JP2022129582A - Information processing system, operator terminal, and program - Google Patents

Abstract

To provide an information processing system, an operator terminal, and a program that enable an operator to efficiently grasp a customer's situation when a chat is handed over from an unmanned chat system to a manned chat system.SOLUTION: An information processing system includes a customer terminal for accepting an input from a customer, and an operator terminal for allowing an operator to make an input regarding a response to the customer in response to a customer's call from the customer terminal. When receiving the call, the operator terminal presents, to the operator, handover information generated based on a customer's input history to the customer terminal by the customer.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing system, an operator terminal, and a program.

In recent years, use of an unmanned chat system in which artificial intelligence (AI) automatically responds to inquiries from customers has been increasing. On the other hand, manned chat systems, in which operators respond to inquiries from customers, continue to be used because they are capable of providing detailed responses to customers.

For example, Patent Literature 1 below describes a chat system that combines an unmanned chat system and a manned chat system. According to Patent Document 1 below, it is possible to appropriately determine whether or not to switch a chat from an unmanned chat system to a manned chat system, and to appropriately select an operator who will take over the chat from the unmanned chat system.

JP 2020-95346 A

However, in the chat system described in Patent Literature 1, when the chat history becomes long, it becomes difficult for the operator who takes over the chat from the unmanned chat system to immediately grasp the customer's situation. .

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to enable an operator to efficiently check a customer's situation when a chat is handed over from an unmanned chat system to a manned chat system. To provide a new and improved information processing system, an operator terminal, and a program that can be grasped.

In order to solve the above problems, according to one aspect of the present invention, there are provided a customer terminal for receiving input from a customer, and an operator for inputting the response to the customer in response to a call from the customer terminal. and a terminal, wherein the operator terminal presents the operator with handover information generated based on the customer's input history to the customer terminal when the call is accepted. .

The customer terminal may accept the input from the customer by automatically responding to the customer's speech.

The input history may include a history of input or speech from the customer to the customer terminal.

The input history may include utterance content of the customer and a translation result of the utterance content into another language.

The input history may include information regarding the customer's emotions.

The takeover information may be generated based on the series of input histories by the customer prior to the call.

The takeover information may include information on the progress of input to the customer terminal by the customer.

In order to solve the above problems, according to another aspect of the present invention, in response to a call from a customer terminal that accepts input from a customer, an operator makes an input regarding the response to the customer, is received, an operator terminal is provided for presenting the operator with handover information generated based on the input history of the customer to the customer terminal.

In order to solve the above problems, according to another aspect of the present invention, a computer is provided with input related to customer service by an operator in response to a call from a customer terminal that accepts input from a customer. A program is provided which functions as an operator terminal for presenting the operator with handover information generated based on the input history of the customer to the customer terminal when the call is accepted.

As described above, according to the present invention, when a chat is handed over from an unmanned chat system to a manned chat system, it is possible for the operator to efficiently grasp the customer's situation.

1 is a schematic diagram showing the overall configuration of an information processing system according to one embodiment of the present invention; FIG. 3 is a block diagram showing the functional configuration of a customer terminal; FIG. 3 is a schematic diagram showing an example of the appearance of a customer terminal; FIG. FIG. 11 is a schematic diagram showing another example of the appearance of the customer terminal; 3 is a block diagram showing the functional configuration of a connection management terminal; FIG. 4 is a table showing an example of data included in an operation log registered in an input history DB of a connection management terminal; FIG. It is a block diagram which shows the function structure of an operator terminal. FIG. 10 is a diagram showing an example of an image presented to an operator as handover information; FIG. 4 is a table showing an example of data included in handover information presented to an operator; It is a schematic diagram which shows the example of an external appearance of an operator terminal. It is a figure which shows the example of an image displayed on a customer terminal. It is a figure which shows the example of an image displayed on an operator terminal. 4 is a sequence diagram illustrating a first operation example of the information processing system according to the same embodiment; FIG. FIG. 10 is a diagram illustrating generation of an operation log and an AI engine log in the first operation example; FIG. 7 is a sequence diagram illustrating a second operation example of the information processing system according to the same embodiment; FIG. 7 is a sequence diagram illustrating a second operation example of the information processing system according to the same embodiment; FIG. 11 is a diagram illustrating generation of an operation log and an AI engine log in the second operation example; FIG. 11 is a diagram illustrating generation of an operation log and an AI engine log in the second operation example; FIG. 11 is a diagram illustrating generation of an operation log and an AI engine log in the second operation example; A hardware configuration example of each terminal of the information processing system according to the embodiment will be described.

