Information processing apparatus, information processing method, and program

Abstract

Provided are an information processing apparatus, an information processing method, and a program capable of suitably protecting personal information while realizing smooth execution of the certification business of long-term care insurance. 【Solution means】The information processing apparatus acquires electronic data of long-term care certification review meeting materials, which are review documents in the certification business of long-term care insurance, from an administrative terminal. Then, it classifies the specific expressions included in the text described in the acquired long-term care certification review meeting materials, and determines whether the classification is a classification target for masking based on the masking setting information stored in advance. Furthermore, based on the determination result, it masks the specific expressions according to the preset content, and provides the long-term care certification review meeting materials after masking to the administrative terminal.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] Conventionally, various systems for preventing leakage of personal information have been proposed. For example, Patent Document 1 discloses a method for protecting personal information stored in a character input support server.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the technique described in Patent Document 1 may lack flexibility in suitably protecting only personal information while leaving the information necessary for business as it is. For example, when protecting personal information described in the documents for review in the certification business of long-term care insurance, i.e., the long-term care certification review meeting materials, it is necessary to leave the information necessary for the long-term care insurance certification business as it is and mask only the personal information. Therefore, there is room for improvement from the viewpoint of suitably protecting personal information while realizing the smooth progress of the long-term care insurance certification business.

[0005] The present invention has been made in view of the above circumstances, and an object thereof is to provide an information processing apparatus, an information processing method, and a program capable of suitably protecting personal information while realizing the smooth progress of the long-term care insurance certification business.

Means for Solving the Problems

[0006] To achieve the above object, an information processing apparatus according to a first aspect of the present invention is A care certification review document acquisition means for acquiring electronic data of care certification review meeting materials, which are review documents in the certification business of long-term care insurance, from an administrative terminal, A classification determination means for classifying unique expressions included in the text described in the care certification review meeting materials acquired by the care certification review meeting material acquisition means, A masking target determination means for determining whether the classification of the unique expression determined by the classification determination means is a classification target for masking based on masking setting information stored in advance, A masking processing means for masking the unique expression according to preset content based on the determination result by the masking target determination means, An output means for providing the care certification review meeting materials after the masking is performed by the masking processing means to the administrative terminal, is provided.

[0007] The masking processing means may perform masking by converting the unique expression into the content specified by the masking setting information. It may be like this.

[0008] The masking processing means may set the display mode of the unique expression after the masking to a specific mode that is a certain mode. A display different from the display mode of the specific expression that has not been masked It may be like this. It may be like this.

[0009] The classification determination means performs morphological analysis of the text described in the care certification review meeting materials and classifies the unique expression using a learning model that has been machine-learned in advance by supervised learning. The masking processing means may set the display mode of the unique expression after the masking to different display modes according to the reliability of the classification of the unique expression using the learning model in the classification determination means. It may be like this.

[0010] When the masking processing means includes a specific character string preset in the specific expression, masking is performed by converting it into a special character string different from the content specified by the masking setting information. It may be like this.

[0011] To achieve the above object, an information processing method according to a second aspect of the present invention is Comprising a means for acquiring materials of the care certification review committee, a classification determination means, a masking target determination means, a masking processing means, and an output means An information processing method by an information processing apparatus, The means for acquiring materials of the care certification review committee A step of obtaining electronic data of care certification review meeting materials, which are review documents in the certification business of long-term care insurance, from an administrative terminal, The classification determination means A classification determination step of classifying specific expressions included in the text described in the care certification review meeting materials obtained in the care certification review meeting materials acquisition step, The masking target determination means A masking target determination step of determining whether the classification of the specific expression determined in the classification determination step is a classification of a masking target based on masking setting information stored in advance, The masking processing means A masking processing step of masking the specific expression according to preset content based on the determination result in the masking target determination step, The output means An output step of providing the care certification review meeting materials after performing the masking in the masking processing step to the administrative terminal, and includes.

[0012] To achieve the above object, a program according to a third aspect of the present invention is A computer, A means for obtaining electronic data of care certification review meeting materials, which are review documents in the certification business of long-term care insurance, from an administrative terminal, A classification determination means for classifying specific expressions included in the text described in the care certification review meeting materials obtained by the care certification review meeting materials acquisition means, Masking target determination means for determining whether or not the classification of the specific expression determined by the classification determination means is the classification of the masking target, based on masking setting information stored in advance. Masking processing means for masking the specific expression according to preset content based on the determination result by the masking target determination means. Output means for providing the long-term care insurance certification review meeting materials after the masking by the masking processing means to the administrative terminal. Function as.

