JP5628133B2 - Name identification apparatus and name identification method - Google Patents

Description

  The present invention relates to a name identification device and a name identification method.

In recent years, traffic IC (Integrated Circuit) cards that can be used as traffic tickets and electronic money have rapidly spread, and along with this, various information services using traffic IC cards are also spreading. For example, the invention disclosed in Patent Document 1 calculates the stay rate around the station for each hour from the use history of a traffic IC card that is a set of location information and time information of a moving individual. Then, by matching the stay rate around the station with the area information, information suitable for the user of the transportation IC card is provided.
On the other hand, when providing such an information providing service, it is conceivable that one user holds a plurality of transportation IC cards. Therefore, it is necessary to perform “name identification”. “Name collation” is a process of assigning a unique key to the same customer by using, as a key, attribute information that can identify the customer, such as an address, name, and telephone number, in a financial institution or the like.
In the case of a traffic IC card, the registered attribute information may be inaccurate. Furthermore, since the input of the information is arbitrary, an item itself may not be registered. Due to this, it is generally difficult to identify traffic IC cards with high accuracy. For example, Patent Document 2 is disclosed as an invention for collating traffic IC cards. In the invention of Patent Document 2, name identification is performed using a customer's credit card number in addition to attribute information.

JP 2004-102950 A (paragraph 0010) JP 2010-55227 A (paragraph 0008)

However, the invention of Patent Document 1 does not assume name identification at all. The invention of Patent Document 2 is effective when one user purchases a product or the like using only one credit card. However, when a single user uses a plurality of credit cards or purchases a product or the like without using a credit card in the first place, name identification cannot be performed.
Therefore, an object of the present invention is to perform name identification of a traffic IC card with high accuracy.

The name identification device of the present invention is a name identification device that determines the identity of a plurality of users who use a plurality of portable information storage media, and the attribute information of the user is associated with the identifier of the portable information storage medium. Memory storing user attribute information to be stored and usage history information in which the time and section when the transportation facility is used using the portable information storage medium are stored in association with the identifier of the portable information storage medium And a combination of identifiers of portable information storage media that may be used by the same user based on attribute information, and a determination result for each acquired combination based on usage history information A first determination result indicating that the same user is using two portable information storage media of the acquired combination, and the accompanying determination unit Combinations acquired by the user Second determination result indicating that two portable information storage media are used, and third determination result indicating that a different user is using two portable information storage media in the acquired combination , And any one of a first determination result, a second determination result, and a fourth determination result indicating that it cannot be said to be any of the third determination results. .
Other means will be described in detail in the detailed description.

  According to the present invention, it is possible to identify traffic IC cards with high accuracy.

It is a figure explaining the relationship between the name collation apparatus which concerns on this embodiment, a boarding ticket system, and an information terminal device. It is a figure explaining the structure of the name collation apparatus which concerns on this embodiment. It is a figure explaining the outline | summary of the process which the name collation apparatus which concerns on this embodiment performs. It is a figure which shows an example of the name collation condition information which concerns on this embodiment. It is a figure which shows an example of the user attribute information which concerns on this embodiment. It is a figure which shows an example of the usage history information which concerns on this embodiment. It is a figure which shows an example of the transfer time information which concerns on this embodiment. (A) is a figure showing an example of name collation intermediate information concerning this embodiment. (B) is a figure which shows an example of the name collation result information which concerns on this embodiment. It is a flowchart of the name collation condition setting process sequence which concerns on this embodiment. It is a flowchart of the name collation process sequence which concerns on this embodiment. It is a flowchart of the name collation process procedure (continuation) which concerns on this embodiment. It is an example of the name collation condition setting screen which concerns on this embodiment.

  Hereinafter, a mode for carrying out the present invention (referred to as “the present embodiment”) will be described in detail with reference to the drawings and the like. In the following, an example in which a user of a transportation IC card (hereinafter sometimes simply referred to as “user”) uses a railroad will be described. However, the present invention can be widely applied when the user uses a transportation system other than the railway, such as a route bus, and also when the user uses both the railway and the transportation system other than the railway.

(Positioning of name identification device etc.)
The relationship between the name identification device 1, the ticket system 2 and the information terminal device 3 will be described with reference to FIG. 1. The name collation apparatus 1 is mutually connectable with the boarding ticket system 2 and the information terminal device 3 via the networks 4a and 4b, respectively.

The name collation apparatus 1 is a general computer, and collates the user of the traffic IC card 9 (details will be described later). The information terminal device 3 is also a general computer, and is used when a user of the name collation device 1 sets name collation condition information (detailed later) for the name collation device 1. The name collation apparatus 1 is usually managed by a railway company or by a main body that provides a service for performing name identification to the railway company, and the number thereof is one. The information terminal device 3 is also usually managed by a railway company or by a main body that provides a service for performing “name identification” to the railway company, but the number thereof is plural.
The “portable information storage medium” corresponds to a transportation IC card.

  The ticket system 2 includes an automatic ticket gate 5, a station server 6 and a management server 7. The automatic ticket gate 5 and the station server 6 can communicate with each other via the network 8a. The station server 6 and the management server 7 can communicate with each other via the network 8b. The automatic ticket gate 5 is an entrance / exit gate having an IC card reader. The automatic ticket gate 5 reads information stored in the traffic IC card 9 passing through the automatic ticket gate 5. The transportation IC card 9 is, for example, a regular ticket, a registered prepaid card, or the like. There are usually a plurality of automatic ticket gates 5 at one station.

