JP2010081529A - Display control apparatus, display control method, and display control program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a display control apparatus and the like for calculating and displaying accurate information on an interaction time during a voice interaction on the basis of a voice reading speed or an interaction progress condition. <P>SOLUTION: The invention relates to a display control apparatus for displaying information on an interaction time, including: an input section 210 for inputting a script sentence in which information indicating an interaction flow is described; script information 250 for storing the inputted script sentence; a conversion section 220 for reading the script sentence from the script information 250 and converting the overall the sentence into Japanese syllabary (HIRAKANA or KATAKANA); a voice reading time calculation section 230 for calculating the total number of voices when reading the script sentence in voice on the basis of a converted result, and calculating a voice reading time required for completing the script sentence on the basis of the total number of voices, the number of actual voices actually uttered for reading the script sentence in voice, and an actual interaction time required for the interaction; and a display control section 240 for displaying, on a screen, information on the calculated voice reading time, the actual interaction time and/or the script sentence as voice reading information. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a display control apparatus that displays information related to a dialogue time when performing a voice dialogue.

When calling a large number of other parties in a call center of the outgoing call business type, in general, follow the script flow (paper-based flow chart that guides the flow of conversation) so that the story does not deviate sideways. There are many ways to proceed with the instruction, and to prepare a document that describes the flow on the desk and take notes while looking at it. In recent years, there is software that displays a script screen on a computer and inputs contents obtained from the other party from the screen.
Further, a technique disclosed in Patent Document 1 is disclosed as a technique having a voice interaction function and preventing a plurality of voice input / output conflicts.
JP 2008-26621 A

  However, in either case, such as the method of proceeding while taking notes along the script flow, or the method of displaying the script screen on the computer and inputting the content obtained from the other party from the screen, the called party How to answer the call, and the amount and quality of the callee's answer itself (eg, if the address is short, the repeat confirmation time is short, but if the address is long or difficult to read, the input or repeat confirmation is long) Due to the difference, it is not possible to answer a rough time when the callee asks "How much time do you need?" Also, the caller has a problem that he cannot be prepared because he cannot grasp the remaining time.

  In particular, inexperienced telephone operators often do not know the remaining prediction time and feel stress. In addition, even veteran telephone operators may be unfamiliar because they are too accustomed to conversely progress more than necessary (because they are speaking quickly, or they are conversing quickly). There are also cases where the other party feels uncomfortable.

  Moreover, although the technique shown in patent document 1 can prevent the competition between several audio | voice input / outputs, it can perform a several audio | voice input / output smoothly with respect to a user at an appropriate timing, respectively. When calculating the time required to read text information, it is assumed that the text is read out by a machine. There is a problem that it is not possible to read out text information of different contents.

  Accordingly, the present invention has been made to solve the above problems, and a display control device and display control for calculating and displaying accurate information related to the dialogue time in the voice dialogue based on the reading speed and the progress of the dialogue. It is an object to provide a method and a display control program.

(1. Display control device)
The display control device disclosed in the present application is a display control device that displays information related to a dialogue time when a voice dialogue is performed, and a script input unit that inputs a script sentence in which information indicating a flow of the dialogue is described; Script storage means for storing the script sentence input by the script input means, conversion means for reading the script sentence stored by the script storage means and converting the entire sentence into hiragana or katakana, and the result of conversion by the conversion means Based on the number of utterances for calculating the total number of utterances when reading the script sentence, the total number of utterances calculated by the utterance number calculating means, the actual number of utterances actually spoken to read the script sentence, Reading time for calculating the reading time required to complete the script sentence based on the actual dialogue time required for the dialogue Means out, the a reading time calculating means information on a reading time calculated is the one in which provided real dialogue time, and / or a display control means for displaying the script text on the screen as a reading information.

  As described above, in the display control device disclosed in the present application, the script sentence in which the information indicating the flow of the dialogue is read, the whole sentence is converted into hiragana or katakana, and the script sentence is based on the converted result. The total number of utterances is calculated when the number of utterances is read out, based on the calculated total number of utterances, the actual number of utterances actually spoken to read out the script sentence, and the actual utterance time required to utter the number of actual utterances. A script sentence for calculating a reading time required to complete the script sentence and displaying the information related to the reading time, the actual utterance time, and / or the script sentence on the screen as reading information. The conversation can be conducted while dynamically checking the remaining time required to complete the conversation and the progress of the conversation, and the caller is not ready to grasp the remaining time. That it does not come an effect that is eliminated.

  Also, unfamiliar telephone operators do not feel the stress because they do not know the estimated remaining time, and veteran telephone operators are too accustomed to conversely advance conversation more than necessary. It is possible to reduce the number of cases in which the user feels uncomfortable.

  In addition, when calculating the reading time required to complete the script sentence, since the caller's utterance time is included as the actual dialog time, information on the dialog time (reading time) according to the response time of the callee , Actual conversation time, remaining time, etc.) dynamically, even if the content of the recipient is unknown or the content of the conversation is unknown, information about the exact conversation time is displayed, making work more efficient There is an effect that it can be accomplished.

(2. Character display mode)
The display control device disclosed in the present application is directed to a script sentence displayed by the display control unit as read-out information when the actually spoken word matches the character described in the script sentence. The display mode of the characters actually spoken in the sentence is changed.

(3. Display of standard reading information)
The display control device disclosed in the present application includes performance information recording means for recording the reading information when the script sentence is completed as reading performance information for each script sentence, and the display control means includes the reading information. And the average value of the reading result information recorded by the result information recording means for the same script sentence as the script sentence displayed as the reading information is displayed as the standard reading information. .

