortcomings of purchasing airline ticket data and traditional questionnaire survey methods in terms of low data dimensional scalability, high acquisition cost, long survey period, and small survey samples. However, this method still has certain shortcomings, mainly including: (1) The recognition results of this method are mixed with samples of non-real aviation travel, such as airport staff (including staff directly related to aircraft travel and personnel selling goods in the airport) and airport pick-up and drop-off personnel, which will cause great interference to the results. (2) Passenger identification is not closely combined with the behavioral characteristics of air passenger travel, and there may be some uncertainty in the analysis results. (3) The current research scope is limited to a few airports, and relevant research has not yet been carried out nationwide, which is difficult to meet the needs of large-scale research.

[0021] Considering that it is difficult for existing technologies to accurately, efficiently, and at low cost identify air passengers on a national scale, based on this, the embodiments of the present invention provide an air passenger identification method with high effectiveness, high data dimension scalability, high data accuracy, and wide applicability, providing basic data support for airport-related research, planning, and evaluation. The following is a description through an embodiment.

[0022] See also Figure 1 , Figure 1 is a schematic flow chart of an air passenger identification method based on mobile phone signaling provided by an embodiment of the present invention. The execution subject of the method may be an electronic device with data processing capability. The method may include the following steps:

[0023] Step S101: for each airport, determine the set of resident users on that day, and obtain all resident data of each resident user on that day; wherein the resident data is an aggregated result obtained by processing multiple signaling data through spatiotemporal aggregation;

[0024] Step S102: for a certain resident user, identify and merge the resident data that are in the same airport area and are continuous in time, and then integrate the merged resident data with the unmerged resident data to obtain a resident data set of the resident user;

[0025] Step S103: Based on the resident data set of each resident user, the travel characteristics of the resident user are determined, and according to the travel characteristics of the resident user, a preset classification rule is applied to determine whether the resident user is an air passenger.

[0026] The scheme of steps S101 to S103 provided by the embodiment of the present invention first collects data for each airport, determines the set of resident users on the day, and obtains all the resident data of these users. These data are the aggregation results obtained by spatiotemporal aggregation of multiple mobile phone signaling data, which can reduce the complexity of the data and extract key information, so that a database containing user spatiotemporal displacement information can be constructed, providing a data basis for subsequent data analysis. Then, for a certain resident user, the resident data that is continuous in time in the same airport area is identified and merged, which helps to more accurately obtain the user's behavior trajectory at the airport, and the merged resident data is integrated with the unmerged resident data. Through the merging and integration process, the redundancy and inconsistency in the data can be reduced, the quality and reliability of the data can be improved, and a more solid foundation for subsequent analysis can be provided. Finally, the travel characteristics of the user are determined based on the resident data set of each user, and then, according to these travel characteristics, the preset classification rules are applied to determine whether the user meets the characteristics of an air passenger. The embodiment of the present invention can accurately identify air passengers from a large number of users. These data can provide important data support for airport hinterland analysis, improving airport landside transportation service levels, supporting airport layout planning, intermodal transportation analysis, optimizing and adjusting airport routes, etc. In general, the embodiments of the present invention comprehensively consider the travel behavior characteristics of air passengers and the data characteristics displayed by mobile phone signaling data during air travel. Through the deep integration of these multi-dimensional information, air passenger groups can be accurately and efficiently identified.

[0027] The following will provide a clear and detailed introduction to each of the above steps.

[0028] In step S101, the embodiment of the present invention adopts the following implementation to determine the resident users at each airport:

[0029] Step a1: Obtain the spatial boundary data of each airport and the residence data of all users;

[0030] In one embodiment of the present invention, the official directory of various airports can be obtained first, and then the spatial boundary vector data of each airport in the directory is captured through public channels on the Internet. This step is to collect the geospatial information of the airport and provide basic data for subsequent geographic information system (GIS) analysis.

[0031] In the GIS software environment, the captured airport spatial boundary vector data is superimposed with the latest satellite imagery, which can verify the accuracy of the airport boundary data and make necessary corrections.

