JP6969818B1 - Information processing equipment, information processing methods and information processing programs - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a highly convenient information processing apparatus, information processing method and information processing program. An information processing apparatus according to the present invention has an acquisition unit that acquires information about a target person from two or more different information sources, and a notation of information about the target person acquired by the acquisition unit as a predetermined notation. The target person is monitored based on the notation change unit to be changed, the integrated unit that integrates the information about the target person acquired by the acquisition unit, and the information about the target person integrated by the integrated unit. It is equipped with a calculation unit that calculates the risk. [Selection diagram] Fig. 1

Description

The present invention relates to an information processing apparatus, an information processing method and an information processing program.

Conventionally, a financial institution or the like may check whether or not a customer has a criminal risk based on an identity verification document. The criminal risk check includes, for example, a check of whether or not the person is likely to perform money laundering and a check of whether or not the person belongs to an antisocial force.

For example, Patent Document 1 proposes a money laundering determination support system that supports comprehensive determination of whether or not a detected suspicious transaction corresponds to money laundering from a plurality of information sources.

Japanese Unexamined Patent Publication No. 2010-22040

As mentioned above, in order to judge the crime risk, it is necessary to comprehensively judge the information acquired from multiple information sources. However, since the document format and the like differ depending on the information source, it is difficult to mechanically process the information acquired from a plurality of information sources, and a large number of manpower is required.

The present invention has been made in view of the above problems, and an object of the present invention is to provide a highly convenient information processing apparatus, information processing method, and information processing program.

In order to solve the above problems, the information processing apparatus of the present invention has a predetermined notation of an acquisition unit that acquires information about the target person from two or more information sources and a notation of information about the target person acquired by the acquisition unit. Based on the notation change unit to be changed to, the integrated unit that integrates the information about the target person acquired by the acquisition unit, and the information about the target person integrated by the integrated unit, the target person is monitored. It is provided with a calculation unit for calculating the risk of becoming.

According to the present invention, it is possible to provide a highly convenient information processing apparatus, information processing method and information processing program.

It is a figure which shows an example of the schematic structure of the information processing system which concerns on embodiment. It is a figure which shows an example of the hardware composition of the server which concerns on embodiment. It is a figure which shows an example of the database stored in the storage device of the server which concerns on embodiment. It is a figure which shows an example of the information stored in a database. It is a figure which shows an example of the information stored in a database. It is a figure which shows an example of the functional structure of the server which concerns on embodiment. It is a figure which shows an example of the hardware composition and the function composition of the user terminal which concerns on embodiment. It is a flowchart which shows an example of the risk calculation process of the server which concerns on embodiment. (A) is a figure which shows an example of the notation change by the notation change part of the server which concerns on embodiment. (B) and (c) are diagrams showing an example of information integration by the integration unit of the server according to the embodiment. It is a flowchart which shows an example of the character recognition processing of the server which concerns on embodiment. It is a figure which shows an example of character recognition by the recognition part of the server which concerns on embodiment. It is a figure which shows an example of the position information addition by the recognition part of the server which concerns on embodiment. It is a figure which shows an example of the search by the search part of the server which concerns on embodiment. It is a figure which shows an example of the horizontal connection by the connection part of the server which concerns on embodiment. It is a figure which shows an example of the vertical connection by the connection part of the server which concerns on embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following explanation, the “target person” is the target person for risk calculation.
In addition, "risk" means that the subject is monitored (for example, foreign PEPs (persons who occupy an important position in foreign governments (foreign heads of state, etc.) and those who were in that position, their families, and substance). It is a risk that falls under the category of corporations whose rulers are these persons) and crimes such as money laundering. In this embodiment, a high risk is likely to be a crime, and a low risk is unlikely to be a crime.

[Embodiment]
FIG. 1 is a diagram showing an example of an outline configuration of an information processing system 1 according to an embodiment. The information processing system 1 has a configuration in which a server 2 and a user terminal 3 are connected via a network 4. The number of servers 2 and user terminals 3 included in the information processing system 1 is arbitrary.

For example, a server (information source) of another system is connected to the network 4, and the server 2 accesses the server via the network 4 and stores information (information about a target person described later). Is configured to be able to be obtained. Software such as crawlers and scrapers can be used to acquire the information on the server. It should be noted that what kind of communication network the network 4 is configured with is arbitrary.

FIG. 2 is a diagram showing an example of a hardware configuration of the server 2 (information processing apparatus) according to the present embodiment. As shown in FIG. 2, the server 2 includes a configuration in which a communication IF 200A, a storage device 200B, and a CPU 200C are connected via a bus.

The communication IF200A is an interface for communicating with an external terminal.

The storage device 200B is, for example, an HDD or a semiconductor storage device. The information processing program and various databases used by the server 2 are stored in the storage device 200B. In the present embodiment, the information processing program and various databases are stored in the storage device 200B of the server 2, but are stored in an external storage device such as a USB memory or an external server connected via a network, and are required. It may be configured to be referenceable or downloadable depending on the situation.

FIG. 3 is a diagram showing an example of a database stored in the storage device 200B of the server 2. As shown in FIG. 3, the storage device 200B includes a correction pattern database 1 (hereinafter, also referred to as a correction pattern DB1), a classification database 2 (hereinafter, also referred to as a classification DB2), and an item master database 3 (hereinafter, an item master). DB3), notation change database 4 (hereinafter, also referred to as notation change DB4), target person database 5 (hereinafter, also referred to as target person DB5), risk calculation database 6 (hereinafter, also referred to as risk calculation DB6). Is remembered.

(Correction pattern DB1)
The correction pattern DB 1 stores a plurality of correction patterns for correcting the image data of the document. FIG. 4A is a diagram showing an example of information stored in the correction pattern DB1. As shown in FIG. 4A, each of the plurality of correction patterns is configured by combining one or more corrections. For example, the correction pattern 1 is configured by combining corrections 1 and 3. Further, the correction pattern 2 is configured by combining corrections 1, 2 and 4. Further, the correction pattern 3 is configured by combining corrections 1, 2 and 3. Further, the correction pattern 4 is configured by combining corrections 1, 3 and 5. Further, the correction pattern 5 is configured by combining corrections 1 and 4. The number of correction patterns is not limited to 5, and may be 3 or more.

Further, the corrections 1 to 5 are, for example, perspective warp (trapezoidal correction), brightness correction, contrast correction, gauss correction, blur correction, and the like, respectively. The combination of corrections of each correction pattern shown in FIG. 4A is only an example, and the type of correction for each correction pattern is arbitrary. Further, the correction is not limited to the five corrections 1 to 5.

