JP7367870B2 - Conversation control program, conversation control method, and information processing device - Google Patents

Description

The present invention relates to a conversation control program, a conversation control method, and an information processing device.

In recent years, an increasing number of companies have introduced automated response systems that utilize technology called chatbots. A chatbot is a computer system that uses artificial intelligence to interact and exchange messages with humans. For example, two-way communication in conjunction with a chatbot may be used to perform counter operations that were traditionally handled by humans.

As a prior art, for example, when chat data sent from a user terminal is transferred to a chatbot via a network, and it is detected that the chat data sent from the user terminal includes content related to personal information, There is a chat system that performs a predetermined filtering process on the chat data.

Japanese Patent Application Publication No. 2018-200602

However, in the conventional technology, when providing a service using two-way communication in cooperation with a chatbot, it is necessary to input personally identifiable information, which may impede the use of the service using the chatbot.

In one aspect, the present invention aims to facilitate the use of a service using a chatbot.

In one embodiment, input information accepted in a chat bot conversation is received from an information processing terminal, a response process is executed based on the input information, and when a masking process request for the input information is received, the chat bot A conversation control program is provided that executes a masking process for not recording or anonymizing the input information in the log related to the conversation when recording a log related to the conversation in the bot.

According to one aspect of the present invention, it is possible to smoothly utilize a service using a chatbot.

FIG. 1 is an explanatory diagram showing an example of a system configuration of a conversation control system 100 according to the first embodiment. FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing apparatus 101. FIG. 3 is a block diagram showing an example of the hardware configuration of the information processing terminal 102. FIG. 4 is an explanatory diagram showing an example of the stored contents of the script table 130. FIG. 5 is an explanatory diagram showing an example of the content stored in chat log DB 140. FIG. 6 is an explanatory diagram showing a specific example of a script. FIG. 7 is an explanatory diagram (part 1) showing an example of a chat screen. FIG. 8 is a block diagram showing an example of the functional configuration of the information processing apparatus 101 according to the first embodiment. FIG. 9 is an explanatory diagram (part 2) showing an example of the chat screen. FIG. 10 is an explanatory diagram showing an example of the operation of the information processing apparatus 101. FIG. 11 is a flowchart (Part 1) illustrating an example of a conversation control processing procedure of the information processing apparatus 101 according to the first embodiment. FIG. 12 is a flowchart (part 2) illustrating an example of the conversation control processing procedure of the information processing apparatus 101 according to the first embodiment. FIG. 13 is a block diagram showing an example of the functional configuration of information processing apparatus 101 according to the second embodiment. FIG. 14 is an explanatory diagram showing an example of the stored contents of the number counter table 1400. FIG. 15 is a flowchart (Part 1) illustrating an example of the first conversation control processing procedure of the information processing apparatus 101 according to the second embodiment. FIG. 16 is a flowchart (part 2) illustrating an example of the first conversation control processing procedure of the information processing apparatus 101 according to the second embodiment. FIG. 17 is a flowchart (part 1) illustrating an example of the second conversation control processing procedure of the information processing apparatus 101 according to the second embodiment. FIG. 18 is a flowchart (Part 2) illustrating an example of the second conversation control processing procedure of the information processing apparatus 101 according to the second embodiment. FIG. 19 is a block diagram showing an example of the functional configuration of information processing apparatus 101 according to the third embodiment. FIG. 20 is an explanatory diagram showing an example of the storage contents of the personal identification information master 2000. FIG. 21 is an explanatory diagram showing a specific example of learning data. FIG. 22 is an explanatory diagram showing an example of password determination. FIG. 23 is an explanatory diagram (part 3) showing an example of the chat screen. FIG. 24 is an explanatory diagram (Part 4) showing an example of the chat screen. FIG. 25 is a flowchart (part 1) illustrating an example of the first conversation control processing procedure of the information processing apparatus 101 according to the third embodiment. FIG. 26 is a flowchart (part 2) illustrating an example of the first conversation control processing procedure of the information processing apparatus 101 according to the third embodiment. FIG. 27 is a flowchart illustrating an example of the second conversation control processing procedure of the information processing apparatus 101 according to the third embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments of a conversation control program, a conversation control method, and an information processing apparatus according to the present invention will be described in detail below with reference to the drawings.

(Embodiment 1)
First, a system configuration example of the conversation control system 100 including the information processing device 101 according to the first embodiment will be described. The conversation control system 100 is applied, for example, to a computer system that provides a service using two-way communication in cooperation with a chatbot.

FIG. 1 is an explanatory diagram showing an example of a system configuration of a conversation control system 100 according to the first embodiment. In FIG. 1, a conversation control system 100 includes an information processing device 101, a plurality of information processing terminals 102 (three in the example of FIG. 1), and an administrator terminal 103. In the conversation control system 100, an information processing device 101, an information processing terminal 102, and an administrator terminal 103 are connected via a wired or wireless network 110. The network 110 is, for example, a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, or the like.

Here, the information processing device 101 is a computer that controls conversations of a chatbot. The information processing device 101 is, for example, a server. The information processing device 101 includes, for example, an FAQ master 120, a script table 130, and a chat log DB (Database) 140. The FAQ master 120 stores FAQs (Frequently Asked Questions).

FAQ means "frequently asked questions" and is a collection of questions and answers to anticipated questions. The question may ask how to solve some problem, or may be a spoken question. The answers include answers that show how to solve the posed problem and answers to spoken questions.

The script table 130 stores scripts that define the conversation flow of the chatbot. Chatbot conversations occur according to a script. Chat log DB 140 stores chat logs. The chat log is a history of conversations between users and chatbots.

Note that the contents of the script table 130 and the chat log DB 140 will be described later using FIGS. 4 and 5.

The information processing terminal 102 is a computer that a user uses when having a conversation with a chatbot. The information processing terminal 102 is, for example, a smartphone, a tablet PC (Personal Computer), a PC, or the like. Further, the information processing terminal 102 may be a digital board installed at a station, an airport, a store, a commercial facility, or the like.

At the information processing terminal 102, the user can search for a desired answer or perform online procedures while interacting with a chatbot by, for example, inputting a message or selecting options. Online procedures are procedures performed online. Examples of online procedures include procedures such as account opening, balance inquiry, and transfer provided by financial institutions, and procedures such as changing communication service plans and model changes provided by communication carriers.

The administrator terminal 103 is a computer used by the administrator of the conversation control system 100. The administrator of the conversation control system 100 is, for example, a designer of a script that defines the conversation flow of the chatbot. The administrator terminal 103 is, for example, a PC. At the administrator terminal 103, the administrator can, for example, design and change scripts, set various threshold values, and the like.

Although not shown, the conversation control system 100 may include an operator terminal. An operator terminal is a computer used by an operator. The operator is a person who responds to the user when switching from conversation with a chatbot to conversation with a human. For example, the operator can interact with the user using the telephone function of the operator terminal, text communication, and the like.

Here, in services that utilize two-way communication in conjunction with chatbots, you may be asked to enter personally identifiable information. For example, when providing some kind of consultation, you may be asked to input personally identifiable information such as your name and address. In this case, it becomes possible to specify who consulted what kind of consultation.

Users with high IT literacy are aware that the information they enter is logged on servers, and that this information may be used for marketing and product recommendations. many. Users who do not want their information to be used may stop using the service if they are asked to input information.

Note that it may be possible to avoid recording in the log any information that the user may not want to know. However, the reality is that business operators want to receive and utilize data, and it is not desirable to uniformly avoid recording information that users may not want to know.

Therefore, in the first embodiment, when the information processing apparatus 101 receives input information accepted in a chatbot conversation, the information processing apparatus 101 executes response processing based on the input information, and when receiving a request for masking processing of the input information, When recording logs related to conversations in a chatbot, a masking process is performed to not record or conceal input information in the logs related to the conversations. In this way, we will explain a conversation control method that allows users to control recording in logs themselves so that users can use services with peace of mind, and aims to smoothly use services using chatbots.

(Example of hardware configuration of information processing device 101)
Next, an example of the hardware configuration of the information processing device 101 will be described.

FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing apparatus 101. In FIG. 2, the information processing device 101 includes a CPU (Central Processing Unit) 201, a memory 202, a disk drive 203, a disk 204, a communication I/F (Interface) 205, and a portable recording medium I/F 206. , and a portable recording medium 207. Further, each component is connected to each other by a bus 200.

Here, the CPU 201 is in charge of overall control of the information processing apparatus 101. CPU 201 may have multiple cores. The memory 202 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), a flash ROM, and the like. Specifically, for example, a flash ROM stores an OS (Operating System) program, a ROM stores an application program, and a RAM is used as a work area for the CPU 201. The program stored in the memory 202 is loaded into the CPU 201 and causes the CPU 201 to execute the coded processing.

The disk drive 203 controls reading/writing of data to/from the disk 204 under the control of the CPU 201 . The disk 204 stores data written under the control of the disk drive 203. Examples of the disk 204 include a magnetic disk and an optical disk.

The communication I/F 205 is connected to a network 110 through a communication line, and is connected to an external computer (for example, the information processing terminal 102 and the administrator terminal 103 shown in FIG. 1) via the network 110. The communication I/F 205 serves as an interface between the network 110 and the inside of the device, and controls data input/output from an external computer. For example, a modem or a LAN adapter can be used as the communication I/F 205.

The portable recording medium I/F 206 controls reading/writing of data to/from the portable recording medium 207 under the control of the CPU 201 . The portable recording medium 207 stores data written under the control of the portable recording medium I/F 206. Examples of the portable recording medium 207 include a CD (Compact Disc)-ROM, a DVD (Digital Versatile Disk), and a USB (Universal Serial Bus) memory.

Note that the information processing device 101 may include, for example, an SSD (Solid State Drive), an input device, a display, etc. in addition to the above-described components. Further, the information processing apparatus 101 does not need to include, for example, the disk drive 203, the disk 204, the portable recording medium I/F 206, and the portable recording medium 207 among the above-mentioned components.

