Method and device for distinguishing hub population types

Abstract

The present invention provides a method and device for distinguishing the type of hub crowd. The method includes: determining the length of stay of the user represented by each user identifier at each hub based on the time of entering the hub base station and the time of leaving the hub base station in the user's transportation hub stay time list; determining the user's city zipper entry and exit table based on the user terminal signaling data; determining the record of each user's corresponding hub city before Δt time before entering the hub and after Δt time after leaving the hub according to the matching relationship between the hub city in the user's transportation hub stay time list and the city name in the user's city zipper entry and exit table; and distinguishing the type of crowd at each hub in the user's transportation hub stay time list based on this. The method for distinguishing the type of hub crowd provided by the present invention takes into account the complexity of the hub crowd, and the corresponding judgment rules have a wider range of application.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method and device for distinguishing hub population types. Background Art

[0002] With the economic growth and the increase of population mobility between cities, the passenger pressure related to urban transportation hubs is increasing day by day, especially during holidays, when the passenger pressure of transportation hubs reaches its peak. Therefore, it is very important to effectively control, manage and plan hub transportation through the analysis of passenger flow and population distribution in urban hubs. The traditional classification of traffic flow in transportation hubs mainly classifies railway transit population, railway departure population, railway arrival population, railway round-trip population, urban passage population and non-railway transit population for railway transportation hubs, and uses stopover points to determine the type of railway hub population. However, due to the complexity of the transportation hub population, the technical solution used has limitations in determining the railway departure population and railway arrival population; and the main determination method used is to formulate logical rules, but there are users who do not meet the logical rules but actually belong to a certain type of railway hub population, and they cannot be determined.

[0003] Therefore, considering the complexity of the population at transportation hubs, improving the judgment of the population at transportation hubs is an important issue that the industry needs to solve urgently. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a method and device for distinguishing the types of hub populations.

[0005] In a first aspect, the present invention provides a method for distinguishing hub crowd types, comprising: determining the length of stay of the user represented by each user identifier at each hub based on the time of entering the hub base station and the time of leaving the hub base station in the user's transportation hub stay time list;

[0006] Based on the user terminal signaling data, determine the user city zipper entry and exit table;

[0007] According to the matching relationship between the first hub city and the second hub city, determine a first record in which the user represented by each user identifier in the user city zipper access table is located in the hub city at the first moment and a second record in which the user is located in the hub city at the second moment;

[0008] Based on the preset hub crowd type discrimination rules, discriminate the crowd type of each hub in the user's transportation hub stay time list;

[0009] The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub;

[0010] The parameters of the hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record;

[0011] The user terminal signaling data at least includes: user identification, base station ID, city to which the base station belongs, time of entering the base station, and time of leaving the base station.

[0012] Optionally, the determining the type of crowd at each hub in the user's transportation hub stay time list based on a preset hub crowd type determination rule includes:

[0013] If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and at the first moment, there is the first record, but at the second moment, there is no second record, then it is determined that the user represented by the user identifier is a passenger departing from the hub;

[0014] If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and there is no first record at the first moment, but there is a second record at the second moment, then the user represented by the user identifier is determined to be a passenger arriving at the hub;

[0015] If there is a record of the hub for the user represented by the user identifier, and the first record exists at the first moment and the second record still exists at the second moment, the user represented by the user identifier is determined to be the hub passenger sending group.

[0016] Optionally, the step of determining the length of stay of the user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list includes:

[0017] Based on the longitude and latitude of each point of the outline of each hub across the country, as well as the longitude and latitude of each base station, the boundary base stations belonging to each hub are determined as a list of hub-range base stations;

[0018] Determine a user transportation hub stay time list based on a matching relationship between a base station ID in the user terminal signaling data and a base station ID in the hub range base station list;

[0019] The hub range base station list includes at least: hub name, hub city, base station ID, and hub type.

[0020] Optionally, the method further includes:

[0021] Based on the user's transportation hub stay time list, determine the total stay time of the user represented by the user identifier at each hub every day;

[0022] Determine the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies a preset duration threshold t2 and the number of days D2 during which the user terminal appears at the hub within a certain time period M;

[0023] Determine a list of resident users near the hub based on the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies the preset duration threshold t2, the number of days D2 during which the user represented by the user identifier appears at the hub, and the time period M;

[0024] If a user represented by a user identifier in the list of resident users near the hub has a related record of the user represented by the user identifier in the user transportation hub residence time list, the record of the user represented by the user identifier in the user transportation hub residence time list is deleted.

[0025] Optionally, the determining of a list of resident users near a hub based on the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies a preset duration threshold t2, the number of days D2 during which the user represented by the user identifier appears at the hub, and the time period M, includes:

[0026] If D1≥M / 2, it is determined that the user represented by the user identifier is a strongly correlated resident user near the hub;

[0027] If M / 3≤D1<M / 2 and D1 / D2≥0.5, it is determined that the user represented by the user identifier is a relatively relevant resident user near the hub;

[0028] Based on the strongly relevant resident users near the hub and the relatively relevant resident users near the hub, a list of resident users near the hub is determined.

[0029] Optionally, the method further includes:

[0030] According to the preset stay time threshold t1, the user's transportation hub stay time list is filtered to obtain the user's transportation hub travel sequence;

[0031] Preprocessing the sorted user's transportation hub travel sequence to obtain the user's transportation hub travel OD;

[0032] If the user represented by the user identifier in the user's transportation hub travel OD has a related record of the user represented by the user identifier in the user's transportation hub stay time list, remove the record of the user represented by the user identifier in the user's transportation hub stay time list;

[0033] The user's transportation hub travel OD includes at least: user identification, starting hub name, starting hub entry time, starting hub departure time, terminal hub name, terminal hub entry time, and terminal hub departure time.

[0034] Optionally, the method also includes: if the user represented by the user identifier does not meet the preset rules for distinguishing the hub population type, but the user represented by the user identifier has a record in the user's transportation hub travel OD, then the user represented by the user identifier is judged as a departing passenger of the starting hub name corresponding to the user identifier, and at the same time, the user represented by the user identifier is judged as an arriving passenger of the terminal hub name corresponding to the user identifier.

