Disclosed document concealment device, disclosed document concealment method, and disclosed document concealment program

Abstract

A disclosed-material-concealing device 30 comprises: an extraction unit 31 that extracts a phrase 310 from original material 301 to be disclosed; a determination unit 32 that determines whether or not to perform a concealing process on the phrase 310 on the basis of an attribute 321 of the extracted phrase, an attribute 302 of the disclosure destination of the original material 301 to be disclosed, and a concealment reference 322; and a generation unit 33 that generates post-concealing-process material 330 to be disclosed, which is the result of performing the concealing process on the phrase 310 determined to undergo the concealing process. The concealment reference 322 represents the relationship between the attribute 321 of the phrase, the attribute 302 of the disclosure destination, and the necessity of performing the concealing process, whereby a certain phrase included in the material to be disclosed to a disclosure requester is accurately concealed with high precision in light of the relationship between the information and the disclosure requester.

Description

[Technical field]

[0001] The present invention relates to a disclosed material concealment device, a disclosed material concealment method, and a disclosed material concealment program. [Background technology]

[0002] For example, in a trial, the perpetrator may wish to view materials related to the victim, or the victim may wish to view materials related to the perpetrator. In this case, information in the materials that the requester does not want to know (such as personal information) is provided to the requester by being blacked out (masked) on the paper. There is a demand for technology that supports the process of concealing information that is included in the materials to be disclosed to the requester and that the requester does not want to know.

[0003] In relation to such technology, Patent Document 1 discloses a document processing method for detecting masking target portions from an input document based on a word dictionary that stores character strings to be masked or parts thereof. In this method, the detected masking target portions are stored in a masking result list, and the masking target portions stored in this masking result list are displayed on a display screen. In this method, when any of the displayed masking target portions is modified by a user, the masking target portions stored in the masking result list are rewritten to the masking target portions modified by the user. In this method, the masking target portions in the document are masked based on the masking target portions stored in the rewritten masking result list.

[0004] Patent Document 2 discloses a named entity extraction method that employs a method of sequentially learning extraction rules for extracting named entities from documents and presents candidates that serve as training data to the worker. In this method, reference materials related to the candidates are presented to the worker to assist in identifying named entity candidates.

[0005] Patent Document 3 discloses a learning system that allows learners to study law etc. according to their level and is also convenient for practitioners engaged in legal-related work. This system uses a comparison article button to indicate a number of mutually similar articles and a comparison between the articles. When a comparison between articles is indicated using the comparison article button, this system extracts articles and makes it possible to compare the extracted articles. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2004-227141 A [Patent Document 2] JP 2006-023968 A [Patent Document 3] JP 2012-027491 A Summary of the Invention [Problem to be solved by the invention]

[0007] The criteria for determining whether or not to conceal a certain phrase (character string) included in the document disclosed to the disclosure requester is not a simple criterion such as concealing all personal information. For example, even if the personal information is included in the disclosure document, it is usually not necessary to conceal it if the personal information is obvious to the disclosure requester (for example, the personal information of the disclosure requester himself or herself, or the personal information of a person who has a close relationship with the disclosure requester). If the disclosure document is concealed more than necessary, the document becomes difficult for the disclosure requester to understand. In addition, if the concealment of a phrase that should be concealed due to the relationship between the information included in the disclosure document and the disclosure requester is not performed due to a misjudgment, information that should not be known to the disclosure requester will be leaked. For the above reasons, the challenge is to conceal a certain phrase included in the document disclosed to the disclosure requester with high accuracy and in consideration of the relationship between the information and the disclosure requester. Patent Documents 1 to 3 do not mention this challenge.

[0008] A primary object of the present invention is to accurately and precisely conceal a certain word or phrase contained in a document to be disclosed to a disclosure requester, taking into account the relationship between the information and the disclosure requester. [Means for solving the problem]

[0009] A disclosure material concealment device according to one embodiment of the present invention includes an extraction means for extracting words from an original disclosure target material, a determination means for determining whether or not to perform concealment processing on the words based on attributes of the extracted words, attributes of a destination of the original disclosure target material, and an anonymization criterion, and a generation means for generating the disclosure target material after anonymization processing by performing the anonymization processing on the words determined to be anonymized, wherein the anonymization criterion represents the relationship between the attributes of the words, the attributes of the destination, and the need to perform the anonymization processing.