(4. Splitting script sentences)
A display control device disclosed in the present application extracts a unique keyword for each block of a script sentence divided into a plurality of blocks by the dividing means, and a dividing unit that divides the script sentence into a plurality of blocks according to an arbitrary item. And when the arbitrary reading keyword extracted by the extracting means is uttered, the reading time calculating means determines that a block including the arbitrary one keyword has been read out. The reading time is calculated.

  Although the present invention has been shown as an apparatus so far, as will be apparent to those skilled in the art, the present invention can also be understood as a method and a program. These outlines of the invention do not enumerate the features essential to the present invention, and a sub-combination of these features can also be an invention.

  That is, a configuration in which a display control device disclosed in the present application or any combination of components is applied to a method, a device, a circuit, a system, a computer program, a recording medium, a data structure, etc. is also effective as another mode. is there.

  Embodiments of the present invention will be described below. The present invention can be implemented in many different forms. Therefore, the present invention should not be construed based only on the description of the present embodiment. Also, the same reference numerals are given to the same elements throughout the present embodiment.

  In the following embodiments, the apparatus will be mainly described. However, as is apparent to those skilled in the art, the present invention can also be implemented as a method and a program for operating a computer. In addition, the present invention can be implemented in hardware, software, or hardware and software embodiments. The program can be recorded on any computer-readable medium such as a hard disk, CD-ROM, DVD-ROM, optical storage device, or magnetic storage device. Furthermore, the program can be recorded on another computer via a network.

(First embodiment of the present invention)
A display control apparatus according to the present embodiment will be described with reference to FIGS. 1 is a hardware configuration diagram of a display control apparatus according to the present embodiment, FIG. 2 is a functional block diagram of the display control apparatus according to the present embodiment, and FIG. 3 is a table configuration of the display control apparatus according to the present embodiment. FIG. 4 is a flowchart illustrating an operation in a preparation stage of the display control apparatus according to the present embodiment. FIG. 5 is a flowchart illustrating an operation in a business stage of the display control apparatus according to the present embodiment. These are figures which show an example of the display screen of the display control apparatus which concerns on this embodiment.

(1. Configuration)
Hereinafter, the configuration of the display control apparatus according to the present embodiment will be described. In FIG. 1, a computer 1 includes a CPU (Central Processing Unit) 101, a RAM (Random Access Memory) 102, a ROM (Read Only Memory) 103, a flash memory (Flash Memory) 104, and an external storage device HD (Hard Disk). 105, a LAN (Local Area Network) card 106, a mouse 107, a keyboard 108, a video card 109, a display 109 a that is a display device electrically connected to the video card 109, a sound card 110, and the sound card 110 electrically Read / write from / to speaker / microphone 110a, which is a sound output device to be connected, and storage media such as a flexible disk, CD-ROM, and DVD-ROM It consists of a drive 111.
Note that the above hardware configuration is merely an example, and it is natural that the components can be changed.

2, the display control apparatus 200 includes an input unit 210, a conversion unit 220, a reading time calculation unit 230, a display control unit 240, script information 250, and conversion information 260.
The input unit 210 performs processing for receiving input of the input information 205. If the input information is a script sentence, the information is stored in the script information 250. If the input information is voice information or elapsed time information, the information is passed to the reading time calculation unit 230 and the display control unit 240.
The conversion unit 220 converts the script text stored in the information of the script information 250 into hiragana or katakana and stores it in the conversion information 260.

  The reading time calculation unit 230 is necessary to complete the script sentence based on the total number of utterances of the script sentence, the actual number of utterances actually spoken to read the script sentence, and the actual conversation time required for the conversation. To calculate the reading time. That is, it is possible to calculate the reading time for the total number of utterances by calculating the reading speed from the actual number of utterances and the actual dialogue time and dividing the total number of utterances by the reading speed.

  In addition, when the reading time calculation unit 230 calculates the reading time, a dialogue is made according to a preset question type (two-choice question, word group selection question, content question, etc.). An estimation unit for estimating the answer time of the other party may be provided, and the reading time may be calculated based on the estimated answer time. For example, in the case of a two-choice question, since there are only “yes” or “no” answers, the answer time of the conversation partner is set short (for example, about 3 to 5 seconds). In order to speak detailed contents, the answering time of the conversation partner may be set long (for example, 30 seconds to 1 minute) to calculate the reading time.

  The display control unit 240 displays the reading time calculated by the reading time calculation unit 230, the actual conversation time input by the input unit 210, and / or the script text stored in the script information 250 on the display 109a as reading information. Perform the process.

The script information 250 is a data part that stores information on a script sentence that the input unit 210 has accepted.
The conversion information 260 is a data part for storing a script sentence converted into hiragana or katakana by the conversion unit 220.

  Here, the configuration of the script information 250 and the conversion information 250 will be described in detail. FIG. 3A is a table configuration example of the script information table, and FIG. 3B is a table configuration example of the conversion information table. In FIG. 3A, the input script sentence is stored by being divided into sentences. The information stored here is used as information for conversion and also used as information for display on the screen.