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In the present specification and drawings, constituent elements having substantially the same functional configuration are denoted by the same reference numerals, thereby omitting redundant description.

<1. Configuration of information processing system>
First, the overall configuration of an information processing system according to an embodiment of the present invention will be described with reference to FIGS. 1 to 12. FIG.

FIG. 1 is a schematic diagram showing the overall configuration of an information processing system 1 according to this embodiment. As shown in FIG. 1, an information processing system 1 includes a connection management terminal 300 and a plurality of operator terminals 200 arranged at a center site 20, a plurality of customer terminals 100 arranged at a customer site 10, and an application server 40. including.

A plurality of operator terminals 200 and a plurality of customer terminals 100 are connected via a communication network N1 such as the Internet. A plurality of operator terminals 200 and a plurality of customer terminals 100 can make voice calls to each other through so-called P2P (peer-to-peer) communication or data communication via a server or the like.

A plurality of customer terminals 100 and the application server 40 are connected via a communication network N2 such as the Internet or a LAN (Local Area Network). A plurality of customer terminals 100 and the application server 40 can transmit and receive data to and from each other.

In the information processing system 1 , a customer performs an input operation to the customer terminal 100 while being attended to by an AI chatbot installed in the customer terminal 100 . At this time, if the customer needs to be answered by an operator instead of the AI chatbot, the customer can receive an answer by a video call from the operator by performing call processing to the operator.

(Customer terminal 100)
FIG. 2 is a block diagram showing the functional configuration of the customer terminal 100. As shown in FIG. As shown in FIG. 2 , the customer terminal 100 includes a control section 120 , a microphone 111 , a speaker 112 , a camera 113 and a display input section 114 . The customer terminal 100 is installed at a customer base 10 such as a public facility, a transportation facility, or a store, and operated by a customer.

A microphone 111 picks up the customer's voice. The speaker 112 outputs voice based on the contents of the operator's speech transmitted from the operator terminal 200 . A camera 113 captures an image of the customer. The display input unit 114 is a touch panel or the like, and displays an image used for responding to a customer, and receives input from the customer to the customer terminal 100 through touching the display screen.

In the information processing system 1, customers are usually served by an image displayed on the display input unit 114 and an unmanned chatbot. However, if the customer wishes to respond to the customer by manned chat, the information processing system 1 can switch the response to the customer from the unmanned chatbot to an operator who operates the operator terminal 200 .

The control unit 120 controls overall operations of the customer terminal 100 . Specifically, control unit 120 includes voice recognition unit 121 , voice generation unit 122 , call function unit 123 , business application unit 124 , AI engine unit 125 , and emotion estimation unit 126 .

The voice recognition unit 121 recognizes the customer's voice picked up by the microphone 111, and recognizes the content of the customer's utterance or keywords included in the customer's utterance. Furthermore, the speech recognition unit 121 may translate the recognized customer's utterance into another language.

The voice generation unit 122 generates voice based on the contents of the operator's utterance transmitted from the operator terminal 200 . Specifically, when the voice itself uttered by the operator is not output from the speaker 112, the voice generation unit 122 generates synthesized voice that reads out the text of the utterance content of the operator. Alternatively, when the language spoken by the operator and the language spoken by the customer are different, the speech generation unit 122 may generate synthesized speech that reads out the text obtained by translating the content of the speech of the operator into the language spoken by the customer. The sound generated by the sound generator 122 is output from the speaker 112, for example.

The call function unit 123 realizes a video call between the customer terminal 100 and the operator terminal 200. FIG. Specifically, the call function unit 123 realizes a video call between the customer terminal 100 and the operator terminal 200 by P2P (peer-to-peer) communication or data communication via a network. For example, the call function unit 123 may transmit audio picked up by the microphone 111 , an image captured by the camera 113 , and an image displayed by the display input unit 114 to the operator terminal 200 . In addition, the call function unit 123 may receive voice or the like picked up by the microphone 211 from the operator terminal 200 .

The business application unit 124 controls the processing of responding to customers in the customer terminal 100 in cooperation with the application server 40 . Specifically, the business application unit 124 may generate an image to be displayed on the display input unit 114 and control the transition of the generated image to perform customer service processing. The response processing at the customer terminal 100 means, for example, executing processing such as information search, point inquiry, ticket issuance, or execution of various procedures by the customer.

The business application unit 124 may use an unmanned chatbot realized by the AI engine unit 125 to respond to customers. For example, the business application unit 124 may guide the customer to input data on the customer terminal 100 and provide data to the customer using an automatic response by an unmanned chatbot.