[0010] In another aspect of achieving the above object, a method for concealing disclosed material according to one embodiment of the present invention comprises using an information processing device to extract words and phrases from an original material to be disclosed, determining whether or not to perform concealment processing on the words and phrases based on attributes of the extracted words and phrases, attributes of a destination of the original material to be disclosed, and concealment criteria, and generating a material to be disclosed after concealment processing in which the words and phrases for which it has been determined that they should be concealed are concealed, wherein the concealment criteria represent a relationship between the attributes of the words and phrases, attributes of the destination of the disclosure, and the need to perform the concealment processing.

[0011] In addition, in a further aspect of achieving the above-mentioned object, a disclosure material concealment program according to one embodiment of the present invention is a program for causing a computer to execute an extraction process for extracting words from an original disclosure target material, a determination process for determining whether or not to perform concealment processing on the words based on attributes of the extracted words, attributes of a disclosure destination of the original disclosure target material, and an anonymization criterion, and a generation process for generating a disclosure target material after anonymization processing by performing the anonymization processing on the words determined to be anonymized, wherein the anonymization criterion represents a relationship between the attributes of the words, the attributes of the disclosure destination, and the need to perform the anonymization processing.

[0012] Furthermore, the present invention can also be realized by a computer-readable, non-volatile recording medium in which such a disclosure document concealment program (computer program) is stored. Effect of the Invention

[0013] According to the present invention, there is provided a disclosure material concealment device etc. that conceals a certain word contained in a material to be disclosed to a disclosure requester with high accuracy and precision based on the relationship between the information and the disclosure requester. [Brief description of the drawings]

[0014] [Figure 1] 1 is a block diagram showing a configuration of a disclosure material concealment device 10 according to a first embodiment of the present invention. [Diagram 2] 1 is a diagram illustrating an example of the configuration of an original disclosure target material 101 and a disclosure target material 164 after anonymization processing according to the first embodiment of the present invention. FIG. [Figure 3A] 1 is a flowchart (1 / 2) showing an operation (process) of the disclosed material concealment device 10 according to the first embodiment of the present invention. [Figure 3B] 1 is a flowchart (2 / 2) showing the operation (processing) of the disclosed material concealment device 10 according to the first embodiment of the present invention. [Figure 4] FIG. 11 is a block diagram showing a configuration of a disclosure material concealment device 30 according to a second embodiment of the present invention. [Diagram 5] 1 is a block diagram showing a configuration of an information processing device 900 capable of realizing the disclosed material concealment device 10 according to the first embodiment of the present invention or the disclosed material concealment device 30 according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

[0016] <First embodiment> 1 is a block diagram showing a configuration of a disclosure material concealment device 10 according to a first embodiment of the present invention. The disclosure material concealment device 10 is a device that generates a disclosure material 164 after concealment processing in which a part of words (character strings) included in an original disclosure material 101 for which a disclosure (view) request has been made is concealed.

[0017] A management terminal device 20 is communicatively connected to the disclosure document concealment device 10. The management terminal device 20 is, for example, a personal computer or other information processing device used when a user of the disclosure document concealment device 10 inputs information to the disclosure document concealment device 10 or checks information output from the disclosure document concealment device 10. The management terminal device 20 is provided with a display screen 200 that displays the information output from the disclosure document concealment device 10.

[0018] The disclosure material concealment device 10 includes an acquisition unit 11, an extraction unit 12, a determination unit 13, a generation unit 14, a learning unit 15, and a memory unit 16. The extraction unit 12, the determination unit 13, the generation unit 14, and the learning unit 15 are examples of an extraction means, a determination means, a generation means, and a learning means, respectively.

[0019] The storage unit 16 is, for example, a storage device such as a RAM (Random Access Memory) or a hard disk 904, which will be described later with reference to Fig. 5. The storage unit 16 stores extraction criteria 161, attribute information 162 of words and phrases, anonymization criteria 163, and disclosure target materials after anonymization processing 164. The information stored in the storage unit 16 will be described in detail later.

