A method and system for identifying tobacco cross-trading personnel

Abstract

The present invention relates to a method and system for identifying tobacco cross-region sales personnel in the technical field of tobacco sales, including the following steps: setting a research area and periodically collecting signaling data of mobile phones of users in the research area; performing duplicate data elimination processing on all signaling data of each user to obtain preprocessed data; performing cutting processing on the preprocessed data of each user to obtain suspected cross-region sales travel chain data and / or non-suspected cross-region sales travel chain data; traversing the suspected cross-region sales travel chain data and determining whether it is a tobacco cross-region sales user, which has the advantage of enhancing the supervision intensity of the tobacco sales market and breaking through the bottleneck of being unable to identify tobacco cross-region sales personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco sales, and in particular to a method and system for identifying people who sell tobacco products in pairs. Background Art

[0002] Currently, due to regional differences and varying consumer habits, counterfeit and illicit cigarettes persist. Furthermore, irregular cigarette circulation persists, significantly impacting and disrupting the cigarette market. Furthermore, the tobacco industry implements a bundled sales policy. For example, Province A might bundle its most in-demand and profitable cigarettes with unpopular cigarettes from other provinces for wholesale sales. This administratively regulated "allocation" marketing model exacerbates the prevalence of mixed goods. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the present invention provides a method and system for identifying tobacco smugglers, which has the advantage of enhancing the supervision of the tobacco sales market and breaking through the bottleneck of being unable to identify tobacco smugglers.

[0004] In order to solve the above technical problems, the present invention is solved by the following technical solutions:

[0005] A method for identifying a person who colluded with other tobacco sellers, comprising the following steps:

[0006] Setting a target area and periodically collecting signaling data from user mobile phones within the target area, wherein the target area includes one or more registered tobacco vending points;

[0007] All signaling data of each user is deduplicated to obtain pre-processed data;

[0008] Screening suspected troll travel chains based on pre-processed data to obtain suspected troll travel chains and / or non-suspected troll travel chains;

[0009] Traverse the suspected cross-selling travel chain data and determine whether the user is a tobacco cross-selling user.

[0010] Optionally, the signaling data includes timestamp data, user identification data and base station location information data, the timestamp data is used to mark the acquisition time of the signaling data, the user identification data is used to distinguish the user to whom the signaling data belongs, and the base station location information data is used to mark the user's location.

[0011] Optionally, the deduplication process includes the following steps:

[0012] According to the user identification data, each signaling data of the user is sorted in chronological order to obtain user data;

[0013] Traverse the user data and obtain the time difference and straight-line distance between two adjacent signaling data within the user data;

[0014] Delete the signaling data that appears repeatedly at the same location according to the time difference and straight-line distance to obtain preprocessed data.

[0015] Optionally, deleting the signaling data that appears repeatedly at the same location according to the time difference and straight-line distance includes the following steps:

[0016] Set a distance threshold S1 and a time threshold T, and judge whether the straight-line distance is less than S1 and the time difference is less than T;

[0017] If so, delete the signaling data with a later acquisition time among the two sets of signaling data;

[0018] If not, retain the two sets of signaling data.

[0019] Optionally, screening the suspected cross-region-smuggling trip chain data according to the preprocessed data includes the following steps:

[0020] Set a threshold K for the basic number of signaling data, and delete the user data with the number of signaling data less than K in the preprocessed data to obtain preprocessed and pruned data;

[0021] Traverse each set of the preprocessed and pruned data, and screen out the suspected cross-region-smuggling trip chain data and non-suspected cross-region-smuggling trip chain data according to the positional relationship and time relationship between the data signals in the preprocessed and pruned data.

[0022] Optionally, traverse the suspected cross-region-smuggling trip chain data and judge whether it is a tobacco cross-region-smuggling user, including the following steps:

[0023] Set a threshold Q, and judge whether the number of suspected cross-region-smuggling trip chain data for each user is less than Q;

[0024] If so, mark this user as a non-tobacco cross-region-smuggling user;

[0025] If not, calculate the driving distance and average driving speed of the suspected cross-region-smuggling trip chain data;

[0026] Set a driving distance threshold S2 and an average driving speed threshold V, and judge whether the driving distance is greater than S2 and at the same time judge whether the average driving speed is greater than V;

[0027] If so, mark this user as a tobacco cross-region-smuggling user;

[0028] If not, mark this user as a non-tobacco cross-region-smuggling user.