(Example of hardware configuration of information processing terminal 102)
Next, an example of the hardware configuration of the information processing terminal 102 will be described.

FIG. 3 is a block diagram showing an example of the hardware configuration of the information processing terminal 102. In FIG. 3, the information processing terminal 102 includes a CPU 301, a memory 302, a display 303, an input device 304, a communication I/F 305, a camera 306, a speaker 307, a microphone 308, and a GPS (Global Positioning System). unit 309. Further, each component is connected to each other by a bus 300.

Here, the CPU 301 is in charge of overall control of the information processing terminal 102. CPU 301 may have multiple cores. The memory 302 is a storage unit including, for example, ROM, RAM, and flash ROM. Specifically, for example, a flash ROM or ROM stores various programs, and a RAM is used as a work area for the CPU 301. The program stored in the memory 302 is loaded into the CPU 301 and causes the CPU 301 to execute the coded processing.

The display 303 is a display device that displays data such as cursors, icons, tool boxes, documents, images, and functional information. As the display 303, for example, a liquid crystal display, an organic EL (electroluminescence) display, or the like can be used.

The input device 304 has keys for inputting characters, numbers, various instructions, etc., and inputs data. The input device 304 may be a touch panel type input pad, a numeric keypad, or the like, or may be a keyboard, a mouse, or the like.

The communication I/F 305 is connected to the network 110 through a communication line, and is connected to an external computer (for example, the information processing device 101) via the network 110. The communication I/F 305 serves as an interface between the network 110 and the inside of the device itself, and controls input/output of data from external devices.

The camera 306 is a photographing device that photographs images (still images or moving images) and outputs image data. The speaker 307 converts the electrical signal into sound and outputs the sound. Microphone 308 receives audio and converts it into an electrical signal.

The GPS unit 309 receives radio waves from GPS satellites and outputs position information of the information processing terminal 102. The location information of the information processing terminal 102 is, for example, information specifying a point on the earth, such as latitude and longitude. Further, as the satellite, for example, a satellite of the quasi-zenith satellite system may be used.

In addition to the above-described components, the information processing terminal 102 includes, for example, an HDD (Hard Disk Drive), an SSD, a short-range wireless communication I/F, a portable recording medium I/F, a portable recording medium, and the like. You can decide. Further, the administrator terminal 103 shown in FIG. 1 can also be realized with the same hardware configuration as the information processing terminal 102.

(Memory contents of script table 130)
Next, the stored contents of the script table 130 included in the information processing apparatus 101 will be explained using FIG. 4. The script table 130 is realized, for example, by a storage device such as the memory 202 and the disk 204 shown in FIG. 2.

FIG. 4 is an explanatory diagram showing an example of the stored contents of the script table 130. In FIG. 4, the script table 130 has service and script fields, and by setting information in each field, script management information 400-1 to 400-n is stored as records.

Here, the service refers to a service that utilizes two-way communication in cooperation with a chatbot. Here, only procedure IDs (for example, A1, A2) that identify services are shown. Examples of services include those that utilize two-way communication in conjunction with chatbots to provide consultation on matters such as health, higher education, and career advancement, as well as to perform various online procedures.

A script is information (scenario) that defines the flow of a chatbot's conversation, and is prepared in association with a service. However, only script IDs (for example, S1, S2) for identifying scripts are shown here. For example, script management information 400-1 indicates script S1 corresponding to service A1.

(Memorized content of chat log DB140)
Next, the storage contents of the chat log DB 140 included in the information processing apparatus 101 will be explained using FIG. 5. Chat log DB 140 is realized, for example, by a storage device such as memory 202 and disk 204 shown in FIG. 2.

FIG. 5 is an explanatory diagram showing an example of the content stored in chat log DB 140. In FIG. 5, chat log DB 140 has fields of chat_id, talklog_id, time stamp, script, label, and message. By setting information in each field, chat logs (for example, chat logs 500-1 to 500-5) are stored as records.

Here, chat_id indicates the ID of the room where the chat is performed. According to chat_id, a series of conversations in the chatbot can be specified. talklog_id is an identifier that identifies a chat log. The time stamp indicates the date and time (GMT+9 hours) when the talk process (step) defined in the script was executed. GMT is Greenwich Mean Time.

The talk process is a process for realizing the operation (behavior) of the chatbot. For example, the talk process includes the process of speaking, the process of displaying options, the process of selecting options according to user operations, the process of performing procedures according to the selected options and input information, and the process of terminating the talk process. Including.

script indicates a script (scenario) applied to a chatbot conversation. label indicates the name of the step in which the talk process was executed among multiple steps in the script. The message indicates sentences uttered in the executed talk process, selected options, input information, processing contents on the system side, error messages, and the like.

For example, the chat log 500-2 is a log with chat_id "100", talklog_id "15044", and time stamp "2020-01-08T14:25:43+09:00". According to the chat log 500-2, it is specified that the talk process (step) of the script "S10" with the label "VRB-1" was executed and the message "Please tell me your name." was displayed. Can be done.

Note that the chat log may include, for example, information indicating whether it is a system log or information indicating whether the log is related to a chatbot or a user. Further, the chat log may include, for example, the IP (Internet Protocol) address of the information processing terminal 102 used by the user.

Here, a specific example of the script will be described using FIG. 6. Here, the script S100 corresponding to the service A100 will be described as an example.

FIG. 6 is an explanatory diagram showing a specific example of a script. In FIG. 6, a script S100 is information (scenario) that defines the conversation flow of the chatbot. However, in FIG. 6, a part of the script S100 is excerpted and displayed. Specifically, for example, the script S100 is information that defines chat processing.

Script S100 includes steps 601-605. Here, step 601 indicates the start of talk processing. Steps 602 and 603 show processing for speaking a message. Step 604 shows processing for displaying options. Step 605 indicates the end of the talk process.

Note that the same label (see FIG. 5) may be set for multiple steps. For example, the same "VRB-1" is set in steps 602 and 603. Although not shown, the script S100 includes, in addition to steps 601 to 605, a step of executing a procedure according to a selected option or input information, a process of searching an FAQ, etc. It will be done.

(Example of chat screen)
Next, an example of a chat screen displayed on the display 303 (FIG. 3) of the information processing terminal 102 will be described.

FIG. 7 is an explanatory diagram (part 1) showing an example of a chat screen. In FIG. 7, a chat screen 700 is an example of an operation screen that displays a chatbot conversation on the information processing terminal 102. In FIG. 7, avatar av is a character representing a chatbot.

On the chat screen 700, for example, a message can be input by selecting a box 710 by a user's operation input using the input device 304 shown in FIG. The message may be input by voice input using the microphone 308 shown in FIG. 3, for example. Furthermore, by selecting a send button 711 on the chat screen 700, the message entered in the box 710 can be sent to the chatbot side (information processing device 101).

On the chat screen 700, a message m1 representing a statement of the avatar av is displayed. Message m1 is an example of a message prompting the user to input the user's name. Additionally, a message m2 representing a user's comment is displayed on the chat screen 700. Message m2 is an example of the name input for message m1 of avatar av.

Additionally, a secret button 720 is displayed on the chat screen 700. The secret button 720 is an example of information that inquires whether or not recording of input information in a log is permitted. Input information is information that is input and indicates options that are selected in a chatbot conversation.

On the chat screen 700, for example, when a secret button 720 is selected by the user's operation input, the off-the-record mode can be set. The off-the-record mode is a mode in which input information is not recorded in the log or is anonymized when recording a log (chat log) related to a chatbot conversation.

This allows the user to control what information is not recorded in the log or is anonymized, out of the information input during chatbot conversations.

(Functional configuration example of information processing device 101)
FIG. 8 is a block diagram showing an example of the functional configuration of the information processing apparatus 101 according to the first embodiment. In FIG. 8, the information processing apparatus 101 includes a reception section 801, a conversation control section 802, and a recording control section 803. Specifically, for example, the reception unit 801 to the recording control unit 803 cause the CPU 201 to execute a program stored in a storage device such as the memory 202, the disk 204, or the portable recording medium 207 shown in FIG. Alternatively, the function is realized by the communication I/F 205. The processing results of each functional unit are stored in a storage device such as the memory 202 or the disk 204, for example.

The reception unit 801 receives a chat start instruction from the information processing terminal 102. Here, the chat start instruction is for starting a conversation between the user and the chatbot, and is, for example, requesting the start of a service using the chatbot. The chat start instruction includes, for example, a service ID.

For example, an instruction to start a chat is performed by a user's operation input on the information processing terminal 102, and is transmitted from the information processing terminal 102 to the information processing apparatus 101. Specifically, for example, the reception unit 801 receives the chat start instruction by receiving the chat start instruction from the information processing terminal 102 .

The conversation control unit 802 starts a chatbot conversation on the information processing terminal 102 in response to a chat start instruction from the information processing terminal 102 . Specifically, for example, the conversation control unit 802 refers to the script table 130 shown in FIG. 4 and identifies the script corresponding to the service ID included in the chat start instruction.

Next, the conversation control unit 802 determines the specified script as a talk script to be applied to the chatbot conversation on the information processing terminal 102. The conversation control unit 802 then starts a chat regarding the service on the information processing terminal 102 using the determined talk script.

For example, assume that the chat start instruction includes the service ID "A1". In this case, the conversation control unit 802 refers to the script table 130 and determines the script S1 corresponding to the service ID "A1" as the talk script. Then, the conversation control unit 802 starts a chatbot conversation regarding the service S1 on the information processing terminal 102 using the determined talk script S1.

Note that the conversation control unit 802 may determine a predetermined script as the talk script in response to a chat start instruction from the information processing terminal 102. Furthermore, the conversation control unit 802 may determine the talk script based on, for example, the user attributes of the information processing terminal 102 or the external environment. The user attribute is information representing the characteristics of the user of the information processing terminal 102. User attributes include, for example, age, gender, and language used. The external environment is information representing the external environment of the information processing terminal 102. The external environment represents, for example, weather, temperature, humidity, time, location, and the like.

