JP2018128577A - Summary sentence display device, summary sentence display method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately and automatically create and display a summary sentence of reception utterance from the voices of a customer and a person in charge of reception.SOLUTION: A summary sentence display device 1 comprises: a voice recognition part 11 that performs voice recognition processing on the voices of a customer and a person in charge of reception to create a voice recognition result; a business extraction part 12 that extracts business from the voice recognition result; a summary sentence creation part 13 that creates a summary sentence including the business; and a display control part 14 that displays the summary sentence on a display part 15.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a summary sentence display device, a summary sentence display method, and a program for displaying a summary sentence based on a database.

  Traditionally, call centers, operators, reception desks, etc., respond to the customer's summary by answering the customer's speech recognition results and transcribe some utterances. It was made as a record.

  In recent years, in order to support operator operations at call centers, systems have been developed that have the ability to recognize speech content in real time and display appropriate response knowledge on the operator's screen using natural language processing technology. (For example, refer nonpatent literature 1).

Seiji Kawamura, 4 others, “Utilization of AI in call centers”, [online], February 2016, [Search January 6, 2017], Internet <URL: http://www.ntt.co.jp/ journal / 1602 / files / jn201602035.pdf>

  Non-Patent Document 1 describes a call that generates a summary sentence composed of “automatic message extraction” for extracting a customer's telephone requirements and “important sentence automatic extraction” for extracting only important utterances during the call. An automatic summarization function is disclosed. However, these requirements and important sentences are such that the filler is removed from the conversation, and it is difficult to automatically extract the requirements themselves and automatically generate a summary sentence. For this reason, the person in charge of the service was unable to create a service record using the summary sentence as it was.

  An object of the present invention made in view of such circumstances is to provide a summary sentence display device, a summary sentence display method, and a program capable of automatically generating and displaying a summary sentence of response contents with a customer with high accuracy. It is to provide.

  In order to solve the above-mentioned problem, the summary sentence display device according to the present invention is a summary sentence display device that automatically generates a summary of the response utterances of the customer and the person in charge of the customer. A speech recognition unit for generating a speech recognition result, a requirement extracting unit for extracting a requirement from the speech recognition result, a summary statement generating portion for generating a summary statement including the requirement, and the summary sentence A display control unit to be displayed on the display unit.

  In order to solve the above-mentioned problem, a summary sentence display method according to the present invention is a summary sentence display method in a summary sentence display device for automatically generating a summary of a response utterance of a customer and a person in charge of a customer, Performing speech recognition processing on a person's voice to generate a speech recognition result, extracting a requirement from the speech recognition result, generating a summary including the requirement, and displaying the summary And a step of displaying on the section.

  In order to solve the above problems, a program according to the present invention causes a computer to function as the summary sentence display device.

  ADVANTAGE OF THE INVENTION According to this invention, when performing customer reception at a call center, a window, etc., the summary sentence of the response content with a customer can be displayed with high precision and automatically. Therefore, it is possible to shorten the time required for creating the response record. Furthermore, even a person in charge who does not have high terminal operation skills can easily create a summary sentence.

It is a block diagram which shows the structural example of the summary sentence display apparatus which concerns on one Embodiment of this invention. It is a figure explaining the requirement extraction in the summary sentence display apparatus which concerns on one Embodiment of this invention. It is a figure which shows the example of a display screen of the display part in the summary sentence display apparatus which concerns on one Embodiment of this invention. It is a flowchart which shows an example of the summary sentence display method which concerns on one Embodiment of this invention.

  Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

FIG. 1 shows a configuration example of a summary sentence display device according to an embodiment of the present invention. The summary sentence display device 1 shown in FIG. 1 includes a voice recognition unit 11, a requirement extraction unit 12, a summary sentence generation unit 13, a display control unit 14, and a display unit 15.

  The summary sentence display device 1 is a device that automatically generates and displays a summary of a response utterance from the voices of the service representative and the customer when the service representative responds with the customer. A representative example of the person in charge is a call center operator.

  The voice recognition unit 11 inputs the voices of the customer and the person in charge of service through different channels (two channels). Then, voice recognition processing is performed for each of the voices of the customer and the person in charge of the customer, and a text indicating a voice recognition result corresponding to the voice is generated and output to the message extracting unit 12 and the display control unit 14. Here, an error may occur in the speech recognition process. Therefore, a process using the N-best method of preparing a plurality of candidates as a recognition result by a speech recognition process of a word included in an utterance may be performed.

