JP2021076674A - Information processor, method for controlling voice chat, and voice chat control program - Google Patents

Abstract

To provide an information processor, a method for controlling a voice chat, and a voice chat control program that can suppress careless mistakes caused by drowsiness.SOLUTION: An information processor 100 includes a determination unit 133 and a changing unit 134. The determination unit 133 determines whether a user is feeling drowsiness on the basis of a chat bot 131 for issuing a question to a user by a voice chat and receiving an answer and information on conversations with the user. The changing unit 134 changes characteristics of the voice of the chat bot 131 if the determination unit has determined that the user is feeling drowsiness.SELECTED DRAWING: Figure 1

Description

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

In support operations at support centers and the like, replies to customers by e-mail or the like are performed. In replying to e-mails, etc., the person in charge checks in pairs in order to prevent mistakes such as problems with the contents of the e-mail, misdelivery, and misattachment of attached materials. In such a check process, a check error may occur due to a decrease in concentration or fatigue in midnight work or all-night work by a two-shift system. Further, an electronic device capable of preventing erroneous operation when drowsiness is detected has been proposed.

Japanese Unexamined Patent Publication No. 2016-6957

When replying to an e-mail or the like, it is conceivable that one of the pairs is replaced with a chatbot and the check is performed by voice chat, while the person in charge checks in pairs. However, the chatbot treats, for example, when the person in charge is sleepy, that the check is completed if there is an answer even if the person responds appropriately to the question. For this reason, the person in charge may perform the check while sleeping, and careless mistakes may occur.

One aspect is to provide an information processing device, a voice chat control method, and a voice chat control program capable of suppressing careless mistakes due to drowsiness.

In one aspect, the information processing apparatus has a determination unit and a change unit. The determination unit determines whether or not the user is drowsy based on the chatbot that asks a question by voice chat with the user and accepts the answer and the information regarding the dialogue with the user. When it is determined that the user is drowsy, the changing unit changes the voice characteristics of the chatbot.

Careless mistakes due to drowsiness can be suppressed.

FIG. 1 is a block diagram showing an example of the configuration of the information processing apparatus of the embodiment. FIG. 2 is a diagram showing an example of a check item storage unit. FIG. 3 is a diagram showing an example of a response time table storage unit. FIG. 4 is a flowchart showing an example of the voice chat control process of the embodiment. FIG. 5 is a diagram showing an example of a computer that executes a voice chat control program.

Hereinafter, examples of the information processing device, the voice chat control method, and the voice chat control program disclosed in the present application will be described in detail based on the drawings. The disclosed technology is not limited by the following examples. In addition, the following examples may be appropriately combined as long as they do not contradict each other.

FIG. 1 is a block diagram showing an example of the configuration of the information processing apparatus of the embodiment. In the information processing device 100, for example, a chatbot that performs a voice chat with a user who is in charge of the support center is operating, and the chatbot asks a question with the user by voice chat and receives an answer. The information processing device 100 determines whether or not the user is drowsy based on the information regarding the chatbot and the dialogue with the user. When the information processing device 100 determines that the user is drowsy, the information processing device 100 changes the voice characteristics of the chatbot. As a result, the information processing device 100 can suppress careless mistakes due to drowsiness.

As shown in FIG. 1, the information processing device 100 includes a communication unit 110, a display unit 111, an operation unit 112, an input / output unit 113, a storage unit 120, and a control unit 130. In addition to the functional units shown in FIG. 1, the information processing device 100 may have various functional units of a known computer, for example, various functional units such as various input devices and audio output devices.

The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is a communication interface that is connected to another information processing device by wire or wirelessly via a network (not shown) and controls information communication with the other information processing device. The communication unit 110 receives check item data from, for example, another information processing device. The communication unit 110 outputs the received check item data to the control unit 130.

The display unit 111 is a display device for displaying various types of information. The display unit 111 is realized by, for example, a liquid crystal display or the like as a display device. The display unit 111 displays various screens such as a display screen input from the control unit 130.

The operation unit 112 is an input device that receives various operations from the user of the information processing device 100. The operation unit 112 is realized by, for example, a keyboard, a mouse, or the like as an input device. The operation unit 112 outputs the operation input by the user to the control unit 130 as operation information. The operation unit 112 may be realized by a touch panel or the like as an input device, or the display device of the display unit 111 and the input device of the operation unit 112 may be integrated.