Advantages of the Invention

[0013] According to the present invention, personal information can be suitably protected while realizing smooth execution of the certification business of long-term care insurance.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Embodiments for Carrying Out the Invention

[0015] (Embodiment) An information processing apparatus, an information processing method, and a program according to an embodiment of the present invention will be described in detail with reference to the drawings. Note that the same or corresponding parts in the drawings are denoted by the same reference numerals. Hereinafter, an example in which the information processing apparatus in the present invention is applied to the information processing system 1 shown in FIG. 1 will be described.

[0016] As shown in FIG. 1, the information processing system 1 is composed of an administrative terminal 200 and an information processing apparatus 100, and each is communicably connected via a network 210. In the illustrated example, an example in which there is a single administrative terminal 200 is shown, but there are a plurality of them. Further, the network 210 is a dedicated network such as a comprehensive administrative network.

[0017] The administrative terminal 200 is, for example, an information terminal (so-called computer) such as a smartphone, a tablet, or a PC (Personal Computer) in an administrative agency that performs care certification work in a local public body, and can transmit and receive various data to and from the information processing apparatus 100 via the network 210.

[0018] The information processing apparatus 100 is an information terminal such as a smartphone, a tablet, or a PC, and can transmit and receive various data to and from the administrative terminal 200 via the network 210. The information processing apparatus 100 has a function of providing only the personal information masked while leaving the information necessary for care certification as it is with respect to the information described in the care certification review meeting materials transmitted from the administrative terminal 200.

[0019] Next, with reference to FIG. 2, the configuration of the information processing apparatus 100 will be described.

[0020] As shown in FIG. 2, the information processing apparatus 100 includes a storage unit 110, a control unit 120, an input / output unit 130, a communication unit 140, and a system bus (not shown) that interconnects these components.

[0021] The storage unit 110 includes a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. The ROM stores a program 111 executed by the CPU (Central Processing Unit) of the control unit 120, various types of data (not shown) necessary in advance for executing the program 111, masking setting information 112, and a learning model 113.

[0022] The program 111 is a program that executes the processing of the information processing system described later and is stored in the storage unit 110 in advance.

[0023] The masking setting information 112 is a list of information (see FIG. 3) for determining whether to perform masking and for specifying the string after masking, and is stored in the storage unit 110 in advance. Note that the content of the masking setting information 112 can be appropriately changed by the user.

[0024] As shown in FIG. 3, the masking setting information 112 includes information such as "classification", "masking presence / absence", and "string after masking". Specifically, "classification" indicates the classification of words included in the nursing care certification review committee materials, and the classification determination unit 122 described later uses the learning model 113 to determine which classification it is by an AI (Artificial Intelligence) learned. For example, in the case where the word "person's name" shown in FIG. 3 is an individual's name (e.g., "○ Yamada ○ Otoko") included in the nursing care certification review committee materials, the classification determination unit 122 determines that the "○ Yamada ○ Otoko" is in the "person's name" classification.

[0025] "Presence or absence of masking" is information indicating whether masking is performed or not, and is set in advance by the user. In the example shown in FIG. 3, for classifications such as "name", "age", and "gender", the setting of "perform masking" is made, while for the classification of "disease name", an example of the setting of "do not perform masking" is shown. "The masked string" indicates the string to be displayed after masking. In the example shown in FIG. 3, for example, it shows that the word "Mr. ○ Yamada" which is a classification of "name" included in the materials of the care certification review committee is replaced (masked) with a string such as "name". Note that the masked string can be changed as appropriate. Also, it may be not only a string but also a symbol or a number. Furthermore, any form may be used as long as the word before masking cannot be visually recognized, such as a blank or a black marker, as long as it is set in advance what form of display to use.

[0026] The learning model 113 is a learning model when performing classification by the classification determination unit 122 described later. The learning model 113 is an AI model in which the information necessary for care certification is learned as supervised learning. More specifically, the learning model 113 is an AI model in which it is learned by supervised learning which classification in care the word to be classified belongs to, such as "○○ Clinic" belonging to the classification of "medical institution name" and "Neo Sti Minami Yamada" belonging to the classification of "facility name". Note that the learning of the learning model 113 in this embodiment is performed in two stages: pre-training using a large amount of text data and post-training specialized for extraction of specific expressions. In pre-training, Japanese morphemes are digitized (vectorized), and in post-training, learning is performed so as to output a determination result as to whether the vector of the digitized token is a specific expression (person name, company name, facility name, etc.) or not. Note that the learning model 113 is, for example, a natural language processing model such as BERT (Bidirectional Encoder Representations from Transformers). The learning model 113 is not limited to a model that performs two stages of pre-training and post-training, and may be, for example, a model that performs only pre-training or a model that performs only post-training.

