JP7231289B2 - voice response system - Google Patents

Description

Cross-reference to related applications

This international application is Japanese Patent Application No. 2 filed with the Japan Patent Office on June 18, 2012
012-137065, Japanese Patent Application No. 2012-137066, and Japanese Patent Application No. 2012-137067, which claims priority based on Japanese Patent Application No. 2012-137065, Japanese Patent Application The entire contents of No. 2012-137066 and Japanese Patent Application No. 2012-137067 are incorporated into this international application by reference.

The present invention relates to a voice response system that makes responses by voice.

As the above-described voice response device, there is known one that retrieves an answer to an input question from a dictionary and outputs the retrieved answer by voice (see Patent Document 1, for example). Also known is a technique for generating an answer to a question based on the content of dialogue with a user (see Patent Document 2, for example).

Japanese Patent No. 4832097 Japanese Patent No. 4924950

The above technique is set to simply give one answer specified by a dictionary to one question.
It is an aspect of the present invention to make voice response systems more user-friendly.

In the invention of the first aspect ,
A voice response system comprising: a request source device that requests a request; a provider device that provides information; and a server capable of communicating with the request source device and the provider device,
The provision source device is configured to be able to set whether to permit information provision,
The server acquires a request from the requesting device, and if the request includes a request specifying the providing source device, transmits the request to the specified providing source device, an information acquisition unit configured to acquire provided information provided from the provider device when the provision is permitted;
a providing unit configured to generate a voice response based on the provided information as a response to a request from the requesting device and to provide the response to the requesting device;
Prepare.
In another aspect of the invention,
A voice response device for responding to input character information by voice,
response acquisition means for acquiring a plurality of different responses to the character information;
voice output means for outputting the plurality of different responses in different voices;
characterized by comprising

According to such a voice response device, a plurality of responses can be output in different tones. can be output in an easy-to-understand manner. Therefore, it is possible to improve usability for the user.

The voice response device of the present invention may be configured as a terminal device possessed by the user, or may be configured as a server that communicates with this terminal device. Character information may be input using input means such as a keyboard, or may be input by converting voice into character information.

By the way, in the above voice response device, like the second aspect of the invention,
Voice input means for the user to input voice, converting the input voice into character information,
voice transmission means for transmitting to an external device that generates a plurality of different responses to the text information and transmits them to the voice response device;
with
The response acquisition means may acquire the response from the external device.

According to such a voice response device, voice can be input in the voice response device, so that character information can be input by voice. In addition, since the response can be generated in the external device, the processing load on the voice response device can be reduced.

In the voice transmitting means, the operation of "converting the input voice into character information" may be performed by the voice response device or may be performed by an external device.
Furthermore, in the above voice response device, as in the third aspect of the invention,
The voice response device or the external device comprises response recording means in which a plurality of different responses including positive responses and negative responses to each piece of character information are recorded for each of the plurality of pieces of character information,
The response acquisition means acquires the positive response and the negative response as the plurality of different responses,
The voice output means may reproduce the affirmative response and the negative response in different tones.

According to such a voice response device, responses from different standpoints, such as affirmative responses and negative responses, can be reproduced with different voices. can be done. Therefore, it is possible to make it difficult for the user who listens to the voice to feel uncomfortable.

Note that the tone of voice may be changed depending on the type of response or the wording used when responding. For example, when responding in a gentle tone, a calm female voice may be played back, and when responding in a violent tone, a brave male voice may be played back. In other words, it is sufficient to associate the content of the response with the personality, and set the tone of voice according to the personality.

Further, the above-described voice response device can be configured to be used at a reception desk in a workplace or a company, or can be configured to convey something that is difficult for the user to say directly to someone instead, as in the fourth aspect of the invention.

When using a voice response device at the reception, the name and company name of the person who comes to the sales are recorded in the voice response device or an external device in advance, and the person who came to the reception gave this name or company name. In that case, the response should be generated so as to play back the voice of the refusal phrase.

Also, in the case of a configuration in which something difficult to say is to be conveyed instead, for example, before a date, if one speaks to the apparatus that he would like to say something today, it can be arranged at an appropriate timing (for example, at a preset time or at a predetermined time). , when a certain amount of time has passed since the conversation was interrupted, etc.), the voice response device should speak instead (reproduce the voice).

Alternatively, it may be configured to speak a word that triggers something difficult to say, for example, a word like "Speaking of which, didn't you tell her something?" That is, instead of outputting the response immediately, the response may be output when the reproduction condition is satisfied, such as after a certain period of time has elapsed.

Further, in the voice response device, as in the fifth aspect of the invention, the external device or the voice response device may acquire information for generating a response to character information from another voice response device. . Further, in the above voice response device, as in the sixth aspect of the invention, when information for generating a response to character information is requested from another voice response device, the information corresponding to this request is returned. may

In this case, the voice response device should be equipped with sensors for detecting location information, temperature, humidity, illuminance, noise level, etc., and a database of dictionary information, etc., and extract necessary information upon request. should be

Such a voice response device (external device) can acquire information for generating a response from another voice response device. In this case, it is possible to acquire information unique to the other voice response device, such as the location of the other voice response device.

It can also transmit its own information to other voice response devices.
Furthermore, in the above voice response device, as in the seventh aspect of the invention, a response (for example, affirmative response or negative response) output by itself or another voice response device is input as character information, and A response may be generated for rebuttal. In other words, from the standpoint of the user, it is possible to hear arguments by both opinions for and against. After hearing this discussion, the user can make a final decision.

This configuration can be implemented using one or more voice response units. In this case, in order for a plurality of voice response devices to exchange voices, the voices may be directly input/output, or wireless communication may be used.

Further, in the invention of the eighth aspect,
A voice response device for responding to input character information by voice,
personality information acquisition means for acquiring personality information in which the personality of a user or a related person representing a person related to the user is associated according to a preset classification;
response acquisition means for acquiring response candidates representing a plurality of different responses to the character information;
voice output means for selecting a response to be output from response candidates according to the personality information and outputting the selected response;
characterized by comprising

According to such a voice response device, it is possible to give different responses according to the character of the user or a person related to the user (related person). Therefore, it is possible to improve usability for the user.

Further, in the above voice response device, as in the ninth aspect of the invention,
a first personality information generating means for generating personality information of the user or the person concerned based on answers to a plurality of preset questions;
The personality information obtaining means may obtain the personality information generated by the personality information generating means.

According to such a voice response device, personality information can be generated in the voice response device. When generating personality information, well-known personality analysis techniques (Rorschach test, Sondy test, etc.) may be used. Also, when generating personality information, aptitude test technology used by companies and the like for recruitment tests may be used.

Furthermore, in the above voice response device, as in the tenth aspect of the invention,
a second personality information generating means for generating personality information of the user or the related person based on a character string included in the input character information;
The personality information obtaining means may obtain the personality information generated by the personality information generating means.

According to such a voice response device, the user can generate personality information while using the voice response device.
Further, in the above voice response device, as in the eleventh aspect of the invention,
preference information generating means for generating preference information indicating the tendency of the user's or the concerned person's preference based on a character string included in the character information;
The voice output means may select a response to be output from the response candidates based on the preference information, and output the selected response.

According to such a voice response device, it is possible to respond according to the preferences of the user or the person concerned.
Further, in the above voice response device, as in the twelfth aspect of the invention, the user's behavior (conversation, moving place, camera image) is learned (recorded and analyzed), and the user's conversation is learned (recorded and analyzed). You may make up for the lack of words in .

For example, in response to the question "Can I have a hamburger steak today?" However, the reason why he said that curry is good is transmitted.

Also, such a configuration may be implemented during a telephone call, or may be configured to voluntarily participate in the user's conversation.
Furthermore, in the above voice response device, as in the thirteenth aspect of the invention,
response candidate acquisition means for acquiring response candidates from a predetermined server or the Internet;
may be provided.

According to such a voice response device, it is possible to acquire response candidates not only from the own device or an external device, but also from any device connected via the Internet or a dedicated line.
Further, in the above voice response device, as in the fourteenth aspect of the invention,
character information generating means for converting user's actions into character information;
may be provided.

Here, the movement referred to in the present invention corresponds to movement caused by muscles such as conversation, handwriting, or gestures (for example, sign language).
Such a voice response device can convert user's actions into character information.

Furthermore, in the above voice response device, as in the fifteenth aspect of the invention,
The character information generating means converts the voice uttered by the user into character information, and accumulates habits during vocalization (pronunciation habits, etc.) as learning information (obtains characteristics and records these characteristics).
You may do so.

According to such a voice response device, it is possible to generate character information based on learning information, so it is possible to improve the accuracy of character information generation.
Further, in the above voice response device, as in the sixteenth aspect of the invention,
transfer means for transferring the learning information to another voice response device;
may be provided.

According to such a voice response device, even when the user uses another voice response device, the learning information recorded by this voice response device can be used. Therefore, it is possible to improve the accuracy of character information generation even when using other voice response devices.

Further, in the above voice response device, as in the seventeenth aspect of the invention, any one of the user's actions and operations may be detected, and learning information or personality information may be generated based on these. .

According to such a voice response device, for example, when it is detected that the user has jumped on a train for several days in a row, the user is urged to leave the house a few minutes earlier from the next day, or the user is likely to get angry from the conversation. If it detects that there is a tendency, it can output a soothing voice or music.

Further, in the above voice response device, as in the eighteenth aspect of the invention,
Other device information acquisition means for acquiring information recorded in another voice response device from another voice response device may be provided.

Such a voice response device can generate a response based on information recorded in another voice response device.
Furthermore, in the above voice response device, as in the nineteenth aspect of the invention,
reproduction condition determination means for determining whether or not the state of the voice response device matches a reproduction condition set in advance as a condition for outputting voice when the character information is not input;
message reproduction means for outputting a preset message when the reproduction condition is met;
may be provided.