(DB2 for classification)
Information for classifying documents is stored in the classification DB 2. FIG. 4B is a diagram showing an example of information stored in the classification DB 2. As shown in FIG. 4B, the classification DB 2 contains pattern matching data (image data, feature point data (for example, image data of a seal, feature point data, etc.)) and keywords peculiar to each type of document. (KW) is associated and stored. The pattern matching data and keywords shown in FIG. 4B are merely examples, and what kind of pattern matching data and keywords should be used as information for classifying documents is arbitrary. The classification unit 206, which will be described later, refers to the classification DB 2 and classifies the image data of the document based on whether or not the image data of the document contains pattern matching data or keywords.

(Item master DB3)
The item master DB 3 stores information on the items to be acquired for each type of document. FIG. 4C is a diagram showing an example of information stored in the item master DB 3. As shown in FIG. 4C, the item master DB 3 stores information items to be acquired for each type of document in association with each other. It is arbitrary what kind of item information is obtained from the document.

(DB4 for notation change)
The notation changing DB 4 stores information for changing the notation of the information about the target person acquired by the server 2 to a predetermined notation. Specifically, the notation change DB 4 stores information for logic processing and information for first and second master processing.

The information for logic processing is information in which information about a target person whose notation is changed (hereinafter, also referred to as a processing description target) is associated with a processing rule for changing the notation of the information. FIG. 5A is a diagram showing an example of information for logic processing stored in the notation change DB 4, and a processing rule is associated with the processing description target. In the example shown in FIG. 5A, when the processing description target is "number (including comma) x digit" + "thousand yen", "number (including comma) x digit" + ",000". It is stipulated to replace it with "". For example, when the processing description target is "1,000 thousand yen" as shown in FIG. 5 (b) and the processing rule illustrated in FIG. 5 (a) is applied, the notation is changed to "1,000,000".
The examples shown in FIGS. 5 (a) and 5 (b) are merely examples, and the information for logic processing has various patterns of associating the processing description target with the processing rule for the processing description target. include. For example, in the information for logic processing, if the processing description target is "number (including comma) x digit" + "million yen", "number (including comma) x digit" + ", It may be specified to replace with "000,000". On the contrary, the processing rule may be stipulated so that when the notation is "1,000,000", it is "1,000 thousand yen", and when it is "1,000,000,000", it is "1,000 million yen".

Further, an example in which an address is associated with a processing rule for changing the notation of the address as information on a target person who is a target for which the notation is changed (hereinafter, also referred to as a processing summary target) will be described.
For example, if the address of the address is written as "5-5-5 Akasaka, Minato-ku, Tokyo" with a hyphen, the first hyphen of the address is "chome" such as "5-5-5 Akasaka, Minato-ku, Tokyo". You may provide a processing rule to change to. Since the purpose is to unify the notation, if the notation of the address is "5-5-5 Akasaka, Minato-ku, Tokyo", the processing rule is "5-5-5 Akasaka, Minato-ku, Tokyo". May be provided. In addition, the first hyphen is "chome", the next hyphen is "ban", and the next hyphen is "5-5-5 Akasaka, Minato-ku, Tokyo" as "5-5-5, Akasaka, Minato-ku, Tokyo". May be provided with a processing rule to change to "No.". On the contrary, the processing rule may be such that "5-5-5 Akasaka, Minato-ku, Tokyo" is set to "5-5-5 Akasaka, Minato-ku, Tokyo".
As described above, the information for logic processing is information in which the processing description target and the processing rule for the processing description target are associated with each other, and the notation is unified by referring to the information for logic processing. It can be changed to the written notation.

The information for the first master processing is information in which the information about the target person who is the processing summary target and the content of the overwriting processing by the dictionary data of the information are associated with each other. FIG. 5C is a diagram showing an example of information for the first master processing stored in the notation change DB 4, and the processing description target is associated with the overwriting processing content by the dictionary data. In the example shown in FIG. 5 (c), when the processing description target is "war yen" in the "amount" item, it is stipulated that "thousand yen" is overwritten. For example, if the processing description target is "1,000 battle yen" as shown in FIG. 5 (d) and the processing content illustrated in FIG. 5 (d) is applied, the error is changed to "1,000 thousand yen". .. The examples shown in FIGS. 5 (c) and 5 (d) are merely examples, and the information for the first master processing includes various patterns of overwriting processing contents by dictionary data in the processing description target. There is.

Further, the dictionary data for changing the external character (gaiji) may be stored in the notation changing DB 4 as the information for the first master processing. External characters are characters that are not registered in character input software such as IME, and cannot be displayed even if they are converted during text input. Since it is necessary to use an external character editor or the like in order to handle external characters, it is preferable to change the external characters to characters that can be handled by character input software such as IME when the information about the target person includes external characters. An example of the change is shown below.
Before conversion: "Taka" Taro Saki ("Taka" is the height of the ladder)
After conversion: Taro Takasaki In the above change example, "high" (ladder height) is changed to "high" registered in character input software such as IME.

In this way, the dictionary for changing the external character (gaiji) is stored in the notation change DB4, and if the information about the target person contains the external character, the external character is changed to a character that can be handled by character input software such as IME. It may be configured to be used.

Further, the notation change DB 4 may store a dictionary for correcting an erroneous address as information for the first master processing. The dictionary stores the notation of a legitimate address. Here, the official address is information that associates the names of prefectures determined based on the administrative divisions of Japan, and the names of cities, wards, villages, counties, etc. included in the names of prefectures, and this information is used. By doing so, it is possible to correct erroneous descriptions of cities, wards, villages, counties, etc. included in the prefecture name of the address.
For example, if the following uncorrected address is obtained as information about the target person, Akasaka is not Shibuya Ward but Minato Ward, so the address will be corrected as follows using the regular address stored in the dictionary. NS.
Address before correction: 3-3-3 Akasaka, Shibuya-ku, Tokyo
Corrected address: 3-3-3 Akasaka, Minato-ku, Tokyo

In addition, to show another example, if the following uncorrected address is obtained as information about the target person, large letters are not used in the administrative division, so the regular address stored in the dictionary is used as shown below. The address is corrected.
Address before correction: 34-2 Yagyu, Oaza Fujie, Higashiura-cho, Chita-gun, Aichi
Corrected address: 34-2 Fujie Yagyu, Higashiura-cho, Chita-gun, Aichi Prefecture
As described above, the information for the first master process is information in which the notation that is erroneous and the correct notation for the erroneous description are variously associated with each other, and by referring to the information for the first master process, the erroneous description is made. Can be corrected to the correct notation.