[0027] The control unit 120 is composed of a CPU, an ASIC (Application Specific Integrated Circuit), etc. The control unit 120 operates according to the program 111 stored in the storage unit 110 and executes the processing according to the program 111. As the main functional units provided by the program 111 stored in the storage unit 110, the control unit 120 includes a nursing care certification review meeting material acquisition and conversion unit 121, a classification determination unit 122, a masking target determination unit 123, a masking processing unit 124, and a correction confirmation output processing unit 125.

[0028] The nursing care certification review meeting material acquisition and conversion unit 121 is a functional unit that acquires nursing care certification review meeting materials from the administrative terminal 200. The nursing care certification review meeting materials include a primary determination result, a certification survey form, and a doctor's opinion letter. The primary determination result is the result of the primary determination based on the certification survey form and the doctor's opinion letter, and is the result determined by the system introduced in the administration. The certification survey form describes the content heard from the nursing care certification target person by the investigator and includes items such as a general survey and special notes. The doctor's opinion letter is described by the attending doctor of the nursing care certification target person. The nursing care certification review meeting materials are a document that combines these, and the nursing care certification review meeting material acquisition and conversion unit 121 has a function of receiving the electronic file (PDF file) of the acquisition of the nursing care certification review meeting materials.

[0029] In addition, the Nursing Care Certification Review Meeting Document Acquisition and Conversion Unit 121 also has a function of converting the nursing care certification review meeting documents obtained from the administrative terminal 200 from image data to character data by performing OCR (Optical Character Reader) input. Note that the conversion of character data by the Nursing Care Certification Review Meeting Document Acquisition and Conversion Unit 121 may be performed by AIOCR. Also, the conversion to character data in the Nursing Care Certification Review Meeting Document Acquisition and Conversion Unit 121 may be performed by an external functional unit via the network 210 instead of the Nursing Care Certification Review Meeting Document Acquisition and Conversion Unit 121. Note that the Nursing Care Certification Review Meeting Document Acquisition and Conversion Unit 121 may obtain, for example, data converted from image data to character data on the side of the administrative terminal 200, that is, the nursing care certification review meeting documents converted to character data, from the administrative terminal 200.

[0030] The Classification and Judgment Unit 122 is a functional unit that classifies the terms included in the nursing care certification review meeting documents obtained by the Nursing Care Certification Review Meeting Document Acquisition and Conversion Unit 121 and converted into character data. Specifically, the Classification and Judgment Unit 122 is a functional unit that classifies the named entities included in the sentences described in the nursing care certification review meeting documents using a named entity extraction function such as BERT. That is, the Classification and Judgment Unit 122 has a function of extracting the named entities included in a given sentence (nursing care certification review meeting document) and classifying the named entities into pre-defined labels. For example, if there is a description in the nursing care certification review meeting document such as "After entering Neostie Nanshan Yamada in H9 year, entered the current fee nursing home Best Life Yamada in July 2022.", the Classification and Judgment Unit 122 performs classification by AI using the learning model 113 and determines that "Neostie Nanshan Yamada" and "Best Life Yamada" belong to the classification of "facility name". Note that the Classification and Judgment Unit 122 may function as a classification acquisition unit. That is, the determination of classification may be performed by an external functional unit via the network 210 instead of the Classification and Judgment Unit 122 in the information processing apparatus 100, and the classification acquisition unit may obtain the classification classified by the external functional unit.

[0031] The masking target determination unit 123 is a functional unit that determines whether to perform masking on the words of the classification determined by the classification determination unit 122. Specifically, the masking target determination unit 123 determines whether to perform masking on the words of the classification determined by the classification determination unit 122 based on the setting of the masking setting information 112. For example, when the setting of the masking setting information 112 is the setting shown in FIG. 3, as described above, if the classification determined by the classification determination unit 122 is a classification such as "person's name", "age", "gender", etc., the masking target determination unit 123 determines that masking is to be performed on the words of the classification. On the other hand, if the classification determined by the classification determination unit 122 is the classification of "disease name", the masking target determination unit 123 determines that masking is not to be performed on the words of the classification. For example, when the classification determination unit 122 determines that "Neosty Nanshan Yamada" and "Home Best Life Yamada" belong to the classification of "facility name", the masking target determination unit 123 determines to mask the "Neosty Nanshan Yamada" and "Home Best Life Yamada" based on the setting of the masking setting information 112 shown in FIG. 3.