[0020] The acquisition unit 11 acquires the original disclosure target material 101 and the attribute information 102 of the disclosure destination from an external device (not shown) in response to an instruction from a user who performs an input operation on the management terminal device 20, for example.

[0021] The original disclosure target material 101 is, for example, a material that the perpetrator requested to be disclosed (viewed) in relation to the victim, or the victim requested to be disclosed in relation to the perpetrator, in a trial of a certain case. Alternatively, the original disclosure target material 101 is, for example, a material that the media publishes as an article about a certain case. Alternatively, the original disclosure target material 101 is, for example, a material created by a certain department in an organization (a company, a government agency, etc.) and requested to be disclosed by another department in the organization or an external institution (police, media, etc.) of the organization. The original disclosure target material 101 may also be a material requested to be disclosed in a case different from the above-mentioned cases.

[0022] The attribute information 102 of the disclosure destination is information that indicates the attributes of a person or organization that has requested the disclosure of the original disclosure target material 101. In this embodiment, hereinafter, the person or organization that has requested the disclosure (viewing) of the original disclosure target material 101 will be referred to as the disclosure destination.

[0023] The attribute information 102 of the disclosure destination indicates, for example, the human relationship of the disclosure destination to a person described in the original disclosure target material 101. More specifically, the human relationship indicates at least one of family members, relatives, friends, working in the same workplace (i.e., superior, colleague, subordinate, etc. at the workplace), and no acquaintance.

[0024] Alternatively, the attribute information 102 of the disclosure destination indicates, for example, the business relationship of the disclosure destination with respect to the department that created the original disclosure target material 101. More specifically, the business relationship indicates, for example, whether it is outside or inside the organization (company, government agency, etc.) to which the department that created the material belongs.

[0025] The acquisition unit 11 inputs the acquired original disclosure target material 101 to the extraction unit 12, and inputs the attribute information 102 of the disclosure target to the determination unit 13. The acquisition unit 11 may store the original disclosure target material 101 and the attribute information 102 of the disclosure target in the storage unit 16.

[0026] The extraction unit 12 extracts words (character strings) from the original disclosure target material 101 acquired by the acquisition unit 11 based on the extraction criteria 161. The extraction criteria 161 are criteria used when extracting words from a sentence using a syntax analysis technique. Note that the syntax analysis technique is a well-known technique, and therefore a detailed description thereof will be omitted in this embodiment.

[0027] Fig. 2 is a diagram illustrating the configuration of the original disclosure target material 101 and the disclosure target material 164 after the anonymization process according to this embodiment. As illustrated in Fig. 2, the extraction unit 12 extracts phrases including phrases A to L from the original disclosure target material 101 as described above. At this time, the extraction unit 12 may also extract position information of each phrase in the original disclosure target material 101 (for example, the coordinates of each phrase in the original disclosure target material 101 represented as a page).

[0028] The extraction unit 12 inputs the result of extracting words and phrases from the original disclosure target material 101 to the determination unit 13. The extraction unit 12 may store the result of extracting words and phrases from the original disclosure target material 101 in the storage unit 16.

[0029] The determination unit 13 determines whether or not to perform an anonymization process for each extracted term, based on the term attribute information 162 related to the term extracted by the extraction unit 12, the disclosure destination attribute information 102 acquired by the acquisition unit 11, and anonymization criteria 163. Note that the anonymization criteria 163 is a criterion that indicates the relationship between the attribute of the extracted term, the attribute of the disclosure destination, and the necessity of performing anonymization process.

[0030] The attribute information 162 of a phrase indicates, for example, a type of personal information. More specifically, the type of personal information indicates at least one of a person's name, age, address, contact information (e.g., a telephone number, an email address, etc.), a financial institution account number, a credit card number, a pension number, a resident's card code, a social security number, a driver's license number, a vehicle number, an insurance card number, and a passport number. The type of personal information is not limited to the above.

[0031] Alternatively, the attribute information 162 of the phrase indicates, for example, the type of organizational information or the level of confidentiality. More specifically, the type of organizational information indicates, for example, any of the organization name, the location of the organization, and contact information. More specifically, the level of confidentiality indicates, for example, organization confidential or related person confidential. The type of organizational information and the level of confidentiality are not limited to those described above.