Further, the information for the second master process is information for deleting unnecessary character data included in the information about the target person. Specifically, the information for the second master processing is information about the target person and character information included in the information.
As described above, the information for the second master processing is the information in which the information about the target person and the information of the characters included in the information are associated with each other, and by referring to the information for the second master processing. , Unnecessary character data other than the characters included in the information about the target person can be recognized and the unnecessary character data can be deleted.

(Target person DB5)
Information about the target person is stored in the target person DB 5 in association with the target person ID. Specifically, the target person DB5 contains transaction information (hereinafter, also simply referred to as account transaction information) in the target person's bank account (hereinafter, also simply referred to as an account), police agency data (for example, criminal history information, etc.). So-called blacklist information such as (anti-social force information), installment sales method / money lending business method credit information agency data (for example, unpaid information by credit card company, storage agency (account transfer)) is stored in association with the target person ID. There is.
Here, when the target person is an individual, the name, address, contact information, personal account transaction information, and blacklist information are stored in association with the target person ID.
If the target person is a corporation, the location of the corporation, the contact information of the corporation, the name of the representative, the name of the standing proxy, the name of the beneficial owner, the name of the agent, the account transaction information of the corporation, and the above representative. , Standing proxy, beneficial owner, and proxy blacklist information are stored in association with the subject ID.
Information about the subject may include age, gender, address, date of birth, registered domicile, SNS reference information, and the like. The "SNS reference information" is a check of the reliability of the personal information from the content posted by the predetermined SNS by the examinee.
The information about the target person stored in the target person DB 5 is acquired by the acquisition unit 210 described later.

(DB6 for risk calculation)
The risk calculation DB 6 stores information for calculating the risk (hereinafter, also simply referred to as risk) for the target person to be monitored from the information about the target person. Specifically, the risk calculation DB 6 has a risk calculation score (hereinafter, also referred to as a risk score) set for each combination (condition) of information about the target person stored in the target person DB 5. Multiple are stored.

For example, the items used when calculating crime risk such as money laundering include the following information.
(1-1) Transaction period (1-2) Transaction amount (1-3) Transaction frequency (1-4) Criminal record (1-5) Location (address in the case of an individual)
(1-6) Access history to account Figure 5 (e) shows an example of a combination of conditions and risk scores. In the example shown in FIG. 5 (e), it is shown that the "risk score" is "30" when "the transaction amount is 5 million yen or more in a period of one month and there is a criminal history".

Also, for example, in foreign PEPs (persons who occupy important positions in foreign governments (heads of state of foreign countries, etc.) and those who were in that position, their families, and corporations whose beneficial owners are these persons). The items used to calculate a certain risk include the following information.
(2-1) List of foreign VIPs (2-2) Customer data (2-3) WEB information by crawling (2-4) Other various information about the target person (2-1) to (2-4) above Based on the information of, the target person's name, location, country of origin, age, transaction history, deposit / withdrawal history, etc. are acquired, and the risk that the target person corresponds to foreign PEPs is calculated based on this acquired information. .. For example, if the subject matches the list of foreign dignitaries, a very high risk (score is approximately 100%) corresponding to foreign PEPs is calculated.

The CPU 200C controls the server 2 and includes a ROM (Read Only Memory) and a RAM (Random Access Memory) (not shown).

As shown in FIG. 6, the server 2 has a receiving unit 201, a transmitting unit 202, a storage device control unit 203, a correction unit 204, a recognition unit 205, a classification unit 206, a determination unit 207, a search unit 208, a coupling unit 209, and an acquisition unit. It has functions such as a unit 210, a notation changing unit 211, an integrated unit 212, and a calculation unit 213. The function shown in FIG. 6 is realized by the CPU 200C executing an information processing program stored in the ROM (not shown) of the server 2.

The receiving unit 201 receives information transmitted from the outside, for example, information about the target person.

The transmission unit 202 transmits information to the outside.

The storage device control unit 203 controls the storage device 200B. Specifically, the storage device control unit 203 controls the storage device 200B to write and read information.

The correction unit 204 corrects the image data of the document by a plurality of correction patterns stored in the correction pattern DB1 (each correction pattern includes one or more different corrections), and the correction unit 204 corrects each correction pattern. Generate a plurality of corresponding corrected images. Specifically, the correction unit 204 generates the corrected image data 1 in which the image data is corrected by the correction pattern 1. Further, the correction unit 204 generates the corrected image data 2 in which the image data is corrected by the correction pattern 2. Further, the correction unit 204 generates the corrected image data 3 in which the image data is corrected by the correction pattern 3. Further, the correction unit 204 generates the corrected image data 4 in which the image data is corrected by the correction pattern 4. Further, the correction unit 204 generates the corrected image data 5 in which the image data is corrected by the correction pattern 5.

The recognition unit 205 recognizes characters from the image data of the document. Here, the recognition unit 205 recognizes characters from a plurality of corrected images corresponding to each correction pattern generated by the correction unit 204. Next, the recognition unit 205 selects the most recognized character from the plurality of corrected image data and uses it as the recognized character. Further, the recognition unit 205 adds position information to the recognized characters. The position information is represented by XY coordinates with the upper left of the document as the zero point, and the horizontal direction is the X axis (positive in the right direction) and the vertical direction is the Y axis (positive in the downward direction) toward the document. There is. The number of pixels may be used as a numerical value representing the coordinates. In addition, which position of the document is set as the zero point is arbitrary. Further, a numerical value other than the number of pixels may be used as the numerical value representing the coordinates.