[0032] Returning to FIG. 2, the masking processing unit 124 is a functional unit that masks words determined to be masked based on the determination result by the masking target determination unit 123. Specifically, the masking processing unit 124 performs masking by changing the words determined to be masked by the masking target determination unit 123 to the "string after masking" set in the masking setting information 112. For example, in the classification determination unit 122, when it is determined that "Neostie Nanshan Yamada" and "Home Best Life Yamada" belong to the classification of "facility name", the masking target determination unit 123 determines to mask the "Neostie Nanshan Yamada" and the "Home Best Life Yamada". Then, the masking processing unit 124 performs masking by changing the "Neostie Nanshan Yamada" and the "Home Best Life Yamada" to "facility name" respectively based on the settings of the masking setting information 112 shown in FIG. 3. Note that the masking processing unit 124 in this embodiment displays the string after masking in a prominent manner (for example, a specific manner such as bold, red, or underlined) so that it is easily visible to the user that masking has been performed. Note that the masking processing unit 124 also has a function of notifying the administrative terminal 200 that the masking of the nursing care certification review meeting materials has been completed.

[0033] The correction confirmation output processing unit 125 is a functional unit that has functions of providing a confirmation screen of the nursing care certification review meeting materials after masking by the masking processing unit 124 to the administrative terminal 200, accepting corrections and executing the corrections, and outputting the results. Specifically, the correction confirmation output processing unit 125 is a functional unit that displays the nursing care certification review meeting materials after masking by the masking processing unit 124 and the nursing care certification review meeting materials before masking in parallel on the administrative terminal 200. Also, the correction confirmation output processing unit 125 is a functional unit that corrects the content of the nursing care certification review meeting materials after masking based on a correction instruction from the administrative terminal 200. Furthermore, the correction confirmation output processing unit 125 is a functional unit that outputs the results by providing the nursing care certification review meeting materials after masking as a PDF file in response to a request from the administrative terminal 200.

[0034] The input / output unit 130 is a device composed of a keyboard, a mouse, a camera, a microphone, a liquid crystal display, an organic EL (Electro-Luminescence) display, etc., and is used for inputting and outputting various data.

[0035] The communication unit 140 is a device for the information processing apparatus 100 to communicate with other information terminals such as the administrative terminal 200 via the network 210. The above is the configuration of the information processing apparatus 100.

[0036] Subsequently, the operation of the information processing system 1 will be described with reference to FIGS. 4 to 8. In this example, the case of performing masking on the care certification review meeting materials shown in FIG. 4 will be described as an example. Specifically, in this embodiment, as shown in FIG. 4, a non-masking target area X, which is an area not subject to masking, and a masking target area Y, which is an area subject to masking, are preset. Note that the non-masking target area X and the masking target area Y can be arbitrarily changed by user settings, and the entire area may be set as the masking target area Y.

[0037] FIG. 5 is a flowchart showing an example of the processing of the information processing system 1. First, the processing of the administrative terminal is started by an operation on the administrative terminal 200 by the user. Specifically, the processing of the administrative terminal is started by performing an operation necessary to execute the masking process of the care certification review meeting materials on the administrative terminal 200.

[0038] When the processing of the administrative terminal is started, the administrative terminal 200 sends request information to request the information processing apparatus 100 to display a processing screen necessary for executing the masking process of the care certification review meeting materials, thereby making a processing procedure request (step S11). Specifically, in the processing of step S11, the administrative terminal 200 sends request information to the information processing apparatus 100 by, for example, an operation of starting an application for uploading the care certification review meeting materials.

[0039] On the side of the information processing apparatus 100, when request information is received, the processing of the information processing apparatus is started. When starting the processing of the information processing apparatus, the control unit 120 of the information processing apparatus 100 provides a processing screen for uploading the care certification review meeting materials to the administrative terminal 200 by transmitting the processing screen (step S12).

[0040] Subsequently, on the side of the administrative terminal 200, when the processing screen is received, the processing screen is displayed on the administrative terminal 200. Therefore, by uploading the care certification review meeting materials (step S13), a PDF file of the care certification review meeting materials is transmitted to the information processing apparatus 100.

[0041] On the side of the information processing apparatus 100, the control unit 120 receives a PDF file (electronic data) of the care certification review meeting materials by the function of the care certification review meeting materials acquisition and conversion unit 121, and converts the received PDF file of the care certification review meeting materials from image data to character data by performing OCR input (step S14). Note that the conversion of the character data in the process of step S14 may be performed by AIOCR or by an external functional unit via the network 210. Note that the care certification review meeting materials acquisition and conversion unit 121 that receives the PDF file of the care certification review meeting materials and this step respectively correspond to the care certification review meeting materials acquisition means and the care certification review meeting materials acquisition step.

[0042] After executing the process of step S14, the control unit 120 executes a classification determination process for determining the classification of the content described in the care certification review meeting materials converted into character data in the process of step S14 by the function of the classification determination unit 122 (step S15). FIG. 6 is a flowchart showing an example of the classification determination process executed in the process of step S15 of FIG. 5. Note that the classification determination unit 122 that executes the process of step S15 and step S15 respectively correspond to the classification determination means and the classification determination step.