[0032] It should be noted that for airport boundary data that cannot be captured through public channels, hand-drawing methods can be used to supplement to ensure the integrity of the data. At the same time, considering that airports may be added, cancelled, rebuilt or expanded, the embodiment of the present invention can also regularly update the spatial boundary vector data of the airport, so as to ensure the accuracy and timeliness of the spatial boundary vector data of the airport.

[0033] Step a2: spatially associate the resident data of each user with the spatial boundary data, determine the resident user set, and obtain all the resident data of these resident users on that day.

[0034] In the embodiment of the present invention, the signaling data is used to capture the geographical location information of all users in the country within a certain time range, and then the original signaling data is processed by time-space aggregation technology to generate the residence data of the day. These residence data accurately depict the residence location of the user within the time range, providing a basis for further data analysis and user behavior research.

[0035] Then, the resident data of these users are spatially correlated with the spatial boundary vector data of all airports in the country, so that users with resident data at the airport and their entire resident data can be screened out. However, in addition to air passengers, non-passenger users such as airport pick-up and drop-off personnel and airport staff also have resident data at the airport, and their presence may interfere with the analysis results. Therefore, the resident users obtained through the above steps can be regarded as potential air passengers, and further identification is required to ensure that real air passengers are identified.

[0036] In addition, considering that the original signaling data may introduce inaccurate information such as redundant data, noise data, and drift data due to force majeure during the collection, transmission, and processing of the data. In order to ensure the accuracy of the data and the effectiveness of the analysis, before executing step S102, the obtained resident data can be cleaned. Specifically, data points with time and space conflicts and invalid resident data with a residence time of less than 15 minutes can be excluded. These resident data can be considered as "dirty data" in the data. Through the data cleaning process, a clean and reliable data source can be finally obtained, which provides a guarantee for the accuracy of subsequent air passenger identification.

[0037] In step S102, the embodiment of the present invention can also perform spatiotemporal aggregation on the resident data after data cleaning. Figure 2 , Figure 2 FIG. 1 is a schematic diagram of a resident data aggregation provided by an embodiment of the present invention. Figure 2 As shown in (a), there are three residence data in Airport 1, including Residence 2, Residence 3 and Residence 4, and two residence data in Airport 2, namely Residence 5 and Residence 6. The residence data in the non-airport area are Residence 1 and Residence 7. Figure 2 As shown in (b), by merging the residence 2, residence 3 and residence 4 in Airport 1, a residence data can be obtained, namely, residence 2-3-4, and by merging the residence 5 and residence 6 in Airport 2, a residence data can be obtained, namely, residence 5-6.

[0038] That is to say, in the embodiment of the present invention, considering that a user may have two or more stays within the airport, in order to obtain the start time and end time of the user's stay at the airport, the embodiment of the present invention uses a spatiotemporal clustering algorithm to merge the stay data within the same airport and continuous in time, obtain the earliest start time and the latest end time at the airport, and merge the aggregated stay data and the unaggregated stay data together to form a spatiotemporally aggregated stay data set, which provides a data basis for the subsequent analysis of the travel characteristics of the resident users.

[0039] Based on the resident data set of the resident user obtained in step S102, the travel characteristics presented by the resident user's resident data are determined, and then combined with the characteristics of the user's use of mobile phones during air travel, the preset classification rules are applied to identify whether the resident user is an air passenger.

[0040] Before introducing the process of identifying an airline passenger, the types of airline passengers involved in the embodiment of the present invention are first introduced.

[0041] In the embodiment of the present invention, the types of air passengers can be subdivided into two categories: domestic air passengers and international air passengers. Domestic air passengers refer to passengers who depart from a city or region within the country and whose destination is also another city or region within the country. International air passengers refer to passengers who cross the border and depart from one country to another country. Since there is no data on China's Hong Kong, Macao and Taiwan in the mobile phone signaling, passengers flying to China's Hong Kong, Macao and Taiwan will also be identified as international air passengers.