According to such a voice response device, voice can be output even when character information is not input (that is, when the user does not speak). For example, by forcing the user to speak, it can be used as a countermeasure against drowsiness while driving a car. In addition, safety can be confirmed by determining whether or not a person living alone responds.

Further, in the above voice response device, as in the twentieth aspect of the invention,
The message reproduction means may acquire news information and output a message regarding the news in the form of a question requesting the user's answer.

According to such a voice response device, it is possible to have a conversation about news, so it is possible to prevent the same conversations from happening all the time. As for the contents of the conversation, for example, when information about the stock price of a certain company is acquired, it is possible to say, "Today, the stock price of XX company has risen by XX yen. Did you know that?" .

Furthermore, in the above voice response device, as in the twenty-first aspect of the invention,
The voice output means or message reproduction means may output a preset message with externally acquired information (news or environment (temperature, weather, location information, etc.) separately acquired) added thereto.

According to such a voice response device, it is possible to output a response combining a predetermined message and acquired information.
Further, in the above voice response device, as in the twenty-second aspect of the invention,
A plurality of messages may be acquired, and a message to be reproduced may be selected and output according to the reproduction frequency of the messages.

According to such a voice response device, by making it difficult to reproduce frequently reproduced messages, it is possible to achieve randomness during message reproduction, and by repeatedly reproducing frequently reproduced messages, it is possible to call attention and improve memory. It can encourage settlement.

Furthermore, in the above voice response device, as in the twenty-third aspect of the invention,
non-response transmission means for transmitting information identifying the user and a message to the effect that no response was obtained to a preset contact address when no response or response to the message was obtained;
may be provided.

According to such a voice response device, it is possible to report to a contact when an answer cannot be obtained. Therefore, for example, an abnormality such as an elderly person living alone can be notified early.
Further, in the above voice response device, as in the twenty-fourth aspect of the invention,
The message reproducing means memorizes the content of the conversation and asks a question to obtain the same content about the content heard (memory confirmation processing)
You may do so.

According to such a voice response device, it is possible to check the memory of the user and to fix the memory.
Furthermore, in the above voice response device, as in the twenty-fifth aspect of the invention,
utterance accuracy detection means for detecting the accuracy of pronunciation and accent of voice input by the user;
Accuracy output means for outputting the detected accuracy;
may be provided.

According to such a voice response device, it is possible to confirm the accuracy of pronunciation and accent. For example, it is effective when practicing a foreign language.
Further, in the above voice response device, as in the twenty-sixth aspect of the invention,
The degree-of-accuracy output means may output speech including the closest word when the degree of accuracy is equal to or less than a predetermined value.

Such a voice response device allows the user to check the accuracy of pronunciation and accent.
Furthermore, in the above voice response device, as in the twenty-seventh aspect of the invention,
The message reproducing means may output the same question again when the degree of accuracy is equal to or less than a certain value.

According to such a voice response device, an accurate answer can be obtained by outputting the same question.
Further, in the above voice response device, as in the twenty-eighth aspect of the invention,
connection control means for identifying a communication partner based on input character information and connecting a communication destination preset for each communication partner with the communication partner;
may be provided.

According to such a voice response device, it is possible to assist in reception work and answering telephone calls.
In particular, in the above voice response device, as in the twenty-ninth aspect of the invention,
The connection control means may identify a sales activity and a visitor, and reproduce a message to decline if it is a sales activity.

According to such a voice response device, it is possible to eliminate a person who may interfere with the user's work without having to deal with the person himself.
Further, in the above voice response device, as in the thirtieth aspect of the invention, a keyword included in input character information (especially voice) may be extracted and a connection destination corresponding to the keyword may be connected. For example, the keyword such as the name of the other party and the connection destination may be associated in advance.

According to such a voice response device, it is possible to assist in tasks such as call forwarding and calling the receptionist.
Further, in the above-described voice response device, as in the thirty-first aspect of the invention, the requirements for speaking by the other party may be recognized based on the keyword, and an outline of what the other party said may be conveyed to the user.

According to such a voice response device, it is possible to assist the intermediary work with the customer.
Furthermore, in the voice response device, as in the thirty-second aspect of the invention,
An emotion that reads the emotion from the tone of voice input by the user and outputs which emotion corresponds to one of emotions including at least one of anger, joy, bewilderment, sadness, and exaltation. A determination means may be provided.

According to such a voice response device, it is possible to output a response according to the user's emotion.
Next, the thirty-third aspect of the invention is
a response generating means for generating a response according to an image captured around the voice response device when the character information is input;
a voice output means for outputting the response by voice;
characterized by comprising

According to such a voice response device, it is possible to output a response by voice according to the captured image. Therefore, usability can be improved compared to a configuration that generates a response only from character information.

As a specific configuration of the present invention, for example, there is a configuration in which character information is input so as to respond to what the recognized object is, and what (who) is the recognized object from the captured image is output by voice. .

By the way, in the above voice response device, like the thirty-fourth aspect of the invention,
a position specifying means search means for searching an object included in the character information from the captured image by image processing and specifying the position of the searched object;
a guide means for guiding to the position of the object;
may be provided.

According to such a voice response device, it is possible to guide the user to an object in the captured image.
Furthermore, in the voice response device, as in the thirty-fifth aspect of the invention,
voice input moving image acquisition means for acquiring a moving image of the shape of a user's mouth when inputting character information by voice;
character information conversion means for converting the voice into character information, and correcting the character information by estimating an unclear part of the voice based on the moving image;
may be provided.

According to such a voice response device, since it is possible to estimate the utterance content from the shape of the mouth, unclear parts of the voice can be estimated satisfactorily.
Further, in the above voice response device, as in the thirty-sixth aspect of the invention,
The message reproducing means may detect the user's irritation or agitation by detecting an unexpectedly uttered voice, and generate a message to suppress the irritation or agitation.

According to such a voice response device, when the user is irritated or upset, they can be suppressed. Therefore, it is possible to suppress the occurrence of troubles between the user and the surroundings.
Furthermore, in the above voice response device, as in the thirty-seventh aspect of the invention,
Route information acquisition means for acquiring route information such as weather, temperature, humidity, traffic information, and road surface conditions to the destination when guiding to the destination,
The message reproducing means may output the route information by voice.

According to such a voice response device, it is possible to notify the user of the situation (route information) to the destination by voice.
Further, in the above voice response device, as in the thirty-eighth aspect of the invention,
sight line detection means for detecting the line of sight of the user;
line-of-sight movement request transmission means for outputting a voice requesting that the user's line of sight be moved to a predetermined position when the line-of-sight of the user does not move to a predetermined position in response to the call by the message reproducing means;
may be provided.

With such a voice response device, the user can be made to look at a specific position. Therefore, it is possible to reliably confirm safety when driving the vehicle.
In addition, in the above voice response device, as in the thirty-ninth aspect of the invention,
A change request transmitting means may be provided for observing the position of the body part and facial expression, and outputting a voice requesting that the position of the body part and facial expression be changed when there is little change in response to the call. .

According to such a voice response device, it is possible to guide the user to move the body part of the user to a specific position or to make a specific facial expression. INDUSTRIAL APPLICABILITY The present invention can be used when driving a vehicle or performing a physical examination.

Furthermore, in the voice response device, as in the 40th aspect of the invention,
Broadcast program acquisition means for acquiring a broadcast program similar to a broadcast program viewed by a user;
a broadcast program supplementing means for complementing the interrupted broadcast program by outputting the broadcast program acquired by itself when the broadcast program is interrupted;
may be provided.

According to such a voice response device, it is possible to supplement the broadcast program viewed by the user so as not to be interrupted.
Further, in the above voice response device, as in the forty-first aspect of the invention,
When a user sings a song without lyrics with lyrics added, the song with lyrics is compared with the lyrics added by the user, and the lyrics are output by voice in the part where only the user's lyrics are missing. Having the means.

According to such a voice response device, it is possible to compensate for a portion (part where the lyrics are interrupted) that the user cannot sing in so-called karaoke.
Furthermore, in the voice response device, as in the forty-second aspect of the invention,
When characters are included in a captured image and a user asks how to read the characters, information on the characters is obtained from the outside and the reading of the characters included in the information is output by voice. means,
may be provided.

According to such a voice response device, it is possible to teach the user how to read characters.
Further, in the above voice response device, as in the forty-third aspect of the invention,
Equipped with behavioral environment detection means for detecting the behavior of the user and the surrounding environment of the user,
The message generating means may generate a message according to the detected behavior or surrounding environment.

According to such a voice response device, it is possible to notify a dangerous place or a restricted area. Also, it is possible to detect that the user has an abnormal behavior.
Furthermore, in the above voice response device, as in the forty-fourth aspect of the invention,
health condition determination means for determining the health condition based on the captured image of the user;
a health message generating means for generating a message according to the health condition;
may be provided.

According to such a voice response device, it is possible to manage the health condition of the user.
Further, in the above voice response device, as in the forty-fifth aspect of the invention,
Reporting means for reporting to a predetermined contact when the health condition is below the reference value,
may be provided.

According to such a voice response device, it is possible to make a report when the user's health condition is below the reference value. Therefore, it is possible to inform others of the abnormality at an earlier stage.
Furthermore, in the voice response device, as in the forty-sixth aspect of the invention, information about the user may be output in response to an inquiry from a person other than the user.

According to such a voice response device, for example, by detecting the contents of the user's meal or the walking distance, etc., it is possible to answer questions in place of the user at a hospital or the like. Also, the user may learn the health condition, self-introduction, and the like.

It should be noted that the invention of each aspect need not be based on other inventions, and can be independent inventions as much as possible.