The station server 6 is a general computer, and accumulates usage history information 33 (details described later) read by the automatic ticket gate 5 for each station. One station server 6 usually exists at one station. The management server 7 is also a general computer, and accumulates usage history information 33 read by the automatic ticket gate 5 for each railway company. One management server 7 usually exists in one railway company.
As is apparent from the above, there are usually as many ticket systems 2 as there are railway companies, and one ticket system 2 includes one management server 7, a plurality of station servers 6, and a plurality of automatic ticket gates 5. Will have.

(Name identification device)
The structure of the name collation apparatus 1 is demonstrated along FIG. The name identification device 1 includes a central control device 11, a main storage device 12, an auxiliary storage device 13, an input device 14, an output device 15, and a communication interface 16. These are connected to each other by a bus. The auxiliary storage device 13 stores name identification condition information 31, user attribute information 32, usage history information 33, transfer time information 34, name identification intermediate information 35, and name identification result information 36 (details will be described later). The name identification unit 21 and the name identification condition setting unit 22 are programs. In the following, when the subject of the operation is described as “XX section is”, the central controller 11 reads the XXX section as a program from the auxiliary storage device 13 and loads it into the main storage device 12. Then, the function (detailed later) of the program is executed.

  Each of the information terminal device 3, the station server 6, and the management server 7 includes a central control device, a main storage device, an auxiliary storage device, an input device, an output device, and a communication interface that are connected to each other by a bus (not shown). ).

(Outline of processing)
The outline of the processing executed by the name identification device 1 will be described with reference to FIG.
The name identification device 1 creates name identification condition information based on an input from the user (name identification condition setting process P1). The name identification condition information stores search conditions and the like necessary for the user attribute information name identification process P3 and the use history information name identification process P5.
The name collation apparatus 1 acquires user attribute information from the ticket system 2 (user attribute information acquisition process P2). User attribute information stores user attribute information (name, gender, etc.). The name collation apparatus 1 acquires use history information from the ticket system 2 (use history acquisition process P4). In the usage history information, a usage history of the transportation IC card 9 is stored.

The name identification device 1 searches the user attribute information based on the name identification condition information and creates name identification intermediate information (user attribute information name identification process P3). The name identification intermediate information is an incomplete intermediate result of name identification created by searching only user attribute information without searching usage history information.
The name identification device 1 searches the usage history information based on the name identification intermediate information and the name identification condition information, and creates name identification result information (use history information name identification process P5). The name identification result information is a final result of name identification created by searching both user attribute information and usage history information.

(Name identification condition information)
The name identification condition information 31 will be described with reference to FIG. In the name identification condition information 31, the condition item value is stored in the condition item value field 102 in association with the condition item stored in the condition item field 101.

The condition items in the condition item column 101 are search key and threshold items used in the above-described user attribute information name identification process P3 and use history information name identification process P5. Here, there are at least four condition items: “attribute key”, “frequency”, “transfer time width”, and “accompanying action time width” (details will be described later).
The condition item value in the condition item value column 102 is a specific value of the condition item, and is the above-described search key and threshold value itself.

(User attribute information)
The user attribute information 32 will be described with reference to FIG. In the user attribute information 32, in association with the card ID stored in the card ID column 111, the name column 112 has a name, the gender column 113 has a gender, and the date of birth column 114 has a date of birth. The telephone number column 115 stores a telephone number, the regular interval column 116 stores a regular interval, and the regular type column 117 stores a regular type.
The card ID in the card ID column 111 is an identifier that uniquely identifies the transportation IC card 9.
The name in the name column 112 is the name of the user.
The gender in the gender column 113 is the gender of the user.
The gender in the date of birth column 114 is the date of birth of the user.
The telephone number in the telephone number column 115 is a user's telephone number.
The regular section in the regular section field 116 is a combination of the starting station name and the ending station name of the section where the fare is a fixed fee regardless of the number of times of travel, when the traffic IC card 9 also serves as a “regular ticket”. It is. When the transportation IC card 9 does not serve as a “regular ticket”, “−” is stored.

The regular type in the regular type column 117 indicates the category of the regular ticket when the transportation IC card 9 also serves as the “regular ticket”. Here, it is either “commuting” or “commuting”. When the transportation IC card 9 does not serve as a “regular ticket”, “−” is stored.
Each time the transportation IC card 9 is issued, the record of the user attribute information 32 is created one by one based on an input from a terminal device such as a regular ticket issuing window at the station. Identity verification at the time of data entry is not essential. Therefore, the data of the record of the user attribute information 32 is not completely accurate and is often not updated to the latest data.

(Usage history information)
The usage history information 33 will be described with reference to FIG. In the usage history information 33, in association with the card ID stored in the card ID column 121, the time column 122 shows the time, the processing name column 123 shows the processing name, the terminal name column 124 shows the terminal name, The amount of money column 125 stores a usage amount.
The card ID in the card ID column 121 is the same as the card ID in FIG.
The time in the time column 122 is the month and date when the automatic ticket gate 5 reads the traffic IC card 9. The time may include year and second.

