JP2003223462A - Information system, terminal, information acquisition method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an information system capable of dispensing with a processing for understanding a meaning and enabling a questioner to easily obtain a response to a question by a natural language. <P>SOLUTION: A center 20 storing a plurality of categories for classifying the question by relating to a cleverness degree of each respondent to each category obtains the question by the natural language and the category of the question from the questioner's side terminal 10, determines the respondent of an output target of the question based on the cleverness degree for each respondent in the category of the question, outputs the question to a respondent's side terminal 30 of the determined respondent, obtains the response by the natural language to the question from the respondent's side terminal 30, and outputs the response to the questioner's side terminal 10. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

TECHNICAL FIELD The present invention relates to an information system and the like.

[0002]

2. Description of the Related Art As an information system for retrieving and notifying information, a center and a terminal are provided, and the information is classified into categories and stored in the center, and the user of the terminal can respond to the request from the terminal. An information system is known that provides the searched information to the user by outputting a list of categories, and sending information to the terminal that matches the category selected by the user from the list to notify the user. There is. Further, there is known an information system in which a word or phrase included in the information stored in the center is full-text searched or the like and is notified from a terminal and provided to the user.

[0003]

In such an information system, a category is selected from a user's terminal or a simple keyword is input, and information is searched based on the selected / input category or keyword. Therefore, for example, in Web search using a search engine on the Internet, there is a problem that many pages not intended by the user are hit. Therefore, it takes a lot of time and labor for the user to discover the desired information, which is a burden on the user.

Therefore, for example, a method is conceivable in which the intention or meaning of a question is understood from the natural language input by the user and information corresponding to an ambiguous question in the natural language from the user is retrieved. However, in order to respond to such ambiguous questions from users, it is necessary for the center and terminals to perform semantic understanding processing. Therefore, there is a problem that it is difficult to perform such processing using a device with limited resources such as a car navigation device or a mobile terminal as a terminal.

Therefore, the present invention provides an information system or the like that can eliminate the need for a process for understanding the meaning and can easily obtain the answer to the question in the natural language acquired from the questioner. The purpose is to

[0006]

According to the information system of claim 1, which is made to solve the above-mentioned problems, a plurality of categories for classifying questions and each category are provided. Are stored in association with each of the respondents in question, the question in the natural language from the questioner and the category of the question are acquired, and based on the degree of expertise of each of the respondents in the question category, The respondent who outputs the question is determined and the question is output to the determined output respondent. Then, an answer in natural language from the respondent to the question is acquired, and the answer is output to the questioner. Therefore, the questioner can obtain a natural language answer to the question in his natural language. That is, it is possible to provide an information system capable of responding to a user's ambiguous inquiry. Further, by doing so, it is not necessary to perform a process for understanding the meaning in the information system. Therefore, the questioner's answer to the question in natural language can be easily notified to the questioner in natural language.

Moreover, the respondent who is the subject of outputting the question acquired from the questioner is determined based on the strength of each respondent in each category. Therefore, for example, since it is possible to output a question only to those who are good at the category of the question from a large number of respondents, there is a high possibility that an accurate answer to the question can be quickly obtained. In addition, it is not necessary to send a question to all of a large number of respondents, and the processing load on the information system can be reduced.
The questions and answers are data in a predetermined data format.

Further, as described in claim 2, this category may be acquired as a category selected from the category list notified to the questioner, or may be acquired by extracting from a question in natural language. If the former method is used, processing such as voice recognition can be eliminated or the processing load on the information system can be reduced, and the questioner can clearly specify the category of the question and specify the output target of his own question. The information system can determine the respondents. Also, if you do the latter, the questioner simply inputs the question in natural language,
Since the categories are automatically extracted, it is possible to easily obtain an answer. The category may be acquired by performing both the former and the latter, or the category may be acquired by performing either one.

Further, as described in claim 3, in addition to the category, additional information may be acquired, and the respondent may be determined in consideration of the additional information. By doing so, it is more likely that an accurate answer to the question can be obtained quickly.
Also, because it is possible to further narrow down the number of respondents,
The processing load can be further reduced. Therefore, the answer to the question in natural language acquired from the questioner,
The questioner can easily obtain it. Similar to the category in claim 2, the additional information may be selected from, for example, a menu or the like, may be directly input by text, or may be acquired from the question. .

As a method of determining the respondent in consideration of the additional information in this manner, for example, as shown in claim 4, a method of determining based on the additional information and the stored information about the respondent may be adopted. it can. For example, by comparing the stored information about the respondent with the additional information, only the respondent including the matching information can be determined as the respondent to be output.

As such additional information, position information can be used as described in claim 5. In addition, as information regarding the respondent, as shown in claim 5,
The location information indicating the area in which the respondent is good can be used. The area that is good at is, for example, an area that the respondent is familiar with. With this configuration, when the content of the question is information on a specific area, the respondent can be accurately determined, and the questioner can easily obtain the answer to the question. The area in which the respondent is good may be determined from information such as the address of the respondent, or information regarding the area in which the respondent is good may be acquired in advance and the acquired information may be used. . Further, as shown in claim 6, it is preferable to use information indicating the current position of the questioner. By doing this, it becomes possible to easily obtain accurate information near the current position. The current position information may be detected and acquired by using, for example, GPS provided in the interrogator's terminal or the like.