The input / output unit 113 has a microphone terminal and a headphone terminal, and a headset worn by the user of the information processing device 100 is connected to the input / output unit 113. The input / output unit 113 converts the voice signal input from the user's headset into voice data and outputs it to the control unit 130. Further, the input / output unit 113 converts the voice data input from the control unit 130 into a voice signal and outputs the voice data to the user's headset.

The storage unit 120 is realized by, for example, a RAM (Random Access Memory), a semiconductor memory element such as a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 has a check item storage unit 121 and a response time table storage unit 122. Further, the storage unit 120 stores information used for processing in the control unit 130.

The check item storage unit 121 stores, for example, check items in the checklist at the time of sending an e-mail. FIG. 2 is a diagram showing an example of a check item storage unit. As shown in FIG. 2, the check item storage unit 121 has items such as "question No.", "check item", and "answer". Further, the "answer" further includes items such as "Yes" and "No".

"Question No." is an identifier that identifies a question in the checklist, that is, a check item. The "check item" is information indicating the content of the question in the checklist. "Yes" in the "Answer" column indicates the next question No. when the user's answer to the check item is Yes. This is information indicating. "No" in the "Answer" column indicates the next question No. when the user's answer to the check item is No. This is information indicating. For example, question No. When the user answers "Yes" to the chatbot question "Does the domain match the customer name?" Of the check item "2", the question No. Move to "3". On the other hand, when the user answers "No" to the question, the question No. Move to "2-1". That is, "Yes" and "No" in the "answer" column are information indicating to the user the next question according to the answer. In addition, the "answer" column may have an item when the question is not applicable.

Returning to the description of FIG. 1, the answer time table storage unit 122 stores the average value of the answer time for each question and the threshold value in association with each other. FIG. 3 is a diagram showing an example of a response time table storage unit. As shown in FIG. 3, the answer time table storage unit 122 has items such as "question No.", "average value of answer time", and "threshold value".

"Question No." is an identifier that identifies a question in the checklist, that is, a check item. The "average answer time" is information representing the average value of the past answer time for each question in seconds. The "threshold value" is a threshold value for detecting a case where the user's response time is long for a chatbot question, and is information representing an offset value with respect to an average value of the response time in seconds. For example, question No. In "1", the first time, which is the detection criterion when the user's response time is long, is set to the average value of the response time + threshold value = 5 seconds + 1 second = 6 seconds. The "threshold value" may be stored with the first time as the threshold value. Further, the first time may be corrected by using the correction value α representing the difference for each individual user.

Returning to the description of FIG. 1, in the control unit 130, for example, a program stored in an internal storage device is executed by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like using the RAM as a work area. It is realized by. Further, the control unit 130 may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

The control unit 130 includes a chatbot 131, a calculation unit 132, a determination unit 133, a change unit 134, and a generation unit 135, and realizes or executes an information processing function or operation described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 1, and may be another configuration as long as it is a configuration for performing information processing described later.

The chatbot 131 performs voice chat with the user and checks the checklist in a format in which the user answers the question of the chatbot. The chatbot 131 refers to the check item storage unit 121, and according to the scenario of the question, the question No. Questions are asked in order from "1", and the next question is moved according to the user's answer. The chatbot 131 outputs the voice data of the voice chat to the calculation unit 132 and the generation unit 135. Further, when an instruction to change the voice characteristics is input from the changing unit 134, the chatbot 131 changes the voice characteristics according to the instruction.

The calculation unit 132 detects the question end time of the chatbot 131 and the answer end time of the user based on the voice data input from the chatbot 131. The calculation unit 132 calculates the answer time by calculating the difference between the question end time of the chatbot 131 and the answer end time of the user. The calculation unit 132 outputs the calculated response time to the determination unit 133. Further, the calculation unit 132 stores the calculated response time as a history in the storage unit 120.

The determination unit 133 refers to, for example, the RTC (Real Time Clock) or HPET (High Precision Event Timer) of the information processing apparatus 100 and acquires the current time. The determination unit 133 determines whether or not the acquired current time is in a preset midnight time zone. The midnight time zone can be, for example, from 22:00 to 5:00 the next day. When the determination unit 133 determines that it is in the midnight time zone, it determines that the user is drowsy. When the determination unit 133 determines that the user is drowsy, the determination unit 133 outputs the first change instruction to the change unit 134 and proceeds to determine the response time. On the other hand, when the determination unit 133 determines that it is not in the midnight time zone (however, since drowsiness may occur after lunch even in the daytime, the time zone in which drowsiness occurs can be set / changed / added by the user), the user. Judge that you are not drowsy. When the determination unit 133 determines that the user is not drowsy, the determination unit 133 proceeds to the determination of the response time without outputting the first change instruction to the change unit 134.