[0043] When starting the classification determination process shown in FIG. 6, the control unit 120 specifies a target area, that is, a masking target area Y, which is the area to be classified, among the nursing care certification review materials converted into character data, by the function of the classification determination unit 122 (step S31). Specifically, in the process of step S31, the classification determination unit 122 specifies the masking target area Y in the nursing care certification review materials according to the preset settings.

[0044] After executing the process of step S31, the control unit 120 performs morphological analysis on the content (such as text) described in the masking target area Y by the function of the classification determination unit 122 (step S32). For example, taking the nursing care certification review materials shown in FIG. 4 as an example, in the process of step S32, the classification determination unit 122 performs morphological analysis on each of the two texts included in the masking target area Y of the certification investigation form and the two texts included in the masking target area Y of the attending physician's opinion form. For example, for the description "After entering Neostie Nanshan Yamada in H9 year and entering the current paid elderly home Best Life Yamada in July 2022" shown in FIG. 4, by executing the process of step S32, it is divided into respective morphemes such as "H9 year / / Neostie Nanshan Yamada / entering / / after / 2022 year / July / / current / paid elderly home / Best Life Yamada / / entering / / becomes / ".

[0045] After executing the process of step S32 shown in FIG. 6, the control unit 120 classifies the proper names of the character strings determined as "nouns" by morphological analysis in the process of step S32 based on the learning model 113 by the function of the classification determination unit 122 (step S33), and ends the classification determination process. Specifically, in the process of step S33, the classification determination unit 122 converts each of the morphemes segmented in the process of step S32 into a vector and determines the classification for each morpheme. More specifically, it classifies whether it is a term related to care certification (a proper name often used in care certification), and when it is a term related to care certification, it determines which classification it belongs to based on the learning model 113 respectively. For example, taking the certification survey form in the care certification review meeting materials shown in FIG. 4 as an example, after morphological analysis is performed in the process of step S32, the classification determination unit 122 performs classification by AI using the learning model 113 in the process of step S33, and terms such as "brain injury", "subarachnoid hemorrhage", "higher brain dysfunction", "Neo Sti Nanshanada", and "Home Best Life Yamada" are proper names often used in care certification, and it is determined that they belong to the classifications of "disease name", "disease name", "disease name", "facility name", and "facility name" respectively. Note that the proper names include personal information such as names of people and facilities, as well as age, gender, place names, and occupations.

[0046] Returning to FIG. 5, after executing the process of step S15, the control unit 120 executes masking by the function of the masking processing unit 124 (step S16). Specifically, in the process of step S16, the control unit 120 first determines, by the function of the masking target determination unit 123, whether each classification determined by the process of step S15 is a masking target, based on the masking setting information 112. And when it is a masking target, by the function of the masking processing unit 124, the specific expression belonging to the classification is converted into the masked character string set in the masking setting information 112, thereby performing masking. For example, taking the certification investigation form in the care certification review meeting materials shown in FIG. 4 as an example, in the process of step S16, the masking target determination unit 123 determines that masking is not performed for "brain injury", "subarachnoid hemorrhage", and "higher brain function disorder" belonging to the classification of "disease name" (see FIG. 3), and determines that masking is performed for "Neo Sti Nanshanada" and "Home Best Life Yamada" belonging to the classification of "facility name" (see FIG. 3). Then, "Neo Sti Nanshanada" and "Home Best Life Yamada" for which masking is determined are each converted into "facility name", which is the masked character string in the masking setting information 112 shown in FIG. 3, by the function of the masking processing unit 124, thereby performing masking. By executing the process of step S16 in this way, the masking target in the care certification review meeting materials shown in FIG. 4 is masked as shown in FIG. 7. FIG. 7 shows an example of the care certification review meeting materials after masking. Note that, as shown in the figure, when it is converted into the masked character string by the function of the masking processing unit 124, the converted character string may be displayed in a prominent manner so that it is easy for the user to visually recognize. Note that the masking processing unit 124 that executes the process of determining whether each classification is a masking target in the process of step S16 and step S16 respectively correspond to the masking target determination means and the masking target determination step, and the masking processing unit 124 that executes masking in the process of step S16 and step S16 respectively correspond to the masking processing means and the masking processing step.

[0047] After executing the process of step S16 shown in FIG. 5, the control unit 120 notifies the administrative terminal 200 of the completion of masking by transmitting a completion notice indicating that the masking has been completed to the administrative terminal 200 by the function of the masking processing unit 124 (step S17).