[0029] Optionally, determining whether a user is a tobacco parallel trader also includes user feature elimination, which eliminates regular users based on the user's residential address feature and eliminates tobacco monopoly users based on the feature of registered tobacco monopoly households.

[0030] Optionally, the user feature elimination includes the following steps:

[0031] Obtain the first location information of the signaling data and the second location information of the last signaling data in the suspected parallel trading travel chain data;

[0032] When the first location information and the second location information are within one kilometer of the target area, it is determined that the user is a regular user, and the user is marked as a non-tobacco parallel trader;

[0033] When the first location information and the second location information are more than one kilometer away from the target area, it is determined that the user is a non-regular user, and the user is marked as a tobacco parallel trader;

[0034] When the user is a registered tobacco monopoly household, the user is marked as a non-tobacco parallel trader.

[0035] A tobacco parallel trader identification system includes a processor and a storage medium, and the storage medium stores the above-mentioned tobacco parallel trader identification method executed by the system.

[0036] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it executes the above-mentioned tobacco parallel trader identification method.

[0037] Adopting the technical solution provided by the present invention, compared with the prior art, it has the following beneficial effects:

[0038] By collecting the signaling data of users, preprocessing and cutting the signaling data, analyzing the signaling data of users, judging the possibility that the user is a tobacco parallel trader based on the analyzed signaling data, and eliminating regular users and registered tobacco monopoly households, thereby increasing the accuracy of judging tobacco parallel traders. By analyzing the signaling data, judging tobacco parallel traders enhances the supervision of the tobacco market and stabilizes the tobacco sales market. Description of the Drawings

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 Flow chart of a method and system for identifying tobacco cross - dealers according to an embodiment of the present invention;

[0041] Figure 2 Signaling data graph of a certain user collected by a method and system for identifying tobacco cross - dealers according to an embodiment of the present invention;

[0042] Figure 3 Pre - processed signaling data graph of a certain user of a method and system for identifying tobacco cross - dealers according to an embodiment of the present invention;

[0043] Figure 4 Graph of suspected cross - dealer travel chain data of a method and system for identifying tobacco cross - dealers according to an embodiment of the present invention. Detailed implementation mode

[0044] The following further elaborates on the present invention in conjunction with embodiments. The following embodiments are explanations of the present invention, and the present invention is not limited to the following embodiments.

[0045] As Figure 1 shown, a method for identifying tobacco cross - dealers includes the following steps: Set a research area, and periodically collect signaling data of mobile phones of users within the research area. The target area includes more than one registered tobacco sales point. The research area can be divided based on, for example, provinces, cities, counties, etc. In this embodiment, the city is used as the research area. Staff collect signaling data of mobile phones of all users within X city and collect it again every once in a while. The collection cycle can be one month, but is not limited to this collection cycle. Staff can set a more reasonable collection cycle according to the cross - dealing cycle of actual tobacco cross - dealers. At the same time, each collection is carried out at a frequency of 10 minutes per time.

[0046] The signaling data includes timestamp data, user identification data, and base station location information data. The timestamp data is used to mark the acquisition time of the signaling data, the user identification data is used to distinguish the owner of the signaling data, and the base station location information data is used to mark the location of the user. When collecting the signaling data, the task interface of the mobile real - time signaling integration platform can be called to submit the base station location information data within X city, and the base station location information data is marked with longitude and latitude. Then, the mobile real - time signaling integration platform returns historical and real - time signaling data according to the task information to complete the collection of the signaling data.

[0047] Deduplicate all signaling data of each user to obtain preprocessed data, including the following steps: Sort each signaling data of the user in chronological order according to the user identification data to obtain user data; Traverse the user data, and obtain the time difference and straight-line distance between two adjacent signaling data in the user data; According to the time difference and the straight-line distance, delete the signaling data that appears repeatedly at the same location to obtain preprocessed data.

[0048] Set a distance threshold S1 and a time threshold T, and judge whether the straight-line distance is less than S1 and the time difference is less than T; If so, delete the signaling data with a later acquisition time in the two groups of signaling data; If not, retain the two groups of signaling data. In this embodiment, S1 can be 100 meters and T can be 1 hour. Assume that a certain user has a total of M signaling data, and there are the i-th data and the (i + 1)-th data at the same time, such that the straight-line distance between the i-th data and the (i + 1)-th data is less than 100 meters and the interval time is less than 1 hour, then it means that the (i + 1)-th data is the signaling data that appears repeatedly at the same location, where M satisfies 1 < i < M - 1. Thus, through such operations, the signaling data that appears repeatedly at the same location is screened out and deleted.