[0032] Alternatively, the attribute information 162 of the phrase may represent, for example, a date and time. For example, the date and time when the original disclosure target material 101 was created, which is written in the original disclosure target material 101, may need to be kept secret in some cases.

[0033] For example, in a trial of a certain incident, for a certain phrase extracted from original disclosure target material 101 requested for disclosure by the victim or perpetrator, attribute information 162 of the phrase is indicated as "contact information." And attribute information 102 of the disclosure destination is indicated as "unacquainted." In this case, since it is not desirable for the "contact information" information to be known by the victim and perpetrator, who never met in the first place, anonymization standard 163 indicates that the phrase is to be anonymized.

[0034] For example, in a trial of a certain case, with regard to a certain phrase extracted from original disclosure target material 101 for which disclosure has been requested by the victim or perpetrator, attribute information 162 of the phrase indicates that it is a "person's name." In addition, attribute information 102 of the disclosure destination indicates that it is "same workplace." In this case, since the names of the victim and perpetrator are known to each other and there is no need to conceal the phrase, concealment standard 163 indicates that the phrase will not be concealed.

[0035] For example, for a certain term extracted from original disclosure target document 101 created by a certain department in a company, attribute information 162 of the term indicates "confidential (organization confidential)". And, attribute information 102 of the disclosure destination indicates "outside the company". In this case, confidential information cannot be disclosed outside the company, so anonymization standard 163 indicates that the term is anonymized. Also, if attribute information 162 of the term indicates "confidential" and attribute information 102 of the disclosure destination indicates "inside the company", confidential information can be disclosed inside the company, so anonymization standard 163 indicates that the term is not anonymized.

[0036] When original disclosure target material 101 related to a certain person is disclosed to a recipient, generally, the deeper the personal relationship between the person and the recipient, the more the personal information is known to each other. Therefore, the anonymization standard 163 shows a tendency to reduce the amount of material to be anonymized the deeper the personal relationship.

[0037] In addition, when the media publishes an article on the original disclosure target material 101 regarding an incident or event, there is more publicly known information about famous people than about ordinary people. Therefore, the anonymization criteria 163 tend to reduce the number of objects to be anonymized when the attribute information 162 of the phrase indicates that it is information about famous people, rather than when it indicates that it is information about ordinary people.

[0038] Moreover, the anonymization standard 163 represents a relationship between the attribute information 102 of the disclosure destination and the attribute information 162 of the phrase, which are generally expressed as a multidimensional vector, and the necessity of performing anonymization processing of the phrase. The anonymization standard 163 may be, for example, a rule-based standard created by a user. Alternatively, the anonymization standard 163 may be, for example, a learning model generated or updated by learning by the learning unit 15 described later. In that case, the anonymization standard 163 is a learning model in which the attribute information 102 of the disclosure destination and the attribute information 162 of the phrase are explanatory variables and the necessity of performing anonymization processing of the phrase is an objective variable.

[0039] The determination unit 13 inputs the determination result as to whether or not to perform the concealment process for each extracted word or phrase to the generation unit 14.

[0040] The generation unit 14 generates the anonymized disclosure target material 164 by performing anonymization processing on each term based on the determination result for each term input from the determination unit 13. In the example shown in Fig. 2, the generation unit 14 generates the anonymized disclosure target material 164 by performing anonymization processing on the terms C, F, and L determined by the determination unit 13 as targets for anonymization.

[0041] 2, the generation unit 14 may perform a process of painting out the anonymized words and phrases in the post-anonymization disclosure target material 164 displayed on the display screen 200 or printed on a paper surface by a printing device (not shown) so that they are not visible. At this time, the generation unit 14 may specify the positions to be painted out by using position information of each word and phrase in the original disclosure target material 101 extracted by the extraction unit 12 (such as the coordinates of each word and phrase in the original disclosure target material 101 represented as a paper surface).

[0042] Alternatively, the generation unit 14 may perform the anonymization process by abstracting a phrase that is a proper noun to be anonymized, for example, person A and place B. In this case, however, a criterion (not shown) for abstracting proper nouns is stored in advance in the storage unit 16, and the generation unit 14 abstracts proper nouns using the criterion.