Further, as the additional information, as described in claim 7, it is preferable that the respondent designation information is included, and the respondent designated by the respondent designation information is determined as the respondent to be output. In this way, the questioner can specify the respondent. Therefore, for example, the questioner can previously specify the questioner who is likely to know the answer to the question to be asked. Therefore, it is possible to further increase the possibility that an accurate answer to the question can be quickly obtained.

Further, as described in claim 8, the answer deadline for the question may be acquired, and the answer to the question may be acquired and output until the acquired answer deadline. In this way, only the answers acquired from the respondent by the answer deadline are output to the questioner. Therefore, for example, for a question that is meaningless if an answer is obtained after the deadline, if the questioner inputs the answer deadline in advance,
No response is output after the response deadline has passed. Also, when the answer deadline for a certain question has passed, there is no need to wait for the answer to that question, the processing load on the information system can be reduced, and the storage capacity for holding information regarding questions and answers is reduced. can do.

The question and the answer in the natural language can be obtained and output in various data formats, but it is preferable to obtain them as voice data or text data. And claim 10
It may be output as voice or text as shown in. Further, it is preferable that the voice data and the text data can be converted as described in claim 11. For example, voice data and text data may be converted to each other. In this way, for example, the question input by voice from the questioner is output to the respondent by text display, the question input in text from the questioner is output to the respondent by voice, and It is possible to output a text response input from the respondent to the questioner by voice, or output a voice response input from the respondent in text. The text data may be obtained in response to input from the keyboard, or may be input as voice and obtained by voice recognition.

When the acquired question or answer contains an inappropriate keyword, it is preferable not to output the question or answer as described in claim 12. By doing so, the questioner and the respondent can comfortably use the system without receiving a message including an inappropriate keyword.

By the way, the category storage means according to claim 1 stores a plurality of categories for classifying questions and the strength of each respondent in each category in association with each other. The degree may be stored based on the information acquired from the respondent, or as shown in claim 13, the questioner's evaluation of the answer is acquired, and based on the acquired evaluation, the respondent's strength Should be updated. For example, if the questioner's evaluation is high, the strength of his or her interest is increased, and if the questioner's evaluation is low, the strength of his or her interest is lowered. In this way, since the degree of specialty changes according to the evaluation of the respondent, it is possible to more appropriately determine the respondent to be output. In particular, it is effective when the respondent himself sets the initial value of the specialty level.

The information system described in each claim is
Since each of them may constitute an information system as a whole, for example, one server (computer) may be provided with all the means as shown in claim 14, or, for example, the interrogator side terminal of claim 15, Like the center and the respondent side terminal, the respective means or parts within the means may be shared (distributed) by a plurality of devices such as computers. In the case of claim 14, while the configuration is such that it is acquired from the network or output to the network,
According to the fifteenth aspect, the configuration includes a part that is acquired from the user or output to the user. Further, the information system may be composed of a plurality of different computers, installed in different places, and information may be exchanged between the computers by communication.

The interrogator side terminal and the responder side terminal of such an information system can be various terminals, but particularly when they are terminals that can be used from a mobile body, an excellent effect is exhibited. For example, with a navigation device as set forth in claim 16, it is possible to easily obtain necessary information as an answer while moving. In particular, a GPS or the like is provided, and
With the above configuration, information near the current position can be easily obtained.

By the way, when a category is extracted from a question in natural language as shown in claim 2, claim 1 is used.
As shown in FIG. 7, the terminal as the interrogator side terminal extracts a category from a question in natural language by voice,
It is preferable to provide a function of informing the questioner of the extracted category, confirming whether the category is correct, and transmitting the extracted category and question when the category is correct. In this way, the processing load on the center side can be reduced, and the questioner can easily determine the category and increase the possibility of obtaining an accurate answer to the question.

By considering each means in the information system described in each claim as a processing step,
It can be a method invention. That is, for example, the information system described in claim 1 can be regarded as a configuration that realizes the information acquisition method described in claim 18. According to the information acquisition method of claim 18, it is possible to obtain the same effect as that of claim 1 described above. Similar to claim 18, by grasping each means in the information system according to each of claims 2 to 16 as a step, the invention can be an information acquisition method. According to the information acquisition method, the invention can be achieved. The same effect as the above-mentioned effect can be obtained.

When each means in the information system according to any one of claims 1 to 16 is realized by a computer system as shown in claim 19, for example,
It can be provided as a program activated on the computer system side. In the case of such a program, for example, a flexible disk, a magneto-optical disk, a CD-R
It can be used by recording it on a computer-readable recording medium such as an OM, a hard disk, a ROM, a RAM, and by loading it into a computer system and activating it as necessary, or by loading it via a network and activating it. Can also be used.

[0022]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments to which the present invention is applied will be described below with reference to the drawings. Needless to say, the embodiment of the present invention is not limited to the following examples, and various forms can be adopted as long as they are within the technical scope of the present invention.