When the conversation control unit 802 receives input information accepted in a chatbot conversation from the information processing terminal 102, it executes response processing based on the input information. Here, the input information is information input by a user's operation using the input device 304 shown in FIG. 3, for example, during a chatbot conversation. Further, the input information may be information indicating an option selected by a user's operation in a chatbot conversation.

The response process based on input information is, for example, a process of searching an FAQ in accordance with information input in a chatbot conversation and outputting the results. The FAQ search is performed using, for example, the FAQ master 120 shown in FIG. Further, the response process based on input information may be a process of performing a procedure according to information input in a chatbot conversation.

The recording control unit 803 records a log regarding the chatbot conversation as a result of the conversation control unit 802 starting the chatbot conversation on the information processing terminal 102 . Specifically, for example, the recording control unit 803 records a chat log when a user or a chatbot speaks or when internal processing of the system is performed. The input information received in the conversation with the chatbot is included in the message of the chat log, for example (see FIG. 5).

In addition, when the recording control unit 803 receives a request for masking processing of input information received in a chatbot conversation from the information processing terminal 102, the recording control unit 803 performs masking processing on the input information when recording a log related to the chatbot conversation. Execute processing. Here, the masking process request is a request for execution of masking process.

The masking process is a process of not recording or anonymizing input information in logs related to chatbot conversations. Not recording in the log may mean, for example, not setting input information in message and creating a chat log with message blank. Moreover, not recording in a log may mean that a chat log in which input information is set in a message is once created, and then the input information is deleted from the chat log.

Concealment means, for example, converting input information into information that cannot be inferred. Information that cannot be inferred is, for example, an asterisk (*) or a blackout. Anonymizing may mean converting input information into information that cannot be inferred and then setting it as a message, or may mean converting input information set in a message to information that cannot be inferred. .

Note that the information processing apparatus 101 may receive input information and a masking process request at the same time, for example, in a chatbot conversation. Furthermore, after receiving input information, the information processing apparatus 101 may decide to receive a request for masking processing of the input information. Further, the information processing apparatus 101 may decide to receive input information that is information to be subjected to masking processing after receiving a masking processing request.

Specifically, for example, the conversation control unit 802 outputs, to the information processing terminal 102, inquiry information regarding whether or not to permit recording of input information in a log in a chatbot conversation. The masking processing request is transmitted from the information processing terminal 102, for example, when an operation is performed on the information processing terminal 102 to disallow recording to a log in response to inquiry information.

The inquiry information is a message, an icon, or the like for inquiring whether to permit recording of input information in a log, and is, for example, the secret button 720 shown in FIG. 7. To explain in more detail, for example, when starting a conversation with a chatbot on the information processing terminal 102, a chat screen 700 including a secret button 720 is displayed on the information processing terminal 102.

When the secret button 720 is selected by the user's operation input on the chat screen 700, an off-the-record setting instruction is transmitted from the information processing terminal 102 to the information processing apparatus 101. The off-the-record setting instruction corresponds to a masking processing request. Upon receiving the off-record setting instruction from the information processing terminal 102, the recording control unit 803 sets the off-record mode (ON).

The off-the-record mode is a mode in which input information is not recorded in the log or is anonymized when recording a log (chat log) related to a chatbot conversation. That is, in the off-the-record mode, the user's comments are not recorded in the log as information subject to masking processing, or are recorded in the log in an anonymized manner.

Specifically, for example, when the recording control unit 803 receives input information accepted in a chatbot conversation from the information processing terminal 102, it determines whether the off-the-record mode is set. Here, if the off-the-record mode is not set, the recording control unit 803 does not perform masking processing on the received input information when recording the chat log.

On the other hand, when the off-the-record mode is set, the recording control unit 803 performs masking processing on the received input information when recording the chat log. To explain in more detail, for example, the recording control unit 803 may delete the input information from the chat log regarding the received input information among the chat logs regarding the conversation in the chatbot, and may delete the input information from the chat log regarding the received input information. The input information in the chat log may be concealed by converting it into information that cannot be guessed, such as an asterisk or redacting.

In addition, although the case where the secret button 720 is pressed before inputting the information to be masked is described here as an example, the present invention is not limited to this. For example, the secret button 720 may be pressed after inputting the information to be masked. In this case, the recording control unit 803 executes the masking process on the input information received after receiving the off-the-record setting instruction (masking process request).

Furthermore, it may be possible to specify part of the input information received in a chatbot conversation as information to be masked. For example, in the chat screen 700, it may be possible to designate part of the information in the message input in the box 710 as the information to be masked by the user's operation input using the input device 304. In this case, the recording control unit 803 may, for example, perform a masking process on information (for example, a part of an address) specified as information to be masked among the received input information. Information other than the specified information among the input information is, for example, recorded as is in the log.

Further, the chat log is recorded in the chat log DB 140 shown in FIG. 5. Specifically, for example, a chat log recorded during a conversation with a chatbot is temporarily stored in a buffer in the memory 202, for example. When the conversation with the chatbot ends, all chat logs in the buffer are output to the chat log DB 140. Chat log 500-1 shown in FIG. 5 is an example of a log that includes masked input information.

Further, for example, on the chat screen 700, information that has already been input as information not subject to masking processing may be additionally designated as information subject to masking processing before the conversation in the chatbot ends. In this case, the recording control unit 803 performs masking, for example, by deleting or anonymizing information from a log that includes additionally specified information to be masked, from among the logs that have been temporarily stored in the buffer in the memory 202. Execute processing.

Each functional unit of the information processing device 101 described above may be realized by a plurality of computers (for example, the information processing device 101 and the information processing terminal 102) within the conversation control system 100. Further, each functional unit of the information processing device 101 described above may be realized by the information processing terminal 102.

(Example of operation of information processing device 101)
Next, an example of the operation of the information processing apparatus 101 according to the first embodiment will be described using FIGS. 9 and 10. Here, we will explain an example of a chat screen that is displayed when providing health consultation using two-way communication linked to a chatbot.

FIG. 9 is an explanatory diagram (part 2) showing an example of the chat screen. FIG. 10 is an explanatory diagram showing an example of the operation of the information processing apparatus 101. In FIG. 9, a message m3 representing a statement made by avatar av is displayed on chat screen 700. Message m3 is an example of a message prompting the user to input consultation details.

Here, the user's name "Fujitaro" is input prior to inputting the user's consultation details. The name "Fujitaro" is personally identifiable information. For this reason, when the content of a user's consultation is input in response to message m3, information that allows identification of who consulted and what kind of consultation is recorded in the log.

Here, it is assumed that the user selects the secret button 720 on the chat screen 700 because the user has determined that he or she does not want to record the contents of his/her consultation in the log. In this case, an off-the-record setting instruction is transmitted from the information processing terminal 102 to the information processing apparatus 101, and off-the-record mode is set (ON).

Note that when the secret button 720 is selected, the display mode of the secret button 720 is changed so that it can be determined that the off-the-record mode is being set, for example (see, for example, FIG. 10). Further, when the secret button 720 is selected, for example, an icon indicating that the off-the-record mode is being set may be displayed.

Furthermore, when the secret button 720 is selected on the chat screen 700 and then selected again, an off-the-record release instruction is sent from the information processing terminal 102 to the information processing apparatus 101, and the off-the-record mode is released ( OFF). Further, the off-record mode may be automatically canceled each time input information is transmitted from the information processing terminal 102 to the information processing apparatus 101.

In FIG. 10, a message m4 representing a user's comment is displayed on a chat screen 700. Message m4 is an example of the consultation content input in response to message m3 of avatar av. The input message m4 is transmitted from the information processing terminal 102 to the information processing device.

For example, upon receiving the message m4, the information processing device 101 refers to the FAQ master 120 and searches for FAQs based on the message m4. The information processing device 101 then outputs the search results to the information processing terminal 102. As a result, on the chat screen 700, search results (not shown), for example, are displayed in a selectable manner as the utterances of the avatar av.

Thereby, the user can obtain answers (FAQ) to the consultation details (questions) input by the user.

In addition, an off-the-record mode is set here. For this reason, the information processing apparatus 101 performs a masking process on the message m4 when recording a chat log regarding the message m4 received in the chatbot conversation.

Specifically, for example, the information processing apparatus 101 records a chat log 500-5 in which the received message m4 is deleted. The message “***deleted***” in the chat log 500-5 indicates that the input information has been deleted. In addition, in FIG. 10, a part of the chat log is excerpted and displayed.

(Conversation control processing procedure of information processing device 101)
Next, the conversation control processing procedure of the information processing apparatus 101 according to the first embodiment will be explained using FIGS. 11 and 12.

11 and 12 are flowcharts illustrating an example of a conversation control processing procedure of the information processing apparatus 101 according to the first embodiment. In the flowchart of FIG. 11, first, the information processing apparatus 101 determines whether a chat start instruction has been received from the information processing terminal 102 (step S1101).

Here, the information processing apparatus 101 waits to receive a chat start instruction (step S1101: No). When the information processing apparatus 101 receives a chat start instruction (step S1101: Yes), the information processing apparatus 101 refers to the script table 130 and determines the script corresponding to the service ID included in the received chat start instruction as a talk script. (Step S1102).

Then, the information processing apparatus 101 starts a chatbot conversation on the information processing terminal 102 using the determined talk script (step S1103). At this time, the information processing apparatus 101 outputs to the information processing terminal 102 inquiry information regarding whether to permit recording of the input information in the log. The inquiry information is, for example, the secret button 720 shown in FIG.

Next, the information processing apparatus 101 determines whether an off-the-record setting instruction has been received from the information processing terminal 102 (step S1104). Here, if an off-the-record setting instruction is received from the information processing terminal 102 (step S1104: Yes), the information processing apparatus 101 turns on the off-the-record mode (step S1105), and proceeds to step S1201 shown in FIG. 12.