In FIG. 3B, a display sentence, a display start position, a display length, a reading method, and a reading character number are stored. The display sentence, the display start position, and the display length are information used when changing the display mode of the read character. For example, when “Watakushi” is input as voice information, the display mode for two characters from the first character in the first line is changed. The reading method is information obtained by changing the display sentence to hiragana, and the number of characters to be read is information on the number of utterances necessary for reading. That is, the total number of utterances for reading out the entire script sentence is the sum of the number of characters read out.
The above is the description of the configuration of the display control apparatus according to the present embodiment.

(2. Operation)
The operation of the display control apparatus according to this embodiment will be described below. In FIG. 4, first, as a preparation stage process, a case-specific script sentence is input to the input unit 210 and stored in the script information 250 (step S <b> 41). By case, since the flow of dialogue changes depending on the scene, script sentences are input assuming various cases so that the change can be dealt with. The script text stored in the script information 250 is converted into a full text hiragana or katakana and stored in the conversion information 260 (step S42).
This completes the description of the preparation stage processing.

Next, the operation of the display control apparatus in the business stage will be described. First, the conversion information corresponding to the script sentence corresponding to the case to be used in the business to be implemented is read from the conversion information 260 (step S51). The display text of the script information 250 is displayed, and the initial reading time is calculated (step S52). In the initial calculation of the reading time, there is no information on the actual reading or the elapsed time, so the reading time is calculated using 400 characters = 1 minute which is the average reading speed of Japanese. That is, when the total number of characters (total number of utterances) in the script sentence is 400 characters, the remaining time is displayed in 60 seconds. At this time, the entire sentence of the script sentence is converted into hiragana or katakana and calculated based on the number of utterances.
In the initial calculation, it may be calculated based on the average reading speed of the Japanese as described above, or the average reading speed is extracted and calculated from the past performance information of the caller. Also good.

  Next, the caller starts reading the script sentence (step S53), and the elapsed time required for reading (dialogue) is stored in the memory as needed. The read voice is acquired, and the voice data is converted into hiragana or katakana (step S54). The voice data and the character string of the conversion information 260 (conversion information table in FIG. 3) are compared (step S55), and if all the conversion information table is read out, the process in the business stage is terminated. If the voice data does not match the character string of the conversion information table, the process returns to step S54. If the voice data matches the character string in the conversion information table, the display mode of the corresponding character in the displayed script sentence is changed and displayed (step S56), and the reading is performed from the elapsed time of the dialogue and the number of reading characters. The upper speed is calculated, the time required for the remaining reading is calculated, and displayed on the display 109a together with the elapsed time of the dialogue (step S57). For example, if the total number of characters (total number of utterances) in a script sentence is 400 characters and it takes 10 seconds to read 52 characters, the remaining time is the number of remaining characters / reading reading speed = (400 characters−52 characters) ) ÷ (52 characters ÷ 10 seconds) ≈67 (seconds). The processing from step S54 to step S57 is repeatedly performed until the entire conversion information table is read out or the dialogue is ended (call is disconnected).

  An example of the display screen in the above processing is shown in FIG. In the conversation progress graph, the elapsed time and the remaining time are displayed, and the current progress rate can be intuitively grasped visually. This conversation progress status graph is constantly updated as the dialog progresses, and the caller can grasp the status of the dialog in real time. For example, if the caller's answer to the caller's question is long, the reading speed will be slow (the script will not be read out, but the elapsed time will be added), so it will always be updated. The progress rate and remaining time can be displayed in real time.

  In addition, when a voice that is not related to a script sentence such as “Ah,” or “Eh,” or a voice such as a greeting that occurs in the flow of conversation is input, the script sentence is not read out, but the elapsed time Is added, the reading speed is slowed down, and the update rate is always performed, so that the progress rate and remaining time can be displayed in real time.

  Furthermore, since the script sentence is prepared according to various cases, the script sentence is also changed according to the change of the dialogue progress pattern, and the total number of characters of the script sentence is also changed. Even in such a case, the reading information is constantly updated, so that the progress rate and the remaining time can be displayed in real time.

  The script text is displayed in the script area, and the caller reads out the script text displayed here and proceeds with the dialogue. When the displayed character string of the script sentence matches the actual voice data, the display mode of the matching character string changes. For example, if you read “Wakakushi, Fujitsuin Ginko”, the character string of the displayed script sentence matches the actual voice data, so the display mode up to “I, Fujitsu Bank” as shown in FIG. Changes. The display of this change can be easily controlled by associating the audio data with the conversion information table shown in FIG. In other words, from the display start position and display length of the conversion information table, extract the character string of the script sentence that matches the voice data from what number of characters of the script sentence displayed in the script area. Therefore, the display mode of the corresponding character string may be changed. If you say `` I am afraid of a place where I am afraid, I am afraid of where I am, '' the display mode does not change until `` I am afraid of a place where I am afraid ''. Change.

Note that the display mode may be changed as long as the caller can visually recognize, such as color, font, thickness, size, underline, fill, blink, or a combination thereof.
“Make a call” and “Hang up” buttons are operated by pressing the mouse to make or hang up the phone, respectively.

Note that, as described above, the answering time may be estimated in advance from the question type and the conversation progress status graph may be calculated using the estimated value for the portion of <partner response> in the script sentence. For example, “Is it your home?” Is a two-choice question, so the answer time is set short. In addition, if there is a question such as “How was the XX product comfortable to use?”, Since it is a question of the content format, the answer time is set long.
The above is the description of the operation of the display control apparatus according to the present embodiment.