[0043] The learning unit 15 generates or updates the anonymization criteria 163 by learning the relationship between the attribute information 162 of the phrase, the attribute information 102 of the disclosure destination, and the necessity of performing anonymization processing of the phrase.

[0044] 2, suppose that the user desires the anonymized disclosure target material 164 in which the phrases C, F, and L have been anonymized, but the anonymized disclosure target material 164 generated by the disclosure material anonymization device 10 does not anonymize the phrase F. In this case, the user can confirm that the anonymized disclosure target material 164 displayed on the display screen 200 of the management terminal device 20 does not anonymize the phrase F. Then, the management terminal device 20 accepts an input operation by the user to modify the anonymized disclosure target material 164 so as to anonymize the phrase F.

[0045] In the above case, the reason why concealment was not performed on the term F may be that the attribute of the term F indicated in the term attribute information 162 is incorrect or unregistered. The user checks the attribute of the term F on a menu screen for confirming and updating the term attribute information 162 displayed on the display screen 200. Then, if it is necessary to update the attribute of the term F, the management terminal device 20 accepts an input operation by the user to update the attribute of the term F in the term attribute information 162.

[0046] The learning unit 15 receives information representing the above-mentioned input operation by the user from the management terminal device 20, and updates the anonymized disclosure target material 164 and the attribute information of the words and phrases 162. The learning unit 15 generates or updates the anonymization standard 163 by performing learning using the attribute information 102 of the disclosure destination, the attribute information 162 of the words and phrases updated as described above, and the anonymized disclosure target material 164 as teacher data.

[0047] Next, the operation (processing) of the disclosure material concealment device 10 according to this embodiment will be described in detail with reference to the flowcharts of FIGS. 3A and 3B.

[0048] The acquisition unit 11 acquires the original disclosure target material 101 and the attribute information 102 of the disclosure destination from an external device (step S101). The extraction unit 12 extracts words and phrases from the original disclosure target material 101 acquired by the acquisition unit 11 using the extraction criterion 161 (step S102). The determination unit 13 determines whether or not to perform anonymization processing for each word and phrase extracted by the extraction unit 12, based on the attribute information 162 of the word and the attribute information 102 of the disclosure destination, and the anonymization criterion 163 (step S103).

[0049] The generation unit 14 generates the disclosure target material 164 after anonymization processing by performing anonymization processing on the words and phrases that were subject to anonymization processing in the judgment by the judgment unit 13, and displays the generated disclosure target material 164 after anonymization processing on the display screen 200 of the management terminal device 20 (step S104).

[0050] If the user does not perform an input operation to correct the anonymized disclosure target material 164 for a certain word in the management terminal device 20 (No in step S105), the entire process ends. If the user performs an input operation to correct the anonymized disclosure target material 164 for a certain word in the management terminal device 20 (Yes in step S105), the learning unit 15 updates the anonymized disclosure target material 164 for the word (step S106).

[0051] If an input operation for updating the word attribute information 162 is not performed in the management terminal device 20 for the word (No in step S107), the process proceeds to step S109. If an input operation for updating the word attribute information 162 for the word is performed in the management terminal device 20 for the word (Yes in step S107), the learning unit 15 updates the word attribute information 162 for the word (step S108).

[0052] The learning unit 15 updates the anonymization criteria 163 by performing learning for the phrase using the attribute information 162 of the phrase, the attribute information 102 of the disclosure destination, and the disclosure target material 164 after the anonymization process as training data (step S109), and then the entire processing is terminated.

[0053] The disclosed material anonymization device 10 according to this embodiment can anonymize a certain phrase contained in a material to be disclosed to a disclosure requester with high accuracy based on the relationship between the information and the disclosure requester. This is because the disclosed material anonymization device 10 anonymizes the phrase contained in the material by using an anonymization criterion 163 that indicates the relationship between the attribute of the phrase contained in the material, the attribute of the disclosure destination, and the necessity of anonymization processing.

[0054] The effects achieved by the disclosed material concealment device 10 according to this embodiment will be described in detail below.