When the recognition unit 205 recognizes a character from the image data of the document, the position information (coordinates) of the recognized character is within a predetermined distance in the horizontal direction (X axis) or the vertical direction (Y axis) (for example). , When the coordinates indicating the position of the character overlap), it is recognized as a character that constitutes a series of words, and the position information (coordinates) of the recognized character is in the horizontal direction (X axis) or the vertical direction (Y axis). ), When the distance is longer than a predetermined distance (for example, when the coordinates indicating the positions of the characters overlap), it is recognized that the character is not a character constituting a series of words but another character or a character constituting the word. Note that the coordinates indicating the position of the characters overlap, for example, when the character of "word" is written in the horizontal direction (X-axis) on the document, the position coordinate of the right end of the character of "word" is , If it is on the right side in the lateral direction (X-axis) from the position coordinates of the left end of the character of "leaf", in other words, the position coordinate of the left end of the character of "leaf" is the position of the right end of the character of "word". It means that it exists on the left side in the lateral direction (X axis) from the coordinates. Further, for example, when the character of "word" is written in the vertical direction (Y axis) on the document, the position coordinate of the lower end of the character of "word" is higher than the position coordinate of the upper end of the character of "leaf". If it exists below in the vertical direction (Y-axis), in other words, the position coordinates of the upper end of the character "leaf" are above the position coordinates of the lower end of the character "word" in the vertical direction (X-axis). Refers to the case where it exists.

The classification unit 206 refers to the classification DB 2 and classifies the image data of the document. Specifically, the classification unit 206 refers to the classification DB 2 and documents that are the source of the image data according to whether or not pattern matching data and keywords prepared for each type of document exist. To classify. The classification unit 206 adds the classified information (document type information) to the image data of the document.

The determination unit 207 refers to the item master DB 3 in which the information of the items to be acquired is stored for each type of document, and determines whether or not the item exists in the character recognized by the recognition unit 205 for each item.

When there is an item that the determination unit 207 does not determine to exist, the search unit 208 searches for each character constituting the item from the characters recognized by the recognition unit 205. Here, the search unit 208 searches for the existence of other characters constituting the item within a predetermined range starting from one of the characters.

The joining unit 209 joins the characters on the image data of the document searched by the search unit 208 in terms of data so that they can be recognized as items.

The acquisition unit 210 acquires information about the target person from a server or a user terminal 3 of another system connected via the network 4. The acquisition unit 210 acquires information about the target person from various information sources by using various methods.
"Various information sources" include, for example, National Police Agency data, installment sales method / money lending business law credit information agency data, and the like.
"Various methods" include, for example, crawling (technology for acquiring information on a WEB site), OCR (Optical Character Recognition), API (Application Programming Interface) linkage with other systems, and user terminal 3. Information entered using it is included.

When the information about the target person is image data, the acquisition unit 210 acquires the characters corresponding to each character as the information about the target person according to the search result in the search unit 208. Specifically, the acquisition unit 210 acquires the character corresponding to the item for each item. More specifically, the acquisition unit 210 acquires the characters up to the next item (next item) existing on the first side (right side in this embodiment) of the item or the characters up to the line feed as the characters corresponding to the item. .. Further, when the characters (excluding the characters constituting the item) do not exist within the predetermined range of the first side (right side in this embodiment) of the item, the acquisition unit 210 has a second side different from the first side of the item. The characters up to the next item (next item) or the characters up to the line feed existing in (lower side in this embodiment) are acquired, and the characters corresponding to the items are acquired as information about the target person.

The notation changing unit 211 changes the notation of the information about the target person acquired by the acquisition unit 210 to a predetermined notation. Specifically, the notation change unit 211 refers to the notation change DB 4, and is an acquisition unit based on the information for logic processing and the information for the first and second master processes stored in the notation change DB 4. The notation of the information about the target person acquired in 210 is changed to the predetermined notation.

The integration unit 212 integrates information about the target person whose display has been changed to a predetermined display by the notation change unit 211. Specifically, the integration unit 212 collates the information about the target person whose display has been changed to the predetermined display by the notation change unit 211 for each item, and extracts non-overlapping items to obtain the information about the target person. Further, the integration unit 212 selects the most duplicated items as the information corresponding to the duplicated items.

The calculation unit 213 calculates the risk of the target person based on the information about the target person integrated by the integration unit 212. Specifically, the calculation unit 213 combines the information corresponding to each item of the information about the target person stored in the target person DB 5 to determine whether or not the condition stored in the risk calculation DB 6 is satisfied. If the conditions are met, the risk score associated with the condition is taken as the risk of the subject.

(User terminal 3)
FIG. 7 is a diagram showing an example of a hardware configuration and a functional configuration of the user terminal 3 according to the embodiment. FIG. 7A is a diagram showing an example of the hardware configuration of the user terminal 3, and FIG. 7B is a diagram showing an example of the functional configuration of the user terminal 3. The user terminal 3 is a PC (Personal Computer), a mobile terminal (for example, a tablet terminal), or the like. As shown in FIG. 7A, the user terminal 3 includes a communication IF 300A, a storage device 300B, an input device 300C, a display device 300D, a CPU 300E, and the like.

The communication IF 300A is an interface for communicating with another device (server 2 in the embodiment).

The storage device 300B is, for example, an HDD (Hard Disk Drive) or a semiconductor storage device (SSD (Solid State Drive)). The storage device 300B stores an identifier (ID) of the user terminal 3, an information processing program, and the like. The identifier may be newly assigned by the server 2 to the user terminal 3, or may use an IP (Internet Protocol) address, a MAC (Media Access Control) address, or the like.

The input device 300C is, for example, a keyboard, a touch panel, or the like, and operates the input device 300C to input information necessary for using the information processing system 1 (for example, information about a target person (including image data)). Can be done.

The display device 300D is, for example, a liquid crystal monitor, an organic EL monitor, or the like. The display device 300D includes a screen necessary for using the information processing system 1 (for example, a screen for inputting information about the target person (including image data), a screen for presenting the risk of the target person calculated by the server 2, and the like. ) Is displayed.

The CPU 300E controls the user terminal 3 and includes a ROM and a RAM (not shown).

As shown in FIG. 7B, the user terminal 3 has functions such as a receiving unit 301, a transmitting unit 302, a storage device control unit 303, an operation receiving unit 304, and a display device control unit 305. The function shown in FIG. 7B is realized by the CPU 300E executing an information processing program stored in the storage device 300B.

The receiving unit 301 receives the information transmitted from the server 2.

The transmission unit 302 assigns an identifier to the information input using the input device 300C and transmits the information to the server 2. By assigning an identifier to the information transmitted from the user terminal 3, the server 2 can recognize from which user terminal 3 the received information is transmitted.

The storage device control unit 303 controls the storage device 300B. Specifically, the storage device control unit 303 controls the storage device 300B to write and read information.

The operation receiving unit 304 receives an input operation on the input device 300C. For example, it accepts an input operation (including an image data input operation) of information related to the target person.