[0042] Among them, the characteristics of domestic air passengers using mobile phones during air travel include the following two points: 1. Users will generate stay information at the departure airport and the arrival airport, and the stay time at the departure airport is generally longer than the stay time at the arrival airport; 2. No signaling data is generated during the flight, that is, the user's communication device is in the state of being turned off or in flight mode, and no signaling will be generated during this period.

[0043] Similarly, there are two types of international air passengers, one is outbound air passengers and the other is inbound air passengers. The outbound airport of outbound air passengers is an international airport, and their last stop of the day is an international airport. After leaving the country, no signaling data of them will be received in China, so there is no stay data in China. The travel characteristics of inbound air passengers are that they are not in China before entering the country, the entry airport is an international airport, and their first stop of the day is an international airport. The signaling data shows that there is no stay data in China before entering the country.

[0044] The embodiment of the present invention provides different identification methods for domestic air passengers, outbound air passengers and inbound air passengers. The process of identifying domestic air passengers is first described below. Based on the resident users and their resident data sets obtained in steps S101 to S102, for domestic air passengers, step S103 can be performed as follows:

[0045] Step b1: For a certain resident user, the resident data in the resident data set are arranged in ascending order according to the resident start time.

[0046] In the embodiment of the present invention, the resident data set may include, but is not limited to, multiple pieces of resident data. Each piece of resident data may include a user identifier, a resident location, a resident start time, a resident end time, and a resident duration.

[0047] It is understandable that if the user appears at the airport, the location of the stay can be represented by the airport logo. By sorting the stay data of each stay user, it is possible to quickly obtain and analyze the data, thereby efficiently mining the travel characteristics of the user.

[0048] Step b2: Determine all the airport residence data whose residence positions are located in the airport area from the sorted residence data set; wherein each piece of airport residence data includes a residence airport identifier and a residence timestamp.

[0049] In one embodiment of the present invention, Figure 2 As shown, by integrating the residence data of each resident user at a single airport, it is achieved that in the residence data set, each airport corresponds to only one piece of aggregated airport residence data. In this way, in the residence data set, if the resident user is a domestic air passenger, two consecutive airport residence data will appear in his residence data set, and if the resident user is not a domestic air passenger, there will be no two consecutive airport stay data in his residence data set. Based on this, for a certain resident user, the implementation method shown in the following step b3 can be implemented.

[0050] Step b3: if the resident airport identifiers in two consecutive airport resident data are different, determine the travel time and appearance distance of the resident user according to the two consecutive airport resident data, determine the travel speed of the resident user according to the appearance time and appearance distance and the route non-linear coefficient, and use the travel speed and travel time as the travel characteristics of the resident user;

[0051] First, for the convenience of description, the embodiment of the present invention refers to the resident users whose resident airport identifiers are different in the two consecutive airport resident data identified in step b3 as "candidate domestic air passengers". The reason is that considering that the method of determining whether the resident airport identifiers in the two consecutive airport resident data are the same only depends on the spatial position relationship, the resident data corresponding to the identified resident users may not be consistent with the actual aviation flight characteristics in terms of travel speed and travel time. Therefore, the embodiment of the present invention also requires further identification of this part of "candidate air passengers", that is, to determine whether their corresponding travel speed and travel time meet the actual aviation flight characteristics.

[0052] For each identified candidate domestic air passenger, its travel time can be determined according to the airport residence time stamps in the two airport residence data used in step b3, and then the straight-line distance between two consecutive residence airports can be calculated according to the location data. It should be pointed out that, considering that the actual flight path of the aircraft is not a straight line, the embodiment of the present invention will obtain the route non-linear coefficient by statistically analyzing the ratio of the actual flight distance of each aircraft to the straight-line distance between airports, and then multiply the straight-line distance corresponding to the candidate domestic air passenger by the route non-linear coefficient, and then divide it by the travel time to obtain the travel speed of the candidate domestic air passenger.

