JP2005332174A - Interaction method, interaction device, voice interaction device, interaction program, voice interaction program and recording medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To naturalize a response language expression in an interaction device in a language expression generating technique for generating a response sentence. <P>SOLUTION: The interaction method comprises executing language understanding processing for extracting a parameter contained in input information; phrase type extraction processing for collating the input information with a phrase pattern database to extract the phrase type of the input information; response content determination processing for determining a response content; response sentence phrase type determination processing for determining a response sentence phrase type; response sentence generation processing for generating a response sentence in reference to the response content and the response sentence phrase type; and history information storage processing for storing, the parameter extracted from the input information, the phrase type extracted from the input information, the response content, the response sentence phrase type, and the response sentence as history information. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a dialogue method, a dialogue device, a voice dialogue device, a dialogue program, a voice dialogue program, and a recording medium on which these are recorded, which accepts a language or voice input and appropriately outputs a response in a language or a voice language. The present invention relates to a language expression generation technique for generating a response sentence.

Conventional technologies in the field of language expression generation technology related to dialogue include a voice response device proposed in Patent Document 1 or a text conversion device proposed in Patent Document 2 and a computer storing a text conversion program. Examples thereof include a recording medium, a dialog system and a dialog method proposed in Patent Document 3, a two-way dialog system and a two-way dialog method, and a recording medium.
In Patent Document 1, when outputting a response corresponding to the recognition result of the input speech, a part of the recognition result is replaced with an associative word and output, thereby eliminating a monotonous response output.

In Patent Document 2, monotonous dialogue is eliminated by grasping the characteristics of the user's conversation from the recognition result of the input speech and changing the conversation pattern, output word, response timing, etc. according to the user's characteristics. It is related as a language expression generation technique that the output word is changed depending on the recognition result of the input speech.
In a general spoken dialogue system currently used, the procedure is such that input speech is once converted into an internal parameter representing the user's request or dialogue state, and the linguistic expression of the response is determined according to the internal parameter. (This procedure is hereinafter referred to as prior art 1).

Also, the voice interaction method proposed in Patent Document 3 generates a plurality of response language expressions in advance, and outputs a shorter response again when the response voice and the user's input voice collide with each other. Is the method. Further, Patent Document 3 includes a method of generating a response sentence using a phrase or expression pattern spoken by the user.
In addition, the speech dialogue method proposed in Patent Document 4 includes means for determining whether the user is confused about the output from the system or whether the user interrupted and uttered, and in those situations, This is a method of adding an additional output that explains a word included in the response output.
JP-A-11-52975 JP 2001-125900 A JP-A-10-260976 JP 2000-259177 A

Here, for example, consider a scene in which a user interacts with a voice interaction system that accepts a conference room reservation. The reservation of the conference room shall be achieved by the user entering the date and time and accepting the confirmation from the system. Further, when storing the date as an internal parameter, it is considered that the data corresponding to the month and day is stored as a parameter, for example, in the case of “April 3”, the month is 4 and the day is 3. . Further, it is assumed that “April 3” is “next Monday” and “after 3 days” from the day when this dialogue is performed.
Here, the user utters an input example 11 such as “I want to make a reservation next Monday”, and the system prompts the user to input a reservation time. For example, “What time is next Monday? It is assumed that the response example 11 such as “is output. Also, another user utters an input example 12 such as “I want to make a reservation on April 3”, and the system side further prompts input of a reservation time. For example, “From what time on April 3 Consider outputting a response example 12 such as "Is it?" In this way, when referring to the same concept of April 3 in the response, if the wording used by the user and the wording of the response on the system side are aligned, an effect of reducing the mechanical impression given to the user can be expected.

