Information processing device, information processing method, program

Abstract

To provide an information processing system, an information processing device, an information processing method, and a program that can more efficiently and highly accurately determine a document that contains personal information.SOLUTION: A method for determining whether processing-target text data contains personal information using a learned model that has been learned with data in which text data is associated with information indicating that personal information is contained in the text data, includes the steps of: acquiring the text data; and determining whether the acquired text data contains personal information using a learned model that has been learned with data in which text data is associated with information indicating that personal information is contained in the text data.SELECTED DRAWING: None

Description

Technical Field

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

Background Art

[0002] With the expansion of the scope of application due to the amendment of the Personal Information Protection Act, the risk of information leakage in businesses has increased, and the importance of measures to prevent personal information leakage has been growing.

[0003] When handling personal information, it is necessary to take measures necessary for the safe management of personal data. However, since electronically stored personal data can be easily replicated, it is easy to fall into a difficult-to-manage state, such as when files replicated during work on an individual's terminal are left unmanaged after the work.

[0004] Furthermore, when transmitting data externally by email or the like, it is necessary to confirm not only for mistransmission but also whether a file containing personal information has been inadvertently attached.

[0005] However, in an organization, it requires an enormous cost to check all the files stored on the terminals managed by each individual or to open and check the files attached to emails each time.

[0006] While suppressing an enormous working cost, a technology that can accurately determine files containing personal information is desired in order to appropriately manage personal information in an organization.

[0007] Patent Document 1 describes a technique for detecting personal information formation information that can form personal information, specifying personal information from the positional relationship of the detected personal information formation information, measuring the number of characters or items of the personal information, and showing it as an index value indicating the degree of inclusion of personal information from the measured value.

Prior Art Documents

Patent Documents

[0008] [Patent Document 1] Japanese Patent Publication No. 2008-117287 [Disclosure of the Invention] [Problems that the invention aims to solve]

[0009] However, in Patent Document 1, the formula for calculating the index value indicating the degree to which personal information is included must be adjusted manually, making it time-consuming to calculate an appropriate index value.

[0010] Therefore, the present invention aims to provide a mechanism that can more efficiently and accurately identify documents containing personal information. [Means for solving the problem]

[0011] The information processing system of the present invention is characterized by comprising: an acquisition means for acquiring text data; and a determination means for determining whether the text data acquired by the acquisition means contains personal information, using a trained model that has been trained on data that associates the text data with information indicating that the text data contains personal information. [Effects of the Invention]

[0012] According to the present invention, it becomes possible to determine whether a document contains personal information more efficiently and with higher accuracy. [Brief explanation of the drawing]

[0013] [Figure 1] This figure shows an example of a system configuration for a webmail service using a personal information inspection device in an embodiment of the present invention. [Figure 2] This is a block diagram showing an example of the hardware configuration of a personal information inspection device, a webmail service, an administrator terminal, and a client terminal in an embodiment of the present invention. [Figure 3] This figure shows an example of the functional configuration of a personal information inspection device and a webmail service in an embodiment of the present invention. [Figure 4] A flowchart showing an example of a process for learning personal information in an embodiment of the present invention. [Figure 5] A diagram showing an example of the configuration of a determination knowledge storage area in an embodiment of the present invention. [Figure 6] A flowchart showing an example of a process for generating a feature vector for a document in an embodiment of the present invention. [Figure 7] A diagram showing an example of learning data in an embodiment of the present invention. [Figure 8] A diagram showing an example of personal information formation information obtained from a document in an embodiment of the present invention. [Figure 9] A diagram showing an example of a feature vector in an embodiment of the present invention. [Figure 10] A diagram showing an example of a feature quantity storage table in an embodiment of the present invention. [Figure 11] A diagram showing an example of a machine learning model obtained as a result of learning in an embodiment of the present invention. [Figure 12] A flowchart showing an example of a personal information index calculation process in an embodiment of the present invention. [Figure 13] A diagram showing an example of a personal information index calculation formula in an embodiment of the present invention. [Figure 14] A diagram showing an example of the process of calculating a predicted value in an embodiment of the present invention. [Figure 15] A flowchart showing an example of an inspection process for an email in a Web mail service in an embodiment of the present invention. [Figure 16] A diagram showing an example of a mail editing screen in a Web mail service in an embodiment of the present invention. [Figure 17] A diagram showing an example of a transmission confirmation screen in a Web mail service in an embodiment of the present invention.