The display device control unit 305 controls the display device 300D. Specifically, the display device control unit 305 controls the display device 300D and screens necessary for using the information processing system 1 according to the embodiment (for example, a screen for inputting information about the target person (image data). Includes), a screen that presents the target person's risk calculated by the server 2, etc.) is displayed.

(Information processing method)
FIG. 8 is a flowchart showing an example of the risk calculation process of the server according to the embodiment.

(Step S101)
The acquisition unit 210 of the server 2 acquires information about the target person from two or more information sources.

(Step S102)
The acquisition unit 210 of the server 2 determines whether or not the acquired information about the target person is text data, in other words, whether or not it is image data. If it is image data (YES), the server 2 executes the process of step 103. If it is not image data (NO), in other words, if it is text data, the server 2 executes the process of step 104.

(Step S103)
The server 2 executes the character recognition process. The details of the character recognition process will be described later.

(Step S104)
The notation change unit 211 of the server 2 refers to the notation change DB 4, and is an acquisition unit 210 based on the information for logic processing and the information for the first and second master processes stored in the notation change DB 4. Change the notation of the acquired information about the target person to the specified notation.

(Step S105)
The integration unit 212 of the server 2 integrates information about the target person whose display has been changed to a predetermined display by the notation change unit 211. The details of the operation of the integrated unit 212 will be described with reference to FIG. 9 described later.

(Step S106)
The calculation unit 213 calculates the risk of the target person based on the information about the target person integrated by the integration unit 212. Since the details of the operation of the calculation unit 213 have been described, duplicate explanations will be omitted.

(Step S107)
The transmission unit 202 outputs the risk calculated by the calculation unit 213 together with the information of the target person (for example, name, corporate name, etc.) for which the risk is calculated. The output risk and target person information are received by the receiving unit 301 of the user terminal 3 and displayed on the display device 300D by the display device control unit 303 of the user terminal 3. When the risk calculated by the calculation unit 213 and the information of the target person are output, if the risk is equal to or higher than the predetermined value, the information of the risk and the target person is output together with the fact that the risk is to be monitored, and the risk is the predetermined value. If it is less than, the risk and target person information may be output as well as not being monitored. Further, the information on the risk and the target person may be output only when the risk exceeds a predetermined value, or the information on the risk and the target person may be output together with the fact that the information is to be monitored.

FIG. 9A is a diagram showing an example of notation change by the notation change unit 211 of the server according to the embodiment. FIG. 9A shows an example in which the notation changing unit 211 changes the notation of the amount of money to a predetermined notation. As shown in FIG. 9A, the notation changing unit 211 corrects the erroneous description based on the information for the first master processing stored in the notation changing DB 4 (in the example of FIG. 9A, “war”. The character of is "thousand"). Further, the notation changing unit 211 deletes unnecessary characters based on the information for the second master processing stored in the notation changing DB 4 (in the example of FIG. 9A, the characters "* excluding tax" are deleted. ing). Next, the notation changing unit 211 unifies the units of the notation changing unit 211 based on the information for logic processing of the notation changing DB 4.

9 (b) and 9 (c) are diagrams showing an example of information integration by the integration unit 212 of the server 2 according to the embodiment. FIG. 9B is information about the target person before the integration by the integration unit 212, and FIG. 9C is information about the target person after the integration by the integration unit 212. As shown in FIGS. 9 (b) and 9 (c), the integration unit 212 integrates information about the target person whose display has been changed to a predetermined display by the notation change unit 211 for each item. Specifically, the integration unit 212 acquires the information of each item from the information about the target person whose display has been changed to the predetermined display by the notation change unit 211, and for the duplicated items, corresponds to the most duplicated items. Select as information to integrate information about the subject obtained from various sources.

(Information processing method)
FIG. 10 is a flowchart showing an example of the character recognition process of the server according to the embodiment.

(Step S201)
The correction unit 204 of the server 2 refers to the correction pattern DB1 and corrects the image data of the document. Specifically, the correction unit 204 corrects the image data of the document by a plurality of correction patterns stored in the correction pattern DB1 (each correction pattern includes one or more different corrections). , Generate a plurality of corrected images corresponding to each correction pattern.

(Step S202)
The recognition unit 205 of the server 2 recognizes characters from the image data of the document. Specifically, the recognition unit 205 recognizes characters from a plurality of corrected images corresponding to each correction pattern generated by the correction unit 204. Next, the recognition unit 205 selects the most recognized character from the plurality of corrected image data and uses it as the recognized character.

FIG. 11 is a diagram showing an example of character recognition by the recognition unit 205. As shown in FIG. 11, the recognition unit 205 recognizes characters from a plurality of corrected images corresponding to each correction pattern generated by the correction unit 204. In the example shown in FIG. 11, in the correction patterns 1, 3 and 5, the recognition result is “Taro Yamada”. Further, in the correction pattern 2, the recognition result is "Taro Yamada". Further, in the correction pattern 3, the recognition result is "unrecognizable", that is, the character cannot be recognized. The recognition unit 205 selects the most recognized character from the plurality of corrected image data, "Taro Yamada" in the example shown in FIG. 11, and determines it as the recognized character. If there is no recognized character with the largest number (for example, when the determination results of the correction patterns 1 to 5 are 2, 2, 2, 2, and 1, respectively), the process of step S202 may be performed again. Alternatively, the correction pattern may be changed to perform the process of step S202, or a notification (an error may be output) may be given as unreadable.

(Step S203)
The recognition unit 205 of the server 2 adds position information to the recognized characters. FIG. 12 is a diagram showing an example of giving position information by the recognition unit 205 (the broken lines, arrows, Top, Left, Bottom, and Right characters in the figure are illustrated for explanation and are actual images. It does not exist as data). 12 (a) is an example of image data of a document to be recognized, and FIG. 12 (b) is an example of position information given to a character recognizing FIG. 12 (a). As shown in FIG. 12, the recognition unit 205 assigns the position information represented by the XY coordinates with the upper left of the document as the zero point to the recognized character. In the example shown in FIG. 12B, Top is the upper end of the character, Left is the left end of the character, Bottom is the lower end of the character, Right is the right end of the character, and Word is the recognized character. As described above, in the present embodiment, the position information is represented by the XY coordinates with the upper left of the document as the zero point, and the number of pixels is used as the numerical value of the coordinates.