[0035] In a second aspect, the present invention provides a device for distinguishing hub population types, including a memory, a transceiver, and a processor;

[0036] Determine the length of stay of the user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list;

[0037] Based on the user terminal signaling data, determine the user city zipper entry and exit table;

[0038] According to the matching relationship between the first hub city and the second hub city, determine a first record in which the user represented by each user identifier in the user city zipper access table is located in the hub city at the first moment and a second record in which the user is located in the hub city at the second moment;

[0039] Based on the preset hub crowd type discrimination rules, discriminate the crowd type of each hub in the user's transportation hub stay time list;

[0040] The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub; the parameters of the preset hub crowd type discrimination rule include: the length of stay of the user represented by each user ID at each hub, the first record and the second record;

[0041] The user terminal signaling data at least includes: user identification, base station ID, city to which the base station belongs, time of entering the base station, and time of leaving the base station.

[0042] In a third aspect, the present invention also provides a device for distinguishing hub population types, the device comprising:

[0043] A stay duration determination module, used to determine the stay duration of the user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list;

[0044] A table generation module, for determining a user city zipper entry and exit table based on user terminal signaling data;

[0045] A record determination module, for determining, based on a matching relationship between a first hub city and a second hub city, a first record of a user represented by each user identifier in the user city zipper access table being located in the hub city at a first moment and a second record of a user being located in the hub city at a second moment;

[0046] A crowd type identification module, used to identify the crowd type of each hub in the user's transportation hub stay time list based on a preset hub crowd type identification rule;

[0047] The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub;

[0048] The parameters of the preset hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record;

[0049] The user terminal signaling data at least includes: user identification, base station ID, city to which the base station belongs, time of entering the base station, and time of leaving the base station.

[0050] In a fourth aspect, the present invention also provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable the processor to execute the steps of the method for identifying hub population types as described in the first aspect above.

[0051] The method and device for distinguishing hub crowd types provided by the present invention distinguish the hub crowd types by determining whether there is a record of the user in the city where the hub is located within a period of time before and after entering / leaving the hub in the order of the time axis. This takes into account the complexity of the hub crowd, and the corresponding determination rules have a wider range of application. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 It is a flow chart of the method for distinguishing hub population types provided by the present invention;

[0054] Figure 2 It is a flow chart of the method for distinguishing hub population types provided by the present invention;

[0055] Figure 3 It is a schematic diagram of the structure of the device for distinguishing the type of hub population provided by the present invention;

[0056] Figure 4 It is a schematic diagram of the structure of the device for distinguishing the type of hub population provided by the present invention. DETAILED DESCRIPTION

[0057] In the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0058] In the present invention, the term "plurality" refers to two or more than two, and other quantifiers are similar to them.

[0059] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] The scheme for distinguishing hub population types proposed in the present invention fully takes into account the needs of various hub populations, adopts the hub timeline sequence to determine whether there is a signaling record in the city where the hub is located within a period of time before / after the user enters / leaves the hub, and combines the stay time of each user in the hub to distinguish the hub population type.

[0061] Figure 1 FIG. 1 is a flow chart of the method for identifying hub population types provided by the present invention. Figure 1 As shown, the method comprises the following steps:

[0062] Step 101: Determine the length of stay of each user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list;

[0063] Specifically, the user's transportation hub stay time list includes at least: user ID, hub name, hub city, hub entry time, hub exit time, and hub type;

[0064] A user is represented by a user identifier, which may be in various forms. In the present invention, the user identifier is mainly one of the following or a combination thereof: IMSI (International Mobile Subscriber Identification Number), MSISDN (Mobile Subscriber International ISDN / PSTNNumber).

[0065] Hub names represent different hubs in different cities, for example, Hongqiao Railway Station, Shanghai South Railway Station, Shanghai West Railway Station, Shanghai Station, Shanghai Pudong International Airport, Shanghai Hongqiao International Airport, Beijing West Railway Station, Beijing South Railway Station, Beijing North Railway Station, etc.

[0066] The city to which the hub belongs indicates the city where the hub is located. For example, Hongqiao Railway Station is located in Shanghai, and Beijing West Railway Station, Beijing South Railway Station and Beijing North Railway Station are all located in Beijing.

[0067] The time of entering the hub indicates the time when the user enters the corresponding hub. Each hub includes multiple base stations. When the user accesses a base station within the hub range, the corresponding time of entering the hub is generated. If the user accesses a base station within the hub range multiple times, there will be multiple records of entering the hub time.

[0068] The time of leaving the hub indicates the time when the user leaves the corresponding hub. Similarly, each hub includes multiple base stations, and the time when the user leaves the hub appears in pairs with the time when the user enters the hub. That is, when there are multiple records of entering the hub time, there are correspondingly multiple records of leaving the hub time.

[0069] Hub type, indicating whether the hub is a railway station, airport (terminal), ferry, etc.

[0070] According to the entry and exit times of the hub base stations in the user's transportation hub stay time list, the length of stay of the user represented by each user ID at each hub is equal to the difference between the time of leaving the hub base station and the time of entering the hub in the record of each user at the hub.

[0071] For example, the user's transportation hub stay time list contains the following records:

[0072] IMSI1, MSISDN, hub A, hub city A1, hub entry time 1, hub departure time 2, railway station;

[0073] IMSI2, MSISDN, hub B, hub city B1, time of entering hub 3, time of leaving hub 4, terminal;

[0074] The calculation method for the user's stay time at each hub is as follows:

[0075] The length of time that user IMSI1 stays at hub A = time 2 of leaving the hub – time 1 of entering the hub;

[0076] The length of time user IMSI2 stays at hub B = time leaving the hub 4 - time entering the hub 3.

[0077] Step 102: Determine the user city zipper entry and exit table based on the user terminal signaling data; the user terminal signaling data at least includes: user identification, base station ID, base station city, base station entry time, and base station exit time.

[0078] Specifically, the user terminal signaling data includes at least: user identification, base station ID, base station city, base station entry time, and base station exit time; each time a user represented by the user identification accesses a base station ID, a corresponding record is generated. The record includes at least the user identification, the base station ID accessed, the base station city, base station entry time, and base station exit time. That is, the user terminal signaling data is recorded in units of base stations. The same user has one or more records in the same base station.

[0079] If there are multiple records for a user in the same base station city, the time-continuous records are merged to obtain a record of the user city zipper entry and exit table. That is, the user city zipper entry and exit table is a record based on the base station city. The same user has one or more records in the same base station city. It is only necessary to ensure the time continuity of each user.

[0080] For example: due to user terminal signaling data, there are multiple records for the city where a user belongs to the same base station (a city includes multiple hubs, and each hub includes multiple base stations). The continuous records of the same user and the same hub are merged in order of entry time. If the user has records of multiple hubs, they are merged separately to obtain the user city zipper entry and exit table. The user city zipper entry and exit table includes at least: user ID, city name, time of entering the city, and time of leaving the city.