As shown in FIG. 1, the present system includes an interrogator side terminal 10 which can be connected to the Internet, respectively.
The center 20 and the respondent side terminal 30 are provided. The interrogator side terminal 10 and the respondent side terminal 30 include a CPU, a ROM,
A computer system including a memory such as a RAM, an I / O and a bus line connecting the I / O, and the like, wherein the I / O is an A / D conversion device that converts a microphone or an audio signal generated by the microphone into audio data. A voice input device including the above, a voice output device for outputting voice from a speaker, a display, a keyboard, a communication device for connecting to the Internet for communication, and the like are connected. Then, the CPU executes the program stored in the memory to input a voice from a microphone or the like to obtain voice data, a voice data acquisition function, and perform voice recognition based on the obtained voice data to perform text recognition as a recognition result. A voice recognition function for obtaining a text, a text acquisition function for obtaining a text based on an input to a keyboard, a transmission function for transmitting information obtained by these functions to the center 20, and a reception function for receiving information transmitted from the center 20 By utilizing these functions, the interrogator side terminal 10 executes the process in the interrogator side terminal described later, and the responder side terminal executes the process in the interrogator side terminal described later.

Questioner side terminal 10 and respondent side terminal 30
Can be configured as, for example, a navigation device, a mobile phone, a game machine, a personal computer, and various other information devices. The questioner side terminal 10 and the respondent side terminal 3
0 may be configured as one terminal. In this case, this terminal functions as the interrogator side terminal 10 when the user makes a question or an evaluation described later (when becoming the interrogator), and when the user makes an answer (when becoming the respondent), the respondent It functions as the side terminal 30.

The center 20 includes a CPU, ROM and RAM
Is a computer that functions as a general server including a memory such as I / O, a bus line connecting these, and the like, and a disk device, a communication device connected to the Internet, and the like are connected to the I / O. There is. The disk device has a user I of an interrogator or an answerer, which is used in the processing described later.
User information such as D, name, address, age, sex, hobbies, work content, etc., a list of question categories, and a specialty category table 40 (FIG. 2A) showing the strength of each user in each category.
) And a list of inappropriate keywords. Then, the CPU executes the program stored in the memory, whereby the interrogator side terminal 10 and the respondent side terminal 3
The functions of receiving information from 0 via the Internet and transmitting information to these terminals are realized, and these functions are used to perform processing relating to questions and answers to be described later.
The center 20 can be connected to a large number of questioner-side terminals 10 and respondent-side terminals, and various processes are executed in parallel by multitasking.

When the questioner who is the user of the questioner side terminal 10 makes a question, the content of the question is input to the questioner side terminal 10 in a natural language from a voice or a keyboard. Further, the questioner selects a category corresponding to the content of the question to be input from the menu displayed on the questioner side terminal 10. For example, as shown in FIG. 2B, this category is included in the major categories such as “(1) Travel / sightseeing, (2) Eating and drinking, (3) Hobbies ...” and the major categories. It has a hierarchical structure consisting of subcategories such as "parks, theme parks, shrines ...". The questioner side terminal 10 previously acquires from the center 20 and stores such a category of questions, that is, a list of categories as shown in FIG. 2B showing the genre (category) of the question. It is displayed in a format and selected using a keyboard or the like. Further, the questioner can input position information, which is a place related to the question, an answer deadline that specifies a time limit of the answer, and the like, if necessary.

For example, as shown in FIG. 1, the questioner inputs a question by voice, "Isn't there a pork bone ramen restaurant with a delicious and rich taste in Nagoya?" When "Ramen", "Nagoya" as the place, and "30 minutes" as the response time limit are selected, the interrogator side terminal 10 transmits these inquiry information to the center together with the user ID. The question category, position information, answer deadline, etc. may be obtained from the result of voice recognition of the content of the natural language. Further, the question is acquired as, for example, text data or voice data and transmitted to the center 20 as a mail or a voice mail.

The center 20 receives the inquiry information and the user ID transmitted from the interrogator side terminal 10, and uses the specialty category table 40 or the like as shown in FIG. Determine the respondents to whom the received inquiry information will be sent. This specialty category table 40 is
As shown in FIG. 2A, the strength of each category is stored for each user. Then, the inquiry information is transmitted to the respondent side terminal 30 of the determined respondent.

The respondent side terminal 30 receives this inquiry information and informs the question in the natural language included in the received inquiry information as a voice or text. Then, when the respondent answers the question informed in this way, for example, as shown in FIG.
There is a ramen shop called "," etc. in a natural language as voice or text. The respondent side terminal 30
The answer of the input voice data or text data of the natural language is transmitted to the center 20 as a mail or a voice mail together with the user ID of the respondent.

When the center 20 receives the answer and the user ID from the answerer side terminal 30, the center 20 transmits the answer and the user ID of the answerer to the questioner side terminal 10. Upon receiving the answer and the user ID of the answerer, the interrogator side terminal 10 notifies the answer by voice or text. As a result, the user can get an answer to his / her question. Then, when the questioner inputs an evaluation to the notified answer to the questioner side terminal 10, the questioner side terminal 10 transmits the evaluation to the center 20,
The center 20 updates the above-mentioned specialty category table 40 based on the received evaluation.