In addition, the system will output a response example 21 such as “What time is next Monday?” As an utterance prompting the user to enter the reservation time. It is considered to output a response example 22 such as “What time is it from?” Or a response example 23 such as “What time is it after 3 days?”. That is, it is considered to use a phrase other than the corresponding phrase for the response when the same phrase included in the response continues for a predetermined number of times. Such a response method can be expected to reduce the mechanical impression given to the user as compared to the case where the system always responds using the same wording.
In order to output the response example 11, the response example 12, the response example 21, the response example 22, and the response example 23 using the technique proposed in Patent Documents 1 and 2, “next Monday” and “April 3” As a single word, and a correspondence table of such words needs to be created as a similar word dictionary or associative word dictionary.

However, the expression “next Monday” corresponds to “April 3” only for a period of about one week. When the next week is reached, a similar word dictionary and associative word dictionary will be newly added. Since it must be constructed, the burden on system operation is large and inefficient.
When using the prior art 1, for example, when the internal parameter includes two variables “month” and “day”, and the values of these variables are “4” and “3”, respectively, the response output from the system Can only do a standard phrase like "April 3". In addition, as a technique that can be easily expanded from the conventional technique 1, a technique in which the system generates a plurality of patterns, for example, the response example 11 and the response example 12 from internal parameters, and one of them is selected with a random number is also conceivable. In this case, the output cannot be selected based on whether it is the same as or different from the wording of the user input.

  Further, in Patent Documents 3 and 4, a response to a case where the user collides with an utterance or a case where the user is confused is realized. If such a case does not occur, the response output of the system changes. As a result, a monotonous response output results, giving a mechanical impression. In claim 7 of Patent Document 3, a technique is proposed in which the system uses the same phrase or expression pattern as the user's utterance. However, when the user always uses the same wording, the system always uses the same wording. Therefore, unlike the response example 22 and the response example 23, it is not possible to soften the mechanical impression by actively changing the wording on the system side.

As described above, when the conventional technology is used, a phrase that has been used for input when referring to a concept that can be expressed by a plurality of phrases, such as a date, in a response sentence of the dialog system, The wording in the response sentence could not be changed according to the wording used for the response. As a result, the wording in the response text of the dialogue system became monotonous and gave a mechanical impression.
It is an object of the present invention to respond to a concept that can be expressed by a plurality of phrases according to a phrase that has been used for input or a phrase that has been used for a system response when referring to a response sentence of a dialog system. It is possible to change the wording in the sentence and reduce the mechanical impression.

Claims 1 and 2 of the present invention include a language understanding process for extracting parameters included in input information to a computer, a wording type extraction process for extracting the wording type of the input information by collating the input information with the wording pattern database, and an input Parameters extracted from information, wording type extracted from input information, response content, wording type of response sentence, history information storage process for storing response sentence as history information, and response for determining response contents from history information A content determination process, a response sentence wording type determination process for determining a response sentence wording type from history information, and a response sentence generation process for generating a response sentence according to the response sentence wording determined in the response sentence wording type determination process; We propose a dialogue method characterized by executing
According to the dialogue method proposed in claims 1 and 2, the wording type included in the input information and the wording type of the response sentence are stored as history information, and the wording type of the response content is determined by referring to the memory. The wording type of the response sentence can be changed according to the wording used in the input and response.

In the dialogue method according to claim 3 of the present invention, when generating a response sentence, a response sentence having the same phrase type as the input phrase type included in the history information is preferentially generated. As a result, the present invention has a function of aligning the phrase of the response sentence with the phrase of the input.
In the dialogue method according to claim 4 of the present invention, when generating a response sentence, a different phrase type is used when the response sentence included in the history information is repeated for a predetermined number of times. Because it uses it, it has a function that prevents the same response sentence from being output at all times.

As described above, according to the present invention, when a concept that can be expressed by a plurality of phrases is referred to in a response sentence of a dialogue system, the wording in the response sentence is changed according to the phrase used for input and response. It becomes possible to make it.
Thus, in the invention according to claim 4, when the same wording is continued a plurality of times in the response, an effect of relieving the mechanical impression given to the user can be expected by preferentially using the wording different from this.