[0081] The time of entering a city is determined by combining the continuous records of a user in the same city in the user terminal signaling data, and determining the earliest time of entering the base station as the time of entering the city.

[0082] The time of leaving the city is obtained by combining the continuous records of a user in the same city in the user terminal signaling data, and determining the latest time of leaving the base station as the time of leaving the city.

[0083] For example, the user terminal signaling data has the following records:

[0084]

[0085] After merging, the corresponding records of the user city zipper entry and exit table are as follows:

[0086] User ID City Name Time to enter the city Departure time IMSI1 City A1 Entering the city time 1 Departure time 3 IMSI1 City B1 Enter the city time 5 Departure time 7 IMSI1 City C1 Entering the city time 9 Departure time: 12

[0087] Step 103: According to the matching relationship between the first hub city and the second hub city, determine a first record where the user represented by each user identifier in the user city zipper access table is located in the hub city at the first moment and a second record where the user is located in the hub city at the second moment;

[0088] The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub;

[0089] Specifically, it is determined whether the "hub city" in the user's transportation hub stay time list has a relevant record in the user's city zipper entry and exit table;

[0090] If there is a corresponding record, further determine whether the entry time of the relevant record in the user's city zipper entry and exit table meets the Δt time before the user's entry time in the same city in the user's transportation hub stay time list;

[0091] Whether the departure time of the relevant record in the user's city zipper entry and exit table satisfies the time Δt after the departure time of the user in the same city in the user's transportation hub stay time list.

[0092] For example, the following records exist in the user's transportation hub stay time list:

[0093]

[0094] The following records exist in the user city zipper entry and exit table:

[0095] User ID City Name Time to enter the city Departure time IMSI1 City A 12:30:01 14:02:00 IMSI1 City B 8:06:05 9:08:05 IMSI2 City A 12:50:01 14:05:00 IMSI2 City B 8:06:05 8:38:02 IMSI3 City A 12:28:01 14:08:00 IMSI3 City B 8:06:05 8:39:02

[0096] Assuming that Δt = 30 minutes, user IMSI1 has data records of city A where hub A1 is located Δt before entering the hub; and also has data records of city B where hub B1 is located Δt after leaving the hub.

[0097] User IMSI2 does not have data records for city A where hub A1 is located before Δt time before entering the hub; nor does it have data records for city B where hub B1 is located after Δt time after leaving the hub;

[0098] User IMSI3 has data records of city A where hub A1 is located before time Δt before entering the hub; but does not have data records of city B where hub B1 is located after time Δt after leaving the hub.

[0099] Step 104: based on a preset hub crowd type discrimination rule, discriminate the crowd type of each hub in the user's transportation hub stay time list;

[0100] The parameters of the hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record;

[0101] Specifically, the conditions for determining the type of people at each hub in the user's transportation hub stay time list include:

[0102] 1. The length of time users stay at each hub;

[0103] 2. Whether there is a record of the city where the hub is located before the user enters the hub at Δt time before each hub;

[0104] 3. Whether there is a record of the city where the hub is located after the user leaves the hub Δt time after each hub.

[0105] Condition 1 is to count the length of time users stay at each hub. If the length of stay is too short, it is possible that the user just took public transportation and passed by the corresponding hub without staying at the hub. If the length of stay is long, the user may be a staff member at the hub, or a resident near the hub, etc.

[0106] Condition 2 indicates whether the user has any record of appearing in the city to which the hub belongs before Δt time before entering the hub.

[0107] Condition 3 indicates whether the user has any record of appearing in the city to which the hub belongs after Δt time after leaving the hub.

[0108] Based on the above three conditions, the type of people at each hub in the user's transportation hub stay time list can be identified.

[0109] The method for distinguishing hub crowd types provided by the present invention distinguishes hub crowd types by determining whether there is a record of users in the city where the hub is located within a period of time before and after entering / leaving the hub in the order of the time axis. This takes into account the complexity of the hub crowd, and the corresponding determination rules have a wider range of application.

[0110] On the basis of the above embodiment, optionally, the method of determining the type of people at each hub in the user's transportation hub stay time list based on a preset hub crowd type determination rule includes:

[0111] If the user represented by the user identifier stays at the hub for a duration greater than the set hub stay duration threshold t3, and there is a record of the city to which the hub belongs before Δt time before the hub entry time, and there is no record of the city to which the hub belongs after Δt time after the hub departure time, then the user represented by the user identifier is determined to be a passenger departing from the hub;

[0112] If the user represented by the user identifier stays at the hub for a duration greater than the set hub stay duration threshold t3, and there is no record of the city to which the hub belongs before Δt time before the hub entry time, and there is a record of the city to which the hub belongs after Δt time after the hub departure time, then the user represented by the user identifier is determined to be a passenger arriving at the hub;

[0113] If the user represented by the user identifier has a record of the hub, and there is a record of the city to which the hub belongs before Δt time before the hub's entry time, and there is still a record of the city to which the hub belongs after Δt time after the hub's departure time, then the user represented by the user identifier is determined to be the hub's passenger delivery group.

[0114] Specifically, there are many ways to set the hub dwell time threshold t3. It can be set based on experience or obtained through statistical value evaluation over a period of time.

[0115] Before the user represented by the user identifier enters the hub, the user has a record in the city, and after leaving the hub, the user still has a record in the city, indicating that the user often appears near the hub, and the user is determined to be a farewell group of the hub;

[0116] If the user's stay time at the hub is greater than a set threshold, and there is no record of the city where the hub is located before entering the hub, but there is a record of the city where the hub is located after leaving the hub, then the user is a hub arrival passenger.

[0117] If the user's stay time at the hub is greater than a set threshold, and there is a record of the city where the hub is located before entering the hub, but there is no record of the city where the hub is located after leaving the hub, then the user is a hub-departing passenger.

[0118] In this way, through different judgment conditions, it is possible to distinguish different types of people in the hub.

[0119] The method for distinguishing hub crowd types provided by the present invention distinguishes hub crowd types by determining whether there is a record of users in the city where the hub is located within a period of time before and after entering / leaving the hub in the order of the time axis. This takes into account the complexity of the hub crowd, and the corresponding determination rules have a wider range of application.