  As described above, according to the display control apparatus according to the present embodiment, the script sentence in which the information indicating the flow of the dialogue is read, the whole sentence is converted into hiragana or katakana, and based on the converted result, Calculate the total number of utterances when reading a script sentence, and calculate the total number of utterances, the actual number of utterances actually spoken to read the script sentence, and the actual utterance time required to utter the actual number of utterances. In order to calculate the reading time required to complete the script sentence based on the script and display the reading time, the actual utterance time, and / or the script sentence as reading information on the screen, the script sentence The conversation can be conducted while dynamically confirming the remaining time required to complete the conversation and the progress of the conversation, and the caller cannot be prepared because the remaining time cannot be grasped. It is eliminated.

  Also, unfamiliar telephone operators do not feel the stress because they do not know the remaining prediction time, and veteran telephone operators are too accustomed to conversely accelerate conversations more than necessary. The number of cases that are uncomfortable can be reduced.

  In addition, when calculating the reading time required to complete the script sentence, since the caller's utterance time is included as the actual dialog time, information on the dialog time (reading time) according to the response time of the callee , Actual conversation time, remaining time, etc.) dynamically, even if the content of the recipient is unknown or the content of the conversation is unknown, information about the exact conversation time is displayed, making work more efficient Can be carried out.

  Furthermore, when the actually spoken word matches the character written in the script sentence, the caller changes the display mode of the actually spoken character in the displayed script sentence, It is possible to prevent reading aloud twice or skipping lines.

  Furthermore, in order to identify the type of question in the script sentence, estimate the response time of the conversation partner according to the identified question type, and calculate the reading time based on the estimated response time of the conversation partner, Accurate reading according to two-choice (for example, yes / no) questions, word group selection (for example, select one from A to D) questions, content-type (for example, questions about impressions), etc. Time can be calculated, and more accurate information about the interaction time can be displayed.

(Second embodiment of the present invention)
The display control apparatus according to the present embodiment will be described with reference to FIGS. FIG. 7 is a functional block diagram of the display control apparatus according to the present embodiment, and FIG. 8 is a diagram illustrating an example of a display screen of the display control apparatus according to the present embodiment.

In FIG. 7, performance information 710 is newly provided as a component as compared with the functional block diagram (FIG. 2) of the display control apparatus according to the first embodiment.
The track record information 710 is a data part in which track record information of work performed by one or more operators is stored. The record information includes record information for each script sentence performed by one or more operators in the past, and specifically includes the time required for dialogue, reading speed, progress information, and the like. These pieces of information are input from the input unit 210 and the reading time calculation unit 230, output to the display control unit 240, and displayed on the display 109a. In addition, when displaying the performance information of a plurality of operators, the average value may be displayed.

  An example of a display screen when the record information is displayed will be described. In FIG. 8, a reference graph is newly displayed as compared with the case of FIG. This reference graph is information displayed based on the result information 710. In other words, by displaying an average graph of past results as a reference graph, the degree of progress and the target reading speed can always be confirmed, which can be used as a guideline for dialogue.

  In the case of FIG. 8, the progress of the reference graph is progressing compared to the conversation progress graph. That is, it can be intuitively understood that the current progress is delayed as compared with the past performance information. By recognizing that the progress is delayed, the caller can work to advance the subsequent dialogue as soon as possible.

  Here, the progress of reading at the same time is shown as a progress graph using the reference graph, but it shows how much time was spent in past performance information to say the same number of characters in the same script sentence. May be.

  Moreover, the average value etc. of performance information may be displayed as it is, and the target value (value used as a standard) based on performance information may be calculated and displayed. In particular, displaying the target value is effective when there is a normal number of cases per day. For example, if there are 50 quotas per day, it is necessary to transfer one case in about 5 minutes. It can be carried out efficiently.

Furthermore, the operation of the display control apparatus according to the present embodiment is the same as that of the first embodiment, and displays reading information and reading information based on past performance information (required for reference graphs and dialogues). (Time) is different.
Furthermore, how much progress delay or advance has occurred may be calculated and displayed.

(Third embodiment of the present invention)
The display control apparatus according to the present embodiment will be described with reference to FIGS. FIG. 9 is a functional block diagram of the display control apparatus according to the present embodiment, FIG. 10 is a flowchart showing an operation in a preparation stage of the display control apparatus according to the present embodiment, and FIG. 11 is a display control apparatus according to the present embodiment. FIG. 12 is a diagram illustrating an example of a display screen of the display control apparatus according to the present embodiment.

  In this embodiment, a script sentence is divided into a plurality of blocks according to arbitrary items, and a unique keyword is extracted for each block. Using such information, more accurate reading information is displayed. In order for the caller to proceed with the work, the dialogue should proceed in the order described in the script sentence. However, the conversation may not proceed in the order of the script sentence due to the flow of the conversation. For example, in a script sentence, a question at the end may be asked at the beginning of the conversation flow. In such a case, there is a possibility that the calculation of the remaining time may deviate from the actual value if it is not reflected in the progress even though the script sentence is actually read out. In the present embodiment, regardless of the order of the script sentences, the block of the read script sentence is reflected in the progress.

(1. Configuration)
In FIG. 9, compared with the functional block diagram (FIG. 7) of the display control apparatus according to the second embodiment, a dividing unit 910 and a keyword extracting unit 920 are newly provided as constituent elements.
The dividing unit 910 performs a process of dividing the script sentence stored in the script information 250 into a plurality of blocks according to arbitrary items (for example, for each question). The divided information is passed to the keyword extraction unit 920 and stored in the script information 250.