  The process name in the process name column 123 is the name of the process performed by the automatic ticket gate 5. When the traffic IC card 9 is read by the automatic ticket gate 5 and the traffic IC card 9 passes from the station premises toward the station premises, the processing name is “entrance”. When the traffic IC card 9 passes from the inside of the station to the outside of the station, the process name is “participation”. In the present embodiment, the automatic ticket gate 5 uses the traffic IC card 9 in the store when the user uses the traffic IC card 9 to shop at a store located inside or outside the station, for example. Includes vending machines that read. In this case, the process name is “product purchase”. Furthermore, the automatic ticket gate 5 includes, for example, a charging machine that is used when a user charges cash to the transportation IC card 9 and is located inside and outside the station. In this case, the process name is “charge”.

The terminal name in the terminal name column 124 is an identifier that uniquely identifies the automatic ticket gate 5 (including vending machines, charging machines, etc.). The terminal name includes the name of the station where the automatic ticket gate 5 is located, such as “A station 0001” and “B station vending machine 01”, so that the location where the user has passed can be identified. It can be specified. Since the user always enters after entering, the “place” indicates a section using the transportation facility.
The usage amount in the usage amount column 125 is the amount of change in the charge balance stored in the transportation IC card 9 before and after the processing. A negative number is stored when it decreases, and a positive number is stored when it increases. Usually, a negative number corresponds to “product purchase” or “participation” (other than using a regular ticket), and a positive number corresponds to “charge”. The process name “entrance” usually corresponds to the usage amount “0”.

(Transfer time information)
The transfer time information 34 will be described with reference to FIG. In the transfer time information 34, the transfer time column 133 stores the transfer time in association with the combination of the station name 1 stored in the station 1 column 131 and the station name 2 stored in the station 2 column 132.
A user passes an automatic ticket gate 5 of a certain station and goes out of the station, and then passes through an automatic ticket gate 5 of another station and enters the station, that is, “participates” in a certain station. “Entering” another station within a predetermined time (the “transfer time” described later) is referred to as “transfer” in the present embodiment. The “one station” and the “other station” do not have to be stations of the same railway company. Furthermore, “one station” and “other station” need not have the same station name.

The station name 1 in the station 1 column 131 is the name of the “certain station” described above. Here, it is a combination of a railway company name, a route name, and a station name in more detail.
The station name 2 in the station 2 column 132 is the name of the “other station” described above. Here, it is a combination of a railway company name, a route name, and a station name in more detail.
The transfer time in the transfer time column 133 is an average time until the user enters “a certain station” and enters “another station”. The transfer time varies depending on the distance between “a certain station” and “another station”, the degree of congestion, and the like.

(Name identification intermediate information)
The name identification intermediate information 35 will be described with reference to FIG. The name identification intermediate information 35 has the same user card ID column 141 which is the only column. In each record, the card IDs of the plurality of transportation IC cards 9 that the name identification device 1 determines that the same user may be using in the user attribute information name identification process P3 are the same user. It is stored as a card ID.
For example, referring to the record on the first line, the traffic IC card 9 whose card ID is “12345” and the traffic IC card 9 whose card ID is “78901” are used by the same user. It can be seen that the name identification device 1 makes a determination in the user attribute information name identification process P3 (FIG. 3). Similarly, referring to the record in the second row, a traffic IC card 9 with a card ID “37777”, a traffic IC card 9 with a card ID “40000”, and a traffic IC card with a card ID “12789”. If the card 9 is used by the same user, it can be seen that the name identification device 1 makes a determination in the user attribute information name identification process P3.

(Name identification result information)
The name identification result information 36 will be described with reference to FIG. In the name identification result information 36, a determination result is stored in the determination result column 152 in association with the same user card ID stored in the same user card ID column 151.
The same user card ID in the same user card ID column 151 is the same as the same user card ID in FIG.
The determination result in the determination result column 152 indicates a result of the name identification device 1 finally determining the relationship between the plurality of identical user card IDs in the usage history information name identification process P5 (FIG. 3). Information. In this embodiment, there are four types of determination results: “same user”, “accompanying person”, “different user”, and “unknown”.

  “Same user” indicates that a plurality of transportation IC cards 9 are used by the same user. The case where one user uses the traffic IC card 9 for each railway company or for each route corresponds to “same user”. In this case, by performing name identification, for example, a plurality of stations where a plurality of transportation IC cards 9 are used, which gives points to the user according to the total amount of usage charges of the plurality of transportation IC cards 9 It is possible to provide a service such as providing local information in the vicinity to the same user.

  “Accompanying person” indicates that a plurality of traffic IC cards 9 are used by different users, but these users are acting together. For example, a case where a parent lends a registered prepaid card to a child and moves as a family corresponds to “accompanying person”. In this case, by performing name identification, it becomes possible to provide guidance on services that can be provided to close friends, such as family trips and group trips.

“Different users” indicates that a plurality of transportation IC cards 9 are used by different users. For example, when a user who is likely to be a user passes through a station far away from a certain station at approximately the same time when the user passes a certain station, it corresponds to a “different user”. . Even if a user who may be the relevant user “entry” (or “participation”) after “entry” to “entry”, it will be changed to “different user”. Equivalent to.
“Unknown” means that the name identification device 1 uses the relationship between the two traffic IC cards 9 in the usage history information name identification process P5 (FIG. 3), whether it is “same user” or “accompanying person”. Furthermore, it indicates that the user cannot be determined as a “different user”.

(Processing procedure)
Hereinafter, the processing procedure of the present embodiment will be described with reference to FIGS. There are two processing procedures: (1) name identification condition setting processing procedure and (2) name identification processing procedure. In order for (2) to be executed, it is assumed that (1) has been completed. (1) corresponds to the process of reference P1 in FIG. (2) corresponds to the processing of reference numerals P2 to P5 in FIG.