[0120] Based on the above embodiment, optionally, the step of determining the length of stay of the user represented by each user identifier at each hub based on the time of entering the hub base station and the time of leaving the hub base station in the user transportation hub stay time list includes:

[0121] Based on the longitude and latitude of each point of the outline of each hub across the country, as well as the longitude and latitude of each base station, the boundary base stations belonging to each hub are determined as a list of hub-range base stations;

[0122] Determine a user transportation hub stay time list based on a matching relationship between a base station ID in the user terminal signaling data and a base station ID in the hub range base station list;

[0123] The hub range base station list includes at least: hub name, hub city, base station ID, and hub type.

[0124] Specifically, before the present invention determines the type of people at each hub in the user's transportation hub dwell time list, it is necessary to first obtain the corresponding user transportation hub dwell time list. The acquisition method is as follows: select all hubs nationwide, select the longitude and latitude of each point according to its outline, and form a closed loop to obtain the longitude and latitude of all boundary points of each hub, and then generate a hub longitude and latitude list; based on the longitude and latitude of base stations nationwide, where the base station is determined as a point, calculate the distance between the longitude and latitude of the base station and the longitude and latitude of each point in the hub longitude and longitude list. If the distance is less than the coverage range of the base station, it is determined that the base station belongs to the hub range boundary base station, and a hub range base station list is generated. Among them, in order to avoid excessive calculation, the distance between the base station and the longitude and latitude of the hub outline is calculated by selecting the base station in the city where the hub is located for calculation.

[0125] The hub range base station list includes at least: hub name, city where the hub is located, base station ID, and hub type.

[0126] Hub type, indicating whether the hub is a railway station, airport (terminal), port, etc.

[0127] Taking into account the situation that users may travel across days (i.e. depart on the same day and arrive at the destination on the next day), the user terminal signaling data is a daily table updated daily, and the user terminal signaling data of two consecutive days are selected, and the base station ID in the user terminal signaling data is matched with the base station ID in the hub range base station list to determine the user hub zipper entry and exit table. The user hub zipper entry and exit table includes at least: user identification, hub name, city to which the hub belongs, time of entering the hub base station, time of leaving the hub base station, and hub type.

[0128] Since there are multiple records for the same hub in the user hub zipper entry and exit table (a hub includes multiple base stations), the continuous records of the same user and the same hub are merged in the order of entry time. If the user has records of multiple hubs, they are merged separately. For example:

[0129] The following records exist in the user hub zipper access table:

[0130] IMSI1, MSISDN, Hub A, Entry Time 1, Departure Time 2;

[0131] IMSI1, MSISDN, Hub A, Entry Time 2, Departure Time 4;

[0132] IMSI1, MSISDN, Hub B, entry time 5, departure time 6;

[0133] IMSI1, MSISDN, Hub B, entry time 6, departure time 8;

[0134] IMSI1, MSISDN, hub A, entry time 9, departure time 10;

[0135] IMSI1, MSISDN, Hub A, entry time 10, departure time 12;

[0136] After merging, the following records are obtained in the user's transportation hub stay time list:

[0137] IMSI1, MSISDN, hub A, entry time 1, departure time 4;

[0138] IMSI1, MSISDN, hub B, entry time 5, departure time 8;

[0139] IMSI1, MSISDN, Hub A, Entry Time 9, Departure Time 12;

[0140] The method for distinguishing hub crowd types provided by the present invention distinguishes hub crowd types by determining whether there is a record of users in the city where the hub is located within a period of time before and after entering / leaving the hub in the order of the time axis. This takes into account the complexity of the hub crowd, and the corresponding determination rules have a wider range of application.

[0141] Based on the above embodiment, optionally, the method further includes:

[0142] Based on the user's transportation hub stay time list, determine the total stay time of the user represented by the user identifier at each hub every day;

[0143] Determine the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies a preset duration threshold t2 and the number of days D2 during which the user terminal appears at the hub base station within a certain time period M;

[0144] Determine a list of resident users near the hub based on the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies the preset duration threshold t2, the number of days D2 during which the user represented by the user identifier appears at the hub base station, and the time period M;

[0145] If a user represented by a user identifier in the list of resident users near the hub has a related record of the user represented by the user identifier in the user transportation hub residence time list, the record of the user represented by the user identifier in the user transportation hub residence time list is deleted.

[0146] Specifically, the stay time threshold t2 can be set in a variety of ways, and can be set based on experience or obtained through statistical value evaluation over a period of time.

[0147] First, based on the list of users’ stay time at transportation hubs, for each user at the same hub every day, the difference between the time of leaving the hub and the time of entering the hub is calculated for each record. The differences of multiple records are summed up to obtain the total time each user stays at each hub every day.

[0148] The total duration of a user's stay at a hub within a certain time period M (in days) is calculated, and the number of days that meet the stay duration threshold t2 is D1, and the number of days that the user appears at the hub within the time period M is D2. Based on the above conditions, determine the list of resident users near the hub; and remove the user records that belong to the nearby resident user list from the user's transportation hub stay time list.

[0149] The method for distinguishing hub crowd types provided by the present invention distinguishes hub crowd types by determining whether there is a record of users in the city where the hub is located within a period of time before and after entering / leaving the hub in the order of the time axis. This takes into account the complexity of the hub crowd, and the corresponding determination rules have a wider range of application.

[0150] On the basis of the above embodiment, optionally, the number of days D1 in which the total duration of stay of the user represented by the user identifier at each hub satisfies the preset duration threshold t2, the number of days D2 in which the user represented by the user identifier appears at the hub, and the time period M, is determined to include:

[0151] If D1≥M / 2, it is determined that the user represented by the user identifier is a strongly correlated resident user near the hub;

[0152] If M / 3≤D1<M / 2 and D1 / D2≥0.5, it is determined that the user represented by the user identifier is a relatively relevant resident user near the hub;

[0153] Based on the strongly relevant resident users near the hub and the relatively relevant resident users near the hub, a list of resident users near the hub is determined.

[0154] Specifically, according to the above-mentioned rules for distinguishing permanent users near hubs, the permanent users near each hub are screened, and on this basis, the records in the list of user stay time at transportation hubs are filtered to remove users from the list of permanent users near the above-mentioned hubs; thus, the final statistical analysis of the data on the type of population at the hub is more targeted.

[0155] The method for distinguishing hub crowd types provided by the present invention distinguishes hub crowd types by determining whether there is a record of users in the city where the hub is located within a period of time before and after entering / leaving the hub in the order of the time axis. This takes into account the complexity of the hub crowd, and the corresponding determination rules have a wider range of application.