On the other hand, if an off-the-record setting instruction has not been received from the information processing terminal 102 (step S1104: No), the information processing apparatus 101 determines whether an off-the-record cancellation instruction has been received from the information processing terminal 102 (step S1106). .

Here, if the off-the-record cancellation instruction has not been received from the information processing terminal 102 (step S1106: No), the information processing apparatus 101 moves to step S1201 shown in FIG. 12. On the other hand, if an off-record cancellation instruction is received from the information processing terminal 102 (step S1106: Yes), the information processing apparatus 101 turns off the off-record mode (step S1107), and proceeds to step S1201 shown in FIG. 12.

In the flowchart of FIG. 12, first, the information processing apparatus 101 determines whether input information received in a chatbot conversation is received from the information processing terminal 102 (step S1201). Here, if input information has not been received (step S1201: No), the information processing apparatus 101 moves to step S1206.

On the other hand, when input information is received (step S1201: Yes), the information processing apparatus 101 executes response processing based on the received input information (step S1202). Next, the information processing apparatus 101 determines whether the off-the-record mode is ON (step S1203).

Here, if the off-the-record mode is ON (step S1203: Yes), the information processing apparatus 101 performs masking processing on the received input information, and outputs a chat log with the input information masked (step S1204), The process moves to step S1206.

On the other hand, if the off-the-record mode is OFF (step S1203: No), the information processing apparatus 101 outputs a chat log including the received input information (step S1205). The information processing apparatus 101 then determines whether to end the chatbot conversation on the information processing terminal 102 (step S1206).

Here, if the conversation is not ended (step S1206: No), the information processing apparatus 101 returns to step S1104 shown in FIG. 11. On the other hand, if the conversation is to be ended (step S1206: Yes), the information processing apparatus 101 ends the series of processes according to this flowchart. Note that the chatbot conversation ends, for example, according to the talk script or in response to a user's forced termination operation.

Thereby, in response to an off-the-record setting instruction from the information processing terminal 102, input information received in a chatbot conversation can be masked and output as a log.

As described above, according to the information processing apparatus 101 according to the first embodiment, it is possible to receive input information accepted in a chatbot conversation from the information processing terminal 102 and execute response processing based on the input information. can. Further, according to the information processing apparatus 101, when a request for masking input information is received, when recording a log related to a conversation in the chatbot, the information processing apparatus 101 does not record in the log related to the input information among the log related to the conversation, or hides the input information. It is possible to perform masking processing to reduce

As a result, in response to a request for masking processing from a user, response processing (for example, FAQ search) based on the input information received in the chatbot conversation can be executed, but the input information will not be left in the log. can do.

Furthermore, the information processing device 101 can output inquiry information to the information processing terminal 102 regarding whether or not to permit recording of input information in a log during a chatbot conversation. According to the information processing device 101, when an operation to disallow recording to a log is performed in response to the inquiry information on the information processing terminal 102, a masking processing request is received from the information processing terminal 102. I can do it.

As a result, during a conversation with a chatbot, for example, the user can perform a simple operation such as pressing the secret button 720 (for example, see Figure 7) before inputting information, so that the input information will not be recorded in the log. It becomes possible to do so.

In this way, according to the information processing apparatus 101, the user himself/herself can control the recording of information input in a chatbot conversation into a log. This eliminates anxiety when using a service that involves inputting information that the user does not want to know. Additionally, even if the input information is masked, the information about which steps in the talk script (scenario) were executed remains in the log, which can be useful for business flow analysis.

(Embodiment 2)
Next, the information processing device 101 according to the second embodiment will be explained. In Embodiment 2, the information processing device 101 associates the information with a location where information is input in a chatbot conversation, receives input information accepted at that location, and receives a masking processing request for the input information. Record the number of times. A case will be described in which the information processing apparatus 101 determines whether the input information received at the location is information to be masked, based on the number of times the information has been recorded. Note that portions similar to those described in Embodiment 1 are designated by the same reference numerals, and illustration and description thereof are omitted.

(Functional configuration example of information processing device 101)
First, an example of the functional configuration of the information processing apparatus 101 according to the second embodiment will be described using FIG. 13.

FIG. 13 is a block diagram showing an example of the functional configuration of information processing apparatus 101 according to the second embodiment. In FIG. 13, the information processing apparatus 101 includes a reception section 801, a conversation control section 802, a recording control section 803, and a counting section 1301. Specifically, for example, the reception unit 801 to the recording control unit 803 and the counting unit 1301 cause the CPU 201 to execute a program stored in a storage device such as the memory 202, the disk 204, or the portable recording medium 207 shown in FIG. This function is realized by the communication I/F 205 or by the communication I/F 205. The processing results of each functional unit are stored in a storage device such as the memory 202 or the disk 204, for example.

Hereinafter, of the functional units of the information processing apparatus 101 according to the second embodiment, parts that are different from the functional units of the information processing apparatus 101 according to the first embodiment will be described.

The counting unit 1301 receives the input information accepted at the first location in association with the first location in the conversation in the chatbot, and records the number of times a masking processing request for the input information has been received. Here, the first location is a location where information is input during a conversation with the chatbot.

For example, in the first part, among multiple steps in the script, a talk process is executed that accepts input of information and selection of options, and then utters the input information and information indicating the selected options. This is a step to The number of times corresponding to the first location is stored, for example, in a number of times counter table 1400 as shown in FIG. 14.

Here, the stored contents of the number counter table 1400 will be explained. The number counter table 1400 is realized, for example, by a storage device such as the memory 202 and the disk 204 shown in FIG.

FIG. 14 is an explanatory diagram showing an example of the stored contents of the number counter table 1400. In FIG. 14, the number counter table 1400 has fields of script, label, and number of times, and by setting information in each field, number of times information (for example, number of times information 1400-1 to 1400-4) is stored as a record. do.

Here, script indicates a script (scenario) applied to a conversation in the chatbot. label indicates the name of the step in which the talk process was executed among multiple steps in the script. The number of times indicates the number of times the input information accepted in the step has been received and a masking processing request for the input information has been received.

For example, the number of times information 1400-1 indicates "5" the number of times the input information accepted in the step labeled "VRB-1" in the script P100 has been received and a masking processing request for the input information has been received.

As an example, assume that in a chatbot conversation based on the talk script P100, input information accepted in a step with label "VRB-1" is received, and a request for masking processing of the input information is received. In this case, the counting unit 1301 increments the number of times in the number of times information 1400-1 corresponding to the script “P100” and the label “VRB-1” in the number of times counter table 1400.

When the recording control unit 803 receives the input information accepted at the first location in the conversation in the chatbot from the information processing terminal 102, the recording control unit 803 determines the input information received based on the number of times it is recorded in association with the first location. It is determined whether the input information is information to be subjected to masking processing. Here, the information to be masked is information that is not recorded in the log or is made confidential when recording a log related to a chatbot conversation.

Specifically, for example, the recording control unit 803 determines that the received input information is information to be masked when the number of times it has been recorded in association with the first location is equal to or greater than a first threshold. to decide. The first threshold value can be set arbitrarily, and is set, for example, according to the length of the period in which the number of times corresponding to the first location is recorded.

As an example, assume that the number of times corresponding to the first location is recorded for a period of one day. In this case, the first threshold is set to a value of about 10, for example. Further, assume that the number of times corresponding to the first location is recorded for a period of one week. In this case, the first threshold is set to a value of about 100, for example.

Further, the recording control unit 803 controls whether the received input information is subject to masking processing if the ratio of the number of times the input information received at the first location is recorded to the total number of times the input information is received is equal to or higher than the second threshold. It may be determined that the information is information. The second threshold value can be set arbitrarily, and is set to a value of about 0.6 (60%) to 0.8 (80%), for example.

Here, if it is determined that the information is subject to masking processing, the recording control unit 803 executes masking processing on the received input information when recording a log related to the conversation in the chatbot. On the other hand, if it is determined that the information is not subject to masking processing, the recording control unit 803 does not perform masking processing on the received input information.

Additionally, the conversation control unit 802 controls information input at the first location when the number of times recorded in association with the first location in the conversation in the chatbot exceeds a first threshold. Inquiry information regarding whether or not to permit recording in the log may be output to the information processing terminal 102.

Then, when the recording control unit 803 receives the input information accepted at the first location from the information processing terminal 102 and receives a masking processing request for the input information, the recording control unit 803 performs a process when recording a log related to the conversation in the chatbot. , a masking process may be performed on the input information.

(Conversation control processing procedure of information processing device 101)
Next, a conversation control processing procedure of the information processing apparatus 101 according to the second embodiment will be explained. In the information processing apparatus 101 according to the second embodiment, for example, after performing the first conversation control process for a predetermined period, the second conversation control process is performed.

First, the first conversation control processing procedure of the information processing apparatus 101 according to the second embodiment will be described using FIGS. 15 and 16.

15 and 16 are flowcharts illustrating an example of the first conversation control processing procedure of the information processing apparatus 101 according to the second embodiment. In the flowchart of FIG. 15, first, the information processing apparatus 101 determines whether a chat start instruction has been received from the information processing terminal 102 (step S1501).

Here, the information processing apparatus 101 waits to receive a chat start instruction (step S1501: No). When the information processing apparatus 101 receives a chat start instruction (step S1501: Yes), the information processing apparatus 101 refers to the script table 130 and determines the script corresponding to the service ID included in the received chat start instruction as a talk script. (Step S1502).

Then, the information processing apparatus 101 starts a chatbot conversation on the information processing terminal 102 using the determined talk script (step S1503). At this time, the information processing apparatus 101 outputs to the information processing terminal 102 inquiry information regarding whether to permit recording of the input information in the log. The inquiry information is, for example, the secret button 720 shown in FIG.