Embodiments for Carrying Out the Invention

[0014] Embodiments of the present invention will be described in detail below with reference to the drawings.

[0015] Figure 1 shows an example of a system configuration for a webmail service using a personal information inspection device according to an embodiment of the present invention.

[0016] The personal information inspection device 100, the webmail service 110, and the administrator terminal 120 are connected via a local area network 130. The webmail service 110 is also configured to connect to a client 150 via an external network 140.

[0017] The webmail service 110 provides the client terminal 150 with the functions of a typical email client, namely, email editing and email sending / receiving functions.

[0018] Furthermore, when a user instructs the Webmail service 110 on the client terminal 150 to send an email or to explicitly check for personal information, the Webmail service 110 requests the personal information checking device 100 to perform a process to determine whether or not personal information is present.

[0019] If the personal information inspection device 100 determines that the email to be sent may contain personal information, the Webmail service 110 displays a message to the user prompting them to confirm whether or not personal information is present and to decide whether or not to send the email, and controls the sending based on the user's decision on whether or not to send the email.

[0020] In embodiments of the present invention, the personal information inspection device 100 may be configured as a service provided to the client terminal 150 via an external network 140, or as part of the functions of a webmail service 110.

[0021] Alternatively, it may be configured as a function of an email client program running on the client terminal 150.

[0022] Figure 2 is a block diagram showing an example of the hardware configuration of a personal information inspection device 100, a webmail service 110, an administrator terminal 120, and a client terminal 150 in an embodiment of the present invention.

[0023] As shown in Figure 2, the information processing device is connected via a system bus 200 to a CPU (Central Processing Unit) 201, ROM (Read Only Memory) 202, RAM (Random Access Memory) 203, storage device 204, input controller 205, audio controller 206, video controller 207, memory controller 208, and communication I / F controller 209.

[0024] CPU201 provides comprehensive control over all devices and controllers connected to system bus 200.

[0025] ROM202 or external memory213 holds the BIOS (Basic Input / Output System) and OS (Operating System), which are control programs executed by the CPU201, as well as computer-readable and executable programs and various necessary data (including data tables) for realizing this information processing method.

[0026] RAM203 functions as the main memory, work area, etc., of the CPU201. The CPU201 loads the necessary programs, etc., from ROM202 or external memory 213 into RAM203, and then executes the loaded programs to perform various operations.

[0027] The input controller 205 controls input from input devices such as a keyboard 210 or a pointing device such as a mouse (not shown). If the input device is a touch panel, the user can give various instructions by pressing (touching with a finger, etc.) icons, cursors, or buttons displayed on the touch panel.

[0028] Furthermore, the touch panel may be a multi-touch screen or other touch panel capable of detecting the positions of multiple fingers touching it.

[0029] The video controller 207 controls the display to an external output device such as the display 212. The display may include the display of a notebook computer integrated with the main unit. The external output device is not limited to a display; for example, it may be a projector. Furthermore, for the aforementioned touch-enabled device, an input device is also provided.

[0030] The video controller 207 can control the video memory (VRAM) used for display control. It can utilize a portion of the RAM 203 as the video memory area, or it can provide a separate, dedicated video memory.

[0031] The memory controller 208 controls access to the external memory 213. The external memory can include an external storage device (hard disk), a flexible disk (FD), or a CompactFlash® memory connected to a PCMCIA card slot via an adapter, which stores boot programs, various applications, font data, user files, editing files, and other data.