[0156] Based on the above embodiment, optionally, the method further includes:

[0157] According to the preset stay time threshold t1, the user's transportation hub stay time list is filtered to obtain the user's transportation hub travel sequence;

[0158] Preprocessing the sorted user's transportation hub travel sequence to obtain the user's transportation hub travel OD;

[0159] If the user represented by the user identifier in the user's transportation hub travel OD has a related record of the user represented by the user identifier in the user's transportation hub stay time list, remove the record of the user represented by the user identifier in the user's transportation hub stay time list;

[0160] The user's transportation hub travel OD includes at least: user identification, starting hub name, starting hub entry time, starting hub departure time, terminal hub name, terminal hub entry time, and terminal hub departure time.

[0161] Specifically, there are many ways to set the stay time threshold t1. It can be set based on experience or obtained through statistical value evaluation over a period of time.

[0162] The records in the user's transportation hub stay time list where the user's stay time at each hub does not meet the stay time threshold t1 are removed, thereby achieving the purpose of removing temporary stop hubs or transfer hubs, which are not the final destination of the user's travel.

[0163] The user transportation hub stay time list after the above processing is arranged in chronological order, that is, sorted according to the early and late time of accessing the hub. For the same user, the hubs with adjacent time are taken in turn to construct the travel OD, O (original) is the starting hub, D (Destination) is the destination hub, and the records whose starting hub and destination hub types are inconsistent, and the records where the starting and destination hubs are in the same city are deleted.

[0164] The hub types are inconsistent. For example, the starting hub is a train station and the terminal hub is an airport. Conversely, the starting hub is an airport and the terminal hub is a train station, which is also inconsistent in hub types.

[0165] The user's transportation hub travel OD is obtained. The starting hub type and the end hub type of each record are consistent, and the starting hub and the end hub are not in the same city.

[0166] The method for distinguishing hub crowd types provided by the present invention makes the subsequent processing data more representative by eliminating the records of stop hubs or transfer hubs in the user's transportation hub stay time list, and generates the user's transportation hub travel OD at the same time. It provides guarantee for the subsequent determination of hub crowd types. As a supplement to the subsequent determination of hub crowd types, it makes full use of data to improve the universality of hub crowd type determination.

[0167] Based on the above embodiment, optionally, the method further includes:

[0168] If the user represented by the user ID does not meet the preset rules for distinguishing the hub population type, but the user represented by the user ID has a record in the user's transportation hub travel OD, the user represented by the user ID is judged as a departing passenger of the starting hub name corresponding to the user ID, and at the same time, the user represented by the user ID is judged as an arriving passenger of the terminal hub name corresponding to the user ID.

[0169] The method for distinguishing hub crowd types provided by the present invention utilizes the user's transportation hub travel OD as a supplement for subsequent distinguishing hub crowd types, fully utilizes data, and improves the universality of hub crowd type determination.

[0170] Figure 2 Flow chart of the method for identifying hub population types provided by the present invention. Figure 2 As shown, step 1, based on the national base station engineering parameter table and the longitude and latitude of the national hub outline, determine the list of base stations within the hub range;

[0171] Step 2: Obtain a user's transportation hub stay time list based on the association between the user terminal signaling data and the base stations in the hub base station list;

[0172] Step 3: According to the hub dwell time threshold t1, the hubs that do not meet t1 are eliminated to obtain the user's transportation hub travel sequence;

[0173] Step 4: Sort the user's transportation hub travel sequence in chronological order, construct the user's transportation hub travel OD, delete the records with inconsistent starting and ending hub types and the starting and ending points in the same city, and generate the user's transportation hub travel OD;

[0174] Step 5: According to the set residence duration threshold t2, calculate the number of days D1 that the user meets the residence duration threshold t2 within a certain time period M and the number of days D2 that the user appears at the hub base station within the time period M. If D1 >= M / 2, the user is considered a strongly relevant resident near the hub; if M / 3 <= D1 < M / 2 and D1 / D2 >= 0.5, the user is considered a relatively relevant resident near the hub. Mark these two types of users as residents near the hub and generate a list of residents near the hub.

[0175] Step 6: Generate a user city zipper in-out table based on the user terminal signaling data.

[0176] Step 7: After removing the users in Step 4 and the list of residents near the hub in Step 5 from the user traffic hub residence time list, perform an associated match with the user city zipper in-out list, and screen out the following populations separately for railway stations and airports: 1) If the residence duration of a user at a certain hub is greater than the set hub residence duration threshold t3 (t3 is not equal to t1 in Step 3), and there is a data record of the city where the hub is located before the Δt moment before entering the hub, and there is no data record of the city where the hub is located after the Δt moment after leaving the hub, then the user is determined to be a departing passenger from the hub; 2) If the residence duration of a user at a certain hub is greater than the set residence duration threshold t3, and there is no data record of the city where the hub is located before the Δt moment before entering the hub, and there is still a data record of the city where the hub is located after the Δt moment after leaving the hub, then the user is determined to be an arriving passenger at the hub; 3) If a user has a record of a certain hub, and there is a data record of the city where the hub is located before the Δt moment before entering the hub, and there is still a data record of the city where the hub is located after the Δt moment after leaving the hub, then the user is determined to be a passenger sending group at the hub.

[0177] Step 8: Use the user traffic hub travel OD in Step 4 as a strong supplement for the discrimination of hub passenger sending. That is, if a user does not meet the rules for discriminating hub passenger sending, but has a traffic hub travel OD record, then the user is regarded as a departing passenger from the starting hub in the traffic hub travel record and also as an arriving passenger at the ending hub in the traffic hub travel record.

[0178] Figure 3 It is a schematic structural diagram of the device for discriminating the types of hub populations provided by the present invention. As Figure 3 shown, the device for discriminating the types of hub populations includes a memory 320, a transceiver 310, and a processor 300; among them, the processor 300 and the memory 320 can also be physically separated.

[0179] The memory 320 is used to store computer programs; the transceiver 310 is used to send and receive data under the control of the processor 300.

[0180] Specifically, the transceiver 310 is used to receive and send data under the control of the processor 300 .

[0181] Among them, Figure 3 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 300 and memory represented by memory 320. The bus architecture may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described in the present invention. The bus interface provides an interface. The transceiver 310 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which may include a wireless channel, a wired channel, an optical cable, and other transmission media.

[0182] The processor 300 is responsible for managing the bus architecture and general processing, and the memory 320 can store data used by the processor 300 when performing operations.