The determination unit 133 refers to the answer time table storage unit 122 for each question, and calculates the first time, which is a detection criterion when the answer time is long, based on the average value and the threshold value of the answer time. When the response time is input from the calculation unit 132, the determination unit 133 determines whether or not the input response time, that is, the current response time is longer than the first time. When the determination unit 133 determines that the current answer time is equal to or less than the first time, the determination unit 133 refers to the past answer time (not shown) stored in the storage unit 120 and calculates the average value of the answer times for each question. .. The determination unit 133 asks the corresponding question No. of the answer time table storage unit 122. The average value of the response time in the above is updated with the calculated average value, and a non-change instruction indicating that the voice characteristics are not changed is output to the change unit 134. On the other hand, when the determination unit 133 determines that the response time this time is longer than the first time, the determination unit 133 outputs a second change instruction to change the characteristics of the voice to the change unit 134.

When the first change instruction is input from the determination unit 133, the change unit 134 raises the pitch of the voice to the chatbot 131 higher than the normal time zone, that is, the time zone different from the midnight time zone. Instruct to change. For example, the changing unit 134 instructs the chatbot 131 to raise the scale by all notes in the midnight time zone as compared with the normal time zone.

When the second change instruction is input from the determination unit 133, the change unit 134 instructs the chatbot 131 to change the characteristics of the voice. The change unit 134 instructs, for example, to change one or more characteristics of pitch, speed, and volume as voice characteristics. For example, the changing unit 134 instructs the chatbot 131 to change from a male voice to a female voice, instruct the voice reproduction speed to be increased, or instruct the chatbot 131 to increase the volume. To do.

Further, the changing unit 134 changes the voice characteristics from the next question, for example, as a timing for changing the voice characteristics for the chatbot 131. The changing unit 134 may change the characteristics of the voice in the middle of the question. Further, the change unit 134 may insert another voice or music between the plurality of questions, that is, between the questions. Other voices and music include, for example, words that urge the user to wake up and one phrase of fast-paced music.

When a non-change instruction is input from the determination unit 133, the change unit 134 does not give an instruction to change the voice characteristics to the chatbot 131. The change unit 134 determines whether or not the check of all the questions has been completed after the second change instruction or the non-change instruction is input from the determination unit 133 and the operation for these instructions is performed. When it is determined that the check of all the questions has not been completed, the change unit 134 instructs the determination unit 133 to continue to determine the midnight time zone and the answer time. When it is determined that the check of all the questions is completed, the change unit 134 ends the voice chat control process.

When the voice data is input from the chatbot 131, the generation unit 135 transcribes the voice data and generates a checked check sheet in which the check contents are reflected. The generation unit 135 stores the generated checked check sheet in the storage unit 120. The generation unit 135 may obtain the contents of the check items by referring to the check item storage unit 121. Further, the generation unit 135 may print the checked check sheet using a printing device (not shown).

Next, the operation of the information processing apparatus of the embodiment will be described. FIG. 4 is a flowchart showing an example of the voice chat control process of the embodiment.

When the chatbot 131 starts the check by voice chat with the user, the determination unit 133 refers to the RTC or HPET and acquires the current time (step S1).

The determination unit 133 determines whether or not the acquired current time is in the midnight time zone (step S2). When the determination unit 133 determines that the time zone is midnight (step S2: Yes), the determination unit 133 determines that the user is drowsy and outputs the first change instruction to the change unit 134. When the first change instruction is input from the determination unit 133, the change unit 134 instructs the chatbot 131 to change the pitch of the voice higher than the normal time zone (step S3). ), Proceed to step S4. At this time, the chatbot 131 changes the voice characteristics according to the instruction for changing the voice characteristics input from the changing unit 134. On the other hand, when the determination unit 133 determines that it is not in the midnight time zone (step S2: No), the determination unit 133 proceeds to step S4 without outputting the first change instruction.

The chatbot 131 refers to the check item storage unit 121, asks a question by voice chat, and receives an answer to the question from the user. The chatbot 131 outputs the voice data of the voice chat to the calculation unit 132. The calculation unit 132 detects the question end time of the chatbot 131 and the answer end time of the user based on the voice data input from the chatbot 131 (step S4).

The calculation unit 132 calculates the answer time based on the question end time of the chatbot 131 and the answer end time of the user (step S5). The calculation unit 132 outputs the calculated response time to the determination unit 133.