[0032] The communication interface controller 209 connects to and communicates with external devices via a network and performs communication control processing over the network. For example, it can handle communication using TCP / IP, telephone lines such as ISDN, and mobile phone 4G and 5G lines.

[0033] Furthermore, the CPU 201 enables display on the display 212 by, for example, performing the process of expanding (rasterizing) outline fonts into the display information area in RAM 203. The CPU 201 also enables user input via a mouse cursor (not shown) on the display 212.

[0034] Figure 3 shows an example of the functional configuration of a personal information inspection device and a webmail service.

[0035] The email editing processing unit 311 has the function of creating and editing emails based on user operations and instructions received via the screen displayed on the web browser 320 of the client terminal 150.

[0036] When the transmission control processing unit 312 receives an email transmission instruction from the user, it extracts text (body, attachments, etc.) from the email and controls the personal information index calculation process performed by each processing unit of the personal information inspection device 100. It also has a function to control the email transmission process by displaying a confirmation dialog as shown in Figure 17 or by receiving confirmation from the user whether or not to send the email, based on the results of the personal information index calculation process.

[0037] The transmission processing unit 313 has the function of sending emails that have been decided to be sent by the transmission control processing unit 312 to the external network 140.

[0038] The personal information learning processing unit 301 has the function of performing personal information learning processing as shown in the flowchart of Figure 4, based on the information uploaded from the administrator terminal 120.

[0039] The feature vector generation processing unit 302 has the function of generating feature vectors for the document to be processed.

[0040] The judgment knowledge storage area 303 is an area that stores pairs of feature vectors generated in the feature vector generation processing unit 302 and labels indicating personal information and non-personal information that are assigned to each document in the training data.

[0041] The personal information inspection processing unit 304 has a function to perform a process to calculate the likelihood that the text content shown in Figure 12 is personal information, based on the text obtained from the transmission control processing unit 312.

[0042] (Personal information learning and processing) Next, using the flowchart in Figure 4, the personal information learning process performed by the personal information learning processing unit 301 in the embodiment of the present invention will be explained. Figure 4 is a flowchart showing the process by which the CPU 201 of the personal information inspection device 100 reads and executes a predetermined control program, and learns the characteristics of personal information based on pre-classified documents of personal and non-personal information uploaded from the administrator terminal 120.

[0043] In step S401, the personal information learning processing unit 301 acquires documents uploaded from the web browser 330 on the administrator terminal 130 as learning data.

[0044] In step S402, the personal information learning processing unit 301 starts the iterative processing up to step S405 for the documents in the learning data acquired in step S401.

[0045] In step S403, the personal information learning processing unit 301 generates feature vectors for the document to be processed using the feature vector generation processing unit 302. The method for generating feature vectors will be described later.

[0046] In step S404, the personal information learning processing unit 301 stores the pair of feature vectors generated in step S403 and labels indicating personal information and non-personal information assigned to each document in the learning data in the feature vector storage table 501 in the judgment knowledge storage area 303 shown in Figure 5.

[0047] In step S405, the personal information learning processing unit 301 repeats the process from step S402 if there are still documents to be processed. If there are no documents to be processed, the process moves to step S406.

[0048] In step S406, the personal information learning processing unit 301 uses machine learning to learn from the feature vectors and labels (personal information / non-personal information) in the feature vector storage table 501, and obtains a model (trained model) as a result of the learning.

[0049] In step S407, the personal information learning processing unit 301 saves the model acquired in step S406 to the model storage table 502 in the judgment knowledge storage area 303.

[0050] In the embodiments of the present invention, the personal information learning process is configured to run on the same hardware as the personal information inspection process, but it may also be configured to run on different hardware. Furthermore, while it is configured to upload training data, it may also be configured to manage personal information on hardware that performs training processing.

[0051] (Feature vector generation process) Next, the feature vector generation process performed by the feature vector generation processing unit 302 in the embodiment of the present invention will be explained using the flowchart in Figure 6.

