Computer-assisted conversation support method

Abstract

A conversation support method, device, and program capable of evaluating conversations in real time are provided. [Solution] A conversation support method using a computer, comprising: a speech analysis step in which a computer analyzes speech related to a conversation and obtains spoken words that are words included in the conversation; a word group analysis step in which the spoken words are analyzed to determine which of a plurality of term groups the speech words fall into, the term groups including either words or phrases or both; and a utterance evaluation step in which utterances are evaluated based on the term groups analyzed in the word group analysis step. The utterance evaluation step is a step in which, each time a utterance related to a conversation is input to the computer, the utterance is evaluated and an evaluation score is obtained up to the point in time at which the utterance was made in the conversation.

Description

[Technical Field]

[0001] The present invention relates to a conversation support method using a computer. [Background technology]

[0002] Patent No. 6739811 describes a presentation support device that draws attention to prohibited words. This device outputs keywords related to prohibited words and an alert. This device also adds up evaluation points for the keywords, related words, and prohibited words included in the presentation to obtain an evaluation point for the entire presentation. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6739811 Summary of the Invention [Problem to be solved by the invention]

[0004] The above-mentioned device is excellent for evaluating presentations. However, the above-mentioned device evaluates the presentation as a whole, and does not evaluate the conversation in real time. Therefore, the object of the present invention is to provide a conversation support method that can evaluate the conversation in real time. [Means for solving the problem]

[0005] The first invention of this specification relates to a conversation support method using a computer. This method includes a speech analysis step, a word group analysis step, and a utterance evaluation step. The speech analysis step is a step in which a computer analyzes speech related to a conversation and obtains spoken words that are words included in the conversation. The word group analysis step is a step in which the computer analyzes the spoken words to determine which of a plurality of term groups the spoken words belong to. The term groups include either words or phrases, or both. The utterance evaluation step is a step in which the computer evaluates the utterance each time a conversation-related utterance is input, based on the term groups analyzed in the word group analysis step. This step may evaluate the utterance each time a conversation-related utterance is input to the computer, and may also obtain an evaluation score up to the point in the conversation when the utterance was made.

[0006] The plurality of term groups may include, for example, one or more of a group of terms related to greetings, a group of terms related to objections, a group of terms related to explanations, a group of terms related to questions, a group of terms related to excuses, a group of terms related to agreements, a group of terms related to promises, and a group of terms related to affirmations.

[0007] It is preferable that the above method further includes a recommended term group display step in which the computer uses the term group analyzed in the word group analysis step to display a recommended term group, which is a term group that is desirable to use next.

[0008] The method further includes inputting a scheduled time for the conversation into the computer; The recommended term group display step preferably further uses the estimated time of the conversation to display the recommended term group.

[0009] It is preferable that the above method further includes an image display step in which the computer displays an image relating to the term group analyzed in the word group analysis step.

[0010] The next invention of this specification relates to a program and a computer-readable information recording medium storing the program, which causes a computer to implement each of the above-mentioned methods. [Effects of the Invention]

[0011] According to the present invention, it is possible to provide a conversation support method that can evaluate a conversation in real time. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a flowchart for explaining a conversation support method using a computer. [Figure 2] FIG. 2 is a block diagram of a conversation support device for implementing the conversation support method. [Figure 3] FIG. 3 is a conceptual diagram showing an example of voice analysis. [Figure 4] Figure 4 is a table in place of a drawing showing examples of term groups. [Figure 5] Figure 5 is a conceptual diagram showing an example of analyzing a group of words. [Figure 6] FIG. 6 is a conceptual diagram showing an example of evaluation of a comment. [Figure 7] Figure 7 is a conceptual diagram showing an example of real-time evaluation of statements and conversations. [Figure 8] FIG. 8 is a conceptual diagram showing an example of a recommended term group. DETAILED DESCRIPTION OF THE INVENTION

[0013] The following describes embodiments of the present invention with reference to the drawings. The present invention is not limited to the embodiments described below, and also includes appropriate modifications of the embodiments below within the scope obvious to those skilled in the art.

[0014] A conversation support method using a computer will now be described. Figure 1 is a flowchart for explaining the conversation support method using a computer. This method includes a speech analysis step (S101), a word group analysis step (S102), and a utterance evaluation step (S103). As shown in Figure 1, this method may further include either or both of a recommended term group display step (S104) and an image display step (S105).