  The keyword extraction unit 920 performs processing for extracting a unique keyword for each block divided by the division unit 910. The extracted keyword is stored in the script information 250 together with the divided information.

  The reading time calculation unit 230 determines whether or not the keyword extracted by the keyword extraction unit 920 is included in the input voice data. If the keyword is not included, the script sentence is not read out (the story is not read). If it is included, the script sentence containing the keyword is read out, and the progress is advanced (counting the number of characters). The reading time is calculated.

  The script information 250 stores information on a script sentence that the input unit 210 has accepted, and stores information divided into a plurality of pieces by the dividing unit 910 and keywords extracted by the keyword extracting unit 920.

The conversion information 260 stores the script sentence converted into hiragana or katakana by the conversion unit 220, and stores information divided into a plurality of pieces by the division unit 910 and the keywords extracted by the keyword extraction unit 920. At this time, the keyword is converted into hiragana or katakana.
Since the functions of the input unit 210, the conversion unit 220, the display control unit 240, and the record information 710 are the same as those in the first or second embodiment, description thereof will be omitted.

(2. Operation)
In FIG. 10, first, as a preparation stage process, a script sentence for each case is input to the input unit 210 and stored in the script information 250 (step S1001). The dividing unit 910 divides the script sentence stored in the script information 250 into a plurality of blocks according to an arbitrary item, and extracts a unique keyword for each block (step S1002). The script is converted into a full text hiragana or katakana for each block by the conversion unit 220 and stored in the conversion information 260 (step S1003). At this time, the keyword is also converted into hiragana or katakana and stored in the conversion information 260.

  Since there may be cases where unique keywords cannot be extracted, unique keywords may be inserted into the script sentence in advance when creating the script sentence.

In addition, by inserting a unique keyword at the beginning of each block, voice data and keywords can be associated with each other when the beginning of the block is read out, and a more realistic dialogue time is displayed. can do. Therefore, it is desirable to create a script sentence so that the first character string of the block (for example, how to cut out conversations) is unique for each block.
This completes the description of the preparation stage processing.

  Next, the operation of the display control apparatus in the business stage will be described. First, conversion information corresponding to a script sentence corresponding to a case to be used in a business to be implemented is read from the conversion information 260 (step S1101). The display text of the script information 250 is displayed, and the initial reading time is calculated (step S1102). The initial calculation method of the reading time is the same as in the first embodiment. Next, reading of the script sentence is started by the caller (step S1103), and the elapsed time required for reading (dialog) is stored in the memory as needed. The read voice is acquired, and the voice data is converted into hiragana or katakana (step S1104). It is determined whether or not the keyword extracted by the keyword extraction unit 920 is included in the converted character string of the voice data (step S1105), and if not included, the process returns to step S1104. If included, the script sentence of the block including the keyword is extracted from the conversion information 260 (conversion information table in FIG. 3) (step S1106), and the read voice data is compared with the extracted script sentence (step S1107). .

  If all the conversion information tables have been read out, the processing in the business stage is terminated. If the voice data does not match the character string in the conversion information table, the process returns to step S1104. If the voice data matches the character string of the conversion information table, the display mode of the corresponding character of the displayed script sentence is changed (step S1108), and the reading is performed from the elapsed time of the dialogue and the number of characters read. The upper speed is calculated, the time required for the remaining reading is calculated, and displayed on the display 109a together with the elapsed time of the dialogue (step S1109). The processing from step S1104 to step S1109 is repeatedly performed until the entire conversion information table is read out or the dialogue is terminated (call is disconnected).

  An example of the display screen in the above processing is shown in FIG. Here, the script area is displayed divided into a plurality of blocks (area 1 to area 3) for each question. In addition, it is assumed that the keyword of the region 1 is “this time”, the keyword of the region 2 is “siblings”, the keyword of the region 3 is “family”, and is extracted as a unique keyword.

  When voice data “this time” is input in the dialogue, the block of region 1 is read out when it is determined that it matches with “this time” of region 1 as compared with the extracted keyword. And reading time is calculated. Similarly, when the voice data “sibling” is input for the other areas, it is determined that the block in area 2 is read out, and when the voice data “kazoku” is input, area 3 Is determined to be read out.

  In FIG. 12, the background of region 1 and the background color of region 3 are changed. This is because the background color is changed for the read block. That is, in FIG. 12, the reading of the regions 1 and 3 is completed first in the flow of the story, and the region 2 to be completed after the block of the region 1 and before the block of the region 3 Indicates that reading is not complete. Thus, by clearly displaying the blocks that have been read out and the blocks that have not been read out, it is possible to prevent the same question from being asked again or an unnecessary question to be asked.

  As described above, according to the display control apparatus according to the present embodiment, the script sentence is divided into a plurality of blocks according to an arbitrary item, a unique keyword is extracted for each block, and the extracted arbitrary one keyword In order to calculate the reading time by determining that the block containing the arbitrary keyword is read out and calculating the reading time, the dialogue does not proceed in the order of the script statement. Even if the last question was asked at the beginning of the dialogue, digested script sentences are reliably counted as reading time, and information about the dialogue time can be accurately displayed. .

  In addition, regarding the block that is determined to be read out by the reading time calculation means, when the reading of the block is completed, the display mode of the block is changed and displayed. Can be clearly distinguished from the previous block, and it is possible to prevent the same question from being asked again or unnecessary questions, and the dialogue proceeds in the order described in the script text. Even if there is no such situation, the caller can grasp the flow of the entire dialogue in units of questions, so that it is possible to stabilize the caller's feelings and perform efficient work. .