The best mode for carrying out the present invention will be described with reference to FIG.
In the figure, reference numeral 100 denotes an interactive apparatus proposed in claims 5 to 8 of the present invention, and 200 denotes a voice interactive apparatus proposed in claim 9 of the present invention.
The dialogue apparatus 100 includes a language understanding processing unit 101, an internal parameter storage unit 102, a phrase pattern database 103, a phrase type extraction unit 104, a response content determination unit 105, a phrase type determination unit 106, and a response sentence generation unit 107. And history information writing means 108.

The voice interaction device 200 is composed of a voice recognition device 201, a dialogue device 100, and a voice synthesis device 202. When voice is input to the voice recognition device 201, the voice recognition device 201 recognizes the input voice. Then, the voice recognition result is input to the interactive apparatus 100 as input information in the form of text data, for example.
The dialogue apparatus 100 understands the input information that has been input, generates a response sentence suitable for the input information, and inputs the response sentence to the speech synthesizer 202 in the form of text data, for example. The speech synthesizer 202 synthesizes the input response sentence with speech and outputs a response speech as a response output of the speech interaction device 200. When the user utters the voice again by outputting the response voice, the utterance is recognized again, the utterance content is processed by the dialog device 100, a response sentence suitable for the utterance content is generated, and the response sentence is synthesized by speech synthesis. It inputs into the apparatus 202 and responds with a voice from the speech synthesizer 202. Dialogue is realized by this repetition.

  In the dialogue apparatus 100 according to the present invention, the language understanding processing means 101 extracts parameters included in the input information. Here, the parameter may be a value related to the date and time required for the reservation when the interactive apparatus 100 is used for accepting a reservation in a conference room, for example. That is, values related to year, month, day, and time are extracted as parameters. For example, for the input information “next Monday”, using the calendar function, next Monday is identified as “April 3”, and “4” is extracted as the month parameter and “3” is extracted as the day parameter. . This extraction process is executed with reference to the internal parameters prepared in the internal parameter storage unit 102. FIG. 2 shows an example of parameters prepared in the internal parameter storage unit 102. Each parameter is given an attribute (value type) in association with it. The “date and time wording type”, “time wording type”, “confirmation flag”, and “response sentence history” shown in FIG. 2 are parameters extracted in each process described later, and these are internal parameter storage units as language understanding results. 102 is written.

The input information is transferred to the wording type extracting means 104, and the wording type is extracted from the word sequence. This extraction process is performed with reference to the wording pattern data stored in the wording pattern database 103. FIG. 3 shows an example of wording pattern data. The wording data shown in FIG. 3 illustrates a date wording database. In FIG. 3,% y,% m, and% d represent the year, month, and day, respectively, and% w represents the name of the day of the week. In this example, the pattern name “-year-month-day” is associated with the type name “year-month-day type”. In addition, the wording of a pattern such as “Thursday of the week” is associated with a type name “Weekday type”, and the wording of a pattern such as “20 days of this week” is associated with a type name of “Weekday type”.
FIG. 4 shows an example of a word pattern database relating to time. % H represents hours and% M represents minutes.

FIG. 5 shows the operation status of the language understanding processing means 101 and the wording type extraction means 104. In step SP1, parameter extraction processing is executed from the input information, and in step SP2, the wording type is extracted. In step SP3, the parameters extracted from the input information and the wording type are written in the internal parameter storage unit 102 as a language understanding result.
When the writing to the internal parameter storage unit 102 is completed, the response content determination unit 105 is activated and the response content determination process is started. The response content determination unit 105 includes a history information reference unit 105 </ b> A, and reads the internal parameter written by the history information reference unit 105 </ b> A into the internal parameter storage unit 102. Refer to the read internal parameters to determine the response contents. The response content is determined as follows.