In addition, when the customer requests that an operator respond to a manned chat instead of the unmanned chatbot, the business application unit 124 transmits to the connection management terminal 300 a call requesting an operator to respond. may The connection management terminal 300 that receives the call requesting the operator to respond can transfer the call to an appropriate operator terminal 200, thereby allowing the operator to respond to the customer. In such a case, the response to the customer at the customer terminal 100 switches from unmanned chat by an unmanned chatbot to manned chat by an operator who operates the operator terminal 200 in response to a request from the customer.

The AI engine unit 125 implements the functions of an unmanned chatbot. Specifically, the AI engine unit 125 may respond to the customer operating the customer terminal 100 by an automatic response (unmanned chatbot) based on a predetermined rule or machine learning algorithm. For example, the AI engine unit 125 may make a preset utterance or the like based on a keyword included in the customer's utterance content or the customer's operation on the display input unit 114 . In addition, the AI engine unit 125 may make an utterance or the like using a machine learning algorithm based on the context of the customer's utterance content (so-called context).

The emotion estimation unit 126 estimates the emotion of the customer operating the customer terminal 100 . Specifically, the emotion estimation unit 126 may estimate the customer's emotion based on the customer's facial expression captured by the camera 113, the customer's voice picked up by the microphone 111, or the like. For example, the emotion estimator 126 may estimate whether the customer's emotion is positive or negative, and the degree to which the customer's emotion is positive or negative. Information about the customer's emotion estimated by the emotion estimation unit 126 may be presented as handover information to an operator who takes over the customer's service from the unmanned chatbot, for example.

FIG. 3 is a schematic diagram showing an example of the appearance of the customer terminal 100. As shown in FIG. The customer terminal 100 may be, for example, a stationary terminal 100A such as a KIOSK terminal or a signage terminal as shown in FIG. The stationary terminal 100A is provided with a microphone 111, a speaker 112, a camera 113, and a display input unit 114 such as a touch panel.

FIG. 4 is a schematic diagram showing another example of the appearance of the customer terminal 100. As shown in FIG. The customer terminal 100 may be a mobile terminal 100B such as a smart phone, a tablet terminal, or a touch panel PC (Personal Computer) as shown in FIG. A notebook PC or the like can also be used as the mobile terminal 100B. The portable terminal 100B is provided with a microphone 111, a speaker 112, a camera 113, and a display input unit 114 such as a touch panel.

(Application server 40)
The application server 40 controls the process of responding to customers in the customer terminal 100 in cooperation with the business application unit 124 . Specifically, the application server 40 may perform processing such as information retrieval, point inquiry, ticket issuance, or execution of various procedures based on the customer's input.

(Connection management terminal 300)
FIG. 5 is a block diagram showing the functional configuration of the connection management terminal 300. As shown in FIG. As shown in FIG. 5, the connection management terminal 300 includes a connection management section 301, an input history DB302, and an AI engine log DB303. The connection management terminal 300 is a server which is installed at the center site 20, manages the connection between the operator terminal 200 and the customer terminal 100, and stores the history of the reception with the customer at each of the customer terminals 100. FIG.

However, the input history DB 302 and the AI engine log DB 303 do not have to be provided in the connection management terminal 300 . For example, the input history DB 302 and the AI engine log DB 303 may be provided in a server outside the connection management terminal 300 or in the customer terminal 100.

The connection management unit 301 manages connection between the operator terminal 200 and the customer terminal 100 . For example, when the connection management unit 301 receives a call requesting an operator to respond from the customer terminal 100 , it selects an operator terminal 200 that can respond from a plurality of operator terminals 200 installed at the center site 20 . After that, the connection management unit 301 transfers the call requesting the operator's response to the selected operator terminal 200 . Thereby, the connection management unit 301 can manage the connection between the operator terminal 200 and the customer terminal 100 .

The input history DB 302 is a database in which the history of input or speech by the customer to the customer terminal 100 is registered. Specifically, the input history DB 302 registers an operation log generated for each input or speech made by the customer to the customer terminal 100 .

FIG. 6 is a table showing an example of data included in an operation log registered in the input history DB 302 of the connection management terminal 300. As shown in FIG. For example, the operation log registered in the input history DB 302 may include data shown in FIG.