Next, the information processing apparatus 101 determines whether an off-the-record setting instruction has been received from the information processing terminal 102 (step S1504). Here, when the off-the-record setting instruction is received from the information processing terminal 102 (step S1504: Yes), the information processing apparatus 101 turns on the off-the-record mode (step S1505), and proceeds to step S1601 shown in FIG. 16.

On the other hand, if an off-the-record setting instruction has not been received from the information processing terminal 102 (step S1504: No), the information processing apparatus 101 determines whether an off-the-record cancellation instruction has been received from the information processing terminal 102 (step S1506). .

Here, if the off-the-record release instruction has not been received from the information processing terminal 102 (step S1506: No), the information processing apparatus 101 moves to step S1601 shown in FIG. 16. On the other hand, if an off-record release instruction is received from the information processing terminal 102 (step S1506: Yes), the information processing apparatus 101 turns off the off-record mode (step S1507), and proceeds to step S1601 shown in FIG. 16.

In the flowchart of FIG. 16, first, the information processing apparatus 101 determines whether input information received in a chatbot conversation is received from the information processing terminal 102 (step S1601). Here, if input information has not been received (step S1601: No), the information processing apparatus 101 moves to step S1607.

On the other hand, when input information is received (step S1601: Yes), the information processing apparatus 101 executes response processing based on the received input information (step S1602). Next, the information processing apparatus 101 determines whether the off-the-record mode is ON (step S1603).

Here, if the off-the-record mode is ON (step S1603: Yes), the information processing apparatus 101 performs masking processing on the received input information, and outputs a chat log with the input information masked (step S1604). Then, the information processing apparatus 101 increments the number of times of the corresponding label in the number of times counter table 1400 (step S1605), and proceeds to step S1607.

On the other hand, if the off-the-record mode is OFF (step S1603: No), the information processing apparatus 101 outputs a chat log including the received input information (step S1606). The information processing apparatus 101 then determines whether to end the chatbot conversation on the information processing terminal 102 (step S1607).

Here, if the conversation is not ended (step S1607: No), the information processing apparatus 101 returns to step S1504 shown in FIG. 15. On the other hand, if the conversation is to be ended (step S1607: Yes), the information processing apparatus 101 ends the series of processes according to this flowchart.

Thereby, in response to an off-the-record setting instruction from the information processing terminal 102, input information received in a chatbot conversation can be masked and output as a log. Furthermore, it is possible to count the number of times a request for masking processing has been made regarding input information received at a step (location) in the talk script.

Next, the second conversation control processing procedure of the information processing apparatus 101 according to the second embodiment will be explained using FIGS. 17 and 18.

17 and 18 are flowcharts illustrating an example of the second conversation control processing procedure of the information processing apparatus 101 according to the second embodiment. In the flowchart of FIG. 17, first, the information processing apparatus 101 determines whether a chat start instruction has been received from the information processing terminal 102 (step S1701).

Here, the information processing apparatus 101 waits to receive a chat start instruction (step S1701: No). When the information processing apparatus 101 receives a chat start instruction (step S1701: Yes), the information processing apparatus 101 refers to the script table 130 and determines the script corresponding to the service ID included in the received chat start instruction as a talk script. (Step S1702).

Then, the information processing apparatus 101 starts a chatbot conversation on the information processing terminal 102 using the determined talk script (step S1703). Next, the information processing apparatus 101 refers to the number counter table 1400 and obtains the number of times of the label of the current position in the determined talk script (step S1704).

Then, the information processing apparatus 101 determines whether the number of times of acquisition is equal to or greater than a threshold value (step S1705). Here, if the number of times is less than the threshold value (step S1705: No), the information processing apparatus 101 turns off the off-record mode (step S1707), and moves to step S1801 shown in FIG. 18.

Note that if the number of times of the current position cannot be acquired in step S1704, the information processing apparatus 101 moves to step S1707.

On the other hand, if the number of times is equal to or greater than the threshold value (step S1705: Yes), the information processing apparatus 101 turns on the off-record mode (step S1706), and moves to step S1801 shown in FIG. 18.

At this time, the information processing apparatus 101 may, for example, enable the secret button 720 in the chat screen 700 as shown in FIG. 10. Further, the information processing device 101 may display a message such as "You are in off-the-record mode. The information you entered will not be recorded on the server" along with the secret button 720 in the chat screen 700. . Furthermore, in the second conversation control process, for example, the secret button 720 may not be displayed on the chat screen 700.

In the flowchart of FIG. 18, first, the information processing apparatus 101 determines whether input information received in a chatbot conversation is received from the information processing terminal 102 (step S1801). Here, if input information has not been received (step S1801: No), the information processing apparatus 101 moves to step S1806.

On the other hand, when input information is received (step S1801: Yes), the information processing apparatus 101 executes response processing based on the received input information (step S1802). Next, the information processing apparatus 101 determines whether the off-the-record mode is ON (step S1803).

Here, if the off-the-record mode is ON (step S1803: Yes), the information processing device 101 performs masking processing on the received input information, and outputs a chat log with the input information masked (step S1804), The process moves to step S1806.

On the other hand, if the off-the-record mode is OFF (step S1803: No), the information processing device 101 outputs a chat log including the received input information (step S1805). The information processing apparatus 101 then determines whether to end the chatbot conversation on the information processing terminal 102 (step S1806).

Here, if the conversation is not ended (step S1806: No), the information processing apparatus 101 returns to step S1704 shown in FIG. 17. On the other hand, if the conversation is to be ended (step S1806: Yes), the information processing apparatus 101 ends the series of processes according to this flowchart.

Thereby, among the steps (locations) in the talk script, the input information received at the step where the number of times the masking process has been requested in the past is equal to or greater than the threshold value can be masked and output as a log.

As described above, according to the information processing device 101 according to the second embodiment, input information received at the first location in association with the first location in the chatbot conversation is received, and , the number of times a masking processing request for the input information has been received can be recorded.

With this, it is possible to record operations to prevent input information from being logged, for example, the number of times the secret button 720 has been pressed, for locations where information is input in a chatbot conversation (steps in the script). .

Further, according to the information processing device 101, when input information accepted at the first point in a chatbot conversation is received from the information processing terminal 102, the received input information is subjected to masking processing based on the number of times it has been recorded. It can be determined whether the information is the target information or not. According to the information processing apparatus 101, when it is determined that the information is subject to masking processing, it is possible to perform masking processing in which the received input information is not recorded in a log or is concealed.

This allows us to determine whether the information entered at that location is subject to masking, considering how many operations have been performed in the past to prevent it from being recorded in the log. can do. Therefore, it is possible to prevent input information from being recorded in the log in areas where many users have performed operations to prevent it from being recorded in the log, without the user having to perform operations such as pressing the secret button 720. Become.

Further, according to the information processing apparatus 101, the information processing apparatus 101 can determine that the received input information is information to be subjected to masking processing when the number of times of recording is equal to or greater than a threshold value. Further, according to the information processing device 101, when the ratio of the number of times the input information input to the first location is recorded to the total number of times the input information is received is equal to or higher than the threshold value, the received input information is subject to masking processing. It can be determined that it is information.

This allows automatic setting of the off-the-record mode where information to be masked is input, taking into account the number and percentage of operations performed by other users to prevent them from being recorded in the log during the aggregation period. You can decide where to go.

(Embodiment 3)
Next, the information processing device 101 according to the third embodiment will be explained. In Embodiment 3, a case will be described in which a warning is given when input information received in a chatbot conversation includes personally identifying information. Note that portions similar to those described in Embodiments 1 and 2 are designated by the same reference numerals, and illustration and description thereof are omitted.

(Functional configuration example of information processing device 101)
First, an example of the functional configuration of the information processing apparatus 101 according to the third embodiment will be described using FIG. 19.

FIG. 19 is a block diagram showing an example of the functional configuration of information processing apparatus 101 according to the third embodiment. In FIG. 19, the information processing apparatus 101 includes a reception section 801, a conversation control section 802, a recording control section 803, and a determination section 1901. Specifically, for example, the reception unit 801 to the recording control unit 803 and the determination unit 1901 cause the CPU 201 to execute a program stored in a storage device such as the memory 202, the disk 204, or the portable recording medium 207 shown in FIG. This function is realized by the communication I/F 205 or by the communication I/F 205. The processing results of each functional unit are stored in a storage device such as the memory 202 or the disk 204, for example.

Hereinafter, among the functional units of the information processing apparatus 101 according to the third embodiment, parts that are different from the functional units of the information processing apparatus 101 according to the first embodiment will be explained.

When receiving input information accepted in a chatbot conversation from the information processing terminal 102, the determination unit 1901 determines whether the input information includes personal identification information. Here, the personal identification information is information that can identify an individual, and includes, for example, a last name, a first name, and an email address.

The determination as to whether or not the input information includes personal identification information is performed using, for example, a personal identification information master 2000 as shown in FIG. 20. Here, the contents stored in the personal identification information master 2000 will be explained. The personal identification information master 2000 is realized, for example, by a storage device such as the memory 202 and the disk 204 shown in FIG. 2.

FIG. 20 is an explanatory diagram showing an example of the storage contents of the personal identification information master 2000. In FIG. 20, a personal identification information master 2000 is dictionary information used to determine whether information that can identify an individual is included. The personal identification information master 2000 stores, for example, character strings such as surnames, first names, and domain names.

Specifically, for example, the determination unit 1901 analyzes the input information and determines that the input information includes personal identification information if the character string stored in the personal identification information master 2000 is included. For example, if the input information includes the character string "Sato", it is determined that the input information includes personal identification information.

When the determination unit 1901 determines that the input information includes personal identification information, the conversation control unit 802 outputs recommendation information for masking processing for information input in the chatbot conversation to the information processing terminal 102. Here, the recommendation information is a message, an icon, etc. for recommending implementation of masking processing.

Specifically, for example, in a chatbot conversation, the conversation control unit 802 sends recommendation information for masking processing to the information processing terminal in association with inquiry information regarding whether to permit recording of input information in a log. It is also possible to output the data to 102. The masking processing request is transmitted from the information processing terminal 102, for example, when an operation is performed on the information processing terminal 102 to disallow recording to a log in response to inquiry information.