[0049] Furthermore, if in the M signaling data, the straight-line distance between the i-th data and the (i + 2)-th data is less than 500 meters and the interval time is less than half an hour, then it means that the (i + 1)-th data is the signaling data that appears repeatedly between two locations, so the (i + 1)-th data is screened out and deleted, where M satisfies 1 < i < M - 2.

[0050] The preprocessed data is the data after deleting the signaling data that appears repeatedly at the same location and the signaling data that appears repeatedly between two locations.

[0051] Screen the suspected cross-region smuggling travel chain data according to the preprocessed data to obtain suspected cross-region smuggling travel chain data and / or non-suspected cross-region smuggling travel chain data, including the following steps: Set a threshold K for the basic number of signaling data, and delete the user data with the number of signaling data less than K in the preprocessed data to obtain preprocessed and reduced data; Traverse each group of preprocessed and reduced data, and screen out the suspected cross-region smuggling travel chain data and non-suspected cross-region smuggling travel chain data according to the positional relationship and time relationship between the data signals in the preprocessed and reduced data.

[0052] The threshold K can be set to 20. If the number of the preprocessed data of a certain user is less than 20, then the preprocessed data of this user is too small and does not meet the cross-region smuggling frequency condition of tobacco cross-region smugglers. This group of preprocessed data can be deleted, and the preprocessed and deleted data is obtained after deletion.

[0053] Traverse the preprocessed deletion data. If there exist i, j, m, n such that i < j < m < n, and i < j - 3, j < m - 3, m < n - 3, and at the same time, for each signaling data between the j-th data and the m-th data, the distance from its previous signaling data is greater than 500 meters, and the time interval between the j-th data and the m-th data is greater than half an hour; there are more than 3 signaling data between the j-th data and the m-th data whose distance from the tobacco specialty store is less than 500 meters, and the time interval of this part of the data from its next signaling data is greater than 10 minutes; the distances between the signaling data between the i-th data and the j-th data are all less than 500 meters, including the i-th data and the j-th data, and the time interval between the i-th data and the j-th data is greater than half an hour; the distances between the signaling data between the m-th data and the n-th data are all less than 500 meters, and the time interval between the m-th data and the n-th data is greater than half an hour, then determine that the data from the (j + 1)-th data to the (m - 1)-th data is a suspected cross-region tobacco sales travel chain data of a user, and a signaling data belongs to only one suspected cross-region tobacco sales travel chain data. If the above conditions are not met, it is determined as non-suspected cross-region tobacco sales travel chain data, thus dividing all the signaling data of the user into two parts, namely suspected cross-region tobacco sales travel chain data and non-suspected cross-region tobacco sales travel chain data.

[0054] Traverse the suspected cross-region tobacco sales travel chain data and determine whether it is a cross-region tobacco sales user, including the following steps: Set a threshold Q, and determine whether the number of suspected cross-region tobacco sales travel chain data of each user is less than Q; if so, mark this user as a non-cross-region tobacco sales user; if not, calculate the driving distance and average driving speed of the suspected cross-region tobacco sales travel chain data.

[0055] Through research, it is found that cross-region tobacco sales users need to travel back and forth between adjacent districts and counties to carry out cross-region tobacco sales behavior, which is characterized by a large range of activity trajectories, high driving speeds, and high travel frequencies. Therefore, by judging the number of suspected cross-region tobacco sales travel chain data of the obtained users, Q can be set to 5. If the number of suspected cross-region tobacco sales travel chain data is less than 5, then this user is a non-cross-region tobacco sales person, and the signaling data collected from this user is excluded.

[0056] Set a driving distance threshold S2 and an average driving speed threshold V, and determine whether the driving distance is greater than S2 and at the same time determine whether the average driving speed is greater than V; if so, mark this user as a cross-region tobacco sales user; if not, mark this user as a non-cross-region tobacco sales user.

[0057] For each piece of suspected cross-region shipment trip chain data, calculate its driving distance and average driving speed. The driving distance threshold S2 can be set to 15 kilometers, and the average driving speed threshold V can be set to 5 kilometers per hour. If the calculated driving distance is greater than 15 kilometers and the average driving speed is greater than 5 kilometers per hour, then it is determined that this piece of suspected cross-region shipment trip chain data has a high probability of being a cross-region shipment trip chain. If the number of cross-region shipment trip chains obtained by this user within one month is more than 5, then mark this user as a suspected tobacco cross-region shipment user. Among them, the calculation method of the driving distance is the sum of the distances between adjacent signaling data in the suspected cross-region shipment trip chain data, and the calculation method of the average driving speed is the sum of the distances divided by the total interval time between adjacent signaling data in this suspected cross-region shipment trip chain data.