As shown in FIG. 6, in the operation log registered in the input history DB 302, data of "tenant ID", "store code", "machine number", and "operation device address" related to the identification of the customer terminal 100 are stored. may be included. Further, the operation log may include "date", "session ID", "operation log serial number", "transfer serial number", and "update date and time" regarding identification of the operation by the customer. Further, in the operation log, "operation category", "selected language", "operation content", "operation content (translation)", "system recognition result", and "system recognition result ( translation)" data may be included. Further, in the operation log, "system response screen ID", "system response content", "system response content (translation)", "response", and "system response voice file name" relating to the response of the customer terminal 100 to the customer's operation are stored. ” data may be included. Further, the operation log may include "emotion during operation" data regarding the customer's emotion.

The AI engine log DB 303 is a database in which an AI engine log is registered, in which a history of input or speech by a customer to the customer terminal 100 is summarized for each session, which is a series of responses. Specifically, in the AI engine log DB 303, an AI engine log is registered in which the operation logs registered in the input history DB 302 are summarized for each series of responses to customers.

For example, the AI engine log may include data such as “tenant ID”, “store code”, and “machine number” regarding the identification of the customer terminal 100 . In addition, the AI engine log may include "date", "session ID", "handover serial number", "handover item serial number", and "update date and time" regarding the identification of the operation by the customer. In addition, the AI engine log may include data of “handover item name” and “handover value” regarding the details of the operation on the customer terminal 100 . The data of "handover item name" and "handover value" are, for example, "operation category", "selected language", "operation content", "operation content (translation)", "system recognition result", and " It may be generated based on a predetermined rule from data of "system recognition result (translation)" or based on a machine learning algorithm.

The data registered in the input history DB 302 and the AI engine log DB 303 are used to generate takeover information, as will be described later. The takeover information is presented to the operator who takes over the customer service from the unmanned chatbot so that the operator can efficiently grasp the status of the customer service.

The data registered in the input history DB 302 and AI engine log DB 303 can also be used for analysis using an appropriate BI (Business Intelligence) tool. Specifically, the data registered in the input history DB 302 and the AI engine log DB 303 are output to a CSV file or the like, and can be used for predictive analysis or the like by a BI tool that inputs the output CSV file. good.

(Operator terminal 200)
FIG. 7 is a block diagram showing the functional configuration of the operator terminal 200. As shown in FIG. As shown in FIG. 7 , the operator terminal 200 includes a control section 220 , a microphone 211 , a speaker 212 , a camera 213 , a display section 214 and an input section 215 . A plurality of operator terminals 200 are installed at a center site 20 such as a call center and operated by an operator.

A microphone 211 picks up the operator's voice. The speaker 212 outputs the customer's voice or the like transmitted from the customer terminal 100 . A camera 213 captures an image of the operator. The display unit 214 displays an image displayed on the display input unit 114 and also displays an image of the customer captured by the camera 113 . The input unit 215 receives input from the operator.

In the information processing system 1, the operator who operates the operator terminal 200 takes over the customer's service from the unmanned chatbot according to the customer's request. At this time, the information processing system 1 presents handover information indicating the status of customer service to the operator who takes over customer service from the unmanned chatbot, thereby allowing the operator to efficiently grasp the customer status. . According to this, the operator can use manned chat to provide detailed service to customers who are difficult to handle with unmanned chatbots.

The control unit 220 controls overall operations of the operator terminal 200 . Specifically, control unit 220 includes call function unit 221 and handover information generation unit 222 .

The call function unit 223 realizes a video call between the operator terminal 200 and the customer terminal 100. FIG. Specifically, the call function unit 223 realizes a video call between the operator terminal 200 and the customer terminal 100 by P2P (peer-to-peer) communication or data communication via a network. For example, the call function unit 223 may transmit the voice or the like picked up by the microphone 211 to the customer terminal 100 . Also, the call function unit 223 may receive voice picked up by the microphone 111 , an image captured by the camera 113 , and an image displayed by the display input unit 114 from the customer terminal 100 .

When the operator terminal 200 receives a call requesting an operator to respond, the handover information generation unit 222 generates handover information summarizing the history of the response between the customer and the customer terminal 100 . Specifically, the handover information generation unit 222 generates handover information based on the history of input or speech by the customer to the customer terminal 100 . For example, the handover information generation unit 222 may generate handover information by summarizing history of operation logs generated for each input or speech by the customer to the customer terminal 100 and registered in the input history DB 302 . The takeover information generation unit 222 may generate takeover information further based on the AI engine log registered in the AI engine log DB 303 . According to this, the takeover information generation unit 222 can generate takeover information including information about the progress of input to the customer terminal 100 by the customer.

In addition, the handover information generation unit 222 may include information about the customer's emotion estimated by the emotion estimation unit 126 in the handover information. According to this, since the operator can know in more detail the situation of the customer who took over the response from the AI chatbot, the operator can respond in accordance with the customer's feelings.