[0048] On the side of the administrative terminal 200, upon receiving the completion notice, a confirmation / correction request for requesting a confirmation / correction screen, which is a screen for the user to confirm and correct the post-masking long-term care certification review meeting materials by an input operation, is transmitted to the information processing apparatus 100 (step S18).

[0049] On the side of the information processing apparatus 100, when receiving a confirmation and correction screen request, the control unit 120 provides the confirmation and correction screen to the administrative terminal 200 by transmitting, to the administrative terminal 200, a confirmation and correction screen which is a screen for confirming and correcting the care certification review meeting materials after masking, by means of the function of the correction confirmation output processing unit 125 (step S19). Specifically, in the process of step S19, as shown in FIG. 8, the correction confirmation output processing unit 125 provides the administrative terminal 200 with a confirmation and correction screen that displays the care certification review meeting materials before masking and the care certification review meeting materials after masking side by side. As a result, on the side of the administrative terminal 200, the care certification review meeting materials before and after masking are displayed in parallel as shown in FIG. 8. Note that FIG. 8 is an explanatory diagram showing an example of the confirmation and correction screen, and shows an example in which the care certification review meeting materials before masking shown in FIG. 4 and the care certification review meeting materials after masking shown in FIG. 7 are displayed in parallel. In this way, by displaying the care certification review meeting materials before and after masking in parallel, it becomes easier for the user to confirm the legitimacy of the masking and to perform corrections easily. Note that the correction confirmation output processing unit 125 that executes the process of step S19 and step S19 respectively correspond to an output means and an output step. Also, in this embodiment, an example is shown in which, based on receiving a confirmation and correction request for requesting a confirmation and correction screen, a confirmation and correction screen which is a screen for confirming and correcting the care certification review meeting materials after masking is transmitted to the administrative terminal 200, but it may be transmitted regardless of the confirmation and correction request. For example, the confirmation and correction screen may be transmitted to the administrative terminal 200 in the process of step S17.

[0050] After the process of step S19 shown in FIG. 5 is executed and the materials of the care certification review meeting before and after masking are displayed on the administrative terminal 200, if it is necessary to correct the materials of the care certification review meeting after masking, that is, if it is determined that correction is necessary by visual inspection by the user, an input operation is performed by the user and correction is instructed (step S20). Specifically, in the process of step S20, the correction content for the materials of the care certification review meeting after masking is input by the input operation of the user, and the content is transmitted to the information processing apparatus 100 as a correction instruction. If there is no correction, the process of step S20 may be skipped.

[0051] When the process of step S20 is executed and a correction instruction is transmitted, on the side of the information processing apparatus 100, the control unit 120 executes the correction of the materials of the care certification review meeting after masking according to the correction content indicated by the correction instruction by the function of the correction confirmation output processing unit 125 (step S21). Then, when the correction is made by the process of step S21, the correction content is reflected, and the correction result is displayed on the administrative terminal 200 side. The correction result is displayed in a state where the correction is reflected for the materials of the care certification review meeting after masking in FIG. 8. Note that the corrected part may be displayed in a conspicuous manner. In this case, it may be a manner different from the manner of the character string masked by the process of step S16 and is a manner that is displayed only when correction is made. When the user of the administrative terminal 200 determines that the correction content is acceptable, the "Save Correction" button shown in FIG. 8 is pressed, and the correction is reflected.

[0052] After the correction is executed in the process of step S21 shown in FIG. 5, or when there is no part to be corrected and the process of step S20 is skipped, the user of the administrative terminal 200 instructs the result output (step S22). Specifically, in the process of step S22, the result output is instructed by performing an input operation for downloading the masked long-term care certification review meeting materials by the user. For example, when the "Download" button shown in FIG. 8 is pressed, the result output is instructed, and an output request is transmitted from the administrative terminal 200 to the information processing apparatus 100.

[0053] When the information processing apparatus 100 receives the output request, the control unit 120 outputs the PDF file of the masked long-term care certification review meeting materials as a processing result by the function of the correction confirmation output processing unit 125 (step S23), and ends the processing of the information processing apparatus. In the process of step S23, the correction confirmation output processing unit 125 converts the masked long-term care certification review meeting materials from character data to image data, and provides it to the administrative terminal 200 as a PDF file, thereby transmitting the PDF file as a processing result.

[0054] On the side of the administrative terminal 200, by receiving the PDF file of the masked long-term care certification review meeting materials transmitted from the information processing apparatus 100, the processing result is acquired (step S24), and the processing of the administrative terminal is ended.