1 is a block diagram showing a schematic configuration of a voice response system to which the present invention is applied; FIG. It is a block diagram which shows schematic structure of a terminal device. 4 is a flowchart showing voice response terminal processing executed by the MPU of the terminal device; 4 is a flowchart showing voice response server processing executed by a computing unit of the server; It is explanatory drawing which shows an example of response candidate DB. 4 is a flowchart showing automatic conversation terminal processing executed by the MPU of the terminal device; 4 is a flowchart showing automatic conversation server processing executed by a computing unit of the server; It is a flowchart which shows the message terminal process which MPU of a terminal device performs. It is a flowchart which shows the message server process which the calculating part of a server performs. 4 is a flowchart showing guidance terminal processing executed by the MPU of the terminal device; It is a flowchart which shows the guidance server process which the calculating part of a server performs. 4 is a flowchart showing reception processing executed by a computing unit of the server; 4 is a flowchart showing information providing terminal processing executed by the MPU of the terminal device; It is explanatory drawing which shows an example of personality DB. It is a flowchart which shows the character information generation process which MPU of a terminal device performs. It is explanatory drawing which shows an example of preference DB. 4 is a flowchart showing preference information generation processing executed by a computing unit of the server; FIG. 4 is an explanatory diagram showing an example of a combination of personality classifications and preferences; It is a flowchart which shows the operation|movement character input process which the calculating part of a server performs. 10 is a flowchart showing another terminal use processing executed by a computing unit of the server; 4 is a flowchart showing storage confirmation processing executed by a computing unit of the server; 4 is a flowchart showing pronunciation determination processing 1 executed by a computing unit of the server; 10 is a flowchart showing pronunciation determination processing 2 executed by a computing unit of the server; 3 is a flowchart showing pronunciation determination processing 3 executed by a computing unit of the server; It is a flowchart which shows the emotion determination process which the calculating part of a server performs. 4 is a flowchart showing emotional response generation processing executed by a computing unit of the server; It is a flowchart which shows the guidance process which the calculating part of a server performs. 4 is a flow chart showing movement request processing 1 executed by a computing unit of the server; FIG. 11 is a flow chart showing movement request processing 2 executed by a computing unit of the server; FIG. It is a flowchart which shows the broadcast music complement process which the calculating part of a server performs. 4 is a flowchart showing character commentary processing executed by a computing unit of the server; It is a flowchart which shows the action response terminal process which the calculating part of a server performs. It is a flowchart which shows the action response server process which the calculating part of a server performs.

Embodiments according to the present invention will be described below with reference to the drawings.
[First embodiment]
[Configuration of this embodiment]
A voice response system 100 to which the present invention is applied is a system configured such that a server 90 generates an appropriate response to voice input at a terminal device 1 and the terminal device 1 outputs the response as voice. is. Specifically, as shown in FIG. 1, a voice response system 100 is configured such that a plurality of terminal devices 1 and a server 90 can communicate with each other via a communication base station 80 or an Internet network 85 .

The server 90 has functions as a normal server device. In particular, the server 90 has a computing unit 101 and various databases (DB). The calculation unit 101 includes a CPU, an R
It is configured as a well-known arithmetic unit having memory such as OM and RAM, and based on the program in the memory, communicates with the terminal device 1 and the like via the Internet network 85, reads and writes data in various DBs, Alternatively, various processes such as voice recognition and response generation for conversing with the user using the terminal device 1 are performed.

Various DBs include, as shown in FIG. 1, voice recognition DB 102, predictive conversion DB 103, voice DB 104, response candidate DB 105, personality DB 106, learning DB 107, preference DB 108, news DB 109, weather DB 110, reproduction condition DB 111, handwritten characters/sign language. DB 112, terminal information DB 113, emotion determination DB 114, health determination DB 115, karaoke DB 116, report destination DB 117, sales DB 118, client DB 119, and the like. The details of these DBs will be described each time the processing is explained.

Next, as shown in FIG. 2, the terminal device 1 is configured such that a behavior sensor unit 10, a communication section 50, a notification section 60, and an operation section 70 are provided in a predetermined housing.
The behavior sensor unit 10 includes a known MPU 31 (microprocessor unit), a memory 39 such as ROM and RAM, and various sensors. For example, a process such as activating a heater for optimizing the temperature of the sensor element is performed so that good detection can be performed.

The behavior sensor unit 10 includes various sensors such as a three-dimensional acceleration sensor 11 (3DG sensor), a three-axis gyro sensor 13, a temperature sensor 15 arranged on the rear surface of the housing, and a humidity sensor arranged on the rear surface of the housing. A sensor 17, a temperature sensor 19 arranged on the front of the housing, a humidity sensor 21 arranged on the front of the housing, an illuminance sensor 23 arranged on the front of the housing, and a sensor 23 arranged on the back of the housing. A wetness sensor 25 , a GPS receiver 27 for detecting the current location of the terminal device 1 , and a wind speed sensor 29 are provided.

The behavior sensor unit 10 also includes an electrocardiogram sensor 33, a heart sound sensor 35, a microphone 37, and a camera 41 as various sensors. The temperature sensors 15 and 19 and the humidity sensors 17 and 21 measure the temperature or humidity of the outside air of the housing as a test object.

The three-dimensional acceleration sensor 11 detects acceleration applied to the terminal device 1 in three mutually orthogonal directions (the vertical direction (Z direction), the width direction of the housing (Y direction), and the thickness direction of the housing (X direction)). Detect and output the detection result.

The three-axis gyro sensor 13 uses the angular velocity applied to the terminal device 1 in the vertical direction (Z direction) and any two directions orthogonal to the vertical direction (the width direction of the housing (Y direction) and the Angular acceleration in the thickness direction (X direction) is detected (counterclockwise velocities in each direction are positive), and the detection results are output.

The temperature sensors 15 and 19 are composed of, for example, thermistor elements whose electric resistance changes according to temperature. In this embodiment, the temperature sensors 15 and 19 detect the temperature in degrees Celsius, and the temperatures described below are all displayed in degrees Celsius.

Humidity sensors 17 and 21 are configured, for example, as well-known polymer film humidity sensors. This polymer film humidity sensor is configured as a capacitor whose dielectric constant changes as the amount of water contained in the polymer film changes according to changes in relative humidity.

The illuminance sensor 23 is configured as a well-known illuminance sensor including a phototransistor, for example.
The wind speed sensor 29 is, for example, a well-known wind speed sensor, and calculates the wind speed from electric power (amount of heat radiation) required to maintain the heater temperature at a predetermined temperature.

The heart sound sensor 35 is configured as a vibration sensor that captures the vibration caused by the heartbeat of the user. Distinguish between noise and other vibrations and noises.

The wetness sensor 25 detects water droplets on the housing surface, and the electrocardiogram sensor 33 detects the heartbeat of the user.
The camera 41 is arranged inside the housing of the terminal device 1 so that the outside of the terminal device 1 is an imaging range.

The communication unit 50 includes a well-known MPU 51, a radio telephone unit 53, and a contact memory 55, and can acquire detection signals from various sensors constituting the behavior sensor unit 10 via an input/output interface (not shown). It is configured. Then, the MPU 51 of the communication section 50 executes processing according to the detection result by the action sensor unit 10, the input signal input via the operation section 70, and the program stored in the ROM (not shown).

Specifically, the MPU 51 of the communication unit 50 functions as a motion detection device that detects a specific motion performed by the user, functions as a positional relationship detection device that detects a positional relationship with the user, It functions as an exercise load detection device for detecting the exercise load applied and the function of transmitting the processing result by the MPU 51 .

The radiotelephone unit 53 is configured to be able to communicate with, for example, a mobile phone base station. and send it to a preset destination.

The contact memory 55 functions as a storage area for storing location information of places visited by the user. In this contact address memory 55, information of contact address (telephone number, etc.) to be contacted when an abnormality occurs in the user is recorded.

The notification unit 60 includes, for example, a display 61 configured as an LCD or an organic EL display, an illumination 63 made up of LEDs capable of emitting light in seven colors, and a speaker 65 . Each unit constituting the notification unit 60 is driven and controlled by the MPU 51 of the communication unit 50 .

Next, the operation unit 70 includes a touch pad 71 , a confirmation button 73 , a fingerprint sensor 75 and a relief request lever 77 .
The touch pad 71 outputs a signal according to the position and pressure touched by the user (the user, the user's guardian, etc.).

The confirmation button 73 is configured to close the contacts of a built-in switch when pressed by the user, and the communication unit 50 can detect that the confirmation button 73 has been pressed. there is

The fingerprint sensor 75 is a well-known fingerprint sensor, and is configured to be able to read fingerprints using, for example, an optical sensor. In place of the fingerprint sensor 75, means capable of recognizing the physical characteristics of a person (means capable of biometrics authentication: means capable of identifying an individual), such as a sensor that recognizes the shape of a vein in the palm of the hand. If it is possible), it can be adopted.

It also has a relief request lever 77 that is connected to a predetermined contact address when operated.
[Processing of this embodiment]
Processing performed in such voice response system 100 will be described below.

The voice response terminal process performed by the terminal device 1 is a process of accepting a voice input by the user, sending the voice to the server 90, and, upon receiving a response to be output from the server 90, reproducing the response in voice. . It should be noted that this process is started when the user inputs a voice input via the operation unit 70 .

Specifically, as shown in FIG. 3, first, input from the microphone 37 is accepted (ON state) (S2), and imaging (recording) by the camera 41 is started (S4). Then, it is determined whether or not there is voice input (S6).

If there is no voice input (S6: NO), it is determined whether or not timeout has occurred (S8). Here, timeout indicates that the permissible time for waiting for processing has been exceeded, and here the permissible time is set to, for example, about 5 seconds.