(Name identification condition setting process)
The name identification condition setting processing procedure will be described with reference to FIG.
In step S301, the name identification condition setting unit 22 of the name identification device 1 displays the name identification condition setting screen 41 (FIG. 12). The name identification condition setting screen 41 is displayed on the output device of the information terminal device 3. The name identification condition setting screen 41 is a screen for accepting input of data in order to create the name identification condition information 31 (FIG. 4). The name collation condition setting screen 41 includes an attribute name collation condition column 161, a use history name collation condition column 162, and an end button 163. The attribute name identification condition column 161 corresponds to the record in the first line of the name identification condition information 31, and the user can select items such as name, sex, date of birth, and the like as attribute keys (search keys). Yes. The use history name identification condition column 162 corresponds to the records in the second to fourth lines of the name identification condition information 31, and the user can input a threshold such as a transfer time width.

In step S <b> 302, the name identification condition setting unit 22 receives “initial registration” or “setting change”. Specifically, the name collation condition setting unit 22 firstly inputs “initial registration when registering name collation condition information for the first time. In other cases, a message such as “Please input setting change” is displayed on the output device of the information terminal device 3.
Second, the name identification condition setting unit 22 accepts that the user inputs “initial registration” or “setting change” via an input device such as a keyboard.

  In step S <b> 303, the name identification condition setting unit 22 determines whether “setting change” has been input. Specifically, the name identification condition setting unit 22 proceeds to step S304 when “setting change” is received in “second” in step S302 (step S303 “YES”), and otherwise (step S303 “ NO ") proceeds to step S306.

  In step S304, the name identification condition setting unit 22 determines whether or not the item condition value after the change has been accepted. Specifically, the name identification condition setting unit 22 performs at least one attribute key in the attribute name identification condition column 161 of the name identification condition setting screen 41 (FIG. 12) until a predetermined time elapses after step S303 ends. Is selected and three threshold values are entered in the usage history name identification condition field 162 and the end button 163 is pressed (“YES” in step S304), the process proceeds to step S305. In other cases (step S304 “NO”), the name identification condition setting processing procedure ends. The name identification condition setting unit 22 highlights the existing registered attribute key and threshold value (flashing display etc. that promotes overwriting), and “Please set the changed value for the registered data” A message may also be displayed.

In step S <b> 305, the name identification condition setting unit 22 updates the record of the name identification condition information 31. Specifically, the name identification condition setting unit 22 overwrites and stores the attribute key and threshold value selected (or input) in step S304 for the existing record of the name identification condition information 31.
Thereafter, the name identification condition setting processing procedure is terminated.

  In step S306, the name identification condition setting unit 22 receives a condition item value. Specifically, the name identification condition setting unit 22 selects at least one attribute key in the attribute name identification condition column 161 of the name identification condition setting screen 41 (FIG. 12), and 3 in the usage history name identification condition column 162. It is accepted that the user presses the end button 163 after inputting one threshold value.

In step S307, the name identification condition setting unit 22 creates a record of the name identification condition information 31. Specifically, the name identification condition setting unit 22 newly creates name identification condition information 31, and stores the attribute key and threshold value selected (or input) in step S306 for each record.
Thereafter, the name identification condition setting processing procedure is terminated.

(Name identification process)
A name identification process procedure will be described with reference to FIGS. 10 and 11.
In step S401, the name collation part 21 of the name collation apparatus 1 acquires name collation condition information 31 (FIG. 4) and user attribute information 32 (FIG. 5).

In step S402, the name collation unit 21 creates name collation intermediate information 35 (FIG. 8A). Specifically, the name collation part 21 acquires the condition item value (attribute key) of the record of the 1st line of the name collation condition information 31 first. Here, it is assumed that “name”, “sex”, and “birth date” are acquired.
Secondly, the name collation unit 21 converts the value of the column having the condition item value (attribute key) acquired in “first” of step S402 in the column of the user attribute information 32 into the hash function. The “hash value” is obtained as an output. This process is performed for all records of the user attribute information 32. For example, when “Kazuo Suzuki, male, 1990/01/01” is input to the hash function, the range of the number of digits and the size is normalized, and a hash value that is easy to compare with each other is output. . When the hash values are close to each other, input values such as character strings and numerical values are close to each other.

  Thirdly, the name collation unit 21 has a plurality of records of the user attribute information 32 that have the same hash value, or the difference between them is within a predetermined numerical range even if it is not the same. Group things together. In other words, the records that are obtained in “first” in step S402 and that all condition item values (attribute keys) are approximate to each other are grouped. The number of records belonging to the same group may be any number as long as it is plural. Note that grouping using hash values is merely an example, and the name collation unit 21 may perform grouping by other known methods.

  Fourthly, the name identification unit 21 newly creates a record of the name identification intermediate information 35 by the number of groups. Then, the card ID combinations of all the records belonging to the group are stored in the same user card ID column 141 of the newly created record for each group.

  In step S403, the name identification unit 21 acquires one record of the name identification intermediate information 35. Here, for example, it is assumed that the record in the first row in FIG. The records acquired here may be referred to as “name identification target records” hereinafter.

In step S404, the name collation part 21 acquires the usage history information 33 (FIG. 6). Specifically, the name collation unit 21 firstly uses the one of the same user card IDs stored in the name collation target record (for example, “12345”) as a search key, and uses history information 33. And the group of the corresponding records is set as the “first group”.
Second, the name collation unit 21 retrieves the usage history information 33 using another arbitrary one of the same user card IDs (for example, “78901”) stored in the name identification target record as a search key, A group of the corresponding records is referred to as a “second group”.