In the following, with respect to a more detailed example of the above-mentioned processing, the content of the processing of each device will be described with reference to FIGS. FIG. 3 is a flowchart showing a flow of a question time process executed in the interrogator side terminal 10 when the question input instruction is a keyboard or voice input in the interrogator side terminal 10. 4 is a functional block diagram showing the contents of the interrogation process in FIG.

The interrogator side terminal 10 is, as shown in FIG.
First, the voice recognition dictionary is set to a dictionary for natural language input to enable the input of inquiry information by voice, and also the input of inquiry information by manual input (keyboard, button input, screen operation, etc.) (S110). ). Then, the input of natural language inquiry information by voice or text from the user is accepted (S120) (the function of performing this voice or manual input corresponds to the user interface shown in FIG. 4). The input content by voice or manual input can include, in addition to the question, a category of the question, a place (positional information), a respondent, a response deadline, and the like. For example, after inputting the content of the question, it is possible to input "Category is XX, place is Aichi, respondent is XX, and deadline is within 30 minutes". The question category, place (positional information), respondent, answer deadline, etc. may be included in the question. For example, the location (location information) may be included in the question, such as "Is there a delicious ramen restaurant in Nagoya?" Or "Is there a beautiful place with autumn leaves around here?" The response deadline is "1.
It may be specified by a relative time from the present such as "within time" or by an absolute time such as "until 17:30". When the input contents input in this way are input by voice, the voice data and text data obtained by voice recognition of the voice data are stored as inquiry information, and when input manually, , Text data is stored as inquiry information (S130, FIG. 4).
Corresponding to the inquiry record).

At S140, it is determined whether the respondent is designated as the inquiry information based on the text data stored at S130. When the respondent is designated (S140: YES), Move to S200,
If not specified (S140: NO), S15
Move to 0.

In S150, it is determined whether or not clear position information (position information previously stored in the memory as a list of position information) is designated as the inquiry information in S130.
If the position information is specified based on the text data stored in step S150 (YES in S150), step S17
If the position information is not designated (S15)
0: NO), and shifts to S160. For example, when the text data of the inquiry information that does not include the clear position information such as "Is there a beautiful place of autumn leaves around here?" Is stored or the position information is not included, the process proceeds to S160. To do.

In S160, the current position is detected by the GPS provided in the interrogator side terminal 10, and the information of the area corresponding to the detected current position is added to the inquiry information and stored. For example, "place is Aichi prefecture" is added. In S170, if the text data of the inquiry information includes position information, the position information is extracted, and the extracted position information is stored as inquiry information for transmission in addition to the inquiry information stored in the memory in S130 ( This corresponds to the position information generation in FIG. 4). For example, if the text data of the inquiry information is "Is there a delicious ramen restaurant in Nagoya?", "Nagoya" is extracted and stored as the position information.

In S180, if the text data of the inquiry information includes a category, the category is extracted and the category database stored in the memory shown in FIG. 4 is referred to. In S190, whether the category extracted in S180 is a category in the category list or not is determined by referring to the category database storing the category list. If the category is in the category database, the category is set for transmission. Store in addition to inquiry information. If the category could not be extracted, or if the extracted category is not in the category database, the category stored in the category database is displayed on the display device in a menu format and is selected by voice or manual input. The selected category is stored as inquiry information for transmission. The category database stores categories in the hierarchical structure shown in FIG. 2B, and the menu is displayed based on this hierarchical structure. Therefore, the user (questioner) can determine the genre (category) of the inquiry by simply following the hierarchy of categories. A plurality of categories may be designated.

On the other hand, in S200, the user information constructed from the past communication history is referred to, and in the subsequent S210, the user ID of the respondent designated as the inquiry information is acquired and added to the inquiry information for transmission (see FIG. It corresponds to "user information" and "user ID" of No. 4.) The questioner may directly input the user ID of the respondent.

Then, in S220, it is determined whether or not the reply deadline is included in the text data of the inquiry information.
If included (S230: YES), the process proceeds to S240, and if not included (S230: NO), S23.
Move to 0. In S230, the initial setting time stored in advance in the memory is set as the reply deadline of the inquiry information. The initial setting time is, for example, 1 hour, 6 hours from the present,
It can be one day or the like.

In S240, the response deadline is acquired from the inquiry information and added to the inquiry information for transmission (corresponding to the generation of the response deadline time in FIG. 4). If the response deadline is specified as a relative time from the present, such as "within 30 minutes", it is converted to an absolute time (date, time, etc.) and then sent as the response deadline. Add to inquiry information.

In S250, the questioner's user information is referred to, and in S260, the questioner's user ID is acquired. Then, in S270, the inquiry information for transmission and the user ID of the interrogator acquired in S260 are transmitted to the center 20.