  In addition, as shown in the above embodiment, it is possible to distinguish the character that has been read out from the character that has not been read out by changing the display mode of the read character string, but the background color of the block is also changed. By doing so, it is possible to more clearly and reliably grasp whether or not it has been read out.

(Other embodiments)
(1. Display of attributes)
A display control apparatus according to the present embodiment will be described with reference to FIG. FIG. 13 is a diagram illustrating an example of a display screen of the display control apparatus according to the present embodiment.
In FIG. 13, the principal attribute and the partner attribute are displayed on the screen. This attribute is determined from the actual conversation time, the number of utterances uttered during the actual conversation time, and / or the ratio of the reading time of the script sentence with respect to the actual conversation time.

  For example, when the actual dialogue time is long, it can be determined that the conversation partner has a good feeling for the dialogue, and when the real dialogue time is short, the dialogue partner has a sense of disgust. In addition, it is possible to determine whether the conversation is performed quickly or slowly based on the number of utterances uttered during the actual conversation time. This can be determined similarly on both the caller side and the callee side. When the dialogue is a quick mouth, it is determined that it is an impatient type person, and when the dialogue is a slow tone, it is judged that it is a moist type person (illustrated in FIG. 13).

  Furthermore, depending on the ratio of the reading time of the script sentence to the actual conversation time, if the ratio was high, the conversation was centered on the main subject without going to the sideways, and if the percentage was low, many topics that were turned to the sideways were conducted. become. When a lot of topics deviating from the sideways are performed, it can be determined that the conversation partner has a personality that he / she likes to talk (illustrated in the partner attribute of FIG. 13).

These determination results are displayed on the screen as attributes of the interlocutor. In some cases, for example, the attribute “I like talking” and “Imperial” may be displayed. That is, a plurality of attributes may be determined by the above determination (illustrated in FIG. 13). The caller side can adjust the pace of the dialogue while referring to these attributes, and can carry out the dialogue according to the personality of the other party.
The display of the attribute may be changed in real time according to the state of the dialog, or the attribute may be determined from the average data up to the present time after the dialog is started and displayed.

  Thus, according to the display control apparatus according to the present embodiment, based on the actual conversation time, the number of utterances uttered during the actual conversation time, and / or the ratio of the reading time of the script sentence with respect to the actual conversation time, Since the attributes of the conversation person are set and displayed, the conversation can be proceeded according to the conversation attributes of the caller and the callee (such as a decoy type or an impregnation type), and work can be efficiently performed.

  Although the present invention has been described with the above embodiments, the technical scope of the present invention is not limited to the scope described in the embodiments, and various modifications or improvements can be added to these embodiments. . And embodiment which added such a change or improvement is also contained in the technical scope of the present invention. This is apparent from the claims and the means for solving the problems.

(2. Appendix)
The following additional notes will be given with respect to the above embodiments.
(Supplementary note 1) A display control apparatus for displaying information related to a dialogue time when a voice dialogue is performed, a script input unit for inputting a script sentence in which information indicating a flow of the dialogue is described, and the script input unit includes: Based on the script storage means for storing the input script sentence, the conversion means for reading the script sentence stored by the script storage means and converting the whole sentence into hiragana or katakana, and the result of conversion by the conversion means, The number of utterances for calculating the total number of utterances when reading the script sentence, the total number of utterances calculated by the utterance number calculating means, the actual number of utterances actually spoken to read the script sentence, and the dialogue Reading time calculation means for calculating a reading time required to complete the script sentence based on the actual dialogue time; Information about between calculation means a reading time calculated is the actual interaction time, and / or display control apparatus and display control means for displaying on the screen the script text as a reading information.

  (Supplementary note 2) In the display control device according to supplementary note 1, when a script sentence displayed as reading information by the display control unit is matched with a word actually spoken and a character described in the script sentence, A display control device that changes a display mode of characters actually spoken in the displayed script sentence.

  (Supplementary note 3) In the display control device according to Supplementary note 1 or 2, the display control device includes achievement information recording means for recording the reading information when the script sentence is completed as reading achievement information for each script sentence. While the control means displays the reading information, the average value of the reading result information recorded by the result information recording means for the same script sentence as the script sentence displayed as the reading information is a standard reading A display control device that displays information.

  (Supplementary note 4) In the display control device according to any one of supplementary notes 1 to 3, a dividing unit that divides the script sentence into a plurality of blocks according to an arbitrary item, and a script sentence divided into a plurality of pieces by the dividing unit Extracting means for extracting a unique keyword for each block, and when the reading time calculating means utters any one keyword extracted by the extracting means, the one arbitrary keyword A display control device for calculating a reading time by determining that a block including the character is read out.

  (Supplementary note 5) In the display control device according to supplementary note 4, when the display control unit completes reading the block for the block determined to be read by the reading time calculation unit, the block The display control apparatus which changes and displays the display mode.

  (Supplementary note 6) In the display control device according to any one of supplementary notes 1 to 5, a question type specifying unit for specifying a question type in the script sentence, and a dialogue according to a question type specified by the question type specifying unit A display control apparatus comprising: an estimation unit configured to estimate a response time of the partner, wherein the reading time calculation unit calculates the reading time based on the response time of the conversation partner estimated by the estimation unit.