[0015] FIG. 2 is a block diagram of a conversation support device for implementing a conversation support method. As shown in FIG. 2, this device 1 includes a speech analysis unit 3, a word group analysis unit 5, and a utterance evaluation unit 7. As shown in FIG. 2, the device 1 may further include either or both of a recommended term group display unit 9 and an image display unit 11. The conversation support device is a computer-based system, and each unit is basically an element for implementing each of the above-mentioned processes. For example, the speech analysis unit 3 is an element for analyzing speech related to a conversation and obtaining spoken words, which are words contained in the conversation. The word group analysis unit 5 is an element for analyzing spoken words to determine which of multiple term groups the spoken words belong to. The utterance evaluation unit 7 is an element for evaluating each utterance related to a conversation based on the analyzed term group each time a utterance is input. The recommended term group display unit 9 is an element for displaying a recommended term group, which is a term group that is recommended to be used next, using the term group analyzed in the word group analysis process. The image display unit 11 is an element for displaying an image related to the term group.

[0016] A computer has an input unit, an output unit, a control unit, a calculation unit, and a memory unit, and each element is connected by a bus or the like so as to be able to exchange information. For example, the memory unit may store a control program or various information. When predetermined information is input from the input unit, the control unit reads out the control program stored in the memory unit. The control unit then reads out the information stored in the memory unit as appropriate and transmits it to the calculation unit. The control unit also transmits the input information to the calculation unit as appropriate. The calculation unit performs calculation processing using the various pieces of information it receives and stores the results in the memory unit. The control unit reads out the calculation results stored in the memory unit and outputs them from the output unit. In this way, various processes and steps are executed. The various processes are executed by the various units and means.

[0017] The device of the present invention may include a terminal connected to a network such as the Internet or an intranet, and a server connected to the network. Of course, a single computer or mobile terminal may function as the device of the present invention, or multiple servers may exist.

[0018] Voice analysis process (S101) The voice analysis process is a process in which a computer analyzes voice related to a conversation and obtains voice words, which are the words contained in the conversation. A conversation may be between people talking to each other, a speaker explaining to an audience or giving a presentation, a salesperson and a customer, or a telephone conversation between a person answering the phone and asking questions or inquiries. The voice is usually a human voice. However, voice also includes computer-generated pseudo-voices. FIG. 3 is a conceptual diagram showing an example of speech analysis. In the example shown in FIG. 3, a conversation between an MR and a doctor (Dr. A) is input to the device. This device may be a device connected to the MR's terminal and the doctor's terminal, or it may be either one of the terminals. Voice related to the conversation may be input to each terminal through the microphone of the MR's terminal and the microphone of the doctor's terminal, and the voice related to the conversation may be input to the device through each terminal. Alternatively, the microphone of the device may directly input the voice related to the conversation between the MR and the doctor (Dr. A) into the device. The control unit of the device reads the voice as appropriate from the memory unit and causes the calculation unit to analyze the voice input. In this way, the device obtains words (voice words) included in the conversation. Such voice analysis devices are publicly known. The device may store the obtained voice words in the memory unit.

[0019] An example of analysis of the spoken words shown in Figure 3 is as follows: MR: Thank you for your continued support, Professor. Today, I'm here to introduce the newly released DPP4 inhibitor, Aipro Tablets. Doctor: (But) there are so many, why are they being released again? I don't plan on using any of the newer DPP4 inhibitors. MR: Doctor, it is true that several DPP4 inhibitors have already been released. Our Aipro tablets have some advantages over other drugs. Which DPP4 inhibitor are you currently using? Doctor: There are many options, so I use different ones depending on the patient's lifestyle. Recently, I've been prescribing Putin tablets more often because they have a strong effect after just one dose.

[0020] Word group analysis process (S102) The word group analysis process is a process in which a computer analyzes a spoken word to determine which of a plurality of term groups it belongs to. A term group includes either words or phrases, or both. A memory unit of the device stores the words and phrases included in each term group. A control unit of the device then causes a calculation unit to perform a calculation to match the spoken word with the words and phrases included in each term group. In this way, it is analyzed to determine which term group the spoken word belongs to. The analysis results may be stored in the memory unit.

[0021] Figure 4 is a table instead of a drawing showing examples of term groups. A term group may be a combination of words or phrases grouped into various elements. A term group may also be one or more of terms that must be spoken, keywords, and NG terms (terms that should not be spoken). Multiple term groups may be divided into term groups whose presence is positive and term groups whose presence is negative. The multiple term groups may include, for example, one or more of the following: a group of terms related to greetings, a group of terms related to counterarguments, a group of terms related to explanations, a group of terms related to questions, a group of terms related to excuses, a group of terms related to agreements, a group of terms related to promises, and a group of terms related to assurances. Note that these term groups do not need to be stored in a computer as, for example, a "group of terms related to greetings."