[0055] The criteria for determining whether or not to conceal a certain word (character string) contained in a document to be disclosed to a disclosure requester are not simple criteria such as concealing all personal information. For example, even if the personal information is contained in the disclosure document, it is usually not necessary to conceal it if the personal information is obvious to the disclosure requester (for example, the personal information of the disclosure requester himself or herself, or the personal information of a person who has a close relationship with the disclosure requester). If more concealment is performed than necessary in the disclosure document, the document will be difficult for the disclosure requester to understand. In addition, if a word that should be concealed is not concealed due to a misjudgment or other reason, information that should not be known to the disclosure requester will be leaked. For the above reasons, the challenge is to conceal a certain word contained in a document to be disclosed to a disclosure requester with high accuracy and accuracy, taking into account the relationship between the information and the disclosure requester.

[0056] In response to such a problem, the disclosure document concealment device 10 according to the present embodiment includes an extraction unit 12, a determination unit 13, and a generation unit 14, and operates as described above with reference to, for example, Figs. 1 to 3B. That is, the extraction unit 12 extracts a word or phrase from the original disclosure target document 101. The determination unit 13 determines whether or not to conceal the word or phrase based on attribute information 162 of the word or phrase representing the attribute of the word or phrase, attribute information 102 of the disclosure target representing the attribute of the disclosure target of the original disclosure target document 101, and an anonymization criterion 163. However, the anonymization criterion 163 represents the relationship between the attribute information 162 of the word or phrase, the attribute information 102 of the disclosure target, and the necessity of anonymization. Then, the generation unit 14 generates the disclosure target document 164 after anonymization processing, in which anonymization processing is performed on the word or phrase determined to be anonymized. As a result, the disclosure material concealment device 10 can conceal a certain word or phrase contained in a material to be disclosed to the disclosure requesting party with high accuracy and precision, taking into account the relationship between the information and the disclosure requesting party.

[0057] The disclosed material anonymization device 10 according to this embodiment further includes a learning unit 15 that generates or updates the anonymization criteria 163 by learning the relationship between the attribute information 162 of the phrase, the attribute information 102 of the disclosure destination, and the necessity of anonymization processing. The learning unit 15 generates or updates the anonymization criteria 163 by accepting an input operation by a user that updates the attribute information 162 of the phrase. This allows the disclosed material anonymization device 10 to increase the accuracy of anonymizing a certain phrase included in a material to be disclosed to a disclosure requesting party, based on the relationship between the information and the disclosure requesting party.

[0058] <Second embodiment> 4 is a block diagram showing a configuration of a disclosed document concealment device 30 according to a second embodiment of the present invention. The disclosed document concealment device 30 includes an extraction unit 31, a determination unit 32, and a generation unit 33. Note that the extraction unit 31, the determination unit 32, and the generation unit 33 are examples of an extraction means, a determination means, and a generation means, respectively.

[0059] The extraction unit 31 extracts words and phrases 310 from an original disclosure target material 301. The original disclosure target material 301 is, for example, a material similar to the original disclosure target material 101 according to the first embodiment. The extraction unit 31 operates in the same manner as the extraction unit 12 according to the first embodiment, for example.

[0060] The determination unit 32 determines whether or not to perform an anonymization process on the term 310, based on the attribute 321 of the extracted term, the attribute 302 of the disclosure destination of the original disclosure target material 301, and the anonymization criterion 322. Note that the anonymization criterion 322 represents the relationship between the attribute 321 of the term, the attribute 302 of the disclosure destination, and the necessity of performing anonymization. The anonymization criterion 322 is, for example, the same criterion as the anonymization criterion 163 according to the first embodiment.

[0061] The attribute 321 of the phrase is, for example, the same attribute as the attribute indicated by the attribute information 162 of the phrase according to the first embodiment. The attribute 302 of the disclosure destination is, for example, the same attribute as the attribute indicated by the attribute information 102 of the disclosure destination according to the first embodiment. The determination unit 32 operates in the same manner as the determination unit 13 according to the first embodiment, for example.