[0058] Determining whether a user is a tobacco cross-region shipment user also includes user feature elimination. User feature elimination means eliminating resident users based on the user's residential address features and eliminating tobacco monopoly users based on the features of registered tobacco monopoly households. Specifically, it includes the following steps: In the suspected cross-region shipment trip chain data, when the location information one and location information two are within one kilometer of the target area, then determine that this user is a resident user and mark this user as a non-tobacco cross-region shipment user; when the location information one and location information two are more than one kilometer outside the target area, then determine that this user is a non-resident user and mark this user as a tobacco cross-region shipment user.

[0059] First, obtain the user's residential address and work address, and determine whether the obtained residential address and work address are within the research area. If so, then determine whether the starting point and ending point of the suspected cross-region shipment trip chain data of this suspected tobacco cross-region shipment user are within one kilometer of the residential address or work address. If so, then determine whether the proportion of all suspected cross-region shipment trip chain data of this suspected tobacco cross-region shipment user that meet the above conditions is greater than 70%. If it is greater, then mark this suspected tobacco cross-region shipment user as a non-tobacco cross-region shipment user and perform elimination.

[0060] On the other hand, obtain the geographical coordinates of all tobacco specialty stores within the research area. If, in the suspected cross-region shipment trip chain data of a suspected tobacco cross-region shipment user, the distance between two adjacent signaling data that are relatively close to the geographical coordinates of the tobacco specialty store is less than 5 kilometers, then mark this suspected tobacco cross-region shipment user as a non-tobacco cross-region shipment user and perform elimination.

[0061] When this user is a registered tobacco monopoly household, then mark this user as a non-tobacco cross-region shipment user. Query whether this user is a user of a registered tobacco specialty store according to the user ID recorded in the signaling data. If it is registered, then mark this suspected tobacco cross-region shipment user as a non-tobacco cross-region shipment user and perform elimination.

[0062] Further, in this embodiment, taking the signaling data of a certain user from January 13, 2021 to January 16, 2021 as an example, the number of collected signaling data of this user is 862. As Figure 2 shown, it is a graph of the longitude of 862 signaling data changing with time, where the abscissa is time and the ordinate is longitude.

[0063] As Figure 3 shown and Figure 2 shown, it is the graph obtained after the preprocessing step. 143 invalid signaling data are cleared, and the total number of signaling data is reduced to 719, with a reduction rate of 16.5%. Compared with Figure 3 and Figure 2 , the signaling data is smoother and the data scale is reduced to a certain extent, which is convenient for subsequent calculations, and finally the suspected cross-region sales travel chain data graph as shown in Figure 4 is obtained.

[0064] A tobacco cross-region sales personnel identification system includes a processor and a storage medium. The storage medium stores a method for identifying tobacco cross-region sales personnel according to any one of the above.

[0065] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it executes the method for identifying tobacco cross-region sales personnel according to any one of the above.

[0066] More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0067] In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless segments, wire segments, optical cables, RF, etc., or any suitable combination of the above.

[0068] In several embodiments provided in this application, it should be understood that the disclosed apparatus and method can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of the modules, units, or components is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units, modules, or components can be combined or integrated into another apparatus, or some features can be ignored or not executed.

[0069] The unit can be or can not be physically separated. The component displayed as a unit can be a physical unit or multiple physical units, that is, it can be located in one place, or can be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0070] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0071] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the method of the present application are performed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above.