  In step S405, the name collation part 21 totals the utilization frequency of a station. Specifically, the name collation unit 21 first sorts the records for each of the first group and the second group using the station name included in the terminal name as a key, and totals the number of records including the same station name. To do. In this process, the name collation unit 21 obtains information [card ID, station name, use frequency] that associates the use frequency for each combination of the card ID and the station name. Note that the name collation unit 21 may delete the acquired information [card ID, station name, use frequency] whose use frequency is less than the condition item value (frequency) on the second line of the name collation condition information 31. Good.

  Second, the name collation unit 21 sorts [card ID, station name, use frequency] in order of frequency of use, so that for each card ID, [card ID, name of station with the highest use frequency, second use frequency Get the information that the station name is high, the third ...

In step S406, the name collation part 21 checks the coincidence between the regular station and the frequently used station. Specifically, the name collation unit 21 first searches the user attribute information 32 (FIG. 5) using the card ID of the first group as a search key, and the “starting point” included in the regular section of the corresponding record. Get “station name” and “end station name”.
Secondly, the name collation unit 21 is the second group of the acquired information [card ID, name of the station with the highest use frequency, name of the station with the second highest use frequency, third,...]. Are identified, and “the most frequently used station name” included in the identified information is acquired.
Thirdly, the name collation unit 21 thirdly obtains at least one of “starting station name” and “ending station name” acquired in “first” in step S406 and “second” in step S406. It is checked whether or not “the most frequently used station name” matches. Then, as the investigation result, the name collation unit 21 generates either “match” or “do not match”.
If the “starting station name” and the “ending station name” cannot be acquired (there is no use of a regular ticket), the name collation unit 21 omits steps S406 and S407 and proceeds to step S408.

  In step S407, the name collation unit 21 determines whether or not the regular station and the frequently used station match. Specifically, the name collation unit 21 proceeds to step S418 if the investigation result generated in “third” in step S406 is “match” (step S407 “YES”), and otherwise ( In step S407 “NO”), the process proceeds to step S408.

In step S408, the name collation part 21 investigates the coincidence between stations with high use frequency. Specifically, the name collation unit 21 firstly, among the information of [Card ID, the name of the station with the highest use frequency, the name of the station with the highest use frequency, the third with the frequency of use, etc.] Then, the one having the card ID of the first group is specified, and “the most frequently used station name” included in the specified information is acquired.
Second, the name collation unit 21 matches the “most frequently used station name” acquired in “first” in step S408 with the “most frequently used station name” acquired in “second” in step S406. Investigate whether or not to do so. When not passing through step S406, the name collation part 21 has acquired information [Card ID, the name of the station with the highest use frequency, the name of the station with the second highest use frequency, the third,... Among them, the one having the card ID of the second group is specified, and after acquiring “the most frequently used station name” included in the specified information, it is checked whether or not they match. Then, as the investigation result, the name collation unit 21 generates either “match” or “do not match”.

  In step S409, the name collation part 21 judges whether stations with high use frequency correspond. Specifically, the name collation unit 21 proceeds to step S418 if the investigation result generated in “second” in step S408 is “match” (step S409 “YES”), and otherwise ( In step S409 “NO”), the process proceeds to step S410.

  In step S410, the name collation unit 21 checks whether there is a history corresponding to transfer. Specifically, the name collation unit 21 first searches the usage history information 33 using the card ID of the first group and the process name “participation” as a search key, and finds the station name included in the terminal name of the corresponding record. Specify “participation transfer station”, and specify the time of the record as “participation time”. There may be multiple corresponding records.

  Second, the name collation unit 21 searches the usage history information 33 using the card ID of the second group and the process name “entrance” as a search key, and sets the station name included in the terminal name of the corresponding record to “entrance transfer station”. And the time of the record is specified as “entrance time”. There may be multiple corresponding records.

Thirdly, the name identification unit 21 checks whether or not there is at least one history that satisfies all of the following conditions 1 to 4.
(Condition 1) The combination of “entrance transfer station” and “entrance transfer station” matches either of the combination of station name 1 and station name 2 in FIG. The matched combination is referred to as “transfer station combination”.
(Condition 2) “Monday” included in “Enter Time” matches “Monday” included in “Admission Time”.
(Condition 3) With regard to “entry time” and “entrance time” with the same “month and day” in condition 2, “hour and minute” included in “entry time” is more than “hour and minute” included in “entry time” It is before in time.
(Condition 4) For “Entering Time” and “Entering Time” with the same “Month and Date” in Condition 2, “Hours” included in “Entering Time” are subtracted from “Hours” included in “Entering Time” The difference is smaller than the value obtained by adding the condition item value (transfer time width) on the third line of the name identification condition information 31 to the transfer time of the record of the transfer time information 34 having “transfer station combination”.
Fourthly, the name collation unit 21 generates either “exists” or “does not exist” as the investigation result.

  In step S411, the name collation unit 21 determines whether there is a history corresponding to transfer. Specifically, the name collation unit 21 proceeds to step S418 if the investigation result generated in “fourth” in step S410 is “exists” (step S411 “YES”), and otherwise ( In step S411 “NO”), the process proceeds to step S412.