In S280, the transmission of the reply information and the user ID of the respondent is waited for from the center, and the reply information and the user ID of the respondent are received (corresponding to acquisition of reply information in FIG. 4). Then, the answer information and the user ID of the answerer are stored in the memory (S290), and when the answer included in the answer information is text data, the answer is displayed on the display, and when the answer is voice data, the speaker is output as voice. Etc. (S300). When the answer is text data, a voice corresponding to the text data may be synthesized and output.

In S310, a display prompting the user to select whether or not to input an evaluation for the answer is displayed, and when an instruction to evaluate the answer is input from a keyboard or the like (S310: YES), FIG. If the instruction to evaluate is not input (S31)
0: NO), the process proceeds to S380 of FIG.

In S320, voice input and manual input (keyboard, button input, screen operation, etc.) are possible, and S330
In, a natural language input by voice and text from the user is accepted, and at least one of voice data and text data is obtained as in S120. For example, the questioner inputs by voice the evaluations such as “OK,” and “Very good”, and obtains these voice data and the text data of the voice recognition result.

Then, in S340, an evaluation value is determined based on the text data obtained in S330. For example, the evaluation value is a value of 5 levels from 1 to 5, and for example, the evaluation value in natural language corresponds to the evaluation value of 3 when the evaluation value includes “OK” and the evaluation value 4 when including “very good”. The evaluation value is determined based on the data such as the evaluation value determination table that has been stored (corresponding to the evaluation value generation in FIG. 4). Of course, the evaluation value may be directly input by voice or manually.

In subsequent S350, the interrogator's user information stored in the memory is referred to, and the interrogator's user ID is acquired in S360. Then, in S370, the evaluation value determined in S340, the user ID of the respondent, and the category included in the response information received in S280 are used as the evaluation information.
The information is transmitted to the center 20 together with the interrogator's user ID acquired in S360.

In S380, the information prompting the user to input whether or not to end the question is displayed, and if an end instruction is input (S380: YES), this process is ended and an instruction to continue is input. If so (S380: NO), the process proceeds to S110 in FIG. When the instruction to continue is input, for example, a message asking the questioner whether to specify the respondent of this answer as the respondent of the next question is displayed, and the respondent of the next question is displayed. When the instruction to specify is input, the respondent should be included in the inquiry information. In this way, it is easy to continuously send questions to respondents who have provided useful answers.

Next, the processing of the center 20 when the center 20 receives a question (when a question is received) will be described with reference to the flowchart of FIG. Further, FIG. 7 shows a functional block diagram of the center 20. In S410 of FIG. 6, the inquiry information including the question (inquiry), the category, the position information, the response deadline, the respondent ID, and the like transmitted from the questioner side terminal 10 and the questioner's user ID are received.

In S420, the user information stored in the center 20 is acquired, and in S430, it is checked whether the user ID received in S410 is included in the user information acquired in S420. Then, in S440, it is determined whether or not there is corresponding user information, and if there is corresponding user information (S440: YES), the process proceeds to S450, while if there is no corresponding user information (S4:
40: NO), and proceeds to S480. In S480, an error message is transmitted to the interrogator side terminal 10 and the inquiry information is deleted. That is, the questioner's user is authenticated, and only after being authenticated, the processing of S450 and thereafter is performed (corresponding to “user check and user information acquisition from user ID” in FIG. 7).

In S450, the inappropriate keyword list stored in the center 20 is referred to, and in S460, it is checked whether the inquiry information contains an inappropriate keyword. If only voice data can be extracted from the inquiry information, the voice data may be recognized by voice recognition to determine the presence or absence of an inappropriate keyword.

In S470, it is determined from the result of the check in S460 whether the content of the inquiry information is appropriate. If the content of the inquiry information is appropriate (S4
70: YES), the process proceeds to S490, and if the content of the inquiry information is not appropriate (S470: NO), S48.
Move to 0 (corresponding to the check of the question in FIG. 7). S
At 480, an error message is sent to the terminal and the inquiry information is deleted.

In S490, the answer deadline included in the inquiry information is referred to and saved in S500 (corresponding to saving the answer deadline time in FIG. 7). In S510, it is determined whether or not the respondent is designated based on whether or not the respondent ID is included in the inquiry information. When the respondent is designated (S510: YES), the process proceeds to S550, When the respondent is not designated (S510: NO), S5
Move to 20.

In S520, the position information included in the inquiry information and the user information stored in the center 20 are referred to, and in S530, the category included in the inquiry information and the specialty category table 40 stored in the center 20 are referred to. Then, the respondents are selected in S540 (corresponding to “selecting respondents from inquiry category and position information and strong category table” in FIG. 7).
As shown in FIG. 2 (a), the category stores the degree of specialty for each user (respondent). That is, which genre (category) the user is good at (knows well) is stored as a degree of goodness, and the degree of goodness is expressed by a numerical value in FIG. 2A. Figure 2 (a)
Indicates that the larger the value, the better the strength, and the smaller the value, the weaker the strength. Note that the specialty level may be expressed by a vector or the like instead of a numerical value. The user level may be input by the user (respondent) himself at the time of user registration, or may be entered in the user information when the user information is registered, such as age, sex, hobbies, work content, etc. It may be automatically determined from the profile.