  (Supplementary note 7) In the display control device according to any one of supplementary notes 1 to 6, the actual conversation time, the number of utterances uttered during the actual conversation time, and / or the ratio of the reading time of the script sentence to the actual conversation time Display control device that sets and displays the attributes of the interlocutor based on the above.

  (Supplementary Note 8) A display control method for displaying information related to a dialogue time when performing voice dialogue, a script input step for inputting a script sentence in which information indicating a flow of the dialogue is described, and the script input step When the input script sentence is stored, the stored script sentence is read, the whole sentence is converted into hiragana or katakana, and the script sentence is read out based on the result converted in the conversion step Utterance number calculating step for calculating the total number of utterances, the total utterance number calculated in the utterance number calculating step, the actual utterance number actually spoken to read out the script sentence, and the actual utterance number The reading time calculation step for calculating the reading time required to complete the script sentence based on the actual utterance time required for When the a reading time calculation information regarding a reading time calculated in step, the actual utterance time, and / or display control method and a display control step of displaying the script text on the screen as a reading information.

  (Supplementary note 9) In the display control method according to supplementary note 8, with respect to the script sentence displayed as the reading information in the display control step, when the actually spoken word matches the character described in the script sentence A display control method for changing a display mode of characters actually spoken in the displayed script sentence.

  (Supplementary note 10) In the display control method according to supplementary note 8 or 9, reading information when the script sentence is completed is recorded for each script sentence as reading result information, and the reading control step performs the reading control step. A display control method for displaying, as standard reading information, an average value of the recorded reading result information for a script sentence that is the same as the script sentence displayed as the reading information as well as displaying information.

  (Supplementary note 11) In the display control method according to any one of supplementary notes 8 to 10, a division step of dividing the script sentence into a plurality of blocks according to an arbitrary item, and a script sentence divided into a plurality of pieces in the division step An extraction step of extracting a unique keyword for each block, and when the arbitrary reading keyword extracted in the extraction step is uttered in the reading time calculation step, the arbitrary one keyword A display control method in which a reading time is calculated by determining that a block including a symbol has been read out.

  (Supplementary note 12) In the display control method according to supplementary note 11, when the display control step has been read out for the block determined to have been read out in the reading time calculation step, the block Display control method for changing and displaying the display mode.

  (Supplementary note 13) In the display control method according to any one of supplementary notes 8 to 12, according to a question type specifying step for specifying a question type in the script sentence, and a question type specified in the question type specifying step, A display control method in which the reading time is calculated based on the answer time of the conversation partner estimated in the estimation step in the reading time calculation step.

  (Supplementary Note 14) In the display control method according to any one of Supplementary Notes 8 to 13, in the actual conversation time, the number of utterances uttered during the actual conversation time, and / or the ratio of the reading time of the script sentence to the actual conversation time Display control method to set and display the attributes of the interlocutor based on the.

  (Supplementary note 15) A display control program for causing a computer to function to display information related to a dialogue time when a voice dialogue is performed, script input means for inputting a script sentence in which information indicating a flow of dialogue is described, Script storage means for storing the script sentence input by the script input means, conversion means for reading the script sentence stored by the script storage means and converting the whole sentence into hiragana or katakana, based on the result of conversion by the conversion means Utterance number calculating means for calculating the total number of utterances when reading the script sentence, the total utterance number calculated by the utterance number calculating means, the actual utterance number actually uttered to read the script sentence, and the actual utterance number Necessary to complete the script sentence based on the actual utterance time required to utter the number of utterances. Reading time calculation means for calculating a reading time, a display for displaying information on the reading time calculated by the reading time calculation means, the actual speech time, and / or the script sentence on the screen as reading information A display control program for causing a computer to function as control means.

  (Supplementary note 16) In the display control program according to supplementary note 15, when a script sentence displayed as read-out information by the display control means matches a word actually spoken and a character described in the script sentence, A display control program for changing a display mode of characters actually spoken in the displayed script sentence.

  (Supplementary note 17) In the display control program according to supplementary note 15 or 16, the computer is caused to function as record information recording means for recording the read information when the script sentence is completed as the read record information for each script sentence. The display control means displays the reading information, and the average value of the reading achievement information recorded by the achievement information recording means for the same script sentence as the script sentence displayed as the reading information, Display control program to display as standard reading information.

  (Supplementary note 18) In the display control program according to any one of Supplementary notes 15 to 17, a dividing unit that divides the script sentence into a plurality of blocks according to an arbitrary item, and a script sentence divided into a plurality of pieces by the dividing unit When the computer functions as an extraction unit that extracts a unique keyword for each block, and the reading time calculation unit utters any one keyword extracted by the extraction unit, the arbitrary one A display control program for calculating a reading time by determining that a block including a keyword has been read out.

  (Supplementary note 19) In the display control program according to supplementary note 18, when the block of the block determined to be read by the reading time calculation unit is completed by the display control unit, Display control program for changing and displaying the display mode.

  (Supplementary note 20) In the display control program according to any one of Supplementary notes 15 to 19, in accordance with the question type specified by the question type specifying means for specifying the question type in the script sentence, and the question type specified by the question type specifying means, the conversation partner A display control program for causing a computer to function as an estimating means for estimating the answering time of the user, and for the reading time calculating means to calculate the reading time based on the answering time of the conversation partner estimated by the estimating means.

  (Supplementary note 21) In the display control program according to any one of Supplementary notes 15 to 20, the actual conversation time, the number of utterances uttered during the actual conversation time, and / or the ratio of the reading time of the script sentence to the actual conversation time A display control program that sets and displays the attributes of the interlocutor based on.