[0055] Thereby, on the side of the administrative terminal 200, it is possible to obtain the masked long-term care certification review meeting materials for the long-term care certification review meeting materials necessary for long-term care certification. The above is the operation of the information processing system 1. As described above, according to the information processing apparatus in this embodiment, it is possible to leave the information necessary for the long-term care insurance certification business as it is and mask only the personal information, so that it is possible to appropriately protect the personal information while realizing the smooth execution of the long-term care insurance certification business. Therefore, the long-term care insurance certification business can be preferably supported.

[0056] (Modification example) Note that the present invention is not limited to the above-described embodiments, and various modifications and applications are possible. For example, the information processing apparatus 100 according to the above-described embodiment does not necessarily have all the technical features shown above, and may have some of the configurations described in the above-described embodiment so as to solve at least one problem in the prior art. Also, at least a part of each of the following modification examples may be combined with each other.

[0057] In the above-described embodiment, when masking is performed in the process of step S16 shown in FIG. 5, an example in which the masked state is displayed in a conspicuous manner so that it can be easily visually recognized by the user is shown, but this is just an example. For example, the display mode of the masked character string may be made different according to the confidence level of the classification by AI, that is, the confidence level of the classification determination in the process of step S15 shown in FIG. 5. Specifically, as shown in FIG. 9, when the confidence level of the classification determination is 70% or more, the masked character string may be displayed according to mode 1, and when it is less than 70%, the masked character string may be displayed according to mode 2, etc., and a display mode corresponding to the confidence level may be set in advance. Note that the set value of the confidence level may be arbitrarily changed by the user.

[0058] In this case, for example, when masking the materials of the care certification review committee shown in FIG. 4, in the process of step S15 in FIG. 5, although it was determined that "Neo Sti Nanshan Yamada" and "Home Best Life Yamada" belong to the classification of "facility name" with a confidence level of 70% or more, it is assumed that "Nanshan Yamada Hospital" was determined to belong to the classification of "medical institution name" with a confidence level of less than 70%. Then, based on the setting in FIG. 9, by executing the process of step S16 in FIG. 5, as shown in FIG. 10, for the parts corresponding to "Neo Sti Nanshan Yamada" and "Home Best Life Yamada", "facility name" is displayed in the display mode of mode 1 as the masked character string, while for the part corresponding to "Nanshan Yamada Hospital", "medical institution name" is displayed in the display mode of mode 2 as the masked character string. In this example, for "Nanshan Yamada Hospital", although the confidence level is less than 70%, it is ultimately the correct masking. However, for example, if it is determined in the process of step S15 in FIG. 5 that it belongs to the classification of "person's name" instead of "medical institution name", the part corresponding to "Nanshan Yamada Hospital" will have "person's name" displayed in the display mode of mode 2 as the masked character string. In such a case, an instruction to correct it to "medical institution name" is given in the process of step S20 in FIG. 5. Such a correction history may be used as the supervised data of the learning model 113 and may be learned again.

[0059] Also, the display modes according to the confidence level of the AI are not limited to two modes. For example, in addition to the above, there may be multiple modes such as mode 3 with a confidence level of less than 50%. In such a case, the masked character string corresponding to the classification with a lower confidence level may be displayed in a mode that is easier for the user to visually recognize. According to this, it becomes easier for the user to recognize the error in the classification determination by the AI, and the efficiency of the work can be improved. Similarly, in the case where the display mode is two modes, the display mode with a lower confidence level may be made more prominent than the display mode with a higher confidence level.

[0060] In addition, in the above-described embodiment, an example was shown in which masking was performed by changing the word determined to be masked to the "string after masking" set in the masking setting information 112, but this is just an example. In addition to this, when a specific string is included, it may be changed to a pre-set string. Specifically, the specific string setting information shown in FIG. 11 is set in advance. When a word determined to be masked contains the specific string shown in the figure, the string after masking may be a special string. For example, as shown in FIG. 11, when the string "Neostie Nanshanada" is included, normally, it is masked to "facility name" based on the setting of the masking setting information 112 shown in FIG. 3, but by setting the specific string setting information as shown in FIG. 11, it can be masked to "adjacent facility" (see FIG. 12). According to this, it becomes possible to convert the string to be masked to a special string only when a specific string is included, and the convenience can be improved.

[0061] In addition, in the above-described embodiment, as shown in FIG. 8, an example was shown in which the nursing care certification review meeting materials before masking and the nursing care certification review meeting materials after masking were displayed side by side. For example, when there is no masking target, as the nursing care certification review meeting materials after masking, the image data before conversion to character data may be displayed as it is. According to this, it is possible to prevent character distortion due to conversion to character data. Further, when the nursing care certification review meeting materials are configured over a plurality of pages, if there is no masking target on the page, by pressing the page transition button for page transition to the content of the next page, the page may be transitioned to the next page. According to this, the workload of the confirmation and correction work can be reduced.