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0073] As described above, 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 within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for identifying tobacco parallel traders, characterized in that, Including the following steps: Set a target area, and periodically collect the signaling data of user mobile phones within the target area, where there is more than one registered tobacco sales point within the target area; Perform duplicate data elimination processing on all signaling data of each user to obtain preprocessed data; Screen for suspected cross-region tobacco trafficking travel chain data based on the preprocessed data to obtain suspected cross-region tobacco trafficking travel chains and / or non-suspected cross-region tobacco trafficking travel chains, specifically including the following steps: Set a threshold K for the basic number of signaling data, delete the user data with the number of signaling data less than K in the preprocessed data to obtain preprocessed and pruned data; Traverse each group of the preprocessed and pruned data, and screen for suspected cross-region tobacco trafficking travel chain data and non-suspected cross-region tobacco trafficking travel chain data according to the positional relationship and time relationship between the data signals in the preprocessed and pruned data; Among them, traversing each group of the preprocessed and pruned data, and screening for suspected cross-region tobacco trafficking travel chain data and non-suspected cross-region tobacco trafficking travel chain data according to the positional relationship and time relationship between the data signals in the preprocessed and pruned data includes the following steps: Traverse the preprocessed and deleted data. If there exist i, j, m, n such that i < j < m < n, and i < j - 3, j < m - 3, m < n - 3, and at the same time, each signaling data between the j-th data and the m-th data has a distance greater than the signaling distance configuration threshold from its previous signaling data, and the time interval between the j-th data and the m-th data is greater than the first signaling time configuration threshold; More than a set number of signaling data between the j-th data and the m-th data are less than the signaling distance configuration threshold from a tobacco specialty store, and the time interval of this part of the data from its next signaling data is greater than the second signaling time configuration threshold; The distances between the signaling data between the i-th data and the j-th data are all less than the signaling distance configuration threshold, including the i-th data and the j-th data, and the time interval between the i-th data and the j-th data is greater than the first signaling time configuration threshold; The distances between the signaling data between the m-th data and the n-th data are all less than the signaling distance configuration threshold, and the time interval between the m-th data and the n-th data is greater than the first signaling time configuration threshold, then it is determined that the data from the (j + 1)-th data to the (m - 1)-th data is a suspected cross-region tobacco trafficking travel chain data of a user, and a signaling data belongs to only one suspected cross-region tobacco trafficking travel chain data. If the above conditions are not met, it is determined as non-suspected cross-region tobacco trafficking travel chain data; Traverse the suspected cross-region tobacco trafficking travel chain data and determine whether it is a tobacco cross-region trafficking user, specifically including the following steps: Set a threshold Q, and determine whether the number of suspected cross-region tobacco trafficking travel chain data of each user is less than Q; If so, mark this user as a non-tobacco cross-region trafficking user; If not, calculate the driving distance and average driving speed of the suspected cross-region tobacco trafficking travel chain data; Set a driving distance threshold S2 and an average driving speed threshold V, and determine whether the driving distance is greater than S2 and at the same time determine whether the average driving speed is greater than V; If so, mark this user as a tobacco cross-region trafficking user; If not, mark this user as a non-tobacco cross-region trafficking user.

2. The method for identifying tobacco cross-region sales personnel according to claim 1, wherein the signaling data includes timestamp data, user identification data, and base station location information data. The timestamp data is used to mark the acquisition time of the signaling data, the user identification data is used to distinguish the user to whom the signaling data belongs, and the base station location information data is used to mark the location of the user.

3. The method for identifying tobacco cross-region sales personnel according to claim 2, wherein the duplicate data elimination process includes the following steps: Sort each signaling data of the user in chronological order according to the user identification data to obtain user data; Traverse the user data, and obtain the time difference and straight-line distance between two adjacent signaling data in the user data; Delete the signaling data that repeatedly appears at the same location according to the time difference and straight-line distance to obtain preprocessed data.

4. The method for identifying tobacco cross-region sales personnel according to claim 3, deleting the signaling data that repeatedly appears at the same location according to the time difference and straight-line distance, includes the following steps: Set a distance threshold S1 and a time threshold T, and determine whether the straight-line distance is less than S1 and the time difference is less than T; If so, delete the signaling data with a later acquisition time in the two groups of signaling data; If not, retain the two groups of signaling data.

5. The method for identifying tobacco cross-region sales personnel according to claim 1, judging whether it is a tobacco cross-region sales user further includes user feature elimination, and the user feature elimination is to eliminate resident users according to the characteristics of the user's residential address and eliminate tobacco monopoly users according to the characteristics of registered tobacco monopoly households.

6. The method for identifying tobacco cross-region sales personnel according to claim 5, wherein the user feature elimination includes the following steps: Obtain the location information one of the first signaling data and the location information two of the last signaling data in the suspected cross-region sales travel chain data; When the location information one and the location information two are within one kilometer of the target area, determine that the user is a resident user and mark the user as a non-tobacco cross-region sales user; When the location information one and the location information two are more than one kilometer away from the target area, determine that the user is a non-resident user and mark the user as a tobacco cross-region sales user; When the user is a registered tobacco monopoly household, mark the user as a non-tobacco cross-region sales user.

7. A tobacco cross-selling personnel identification system, comprising a processor and a storage medium, characterized in that, The storage medium stores the method for identifying tobacco cross-region sales personnel according to any one of claims 1-6.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it executes the method for identifying tobacco cross-region sales personnel according to any one of claims 1-6.

Images