[0052] In step S601, the feature vector generation processing unit 302 extracts personal information formation information, along with its occurrence position and character count, from the text of the document received as input, using morphological analysis and pattern matching, based on words and patterns that have been previously defined as personal information items and sensitive information items.

[0053] In step S602, the feature vector generation processing unit 302 obtains statistical values ​​based on type and character count from the document and extracted personal information formation information.

[0054] In step S603, the feature vector generation processing unit 302 combines the statistical values ​​obtained in step S602 into a feature vector.

[0055] (Specific examples of personal information learning and processing) Next, as a concrete example of personal information learning processing, we will explain the case where the processing shown in Figure 4 is performed on the learning data 700 shown in Figure 7.

[0056] In step S401, the personal information learning processing unit 301 acquires the document 700 uploaded from the web browser 330 on the administrator terminal 130 as learning data.

[0057] In step S402, the personal information learning processing unit 301 starts the iterative processing up to step S405 for the document 701 in the learning data 700 acquired in step S401.

[0058] In step S403, the personal information learning processing unit 301 generates feature vectors for the document 701 to be processed using the feature vector generation processing unit 302.

[0059] In step S601, the feature vector generation processing unit 302 extracts personal information forming information 801, as shown in Figure 8, from the text of the document 701 received as input, using morphological analysis and pattern matching, based on words and patterns that have been previously defined as personal information items and sensitive information items, along with their occurrence positions and character counts.

[0060] In step S602, the feature vector generation processing unit 302 obtains statistical values ​​from the document and the extracted personal information formation information 801 based on the type and number of characters shown in Figure 9.

[0061] In step S603, the feature vector generation processing unit 302 combines the statistical values ​​obtained in step S602 into a feature vector 901. In this embodiment of the present invention, normalization and other processes are omitted for the sake of clarity, but the system may be configured to perform normalization.

[0062] In step S404, the personal information learning processing unit 301 saves the feature vector 901 generated in step S403 and the set of labels TRUE indicating personal information / non-personal information, which are assigned to each document in the learning data, to the feature vector storage table 501 shown in Figure 10.

[0063] In step S405, the personal information learning processing unit 301 repeats the process from step S402 because there are still documents 702 to be processed.

[0064] The same steps are then performed for all 700 documents in the training data.

[0065] In step S406, the personal information learning processing unit 301 performs machine learning on the feature vector storage table 501 to acquire a model.

[0066] In the embodiments of the present invention, a linear SVM (Support Vector Machine) is used.

[0067] In step S407, the personal information learning processing unit 301 stores the model shown in Figure 11, which was acquired as a learning result, in the model storage table 502 in the judgment knowledge storage area 303. The acquired model determines that personal information is present if the predicted value (calculation result) is a positive value.

[0068] In the embodiments of the present invention, a linear SVM was used as the machine learning method for the sake of ease of explanation, but any method can be used as long as it can classify data into two binary categories (true or false) and the degree of this classification can be expressed numerically.

[0069] (Personal information inspection and processing) Next, using the flowchart in Figure 12, the personal information inspection process performed by the personal information inspection processing unit 304 in the embodiment of the present invention will be explained.

[0070] The flowchart in Figure 12 shows the process by which the CPU 201 of the personal information inspection device 100 reads and executes a predetermined control program, and calculates a numerical value indicating the degree to which the content of the input text is likely to be personal information.

[0071] In step S1201, the personal information inspection processing unit 304 obtains the text of the document to be processed.

[0072] In step S1202, the personal information inspection processing unit 304 obtains feature vectors for the input document using the flowchart in Figure 6 described above, based on the text acquired in step S1201.

[0073] In step S1203, the personal information inspection processing unit 304 calculates a predicted value for the feature vector obtained in step S1202 using the model stored in the model storage table 502 in the judgment knowledge storage area 303.

[0074] In step S1204, the personal information inspection processing unit 304 converts the predicted value calculated in step S1203 into a value that is easy to grasp intuitively, and outputs it as a personal information index. In the embodiment of the present invention, the personal information index calculation formula shown in Figure 13 is used, but other calculation formulas may be used, or the predicted value may be used as is.