If it has timed out (S8: YES), the process proceeds to S30, which will be described later. If the timeout has not occurred (S8: NO), the process returns to S6.
If there is voice input (S6: YES), the voice is recorded in the memory (S10), and it is determined whether or not the voice input has ended (S12). Here, it is determined that the voice input has ended when the voice is interrupted for a predetermined time or more, or when the end of the voice input is input via the operation unit 70 .

If voice input has not ended (S12: NO), the process returns to S10. Also, if the voice input has been completed (S12: YES), the data such as the ID for identifying itself, the voice, and the captured image are packet-transmitted to the server 90 (S14). Note that the process of transmitting data may be performed between S10 and S12.

Subsequently, it is determined whether or not data transmission is completed (S16). If the transmission is not completed (S16: NO), the process returns to S14.
Also, if the transmission has been completed (S16: YES), it is determined whether or not data (packets) transmitted by voice response server processing, which will be described later, has been received (S18). If no data has been received (S18: NO), it is determined whether or not a timeout has occurred (S20).

If it has timed out (S20: YES), the process proceeds to S30, which will be described later. If the timeout has not occurred (S20: NO), the process returns to S18.
Also, if the data is received (S18: YES), the packet is received (S22). In this process, one or a plurality of different responses to character information are obtained in association with different tones.

Then, it is determined whether or not the reception is completed (S24). If the reception has not been completed (S24: NO), it is determined whether or not timeout has occurred (S26).
If it has timed out (S26: YES), the fact that an error has occurred is output via the notification unit 60, and the voice response terminal processing is terminated. If the timeout has not occurred (S26: NO), the process returns to S22.

Further, if the reception is completed (S24: YES), the response based on the received packet is output by voice from the speaker 65 (S28). In this process, when reproducing a plurality of responses, the plurality of responses are reproduced with different tones. When such processing ends, the voice response terminal processing ends.

Next, voice response server processing performed by the server 90 (external device) will be described with reference to FIG. The voice response server process is a process of receiving voice from the terminal device 1 , performing voice recognition to convert the voice into character information, and generating a response to the voice and returning it to the terminal device 1 . In particular, in this embodiment, there are cases where multiple responses are transmitted in association with voices of different tones.

As details of the voice response server processing, as shown in FIG. 4, first, it is determined whether or not a packet has been received from any terminal device 1 (S42). If no packet has been received (S42: NO), the process of S42 is repeated.

Also, if the packet is received (S42: YES), the terminal device 1 of the communication partner is specified (S44). In this process, the terminal device 1 is specified by the ID of the terminal device 1 included in the packet.

Next, the voice contained in the packet is recognized (S46). Here, in the speech recognition DB 102, a large number of voice waveforms are associated with a large number of characters. The predictive conversion DB 103 also associates words that are likely to be used after a certain word.

Therefore, in this process, by referring to the speech recognition DB 102 and the predictive conversion DB 103, well-known speech recognition processing is performed to convert speech into character information.
Subsequently, an object in the captured image is specified by image processing the captured image (S48). Then, the user's emotion is determined based on the waveform of the voice and the ending of words (S50).

In this process, by referring to the emotion determination DB 114 in which voice waveforms (voice tone), endings of words, etc. are associated with categories of emotions such as anger, joy, confusion, sadness, exaltation, etc., the user can is determined to which category the emotion of is, and the result of this determination is recorded in the memory. Subsequently, by referring to the learning DB 107, the words that the user often speaks are retrieved, and the part where the character information generated by the voice recognition is ambiguous is corrected.

Note that the learning DB 107 records the features of each user, such as words that the user often speaks and pronunciation habits. Further, data is added/corrected to the learning DB 107 in conversation with the user.

Subsequently, the corrected character information is specified as the input character information (S54), and a sentence similar to the character information is input and searched from the response candidate DB 105, thereby obtaining a response from the response candidate DB 105 (S56). . Here, in the response candidate DB 105, as shown in FIG. 5, input character information, first output, first output tone, second output, and second output tone are uniquely associated.

For example, as shown in the first row of FIG. 5, when the character information "today's * weather" is input, the first output "today's * weather is *" is voiced by woman 1. are output in association with each other. However, the part marked with "*" is obtained by accessing the weather DB 110 in which the name of the area and the weather forecast for several days in that area are associated with each other.

In addition, when the character information "today's * weather" is input, the weather at the timing when the weather changes today is also acquired from the weather DB 110, and the second output "however * is *." 1 voice tone is output. When the weather in Tokyo today is sunny and the weather tomorrow is rainy, when "today's weather in Tokyo" is input, "Today's weather in Tokyo is sunny." In Man 1's voice, "However, it will rain tomorrow."

In this embodiment, the case of outputting a plurality of responses has been described, but if there is only one response to an input, only one response will be output. Therefore, it is determined whether or not there is one response (S58). If there is only one response (S58: YES), the process proceeds to S62, which will be described later.

If there are multiple responses (S58: NO), the content of the response and the tone of voice are associated (S60). Here, the speech DB 104 stores a database of artificial speech for each tone, and in this process, the tone set for each response is associated with the tone in the database.

Subsequently, the content of the response is converted into voice (S62). In this process, based on the database stored in the voice DB 104, the process of outputting the content of the response (character information) as voice is performed.

Then, the generated response (voice) is packet-transmitted to the terminal device 1 of the communication partner (S64). It should be noted that the packet may be transmitted while the voice of the response content is being generated.
Subsequently, the content of the conversation is recorded (S68). In this process, the input character information and the output response content are recorded in the learning DB 107 as conversation content. At this time, keywords (words recorded in the speech recognition DB 102 ) included in the content of the conversation, features at the time of pronunciation, etc. are recorded in the learning DB 107 .

When such processing ends, the voice response server processing ends.
[Effects of this embodiment]
The voice response system 100 described in detail above is a system that makes responses to input character information by voice, and the terminal device 1 (MPU 31) acquires a plurality of different responses to the character information, different responses in different tones.

According to the voice response system 100, it is possible to output a plurality of responses in different tones. Therefore, even if one solution to one character information cannot be specified, different solutions can be used in different tones. It can be output in an easy-to-understand manner. Therefore, it is possible to improve usability for the user.

In the voice response system 100, the terminal device 1 inputs the user's voice through the microphone 37, and the server 90 (calculation unit 101) converts the input voice into character information, and responds to the character information. A plurality of different responses are generated and sent to the terminal device 1 . The terminal device 1 then obtains a response from the server 90 .

According to the voice response system 100 as described above, since the terminal device 1 can input voice, it is possible to configure the text information to be input by voice. Moreover, since the response can be generated in the server 90, the processing load in the voice response system 100 can be reduced.

Further, in the voice response system 100, the server 90 converts the voice uttered by the user into character information, and accumulates habits when uttering (pronunciation habits, etc.) as learning information. keep a record).

According to the voice response system 100 as described above, character information can be generated based on the learning information, so the accuracy of character information generation can be improved.
Furthermore, in the voice response system 100, the server 90 reads the emotion from the voice tone of the voice input by the user, and usually includes at least one of anger, joy, confusion, sadness, and exaltation. , to output which emotion it corresponds to.

According to such a voice response system 100, it is possible to output a response according to the user's emotion.
[Modification of First Embodiment]
In the present embodiment, voice recognition is used as a configuration for inputting character information, but not limited to voice recognition, input means (operation unit 70) such as a keyboard or touch panel may be used for input. Further, although the server 90 performs the operation of "converting the input voice into character information", the terminal device 1 may perform the operation.

Furthermore, in the voice response system 100, the server 90 has a response candidate DB 105 in which a plurality of different responses including positive responses and negative responses to each piece of character information are recorded for each of the plurality of pieces of character information. In addition, the terminal device 1 may acquire a positive response and a negative response as a plurality of different responses, and reproduce the positive response and the negative response in different tones.

For example, as shown in the second row of FIG. 5, when a voice saying "Can I buy something?" Output. On the other hand, negative information such as bad reputation is output in a tone different from the female voice associated with the positive information (here, male voice).

According to the voice response system 100, it is possible to reproduce responses from different positions, such as affirmative responses and negative responses, with different voices. can be done. Therefore, it is possible to make it difficult for the user who listens to the voice to feel uncomfortable.

Note that the tone of voice may be changed depending on the type of response or the wording used when responding. For example, when responding in a gentle tone, a calm female voice may be played back, and when responding in a violent tone, a brave male voice may be played back. In other words, it is sufficient to associate the content of the response with the personality, and set the tone of voice according to the personality.

Furthermore, in the voice response system 100, a response (for example, affirmative response or negative response) output by one's own terminal device 1 or another terminal device 1 is input as character information, and the response is counterargued. may generate a response of In other words, from the standpoint of the user, it is possible to hear arguments by both opinions for and against. After hearing this discussion, the user can make a final decision.

This configuration can be realized using one or more terminal devices 1 . In order for a plurality of terminal devices 1 to exchange voices with each other, the voices may be input/output directly or wireless communication may be used. When a plurality of terminal devices 1 and the server 90 communicate with each other, data may be transmitted to other terminal devices 1 in the process of S66.

Furthermore, in the voice response system 100, the computing unit 101 learns (records and analyzes) the user's behavior (conversation, moving place, camera image), and compensates for the lack of words in the user's conversation. You may do so.

For example, in response to the question "Can I have a hamburger steak today?" However, the reason why he said that curry is good is transmitted.

Also, such a configuration may be implemented during a telephone call, or may be configured to voluntarily participate in the user's conversation.
Furthermore, in the voice response system 100, the server 90 may acquire response candidates from a predetermined server or from the Internet.

According to the voice response system 100 as described above, it is possible to acquire response candidates not only from the server 90 but also from any device connected to the Internet, a dedicated line, or the like.
[Second embodiment]
[Processing of Second Embodiment]
Next, another type of voice response system will be described. This Embodiment (Second Embodiment) In the following embodiments, only the parts that are different from the voice response system 100 of the first embodiment will be described in detail. , and description thereof is omitted.