The selection of the respondents in S540 is performed, for example, by extracting the users whose place designated as the position information is included in the address stored as the user information. For example, when "Nagoya city" is included as the position information, the users whose address stored as the user information includes "Nagoya city" are extracted. Then, with respect to the extracted users, for example, a predetermined number of persons (for example, 10 people) is output in order from the user having a high category specialty, by referring to the category expertise included in the inquiry information. Decide as a person. It should be noted that there may be a plurality of respondents like this.
You can be just a person.

Then, in S550, the user information of the respondent is referred to, the user information is acquired in S560, and S57 is obtained.
The inquiry information at 0 and the user ID of the interrogator received at S410 are transmitted to the respondent side terminal 30 of the respondent. next,
In this way, the respondent-side terminal 3 when the inquiry information and the questioner's user ID transmitted from the center 20 are received
The process of 0 will be described with reference to the flowchart of FIG. 8 and the functional block diagram of FIG.

In S610 of FIG. 8, the inquiry information and the user ID of the inquirer are received from the center 20, and S620
Is stored in the memory in step S630, and the question in the inquiry information is output to the respondent by voice or display in step S630. That is, when the question is text data, the question is displayed on the display, and when the question is voice data, it is output as voice from a speaker or the like. When the question is text data, a voice corresponding to the text data may be synthesized and output.

In S640, a display prompting the user to select whether or not to input the answer to the output question is displayed, and if an instruction to evaluate the answer is manually input or input by voice (S640: YES). ), Move to S650,
When the instruction not to evaluate is input (S64
(0: NO), the process proceeds to S700 and the non-response message is sent to the center 20.

In step S650, the voice recognition dictionary is set to a dictionary for natural language input to enable input of inquiry information by voice, and input of inquiry information by manual input (keyboard, button input, screen operation, etc.) is performed. to enable. Then, in S660, the input of a natural language answer by voice or text from the user is accepted, and the answer is acquired as voice data or text data. The function of performing this voice or manual input corresponds to the user interface shown in FIG.

Then, in subsequent S670, the user information of the respondent stored in the memory is referred to, and the user ID of the respondent is acquired in S680 (corresponding to user ID acquisition in FIG. 9). Then, in S690, the answer and the user ID of the interrogator received in S610 and the inquiry information are transmitted to the center 20 as the response information together with the user ID of the respondent (corresponding to the communication in FIG. 9).

Next, referring to the flowchart of FIG. 10 and the functional block diagram of FIG. 7, regarding the processing in the center 20 when receiving the reply information and the user ID of the answerer transmitted from the answerer side terminal 30 in this way. Explain. In S810 of FIG. 10, the response information and the user ID of the respondent are received. Then, in S820, the user information is referred to, and S83
At 0, it is checked whether the user ID received in S810 is included in the user information referred to in S820. Then, in S840, it is determined whether there is corresponding user information, and if there is corresponding user information (S84
0: YES), the process proceeds to S850, and if there is no corresponding user information (S840: NO), the process proceeds to S910. That is, the user authentication of the respondent is performed (corresponding to “user check and user information acquisition from user ID” in FIG. 7).

In S850, the reply deadline included in the inquiry information in the reply information received in S810 is referred to,
In S860, it is determined whether or not a response has been made within the response deadline based on the response deadline and the current date and time (corresponding to the check of the response deadline time in FIG. 7). If the answer is within the answer deadline (S860: YES), the process proceeds to S870, and if the answer is not within the answer deadline (S86).
0: NO), and proceeds to S910.

In S870 to S890, the inappropriate keyword list stored in the center 20 is referred to in the same manner as in S450 to S470 of FIG. 6 described above (S87).
0), it is checked whether or not the answer to the inquiry information includes an inappropriate keyword (S880). And
From the check result, it is determined whether or not the content of the inquiry information is appropriate (S890). If the content of the inquiry information is appropriate (S890: YES), S900
If the content of the inquiry information is not appropriate (S890: NO), the process proceeds to S910 (corresponding to the answer check in FIG. 7).

In S900, the answer information and the user ID of the answerer are transmitted to the questioner side terminal 10 based on the user ID of the questioner included in the answer information. In this way, the answer information including the answer of the answerer can be sent to the interrogator side terminal 10. At the interrogator side terminal 10, S2 of FIG.
By the processing shown from 80 onward, the answerer is informed of the answer, and the evaluation information is transmitted to the center 20 by the processing of FIG. 5 as necessary.

On the other hand, in S910, an error message is transmitted to the respondent side terminal 30, and in S910 the response is deleted. Next, the processing of the center 20 when receiving the evaluation information from the interrogator side terminal 10 will be described with reference to the flowchart of FIG. 11 and the functional block diagram of FIG. 7.