For example, it is checked whether the internal parameters read from the internal parameter storage unit 102 include all parameters necessary for the reservation. If there is an insufficient parameter, the content is determined as “information request type” that prompts the user to supplement the insufficient parameter. On the other hand, if all the parameters necessary for the reservation are available but the value of the confirmation flag is “not yet”, the content is determined as “confirmation type” for confirming whether or not this content is acceptable.
When the response content is determined, the response content determination means 105 determines a template to be used for the response sentence. For example, a template group that prompts the user to input information, such as “From what time in% date?” Or “From what day% time?” Is prepared. Then, the template corresponding to the content prompting the input of necessary parameters is selected and determined.

When the response content template is determined by the response content determination means 105, the template is handed over to the wording type determination means 106 to determine the wording type of the response text. The wording type is determined by referring to the history information added to the internal parameter read from the internal parameter storage unit 102. That is, processing such as selecting a wording type of a response sentence of the same type as the wording type used for the user's input is performed.
When the wording type of the response sentence is determined, the response sentence generating unit 107 substitutes the determined wording type word string in the “% date” portion of the template, for example, generates a response sentence, and synthesizes the response sentence by speech synthesis Output to the device 202. At the same time, the history information writing means 108 stores the response content determined by the response content determination means 105, the wording type determined by the wording type determination means 106, and the response text generated by the response text generation means 107 as an internal history. Write to part 102. This writing completes the first dialogue. When the response sentence is emitted as a voice and the user utters the uttered response sentence, the utterance is recognized as a voice and a second dialogue state is entered. A parameter that is insufficient for reservation is replenished every time the dialogue is made. When all parameters are provided, a confirmation-type response is generated. The value of is changed to “1”, which means that the reservation is completed, and the dialogue is terminated.

FIG. 6 shows a flowchart for explaining the operations of the response content determination means 105, the phrase type determination means 106, the response sentence generation means 107, and the history information writing means 108 described above.
In step SP11, the history information reference unit 105A reads the internal parameter written in the internal parameter storage unit 102.
In step SP12, the response content is determined, and in step SP13, a template is determined. When the template is determined, the wording type is determined in step SP14, and the word string of the wording determined in the wording type determination step SP14 is substituted for the corresponding part of the template in step SP15 to generate a response sentence. In step SP16, history information is written in the internal pattern storage unit 102, and the process returns to step SP11 to enter a waiting state for the next dialog.
Specific examples will be described below.

FIG. 7 shows the configuration of the main part of the dialogue apparatus proposed in claim 7 of the present invention. The feature of the dialogue apparatus proposed in claim 7 is that the phrase type determining means 106 is provided with the same type determining means 106A.
The same type determination unit 106A refers to the phrase type extracted from the input information in the history information read by the history information reference unit 105A provided in the response content determination unit 105, and determines the phrase type to be applied to the response sentence from the input information. The same wording type as the extracted wording type is preferentially determined.

  In other words, if the wording type extracted from the input information is the “year / month / day type” shown in FIG. 3, the word string “year / month / day type” is added to the “% date” portion of the template when applied to the above example. Is assigned. If the wording type extracted from the input information is the “weekday type” shown in FIG. 3, a “weekday” type word string is substituted for the “% date” portion of the template.

This is shown in FIG. The left column represents the processing step name of each part, and the right column represents the processing result. In this example, a case where “please make a reservation next Monday” is input as input information will be described as an example.
In the parameter extraction step, the calendar function is used to identify “next Monday” and “April 3”, and the month parameter is extracted as “4” and the day parameter is extracted as “3”.
In the wording type extraction step, the wording pattern database 103 is referred to, and “date wording type” is extracted as “weekday” type.
In the internal parameter writing step, these extracted parameters are written in the internal parameter storage unit 102. When writing to the internal parameter storage unit 102, a template of parameters necessary for reservation is prepared in the writing format, and the lack of parameters necessary for reservation is detected at the time of writing. The example shown in FIG. 8 shows an example in which the parameters related to time and the time phrase type are insufficient.