[0062] The generating unit 33 generates the anonymized disclosure target material 330 by performing anonymization processing on the phrase 310 determined to be anonymized. The anonymized disclosure target material 330 is, for example, a material similar to the anonymized disclosure target material 164 according to the first embodiment. The generating unit 33 operates in the same manner as the generating unit 14 according to the first embodiment, for example.

[0063] The disclosed material anonymization device 30 according to this embodiment can anonymize a certain phrase contained in a material to be disclosed to a disclosure requester with high accuracy based on the relationship between the information and the disclosure requester. This is because the disclosed material anonymization device 30 anonymizes the phrase contained in the material by using an anonymization criterion 322 that indicates the relationship between the attribute of the phrase contained in the material, the attribute of the disclosure destination, and the necessity of anonymization processing.

[0064] <Hardware configuration example> In each of the above-mentioned embodiments, each unit of the disclosed document concealment device 10 shown in Fig. 1 or the disclosed document concealment device 30 shown in Fig. 4 can be realized by a dedicated HW (Hardware) (electronic circuit). In Fig. 1 and Fig. 4, at least the following configurations can be regarded as functional (processing) units (software modules) of a software program. ·Acquisition part 11, Extraction units 12 and 31, Determination units 13 and 32, Generation units 14 and 33, · Learning section 15, Memory control function in the memory unit 16.

[0065] However, the division of the various parts shown in these drawings is for the convenience of explanation, and various configurations may be assumed when implementing the system. An example of the hardware environment in this case will be described with reference to FIG.

[0066] Fig. 5 is a diagram for illustratively explaining the configuration of an information processing device 900 (computer) capable of realizing the disclosed document anonymization device 10 according to the first embodiment of the present invention or the disclosed document anonymization device 30 according to the second embodiment of the present invention. That is, Fig. 5 shows the configuration of a computer (information processing device) capable of realizing the disclosed document anonymization devices 10 and 30 shown in Figs. 1 and 4, and represents a hardware environment capable of realizing each function in the above-mentioned embodiments.

[0067] The information processing device 900 shown in FIG. 5 includes the following components, but may not include some of the following components. ·CPU(Central_Processing_Unit)901, ROM (Read_Only_Memory) 902, ·RAM(Random_Access_Memory)903, Hard disk (storage device) 904, A communication interface 905 for communicating with external devices; Bus 906 (communication line), A reader / writer 908 capable of reading and writing data stored in a recording medium 907 such as a CD-ROM (Compact Disc Read Only Memory), · Input / output interfaces 909 such as monitors, speakers, keyboards, etc.

[0068] That is, the information processing device 900 including the above components is a general computer in which these components are connected via a bus 906. The information processing device 900 may include a plurality of CPUs 901, or may include a CPU 901 configured with multiple cores. The information processing device 900 may include a GPU (Graphical Processing Unit) (not shown) in addition to the CPU 901.

[0069] The present invention, explained using the above-mentioned embodiment as an example, supplies a computer program capable of realizing the following functions to the information processing device 900 shown in Fig. 5. The functions are the above-mentioned configurations in the block configuration diagrams (Figs. 1 and 4) referred to in the explanation of the embodiment, or the functions of the flowcharts (Figs. 3A and 3B). The present invention is then achieved by reading the computer program into the CPU 901 of the hardware, interpreting it, and executing it. The computer program supplied to the device may be stored in a readable and writable volatile memory (RAM 903), or a non-volatile storage device such as a ROM 902 or a hard disk 904.

[0070] In the above case, the method of supplying the computer program to the hardware can be a currently common procedure, such as installing the program in the device via a recording medium 907 such as a CD-ROM, or downloading the program from an external source via a communication line such as the Internet. In such a case, the present invention can be considered to be configured by the code constituting the computer program, or the recording medium 907 on which the code is stored.

[0071] The present invention has been described above by taking the above-mentioned embodiment as an exemplary example. However, the present invention is not limited to the above-mentioned embodiment. That is, the present invention can be applied in various aspects that can be understood by a person skilled in the art within the scope of the present invention.