[0062] In addition, in the above-described embodiment, an example of performing parallel display correction on the care certification review meeting materials before masking and the care certification review meeting materials after masking was shown, but this is just one example. In addition to this, for example, as shown in FIG. 12, when correcting the text after masking, correction candidates may be displayed by selecting the text after masking to be corrected. The user may select the desired correction content from the correction candidates. According to this, it becomes possible to easily perform the correction work.

[0063] Note that the information processing apparatus 100 according to the above-described embodiment can be realized not by a dedicated apparatus but by using a normal computer. For example, an information processing apparatus 100 that executes the above-described processing may be configured by installing the program for executing any of the above in a computer from a recording medium storing the program. Also, one information processing apparatus 100 may be configured by a plurality of computers operating in cooperation.

[0064] Also, in the case where the above-described functions are realized by sharing between the OS (Operating System) and the application or by cooperation between the OS and the application, only the part other than the OS may be stored in the medium.

[0065] Also, it is possible to superimpose the program on a carrier wave and distribute it via a communication network. For example, the program may be posted on a bulletin board (BBS, Bulletin Board System) on the communication network, and the program may be distributed via the network. Then, these programs may be started and configured to be able to execute the above-described processing by executing them in the same manner as other application programs under the control of the operating system.

Explanation of Signs

[0066] 1 Information processing system 100, information processing apparatus, 110 storage unit, 111 program, 112 masking setting information, 113 learning model, 120 control unit, 121 nursing certification review meeting material acquisition and conversion unit, 122 classification determination unit, 123 masking target determination unit, 124 masking processing unit, 125 correction confirmation output processing unit, 130 input / output unit, 140 communication unit, 210 network, 200 administrative terminal

Claims

1. A means for acquiring electronic data of nursing care certification examination committee materials, which are examination documents in nursing care insurance certification work, from an administrative terminal; A classification determination means for classifying named entities contained in a sentence described in the nursing care certification examination committee material acquired by the nursing care certification examination committee material acquisition means; a masking target determination means for determining whether or not the classification of the named entity determined by the classification determination means is a classification to be masked based on pre-stored masking setting information; a masking processing means for masking the named entity in accordance with preset content based on a result of the determination by the masking target determination means; an output means for providing the nursing care certification examination committee materials after the masking process is performed by the masking processing means to the administrative terminal; An information processing device comprising:

2. The masking processing means performs masking by converting the named entity into a content specified by the masking setting information.

2. The information processing apparatus according to claim 1,

3. the masking processing means sets a display mode of the named entity after the masking to a specific display mode that is different from a display mode of the named entity that is not subjected to the masking, 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. The classification determination means performs a morphological analysis of the sentences described in the nursing care certification examination committee materials and classifies the named entities using a learning model that has been machine-learned in advance by supervised learning; the masking processing means changes a display mode of the named entity after the masking process depending on a reliability of classification of the named entity using the learning model in the classification determination means, 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

5. the masking processing means performs masking by converting the named entity including a predetermined specific character string into a special character string different from the content specified by the masking setting information, when the named entity includes a predetermined specific character string; 2. The information processing apparatus according to claim 1,

6. An information processing method by an information processing device including a nursing care certification examination committee material acquisition means, a classification determination means, a masking target determination means, a masking processing means, and an output means, A nursing care certification examination committee material acquisition step in which the nursing care certification examination committee material acquisition means acquires electronic data of nursing care certification examination committee materials, which are examination documents in nursing care insurance certification work, from an administrative terminal; A classification determination step in which the classification determination means classifies named entities contained in the sentences described in the nursing care certification examination committee materials acquired in the nursing care certification examination committee material acquisition step; a masking target determination step in which the masking target determination means determines whether or not the classification of the named entity determined in the classification determination step is a classification of a masking target based on masking setting information stored in advance; a masking processing step in which the masking processing means masks the named entity in accordance with preset content based on a result of the determination in the masking target determination step; An output step in which the output means provides the nursing care certification examination committee materials after the masking process step is performed to the administrative terminal; An information processing method comprising:

7. Computer, A means for acquiring nursing care certification examination committee materials from an administrative terminal, the electronic data of nursing care certification examination committee materials being examination documents in nursing care insurance certification operations; A classification determination means for classifying named entities contained in a sentence described in the nursing care certification examination committee material acquired by the nursing care certification examination committee material acquisition means; a masking target determination means for determining whether or not the classification of the named entity determined by the classification determination means is a classification to be masked based on pre-stored masking setting information; a masking processing means for masking the named entity in accordance with preset content based on a result of the determination by the masking target determination means; An output means for providing the nursing care certification examination committee materials after the masking process is performed by the masking processing means to the administrative terminal; A program that functions as a

Images