Since there is a lack of parameters, the response content determination step determines “information request type” as the response content.
In the template determination step, “from what time in% date?” Is selected and determined as a template.
In the wording type determination step, the wording type extracted from the input information in the history information is referred to, and the wording type applied to the response sentence is determined to be the same “weekday” type as the input information.

In the response sentence generation step, "Wednesday" type language expression "Next Monday" is substituted into the "% date" part of the template to generate a response sentence "What time is next Monday?" To do.
When the response text is generated, the parameters extracted from the input information in the history information recording step, the date wording type, the response text, and the response content are written.

FIG. 9 shows an embodiment of an interactive apparatus proposed in claim 8 of the present invention. In this embodiment, the response sentence generated when the same phrase type used in the response sentence appears more than a predetermined number of times is changed to a different phrase from the corresponding phrase, and given to the user. The example which tries to relieve a good impression is shown. For this purpose, the wording type determination means 106 is characterized in that a different type determination means 106B is added to the same type determination means 106A shown in FIG.
According to this configuration, when the number of dialogues is within a predetermined number of times, the wording applied to the response sentence is aligned with the same wording type as the input information as described above, and the conversation with the user is facilitated and used in the response sentence. When the same wording type appears more than a predetermined number of times, for example, four times, the wording type applied to the response sentence can be made different.

The operation status of the different type determining means 106B will be described with reference to FIGS. In FIG. 10, the parameter extraction step and the wording type extraction step shown in FIG. 8 are omitted, and a situation in which a dialogue has already been performed four times and a fifth response sentence is being generated is shown.
The same “weekday” type as the “weekday” type extracted from the input information is applied to the response sentences up to the fourth time (the data written to the internal parameter storage unit shown in FIG. 10). (See response sentences 1 to 4).
On the other hand, the different type determination means 106B operates in the fifth response sentence, and the wording type “% date” of the template is changed to the “year / month / day” type as shown in the response sentence 5 shown in FIG. Yes. By changing the wording of the “% date” part to the “year / month / day” type, “next Monday” was substituted in the past four response sentences, but for the “year / month / day” type, it was extracted with the month parameter. Using “4” and “3” extracted by the day parameter, “April 3” is substituted, and a response sentence that confirms “From 3 o'clock on April 3?” Is generated. As a result, it can be expected that the same wording is always used in the response sentence, and the mechanical impression is eased.

  The dialog apparatus and the voice dialog apparatus of the present invention described above can be mainly configured by a computer. It is possible to cause a computer to function as a dialog device and a voice dialog device by causing a computer to decode and execute a dialog program and a voice dialog program written in a program language that can be decoded. The dialogue program and the voice dialogue program are recorded on a computer-readable recording medium such as a magnetic disk or a CD-ROM, and installed in the computer from these recording media or installed in the computer through a communication line, and are provided in the computer. It is decoded and executed by the central processing unit (CPU).

  The dialogue method, dialogue device, voice dialogue device, dialogue program, and voice dialogue program according to the present invention are utilized in the fields of an automatic reservation system, an automatic guidance system, and the like.

The block diagram for demonstrating the whole structure of this invention. The figure for demonstrating the internal condition of the internal parameter memory | storage part used for this invention. The figure for demonstrating the mode of the inside of the wording pattern database used for this invention. The figure for demonstrating the mode inside the wording pattern database similarly to FIG. The flowchart for demonstrating operation | movement of the language understanding process means and phrase type extraction means shown in FIG. The flowchart for demonstrating operation | movement of the response content determination means shown in FIG. 1, a phrase type determination means, and a response sentence production | generation means. The block diagram for demonstrating the structure of the principal part of the dialogue apparatus proposed by Claim 7 of this invention. The flowchart for demonstrating operation | movement of the Example shown in FIG. The block diagram for demonstrating the structure of the principal part of the dialogue apparatus proposed by Claim 8 of this invention. The flowchart for demonstrating operation | movement of the Example shown in FIG. 11 is a flowchart for explaining the continuation of FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Dialogue device 106 Wording type determination means 101 Language understanding processing means 106A Same type determination means 102 Internal parameter memory | storage part 106B Different type determination means 103 Wording pattern database 107 Response sentence generation means
104 wording type extraction means 108 history information writing means 105 response content determination means 200 voice dialogue apparatus 105A history information reference means 201 voice recognition apparatus
202 Speech synthesizer