In S1010 of FIG. 11, the interrogator side terminal 1
The evaluation information and the user ID of the questioner transmitted from 0 are received. In S1020, the user information stored in the center 20 is acquired, and in S1030, it is checked whether the user ID of the interrogator received in S1010 is included in the user information acquired in S1020. And S1040
Then, it is determined whether there is corresponding user information, and if there is corresponding user information (S1040: YE
On the other hand, if there is no corresponding user information (S1040: NO), the process proceeds to S1070. In S1070, an error message is transmitted to the interrogator side terminal 10. That is, the questioner's user is authenticated, and the processing from S1050 is performed only when the user is authenticated (corresponding to "user check and user information acquisition from user ID" in FIG. 7).

In S1050, the customer category table 40 is referred to, and in S1060, the user ID of the respondent included in the evaluation information received in S1010 and the customer degree corresponding to the category in the customer category table 40 are evaluated. Is updated based on the evaluation included in (corresponding to the update of the specialty category table in FIG. 7). For example, if the evaluation value is 4, 0.4, which is 1/10 of that, is added to the degree of interest.

With the above-described configuration, it is possible to select an inquirer who is good in the field and make an inquiry and obtain an answer to an ambiguous inquiry of an inquirer who is difficult to understand by the system. In the above embodiment, the respondents are decided based on the category, the position information, etc. However, for example, if the users are grouped in advance and the respondents of the inquiry destination are decided within the range of the group. Good. Further, only the respondents in the group designated by the user may be determined as the respondents of the inquiry destination. That is, a group may be designated as the additional information in the claims. The group may be set so that the respondent can set his own group, or may be set automatically from the user information stored in the center 20. For example, referring to user information,
Group by sex.

As a method of transmitting inquiry information to the respondents who have narrowed down the inquiry based on category, respondent, place (positional information), etc. OK, you may send a limited number of the respondents who have been narrowed down, or you may send at least one from the highest ranked category value among the narrowed down respondents to give feedback from the questioner (answers). ) And decide whether to send it to the next respondent.

In the above embodiment, the center 20 updates the specialty category table 40 based on the evaluation information when receiving the evaluation information from the interrogator side terminal 10. When it is received from the terminal 30, it may be updated so as to increase the evaluation. Further, when the reply information is not sent by the reply deadline, the evaluation may be updated so as to lower the evaluation.

In the present embodiment, when the invention described in each claim is grasped by the structure shown in claim 14, the center 20 corresponds to an information system which is a server, and the specialty category table 4
The disk device that stores 0 corresponds to the category specialty degree storage unit, the disk device that stores user information corresponds to the respondent information storage unit, and the process of S410 is the question acquisition unit.
Corresponding to the processing as a category acquisition means / additional information acquisition means / response time limit acquisition means, S450 to 470, S870
The processes of to 890 correspond to the process as the inappropriate keyword determining unit, the processes of S510 to 560 correspond to the process of the respondent determining unit, and the process of S570 corresponds to the process of the question outputting unit. Further, the processing of S810 corresponds to the processing as the answer acquisition means, and the processing of S900 corresponds to the processing as the answer output means. And S1010
Processing corresponds to the processing as the evaluation acquisition unit, and S106.
The processing of 0 corresponds to the processing as the specialty degree updating means.

When the invention described in each claim is grasped with the structure shown in claim 15, the interrogator side terminal 10 corresponds to the interrogator side terminal, the center 20 corresponds to the center, and the respondent side terminal. Reference numeral 30 corresponds to the respondent side terminal, and the questioner side terminal 10, the center 20, and the respondent side terminal 3 shown in FIGS.
A system consisting of 0 corresponds to an information system.

[Brief description of drawings]

FIG. 1 is an explanatory diagram showing a configuration of an information system and a usage example.

FIG. 2 is an explanatory diagram showing a specialty category table and a list of categories.

FIG. 3 is a flowchart showing a process at the time of a question in the interrogator side terminal.

FIG. 4 is a functional block diagram of an interrogator side terminal.

FIG. 5 is a flowchart showing processing at the time of evaluation in the interrogator side terminal.

FIG. 6 is a flowchart showing a process when a question is received at the center.

FIG. 7 is a functional block diagram of a center.

FIG. 8 is a flowchart showing processing in the respondent terminal.

FIG. 9 is a functional block diagram of a respondent terminal.

FIG. 10 is a flowchart showing processing when a response is received at the center.

FIG. 11 is a flowchart showing a process when an evaluation is received at the center.

[Explanation of symbols]

10 ... Questioner side terminal 20 ... Center 30 ... Respondent side terminal 40 ... Good category list

Continued front page    F term (reference) 2F029 AA02 AA07 AC13 AC18                 5B075 NR12 PP07 PP24 PQ04 UU40                 5H180 AA01 AA21 AA30 BB01 BB13                       FF13 FF25 FF27 FF32

Claims (19)