[0183] The processor 300 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0184] The processor 300 calls the computer program stored in the memory 320 to execute any of the methods provided by the present invention according to the obtained executable instructions, for example:

[0185] Determine the length of stay of the user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list;

[0186] Based on the user terminal signaling data, determine the user city zipper entry and exit table;

[0187] According to the matching relationship between the first hub city and the second hub city, determine a first record in which the user represented by each user identifier in the user city zipper access table is located in the hub city at the first moment and a second record in which the user is located in the hub city at the second moment;

[0188] Based on the preset hub crowd type discrimination rules, discriminate the crowd type of each hub in the user's transportation hub stay time list;

[0189] The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub;

[0190] The parameters of the hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record;

[0191] The user terminal signaling data at least includes: user identification, base station ID, city to which the base station belongs, time of entering the base station, and time of leaving the base station.

[0192] Optionally, the determining the type of crowd at each hub in the user's transportation hub stay time list based on a preset hub crowd type determination rule includes:

[0193] If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and at the first moment, there is the first record, but at the second moment, there is no second record, then it is determined that the user represented by the user identifier is a passenger departing from the hub;

[0194] If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and there is no first record at the first moment, but there is a second record at the second moment, then the user represented by the user identifier is determined to be a passenger arriving at the hub;

[0195] If there is a record of the hub for the user represented by the user identifier, and the first record exists at the first moment and the second record still exists at the second moment, the user represented by the user identifier is determined to be the hub passenger sending group.

[0196] Optionally, the step of determining the length of stay of the user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list includes:

[0197] Based on the longitude and latitude of each point of the outline of each hub across the country, as well as the longitude and latitude of each base station, the boundary base stations belonging to each hub are determined as a list of hub-range base stations;

[0198] Determine a user transportation hub stay time list based on a matching relationship between a base station ID in the user terminal signaling data and a base station ID in the hub range base station list;

[0199] The hub range base station list includes at least: hub name, hub city, base station ID, and hub type.

[0200] Optionally, the method further includes:

[0201] Based on the user's transportation hub stay time list, determine the total stay time of the user represented by the user identifier at each hub every day;

[0202] Determine the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies a preset duration threshold t2 and the number of days D2 during which the user terminal appears at the hub within a certain time period M;

[0203] Determine a list of resident users near the hub based on the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies the preset duration threshold t2, the number of days D2 during which the user represented by the user identifier appears at the hub, and the time period M;

[0204] If a user represented by a user identifier in the list of resident users near the hub has a related record of the user represented by the user identifier in the user transportation hub residence time list, the record of the user represented by the user identifier in the user transportation hub residence time list is deleted.

[0205] Optionally, the determining of a list of resident users near a hub based on the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies a preset duration threshold t2, the number of days D2 during which the user represented by the user identifier appears at the hub, and the time period M, includes:

[0206] If D1≥M / 2, it is determined that the user represented by the user identifier is a strongly correlated resident user near the hub;

[0207] If M / 3≤D1<M / 2 and D1 / D2≥0.5, it is determined that the user represented by the user identifier is a relatively relevant resident user near the hub;

[0208] Based on the strongly relevant resident users near the hub and the relatively relevant resident users near the hub, a list of resident users near the hub is determined.

[0209] Optionally, the method further includes:

[0210] According to the preset stay time threshold t1, the user's transportation hub stay time list is filtered to obtain the user's transportation hub travel sequence;

[0211] Preprocessing the sorted user's transportation hub travel sequence to obtain the user's transportation hub travel OD;

[0212] If the user represented by the user identifier in the user's transportation hub travel OD has a related record of the user represented by the user identifier in the user's transportation hub stay time list, remove the record of the user represented by the user identifier in the user's transportation hub stay time list;

[0213] The user's transportation hub travel OD includes at least: user identification, starting hub name, starting hub entry time, starting hub departure time, terminal hub name, terminal hub entry time, and terminal hub departure time.

[0214] Optionally, the method further includes:

[0215] If the user represented by the user ID does not meet the preset rules for distinguishing the hub population type, but the user represented by the user ID has a record in the user's transportation hub travel OD, the user represented by the user ID is judged as a departing passenger of the starting hub name corresponding to the user ID, and at the same time, the user represented by the user ID is judged as an arriving passenger of the terminal hub name corresponding to the user ID.

[0216] It should be noted here that the above-mentioned device for distinguishing hub population types provided by the present invention can implement all the method steps implemented in the embodiment of the above-mentioned method for distinguishing hub population types, and can achieve the same technical effect. The parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0217] Figure 4 Schematic diagram of the structure of the device for distinguishing the type of hub population provided by the present invention. Figure 4 As shown, the device comprises:

[0218] The stay duration determination module 401 is used to determine the stay duration of the user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list;

[0219] Table generation module 402, for determining a user city zipper entry and exit table based on user terminal signaling data;

[0220] A record determination module 403 is used to determine, based on the matching relationship between the first hub city and the second hub city, a first record of the user represented by each user identifier in the user city zipper access table being located in the hub city at the first moment and a second record of the user being located in the hub city at the second moment;

[0221] A crowd type identification module 404 is used to identify the crowd type of each hub in the user's transportation hub stay time list based on a preset hub crowd type identification rule;

[0222] The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub;

[0223] The parameters of the preset hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record;

[0224] The user terminal signaling data at least includes: user identification, base station ID, city to which the base station belongs, time of entering the base station, and time of leaving the base station.

[0225] Optionally, the determining the type of crowd at each hub in the user's transportation hub stay time list based on a preset hub crowd type determination rule includes:

[0226] If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and at the first moment, there is the first record, but at the second moment, there is no second record, then it is determined that the user represented by the user identifier is a passenger departing from the hub;

[0227] If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and there is no first record at the first moment, but there is a second record at the second moment, then the user represented by the user identifier is determined to be a passenger arriving at the hub;

[0228] If there is a record of the hub for the user represented by the user identifier, and the first record exists at the first moment and the second record still exists at the second moment, the user represented by the user identifier is determined to be the hub passenger sending group.

[0229] Optionally, the step of determining the length of stay of the user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list includes:

[0230] Based on the longitude and latitude of each point of the outline of each hub across the country, as well as the longitude and latitude of each base station, the boundary base stations belonging to each hub are determined as a list of hub-range base stations;

[0231] Determine a user transportation hub stay time list based on a matching relationship between a base station ID in the user terminal signaling data and a base station ID in the hub range base station list;

[0232] The hub range base station list includes at least: hub name, hub city, base station ID, and hub type.