Claims (12)

On the computer,
Language understanding process to extract parameters included in input information;
A wording type extraction process that extracts the wording type of the input information by comparing the input information with the wording pattern database,
Response content determination processing for determining the response content;
A response sentence wording type determination process for determining a response sentence wording type;
A response sentence generation process for generating a response sentence with reference to the response content and the phrase type of the response sentence;
A history information storage process for storing the parameters extracted from the input information, the wording type extracted from the input information, the response content, the wording type of the response text, and the response text as history information;
An interactive method characterized by causing the system to execute. The dialogue method according to claim 1,
The response content determination process refers to the history information stored in the history information storage process, executes a response content determination process according to the history of the conversation,
The response sentence wording type determination process refers to the history information stored in the history information storage process, and executes a response sentence wording type determination process according to a history of dialogue,
How to interact. Either of the dialogue methods according to claim 1 or 2,
The response sentence wording type determination process refers to the wording type of the input information extracted from the input information included in the history information stored in the history information storage process, and the wording type of the response sentence is the wording type of the input information. An interactive method characterized by preferentially determining the same type. Either of the dialogue methods according to claim 1 or 2,
The response sentence wording type determination process refers to the response sentence wording type history included in the history information stored in the history information storage process, and is the same as the response sentence wording type more than a predetermined number of times. If the phrase is continuous, a dialogue type other than the phrase type is preferentially determined. A wording database that maps wording patterns given in input information to wording types;
Language understanding processing means for referring to input information and extracting parameters included in the input information;
Referring to the input information and the wording database, wording type extracting means for extracting the wording type of the input information;
Response content determination means for determining the response content;
A response sentence wording type determining means for determining a response sentence wording type;
A response sentence generation means for generating a response sentence with reference to the phrase type of the response sentence and the previous response content;
The parameters given by the input information are associated with the attributes of the parameters, the wording type given by the input information, the response contents, the wording type of the response text, and the history of the response text are stored as internal parameters. An internal parameter storage unit;
An interactive apparatus comprising: The interactive apparatus according to claim 5, wherein
The response content determination means includes means for referring to the internal parameter stored in the internal parameter storage unit, and determines the response content according to the history of dialogue,
The response sentence wording type determining means includes means for referring to the internal parameter stored in the internal parameter storage unit, and determines the wording type of the response sentence according to the history of the dialog. Either of the interactive devices according to claim 5 or 6,
The wording type determining means for determining the wording type of the response sentence preferentially decides the wording type of the response sentence to the wording type of the same type as the wording type of the input information for each dialogue. Either of the interactive devices according to claim 5 or 6,
The wording type determining means for determining the wording type of the response sentence is a word type other than the wording type when the wording type of the response sentence stored in the internal parameter is equal to or more than a predetermined number of times. An interactive apparatus characterized by preferentially determining the wording type.   A speech recognition device for recognizing input speech and outputting the speech recognition result as input information to the interactive device according to claim 5 and a speech synthesizer for converting a response sentence generated by the interactive device into a speech signal are added. A voice interactive apparatus characterized by the above.   An interactive program that is described in a program language that can be read by a computer, and that causes the computer to function as an interactive device according to any one of claims 5 to 8.   10. A spoken dialogue program that is written in a computer-readable program language and causes the computer to function as the spoken dialogue device according to claim 9.   12. A recording medium comprising a computer-readable recording medium and recording at least one of the interactive program and the voice interactive program according to claim 10 and 11.

Images