The voice response system of the second embodiment outputs voice even when the user does not input character information. Specifically, the terminal device 1 performs automatic conversation terminal processing shown in FIG. The automatic conversation terminal process is, for example, a process that is started when the power of the terminal device 1 is turned on, and is a process that is repeatedly executed thereafter.

In the automatic conversation terminal processing, first, it is determined whether or not the setting for automatic conversation is ON (S82). Whether or not automatic conversation is to be performed can be set by the user via the operation unit 70 or by inputting voice.

If the automatic conversation is OFF (S82: NO), the automatic conversation terminal processing is terminated. Also, if the automatic conversation mode is ON (S82: YES), the fact that the automatic conversation mode has been set is transmitted to the server 90 together with the ID for identifying itself (S84).

Subsequently, it is determined whether or not a packet has been received from the server 90 (S86). If no packet has been received (S86: NO), the process of S86 is repeated. Also, if a packet has been received (S86: YES), the same processes as those of S22 to S30 described above are performed, and when these processes are completed, the automatic conversation terminal process is terminated.

Further, the server 90 executes automatic conversation server processing shown in FIG. The automatic conversation server process is a process that is started, for example, when the power of the server 90 is turned on, and then repeatedly executed.

In the automatic conversation server process, first, it is determined whether or not it is received from the terminal device 1 that the automatic conversation mode has been set (S92). If the notification that the automatic conversation mode has been set has not been received (S92: NO), the process proceeds to S98.

If the fact that the automatic conversation mode has been set is received (S92: YES), the terminal device 1 to be the communication partner is specified based on the ID contained in the received packet (S94), and A setting is made for automatic conversation (S96). Subsequently, it is determined whether or not the reproduction condition is satisfied for each of the terminal devices 1 set to have automatic conversation (S98).

Here, the reproduction condition is, for example, that a certain period of time has passed since the previous conversation (voice input), or that any sensor value is abnormal at a certain time of the day, or under certain weather conditions. Indicates when the value is indicated.

If the reproduction condition is not satisfied (S98: NO), the automatic conversation server process is terminated. Also, if the reproduction conditions are satisfied (S98: YES), a message corresponding to the reproduction conditions is generated (S100).

Here, the message corresponding to the reproduction condition may be, for example, fixed phrases such as "Good morning" or "Hello." may be related to the news of When the message is about the latest news, for example, when information about the stock price of a certain company is acquired, the message "The stock price of XX company went up by XX yen today. Did you know? and so on.

When this process ends, the processes of S42 to S54 described above are performed. Then, when the process of S54 is completed, it is determined whether or not a predetermined answer has been obtained from the terminal device 1, which is the communication partner (S112). Here, the predetermined answer may be, for example, some voice or a specific answer. Specific answers are, for example, "I know" or "I don't know" to the question "Do you know?" On the other hand, those including words indicating the weather such as "It's raining" and "It's sunny" are applicable.

If there is a predetermined answer (S112: YES), the automatic conversation server process is terminated. If there is no predetermined response (S112: NO), the message sent in S100 is resent (S114). When retransmitting the message in this way, the tone of voice is changed to produce a voice that is strong and harsh.

Subsequently, the destination DB 117, in which the terminal device 1 and the destination are associated in advance, is referred to, and a message to the effect that no response has been received from the predetermined destination is transmitted (S116). When such processing ends, the automatic conversation server processing ends.

[Effects of Second Embodiment]
In the voice response system 100 described above, the server 90 determines whether or not the situation of the voice response system 100 matches the playback condition set in advance as a condition for outputting voice when character information is not input. Then, when the playback condition is met, a preset message is output.

According to such a voice response system 100, voice can be output even when character information is not input (that is, when the user does not speak). For example, by forcing the user to speak, it can be used as a countermeasure against drowsiness while driving a car. In addition, safety can be confirmed by determining whether or not a person living alone responds.

In the voice response system 100, the server 90 acquires news information and outputs a message regarding the news in the form of a question requesting the user's answer.
According to the voice response system 100 as described above, it is possible to have a conversation about the news, so that it is possible to prevent the same conversation from occurring all the time.

Further, in the voice response system 100, the server 90 adds externally acquired information (news and environment (temperature, weather, location information, etc.) separately acquired) to a preset message and outputs the message.

According to such a voice response system 100, it is possible to output a response combining a predetermined message and acquired information.
Further, in the voice response system 100, when the server 90 does not receive a response or message, the server 90 sends information identifying the user and the fact that no response was obtained to a preset contact address. Send.

According to the voice response system 100 as described above, it is possible to notify the contact when an answer is not obtained. Therefore, for example, an abnormality such as an elderly person living alone can be notified early.

[Modification of Second Embodiment]
In addition, in the voice response system 100, the server 90 may acquire a plurality of messages, and select and output a message to be reproduced according to the reproduction frequency of the messages.

According to the voice response system 100, by making it difficult to reproduce messages with high reproduction frequency, randomness can be achieved during message reproduction. can encourage the establishment of

[Third embodiment]
[Processing of the third embodiment]
Next, in the voice response system of the third embodiment, it is configured such that the terminal device 1 instead of the user tells someone that it is difficult to say directly. For example, before a date, if you talk to this device that you want to say something like this today, at an appropriate timing (for example, at a preset time or when a certain period of time has passed since the conversation was interrupted), Let the voice response system 100 speak for you (play the voice).

Specifically, the terminal device 1 executes the message terminal processing shown in FIG. 8, and the server 90 executes the message server processing shown in FIG. The message terminal process is a process that is started, for example, when the power of the terminal device 1 is turned on, and then repeatedly executed.

In the message terminal processing, as shown in FIG. 8, first, it is determined whether or not the message mode is set by the user (S132). If the message mode is not set (S132: NO), the process of S132 is repeated.

If the message mode is set (S132: YES), the processing of S2 to S8 is performed. (S134). Then, the processing of S10 to S16 is performed.

If the determination in S16 is affirmative, it is determined whether or not a packet has been received from the server 90 (S136). If no packet has been received (S136: NO), the process of S136 is repeated. Also, if the packet has been received (S136: YES), the processing of S24 to S30 is executed, and the message terminal processing ends.

Next, the message server process is a process that is started, for example, when the power of the server 90 is turned on, and is repeatedly executed after that. Specifically, first, it is determined whether or not a packet has been received from any terminal device 1 (S142). If no packet has been received (S142: NO), the process proceeds to S156, which will be described later.

If the packet has been received (S142: YES), the terminal device 1 of the communication partner is specified (S44), and it is determined whether or not the packet contains a mode flag such as a message mode flag (S144). . If there is no mode flag (S144: NO), the process proceeds to S148.

If there is a mode flag (S144: YES), the server 90 also sets the mode by setting the flag corresponding to the terminal device 1 of the communication partner to the ON state (S146). For example, if the message mode flag corresponds to the message mode, the processing of S46 to S152 described later is performed, and if the guidance mode flag to be described later corresponds to the guidance mode, S46 to S176 (see FIG. 11) are performed. will be

Subsequently, it is determined whether or not the message flag is ON (S148). If the message flag is ON (S148: YES), the processes of S46 to S54 are executed, and then the message reproduction condition is extracted (S150).

Here, the message reproduction condition can be set in advance by the user via the operation unit 70 of the terminal device 1, and corresponds to time and position, for example. Note that the message reproduction condition is transmitted to the server 90 at the time of packet transmission for message terminal processing.

Subsequently, the message and voice (voice tone) are associated with each other and recorded in the memory (S152), and the process proceeds to S156. Also, if the message flag is OFF (S148: NO), processing relating to other modes is performed (S154), and it is determined whether or not the reproduction timing has come (S156). Here, the reproduction timing indicates the content set in the message reproduction condition.

If it is not the reproduction timing (S156: NO), the message server processing is terminated immediately. Also, if it is the reproduction timing (S156: YES), the processing of S62 to S64 is executed, and the message server processing ends.

[Effects of the third embodiment]
According to the voice response system of the third embodiment as described above, the voice input by the user can be played not immediately but when the condition for message playback is satisfied after a certain period of time.

For example, as shown in the third row of FIG. will be played.

[Modified example of the third embodiment]
In the above-described third embodiment, the content of the user's speech is configured to be played back. It is good also as composition which speaks words, such as. Specifically, the terminal device 1 executes the guidance terminal processing shown in FIG. 10, and the server 90 executes the guidance server processing shown in FIG.

The guidance terminal process is a process that is started, for example, when the power of the terminal device 1 is turned on, and then repeatedly executed. For example, the process is started when the power of the terminal device 1 is turned on, and is repeatedly executed thereafter.

In the guidance terminal process, as shown in FIG. 10, first, it is determined whether or not the guidance mode is set by the user (S162). If the guidance mode is not set (S162: NO), the process of S162 is repeated.

Further, if the guidance mode is set (S162: YES), the processing of S2 to S8 is performed. (S164). Then, the processing of S10 to S16 is performed.

If the determination in S16 is affirmative, it is determined whether or not a packet has been received from the server 90 (S166). If no packet has been received (S166: NO), the process of S166 is repeated. Also, if the packet has been received (S166: YES), the processing of S24 to S30 is performed, and the guiding terminal processing ends.

Next, the guidance server process is a process that is started, for example, when the power of the server 90 is turned on, and then repeatedly executed. Specifically, the processes of S142 to S146 described above are executed. Then, it is determined whether or not the guidance flag is ON (S172).