[0053] Step b4: Obtain the preset flight time and determine the target flight speed range.

[0054] In one embodiment of the present invention, the preset flight time can be customized according to actual needs. For example, the preset flight time is actually set to 20 minutes, and the target flight speed range can be determined based on the travel speeds corresponding to the candidate domestic air passengers identified in step b3.

[0055] In one embodiment of the present invention, the target flight speed interval can be determined by: using the mean and standard deviation to determine a probability density function expression, integrating the probability density function expression to determine a cumulative distribution function value; setting an interval probability value, and by searching for the cumulative distribution function value, determining the interval of flight speed that makes the cumulative distribution function value reach the interval probability value as the target flight speed interval. In the embodiment of the present invention, the relationship of the probability density function is as follows:

[0056]

[0057] Among them, μ is the mean, σ is the standard deviation, and x is the travel speed of the resident users.

[0058] Assuming that the flight speed interval is represented by [a, b], where a is the lowest flight speed and b is the highest flight speed, the calculation formula for the interval probability value corresponding to the flight speed interval is: For a and b, we can first perform a standard transformation, that is, Then combined with the probability density function f(x), For example, if the preset interval probability value is 95%, then we need to find a and b so that P(a <X<b)=0.95。

[0059] Through the above implementation, the embodiment of the present invention can identify the probability value of the travel speed within a specific flight speed interval. Specifically, the embodiment of the present invention can determine the probability value of the flight speed falling into which interval satisfies the preset interval probability value, and then define the flight speed interval as the target flight speed interval for subsequent classification rules. For example, if the preset interval probability value is 95%, the embodiment of the present invention finds through probability density function (PDF) analysis that the probability of the flight speed in the interval of 250km / h to 1000km / h reaches 95%, and then determines this speed interval as the target speed interval, and further refines the identification of the candidate domestic air passengers identified in step b3, that is, executes the following step b5.

[0060] Step b5: If the travel speed is within the target flight speed range and the travel time is greater than the preset flight time, it is determined that the resident user is a domestic air passenger.

[0061] In an embodiment of the present invention, a classification rule for domestic air passengers is designed based on the determined target flight speed range and the preset flight time, that is: if the travel speed of the resident user is within the target flight speed range and the travel time is greater than the preset flight time, the resident user is determined to be a domestic air passenger, otherwise the resident user is determined to be a non-domestic air passenger.

[0062] In another embodiment of the present invention, considering that some airports are relatively small in scale, the time for users to leave the airports after arriving at such airports is relatively short, and it is likely that the user's stay information will not be captured, resulting in such users being omitted in the initial judgment of step b3, that is, the candidate domestic air passengers are incomplete. Therefore, in order to ensure the accuracy of recognition, the following steps can also be performed while executing step b3:

[0063] Step c1: For a certain resident user, if there is no airport resident data after a piece of airport resident data, then determine the first resident location of the resident user after the resident user resides at the airport.

[0064] Step c2: taking the first stop position after the airport stop as the search center and searching according to the preset search radius;

[0065] Step c3: If there is an airport within the preset search radius, the travel characteristics of the resident user are determined based on the airport residence data and the first residence after the airport residence, and the process returns to step b4.

[0066] In the above implementation, the search radius can be customized according to actual needs, such as 10 km, which is not limited in the embodiment of the present invention.

[0067] The above implementation method illustrates that for a user who has only stayed at the departure airport, if there is no other airport stay data in the stay data after that, the embodiment of the present invention will find the first stay location of the user after staying at the airport. Then use this stay location as the center point of the search and search according to the pre-set search radius. If there is an airport within the determined search radius, the user's travel characteristics will be determined based on the user's stay data at the airport and the first stay location after staying at the airport, and then return to step b4 to continue execution.