As described above, the recognition unit 205 recognizes all the characters included in the image data, and gives the recognized characters the position information represented by the XY coordinates with the upper left of the document as the zero point. In the example shown in FIG. 12, the upper end (Top), left end (Left), lower end (Font), and right end (Right) of the character are located away from the actual character, but this is a recognized character. This is because the upper end (Top), the left end (Left), the lower end (Bottom), and the right end (Right) of the character are determined according to the font size of the character. Further, in the present embodiment, the position information of the character is shown by the upper end (Top), the left end (Left), the lower end (Bottom), and the right end (Right), but the X-axis and the Y of the upper left and the lower right of the character are shown. The position of the character may be indicated by the position coordinates of the axis or the position coordinates of the X-axis and the Y-axis of the upper right and the lower left of the character, respectively.

(Step S204)
The classification unit 206 refers to the classification DB 2 and classifies the image data of the document. Specifically, the classification unit 206 refers to the classification DB 2 and determines whether or not the prepared pattern matching data or keywords exist in the characters recognized by the recognition unit 205 for each type of document. When the characters recognized by the recognition unit 205 include any one of the prepared pattern matching data or keywords, the classification unit 206 corresponds the image data of the document to the pattern matching data or keywords. Classify by type. Further, the classification unit 206 adds the classified information (document type information) to the image data of the document.

(Step S205)
The determination unit 207 refers to the item master DB 3 and determines for each item whether or not there is an item corresponding to the type of the document classified by the classification unit 206. If there is an item that is not determined to be present by the determination unit 207 (YES), the server 2 proceeds to the process of step S206. If there is no item that is not determined to be present by the determination unit 207 (NO), the server 2 proceeds to the process of step S208.

(Step S206)
The search unit 208 searches for each character constituting an item that is determined not to exist by the determination unit 207 from the characters recognized by the recognition unit 205. Here, the search unit 208 searches for the existence of other characters constituting the item within a predetermined range starting from one of the characters.

FIG. 13 is a diagram showing an example of a search by the search unit 208 (the characters of the broken line, arrow, Top, Left, Bottom, and Right in the figure are shown for explanation and are used as actual image data. Does not exist). FIG. 13A is a diagram showing an example of a lateral (X coordinate) search by the search unit 208. As shown in FIG. 13A, when the items of "name" are arranged in the horizontal direction (X-axis direction) at a distance of a predetermined interval or more, the characters of "name" and the characters of "name" are independent of each other. Because it is read in, it cannot be recognized as a "name" item even though the "name" item exists on the document. Therefore, the search unit 208 is a "name" which is another character constituting the item of "name" within a predetermined range starting from "name" which is one character of each character constituting the item of "name". Search for the existence. More specifically, the search unit 208 searches for the continuous existence of the character "name" on the X-axis line in the Y coordinate of the character "Mr.".

Whether or not the characters are arranged side by side in the horizontal direction (X-axis direction) is determined by the upper end (position of "Top" in FIG. 13A) or the lower end (FIG. 13) of the characters recognized by the recognition unit 205. The position of "Bottom" in 13 (a)) may be used as a reference. Specifically, the Y coordinate value (zero) of the upper end Top or the lower end Bottom of each character (“Mr.” and “First name” in the example shown in FIG. 13 (a)) separated by a predetermined interval in the horizontal direction (X-axis direction). If the difference (the number of pixels from the point) is within a predetermined range (for example, ± 20 pixels), it may be determined that the characters are arranged side by side in the horizontal direction (X-axis direction). Characters that make up an item are usually considered to have the same font and size, so each character is separated by a predetermined interval in the horizontal direction (X-axis direction) (in the example shown in FIG. 13A, "Mr." And if the difference in the Y coordinate value (number of pixels from the zero point) of the upper end Top or the lower end Bottom of "name") is within a predetermined range, the characters are arranged side by side in the horizontal direction (X-axis direction). It can be determined.

FIG. 13B is a diagram showing an example of a vertical direction (Y coordinate) search by the search unit 208. As shown in FIG. 13 (b), when the item of "symbol" is arranged in the vertical direction (Y-axis direction), the character of "ki" and the character of "go" are read independently. Even though the "symbol" item exists on the document, it cannot be recognized as a "symbol" item. Therefore, the search unit 208 is a "number" which is another character constituting the item of the "symbol" within a predetermined range starting from "note" which is one character of each character constituting the item of the "symbol". Search for the existence. More specifically, the search unit 208 searches for the continuous existence of the character "No." on the Y-axis line in the X coordinate of the character "Note".

Whether or not the characters are arranged side by side in the vertical direction (Y-axis direction) is determined by the left end (position of "Left" in FIG. 13B) or the right end (FIG. 13) of the characters recognized by the recognition unit 205. 13 (b) “Right” position) may be used as a reference. Specifically, the Z coordinate value (zero) of the left end L or the right end R of each character (“Note” and “No.” in the example shown in FIG. 13 (b)) separated by a predetermined interval in the vertical direction (Y-axis direction). If the difference (the number of pixels from the point) is within a predetermined range (for example, ± 20 pixels), it may be determined that the characters are arranged side by side in the vertical direction (Y-axis direction). Characters that make up an item are usually considered to have the same font and size, so each character is separated by a predetermined interval in the vertical direction (Y-axis direction) (“Note” in the example shown in FIG. 13 (b)). And "No.") If the difference between the X coordinate values (number of pixels from the zero point) of the left end L or the right end R is within a predetermined range, the characters are arranged side by side in the vertical direction (Y-axis direction). It can be determined.

As described above, the search unit 208 searches for other characters constituting the item in the horizontal direction (Z-axis direction) and the vertical direction (Y-axis direction) starting from one character of each character. Specifically, it searches for the existence of other characters constituting the item continuously on the X-axis line in the Y coordinate of the first character of each character constituting the item. When the search unit 208 is continuous on the X-axis line in the Y coordinate of the first character of each character constituting the item and there is no other character constituting the item, the search unit 208 of each character constituting the item Search for the existence of other characters that make up the item in succession on the Y-axis line within the X coordinate of the first character.

(Step S207)
The joining unit 209 joins the characters on the image data of the document searched by the search unit 208 in terms of data so that they can be recognized as items. More specifically, the joining unit 209 performs a process of combining the characters searched by the search unit 208 and combining them in terms of data so that they can be recognized as items. FIG. 14 is a diagram showing an example of the combination of characters in the horizontal direction by the connection portion 209 (the broken line in the figure is shown for illustration purposes and does not exist as actual image data). FIG. 14A is a diagram showing an example of image data of characters before joining. FIG. 14B is an example of the position information given to the characters “Mr.” and “First name” recognized by the recognition unit 205. FIG. 14C is a diagram showing an example of image data of characters after being joined by the joining portion 209. FIG. 14D is an example of the position information given to the characters of the “name” after the combination. As shown in FIGS. 14 (c) and 14 (d), the joint portion 209 uses the position information of the left end (Left) of the “name” as the position information of the left end (Left) of the “name” and the right end of the “name”. By using the position information of (Right) as the position information of the right end (Right) of the "name", the characters of "name" and "name" are combined in terms of data so that they can be recognized as one item "name".