Furthermore, when the history of the operation log includes the customer's utterance, the takeover information generation unit 222 may include the result of translating the utterance into another language in the takeover information in addition to the customer's utterance.

FIG. 8 is a diagram showing an example of an image presented to the operator as handover information. FIG. 9 is a table showing an example of data included in handover information presented to the operator. The handover information presented to the operator may be presented to the operator by, for example, displaying the image shown in FIG.

As shown in FIG. 9, the handover information presented to the operator may include an "incoming call notification message" corresponding to the reason why the operator was called. In addition, the handover information may include "operation time", "button operation", and "speech operation", which indicate the outline of the operation of the customer terminal 100 by the customer. In addition, the handover information may include "language" indicating the language of the customer's utterance, and "response OK rate" indicating the recognition status of the customer's utterance. Furthermore, the takeover information may include "details of operations" indicating specific operations performed by the customer.

For example, the operator refers to the "utterance operation" and the "response OK rate" to understand how successful the voice input is at the customer terminal 100 where the input operation is performed by the customer's utterance. can be done. Further, the operator can grasp the progress of the customer's input to the customer terminal 100 in more detail by referring to the "details of operation".

FIG. 10 is a schematic diagram showing an example of the appearance of the operator terminal 200. As shown in FIG. The operator terminal 200 may be, for example, a personal terminal 200A such as a desktop PC as shown in FIG. The personal terminal 200A is provided with a microphone 211, a speaker 212, a camera 213, a display unit 214 such as a display, and an input unit 215 such as a keyboard and mouse.

According to the information processing system 1, the response to customers on the customer terminal 100 can be switched from unmanned chat by an unmanned chatbot to manned chat by an operator who operates the operator terminal 200 according to the customer's request.

Further, the information processing system 1 transmits the handover information generated by the handover information generation unit 222 to the operator when switching from the unmanned chat by the unmanned chatbot to the manned chat by the operator who operates the operator terminal 200. can be presented. According to this, the operator can efficiently grasp the status of the customer and the progress of the response to the customer by the customer terminal 100 by confirming the presented handover information. Therefore, the operator can shorten the time required to grasp the customer's situation, and can respond to the customer more accurately.

For example, a customer can conduct a manned chat with an operator via display image 510 shown in FIG. Also, the operator can have a manned chat with the customer via the display image 520 shown in FIG. FIG. 11 is a diagram showing an example of an image displayed on the customer terminal 100. As shown in FIG. FIG. 12 is a diagram showing an example of an image displayed on the operator terminal 200. As shown in FIG.

A display image 510 shown in FIG. 11 is displayed on the display input unit 114 of the customer terminal 100, for example. As shown in FIG. 11 , display image 510 includes business area 512 and avatar area 511 . The business area 512 is an area where an image for presenting information to the customer and an image for accepting input from the customer are displayed. An avatar area 511 is an area where an avatar 500 acting for the operator's speech is displayed. By being served by the avatar 500 displayed in the avatar area 511 , the customer can more smoothly perform input or operations in the business area 512 .

An image of the operator captured by the camera 213 may be displayed in the avatar area 511 instead of the avatar 500 .

A display image 520 shown in FIG. 12 is displayed on the display unit 214 of the operator terminal 200, for example. As shown in FIG. 12 , display image 520 includes shared area 522 , customer image area 523 , avatar area 521 , and call area 524 . The shared area 522 is an area where the image of the business area 512 of the display image 510 is shared and displayed. The customer image area 523 is an area where an image of the customer captured by the camera 113 of the customer terminal 100 is displayed. Avatar area 521 is an area where the image of avatar 500 displayed in avatar area 511 of display image 510 is shared and displayed. The call area 524 is an area where the content of the operator's utterance picked up by the microphone 211 of the operator terminal 200 is converted into text by voice recognition and displayed. The operator can guide the customer to input or operate in the business area 512 while confirming the image of the business area 512 shared in the shared area 522 and the customer's image displayed in the customer image area 523 .

Note that the customer image displayed in the customer image area 523 may be avatarized like the avatar 500 of the display image 510 .

<2. Operation of Information Processing System>
Next, with reference to FIGS. 13 to 19, operations of the information processing system 1 according to the present embodiment will be described separately for a first operation example and a second operation example.

(First operation example)
FIG. 13 is a sequence diagram illustrating a first operation example of the information processing system 1 according to this embodiment. FIG. 14 is a diagram illustrating generation of an operation log and an AI engine log in the first operation example. A first operation example is an operation example when the information processing system 1 does not switch from an unmanned chat to a manned chat.