[0072] This application claims priority to Japanese Patent Application No. 2021-176074, filed on October 28, 2021, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0073] 10. Disclosure Document Concealment Device 101 Original disclosure material 102 Attribute information of disclosure recipient 11 Acquisition Department 12 Extraction part 13 Judgment section 14 Generation part 15 Learning Department 16 Memory section 161 Extraction criteria 162 Attribute information of words 163 Confidentiality Standards 164 Documents to be disclosed after redaction 20 Management terminal 200 display screen 30 Disclosure Document Concealment Device 301 Original disclosure material 302 Attributes of the Disclosure 31 Extraction part 310 words 32 Judgment section 321 Term Attributes 322 Confidentiality Standards 33 Generation part 330 Documents to be disclosed after redaction 900 Information processing device 901 CPU 902 ROM 903 RAM 904 Hard disk (storage device) 905 Communication Interface 906 Bus 907 Recording media 908 Reader / Writer 909 Input / Output Interface

Claims

1. An extraction means for extracting words and phrases from the original disclosure target material; a determination means for determining whether or not to perform an anonymization process on the extracted term based on an attribute of the term, an attribute of a disclosure destination of the original disclosure target material, and an anonymization criterion; a generating means for generating a post-anonymization-processed disclosure target material by performing the anonymization process on the word or phrase determined to be anonymized; Equipped with the anonymization criterion represents a relationship between an attribute of the phrase, an attribute of the disclosure destination, and a need to perform the anonymization process; The attribute of the phrase indicates a type of personal information or a date and time, The attribute of the disclosure destination represents a relationship between the disclosure destination and a person described in the original disclosure target material, A device for concealing disclosed information.

2. The type of personal information indicates at least one of a person's name, age, address, contact information, a financial institution account number, a credit card number, a pension number, a resident's card code, a social security number, a driver's license number, a vehicle registration number, an insurance card number, and a passport number, The human relationships indicate at least one of family, relatives, friends, being in the same workplace, and not knowing each other. The disclosure material concealment device according to claim 1.

3. The attribute of the phrase indicates a type of organizational information or a level of confidentiality; The attribute of the disclosure destination represents a business relationship of the disclosure destination with respect to the department that created the original disclosure target material, The disclosure material concealment device according to claim 1.

4. The type of organization information indicates any one of an organization name, an organization location, and a contact information, The level of confidentiality indicates organization confidentiality or person confidentiality, The business relationship may be external or internal to the organization to which the production department belongs. The disclosure material concealment device according to claim 3.

5. a learning means for learning a relationship between an attribute of the phrase, an attribute of the disclosure destination, and a need for performing the anonymization process, to generate or update the anonymization criteria; The disclosure material concealment device according to any one of claims 1 to 4.

6. the learning means generates or updates the anonymization criteria by receiving an input operation by a user that updates attributes of the words and phrases; The disclosure material concealment device according to claim 5.

7. the generating means performs the concealment process by painting over the words so that they are not visible or by abstracting the words. The disclosure material concealment device according to any one of claims 1 to 6.

8. By the information processing device, Extract words and phrases from the original disclosure material, determining whether or not to perform anonymization processing on the extracted term based on an attribute of the term, an attribute of a disclosure destination of the original disclosure target material, and anonymization criteria; generating a post-anonymization-processed disclosure target material by performing the anonymization process on the phrase determined to be anonymized; 1. A method comprising: the anonymization criterion represents a relationship between an attribute of the phrase, an attribute of the disclosure destination, and a need to perform the anonymization process; The attribute of the phrase indicates a type of personal information or a date and time, The attribute of the disclosure destination represents a relationship between the disclosure destination and a person described in the original disclosure target material, Methods for concealing disclosed documents.

9. an extraction process for extracting words and phrases from the original disclosure target materials; a determination process for determining whether or not to perform an anonymization process on the extracted term based on an attribute of the term, an attribute of a disclosure destination of the original disclosure target material, and an anonymization criterion; a generation process for generating a post-anonymization-processed disclosure target material by performing the anonymization process on the phrase determined to be anonymized; A program for causing a computer to execute the above, the anonymization criterion represents a relationship between an attribute of the phrase, an attribute of the disclosure destination, and a need to perform the anonymization process; The attribute of the phrase indicates a type of personal information or a date and time, The attribute of the disclosure destination represents a relationship between the disclosure destination and a person described in the original disclosure target material, Disclosure document concealment program.

Images