  In step S412, the name collation unit 21 checks whether there is a history corresponding to the accompanying behavior. Specifically, the name collation unit 21 first searches the usage history information 33 using the card ID of the first group and the process name “entrance” or “participation” as a search key, and sets the terminal name of the corresponding record. The station name included is specified as “accompanying entry / exit station 1”, and the time of the record is specified as “accompanying entry / exit time 1”. There may be multiple corresponding records.

Second, the name collation unit 21 searches the use history information 33 using the card ID of the second group and the process name “entrance” or “participation” as a search key, and sets the station name included in the terminal name of the corresponding record to “ “Accompanying entry / exit station 2” is specified, and the time of the record is specified as “accompanying entry / exit time 2”. There may be multiple corresponding records.
Note that when “entrance” is used as a search key in “first”, “entrance” is also used as a search key in “second”. Similarly, when “participation” is used as a search key in “first”, “participation” is also used as a search key in “second”.

Third, the name identification unit 21 checks whether there is at least one history that satisfies all of the following conditions 5 to 7.
(Condition 5) “Accompanying entry / exit station 1” and “Accompanying entry / exit station 2” match.
(Condition 6) “Month / day” included in “accompanying entry / exit time 1” matches “month / day” included in “accompanying admission / entry time 2”.
(Condition 7) For “Accompanying Entrance / Exit Time 1” and “Accompanying Entrance / Exit Time 2” with the same “Month / Day” in Condition 6, “Accompanying Enter / Exit Time 1” The absolute value of the difference obtained by subtracting “hour” included in “participation time 2” is smaller than the condition item value (accompanying action time width) of the record in the fourth line of the name identification condition information 31.
Fourthly, the name collation unit 21 generates either “exists” or “does not exist” as the investigation result.

  In step S413, the name collation unit 21 determines whether there is a history corresponding to the accompanying behavior. Specifically, the name collation unit 21 proceeds to step S419 if the investigation result generated in “fourth” in step S412 is “exists” (step S413 “YES”), and otherwise ( Step S413 “NO”) proceeds to Step S414.

In step S414, the name collation unit 21 checks whether there is a history corresponding to a different user. Specifically, the name identification unit 21 checks whether or not there is at least one history that satisfies all of the following conditions 8 to 10.
(Condition 8) “Accompanying station 1” and “Accompanying station 2” are different.
(Condition 9) “Monday” included in “Accompanying entry / exit time 1” matches “Monday” included in “Accompanying entry / exit time 2”.
(Condition 10) For “Accompanying Entrance / Exit Time 1” and “Accompanying Entrance / Exit Time 2” with the same “Month / Day” in Condition 9, “Accompanying Enter / Exit Time 1” The absolute value of the difference obtained by subtracting “hour” included in “participation time 2” is smaller than the condition item value (accompanying action time width) of the record in the fourth line of the name identification condition information 31.
The name collation unit 21 generates either “exists” or “does not exist” as the investigation result.

The name collation part 21 may perform the following step S414 (the 2) instead of the process of step S414 mentioned above.
In step S414 (part 2), the name collation unit 21 checks whether there is a history corresponding to a different user. Specifically, the name collation unit 21 first searches the usage history information 33 using the card ID of the first group and the process name “admission” as a search key, and finds the station name included in the terminal name of the corresponding record. “Accompanying admission station 1” is specified, and the time of the record is specified as “accompanying admission time 1”. There may be multiple corresponding records.

  Second, the name collation unit 21 searches the usage history information 33 using the card ID of the first group and the process name “participation” as a search key, and determines the station name included in the terminal name of the corresponding record as “accompanying station 1 ", And the time of the record is specified as" accompanying appearance time 1 ". There may be multiple corresponding records.

  Thirdly, the name collation unit 21 searches the usage history information 33 using the card ID of the second group and the process name “admission” as a search key, and determines the station name included in the terminal name of the corresponding record as “accompanying admission station 2”. And the time of the record is specified as “accompanying admission time 2”. There may be multiple corresponding records.

  Fourth, the name collation unit 21 searches the usage history information 33 using the card ID of the second group and the process name “participation” as a search key, and determines the station name included in the terminal name of the corresponding record as “accompanying station 2 And the time of the record is specified as “accompanying appearance time 2”. There may be multiple corresponding records.

Fifth, the name collation unit 21 checks whether there is at least one history that satisfies all of the following conditions 11 to 13.
(Condition 11) “Accompanying admission station 1” and “accompanying admission station 2” are different. Or “accompanying station 1” and “accompanying station 2” are different.
(Condition 12) “Month and day” included in “accompanying admission time 1” are “month and date” included in “accompanying admission time 2”, “month and date” included in “accompanying admission time 1”, and “ Matches all of the “month and day” included in the “participation time 2”.
(Condition 13) For “accompanying admission time 1” etc. in which “month and day” match in condition 12, “hour and minute” included in “accompanying admission time 1” and “hour and minute included in“ accompanying admission time 1 ” "Hour and minute" included in "Accompanying admission time 2" or "Hour and minute" included in "Accompanying admission time 2" are included in the period between the time and "."
Sixth, the name identification unit 21 generates either “exists” or “does not exist” as the investigation result.

  In step S415, the name collation part 21 judges whether there exists a log | history applicable to a different user. Specifically, in the case where the investigation result generated in step S414 (or “sixth” in step S414 (part 2)) is “exists” (step S415 “YES”), the name collation unit 21 The process proceeds to step S417, and otherwise (step S415 “NO”), the process proceeds to step S416.