When the response time is input from the calculation unit 132, the determination unit 133 determines whether or not the input current response time is longer than the first time (step S6). When the determination unit 133 determines that the current answer time is equal to or less than the first time (step S6: No), the determination unit 133 calculates the average value of the answer times for each question and the corresponding answer of the answer time table storage unit 122. Update the time average. Further, the determination unit 133 outputs a non-change instruction to the change unit 134 to the effect that the characteristics of the voice are not changed. When the non-change instruction is input from the determination unit 133, the change unit 134 does not give an instruction to change the voice characteristics to the chatbot 131, and proceeds to step S8.

On the other hand, when the determination unit 133 determines that the response time this time is longer than the first time (step S6: Yes), the determination unit 133 gives the change unit 134 a second change instruction to change the voice characteristics. Output. When the second change instruction is input from the determination unit 133, the change unit 134 instructs the chatbot 131 to change the characteristics of the voice (step S7), and proceeds to step S8. At this time, the chatbot 131 changes the voice characteristics according to the instruction for changing the voice characteristics input from the changing unit 134.

The change unit 134 determines whether or not the check of all the questions has been completed (step S8). When the change unit 134 determines that the check of all the questions has not been completed (step S8: No), the change unit 134 returns to step S1. When it is determined that the check of all the questions is completed (step S8: Yes), the change unit 134 ends the check process. As a result, the information processing device 100 can suppress careless mistakes due to drowsiness.

In this way, the information processing device 100 determines whether or not the user is drowsy based on the chatbot 131 that asks a question and receives an answer by voice chat with the user and the information regarding the dialogue with the user. To do. Further, when the information processing device 100 determines that the user is drowsy, the information processing device 100 changes the voice characteristics of the chatbot 131. As a result, careless mistakes due to drowsiness can be suppressed. That is, it is possible to urge the user to wake up when answering in a sleepy state.

Further, the information processing apparatus 100 stores an answer time table in which the average value of the answer time calculated based on the question end time of the chatbot 131 and the answer end time of the user and the threshold value are stored in association with each question. When the calculated response time is longer than the first time based on the average value and the threshold value with reference to the storage unit 122, it is determined that the user is drowsy, and as a result, the user's reaction time to the question is long. In some cases, it can be determined that the person is drowsy.

In addition, the characteristics of voice are one or more characteristics of pitch, speed, and volume. As a result, the user can be encouraged to wake up.

Further, when the information processing apparatus 100 determines that the user is drowsy, the information processing device 100 changes the characteristics of the voice from the next question or in the middle of the question. As a result, the user can be encouraged to wake up.

Further, when the information processing apparatus 100 determines that the user is drowsy, another voice or music is inserted between the plurality of questions. As a result, the user can be encouraged to wake up.

Further, the information processing device 100 acquires the current time as information related to the dialogue, and determines that the user is drowsy when the current time is a preset midnight time zone or a drowsiness occurrence time zone. Further, when the information processing apparatus 100 determines that the user is drowsy, the information processing device 100 changes the pitch of the voice of the chatbot 131 to be higher than that of a time zone different from the midnight time zone.

In the above embodiment, the check process is performed using voice chat, but the present invention is not limited to this. For example, it can be applied to a check process in which a question is displayed on a display screen and input such as "Y" or "N" from a keyboard or selection by a mouse or a touch panel is accepted. In this case, the user interferes with the check process by displaying the release button on the display screen when the response time is longer than the first time, and restarts the check process by accepting the operation of the release button. You may want to check that your five senses are working.

Further, in the above embodiment, the information processing apparatus 100 performs the operation of the chatbot and the voice chat control process, but the present invention is not limited to this. For example, the server may operate the chatbot and perform voice chat control processing so that the user calls the server to perform voice chat. In addition, the chatbot may run on another server.

Further, each component of each of the illustrated parts does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each part is not limited to the one shown in the figure, and all or part of them are functionally or physically distributed / integrated in arbitrary units according to various loads and usage conditions. Can be configured. For example, the determination unit 133 of the information processing device 100 and the change unit 134 may be integrated. Further, the illustrated processes are not limited to the above order, and may be performed simultaneously or in a different order as long as the processing contents do not contradict each other.

Further, the various processing functions performed by each device may execute all or any part thereof on the CPU (or a microcomputer such as an MPU or a MCU (Micro Controller Unit)). In addition, various processing functions may be executed in whole or in any part on a program analyzed and executed by a CPU (or a microcomputer such as an MPU or MCU) or on hardware by wired logic. Needless to say, it's good.