[0233] Optionally, the stay duration determination module 401 is further used to determine the total stay duration of the user represented by the user identifier at each hub per day based on the user's transportation hub stay time list;

[0234] Determine the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies a preset duration threshold t2 and the number of days D2 during which the user terminal appears at the hub within a certain time period M;

[0235] The table generation module 402 is also used to determine a list of resident users near the hub based on the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies the preset duration threshold t2, the number of days D2 during which the user represented by the user identifier appears at the hub, and the time period M;

[0236] If a user represented by a user identifier in the list of resident users near the hub has a related record of the user represented by the user identifier in the user transportation hub residence time list, the record of the user represented by the user identifier in the user transportation hub residence time list is deleted.

[0237] Optionally, the determining of a list of resident users near a hub based on the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies a preset duration threshold t2, the number of days D2 during which the user represented by the user identifier appears at the hub, and the time period M, includes:

[0238] If D1≥M / 2, it is determined that the user represented by the user identifier is a strongly correlated resident user near the hub;

[0239] If M / 3≤D1<M / 2 and D1 / D2≥0.5, it is determined that the user represented by the user identifier is a relatively relevant resident user near the hub;

[0240] Based on the strongly relevant resident users near the hub and the relatively relevant resident users near the hub, a list of resident users near the hub is determined.

[0241] Optionally, the table generation module 402 is further used to filter the user's transportation hub stay time list according to a preset stay time threshold t1 to obtain the user's transportation hub travel sequence;

[0242] Preprocessing the sorted user's transportation hub travel sequence to obtain the user's transportation hub travel OD;

[0243] If the user represented by the user identifier in the user's transportation hub travel OD has a related record of the user represented by the user identifier in the user's transportation hub stay time list, remove the record of the user represented by the user identifier in the user's transportation hub stay time list;

[0244] The user's transportation hub travel OD includes at least: user identification, starting hub name, starting hub entry time, starting hub departure time, terminal hub name, terminal hub entry time, and terminal hub departure time.

[0245] Optionally, the crowd type identification module 404 is also used to identify the user represented by the user identifier as a departing passenger of the starting hub name corresponding to the user identifier, and at the same time, identify the user represented by the user identifier as an arriving passenger of the terminal hub name corresponding to the user identifier if the user represented by the user identifier does not meet the preset hub crowd type identification rules, but the user represented by the user identifier has a record in the user's transportation hub travel OD.

[0246] It should be noted that the division of units in the present invention 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 invention may be integrated into a processing unit, or each unit 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 software functional units.

[0247] 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 processor-readable storage medium. Based on this understanding, the technical solution of the present invention 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. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0248] It should be noted here that the above-mentioned device provided by the present invention can implement all the method steps implemented by the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects that are the same as the method embodiment in this embodiment will not be described in detail here.

[0249] On the other hand, the present invention further provides a processor-readable storage medium, the processor-readable storage medium storing a computer program, the computer program being used to cause the processor to execute the method for distinguishing the type of hub crowd provided in the above embodiments, including: determining the length of stay of the user represented by each user identifier at each hub based on the time of entering the hub base station and the time of leaving the hub base station in the user's transportation hub stay time list;

[0250] Based on the user terminal signaling data, determine the user city zipper entry and exit table;

[0251] According to the matching relationship between the first hub city and the second hub city, determine a first record in which the user represented by each user identifier in the user city zipper access table is located in the hub city at the first moment and a second record in which the user is located in the hub city at the second moment;

[0252] Based on the preset hub crowd type discrimination rules, discriminate the crowd type of each hub in the user's transportation hub stay time list;

[0253] The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub;

[0254] The parameters of the hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record;

[0255] The user terminal signaling data at least includes: user identification, base station ID, city to which the base station belongs, time of entering the base station, and time of leaving the base station.

[0256] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0257] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0258] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to 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 processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable 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 produce 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.

[0259] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor 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.

[0260] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0261] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for identifying hub population types, characterized in that: include: Based on the entry time into the hub base station and the exit time from the hub base station in the user's transportation hub stay time list, determine the stay time of the user represented by each user identifier at each hub; Based on the user terminal signaling data, determine the user city zipper entry and exit table; wherein the user city zipper entry and exit table is recorded in units of the city to which the base station belongs; According to the matching relationship between the city to which the first hub belongs and the city to which the second hub belongs, determine a first record in which the user represented by each user identifier in the user city zipper access table is located in the city to which the hub belongs at a first moment and a second record in which the user is located in the city to which the hub belongs at a second moment; the hub is one of the multiple hubs; Based on the preset hub crowd type discrimination rules, discriminate the crowd type of each hub in the user's transportation hub stay time list; The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub; The parameters of the hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record; The user terminal signaling data includes at least: user identification, base station ID, base station city, base station entry time, and base station exit time; The conditions for determining the type of people at each hub in the user's transportation hub stay time list include: the length of time the user stays at each hub; whether there is a record of the city where the hub is located before the first recording time Δt before the user's entry into the hub at each hub; whether there is a record of the city where the hub is located after the first recording time Δt after the user's departure from the hub at each hub; The method of determining the type of people at each hub in the user's transportation hub stay time list based on a preset hub crowd type determination rule includes: If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and the first record exists at the first moment, but the second record does not exist at the second moment, then it is determined that the user represented by the user identifier is a passenger departing from the hub; If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and there is no first record at the first moment, but there is a second record at the second moment, then the user represented by the user identifier is determined to be a passenger arriving at the hub; If there is a record of the hub for the user represented by the user identifier, and the first record exists at the first moment and the second record still exists at the second moment, the user represented by the user identifier is determined to be the hub passenger sending group.

2. The method for identifying hub population types according to claim 1, characterized in that: The method of determining the length of stay of each user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list includes: Based on the longitude and latitude of each point of the outline of each hub across the country, as well as the longitude and latitude of each base station, the boundary base stations belonging to each hub are determined as a list of hub-range base stations; Determine a user transportation hub stay time list based on a matching relationship between a base station ID in the user terminal signaling data and a base station ID in the hub range base station list; The hub range base station list includes at least: hub name, hub city, base station ID, and hub type.

3. The method for identifying hub population types according to claim 1 or 2, characterized in that: The method further comprises: Based on the user's transportation hub stay time list, determine the total stay time of the user represented by the user identifier at each hub every day; Determine the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies a preset duration threshold t2 and the number of days D2 during which the user terminal appears at the hub within a certain time period M; Determine a list of resident users near the hub based on the number of days D1 during which the total duration of stay of the user represented by the user identifier at each hub satisfies the preset duration threshold t2, the number of days D2 during which the user represented by the user identifier appears at the hub, and the time period M; If a user represented by a user identifier in the list of resident users near the hub has a related record of the user represented by the user identifier in the user transportation hub residence time list, the record of the user represented by the user identifier in the user transportation hub residence time list is deleted.