[0068] For example: suppose a user stays at Airport A, then leaves Airport A, and has no data of entering any airports afterwards. The embodiment of the present invention will find the first location where the user stays after leaving Airport A, such as a train station. Assuming that the preset search radius is 10 kilometers, then all locations within a 10-kilometer radius around the train station will be searched. If Airport B is found within a search radius of 10 kilometers around the train station, the user's travel characteristics will be determined based on the user's stay data at Airport A and the user's first location (train station) after leaving Airport A. After determining the travel characteristics, the algorithm will return to step b4 to continue executing subsequent steps.

[0069] Through the above implementation, the embodiment of the present invention can accurately identify which of the users staying at the airport are domestic air passengers. The following describes the identification process of international air passengers, specifically involving identifying whether a user is an outbound air passenger or an inbound air passenger.

[0070] In one embodiment of the present invention, for a certain resident user, the method of identifying whether the user is an outbound air passenger is as follows: Steps d1 to d3:

[0071] Step d1: for a certain resident user, obtain the last resident data in the resident data set of the day;

[0072] Step d2: If the residence location corresponding to the last residence data is located in the international airport area, then all residence data within a preset number of days after the current day are obtained;

[0073] Step d3: If the resident data of the resident user is not found in the acquired resident data within the preset number of days, it is determined that the resident user is an outbound air passenger.

[0074] Based on steps d1 to d3, the classification rules for outbound air passengers can be understood as follows: for a user who stays at the airport, if the last data in the stay data set of the day shows that the user stays in the international airport area, then the system will obtain all the stay data within the preset number of days starting from that day. If no stay data of the user is found in these stay data, then the system will determine that the user is an outbound air passenger; if the stay data of the user is found, then it is determined that the user is not an outbound air passenger.

[0075] For example, suppose the last stay data of a user at International Airport B is on March 1, and the system preset number of days is 3. Then the system will obtain all the stay data from March 2 to March 4. If no stay data of the user is found in the data from March 2 to March 4, the system will consider the user to be an outbound air passenger (who may have left for other places). If there is stay data of the user during this period, the system will consider the user not to be an outbound air passenger.

[0076] Similarly, the implementation method of identifying whether a user residing at an airport is an inbound air passenger is shown in the following steps d4 to d6:

[0077] Step d4: for a certain resident user, obtaining the first resident data in the resident data set of the day;

[0078] Step d5: If the residence location corresponding to the first piece of residence data is located within the international airport area, then all residence data within a preset number of days before the current day are obtained;

[0079] Step d6: If the resident data of the resident user is not found in the resident data obtained within the preset number of days before the current day, it is determined that the resident user is an inbound air passenger.

[0080] Based on steps d4 to d6, the classification rules for inbound air passengers can be understood as follows: for a user who stays at the airport, if the first data in the residence data set of the day shows that the user stays in the international airport area, then the system will obtain all the residence data within the preset number of days before the residence date corresponding to the residence data. If no residence data of the user is found in these residence data, then it is determined that the user is an inbound air passenger; if the residence data of the user is found, then it is determined that the user is not an inbound air passenger.

[0081] For example, the first residence data of a user at International Airport A is on March 1, and the system preset number of days is 3. Then the system will obtain all residence data from February 26 to February 28. If no residence data of the user is found in the data from February 26 to February 28, the system will consider the user to be an inbound air passenger (perhaps just arrived at Airport A). If there is residence data of the user during this period, the system will consider the user not to be an air passenger.

[0082] The embodiment of the present invention can quickly and accurately identify international air passengers through the above implementation methods.

[0083] In a specific embodiment of the present invention, the data of identified domestic and international air passengers can be further integrated to eventually form a detailed list. The list will contain multiple fields such as user ID, departure airport name, arrival time at departure airport, departure time at departure airport, arrival airport name, arrival time at airport, departure time at arrival airport, flight time, flight distance, and flight speed. In particular, for outbound international air passengers, the arrival airport field in the list will be left blank; while for inbound international air passengers, the departure airport field will be left blank. These lists not only provide detailed information about passengers, but also help airlines and airport management departments optimize resource allocation and scheduling, and provide passenger behavior analysis to improve service quality and enhance passenger experience.