By the way, various processes described in each of the above embodiments can be realized by executing a program prepared in advance on a computer. Therefore, in the following, an example of a computer that executes a program having the same functions as those in each of the above embodiments will be described. FIG. 5 is a diagram showing an example of a computer that executes a voice chat control program.

As shown in FIG. 5, the computer 200 includes a CPU 201 that executes various arithmetic processes, an input device 202 that accepts data input, and a monitor 203. Further, the computer 200 includes a medium reading device 204 for reading a program or the like from a storage medium, an interface device 205 for connecting to various devices, and a communication device 206 for connecting to another information processing device or the like by wire or wirelessly. Has. Further, the computer 200 has a RAM 207 that temporarily stores various information and a hard disk device 208. Further, each of the devices 201 to 208 is connected to the bus 209.

The hard disk device 208 stores a voice chat control program having the same functions as the chatbot 131, the calculation unit 132, the determination unit 133, the change unit 134, and the generation unit 135 shown in FIG. Further, the hard disk device 208 stores the check item storage unit 121 and the response time table storage unit 122. The input device 202 receives, for example, input of various information such as operation information from a user of the computer 200. The monitor 203 displays various screens such as a display screen for the user of the computer 200, for example. For example, a headset, a printing device, or the like is connected to the interface device 205. The communication device 206 has, for example, the same function as the communication unit 110 shown in FIG. 1 and is connected to a network (not shown) to exchange various information with other information processing devices.

The CPU 201 performs various processes by reading out each program stored in the hard disk device 208, expanding the program in the RAM 207, and executing the program. Further, these programs can make the computer 200 function as the chatbot 131, the calculation unit 132, the determination unit 133, the change unit 134, and the generation unit 135 shown in FIG.

The voice chat control program does not necessarily have to be stored in the hard disk device 208. For example, the computer 200 may read and execute a program stored in a storage medium that can be read by the computer 200. The storage medium that can be read by the computer 200 is, for example, a portable recording medium such as a CD-ROM, a DVD (Digital Versatile Disc), or a USB (Universal Serial Bus) memory, a semiconductor memory such as a flash memory, a hard disk drive, or the like. .. Further, the voice chat control program may be stored in a device connected to a public line, the Internet, a LAN, or the like, and the computer 200 may read the voice chat control program from these and execute the program.

100 Information processing device 110 Communication unit 111 Display unit 112 Operation unit 113 Input / output unit 120 Storage unit 121 Check item storage unit 122 Answer time table storage unit 130 Control unit 131 Chatbot 132 Calculation unit 133 Judgment unit 134 Change unit 135 Generation unit

Claims (8)

A chatbot that asks questions by voice chat with the user and accepts answers, a determination unit that determines whether or not the user is drowsy based on information about the dialogue with the user, and a determination unit.
When it is determined that the user is drowsy, a change unit that changes the voice characteristics of the chatbot, and a change unit.
An information processing device characterized by having. The determination unit refers to a storage unit that stores the average value of the answer time calculated based on the question end time of the chatbot, the answer end time of the user, and the threshold value for each question. If the calculated response time is longer than the first time based on the average value and the threshold value, it is determined that the user is drowsy.
The information processing apparatus according to claim 1. The audio characteristic is one or more of pitch, speed, and volume.
The information processing apparatus according to claim 1 or 2. When it is determined that the user is drowsy, the change unit changes the characteristics of the voice from the next question or in the middle of the question.
The information processing apparatus according to any one of claims 1 to 3. The change unit inserts other voice or music between the plurality of questions when it is determined that the user is drowsy.
The information processing apparatus according to any one of claims 1 to 4. The determination unit acquires the current time as information regarding the dialogue, and if the current time is a preset midnight time zone or a drowsiness occurrence time zone, determines that the user is drowsy.
When it is determined that the user is drowsy, the changing unit changes the pitch of the chatbot voice higher than the time zone different from the midnight time zone.
The information processing apparatus according to claim 1. Based on the chatbot that asks questions and accepts answers by voice chat with the user and the information about the dialogue with the user, it is determined whether or not the user is drowsy.
If it is determined that the user is drowsy, the voice characteristics of the chatbot are changed.
A voice chat control method characterized by a computer performing processing. Based on the chatbot that asks questions and accepts answers by voice chat with the user and the information about the dialogue with the user, it is determined whether or not the user is drowsy.
If it is determined that the user is drowsy, the voice characteristics of the chatbot are changed.
A voice chat control program characterized by having a computer perform processing.

Images