[0075] (Specific examples of personal information inspection and processing) Next, as a concrete example of personal information inspection processing, we will explain the case where the processing shown in Figure 12 is performed on the inspection target document 1401 shown in Figure 14.

[0076] In step S1201, the personal information inspection processing unit 304 retrieves text 1402 from the document 1401 to be processed.

[0077] In step S1202, the personal information inspection processing unit 304 obtains a feature vector 1403 for the input document using the flowchart in Figure 6 described above, based on the text obtained in step S1201.

[0078] In step S1203, the personal information inspection processing unit 304 calculates a predicted value of 1460.960 (1404) using the model stored in the model storage table 502 in the judgment knowledge storage area 303, based on the feature vector 1403 obtained in step S1202.

[0079] In step S1204, the personal information inspection processing unit 304 calculates the personal information index using the personal information index calculation formula shown in Figure 13, based on the predicted value of 1460.960 calculated in step S1203. Here, it is assumed that Rmin = -1700 and Rmax = 2000. As a result, we obtain 50 + 50 × 1460.960 ÷ max(2000, -(-1700)) = 86.524 as the personal information index.

[0080] In this way, by simply preparing a set of documents that have been determined to contain or not contain personal information, it becomes possible to calculate a personal information index, which indicates the likelihood that a document contains personal information, without the need for manual adjustments. Furthermore, since the personal information index is calculated based on statistical information, even if there are some errors in the extraction of information that forms personal information, it can still indicate with high accuracy the certainty that the information is personal information. By using the calculated personal information index, it becomes possible to process information according to its accuracy, enabling efficient management of personal information.

[0081] Next, using the flowchart shown in Figure 15, we will explain a specific application example of the present invention: a case in which the transmission of personal information is confirmed when sending an email, and feedback is obtained from the user. In this embodiment, we will explain the application using email transmission as an example, but there are other application examples, such as determining whether a document contains personal information when printing it, or determining whether a document contains personal information when uploading it to a web service.

[0082] Figure 15 is a flowchart showing the process by which the CPU 201 of the Webmail service 110 reads and executes a predetermined control program, and which is performed when a send command is issued by pressing the send button 1602 on the email editing screen 1601 displayed on the Web browser 320 of the client terminal 150, as shown in Figure 16.

[0083] In step S1501, the transmission control processing unit 312 receives an instruction to send an email.

[0084] In step S1502, the transmission control processing unit 312 starts the iterative processing up to step S1509 for the files attached to the email that has been instructed to be sent. Note that the email body and other parts may also be targeted, not just the attached files.

[0085] In step S1503, the transmission control processing unit 312 extracts text from the attached file to be processed. If the attached file is an image, the text is obtained by performing OCR processing on the image.

[0086] In step S1504, the transmission control processing unit 312 calculates a personal information index using the personal information inspection device 100 for the text extracted in step S1503.

[0087] In step S1505, the transmission control processing unit 312 moves the process to step S1506 if the personal information index calculated in step S1504 is equal to or greater than a predetermined value. If it is less than a predetermined value, the process moves to step S1509.

[0088] In step S1506, the transmission control processing unit 312 displays the confirmation dialog shown in Figure 17 to obtain the user's consent to transmit the data and to determine whether or not the data contains personal information.

[0089] In step S1507, the transmission control processing unit 312 sends the user's determination of whether or not the data obtained in step S1505 is personal information to the personal information inspection device 100 and instructs the device 100 to save it in the feature vector storage table 501 along with the feature vector being processed.

[0090] In step S1508, if the transmission permission status obtained in step S1505 is "transmit", the transmission control processing unit 312 proceeds to step S1509. If the transmission permission status is "cancel", the processing ends.

[0091] In step S1509, the transmission control processing unit 312 repeats the process from step S1502 if there are still attachments to be processed. If there are no more attachments to be processed, the process moves to step S1510.