As shown in FIG. 13, first, when the customer touches the display input unit 114 or the like, the customer terminal 100 is activated (S101), and a page (for example, a web page) for responding to the customer is displayed. It is acquired (S102). The acquired page is displayed as an image on the display input unit 114 (S103), and an unmanned chatbot (not shown) responds to the customer. The customer performs an input operation or an utterance operation on the displayed image while chatting with the unmanned chatbot (S104). As a result, the page corresponding to the input operation or speech operation performed by the customer is acquired (S105), and the acquired page is displayed on the display input unit 114 as an image.

Subsequently, the control unit 120 outputs an operation log corresponding to the input operation or speech operation performed by the customer (S106). With the above operations from step S104 to step S106 as one unit, the customer's input operation or speech operation to the customer terminal 100 is repeatedly performed. The customer may make an input to the customer terminal 100 by an operation other than the input operation or the utterance operation. Further, the customer terminal 100 may include information about the customer's emotion in the operation log by estimating the customer's emotion.

After that, when the customer's operation on the customer terminal 100 ends (S118), the control unit 120 stores the operation log generated for each customer's input operation or speech operation in units of a series of sessions from the start of the operation to the end of the operation. It is transmitted to the connection management terminal 300 (S110). As a result, the connection management terminal 300 registers the operation log transmitted on a session-by-session basis in the input history DB 302 (S111), and transmits a notification of completion of registration in the input history DB 302 to the customer terminal 100 (S112).

It should be noted that the registration of the operation log in the input history DB 302 may not be performed in units of a series of sessions from the start of the customer's operation to the end of the operation. Registration of the operation log in the input history DB 302 may be performed each time the customer performs an input operation or an utterance operation.

Next, the control unit 120 generates an AI engine log from a series of session-based operation logs, and outputs the generated AI engine log (S113). The control unit 120 transmits the output AI engine log to the connection management terminal 300 (S114). As a result, the connection management terminal 300 registers the transmitted AI engine log in the AI engine log DB 303 (S115), and transmits a notification of completion of registration in the AI engine log DB 303 to the customer terminal 100 (S116).

For example, as shown in FIG. 14, an operation log including various information as shown in FIG. Each of the generated operation logs is assigned the same session ID and a continuous operation log serial number.

In FIG. 14, an operation log of utterance operations of "tell me where", "I want to go to the post office", and "I want to arrive at around 12:00" is generated in order, and then the operation end of "return to menu" is generated. An operation log of the input operation shown is generated. In addition, in FIG. 14, after the input operation indicating the end of the operation, the operation log of the utterance operations "tell me where", "I want to go to the post office", and "I want to arrive at about 12:00" is summarized. An AI engine log is generated. These operation logs and AI engine logs can be used, for example, for predictive analysis by BI tools.

(Second operation example)
15 and 16 are sequence diagrams illustrating a second operation example of the information processing system 1 according to this embodiment. 17 to 19 are diagrams for explaining the generation of the operation log and AI engine log in the second operation example. A second operation example is an operation example when switching from an unmanned chat to a manned chat is performed in the information processing system 1 .

As shown in FIG. 15, similarly to the first operation example, the customer terminal 100 is activated (S101) when the customer touches the display input unit 114 or the like, and is used to respond to the customer. page (for example, a web page) is obtained (S102). The acquired page is displayed as an image on the display input unit 114 (S103), and an unmanned chatbot (not shown) responds to the customer. The customer performs an input operation or an utterance operation on the displayed image while chatting with the unmanned chatbot (S104). As a result, the page corresponding to the input operation or speech operation performed by the customer is acquired (S105), and the acquired page is displayed on the display input unit 114 as an image.

Subsequently, the control unit 120 outputs an operation log corresponding to the input operation or speech operation performed by the customer (S106). With the above operations from step S104 to step S106 as one unit, the customer's input operation or speech operation to the customer terminal 100 is repeatedly performed. The customer may make an input to the customer terminal 100 by an operation other than the input operation or the utterance operation. Further, the customer terminal 100 may include information about the customer's emotion in the operation log by estimating the customer's emotion.

After that, when the customer performs a calling operation requesting a manned chat by an operator (S201), the control unit 120 stores an operation log generated for each input operation or speech operation of the customer from the start of the operation to the end of the operation. session unit to the connection management terminal 300 (S110). As a result, the connection management terminal 300 registers the operation log transmitted on a session-by-session basis in the input history DB 302 (S111), and transmits a notification of completion of registration in the input history DB 302 to the customer terminal 100 (S112).