[Claims] 1. A plurality of categories for classifying questions,
Category specialty degree storing means for storing the strength of each respondent in each category in association with each other, question obtaining means for obtaining a question in a natural language from the questioner, and category for obtaining the category of the question in a natural language Acquisition means, based on the strength of each of the respondents stored in the category strength degree storage means in the category acquired by the category acquisition means, the respondents who are the output target of the question acquired by the question acquisition means, Respondent determination means for determining, question output means for outputting the question to the respondent determined by the respondent determination means, answer acquisition means for acquiring an answer in natural language to the question, the answer acquisition And an answer output means for outputting the answer acquired by the means to the questioner. . 2. The information system according to claim 1, wherein the category acquisition unit acquires the category as a category selected from a category list notified to a questioner, or the question. An information system characterized by extracting and acquiring from a question in a natural language acquired by an acquisition means. 3. The information system according to claim 1, further comprising: additional information acquisition means for acquiring additional information from the questioner with respect to the question, wherein the respondent determination means is the additional information acquisition means. An information system characterized in that the respondent to be output is determined in consideration of the acquired additional information. 4. The information system according to claim 3, further comprising an answerer information storage means for storing information about an answerer, wherein the answerer determination means includes the additional information acquired by the additional information acquisition means, An information system, characterized in that the respondent to be output is determined based on the information regarding the respondent stored in the respondent information storage means. 5. The information system according to claim 4, wherein the respondent information storage unit stores, as the information regarding the respondent, position information indicating an area in which the respondent is good at, and asks the question as the additional information. An information system characterized by using related position information. 6. The information system according to claim 5, wherein the position information is information indicating a current position of the interrogator. 7. The information system according to any one of claims 3 to 6, wherein the additional information includes respondent designation information for designating a respondent, and the respondent determination means specifies the respondent. An information system characterized in that a respondent designated by information is determined as the respondent to be output. 8. The information system according to any one of claims 1 to 7, further comprising: an answer deadline acquisition unit that acquires an answer deadline of a question from a questioner, wherein the answer acquisition unit is the answer deadline acquisition unit. An information system characterized in that it acquires an answer to the question until the acquired answer deadline, and the answer output means outputs the answer to the question until the answer deadline acquired by the answer deadline acquisition means. 9. The information system according to claim 1, wherein the question acquisition unit and the answer acquisition unit acquire the question or the answer as voice data or text data. Information system. 10. The information system according to claim 1, wherein the question output unit and the answer output unit output the question or the answer as voice or text. . 11. The information system according to claim 9 or 10, further comprising data conversion means for converting the data format of voice data and text data. 12. The information system according to any one of claims 1 to 11, further comprising: an inappropriate keyword determining unit for determining whether or not an inappropriate keyword is included in the question or the answer, The information system, wherein the keyword determining means prohibits the output of the question or the answer when it is determined that the keyword is included. 13. The information system according to any one of claims 1 to 12, wherein an evaluation acquisition unit acquires an evaluation of a questioner with respect to the answer output by the answer output unit, and an evaluation acquisition unit acquires the evaluation. An information system, comprising: a strength update means for updating the strength of the respondent stored in the category storage means based on an evaluation. 14. The information system according to claim 1, wherein the information system is a server, and the server is configured to be communicable with a questioner side terminal and a respondent side terminal via a network. The question acquisition unit receives the question from the questioner side terminal, the category acquisition unit receives the category from the questioner side terminal, and the question output unit answers the question. An information system, wherein the answer acquisition means receives the answer from the answerer side terminal, and the answer output means sends the answer to the questioner side terminal. 15. The information system according to claim 1, wherein the information system includes an interrogator side terminal, a center, and a respondent side terminal, and the center is the interrogator side. It is configured to be able to communicate with a terminal and the respondent side terminal via a network, and the question acquiring means, the questioner side terminal for inputting a question from a questioner and transmitting it to the center, and the questioner. It is composed of the center that receives the question transmitted from the side terminal, and the category acquisition means is transmitted from the questioner side terminal that transmits the category acquired from the questioner to the center and the questioner side terminal. The question output unit is configured to receive the question and the question output unit is configured to transmit the question to the respondent side terminal, and the center to be transmitted from the center. The answer acquisition means is configured to include an answerer side terminal that receives a question and outputs the answer to the respondent, and the answer acquisition unit is transmitted from the answerer side terminal that transmits the answer to the center and the answerer side terminal. The answer output means is composed of the center that sends the answer to the interrogator side terminal, and the answerer side terminal that receives the answer sent from the center. Information system characterized by: 16. The information system according to claim 14, wherein at least one of the interrogator side terminal and the respondent side terminal is a navigation device. 17. A terminal as the interrogator side terminal in the information system according to any one of claims 14 to 16, which recognizes a voice question input from the interrogator, and based on the recognition result, From the list of categories stored in advance, a category corresponding to the input voice is determined and notified, and an instruction that the notified category is appropriate as the category of the voice question input from the interrogator is the interrogator. A terminal which transmits the informed category and the question input by the questioner when input from the terminal. 18. A plurality of categories for classifying a question and the strength of each respondent in each category are stored in association with each other, a question in a natural language from the questioner is acquired, and a category of the question is acquired. Then, the respondent who outputs the question is determined based on the stored strength of each respondent in the question category, the question is output to the determined respondent, and the natural language for the question is output. The method for acquiring information is characterized by acquiring the answer by and outputting the answer to the questioner. 19. A program for causing a computer to function as the information system according to any one of claims 1 to 16.