  The message extraction unit 12 identifies a customer's message utterance from the text input from the voice recognition unit 11, extracts a message from the message utterance, and summarizes information indicating the message (message information). Output to the sentence generator 13. Further, when the response by the person in charge of the response is completed, the response end information indicating that the response is completed is output to the summary sentence generation unit 13.

  The message extraction unit 12 extracts the above-described message, further identifies the message confirmation utterance of the person in charge, extracts the message confirmation from the message confirmation utterance, and displays information indicating both of the message information May be output to the summary sentence generator 13.

  FIG. 2 is a diagram for explaining extraction of a business utterance and extraction of a business confirmation utterance. The left side of FIG. 2 shows an example of the customer and the person in charge of the customer. The customer's utterance is shown in the solid line frame, and the customer's utterance is shown in the dotted line frame. In this example, among the customer's utterances, “Oh, the other day, my son got a car license” and “I want to change my son to be eligible for car insurance even if I drive.” Is a business utterance. Then, by connecting this utterance and deleting the filler “Ano”, “The other day, my son got a car license, and even if my son drove, it was changed to be covered by car insurance. I want to do this.

  Also, among the utterances of the staff in charge, “Is it okay if I want my newly licensed son to be covered by car insurance?” Is a business confirmation utterance. Since this business confirmation utterance does not include a filler, the business confirmation is performed as it is.

  When responding to a customer, immediately after the customer utters an utterance that corresponds to the business (a business utterance), the person in charge of the service may make a utterance (a business confirmation utterance) for reviewing and confirming the business. It is common. The requirement extraction unit 12 can use such an interactive structure. That is, the message extraction unit 12 can extract a message with reference to the message confirmation utterance.

  For example, in the example shown in FIG. 2, the customer wants to change so that his son gets a car license the other day. When the business utterance is said, the person in charge of the service makes a business utterance confirming, “Are you sure you want to make your newly licensed son eligible for car insurance?” Using such a dialogue structure, the utterance of the person in charge of the response ends with a term indicating confirmation such as “Is it?”, “Is it?”, “Is it?”, And is common to the utterance of the customer just before When there are many terms, the utterance of the person in charge can be identified as the utterance for confirming the requirement. Also, if the person in charge of the response includes a term that explicitly indicates the message at the beginning of the utterance, such as “The content of the message is ~”, the utterance is identified as a message for confirming the message. can do. The customer's utterance immediately before the business confirmation utterance can be specified as the business utterance. It should be noted that when extracting a requirement from a requirement utterance and when extracting a requirement confirmation from a requirement confirmation utterance, it is desirable to remove fillers such as “ano” and “yes”.

  When the summary information generation unit 13 acquires the requirement information from the requirement extraction unit 12, the summary statement generation unit 13 generates a summary statement including the requirement or a summary statement including the requirement and the requirement confirmation and outputs the summary statement to the display control unit 14. . The summary sentence generation unit 13 may sequentially connect the requirements indicated by the requirement information and output the summary information immediately after acquiring the response end information to the display control unit 14. Is output to the display control unit 14 as a summary sentence each time the business information is acquired. It is desirable that the requirements and the requirements confirmation be in a state that can be distinguished in the summary. Also, the summary may include the date and time of the person in charge, the name of the person in charge, and the like.

  When the display control unit 14 acquires information indicating the summary sentence from the summary sentence generation unit 13, the display control unit 14 causes the display unit 15 to display the summary sentence. In addition, the display control unit 14 acquires text that is a voice recognition result from the voice recognition unit 11 and causes the display unit 15 to display the text. When the summary sentence includes a message and a message confirmation, the display control unit 14 desirably distinguishes both of them from the display unit 15 and displays them.

  The display control unit 14 may further cause the display unit 15 to display a portion selected by the person in charge of the summary sentence displayed on the display unit 15 as a response record.

  The display unit 15 is a display that displays data input from the display control unit 14. In the present embodiment, the summary sentence display device 1 includes the display unit 15, but the display unit 15 may be a device independent of the summary sentence display device 1.

  FIG. 3 shows a display screen example of the display unit 15. The screen displayed by the display unit 15 includes a left screen area 151, an upper right screen area 152, and a lower right screen area 153.

  In the left screen area 151, the voice recognition result by the voice recognition unit 11 is displayed in real time. The voice recognition result of the customer and the voice recognition result of the person in charge are displayed separately. In FIG. 3, the voice recognition result of the customer is shown in a solid line frame, and the voice recognition result of the person in charge is shown in a dotted frame.

  The upper right screen area 152 displays the summary result. As the summary result, only the “business” extracted from the business utterance may be displayed, or as shown in FIG. 3, the “business confirmation” extracted from the business utterance is displayed together. Also good. Since the speech recognition by the speech recognition unit 11 and the requirement extraction by the requirement extraction unit 12 are performed in real time, the summary result is updated every time the requirement is extracted.