[0092] In step S1510, the transmission control processing unit 312 sends the email to the transmission processing unit 313 and sends the email.

[0093] In this way, by collecting user judgments on whether or not something is personal information, the personal information inspection device 100 can periodically perform learning processes, enabling the calculation of a personal information index that matches the user's judgment without requiring manual adjustments.

[0094] In the embodiment of the present invention, the system is configured to learn from all saved feature vectors. However, when saving feature vectors, information identifying the user's department or the user themselves may be added, and the system may be configured to perform learning for each department or user. Then, for documents related to the user or the user's department, the model generated by this learning may be used to determine whether or not they contain personal information.

[0095] The present invention can take the form of, for example, a system, apparatus, method, program, or recording medium. Specifically, it may be applied to a system consisting of multiple devices, or to an apparatus consisting of a single device.

[0096] Furthermore, the program in this invention is a program that a computer can execute using the processing methods shown in the flowcharts in Figures 4 and 12, and the storage medium of this invention stores the program that a computer can execute using the processing methods in Figures 4 and 12. Note that the program in this invention may also be a separate program for each processing method of each device in Figures 4 and 12.

[0097] As described above, it goes without saying that the object of the present invention can also be achieved by supplying a recording medium containing a program that realizes the functions of the embodiments described above to a system or device, and by having the computer (or CPU or MPU) of that system or device read and execute the program stored on the recording medium.

[0098] In this case, the program read from the recording medium itself realizes the novel function of the present invention, and the recording medium on which that program is recorded constitutes the present invention.

[0099] For recording media used to supply programs, examples include flexible disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, CD-Rs, DVD-ROMs, magnetic tapes, non-volatile memory cards, ROMs, EEPROMs, silicon disks, and the like.

[0100] Furthermore, it goes without saying that the functions of the aforementioned embodiments are realized not only by the computer executing the program it has read, but also by the operating system (OS) running on the computer performing some or all of the actual processing based on the instructions of that program, thereby realizing the functions of the aforementioned embodiments.

[0101] Furthermore, it goes without saying that this also includes cases where, after a program read from a recording medium is written to the memory of a function expansion board inserted into a computer or a function expansion unit connected to a computer, the CPU or other components of the function expansion board or function expansion unit perform some or all of the actual processing based on the instructions of the program code, and the functions of the aforementioned embodiments are realized through that processing.

[0102] Furthermore, the present invention may be applied to a system consisting of multiple devices or to a device consisting of a single device. It goes without saying that the present invention can also be applied when the results are achieved by supplying a program to a system or device. In this case, by reading a recording medium containing a program for achieving the present invention into the system or device, the system or device can enjoy the effects of the present invention.

[0103] Furthermore, by downloading and reading the program for achieving the present invention from a server, database, etc. on a network using a communication program, the system or device can enjoy the effects of the present invention. It should be noted that configurations combining the above-described embodiments and their variations are all included in the present invention. [Explanation of symbols]

[0104] 100 Personal Information Inspection Devices 110 Webmail Service 120 Administrator terminals 130 LAN 140 External Network 150 client terminals

Claims

1. A means for acquiring text data that has received a transmission instruction, An output means that outputs information relating to the results of inference processing by a trained model on the acquired text data, a selection receiving unit that accepts a selection of whether the text data contains personal information, and an instruction receiving unit independent of the selection receiving unit that accepts an instruction of whether or not to transmit the text data. A selection operation receiving means that receives a selection operation from the user to the selection receiving unit to determine whether the text data for which the transmission instruction was received contains personal information, A control means that controls the training of the trained model using the selection based on the selection operation received by the selection operation receiving means and the text data, An instruction receiving means that receives an instruction on whether or not to send the text data acquired by the acquisition means, which has output information relating to the results of the inference process, to the recipient. Equipped with, The information processing system is characterized in that the control means controls the learning of the trained model based on the selection in the selection receiving unit, regardless of whether or not to transmit data based on the instruction received by the instruction receiving means.