4. The method for identifying hub population types according to claim 3 is characterized in that: The determining of a list of resident users near a hub based on the number of days D1 in which the total duration of stay of the user represented by the user identifier in each hub satisfies a preset duration threshold t2, the number of days D2 in which the user represented by the user identifier appears in the hub, and the time period M, includes: If D1≥M / 2, it is determined that the user represented by the user identifier is a strongly correlated resident user near the hub; If M / 3≤D1<M / 2 and D1 / D2≥0.5, it is determined that the user represented by the user identifier is a relatively relevant resident user near the hub; Based on the strongly relevant resident users near the hub and the relatively relevant resident users near the hub, a list of resident users near the hub is determined.

5. The method for identifying hub population types according to claim 1, characterized in that: The method further comprises: According to the preset stay time threshold t1, the user's transportation hub stay time list is filtered to obtain the user's transportation hub travel sequence; Preprocessing the sorted user's transportation hub travel sequence to obtain the user's transportation hub travel OD; If the user represented by the user identifier in the user's transportation hub travel OD has a related record of the user represented by the user identifier in the user's transportation hub stay time list, remove the record of the user represented by the user identifier in the user's transportation hub stay time list; The user's transportation hub travel OD includes at least: user identification, starting hub name, starting hub entry time, starting hub departure time, terminal hub name, terminal hub entry time, and terminal hub departure time.

6. The method for identifying hub population types according to claim 1, characterized in that: The method further comprises: If the user represented by the user ID does not meet the preset rules for distinguishing the hub population type, but the user represented by the user ID has a record in the user's transportation hub travel OD, the user represented by the user ID is judged as a departing passenger of the starting hub name corresponding to the user ID, and at the same time, the user represented by the user ID is judged as an arriving passenger of the terminal hub name corresponding to the user ID.

7. A device for distinguishing the type of hub population, comprising a memory, a transceiver, and a processor; Memory for storing computer programs; A transceiver, used for transmitting and receiving data under the control of the processor; a processor, used for executing the computer program in the memory and implementing the following steps: Based on the entry time into the hub base station and the exit time from the hub base station in the user's transportation hub stay time list, determine the stay time of the user represented by each user identifier at each hub; Based on the user terminal signaling data, determine the user city zipper entry and exit table; wherein the user city zipper entry and exit table is recorded in units of the city to which the base station belongs; According to the matching relationship between the city to which the first hub belongs and the city to which the second hub belongs, determine a first record in which the user represented by each user identifier in the user city zipper access table is located in the city to which the hub belongs at a first moment and a second record in which the user is located in the city to which the hub belongs at a second moment; the hub is one of the multiple hubs; Based on the preset hub crowd type discrimination rules, discriminate the crowd type of each hub in the user's transportation hub stay time list; The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub; The parameters of the preset hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record; The user terminal signaling data includes at least: user identification, base station ID, base station city, base station entry time, and base station exit time; The conditions for determining the type of people at each hub in the user's transportation hub stay time list include: the length of time the user stays at each hub; whether there is a record of the city where the hub is located before the first recording time Δt before the user's entry into the hub at each hub; whether there is a record of the city where the hub is located after the first recording time Δt after the user's departure from the hub at each hub; The method of determining the type of people at each hub in the user's transportation hub stay time list based on a preset hub crowd type determination rule includes: If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and the first record exists at the first moment, but the second record does not exist at the second moment, then it is determined that the user represented by the user identifier is a passenger departing from the hub; If the length of stay of the user represented by the user identifier at the hub is greater than the set hub stay length threshold t3, and there is no first record at the first moment, but there is a second record at the second moment, then the user represented by the user identifier is determined to be a passenger arriving at the hub; If there is a record of the hub for the user represented by the user identifier, and the first record exists at the first moment and the second record still exists at the second moment, the user represented by the user identifier is determined to be the hub passenger sending group.

8. A device for identifying hub population types, characterized in that: The device comprises: A stay duration determination module, used to determine the stay duration of the user represented by each user identifier at each hub based on the entry hub base station time and the exit hub base station time in the user transportation hub stay time list; A table generation module is used to determine a user city zipper entry and exit table based on user terminal signaling data; wherein the user city zipper entry and exit table is a record based on the city to which the base station belongs; A record determination module is used to determine, based on a matching relationship between a city to which a first hub belongs and a city to which a second hub belongs, a first record that a user represented by each user identifier in the user city zipper access table is located in the city to which the hub belongs at a first moment and a second record that the user is located in the city to which the hub belongs at a second moment; the hub is one of the multiple hubs; A crowd type identification module, used to identify the crowd type of each hub in the user's transportation hub stay time list based on a preset hub crowd type identification rule; The first hub city is a hub city in any record of the user's transportation hub stay time list, the second hub city is a city name in any record of the user's city zipper entry and exit table, the first moment is the Δt moment before the user represented by each user ID enters the hub, and the second moment is the Δt moment after the user represented by each user ID leaves the hub; The parameters of the preset hub population type discrimination rule include: the length of stay of the user represented by each user identifier at each hub, the first record and the second record; The user terminal signaling data includes at least: user identification, base station ID, base station city, base station entry time, and base station exit time; The conditions for determining the type of people at each hub in the user's transportation hub stay time list include: the length of time the user stays at each hub; whether there is a record of the city where the hub is located before the first recording time Δt before the user's entry into the hub at each hub; whether there is a record of the city where the hub is located after the first recording time Δt after the user's departure from the hub at each hub; The crowd type identification module is also used for: if the user represented by the user identifier stays at the hub for a period of time greater than the set hub stay time threshold t3, and at the first moment, the first record exists, but at the second moment, there is no second record, then the user represented by the user identifier is determined to be a passenger departing from the hub; if the user represented by the user identifier stays at the hub for a period of time greater than the set hub stay time threshold t3, and at the first moment, there is no first record, but at the second moment, there is the second record, then the user represented by the user identifier is determined to be a passenger arriving at the hub; if the user represented by the user identifier has a record of the hub, and at the first moment, the first record exists, but at the second moment, the second record still exists, then the users represented by the user identifier are determined to be the hub seeing-off crowd.

9. A processor-readable storage medium, characterized in that: The processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the method for determining the hub population type according to any one of claims 1 to 6.

Images