FIG. 15 is a diagram showing an example of joining characters in the vertical direction by the joining portion 209 (the broken line in the figure is shown for illustration purposes and does not exist as actual image data). FIG. 15A is a diagram showing an example of image data of characters before joining. FIG. 15B is an example of the position information given to the characters “Note” and “No.” recognized by the recognition unit 205. FIG. 15C is a diagram showing an example of image data of characters after being joined by the joining portion 209. FIG. 15D is an example of the position information given to the characters of the “symbol” after the combination. As shown in FIGS. 15 (c) and 15 (d), the joint portion 209 uses the position information of the upper end (Top) of the “note” as the position information of the upper end (Top) of the “symbol” and the lower end of the “number”. By using the position information of (Bottom) as the position information of the lower end (Bottom) of the "symbol", the characters "ki" and "go" are combined in terms of data so that they can be recognized as one item "symbol".
In this way, the joining unit 209 joins the characters searched by the search unit 208 and performs the joining process so that they can be handled as one piece of information.

(Step S208)
The acquisition unit 210 acquires characters corresponding to each item. Specifically, the acquisition unit 210 acquires the next item (next item) existing on the first side of the item (on the right side in this embodiment) or the character up to the line feed as the character corresponding to the item (FIG. 14). In the example shown, the character "Taro Yamada" is used, and in the example shown in FIG. 15, the character "20135" is used). Further, when the character (excluding the characters constituting the item) does not exist within the predetermined range of the first side of the item (right side in this embodiment: corresponding to horizontal writing), the acquisition unit 210 is the first side of the item. The next item (next item) or the character up to the line feed existing on a different second side (lower side: corresponding to vertical writing in this embodiment) is acquired as the character corresponding to the item.

In addition, the acquisition unit 210 acquires the character existing on the first side (right side in this embodiment) of the item as the character corresponding to the item, depending on the type of processing classified by the classification unit 206, or the item. It may be decided whether to acquire the character existing on the second side (lower side in this embodiment: corresponding to vertical writing) as the character corresponding to the item. In this case, whether the document is written vertically or horizontally is stored in the classification DB 2 according to the type of the document, and the acquisition unit 210 refers to the classification DB 2 and classifies the document in the classification unit 206. Depending on the type of processing performed, the characters existing on the first side of the item (right side in this embodiment) are acquired as the characters corresponding to the item, or the second side of the item (lower side in this embodiment: vertical). It may be decided whether to acquire the character existing in (corresponding to writing) as the character corresponding to the item.

As described above, the server 2 according to the embodiment changes the notation of the information about the target person acquired by the acquisition unit 210 and the acquisition unit 210 to acquire the information about the target person from two or more information sources to a predetermined notation. The target person monitors based on the information about the target person integrated by the notation changing unit 211, the integrated unit 212 that integrates the information about the target person changed to the predetermined display by the notation changing unit 211, and the integrated unit 212. It is provided with a calculation unit 213 for calculating a target risk. Therefore, the risk of the target person can be calculated based on a lot of information, and the convenience is improved.

Further, the notation changing unit 211 of the server 2 according to the embodiment is information relating the information about the target person stored in the notation changing DB 4 and the processing rule for changing the notation of the information (information for logic processing). , And based on the processing rule, the notation of the information about the target person acquired by the acquisition unit 210 is changed to a predetermined notation. Therefore, it is possible to accurately integrate information about the target person obtained from various information sources.

Further, the notation changing unit 211 of the server 2 according to the embodiment is information relating the information about the target person stored in the notation changing DB 4 and the overwriting processing content of the information by the dictionary data (for the first master processing). Information), and based on the processing content, the notation of the information about the target person acquired by the acquisition unit 210 is changed to the predetermined notation. Therefore, it is possible to more accurately integrate the information about the subject obtained from various information sources.

Further, the integrated unit 212 of the server 2 according to the embodiment collates the information about the target person whose display has been changed to the predetermined display by the notation changing unit 211 for each item, and regarding the duplicated items, the most frequently described items are duplicated. Select as the corresponding information. Therefore, it is possible to improve the accuracy in integrating the information about the subject obtained from various information sources.

Further, the calculation unit 213 of the server 2 according to the embodiment monitors the target person based on the risk score set for the combination of each item of the information about the target person stored in the risk calculation DB 6. Calculate the risk. Therefore, by changing the risk rate for each item, the target person can flexibly change the calculation of the risk to be monitored, and the convenience is improved.

Further, the server 2 according to the embodiment refers to the recognition unit 205 that recognizes characters from the image of the document and the information of the items acquired from the document, and determines whether or not the character recognized by the recognition unit 205 has an item. When there is a determination unit 207 for determination and an item for which the determination unit 207 is not determined to exist, the search unit 208 and the search unit 208 search for each character constituting the item from the characters recognized by the recognition unit 205. It includes a connecting unit 209 that processes each character so as to be recognizable as an item, and an acquisition unit 210 that acquires characters corresponding to each item as information about a target person. Therefore, the document can be read effectively, and the character recognition rate of the document is improved.

Further, the search unit 208 of the server 2 according to the present embodiment searches for the existence of other characters constituting the item within a predetermined range starting from one of the characters. Since the search is performed within a predetermined range in this way, characters existing at distant places are not mistakenly recognized as characters constituting the item. Therefore, it is possible to reduce the risk of erroneously acquiring the information corresponding to the item.

Further, the acquisition unit 210 of the server 2 according to the present embodiment acquires the character existing on the first side of the item as the character corresponding to the item. Therefore, it is possible to reduce the risk of erroneously acquiring the information corresponding to the item.

Further, when the character does not exist within the predetermined range on the first side of the item, the acquisition unit 210 of the server 2 according to the present embodiment sets the character existing on the second side different from the first side of the item into the item. Get as the corresponding character. Therefore, the information corresponding to the item can be acquired more effectively.