  In the example shown in FIG. 3, a button “transcribe to reception record input” is displayed in the upper right screen area 152. When a person in charge selects a necessary part of “business” or “confirmation of business” and clicks a “transfer to service record input” button, the display control unit 14 displays the lower right screen area 153. The selected part is displayed (that is, the selected sentence is transcribed). In the reception record input field, editing work by the person in charge of the reception is also possible. Accordingly, only necessary portions of the summary results automatically created and displayed can be used, and editing can be performed thereafter, so that a response record can be easily created in a short time.

  Next, a summary sentence display method by the summary sentence display device 1 will be described. FIG. 4 is a flowchart showing an example of the summary sentence display method.

  First, the voices of the customer and the person in charge of the customer are input through different channels, and the voice recognition unit 11 performs voice recognition processing on the voices of the customer and the person in charge of the customer (step S101), thereby generating a text indicating the voice recognition result (step S101). Step S102).

  Next, the text generated in step S102 is analyzed by the message extraction unit 12, a message (and a message confirmation) is extracted (step S103), and a summary sentence is generated by the summary sentence generation unit 13 (step S104). ).

  Next, the display control unit 14 causes the display unit 15 to display the summary sentence generated by the summary sentence generation unit 13 (step S105).

  In addition, a computer can be suitably used for causing the above-described summary sentence display device 1 to function, and such a computer stores a program that describes processing contents for realizing each function of the summary sentence display device 1. This can be realized by storing the program in a database and reading and executing the program by the CPU of the computer.

  The program may be recorded on a computer readable medium. If a computer-readable medium is used, it can be installed on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, but may be a recording medium such as a CD-ROM or a DVD-ROM.

  As described above, in the present invention, a requirement is extracted from the voice recognition results of the customer and the person in charge of the customer, and a summary sentence including the requirement is displayed. When the present invention is applied at a call center, a window, etc., it becomes possible to greatly reduce the time required for the reception person to create an answer record when dealing with a customer. Therefore, in the case of a call center, the period until landing can be shortened. In addition, the person in charge can automatically display the summary results without requiring complicated operations, so that even a person in charge who does not have high terminal operation skills can easily create a summary sentence. become.

  In addition, a message is extracted from the customer's message, and a message confirmation is extracted from the message confirmation message of the person in charge, and both are displayed as a summary sentence. It is possible to improve convenience.

  Although the above embodiment has been described as a representative example, it will be apparent to those skilled in the art that many changes and substitutions can be made within the spirit and scope of the invention. Therefore, the present invention should not be construed as being limited by the above-described embodiments, and various modifications and changes can be made without departing from the scope of the claims. For example, it is possible to combine a plurality of constituent blocks described in the configuration diagram of the embodiment into one, or to divide one constituent block.

DESCRIPTION OF SYMBOLS 1 Summary sentence display apparatus 11 Voice recognition part 12 Message extraction part 13 Summary sentence generation part 14 Display control part 15 Display part 151 Left screen area 152 Upper right side screen area 153 Right lower side screen area

Claims (6)

A summary sentence display device that automatically generates a summary of customer utterances and customer utterances,
A voice recognition unit that generates voice recognition results by performing voice recognition processing on the voices of the customer and the person in charge;
A message extraction unit for extracting messages from the speech recognition result;
A summary sentence generation unit for generating a summary sentence including the requirement;
A display control unit for displaying the summary sentence on a display unit;
A summary sentence display device comprising:   The summary message display device according to claim 1, wherein the message extraction unit extracts the message with reference to a message confirmation utterance of the person in charge. The message extraction unit extracts the message from the customer's message utterance, and extracts a message confirmation from the message confirmation utterance of the person in charge.
The summary sentence generation unit generates a summary sentence including the requirement and the requirement confirmation,
The summary display device according to claim 1, wherein the display control unit displays the summary sentence on the display unit by distinguishing between the message and the message confirmation.   4. The summary sentence display device according to claim 1, wherein the display control unit displays a selected portion of the summary sentence as a response record. 5.   The program for functioning a computer as a summary sentence display apparatus as described in any one of Claim 1 to 4. A summary sentence display method in a summary sentence display device that automatically generates a summary of customer utterances and reception utterances,
Performing voice recognition processing on the voice of the customer and the person in charge and generating a voice recognition result;
Extracting a requirement from the speech recognition result;
Generating a summary sentence including the message;
Displaying the summary sentence on a display unit;
The summary sentence display method characterized by including this.

Images