In step S416, the name collation unit 21 adds “unknown” to the name collation result information 36 (FIG. 8B). Specifically, first, the name identification unit 21 creates a new record of the name identification result information 36.
Second, the name identification unit 21 stores the same user card ID of the “name identification target record” in the same user card ID column 151 of the new record, and generates “unknown” in the determination result column 152. Remember me.

In step S417, the name collation unit 21 adds “different user” to the name collation result information 36 (FIG. 8B). Specifically, first, the name identification unit 21 creates a new record of the name identification result information 36.
Second, the name identification unit 21 stores the same user card ID of the “name identification target record” in the same user card ID column 151 of the new record, and generates “different user” in the determination result column 152. And remember.

In step S418, the name collation unit 21 adds “same user” to the name collation result information 36 (FIG. 8B). Specifically, first, the name identification unit 21 creates a new record of the name identification result information 36.
Second, the name identification unit 21 stores the same user card ID of the “name identification target record” in the same user card ID column 151 of the new record, and generates “same user” in the determination result column 152. And remember.

In step S419, the name collation unit 21 adds “accompanying person” to the name collation result information 36 (FIG. 8B). Specifically, first, the name identification unit 21 creates a new record of the name identification result information 36.
Second, the name collation unit 21 stores the same user card ID of the “name identification target record” in the same user card ID column 151 of the new record, and generates “accompanying actor” in the determination result column 152 And remember.

  In step S420, the name identification unit 21 determines whether there is a next record of the name identification intermediate information 35 (FIG. 8A). Specifically, if the unprocessed record that should become the next “name identification target record” remains in the name identification intermediate information 35 (step S420 “YES”), the name identification unit 21 returns to step S403, Otherwise (step S420 “NO”), the name identification process is terminated.

(Supplementary explanation of steps S403 to S420)
In the above description, it is assumed that there are two identical user card IDs included in the name identification target record. For example, when the name identification target record is the record on the first line in FIG. 8A, the same user card ID is two, “12345” and “78901”. At this time, the name collation unit 21 determines whether the determination result of “12345” and “78901” is any one of “same user”, “accompanying person”, “different user”, and “unknown”. To decide.

  However, the same user card ID included in the name identification target record may be three or more. For example, when the name identification target record is the record in the second row of FIG. 8A, the same user card ID is three of “37777”, “40000”, and “12789”. At this time, the name collation part 21 performs the process of step S403-S419 about all the combinations of two same user card ID. Specifically, the name collation unit 21 first determines whether the determination result of “37777” and “40000” is “same user”, “accompanying person”, “different user”, or “unknown”. Next, the same processing is performed for the determination results of “37777” and “12789”, and finally, the same processing is performed for the determination results of “40000” and “12789”. Do. That is, the determination result may be different for each combination of the same user card ID.

  In such a case, the name collation unit 21 stores the determination result of the name collation result information 36 in step S416 (S417, S418, S419), and the determination result is the same user card ID as the object of the determination. Store in association with the combination. For example, “37777 and 40000 are the same user, 37777 and 12789 are the same user, and 40000 and 12789 are unknown”.

(Modification 1)
In the above description, it is assumed that the user attribute information 32 acquired from the ticket system 2 has the same data type when there are a plurality of ticket systems 2. Further, the description has been made on the assumption that all the usage history information 33 acquired from the ticket system 2 also has the same data type.
However, if the ticket system 2 is different (if the railway company is different), the data types of the user attribute information 32 and the usage history information 33 are usually different. Therefore, the name identification apparatus 1 includes a data type conversion unit as a program. In step S401, the data type conversion unit converts the acquired data type of the user attribute information 32 into a specific data type that can be processed by the name identification device 1. Further, in step S404, the data type conversion unit converts the acquired data type of the usage history information 33 into a specific data type that can be processed by the name identification device 1.

(Modification 2)
The number of records of the usage history information 33 is enormous. Therefore, the name collation unit 21 of the name collation apparatus 1 can increase the processing speed by adding, for example, “current month” as a search key for retrieving time in step S404. Furthermore, by using a specific time range (spring, autumn, etc.) as a search key, the name collation apparatus 1 can obtain a determination result for the specific time range.

(Modification 3)
The type of information of the usage history information 33 is not limited to that shown in FIG. For example, the usage history information 33 stores the time and place (terminal name) at the time of payment processing at a station staff counter or an automatic payment machine, and the time and place when the information terminal is contacted for stamp rally or coupon acquisition. Also good.

(Modification 4)
All the threshold values described above are not limited to fixed values, but may be variable values. For example, the transfer time width and accompanying action time width in the name identification condition information 31 (FIG. 4) may be changed for each station and for each time (season) according to the average number of entrances / exits.

(Effect of this embodiment)
According to the present embodiment, name identification can be performed with high accuracy. Accordingly, it is possible to provide sales promotion information that is more suitable for the user's action area and purchase preference. For example, to provide one user with promotional information around the station before and after transfer, to aggregate points for multiple transportation IC cards, and to provide promotional information for families and groups Etc. becomes possible.

  The present invention is not limited to the above-described embodiment, and can be modified without departing from the spirit of the present invention.