Further, the server 2 according to the present embodiment includes a correction unit 204 that corrects an image of a document by a plurality of correction patterns and generates a plurality of corrected images corresponding to each correction pattern. Then, the recognition unit 205 recognizes characters from a plurality of corrected images corresponding to each correction pattern generated by the correction unit 204, and selects the most recognized characters from the plurality of corrected images. .. Therefore, at least one of the probability of erroneously reading a character and the probability of not being able to read a character can be reduced, and the correct answer rate of character recognition is improved.

Also, in this embodiment, the correction patterns each include one or more different corrections. Since one or more different corrections are combined in this way, at least one of the probability of erroneously reading a character and the probability of not being able to read a character can be further reduced, and the correct answer rate of character recognition is further improved.

[Modification 1 of the embodiment]
In the above embodiment, the classification unit 206 refers to the classification DB 2 and determines whether or not the prepared pattern matching data or keywords exist in the characters recognized by the recognition unit 205 for each type of document. When the characters recognized by the recognition unit 205 include any one of the prepared pattern match data or keywords, the image data of the document is classified into the types corresponding to the pattern match data or keywords. ing.

However, the classification unit 206 refers to the classification DB 2 and determines whether or not the prepared pattern matching data or keywords exist in the characters recognized by the recognition unit 205 for each type of document, and the recognition unit 205 determines. The image data of the document may be classified into the types in which the prepared pattern matching data and keywords are most contained in the characters recognized in.

In addition, pattern matching data (image data, feature point data (for example, image data of seals, feature point data, etc.)) and keywords (KW) that should not be included for each type of document are stored in the classification DB2. If the characters recognized by the recognition unit 205 include pattern matching data or keywords that should not be included, the image data of the document is classified into the type corresponding to the pattern matching data or keywords. It may not be classified.

[Modification 2 of the embodiment]
Further, in the above embodiment, the item master DB 3 stores the items of information to be acquired for each type of document in association with each other, but the names of the items of information to be acquired for each type of document are unified. You may associate and memorize the name of. Depending on the type of document, the name of the item may differ even though the content is the same. For example, it is conceivable that the item is "name" in one type of document, but the item is "name" in another type of document. In addition, it is conceivable that the item is "address" in one type of document, but the item is "house" in another type of document.

In such a case, in the item master DB3, the name of the item of the information to be acquired for each type of document (for example, "address" or "house") is associated with the unified name of the item (for example, "address"). It may be memorized and the unified item information may be added to the characters corresponding to the items. With this configuration, the names of different items can be unified and managed depending on the type of document, and the convenience of data use such as search and name identification is improved.

1 Information processing system 2 Server (information processing device)
200A communication IF
200B storage device 200C CPU
201 Reception unit 202 Transmission unit 203 Storage device control unit 204 Correction unit 205 Recognition unit 206 Classification unit 207 Determination unit 208 Search unit 209 Coupling unit 210 Acquisition unit 211 Notation change unit 212 Integration unit 213 Calculation unit 3 User terminal 300A Communication IF
300B Storage device 300C Input device 300D Display device 300E CPU
301 Receiving unit 302 Transmitting unit 303 Storage device control unit 304 Operation receiving unit 305 Display device control unit 4 Network DB1 Correction pattern database DB2 Classification database DB3 Item master database DB4 Notation change database DB5 Target person database DB6 Risk calculation database

Claims (8)

An acquisition department that acquires information about the target person from two or more sources,
A notation change unit that changes the notation of information about the target person acquired by the acquisition unit to a predetermined notation, and a notation change unit.
An integrated unit that integrates information about the target person whose display has been changed to a predetermined display in the notation changing unit, and an integrated unit.
A calculation unit for calculating the risk of the target person being monitored based on the information about the target person integrated in the integration unit is provided .
The integrated part is
The information about the target person whose display has been changed to a predetermined display is collated for each item in the notation change unit, and the most frequently described items are selected as the information corresponding to the duplicated items for the duplicated items.
An information processing device characterized by this. The notation change part
With reference to the information relating the information about the target person and the processing rule for changing the notation of the information, the notation of the information about the target person acquired by the acquisition unit is defined as the predetermined information based on the processing rule. Change to notation,
The information processing apparatus according to claim 1. The notation change part
With reference to the information relating the information about the target person and the overwriting processing content by the dictionary data of the information, the notation of the information about the target person acquired by the acquisition unit based on the processing content is described as defined above. Change to notation,
The information processing apparatus according to claim 1 or 2, wherein the information processing device is characterized by the above. The calculation unit
Based on the risk score set for each combination of information about the subject, the risk for which the subject is monitored is calculated.
The information processing apparatus according to any one of claims 1 to 3, wherein the information processing apparatus is characterized. A recognition unit that recognizes characters from image data,
A determination unit that refers to the information of the item acquired from the document and determines whether or not the item exists in the character recognized by the recognition unit.
When there is an item for which it is not determined that the determination unit exists, a search unit for searching each character constituting the item from the characters recognized by the recognition unit is provided.
The acquisition unit
According to the search result in the search unit, the character corresponding to each character is acquired as information about the target person.
The information processing apparatus according to any one of claims 1 to 4, wherein the information processing apparatus is characterized. The search unit
The information processing apparatus according to claim 5 , wherein the information processing apparatus is characterized in that it searches for the existence of other characters constituting the item within a predetermined range starting from one of the characters. The process by which the acquisition department acquires information about the target person from two or more sources,
The process in which the notation changing unit changes the notation of the information about the target person acquired by the acquisition unit to a predetermined notation, and
The process in which the integration unit integrates the information about the target person acquired by the acquisition unit, and
Calculating unit, based on the integrated information on the subject by the integration unit, have a, a step of calculating the risk of the subject is to be monitored,
The integrated part is
The information about the target person whose display has been changed to a predetermined display is collated for each item in the notation change unit, and the most frequently described items are selected as the information corresponding to the duplicated items for the duplicated items.
An information processing method characterized by that. Computer,
Acquisition department that acquires information about the target person from two or more sources,
A notation change unit that changes the notation of information about the target person acquired by the acquisition unit to a predetermined notation,
An integrated unit that integrates information about the target person acquired by the acquisition unit,
Based on the information about the target person integrated in the integrated unit, the target person is made to function as a calculation unit for calculating the risk of being monitored .
The integrated part is
The information about the target person whose display has been changed to a predetermined display is collated for each item in the notation change unit, and the most frequently described items are selected as the information corresponding to the duplicated items for the duplicated items.
An information processing program characterized by this.

Images