[0084] Based on Figure 1 With the same inventive concept, the embodiment of the present invention also provides an air passenger identification device based on mobile phone signaling. Figure 3 , Figure 3 The functional module diagram of the air passenger identification device based on mobile phone signaling provided by the embodiment of the present invention. The air passenger identification device based on mobile phone signaling 30 may include: a determination module 301 , an acquisition module 302 , an aggregation module 303 and an identification module 304 .

[0085] A determination module 301 is used to determine the set of resident users on that day for each airport;

[0086] An acquisition module 302 is used to acquire all resident data of each resident user; wherein the resident data is an aggregated result obtained by processing multiple signaling data through spatiotemporal aggregation;

[0087] Aggregation module 303, for a certain resident user, identifying and merging the resident data in the same airport area and continuous in time, and then integrating the merged resident data with the unmerged resident data to obtain a resident data set of the resident user;

[0088] The identification module 304 is used to determine the travel characteristics of the resident users based on the resident data set of each resident user, and apply preset classification rules to determine whether the resident users are air passengers according to the travel characteristics of the resident users.

[0089] It is understandable that the determination module 301, the acquisition module 302, the aggregation module 303 and the identification module 304 can be executed in coordination. Figure 1 Each step in the process is performed to achieve the corresponding technical effect.

[0090] In an optional implementation, the identification module 304 is specifically used to, for a certain resident user, arrange the resident data in the resident data set in ascending order according to the resident start time; determine the airport resident data whose resident locations are located in the airport area from the sorted resident data set; wherein each airport resident data includes a resident airport identifier and a resident timestamp; if the resident airport identifiers in two consecutive airport resident data are different, determine the travel time and travel distance of the resident user according to the two consecutive airport resident data, determine the travel speed of the resident user according to the travel time, travel distance and the non-linear coefficient of the route, and use the travel speed and the travel time as the travel characteristics of the resident user; obtain a preset flight time, and determine a target flight speed range; if the travel speed is within the target flight speed range and the travel time is greater than the preset flight time, determine that the resident user is an air passenger, otherwise determine that the resident user is not an air passenger.

[0091] In an optional embodiment, the identification module 304 is specifically used for airport stay data for a certain resident user. If there is no airport stay data after a piece of airport stay data, the first stay position of the resident user after the stay at the airport is determined; the first stay position after the stay at the airport is used as the search center, and the search is performed according to a preset search radius; if there is an airport within the preset search radius, the travel characteristics of the resident user are determined based on the airport stay data and the first stay position after the stay at the airport, and the step of returning to execute obtaining the preset flight time and determining the target flight speed range is performed.

[0092] In an optional embodiment, the determination module 301 is further used to calculate the mean and standard deviation of the travel speeds corresponding to resident users with different resident airport identifiers in two consecutive airport stay data; determine a probability density function expression using the mean and standard deviation, and integrate the probability density function expression to determine a cumulative distribution function value; set an interval probability value, and determine, by looking up the cumulative distribution function value, an interval of flight speeds that makes the cumulative distribution function value reach the interval probability value as the target flight speed interval.

[0093] In an optional implementation, the identification module 304 is further specifically used to: for a certain resident user, obtain the last resident data in the resident data set of the day; if the resident location corresponding to the last resident data is located in the international airport area, then obtain all resident data within a preset number of days after the day; if the resident data of the resident user is not found in the resident data within the preset number of days obtained, then determine that the resident user is an outbound air passenger.

[0094] In an optional implementation, the identification module 304 is further specifically used to: for a certain resident user, obtain the first resident data in the resident data set of the day; if the resident location corresponding to the first resident data is located in the national aircraft airport area, obtain all the resident data within a preset number of days before the day; if the resident data of the resident user is not found in the resident data within the preset number of days before the day, determine that the resident user is an inbound air passenger.

[0095] In an optional implementation, the determination module 301 is specifically used to obtain the spatial boundary data of each airport and the residence data of all users; spatially associate the residence data of each user with the spatial boundary data, and determine the users whose residence locations in the residence data are located within the airport as resident users.