It should be noted that the registration of the operation log in the input history DB 302 may not be performed in units of a series of sessions from the start of the customer's operation to the end of the operation. Registration of the operation log in the input history DB 302 may be performed each time the customer performs an input operation or an utterance operation.

Next, the control unit 120 generates an AI engine log from a series of session-based operation logs, and outputs the generated AI engine log (S113). The control unit 120 transmits the output AI engine log to the connection management terminal 300 (S114). As a result, the connection management terminal 300 registers the transmitted AI engine log in the AI engine log DB 303 (S115), and transmits a notification of completion of registration in the AI engine log DB 303 to the customer terminal 100 (S116).

Next, as shown in FIG. 16, when the customer performs a calling operation (S201), a call requesting an operator to respond is transmitted to the connection management terminal 300 (S202). The connection management terminal 300 transfers the received call to the operator terminal 200 (S203). The operator terminal 200 to which the outgoing call is transferred is the operator terminal 200 operated by an operator who can respond to customers.

After that, the operator terminal 200 that received the call acquires the terminal information of the customer terminal 100 operated by the customer (S204). Furthermore, the operator terminal 200 acquires the customer's operation log on the customer terminal 100 from the input history DB 302 (S205). Additionally, the operator terminal 200 may acquire the AI engine log corresponding to the acquired operation log from the AI engine log DB 303 .

Subsequently, the operator terminal 200 notifies the operator of the incoming call requesting a response via the speaker 212 or the display unit 214 (S206), and presents the handover information generated based on the operation log to the operator ( S207). Note that the takeover information may be generated further based on the AI engine log.

The operator who grasps the customer's situation from the presented handover information responds to the incoming call (S208), thereby starting a manned chat by voice call between the customer and the operator. As a result, the customer can switch from the unmanned chat by the unmanned chatbot to the manned chat by the operator and receive a response. In addition, since the operator who responds to the customer can grasp the history of the customer's operation and the like from the handover information, it is possible to respond to the customer more accurately.

For example, as shown in FIG. 17, an operation log including various information as shown in FIG. Each of the generated operation logs is assigned the same session ID and a continuous operation log serial number.

In FIG. 17, for example, an operation log of utterance operations "tell me where", "I want to go to the post office", and "I want to arrive at about 12 o'clock" is generated in order, and then an operator "press call button" is generated. is generated. Also, as shown in FIG. 18, an AI engine log is generated that summarizes the operation logs of the utterance operations "tell me where", "I want to go to the post office", and "I want to arrive around 12:00". be.

Furthermore, based on each of the operation logs and the AI engine log that summarizes each of the operation logs, a pop-up image showing handover information as shown in FIG. 8 is generated. By presenting the generated pop-up image to the operator, the operator can more efficiently grasp the customer's situation.

Here, a case where an input operation of "pressing the call button" requesting an operator's response is performed again after the input operation of requesting an operator's response is performed with reference to FIG. 19 will be described.

In such a case, as shown in FIG. 19, after the operation log of the input operation requesting the operator's response of "pressing the call button", the operation log of the input operation requesting the operator's response of "pressing the call button" is displayed again. generated.

At this time, an AI engine log is generated again, which summarizes operation logs of utterance operations such as "tell me where", "I want to go to the post office", and "I want to arrive around 12 o'clock". Note that the regenerated AI engine log is generated with the takeover serial number value increased to "2" in order to distinguish it from the AI engine log generated at the time of the first call. As a result, a pop-up image showing the takeover information as shown in FIG. 8 is generated based on the newly generated AI engine log with the takeover serial number of "2" and each of the operation logs. The generated pop-up image is presented to the operator so that the operator can grasp the customer's situation again.

According to the above operation, the information processing system 1 according to the present embodiment can switch the response to the customer on the customer terminal 100 from the unmanned chat to the manned chat according to the customer's request. Further, the information processing system 1 can present handover information based on the operation log to the operator who takes over the chat when switching the response to the customer from the unmanned chat to the manned chat. According to this, the operator can efficiently grasp the customer's situation by confirming the presented handover information, so that it is possible to provide an accurate response to the customer.

<3. Hardware configuration example>
Next, a hardware configuration example of each terminal of the information processing system 1 according to the present embodiment will be described with reference to FIG. 20 . FIG. 20 is a block diagram showing the hardware configuration of each terminal of the information processing system 1 according to this embodiment.