If the guidance flag is ON (S172: YES), the processes of S46 to S54 are performed, and then the guidance regeneration condition is extracted (S174).
Here, like the message playback condition, the guidance playback condition can also be set in advance by the user via the operation unit 70 of the terminal device 1, and corresponds to time and position, for example. The guidance reproduction condition is transmitted to the server 90 when transmitting packets for message terminal processing.

Subsequently, guidance content is generated, and the guidance content and voice (voice tone) are associated with each other and recorded in memory (S176). Here, as the contents of guidance, for example, words expressing wishes such as "want" and "hope" included in the input character information are searched, keywords preceding these words are extracted, and these keywords are guided. The words registered as words are output as guidance contents. Keywords and words indicating guidance content are pre-correlated and recorded in the response candidate DB 105 .

Subsequently, the processing from S156 onward described above is performed, and the server processing ends. Also, if the guidance flag is OFF (S172: NO), the processing relating to other modes is performed (S154), the above-described processing from S156 onwards is performed, and the server processing ends.

According to such a configuration of the modified example of the third embodiment, instead of directly outputting the words the user wants to say, it is possible to induce the user to speak the words the user wants to say.
[Fourth embodiment]
[Processing of the fourth embodiment]
Next, an example of using the terminal device 1 for reception work will be described. In this embodiment, the terminal device 1 is installed at a reception desk of a company or the like. In addition, it can also be adopted for telephone reception such as company's representative telephone and telephone banking. Here, this embodiment is implemented by replacing the process of S56 in the first embodiment with the acceptance process shown in FIG.

In the reception process, as shown in FIG. 12, first, it is determined whether or not the character information includes a company name (S192). In this process, it is determined whether or not a general name or company name (recorded in the speech recognition DB 102) is included.

If the character information does not contain a company name or a personal name (S192: YES), a response to ask for the company name and personal name is generated (S194), and the acceptance process ends. This process generates a response such as, for example, "Please tell us your name and what you are doing."

If the character information includes a company name or personal name (S192: NO), the company name or personal name is extracted from sales DB 118 and client DB 119 (S196). Here, in the sales DB 118, the names of companies and persons in charge who have made sales in the past, or the names of complainers who only complain are recorded. In addition, the client DB 119 stores the company name, the person in charge of the company, the person in charge on the side of the user of the terminal device 1 (side of the company), the schedule such as the scheduled meeting time, and the contact information for each person in charge. ing.

Subsequently, it is determined whether or not the company name and personal name could be extracted from the sales DB 118, that is, whether or not the company name and personal name included in the character information were included in the sales DB 118 (S198). If the company name and personal name can be extracted from the sales DB 118 (S198: YES), a sales refusal response to the effect of refusing the sales (response refusing the brokerage) is generated (S200), and the reception process ends.

Also, if the company name and personal name cannot be extracted from the sales DB 118 (S198: NO), the person who came to the reception visits at a time close to the schedule in the client DB 119 (for example, within one hour before or after the current time). It is determined whether or not the person is coming (S202). If it is a person who will be visiting at a near time (S202: YES), the contact information of the person in charge of this person is extracted from the client DB 119 so that this person in charge and the person who came to the reception can have a conversation. , is connected to this person in charge (S204). In this process, it is only necessary to connect to the extension phone, mobile phone, etc. of the person in charge.

Subsequently, an acceptance response for the client is generated (S206). Here, as the reception response for the client, for example, a response such as "Mr. When such processing ends, the reception processing ends.

If it is not the person who will be visiting at a near time (S202: NO), it connects to the preset contact information for the reception, so that the person in charge and the person who came to the reception can have a conversation. Connect to the person in charge of reception (S208). Then, a normal acceptance response is generated (S210).

Here, as a normal reception response, for example, a response such as "Please wait for a while as we are connecting to the reception." When such processing ends, the reception processing ends.

[Effects of Fourth Embodiment]
The above-described voice response system 100 is configured to be used at the workplace or at the reception desk of a company. In this configuration, the name of the person who comes to the sales office and the name of the company are recorded in advance in the sales DB 118 of the server 90, and when the person who comes to the reception gives his/her name or company name, a refusal is voiced. Generate the response as you would play it.

Further, in the voice response system 100, the server 90 identifies a communication partner based on the input character information, and connects the communication partner with a communication destination preset for each communication partner.
According to such a voice response system 100, it is possible to assist in reception work and answering telephone calls. In addition, according to the voice response system 100, it is possible to eliminate a person who may interfere with the user's work without having to deal with the person himself.

Further, in the voice response system 100, the server 90 extracts a keyword included in the input character information (especially voice) and connects to a connection destination corresponding to the keyword. For example, a keyword such as the name of the other party and its connection destination are associated in advance.

According to the voice response system 100 as described above, it is possible to assist in operations such as call forwarding and calling the receptionist.
[Modified example of the fourth embodiment]
In the above embodiment, the connection destination is set according to the other party. It may be recognized and the connection destination may be changed according to requirements.

In addition, in the voice response system 100, the server 90 may recognize the requirements of the other party's speech based on the keyword, and may provide the user with an outline of what the other party said.
According to the voice response system 100 as described above, it is possible to assist the intermediary work with the customer.

[Fifth embodiment]
[Processing of the fifth embodiment]
Next, the terminal device 1 may receive a request from another terminal device 1 and provide information requested by the other terminal device 1 .

In such a configuration, the server 90 requests necessary information from the other terminal device 1 in the process of S56, acquires the necessary information from the other terminal device 1, and then generates a response. Then, in the terminal device 1 that provides the necessary information, the information providing terminal processing shown in FIG. 13 is performed. The information providing terminal process is, for example, a process that is started when there is a request from the server 90 .

As shown in FIG. 13, the information providing terminal process first extracts information providing destinations (S222). This information provider indicates another terminal device 1 requesting information, and the request from the server 90 includes an ID for specifying this other terminal device 1 .

Subsequently, it is determined whether or not the person is a party to whom provision of information is permitted (S224). Here, in the terminal information DB 113, IDs of parties to whom provision of information is permitted, such as family members and friends, are recorded in advance. In this process, determination is made by referring to this terminal information DB 113 .

If the other party is permitted to provide information (S224: YES), the requested information is acquired from its own memory 39 and various sensors (S226), and this data is transmitted to the server 90 (S228). Also, if the other party is not permitted to provide information (S224: NO), a refusal to provide information is transmitted to the server 90 (S230).

When such processing ends, the information providing terminal processing ends.
In this configuration, for example, as shown in the fourth row of FIG. 5, in response to the question "What is Mr. XX doing?" Then, the terminal device 1 returns position information.

Then, the server 90 recognizes Mr. XX's behavior based on the position information. For example, if the robot is moving on a railroad track at a speed faster than a human can run, it will judge that the robot is traveling on a train, saying, “Mr. XX is on the train. and will generate a response.

[Effects of the fifth embodiment]
In the above voice response system 100, the server 90 acquires information recorded in the other terminal device 1 from another terminal device 1 different from the terminal device 1 of the request source, and provides the other terminal device 1 with the information. That is, the server 90 in the voice response system 100 acquires information for generating a response to text information from the other terminal device 1 .

According to such a voice response system 100, a response can be generated based on information recorded in another terminal device 1. FIG.
Further, in the voice response system 100, when the terminal device 1 receives a request from another terminal device 1 for information for generating a response to character information, the terminal device 1 returns information in response to this request.

In this configuration, the terminal device 1 is provided with sensors for detecting position information, temperature, humidity, illuminance, noise level, etc., and a database of dictionary information, etc., and extracts necessary information upon request.

According to the voice response system 100 as described above, it is possible to acquire information unique to the other terminal device 1 such as the position of the other terminal device 1 . In addition, it is possible to transmit information specific to itself to other terminal devices 1 .

[Sixth embodiment]
[Processing of the sixth embodiment]
Next, in the voice response system of the sixth embodiment, a personality DB 106 is prepared in which personality information in which the personality of a user or a person related to the user is associated according to a preset category is recorded. ing. For example, as shown in FIG. 14, the personality DB 106 records the names of users and related persons in association with their personality classifications.

Further, in the personality DB 106 shown in FIG. 14, personality tests are conducted on users and related persons, and the test results are also recorded. Here, when generating personality information, well-known personality analysis techniques (Rorschach test, Sondy test, etc.) may be used. Also, when generating personality information, aptitude test technology used by companies and the like for recruitment tests may be used.

When generating character information, for example, the character information generation process shown in FIG. 15 is performed. The personality information generation process is, for example, a process that is started when an instruction to generate personality information is input using the operation unit 70 or the like in the terminal device 1 .

In the personality information generation process, as shown in FIG. 15, first, the microphone 37 is turned on (S242), and one of the predetermined four-choice questions is output by voice (S244). At this time, the 4-choice questions may be acquired from the server 90, or may be questions recorded in the memory 39 in advance.

Next, it is determined whether or not there is a voice response from the target person (the user or a related person) (S246). If there is no answer (S246: NO), the process of S246 is repeated.
If there is an answer (S246: YES), conversation parameters such as word endings and conversation speed are extracted (S248), and it is determined whether or not the current question is the final question (S250). If it is not the final question (S250: NO), the next question is selected (S252) and the process returns to S242.

If it is the final question (S250: YES), character analysis is performed by answering the 4-choice question (S254), and character analysis is performed using conversation parameters (S256). Here, in personality analysis using conversational parameters, people who are confident tend to have strong endings, and those who are not confident tend to have weak endings. trends can be captured.

Subsequently, the results of the character analysis are comprehensively analyzed, such as by taking a weighted average (S258), and sorted into character categories (S260). Specifically, the personality of the subject obtained from the test is scored, and each score is sorted into personality categories.

Subsequently, the target person and the personality classification are associated (S262) and recorded in the personality DB 106 (S264). In other words, the relationship between the subject and the personality classification is transmitted to the server 90 . At this time, the test results are also transmitted to the server 90, and the server 90 constructs the personality DB 106 as shown in FIG. When such processing ends, the personality information generation processing ends.