2. Transmission control means that controls the transmission of text data based on the instructions received by the instruction receiving means. The information processing system according to claim 1, further comprising the features described above.

3. The information processing system according to claim 1 or 2, characterized in that the information relating to the result of the inference process is information relating to the possibility that the text data contains personal information.

4. The information processing system according to any one of claims 1 to 3, characterized in that the information relating to the results of the inference process includes information indicating text data that has been determined to potentially contain personal information.

5. The information processing system according to any one of claims 1 to 4, characterized in that the information relating to the result of the inference process is a result based on a personal information index relating to the text data.

6. The information processing system according to any one of claims 1 to 5, characterized in that the output means outputs information relating to the result of the inference process when the personal information index relating to the text data satisfies predetermined conditions.

7. The information processing system according to claim 6, characterized in that the condition described above is met when the personal information index output by the trained model meets a predetermined value.

8. An extraction method for extracting personal information from text data, The information processing system according to any one of claims 1 to 7, further comprising a generation means for generating a trained model using data that associates personal information formation information extracted by the extraction means with information on whether or not personal information set in the text data from which the personal information formation information is extracted is included.

9. The information processing system according to claim 8, characterized in that the generation means generates a trained model using data that associates the number of extractions for each type of personal information forming information extracted by the extraction means with information on whether or not personal information is included in the text data that is the source of the personal information forming information.

10. The selection operation received by the selection operation receiving means is stored in association with the selection operation, which determines whether or not personal information is included, and the information relating to the user who performed the selection operation or the user's affiliation. The information processing system according to claim 8 or 9, characterized in that the generation means generates a trained model for each user or user who performed the selection operation.

11. The information processing system according to any one of claims 1 to 10, characterized in that the text data includes at least one of the body of an email and the text contained in a file attached to the email.

12. The information processing system according to any one of claims 1 to 11, characterized in that the output means outputs information relating to the results of inference processing by a trained model on the text data for which the transmission instruction was received, in response to the receipt of the transmission instruction.

13. A program for causing a computer to function as one of the means described in any one of claims 1 to 12.

14. The acquisition means of the information processing system includes an acquisition process for acquiring text data that has received a transmission instruction, The output means of the information processing system outputs information relating to the results of inference processing by a trained model on the acquired text data, a selection receiving unit that accepts a selection as to whether the text data contains personal information, and an instruction receiving unit independent of the selection receiving unit that accepts an instruction as to whether or not to transmit the text data, in an output step, The selection operation receiving means of the information processing system includes a selection operation receiving step in which the user makes a selection operation to the selection receiving unit regarding whether the text data for which the transmission instruction was received contains personal information, The control means of the information processing system includes a control step that controls the system to perform training on the trained model using the selection based on the selection operation received in the selection operation acceptance step and the text data, The instruction receiving means of the information processing system includes an instruction receiving step that receives an instruction on whether or not to send to a destination the text data acquired in the acquisition step, which has information relating to the result of the inference process output, Equipped with, The control step is characterized by controlling the learning of the trained model based on the selection in the selection receiving unit, regardless of whether or not to transmit data based on the instruction received in the instruction receiving step.

15. A means for acquiring text data that has received a transmission instruction, An output means that outputs information relating to the results of inference processing by a trained model on the acquired text data, a selection receiving unit that accepts a selection of whether the text data contains personal information, and an instruction receiving unit independent of the selection receiving unit that accepts an instruction of whether or not to transmit the text data. A selection operation receiving means that receives a selection operation from the user to the selection receiving unit to determine whether the text data for which the transmission instruction was received contains personal information, A control means that controls the training of the trained model using the selection based on the selection operation received by the selection operation receiving means and the text data, An instruction receiving means that receives an instruction on whether or not to send the text data acquired by the acquisition means, which has output information relating to the results of the inference process, to the recipient. Equipped with, The information processing apparatus is characterized in that the control means controls the learning of the trained model based on the selection in the selection receiving unit, regardless of whether or not to transmit data based on the instruction received by the instruction receiving means.

Images