Thereby, after input information including personal identification information is input, the user can select whether to perform masking processing on information input thereafter. Note that a specific example of recommendation information for masking processing that is output in association with inquiry information will be described later using FIG. 23.

Further, the determination unit 1901 may use the machine learning model M to determine whether a specific word is included in input information received in a chatbot conversation on the information processing terminal 102. Here, the specific word is, for example, a password, a credit card number, etc. The machine learning model M is a machine learning model for classifying whether an input character string is a specific word or not.

Specifically, for example, the determination unit 1901 performs morphological analysis on received input information (text data) and divides it into words. Next, the determining unit 1901 uses the machine learning model M to determine whether each divided word is a specific word. Then, when determining that at least one of the words is a specific word, the determining unit 1901 determines that the input information includes the specific word.

The machine learning model M is generated by machine learning such as deep learning, using, as learning data (teacher data), character string data to which a label indicating whether or not the word is a specific word is given, for example. To explain in more detail, for example, the machine learning model M can be generated by deep learning using an algorithm such as CNN or LSTM.

Note that CNN is an abbreviation for Convolutional Neural Network. LSTM is an abbreviation for Long Short-Term Memory. An example of generating the machine learning model M will be described later using FIG. 21. Further, an example of determining a specific word will be described later using FIG. 22.

The conversation control unit 802 may output alerting information to the information processing terminal 102 when the determination unit 1901 determines that the input information includes a specific word. Here, the alert information is a message, an icon, or the like for alerting the user to whether or not he/she is inputting important information. Specifically, for example, the conversation control unit 802 decides to output alerting information to the information processing terminal 102 in association with input information determined to include a specific word in a chatbot conversation. It's okay.

Furthermore, the conversation control unit 802 may receive new input information from the information processing terminal 102 regarding the input information determined to include a specific word. In this case, the conversation control unit 802 executes response processing based on new input information received from the information processing terminal 102. Furthermore, the conversation control unit 802 discards (deletes) input information that is determined to include a specific word, for example. That is, for input information determined to include a specific word, response processing is not executed and no log is recorded.

Further, the alert information may be information that recommends implementation of masking processing for input information determined to include a specific word. In this case, when the recording control unit 803 receives a request for masking processing of input information determined to include a specific word, when recording a log related to a conversation in the chatbot, the recording control unit 803 inputs the input information from the log related to the conversation Executes masking processing for the input information in the information-related log.

Note that a specific example of the alert information that is output when it is determined that the input information includes a specific word will be described later using FIG. 24.

(Example of generation of machine learning model M)
Next, an example of generating the machine learning model M will be described using FIG. 21. Here, a specific word will be explained using "password" as an example.

FIG. 21 is an explanatory diagram showing a specific example of learning data. In FIG. 21, learning data 2100 is a set of labeled teacher data (for example, teacher data 2100-1 to 2100-4). For example, the learning data 2100 includes teacher data regarding each character string of a character string group (reference numeral 2110 in FIG. 21) including a random character string group and an English word group.

The random character string group is a character string group that is assumed to be a password, and is, for example, a character string group that evenly includes arbitrary character strings of patterns 1 to 9 below. Example) is an example of a character string corresponding to each pattern.

Pattern 1: With numbers/with symbols/with uppercase letters, string length: 4-20
Example) w7mG$ijG

Pattern 2: With numbers/no symbols/no capital letters, string length: 4-20
Example) a0r37m6b

Pattern 3: No numbers/with symbols/no capital letters, string length: 4-20
Example) a. opi｜/$

Pattern 4: No numbers/no symbols/capital letters, string length: 4-20
Example) GqADkYwH

Pattern 5: With numbers/with symbols/no capital letters, string length: 4-20
Example) | m39) uk#

Pattern 6: With numbers/no symbols/with uppercase letters, string length: 4-20
Example) Dm3fGdQo

Pattern 7: With numbers/with symbols/no capital letters, string length: 4-20
Example) -z02;sm6

Pattern 8: No numbers/with symbols/with uppercase letters, string length: 4-20
Example) fz. Cs{! ～

Pattern 9: No numbers/no symbols/no capital letters, string length: 4-20
Example) miqmxyfi

The English word group is a character string group containing arbitrary English words. The random character string group and the English word group each include approximately several thousand character strings (for example, 7,000 to 8,000 characters).

Each character string (word) is represented by a vector representation (numeral 2120 in FIG. 21). For example, each character string is continuous data (character string data) in which vector data representing each character included in each character string is arranged in the order of appearance. Each character is represented, for example, by a 128-dimensional one-hot vector in which the column corresponding to the ASCII code of each character is "1" and the other columns are "0". ASCII is an abbreviation for American Standard Code for Information Interchange.

The label is information indicating whether the character string is a password (numeral 2130 in FIG. 21). Here, if the character string is a password, a label "0.0" is assigned. Further, if the character string is a non-password, a label "1.0" is assigned.

The determination unit 1901 generates a machine learning model M by, for example, forming an RNN/LSTM based on the learning data 2100, regarding the character string as time-series continuous data, and performing machine learning. The machine learning model M receives, for example, continuous data (array) of ASCII characters (vector representation) as input and outputs a value indicating the degree to which the data is a password.

The value indicating the degree to which the password is a password is expressed by a numerical value (decimal number) from 0 to 1. Here, the value indicating the degree of being a password is in the range from 0 to 1, and the higher the degree of being a password, the lower the value, and the lower the degree of being a password, the higher the value.

Here, an example of password determination will be described using FIG. 22. Here, the character string to be determined is "hVLVcaWf".

FIG. 22 is an explanatory diagram showing an example of password determination. In FIG. 22, continuous data 2200 is a vector representation of the character string "hVLVcaWf." Specifically, continuous data 2200 is vector data representing each character included in the character string "hVLVcaWf" arranged in the order of appearance.

For example, the character "h" included in the character string "hVLVcaWf" is represented by vector data in which the 104th column corresponding to the ASCII code is "1" and the other columns are "0". Further, the character "V" included in the character string "hVLVcaWf" is represented by vector data in which the 86th column corresponding to the ASCII code is "1" and the other columns are "0".

Here, it is assumed that as a result of inputting continuous data 2200 to machine learning model M, an output value "0.00001" is output. In this case, the determination unit 1901 determines that it is a password, for example, when the output value "0.00001" of the machine learning model M is less than the threshold value α. The threshold value α can be set arbitrarily, and is set to a value of about 0.5, for example. For example, if the threshold value α is “α=0.5”, the determination unit 1901 determines that the character string “hVLVcaWf” is a password because the output value “0.00001” is less than the threshold value α. .

(Specific example of recommendation information for masking processing)
Next, a specific example of recommendation information for masking processing that is output in association with inquiry information will be described using FIG. 23.

FIG. 23 is an explanatory diagram (part 3) showing an example of the chat screen. In FIG. 23, a chat screen 2300 is an example of an operation screen that displays a chatbot conversation on the information processing terminal 102. Here, similar to the chat screen 700 shown in FIG. 9, a case where some kind of consultation is performed using two-way communication in cooperation with a chatbot will be described as an example.

On the chat screen 2300, for example, a message can be input by selecting a box 2310 by a user's operation input using the input device 304 shown in FIG. Furthermore, by selecting a send button 2311 on the chat screen 2300, the message entered in the box 2310 can be sent to the chatbot side (information processing device 101).

Here, the chat screen 2300 displays messages m11 and m13 representing the utterances of the avatar av, and a message m12 representing the user's utterances. Message m11 is an example of a message prompting the user to input the user's name. The message m12 is an example of the name input for the message m1 of the avatar av. The message m13 is an example of a message that prompts the user to input consultation details.

Here, the user's name "Taro Sato" is input prior to inputting the content of the user's consultation. In this case, "Taro Sato" received in the chatbot conversation is transmitted from the information processing terminal 102 to the information processing apparatus 101 as input information. The determination unit 1901 refers to the personal identification information master 2000 and determines whether or not the input information “Taro Sato” includes personal identification information.

Here, since the input information "Taro Sato" includes "Sato" stored in the personal identification information master 2000, it is determined that the input information "Taro Sato" includes personal identification information. In this case, the conversation control unit 802 outputs masking processing recommendation information to the information processing terminal 102 in association with inquiry information regarding whether to permit recording of the input information in the log.

That is, when personally identifiable information is input in a chatbot conversation, the information input thereafter is recorded on the server (for example, the information processing device 101) in a state in which the individual can be identified. That will happen. Therefore, the information processing apparatus 101 recommends masking processing for information that will be input later in the chatbot conversation.

In the example of FIG. 23, a recommendation message 2330 is displayed in association with a secret button 2320 on the chat screen 2300. The secret button 2320 is an example of inquiry information regarding whether to permit recording of input information in a log. The recommendation message 2330 is an example of recommendation information for masking processing.

According to the recommendation message 2330, if the user presses the secret button 2320, the user can understand that the input information will not be recorded in the log. For example, assume that the user selects the secret button 2320 on the chat screen 2300 because he does not want to record his consultation details in the log. In this case, an off-the-record setting instruction is transmitted from the information processing terminal 102 to the information processing apparatus 101, and off-the-record mode is set (ON).

(Specific example of alert information)
Next, a specific example of the alert information that is output when it is determined that the input information includes a specific word will be described using FIG. 24.

FIG. 24 is an explanatory diagram (Part 4) showing an example of the chat screen. In FIG. 24, a chat screen 2400 is an example of an operation screen that displays a chatbot conversation on the information processing terminal 102. Here, similar to the chat screen 700 shown in FIG. 9, a case where some kind of consultation is performed using two-way communication in cooperation with a chatbot will be described as an example.

Here, the chat screen 2400 displays messages m21 and m23 representing comments made by the avatar av, and a message m22 representing comments made by the user. Here, it is assumed that the content of the user's consultation is input into the box 2410 and the send button 2411 is selected in response to the message m23 of the avatar AV.