When using the personality DB 106 generated in this manner, correspondences between personality classes and different responses are prepared in the response candidate DB 105 . Then, in the process of S56, the server 90 acquires a plurality of response candidates representing different responses to the character information, selects a response to be output from the response candidates according to the personality information, and performs the processes of S60 and S64. Causes the selected response to be printed.

[Effects of the sixth embodiment]
In the above-described voice response system 100, the terminal device 1 generates character information of a user or a related person based on answers to a plurality of preset questions, and acquires the generated character information.

According to the voice response system 100 as described above, personality information can be generated in the server 90 or the terminal device 1 .
Further, in the voice response system 100, the computing unit 101 generates character information of the user or related person based on the character string included in the input character information.

According to the voice response system 100, personality information can be generated while the user uses the voice response system 100. FIG.
In addition, according to the voice response system 100, different responses can be made according to the character of the user or the person related to the user (related person). Therefore, it is possible to improve usability for the user.

[Modified example of the sixth embodiment]
In the sixth embodiment described above, one response may be output according to personality, or a plurality of responses may be output in association with voices of different tones.

Further, the processes of S248 and S254 to S264 in the personality information generation process may be performed by the server 90. FIG. In this case, voices and problems may be exchanged between the terminal device 1 and the server 90 while causing the server 90 to identify the terminal device 1, as in the first embodiment.

Furthermore, in the voice response system 100, the server 90 may detect any of the user's actions and operations, and generate learning information or personality information based on these.

According to the voice response system 100, for example, when it is detected that the user has jumped on a train for several days in a row, the user is urged to leave home several minutes earlier from the next day, or the user is angered by the conversation. If it is detected that there is a tendency to be irritable, it is possible to output a voice or music that suppresses the mood.

[Seventh embodiment]
[Processing of the seventh embodiment]
Next, in the voice response system of the seventh embodiment, a preference DB 108 is prepared in which preference information in which preferences of users and related parties are associated according to preset categories is recorded. For example, as shown in FIG. 16, the preference DB 108 contains the names of users and related parties, and the preferences of these persons. are recorded in association with each other.

In particular, food preferences are sweet (sweet), spicy (spicy), and medium in between. Color preferences are warm colors (warm), cold colors (cold), medium in between, and hobbies. is classified into indoor hobbies (inside), outdoor hobbies (outside), and both indoor and outdoor hobbies (inside and outside).

When constructing such a preference DB 108, for example, preference information generation processing shown in FIG. 17 is executed. The preference information generation process is performed, for example, between S48 and S54.
More specifically, as shown in FIG. 17, keywords related to preferences are extracted from character information (S282), and objects related to preferences are extracted from objects specified by image processing (S284). In the preference DB 108, keywords related to preferences are associated with types of preferences and classifications within those types (for food preferences, sweet, medium, spicy, etc.). When a keyword or an object is included in the preference DB 108, it is extracted as related to preference.

Subsequently, the counter is incremented for each group of keywords related to preference (S288). For example, when a kimchi whose preference type is "food preference" and whose type is "spicy" is extracted, the counter corresponding to "food preference" and "spicy" is incremented. .

Then, based on the counter value, the preference information (preference DB 108) is updated (S290). In other words, for each "type of preference", the "type" with the largest counter value is recorded in the preference DB 108 as the feature of the preference of the user or related person as the one that best matches the preference. When such processing ends, the preference information generation processing ends.

When using the preference DB 108 generated in this manner, the response candidate DB 105 prepares responses corresponding to different preferences for each preference, and the server 90 generates a plurality of different responses for the character information in the process of S56. A response candidate representing a response is acquired, a response to be output is selected from the response candidates according to the preference information, and the selected response is output in the processes of S60 and S64.

[Effects of the seventh embodiment]
In the above-described voice response system 100, the server 90 generates preference information indicating the tendency of the preference of the user or related person based on the character string included in the character information. Then, a response to be output is selected from the response candidates based on the preference information, and the selected response is output.

According to such a voice response system 100, responses can be made according to the preferences of the user or the person concerned. For example, when the user asks the terminal device 1, "What would Mr. ○○ want?" when buying a present for a related person, a response corresponding to the preference information can be obtained.

[Modification of the seventh embodiment]
As shown in FIG. 18, the response candidate DB 105 may have a table in which personality classifications and preference information are associated with each other.

For example, in the example shown in FIG. 18, personality classifications and color preferences are associated with each other, and products that can be estimated to please a woman as a gift are arranged in a matrix.
In the processing of S56, it is also possible to generate a response taking into account both personality and taste in this way.

[Eighth embodiment]
[Processing of the eighth embodiment]
In the above embodiment, voice is converted into character information, but user's actions may be converted into character information.

Specifically, the terminal device 1 captures the user's motion as a captured image and transmits the captured image to the server 90, and the server 90 performs, for example, the motion character input process shown in FIG. The action character input process is a process that is started when a part of the user's body appears in the captured image in the process of S48.

In the action character input process, as shown in FIG. 19, first, a captured image is acquired (S302). Then, it is determined whether the user is trying to input characters by handwriting or by sign language (S304, S308).

In these processes, for example, when the user's upper body and face appear in the captured image, it is determined that the user is trying to input characters in sign language, and the user's face does not appear in the captured image. If a hand is shown, it is determined that the user is trying to input characters by handwriting.

If characters are to be input by handwriting (S304: YES), the behavior of the fingertip or pen tip is recorded (S306), and the behavior is converted into character information based on this behavior (S312). Here, in the handwritten character/sign language DB 112, characters are associated with actions when characters are handwritten, and hand movements are associated with characters expressed in sign language. In the process of S<b>312 , character information is generated by referring to the handwritten character/sign language DB 112 .

If a character is to be input in sign language (S304: NO, S308: YES), the handwritten character/sign language DB 112 is referenced to recognize the sign language content, and the above-described processing of S312 is performed. Also, if the character is not to be input by handwriting or sign language (S308: NO), input processing by another method is performed (S314).

Subsequently, the character input by motion and the character input by voice are associated, and whether or not there is a similar voice (whether or not the reference waveform based on the character and the pronunciation waveform match the reference value or more ) is determined (S316). If there is such voice input (S316: YES), the accent and pronunciation characteristics when this user inputs this character are recorded in the learning DB 107 in association with the character (S318), and operation character input processing is performed. exit.

Also, if there is no such voice input (S316: NO), the action character input process is terminated.
[Effects of the eighth embodiment]
Since the voice response system 100 converts the user's actions into character information, the user can input the character information without vocalizing.

[Modification of the eighth embodiment]
The motions of the present embodiment may be handwriting or gestures (for example, sign language) as well as muscle motions.

[Ninth Embodiment]
[Processing of the ninth embodiment]
The contents of the learning DB 107 may be made available in another terminal device 1 when the user uses another terminal device 1 other than the terminal device 1 that the user normally uses. In this case, the ID and password of the terminal device 1 that is usually used are sent to the server 90 from the other terminal device 1 together with the usage request.

Then, the server 90 executes the other terminal use process shown in FIG. The other terminal use process is a process that is started when a use request is received.
In the other terminal use process, as shown in FIG. 20, first, it is determined whether or not an ID and a password have been entered (S332). If the ID and password have not been entered (S332: NO), the process of S332 is repeated.

Also, if the ID and password have been entered (S332: YES), it is determined whether authentication by the ID and password has been completed (S334). If the authentication is completed (S334: YES), the completion of the authentication is transmitted to the other terminal device 1 (S336), and the other terminal device 1 stores the learning DB 107 of the terminal device 1 corresponding to the ID and password. It is set to be used (S338).

If the authentication is not completed (S334: NO), an error message is sent to the other terminal device 1 (S340), and the other terminal use process is terminated.
[Effects of the ninth embodiment]
Also, in the voice response system 100, the server 90 transfers the learning information of a certain terminal device 1 to another terminal device 1. FIG.

According to such a voice response system 100, even when a user using a certain terminal device 1 uses another terminal device 1, learning information recorded in a certain terminal device 1 (recorded in the server 90 learning information) can be used. Therefore, even when using another terminal device 1, it is possible to improve the generation accuracy of the character information. In particular, it is effective when the user possesses a plurality of terminal devices 1 .

Furthermore, in the voice response system 100, the server 90 outputs information about the user in response to an inquiry from a person other than the user.
According to such a voice response system 100, for example, by detecting the content of the user's meal, the walking distance, etc., it is possible to answer questions in place of the user at a hospital or the like. Also, the user may learn the health condition, self-introduction, and the like.

[Modification of the ninth embodiment]
As in the configuration of the ninth embodiment, when receiving a request to end use, an ID and a password, use of the learning DB 107 for the terminal device 1 corresponding to the ID and password may be ended (prohibited).

[Tenth embodiment]
[Processing of the tenth embodiment]
In the voice response system of the tenth embodiment, the server 90 stores the contents of the conversation and asks questions to obtain the same contents as the contents heard. Specifically, at S100 of the automatic conversation server process shown in FIG. 7, the memory confirmation process shown in FIG. 21 is executed.

In the memory confirmation process, as shown in FIG. 21, past conversation contents are extracted from the learning DB 107 (S352), and a question is generated whose answer is a keyword contained in any of the conversation contents (S353). When such processing ends, the storage confirmation processing ends.

In the memory confirmation process, for example, "What was the menu for dinner last night?" or "Where did you go three days ago?"
[Effects of the tenth embodiment]
According to the voice response system 100 as described above, it is possible to check the memory of the user and to fix the memory. It is also considered effective for suppressing the progression of dementia in the elderly.