[0096] It should be noted that the division of modules in the above embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0097] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program executable code.

[0098] The embodiment of the present invention further provides an electronic device 40, see Figure 4 , Figure 4 The structural block diagram of the electronic device provided by the embodiment of the present invention includes: a memory 401, a processor 402 and a communication interface 403. The memory 401, the processor 402 and the communication interface 403 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0099] Optionally, the bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0100] In the embodiment of the present invention, the processor 402 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiment of the present invention. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor. The software module may be located in the memory 401, and the processor 402 reads the program instructions in the memory 401 and completes the steps of the above method in combination with its hardware.

[0101] In the embodiment of the present invention, the memory 401 may be a non-volatile memory, such as a hard disk (HDD) or a solid-state drive (SSD), etc., or a volatile memory (VolatileMemory), such as RAM. The memory may also be any other medium that can be used to carry or store the desired program executable code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the embodiment of the present invention may also be a circuit or any other device that can realize a storage function, for storing instructions and / or data.

[0102] The memory 401 can be used to store software programs and modules, such as the instructions / modules of the mobile phone signaling-based air passenger identification device 30 provided in the embodiment of the present invention, which can be stored in the memory 401 or in the operating system (OS) of the fixed computer device 400 in the form of software or firmware. The processor 402 executes the software programs and modules stored in the memory 401 to perform various functional applications and data processing. The communication interface 403 can be used to communicate signaling or data with other node devices.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0104] Understandably, Figure 4 The structure shown is for illustration only. The electronic device may also include Figure 4 More or fewer components as shown, or with Figure 4 Different configurations are shown. Figure 4 The components shown may be implemented in hardware, software or a combination thereof.

[0105] The electronic device 40 may also include a network device and / or a user device. The network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

[0106] Based on the above embodiments, the present application also provides a storage medium, in which a computer program is stored. When the computer program is executed by a computer, the computer executes the airline passenger identification method based on mobile phone signaling provided in the above embodiments.

[0107] Based on the above embodiments, an embodiment of the present invention further provides a computer program. When the computer program is executed on a computer, the computer executes the airline passenger identification method based on mobile phone signaling provided in the above embodiments.

[0108] Based on the above embodiments, an embodiment of the present invention further provides a chip, which is used to read a computer program stored in a memory and to execute the airline passenger identification method based on mobile phone signaling provided in the above embodiments.

[0109] A computer program product is also provided in an embodiment of the present invention, comprising instructions, which, when executed on a computer, enable the computer to execute the method for identifying airline passengers based on mobile phone signaling provided in the above embodiment.

[0110] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by instructions. These instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for identifying airline passengers based on mobile phone signaling, characterized in that: The method comprises: For each airport, determine the set of resident users on that day, and obtain all resident data of each resident user on that day; wherein the resident data is an aggregation result obtained by performing spatiotemporal aggregation processing on multiple mobile phone signaling data; For each of the resident users, identifying and merging the resident data that are in the same airport area and are continuous in time, and then integrating the merged resident data with the unmerged resident data to obtain a resident data set of the resident user; Based on the resident data set of each resident user, the travel characteristics of the resident user are determined, and according to the travel characteristics of the resident user, a preset classification rule is applied to determine whether the resident user is an air passenger.

2. The method for identifying airline passengers based on mobile phone signaling according to claim 1, characterized in that: Determining travel characteristics of each resident user based on a resident data set of each resident user, and applying a preset classification rule to determine whether the resident user is an air passenger according to the travel characteristics of the resident user, including: For a certain resident user, arranging the resident data in the resident data set in ascending order according to the resident start time; Determine all the airport residence data whose residence positions are located in the airport area from the sorted residence data set; wherein each piece of the airport residence data includes a residence airport identifier and a residence timestamp; If the resident airport identifiers in two consecutive airport resident data are different, determining the travel time and travel distance of the resident user according to the two consecutive airport resident data, determining the travel speed of the resident user according to the travel time and travel distance and the route non-linear coefficient, and using the travel speed and the travel time as the travel characteristics of the resident user; Get the preset flight time and determine the target flight speed range; If the travel speed is within the target flight speed range and the travel time is greater than the preset flight time, it is determined that the resident user is a domestic air passenger.