[0022] Figure 5 is a conceptual diagram showing an example of analyzing a word group. As shown in Figure 5, for example, the phrase "Thank you for your continued support" is included in the term group "greetings." Therefore, when an MR utters "Thank you for your continued support, teacher," this utterance is analyzed as a "greeting." Then, the fact that a "greeting" was used in this conversation is stored in the memory unit. Next, the doctor says, "(But) there are plenty already, and yet another one has been released? I don't intend to use any new DPP4 inhibitors." The combination of the words "but" and "I don't intend to" contained in the doctor's statement is analyzed as a "rebuttal." The memory then stores in memory the fact that a "rebuttal" was made after the "greeting" described above.

[0023] Comment evaluation process (S103) The utterance evaluation step is a step in which the computer evaluates a utterance each time a utterance related to a conversation is input based on the term groups analyzed in the word group analysis step. This step may be a step in which the computer evaluates the utterance each time a utterance related to a conversation is input to the computer, and also obtains an evaluation score up to the point in time when the utterance was made in the conversation. For example, an evaluation score is assigned to each term group in the memory unit. The control unit of the device then reads out the evaluation score stored in association with the term group from the memory unit and evaluates the utterance. Note that the device may also simultaneously evaluate the entire conversation, which is a collection of utterances. Furthermore, evaluation scores may be stored in the memory unit in association with the relationship between the term groups of one utterance and the term groups of another utterance.

[0024] For example, the memory unit stores 0 points for the term group: "greetings." The memory unit also stores -1 point for the term group: "counterargument" in the other utterance that follows the term group: "greetings" in one utterance. The memory unit may also store +1 point for the term group: "counterargument" in the other utterance that follows the term group: "counterargument" in one utterance. This device may analyze terms included in conversational text to determine coefficients. In this case, for example, if a term related to coefficient 3 (DDP4 inhibitor) is included in the conversation after the first "counterargument," processing may be performed to add 3 points to the term group: "counterargument" in the next other utterance, calculated as 3 x (+1). In this case, the device stores point-adding terms and point-adding coefficients, analyzes conversational text, and when it is determined that a point-adding term is included, temporarily stores the point-adding coefficient, and multiplies this point-adding coefficient by the evaluation score when evaluating the utterances. For example, these point-adding terms and point-adding coefficients may be stored in a memory unit in association with materials (e.g., presentation materials), and when a conversation about the materials takes place, the point-adding terms and point-adding coefficients related to the materials may be read out as appropriate.

[0025] FIG. 6 is a conceptual diagram showing an example of evaluation of a comment. MR: Thank you for your continued support, Professor. "Today, I'm here to introduce the newly released DPP4 inhibitor, Aipro tablets." The term group "greetings" is stored in the device in association with this statement. Therefore, the device's control unit reads out the evaluation score of 0 points associated with the term group "greetings" from the memory unit. This statement is then evaluated as 0 points.

[0026] Next, the doctor Doctor: (But) there are so many, why are they being released again? "I don't plan on using any more new DPP4 inhibitors," he said. In relation to this utterance, the term group: "counterargument" is stored in the device. Then, the control unit of the device reads out from the memory unit the evaluation score of -1 point associated with the term group: "counterargument" of the other utterance that follows the term group: "greeting" of one utterance. In this way, utterances are evaluated in real time.

[0027] The device also stores the evaluation scores included in the conversation up to this utterance. Then, the device performs a calculation to add up the evaluation scores for this utterance. In this way, the device can obtain the evaluation scores up to the point where a certain utterance is made in the conversation. The obtained evaluation scores for the conversation up to the point where a certain utterance is made may then be stored in the storage unit as appropriate and output.

[0028] Figure 7 is a conceptual diagram showing an example of evaluating statements and conversations in real time. As shown in Figure 7, in this example, each time a statement is made, the statement and the conversation leading up to that statement are evaluated, and the evaluation content, such as ↑↑↓↓, is displayed in real time on the display unit of the terminal of the explainer, speaker, or presenter.

[0029] The above method preferably further includes a recommended term group display step in which the computer uses the term groups analyzed in the word group analysis step to display a recommended term group, which is a term group that is desirable to use next. The device stores a term group that is desirable to be uttered after a certain term group, or a third term group that is desirable to be uttered next when a second term group comes after a first term group. The device then analyzes the utterance and reads out a term group that is desirable to be uttered next from the storage unit using information about the utterance, the previous utterance, and the term group to which the previous utterance belongs. The device then outputs the terms included in the read term group that is desirable to be uttered next. The terms are then displayed on the output unit (e.g., a monitor) of the speaker's terminal. In this way, the device can support the speaker in conversation.

[0030] Figure 8 is a conceptual diagram showing an example of recommended term groups. For example, if a term group A1 is used after a certain term group, the recommended term groups may be displayed in the speaker's output unit as term groups B1, B2, and B3 (or terms selected from or included in these term groups), or the best recommended term groups may be displayed as term groups B1 and C1.