1 name identification device 2 ticket system 3 information terminal device 4a, 4b, 8a, 8b network 5 automatic ticket gate 6 station server 7 management server 9 traffic IC card (portable information storage medium)
11 Central control unit (control unit)
12 Main storage device (storage unit)
13 Auxiliary storage device (storage unit)
DESCRIPTION OF SYMBOLS 14 Input device 15 Output device 16 Communication interface 21 Name collation part 22 Name collation condition setting part 31 Name collation condition information 32 User attribute information 33 Usage history information 34 Transfer time information 35 Name collation intermediate information 36 Name collation result information 41 Name collation condition setting screen

Claims (10)

A name collation device for determining the identity of a plurality of users using a plurality of portable information storage media,
User attribute information in which the attribute information of the user is stored in association with the identifier of the portable information storage medium;
In association with the identifier of the portable information storage medium, usage history information in which the time and section of using the transportation means using the portable information storage medium are stored;
A storage unit for storing
Obtaining a combination of two identifiers of the portable information storage medium that may be used by the same user based on the attribute information;
Based on the usage history information, a control unit that generates a determination result for each acquired combination;
Have
The determination result is
A first determination result indicating that the same user is using two portable information storage media of the acquired combination;
A second determination result indicating that two accompanying users are using two portable information storage media in the acquired combination;
A third determination result indicating that different users are using two portable information storage media of the acquired combination; and
A fourth determination result indicating that none of the first determination result, the second determination result, and the third determination result can be said;
Any of
Name identification device characterized by. At least one of the plurality of portable information storage media also serves as a commuter pass,
The controller is
Acquire the commuter pass entrance station or commuter pass departure station included in the attribute information,
From the section of the usage history information, obtain a frequently used station,
If the acquired regular ticket entry station or regular ticket entry station coincides with the acquired frequently used station, generating the first determination result;
The name collation apparatus of Claim 1 characterized by the above-mentioned. The controller is
From the usage history information, for each identifier of the portable information storage medium, obtain a section of high usage frequency,
If the acquired frequently used sections match, generating the first determination result;
The name collation apparatus of Claim 1 characterized by the above-mentioned. The usage history information is
In association with the identifier of the portable information storage medium, storing information indicating that the user has entered the transportation station and has entered the transportation station,
The controller is
From the usage history information, specify the station and time at which the first user participated,
From the usage history information, specify the station and time when the second user entered,
In the case where the station that has entered matches the station that has entered, and the time of entry is within a period until a predetermined time elapses from the time of entry, the first user and the Generating the first determination result on the assumption that the second user is the same;
The name collation apparatus of Claim 1 characterized by the above-mentioned. The usage history information is
In association with the identifier of the portable information storage medium, storing information indicating that the user has entered the transportation station and has entered the transportation station,
The controller is
From the usage history information, identify the station and time at which the first user entered or participated,
From the usage history information, specify the station and time at which the second user entered or entered,
The station at which the first user enters or participates coincides with the station at which the second user enters or participates, and the time at which the first user enters or participates, and the second user When the difference between the time when the user entered or entered is within a predetermined time, the first determination result is the second determination result because the first user and the second user are different persons accompanying the user. Generating,
The name collation apparatus of Claim 1 characterized by the above-mentioned. The usage history information is
In association with the identifier of the portable information storage medium, storing information indicating that the user has entered the transportation station and has entered the transportation station,
The controller is
From the usage history information, identify the station and time at which the first user entered or participated,
From the usage history information, specify the station and time at which the second user entered or entered,
The station at which the first user enters or participates is different from the station at which the second user enters or participates, and the time at which the first user enters or participates, and the second user If the difference between the time when the user entered or entered is within a predetermined time, the first determination result is generated because the first user and the second user are different persons. To do,
The name collation apparatus of Claim 1 characterized by the above-mentioned. The usage history information is
In association with the identifier of the portable information storage medium, storing information indicating that the user has entered the transportation station and has entered the transportation station,
The controller is
From the usage history information, identify the station and time at which the first user entered or participated,
From the usage history information, specify the station and time at which the second user entered or entered,
The station where the first user enters or participates is different from the station where the second user enters or participates, and the time when the first user enters and the first user When the time when the second user enters or participates within the period between the time of participation, the first user and the second user are different persons. Generating the third determination result;
The name collation apparatus of Claim 1 characterized by the above-mentioned. The controller is
A plurality of user attribute information with different data formats, or a plurality of usage history information with different data formats, a different data format is converted into an arbitrary data format,
The name collation apparatus of Claim 1 characterized by the above-mentioned. The controller is
When the identifiers of three or more portable information storage media that may be used by the same user are acquired based on the attribute information,
Generating the determination result based on the usage history information for every combination of identifiers of the two portable information storage media among the identifiers of the three or more portable information storage media;
The name collation apparatus in any one of Claim 1 thru | or 8 characterized by these. A name identification method for a name identification device for determining the identity of a plurality of users using a plurality of portable information storage media,
The storage unit of the name identification device is
User attribute information in which the attribute information of the user is stored in association with the identifier of the portable information storage medium;
In association with the identifier of the portable information storage medium, usage history information in which the time and section of using the transportation means using the portable information storage medium are stored;
And store
The control unit of the name identification device is
Obtaining a combination of identifiers of the portable information storage medium that may be used by the same user based on the attribute information;
Based on the usage history information, generate a determination result for each acquired combination,
The determination result is
A first determination result indicating that the same user is using two portable information storage media of the acquired combination;
A second determination result indicating that two accompanying users are using two portable information storage media in the acquired combination;
A third determination result indicating that different users are using two portable information storage media of the acquired combination; and
A fourth determination result indicating that none of the first determination result, the second determination result, and the third determination result can be said;
Any of
Name identification method characterized by.

Images