In this case, the content of the consultation input in box 2410 is transmitted from information processing terminal 102 to information processing apparatus 101 as input information. The determination unit 1901 divides the input information (consultation content) into words, and uses the machine learning model M to determine whether each divided word includes a password.

For example, if a part of the consultation content entered in box 2410 is ``By the way, the password is hVLVcaWf.'', the words ``by the way'', ``password'', ``ha'', ``hVLVcaWf'', ``desu'', and ``. ”. Then, the word "hVLVcaWf" is determined to be a password.

In this case, the conversation control unit 802 outputs the alerting information to the information processing terminal 102 in association with the input information determined to include the password. For example, in a conversation with a chatbot, if a sentence that includes a password is input as part of the user's consultation, the system alerts the user to make sure they are not entering important information, as it is possible that the password was entered by mistake.

In the example of FIG. 24, alert information 2430 is displayed on chat screen 2400 in association with secret button 2420 provided next to box 2410. The secret button 2420 is an example of inquiry information regarding whether to permit recording of input information in a log. The alert information 2430 is an example of information that alerts the user to whether important information is being input and recommends that masking processing be performed on the input information.

According to the alert information 2430, the user can confirm whether or not he/she has inputted important information. For example, if the user realizes that he or she has entered the password by mistake, the user can re-enter the consultation details in box 2410 and select the send button 2411 to send new input information from the information processing terminal 102. It can be transmitted to the information processing device 101.

In this case, the conversation control unit 802 executes response processing based on new input information received from the information processing terminal 102. Furthermore, the conversation control unit 802 discards input information that is determined to include a password. Further, the recording control unit 803 does not record input information determined to include a password in the log.

Furthermore, if the user determines that there is no problem even if the password is included, the input information can be confirmed by selecting the send button 2411 again, for example, without re-entering the consultation details. In this case, response processing based on input information including the password is executed.

Further, by selecting the secret button 2420 and then selecting the send button 2411 again, the user can confirm the input information and set (ON) the off-the-record mode. In this case, when recording a log related to a chatbot conversation, a masking process is performed on the input information.

(Conversation control processing procedure of information processing device 101)
Next, a conversation control processing procedure of the information processing apparatus 101 according to the third embodiment will be explained. First, the first conversation control processing procedure of the information processing apparatus 101 according to the third embodiment will be described using FIGS. 25 and 26. In the first conversation control process, if the input information received in the chatbot conversation includes personal identification information, a masking process is recommended.

25 and 26 are flowcharts illustrating an example of the first conversation control processing procedure of the information processing apparatus 101 according to the third embodiment. In the flowchart of FIG. 25, first, the information processing apparatus 101 determines whether a chat start instruction has been received from the information processing terminal 102 (step S2501).

Here, the information processing apparatus 101 waits to receive a chat start instruction (step S2501: No). When the information processing apparatus 101 receives a chat start instruction (step S2501: Yes), the information processing apparatus 101 refers to the script table 130 and determines the script corresponding to the service ID included in the received chat start instruction as a talk script. (Step S2502).

Then, the information processing apparatus 101 starts a chatbot conversation on the information processing terminal 102 using the determined talk script (step S2503). At this time, the information processing apparatus 101 outputs to the information processing terminal 102 inquiry information regarding whether to permit recording of the input information in the log. The inquiry information is, for example, the secret button 2320 shown in FIG. 23.

Next, the information processing apparatus 101 determines whether personal identification information has been input in the chatbot conversation (step S2504). Here, if the personal identification information has not been input (step S2504: No), the information processing apparatus 101 moves to step S2506.

On the other hand, if the personal identification information has been input (step S2504: Yes), the information processing device 101 associates the input information with inquiry information regarding whether to permit recording of the input information in the log in the chatbot conversation. , outputs recommendation information for the masking process to the information processing terminal 102 (step S2505).

Next, the information processing apparatus 101 determines whether an off-the-record setting instruction has been received from the information processing terminal 102 (step S2506). Here, if the off-the-record setting instruction has not been received from the information processing terminal 102 (step S2506: No), the information processing apparatus 101 moves to step S2601 shown in FIG. 26.

On the other hand, if the off-the-record setting instruction is received from the information processing terminal 102 (step S2506: Yes), the information processing apparatus 101 turns on the off-the-record mode (step S2507), and proceeds to step S2601 shown in FIG. 26.

In the flowchart of FIG. 26, first, the information processing apparatus 101 determines whether input information accepted in a chatbot conversation is received from the information processing terminal 102 (step S2601). Here, if input information has not been received (step S2601: No), the information processing apparatus 101 moves to step S2609.

On the other hand, when input information is received (step S2601: Yes), the information processing apparatus 101 executes response processing based on the received input information (step S2602). Next, the information processing apparatus 101 determines whether the off-the-record mode is ON (step S2603).

Here, if the off-the-record mode is ON (step S2603: Yes), the information processing apparatus 101 performs masking processing on the received input information, and outputs a chat log with the input information masked (step S2604). Then, the information processing apparatus 101 turns off the off-the-record mode (step S2605), and proceeds to step S2607.

On the other hand, if the off-the-record mode is OFF (step S2603: No), the information processing apparatus 101 outputs a chat log including the received input information (step S2606). The information processing apparatus 101 then determines whether the received input information includes personal identification information (step S2607).

Here, if the input information does not include personal identification information (step S2607: No), the information processing apparatus 101 moves to step S2609. On the other hand, if the input information includes personal identification information (step S2607: Yes), the information processing apparatus 101 records that the personal identification information has been input (step S2608).

The information processing apparatus 101 then determines whether to end the chatbot conversation on the information processing terminal 102 (step S2609). Here, if the conversation is not ended (step S2609: No), the information processing apparatus 101 returns to step S2504 shown in FIG. 25. On the other hand, if the conversation is to be ended (step S2609: Yes), the information processing apparatus 101 ends the series of processes according to this flowchart.

Thereby, if the input information received in the chatbot conversation on the information processing terminal 102 includes personal identification information, it is possible to recommend that information input later in the chatbot conversation be masked.

Next, the second conversation control processing procedure of the information processing apparatus 101 according to the third embodiment will be explained using FIG. 27. In the second conversation control process, if the input information received in the chatbot conversation includes a password, alerting information is output. Further, in FIG. 27, a description of the process of recording a log related to a chatbot conversation is omitted.

FIG. 27 is a flowchart illustrating an example of the second conversation control processing procedure of the information processing apparatus 101 according to the third embodiment. In the flowchart of FIG. 27, first, the information processing apparatus 101 determines whether a chat start instruction has been received from the information processing terminal 102 (step S2701).

Here, the information processing apparatus 101 waits to receive a chat start instruction (step S2701: No). When the information processing apparatus 101 receives a chat start instruction (step S2701: Yes), the information processing apparatus 101 refers to the script table 130 and determines the script corresponding to the service ID included in the received chat start instruction as a talk script. (Step S2702).

Then, the information processing apparatus 101 starts a chatbot conversation on the information processing terminal 102 using the determined talk script (step S2703). At this time, the information processing apparatus 101 may output to the information processing terminal 102 inquiry information regarding whether or not to permit recording of the input information in the log. The inquiry information is, for example, the secret button 2420 shown in FIG. 24.

Next, the information processing apparatus 101 determines whether input information accepted in the chatbot conversation is received from the information processing terminal 102 (step S2704). Here, if input information has not been received (step S2704: No), the information processing apparatus 101 moves to step S2711.

On the other hand, when input information is received (step S2704: Yes), the information processing apparatus 101 executes password detection processing for the received input information (step S2705). The password detection process is a process that uses the machine learning model M to detect a password included in input information.

Next, the information processing apparatus 101 determines whether a password has been detected (step S2706). Here, if a password is not detected (step S2706: No), the information processing apparatus 101 executes response processing based on the received input information (step S2707), and proceeds to step S2711.

On the other hand, if a password is detected (step S2706: Yes), the information processing apparatus 101 outputs alert information to the information processing terminal 102 (step S2708). The information processing apparatus 101 then determines whether new input information has been received from the information processing terminal 102 for the input information for which the password has been detected (step S2709).

Here, if new input information has not been received (step S2709: No), the information processing apparatus 101 moves to step S2707. On the other hand, when new input information is received (step S2709: Yes), the information processing apparatus 101 executes response processing based on the received new input information (step S2710).

The information processing apparatus 101 then determines whether to end the chatbot conversation on the information processing terminal 102 (step S2711). Here, if the conversation is not ended (step S2711: No), the information processing apparatus 101 returns to step S2704. On the other hand, if the conversation is to be ended (step S2711: Yes), the information processing apparatus 101 ends the series of processes according to this flowchart.

As a result, when a password is included in the input information received in a chatbot conversation, it is possible to alert the user to whether the password has been entered incorrectly.

As described above, according to the information processing apparatus 101 according to the third embodiment, when input information accepted in a chatbot conversation is received from the information processing terminal 102, whether the input information includes personally identifying information or not. It can be determined whether or not. According to the information processing device 101, if it is determined that personally identifying information is included, it is possible to output to the information processing terminal 102 information that recommends masking processing for information input in a chatbot conversation.

Thereby, if the input information received in the chatbot conversation on the information processing terminal 102 includes personal identification information, it is possible to recommend that information input later in the chatbot conversation be masked. For example, once personally identifiable information is entered, any information entered thereafter will be recorded in a log in a manner that allows the individual to be identified. Therefore, when personally identifiable information is input, masking processing is recommended for information input after that.

Further, according to the information processing device 101, a machine learning model (M) for classifying whether an input character string is a specific word or not is used in a chatbot conversation on the information processing terminal 102. It is possible to determine whether or not the received input information includes a specific word. According to the information processing device 101, when it is determined that the input information includes a specific word, the information processing device 101 can output alert information to the information processing terminal 102.