A hardware configuration example of the information processing device 900 that implements the customer terminal 100, the operator terminal 200, and the connection management terminal 300 according to the present embodiment will be described below. Note that the hardware configuration example of the information processing apparatus 900 described below is merely an example. Therefore, unnecessary configurations may be deleted from the hardware configuration of the information processing apparatus 900 described below, and new configurations may be added.

The functions of the customer terminal 100, the operator terminal 200, and the connection management terminal 300 according to this embodiment can be realized by cooperation between software and the hardware of the information processing device 900 described below. The functions of the control units 120 and 220 and the connection management unit 301 may be executed by the CPU 901, for example.

As shown in FIG. 20, an information processing apparatus 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external It comprises a bus 906 , an interface 907 , an input device 908 , an output device 909 , a storage device 910 and a communication device 911 .

The CPU 901 functions as an arithmetic processing device and a control device, and controls general operations within the information processing device 900 according to various programs. CPU 901 is, for example, a microprocessor. The ROM 902 stores programs and calculation parameters used by the CPU 901 . The RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution of the programs, and the like. These are interconnected by a host bus 904 comprising a CPU bus or the like.

The host bus 904 is connected via a bridge 905 to an external bus 906 such as a PCI (Peripheral Component Interconnect/Interface) bus. Note that the host bus 904, bridge 905, and external bus 906 do not necessarily have to be configured separately, and these functions may be implemented in one bus.

The input device 908 includes input means for the user to input information, such as a mouse, keyboard, touch panel, button, microphone, switch, or lever, and an input control circuit that generates an input signal based on the user's input. Configured. A user who operates the information processing apparatus 900 can input various data to the information processing apparatus 900 and instruct processing operations by operating the input device 908 .

The output device 909 is, for example, a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, a display device such as a lamp, or an audio output device such as a speaker. including.

The storage device 910 is a device for data storage. The storage device 910 includes a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded on the storage medium, and the like. The storage device 910 is, for example, an HDD (Hard Disk Drive) device. The storage device 910 can store programs executed by the CPU 901 and various data.

The communication device 911 is, for example, a communication interface configured with a communication device or the like for connecting to a network. The communication device 911 may be a communication interface that supports either wireless communication or wired communication.

It is also possible to create a program for causing hardware such as the CPU 901, ROM 902, and RAM 903 built into the computer to exhibit functions equivalent to those of the customer terminal 100, operator terminal 200, and connection management terminal 300 described above. It is also possible to provide a computer-readable recording medium recording the program.

Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention belongs can conceive of various modifications or modifications within the scope of the technical idea described in the claims. It is understood that these also naturally belong to the technical scope of the present invention.

For example, in the information processing system 1 according to one embodiment of the present invention, the customer terminal 100 may be a cash processing device, a ticket vending machine, or the like.

1 information processing system 10 customer site 100 customer terminal 111, 211 microphone 112, 212 speaker 113, 213 camera 114 display input unit 120, 220 control unit 121 voice recognition unit 122 voice generation unit 123, 223 call function unit 124 business application unit 125 Engine unit 126 Emotion estimation unit 20 Center site 200 Operator terminal 214 Display unit 215 Input unit 221 Call function unit 222 Handover information generation unit 300 Connection management terminal 301 Connection management unit 302 Input history DB
303 AI Engine Log DB
40 application server

Claims (9)

a customer terminal that receives input from a customer;
an operator terminal in which an operator makes an input regarding the response to the customer in response to a call from the customer terminal;
with
The information processing system, wherein the operator terminal presents the operator with handover information generated based on an input history of the customer to the customer terminal when the call is accepted. 2. The information processing system according to claim 1, wherein said customer terminal receives input from said customer by automatically responding to said customer's speech. 3. The information processing system according to claim 2, wherein said input history includes a history of input or speech from said customer to said customer terminal. 4. The information processing system according to claim 3, wherein said input history includes utterance content of said customer and a translation result of said utterance content into another language. 5. The information processing system according to any one of claims 1 to 4, wherein said input history includes information on emotions of said customer. 6. The information processing system according to any one of claims 1 to 5, wherein said handover information is generated based on said series of said input history by said customer before said call. 7. The information processing system according to any one of claims 1 to 6, wherein said takeover information includes information on progress of input to said customer terminal by said customer. In response to a call from a customer terminal that accepts input from a customer, an operator makes an input regarding the response to the customer. operator terminal for presenting the handover information to the operator. the computer,
In response to a call from a customer terminal that accepts input from a customer, an operator makes an input regarding the response to the customer. A program that functions as an operator terminal that presents the handover information to the operator.

Images