It is a hardware block diagram of the display control apparatus which concerns on 1st Embodiment. It is a functional block diagram of a display control device concerning a 1st embodiment. It is a figure which shows an example of the table structure of the display control apparatus which concerns on 1st Embodiment. It is a flowchart which shows the operation | movement of the preparation stage of the display control apparatus which concerns on 1st Embodiment. It is a flowchart which shows the operation | movement of the work stage of the display control apparatus which concerns on 1st Embodiment. It is a figure which shows an example of the display screen of the display control apparatus which concerns on 1st Embodiment. It is a functional block diagram of the display control apparatus which concerns on 2nd Embodiment. It is a figure which shows an example of the display screen of the display control apparatus which concerns on 2nd Embodiment. It is a functional block diagram of the display control apparatus which concerns on 3rd Embodiment. It is a flowchart which shows operation | movement of the preparation stage of the display control apparatus which concerns on 3rd Embodiment. It is a flowchart which shows operation | movement of the work stage of the display control apparatus which concerns on 3rd Embodiment. It is a figure which shows an example of the display screen of the display control apparatus which concerns on 3rd Embodiment. It is a figure which shows an example of the display screen of the display control apparatus which concerns on other embodiment.

Explanation of symbols

1 Computer 101 CPU
102 RAM
103 ROM
104 Flash memory 105 HD
106 LAN card 107 Mouse 108 Keyboard 109 Video card 109a Display 110 Sound card 110a Speaker / microphone 111 Drive 200 Display control device 205 Input information 210 Input unit 220 Conversion unit 230 Reading time calculation unit 240 Display control unit 250 Script information 260 Conversion information 710 Result information 910 Division unit 920 Keyword extraction unit

Claims (8)

A display control device that displays information about dialogue time when performing voice dialogue,
Script input means for inputting a script sentence in which information indicating a flow of dialogue is described;
Script storage means for storing a script sentence input by the script input means;
Conversion means for reading a script sentence stored by the script storage means and converting the whole sentence into hiragana or katakana;
Based on the result of conversion by the conversion means, the number of utterances calculating means for calculating the total number of utterances when reading the script sentence;
Based on the total number of utterances calculated by the utterance number calculating means, the actual number of utterances actually spoken to read the script sentence, and the actual conversation time required for the conversation, the reading necessary to complete the script sentence is required. Reading time calculation means for calculating an upper time;
A display control apparatus comprising: display control means for displaying information on the reading time calculated by the reading time calculation means, the actual dialogue time, and / or the script sentence on the screen as reading information. The display control device according to claim 1,
Regarding the script sentence displayed as the reading information by the display control means, when the actually spoken word matches the character described in the script sentence, the character of the actually spoken letter in the displayed script sentence A display control device for changing a display mode. In the display control device according to claim 1 or 2,
A performance information recording means for recording the reading information when the script sentence is completed as the reading performance information for each script sentence,
The display control means displays the reading information, and the average value of the reading achievement information recorded by the achievement information recording means for the same script sentence as the script sentence displayed as the reading information is standard. Display control device that displays as reading information. The display control device according to any one of claims 1 to 3,
Dividing means for dividing the script sentence into a plurality of blocks according to arbitrary items;
An extraction means for extracting a unique keyword for each block of the script sentence divided into a plurality by the dividing means,
When the reading time calculation unit utters any one keyword extracted by the extraction unit, the reading time calculation unit determines that a block including the one keyword is read and calculates reading time Display control device. A display control method for displaying information about a dialogue time when performing a voice dialogue,
A script input step for inputting a script sentence in which information indicating a flow of dialogue is described;
Storing the script sentence input in the script input step, reading the stored script sentence, and converting the entire sentence into hiragana or katakana;
Based on the result converted in the conversion step, the number of utterances calculating step for calculating the total number of utterances when reading the script sentence;
Based on the total number of utterances calculated in the utterance number calculating step, the actual number of utterances actually spoken to read out the script sentence, and the actual utterance time required to utter the actual utterance number, A reading time calculating step for calculating a reading time necessary for completing
A display control method comprising: a display control step of displaying information on the reading time calculated in the reading time calculating step, the actual utterance time, and / or the script sentence as reading information on a screen. The display control method according to claim 5,
Regarding the script sentence displayed as reading information in the display control step, when the actually spoken word matches the character described in the script sentence, the actually spoken character in the displayed script sentence A display control method for changing the display mode. A display control program for causing a computer to function to display information about a dialogue time when performing a voice dialogue,
Script input means for inputting a script sentence in which information indicating a flow of dialogue is described;
Script storage means for storing a script sentence input by the script input means;
Conversion means for reading a script sentence stored by the script storage means and converting the whole sentence into hiragana or katakana;
Based on the result converted by the conversion means, the number of utterances calculating means for calculating the total number of utterances when reading the script sentence;
Based on the total number of utterances calculated by the utterance number calculating means, the actual number of utterances actually spoken to read the script sentence, and the actual utterance time required to utter the actual utterance number, Reading time calculation means for calculating the reading time required for completion,
A display control program for causing a computer to function as display control means for displaying information related to reading time calculated by the reading time calculation means, the actual utterance time, and / or the script sentence on the screen as reading information. In the display control program according to claim 7,
Regarding the script sentence displayed as the reading information by the display control means, when the actually spoken word matches the character described in the script sentence, the character of the actually spoken letter in the displayed script sentence A display control program for changing the display mode.

Images