As a result, when input information received in a chatbot conversation includes a specific word such as a password, it is possible to alert the user to whether unnecessary information is being input by mistake.

For these reasons, according to the information processing apparatus 101 according to the first to third embodiments, it is possible to smoothly utilize a service using a chatbot. Embodiments 1 to 3 may be combined without contradiction. For example, the information processing apparatus 101 according to the first embodiment may have the functions of the information processing apparatus 101 according to the second embodiment and the functions of the information processing apparatus 101 according to the third embodiment.

Note that the conversation control method described in this embodiment can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. This conversation control program is recorded on a computer-readable recording medium such as a hard disk, flexible disk, CD-ROM, DVD, or USB memory, and is executed by being read from the recording medium by the computer. Further, this conversation control program may be distributed via a network such as the Internet.

Further, the information processing device 101 described in this embodiment can also be realized by a specific application IC such as a standard cell or a structured ASIC (Application Specific Integrated Circuit), or a PLD (Programmable Logic Device) such as an FPGA.

Regarding the embodiments described above, the following additional notes are further disclosed.

(Additional Note 1) Receive input information accepted in a chatbot conversation from an information processing terminal, and execute response processing based on the input information,
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. ,
A conversation control program that causes a computer to perform processing.

(Supplementary note 2) causing the computer to execute a process of outputting inquiry information to the information processing terminal as to whether or not to permit recording of input information in a log in a conversation with the chatbot;
A supplementary note characterized in that the masking processing request is sent from the information processing terminal when an operation to disallow recording to a log is performed in response to the inquiry information on the information processing terminal. 1. The conversation control program described in 1.

(Additional Note 3) In association with the first part of the conversation in the chatbot, the input information accepted at the first part is received, and the number of times a masking processing request for the input information is received is recorded. ,
When input information accepted at the first location in the conversation in the chatbot is received from an information processing terminal, whether or not the received input information is information to be subjected to masking processing based on the recorded number of times. determine whether
performing a masking process of not recording the received input information in a log or concealing the received input information when it is determined that the information is subject to the masking process;
The conversation control program according to supplementary note 1, which causes the computer to execute the process.

(Additional note 4) The process for determining the above is
If the number of recorded times is equal to or greater than a threshold value, or if the ratio of the number of times to the total number of times the input information inputted to the first location is received is equal to or greater than a threshold value, the input information received is The conversation control program according to appendix 3, characterized in that the conversation control program determines that the information is to be subjected to the masking process.

(Additional note 5) When input information accepted in a chatbot conversation is received from an information processing terminal, it is determined whether or not the input information includes personally identifying information,
If it is determined that the personally identifying information is included, outputting information to the information processing terminal that recommends masking processing for the information input in the chatbot conversation;
The conversation control program according to supplementary note 1, which causes the computer to execute the process.

(Additional note 6) In the conversation with the chatbot, the computer performs a process of outputting the recommended information to the information processing terminal in association with inquiry information regarding whether to permit recording of input information in a log. run it,
A supplementary note characterized in that the masking processing request is sent from the information processing terminal when an operation to disallow recording to a log is performed in response to the inquiry information on the information processing terminal. 5. The conversation control program described in 5.

(Additional Note 7) Using a machine learning model to classify whether an input character string is a specific word or not, we will use a machine learning model to classify whether the input character string is a specific word or not. Determine whether it is included,
If it is determined that the input information includes the specific word, outputting alert information to the information processing terminal;
The conversation control program according to supplementary note 1, which causes the computer to execute the process.

(Additional Note 8) The machine learning model uses the string data that has been given a label indicating that it is the specific word, and the string data that has been given a label that indicates that it is not the specific word, as training data. The conversation control program according to appendix 7, wherein the conversation control program is generated by performing machine learning as follows.

(Additional Note 9) Receive input information accepted in a chatbot conversation from an information processing terminal, and execute response processing based on the input information,
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. ,
A conversation control method characterized in that processing is executed by a computer.

(Additional Note 10) When input information accepted in a chatbot conversation is received from an information processing terminal, a conversation control unit that executes a response process based on the input information;
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. a recording control unit;
An information processing device comprising:

100 Conversation control system 101 Information processing device 102 Information processing terminal 103 Administrator terminal 110 Network 120 FAQ master 130 Script table 140 Chat log DB
200,300 Bus 201,301 CPU
202,302 Memory 203 Disk Drive 204 Disk 205,305 Communication I/F
206 Portable recording medium I/F
207 Portable recording medium 303 Display 304 Input device 306 Camera 307 Speaker 308 Microphone 309 GPS unit 700, 2300, 2400 Chat screen 801 Reception section 802 Conversation control section 803 Recording control section 1301 Counting section 1400 Number of times counter table 1901 Judgment section 2000 Individual identification Information Master 2100 Learning Data

Claims (13)

Receive input information accepted in a chatbot conversation from an information processing terminal, execute response processing based on the input information,
receiving input information received at the first location in association with a first location in the conversation in the chatbot, and recording the number of times a masking processing request for the input information has been received;
When input information accepted at the first location in the conversation in the chatbot is received from an information processing terminal, whether or not the received input information is information to be subjected to masking processing based on the recorded number of times. determine whether
When it is determined that the information is subject to the masking process, when recording a log related to the conversation in the chatbot, masking that does not record the received input information in the log or conceals the received input information in the log related to the conversation. execute the process,
A conversation control program that causes a computer to perform processing. If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. ,
The conversation control program according to claim 1, which causes the computer to execute the process. causing the computer to execute a process of outputting inquiry information to the information processing terminal as to whether or not to permit recording of input information in a log in a conversation with the chatbot;
Claim characterized in that the masking processing request is sent from the information processing terminal when an operation to disallow recording to a log is performed in response to the inquiry information at the information processing terminal. The conversation control program according to item 2. When input information accepted in a chatbot conversation is received from an information processing terminal, determining whether or not the input information includes personally identifying information,
If it is determined that the personally identifying information is included, outputting information to the information processing terminal that recommends masking processing for the information input in the chatbot conversation;
The conversation control program according to claim 2 or 3, which causes the computer to execute the process. Using a machine learning model to classify whether an input string of characters is a specific word, it is possible to determine whether the specific word is included in the input information received in a chatbot conversation on an information processing terminal. determine whether
If it is determined that the input information includes the specific word, outputting alert information to the information processing terminal;
The conversation control program according to any one of claims 2 to 4, which causes the computer to execute the processing. Receive input information accepted in a chatbot conversation from an information processing terminal, execute response processing based on the input information,
When the input information is received, determining whether the input information includes personally identifying information,
If it is determined that the personally identifying information is included, outputting information to the information processing terminal that recommends masking processing for the information input in the chatbot conversation;
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. ,
A conversation control program that causes a computer to perform processing. Receive input information accepted in a chatbot conversation from an information processing terminal, execute response processing based on the input information,
Determining whether the input information includes the specific word using a machine learning model for classifying whether the input character string is a specific word,
If it is determined that the input information includes the specific word, outputting alert information to the information processing terminal;
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. ,
A conversation control program that causes a computer to perform processing. Receive input information accepted in a chatbot conversation from an information processing terminal, execute response processing based on the input information,
receiving input information received at the first location in association with a first location in the conversation in the chatbot, and recording the number of times a masking processing request for the input information has been received;
When input information accepted at the first location in the conversation in the chatbot is received from an information processing terminal, whether or not the received input information is information to be subjected to masking processing based on the recorded number of times. determine whether
When it is determined that the information is subject to the masking process, when recording a log related to the conversation in the chatbot, masking that does not record the received input information in the log or conceals the received input information in the log related to the conversation. execute the process,
A conversation control method characterized in that processing is executed by a computer. Receive input information accepted in a chatbot conversation from an information processing terminal, execute response processing based on the input information,
When the input information is received, determining whether the input information includes personally identifying information,
If it is determined that the personally identifying information is included, outputting information to the information processing terminal that recommends masking processing for the information input in the chatbot conversation;
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. ,
A conversation control method characterized in that processing is executed by a computer. Receive input information accepted in a chatbot conversation from an information processing terminal, execute response processing based on the input information,
Determining whether the input information includes the specific word using a machine learning model for classifying whether the input character string is a specific word,
If it is determined that the input information includes the specific word, outputting alert information to the information processing terminal;
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. ,
A conversation control method characterized in that processing is executed by a computer. a conversation control unit that executes a response process based on the input information when input information accepted in a chatbot conversation is received from an information processing terminal;
a counter that receives input information received at the first location in association with a first location in the conversation in the chatbot, and records the number of times a masking processing request for the input information has been received;
When input information accepted at the first point in the conversation in the chatbot is received from an information processing terminal, the received input information is information to be subjected to masking processing based on the number of times recorded by the counting unit. If it is determined that the information is subject to the masking process, when recording a log related to the conversation in the chatbot, the input information received from the log related to the conversation is a recording control unit that performs masking processing to not record in the log or to conceal it;
An information processing device comprising: a conversation control unit that executes a response process based on the input information when input information accepted in a chatbot conversation is received from an information processing terminal;
a determination unit that determines whether personal identification information is included in the input information when the input information is received;
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. a recording control unit;
has
The conversation control unit includes:
Information processing characterized in that when the determination unit determines that the personal identification information is included, information that recommends masking processing for information input in the conversation in the chatbot is output to the information processing terminal. Device. a conversation control unit that executes a response process based on the input information when input information accepted in a chatbot conversation is received from an information processing terminal;
a determination unit that determines whether the input information includes the specific word using a machine learning model for classifying whether the input character string is a specific word;
If a request for masking processing of the input information is received, when recording a log related to the conversation in the chatbot, perform a masking process to not record or conceal the log related to the input information among the logs related to the conversation. a recording control unit;
has
The conversation control unit includes:
An information processing apparatus characterized in that when the determination unit determines that the input information includes the specific word, the information processing apparatus outputs attention-calling information to the information processing terminal.

Images