3. The method for identifying airline passengers based on mobile phone signaling according to claim 2, characterized in that: The method further comprises: If there is no airport stay data after a piece of airport stay data, determining the first stay location of the stay user after the stay at the airport; Taking the first stop position after the airport stops as the search center, searching according to a preset search radius; If an airport exists within the preset search radius, the travel characteristics of the resident user are determined based on the airport residence data and the first residence position after the airport residence, and the process returns to execute the steps of obtaining the preset flight time and determining the target flight speed range.

4. The method for identifying airline passengers based on mobile phone signaling according to claim 2 or 3, characterized in that: The method for determining the target flight speed range includes: Calculate the mean and standard deviation of the travel speed according to the travel speeds corresponding to the resident users with different resident airport identifiers in two consecutive airport resident data; The probability density function expression is determined using the mean and standard deviation, and the probability density function expression is integrated to determine the cumulative distribution function value; an interval probability value is set, and by looking up the cumulative distribution function value, an interval of flight speed that makes the cumulative distribution function value reach the interval probability value is determined as the target flight speed interval.

5. The method for identifying airline passengers based on mobile phone signaling according to claim 2, characterized in that: Based on the resident data set of each resident user, determining the travel characteristics of the resident user, and applying a preset classification rule to determine whether the resident user is an air passenger according to the travel characteristics of the resident user, further comprising: For a certain resident user, obtaining the last resident data in the resident data set of the day; If the residence location corresponding to the last residence data is located in the international airport area, then all residence data within a preset number of days after that day are obtained; If the resident data of the resident user is not found in the acquired resident data within the preset number of days after the current day, it is determined that the resident user is an outbound air passenger.

6. The method for identifying airline passengers based on mobile phone signaling according to claim 2, characterized in that: Based on the resident data set of each resident user, determining the travel characteristics of the resident user, and applying a preset classification rule to determine whether the resident user is an air passenger according to the travel characteristics of the resident user, further comprising: For a certain resident user, obtaining the first resident data in the resident data set of the day; If the residence location corresponding to the first piece of residence data is within the national aircraft airport area, then all residence data within a preset number of days before the current day are obtained; If the resident data of the resident user is not found in the acquired resident data within the preset number of days before the current day, it is determined that the resident user is an inbound air passenger.

7. The method for identifying airline passengers based on mobile phone signaling according to claim 1, characterized in that: For each airport, determine the set of resident users on that day, and obtain all the resident data of each resident user on that day, including: Obtain spatial boundary data of each airport and residence data of all users; The resident data of each user is spatially associated with the spatial boundary data to determine the resident user set, and all resident data of the resident users on that day are obtained.

8. The method for identifying airline passengers based on mobile phone signaling according to claim 1, characterized in that: After determining the set of resident users on that day for each airport and obtaining all resident data of each resident user on that day, the method further includes: The resident data is cleansed.

9. An aviation passenger identification device based on mobile phone signaling, characterized in that: include: A determination module, used for determining the set of resident users on that day for each airport; An acquisition module, used to acquire all resident data of each resident user; wherein the resident data is an aggregation result obtained by performing spatiotemporal aggregation processing on multiple signaling data; an aggregation module, for identifying and merging the residence data of each resident user that is in the same airport area and is continuous in time, and then integrating the merged residence data with the unmerged residence data to obtain a residence data set of the resident user; The identification module is used to determine the travel characteristics of each resident user based on the resident data set of each resident user, and apply preset classification rules to determine whether the resident user is an air passenger according to the travel characteristics of the resident user.

10. An electronic device, characterized in that: The invention comprises a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the method for identifying airline passengers based on mobile phone signaling as described in any one of claims 1 to 8.

Images