[0031] The above method may further include a step of inputting the expected duration of the conversation into the computer. The recommended term group display step preferably further uses the expected duration of the conversation to display the recommended term group. The expected duration of the conversation may be the beginning and end of the conversation, or the duration of the conversation (for example, within one hour). The device preferably has a clock unit that measures time and duration. The memory unit divides the conversation into conversation time regions such as the beginning, middle, and end. The memory unit then assigns identification information corresponding to the conversation time region to the terms included in the term group and stores them. Then, when reading out terms included in the term group, the device can read out and output terms corresponding to the conversation time region of the conversation. For example, when the conversation reaches a predetermined time before the scheduled time or when the conversation reaches its end, a group of recommended words can be stored in the memory unit to end the conversation, and the words can be read out and displayed as appropriate. This makes it possible to finish a lecture or presentation within the predetermined time. Examples of words that end the conversation are "to sum up" and "to briefly explain the rest."

[0032] Preferably, the above method further includes an image display step in which the computer displays an image related to the term group analyzed in the word group analysis step. An example of an image related to a term group is an evaluation score related to the term group or an arrow symbol (e.g., ↑↓) representing the evaluation score. The memory unit stores images related to these term groups. The device then identifies a term group related to expression. The device then uses information about the identified term group to read an image related to the term group from the memory unit. The device then outputs the read image. For example, if the image is related to an evaluation value, the user can instantly know whether their own comment was positive or negative.

[0033] The next invention of this specification relates to a program or a computer-readable information recording medium storing the program. This program is a program for causing a computer to implement each of the above-mentioned methods. For example, this program causes a computer to analyze speech related to a conversation, obtain spoken words that are words contained in the conversation, analyze the spoken words to determine which of multiple term groups the spoken words belong to, and evaluate each conversational utterance based on the analyzed term group each time the utterance is input. [Industrial Applicability]

[0034] This invention can be used in the information industry. [Explanation of symbols]

[0035] 1. Conversation support device 3. Audio analysis section 5. Word Group Analysis 7. Speech Evaluation Section 9 Recommended term group display section 11 Image display section

Claims

1. A conversation support method using a computer, comprising: The computer a speech analysis step for analyzing speech relating to a conversation to obtain speech words, which are words contained in the conversation; a word group analysis step for analyzing the spoken words to determine which of a plurality of term groups they belong to, the term groups including either words or phrases, or both; Based on the term group analyzed in the word group analysis step, a statement evaluation step of evaluating a statement related to the conversation each time the statement is input to the computer; an image display step for displaying an image relating to the term group analyzed in the word group analysis step, The image related to the group of terms is a rating score related to the group of terms or an arrow symbol representing the rating score. method.

2. 2. The method of claim 1 , the plurality of term groups include one or more of a group of terms related to greetings, a group of terms related to objections, a group of terms related to explanations, a group of terms related to questions, a group of terms related to excuses, a group of terms related to agreements, a group of terms related to promises, and a group of terms related to affirmations; method.

3. 2. The method of claim 1 , The computer The method further includes a recommended term group display step for displaying a recommended term group, which is a term group that is desirable to be used next, using the term group analyzed in the word group analysis step. method.

4. 4. The method of claim 3, inputting a scheduled time for the conversation into the computer; The recommended term group display step further uses a scheduled time of the conversation to display the recommended term group. method.

5. A conversation support device 1, a speech analysis unit 3 for analyzing speech related to a conversation and obtaining speech words that are words included in the conversation; a word group analysis unit 5 for analyzing which of a plurality of term groups each of the spoken words belongs to, the term groups including either or both of words and phrases; a utterance evaluation unit (7) that evaluates utterances related to the conversation based on the term group analyzed by the word group analysis unit (5); an image display unit for displaying an image relating to the term group analyzed by the word group analysis unit 5, the utterance evaluation unit 7 evaluates the utterance related to the conversation every time the utterance related to the conversation is input to the conversation support device 1; The image related to the group of terms is a rating score related to the group of terms or an arrow symbol representing the rating score. Device.

6. To the computer, a speech analysis step for analyzing speech relating to a conversation to obtain speech words, which are words contained in the conversation; a word group analysis step for analyzing the spoken words to determine which of a plurality of term groups they belong to, the term groups including either words or phrases, or both; Based on the term group analyzed in the word group analysis step, a statement evaluation step of evaluating a statement related to the conversation each time the statement is input to the computer; an image display step for displaying an image relating to the term group analyzed in the word group analysis step, The image relating to the group of terms is a rating score for the group of terms or an arrow symbol representing the rating score. A program for implementing the method.

7. 7. A computer-readable information recording medium storing the program according to claim 6.

Images