[Eleventh embodiment]
[Processing of the eleventh embodiment]
Next, the voice response system of the eleventh embodiment is configured so that the user can practice foreign languages using the terminal device 1 and the server 90 .

Specifically, the pronunciation determination process 1 shown in FIG. 22, the pronunciation determination process 2 shown in FIG. 23, and the pronunciation determination process 3 shown in FIG. 24 are sequentially executed. However, the server 90 executes one of the pronunciation determination processes 1 to 3 each time the voice response server process (FIG. 2) is executed. Further, each of the pronunciation determination processes 1 to 3 is executed as the process of S56 described above.

First, in the pronunciation determination process 1, as shown in FIG. 22, a response is generated to the effect that an instruction to input a predetermined sentence by voice is generated (S362). In this process, for example, a sentence that serves as a model of a foreign language is generated, and this sentence is urged to imitate and speak following the model. When this process ends, the pronunciation determination process 1 ends.

Next, when a voice is input with pronunciation determination processing 1, pronunciation determination processing 2 is performed. In the pronunciation determination process 2, as shown in FIG. 23, the accuracy of pronunciation and accent is scored (S372). In this processing, the speech is captured as a waveform, and the degree of matching of the waveform with the waveform of the sample text is scored.

Then, this score is recorded in the memory (S374), and the pronunciation determination process 2 ends. Subsequently, pronunciation determination processing 3 is performed. In pronunciation determination processing 3, as shown in FIG. 24, first, it is determined whether or not the score is less than a threshold (S382).

If the score is less than the threshold (S382: YES), a response is generated to instruct the input of the same sentence again (S384). In this process, for example, a response is generated again to prompt the speaker to imitate the model and speak again.

If the score is equal to or greater than the threshold (S382: NO), a response is generated indicating that the pronunciation was good and prompting the user to input the next sentence (S386). For example, generate a response such as "Good pronunciation. Let's move on."

When such processing ends, the pronunciation judgment processing 3 ends.
[Effects of the eleventh embodiment]
In the voice response system 100, the server 90 detects the degree of accuracy of the pronunciation and accent of the voice input by the user, and outputs the detected degree of accuracy.

According to such voice response system 100, accuracy of pronunciation and accent can be confirmed. For example, it is effective when practicing a foreign language.
Furthermore, in the voice response system 100, the server 90 outputs the same question again when the degree of accuracy is equal to or less than a certain value.

According to such a voice response system 100, an accurate answer can be obtained by outputting the same question.
[Modified example of the eleventh embodiment]
In the voice response system 100, the server 90 may output a voice containing the word closest to the pronunciation of the user for confirmation when the degree of accuracy is below a certain value.

According to the voice response system 100, the user can check the accuracy of pronunciation and accent.
[Twelfth embodiment]
[Processing of the 12th embodiment]
Next, the voice response system of the 12th embodiment will be explained. The voice response system of the twelfth embodiment detects the user's emotion from the voice input by the user, and generates a soothing response to the user according to the user's emotion.

Specifically, an emotion determination process shown in FIG. 25 and an emotion response generation process shown in FIG. 26 are executed. The emotion determination process is executed as details of the process of S50 described above, and as shown in FIG. (S392), then the emotions are classified by score and recorded in memory (S394).

When such processing ends, the emotion determination processing ends. Subsequently, in the process of S56 described above, the emotional response generation process is executed.
Specifically, as shown in FIG. 26, first, the emotion category set in the emotion determination process is determined (S412). If the emotion category is normal (S412: normal), a normal greeting such as "Hello" is generated as a response (message) (S414).

Also, if the emotion classification is anger (S412: anger), a sentence such as "Are you offended?" is generated as a response to calm the other party's emotion (S416). Furthermore, if the emotion category is joy (S412: joy), a greeting sentence with brighter nuances than ordinary greeting sentences, such as "You are having fun today", is generated as a response (S418).

Also, if the emotion category is confused (S412: confused), a greeting sentence for caring for the other party, such as "What's wrong?", is generated as a response (S420). When such processing ends, the emotional response generation processing ends.

[Effects of the 12th embodiment]
In the voice response system 100, the server 90 detects the user's irritability and agitation by detecting an unexpectedly uttered voice, and generates a message to suppress the irritation and agitation.

According to the voice response system 100 as described above, when the user is irritated or upset, they can be suppressed. Therefore, it is possible to suppress vocalization of trouble between the user and the surroundings.

[Thirteenth embodiment]
[Processing of the thirteenth embodiment]
Next, the voice response system of the thirteenth embodiment will be explained. In the voice response system of the thirteenth embodiment, processing is performed to guide the user to an object in the captured image. This process is executed in the server 90 as details of the process of S56 described above.

When a voice such as "Please guide me to the visible tower" is input on the terminal device 1, guidance processing is performed in the processing of S56. In the guidance process, as shown in FIG. 27, terminal position information is first acquired from the GPS receiver 27 of the terminal device 1 (S432).

Then, based on the voice (character information) and image processing, the target object is specified from among the objects in the captured image, and its position is specified (S434). In this process, the position of the object is specified in the map information (which may be acquired from the outside or held by the server 90) based on the shape, relative position, etc. of the object. For example, when a tower is shown in the captured image, the tower is specified on the map from the position of the terminal device 1 and the shape of the tower.

Subsequently, a route to this object is searched (S436), and route information is acquired (S438). This process can be realized using the same process as that in a known cloud system navigation device.

Then, a response for guiding the route is generated (S440). Also in this process, it is sufficient to generate a response similar to guidance by the navigation device.
When such processing ends, the guidance processing ends. When the guidance process is performed while the user is moving, the automatic conversation server process may be used to reproduce the message under the reproduction condition that the user reaches the point to be guided.

[Effects of the thirteenth embodiment]
In the voice response system 100, when character information is input, the server 90 generates a response according to the captured image of the surroundings of the voice response system 100, and outputs this response as voice.

According to such a voice response system 100, it is possible to output a response by voice according to the captured image. Therefore, usability can be improved compared to a configuration that generates a response only from character information.

Further, in the voice response system 100, the server 90 searches for an object included in the character information from the captured image by image processing, identifies the position of the searched object, and guides the user to the position of the object.

According to such voice response system 100, it is possible to guide the user to an object in the captured image.
Further, in the voice response system 100, the server 90 acquires route information such as weather, temperature, humidity, traffic information, and road surface conditions to the destination when providing guidance to the destination, and outputs the route information by voice. output.

According to such a voice response system 100, it is possible to notify the user of the situation (route information) to the destination by voice.
[Modification of the thirteenth embodiment]
In addition to the above configuration, text information may be input so as to respond to what the recognized object is, and what (who) is the recognized object from the captured image may be output by voice.

Further, in the voice response system 100, the server 90 may acquire a moving image of the shape of the user's mouth when inputting character information by voice instead of the process of S48. In this case, instead of the process of S52, the voice may be converted into character information, and based on the moving image, an unclear portion of the voice may be estimated to correct the character information.

According to the voice response system 100 as described above, since it is possible to estimate the utterance content from the shape of the mouth, unclear parts of the voice can be estimated satisfactorily.
[14th embodiment]
[Processing of the 14th embodiment]
Next, the voice response system of the 14th embodiment will be explained. In the voice response system of the fourteenth embodiment, the user is requested to perform a predetermined action, and it is determined whether the user has performed the action as requested. In this configuration, in the automatic conversation terminal processing shown in FIG. 6 and the automatic conversation server processing shown in FIG. 7, the movement request processing 1 shown in FIG. 28 and the movement request processing 2 shown in FIG. implemented in order.

First, when the process of S54 is completed, the movement request process 1 is started. In the movement request process 1, as shown in FIG. (S452). When this process ends, the movement request process 1 ends.

Subsequently, when the process of S54 is completed, the movement request process 2 is started. In the movement request process 2, as shown in FIG. S462). In this processing, an image captured by the camera is processed, and the user's motion is detected using detection results obtained by various sensors of the terminal device 1 . Note that when the line of sight is detected by image processing, a well-known technique for line of sight recognition may be employed.

If the line of sight or head does not move as instructed (S462: NO), the response generated in S452 is output again (S464). Also, if the line of sight and head are moving as instructed (S462: YES), another arbitrary response is generated (S466).

When such processing ends, the movement request processing 2 ends.
[Effect of Fourteenth Embodiment]
The voice response system 100 detects the line of sight of the user, and if the line of sight of the user does not move to a predetermined position in response to the call, outputs a voice requesting that the line of sight be moved to the predetermined position.

According to such a voice response system 100, the user can be made to look at a specific position. Therefore, it is possible to reliably confirm safety when driving the vehicle.
In the voice response system 100, the server 90 observes the position of the body part and the facial expression, and if there is little change in response to the call, outputs a voice requesting to change the position of the body part or the facial expression. do.

According to such a voice response system 100, it is possible to guide the user to move the body part of the user to a specific position or to make a specific facial expression. INDUSTRIAL APPLICABILITY The present invention can be used when driving a vehicle or performing a physical examination.

[15th embodiment]
[Processing of the fifteenth embodiment]
Next, the voice response system of the fifteenth embodiment will be explained. In the voice response system of the fifteenth embodiment, when the user inputs a broadcast program or a piece of music as voice, a process of complementing the broadcast program or the piece of music is performed.

In this configuration, the broadcast music complementing process shown in FIG. 30 is performed as the details of S56 described above. In the broadcast music complementing process, as shown in FIG. 30, first, it is determined whether or not the broadcast program or music (the song if the user sings it) is interrupted (S482).

If it is interrupted (S482: YES), the synchronized broadcast program and music are set as the response content in the process of S492 described later (S484), and the broadcast music complementing process is terminated. If there is no interruption (S482: NO), the broadcast program is acquired if the broadcast program is being viewed (S486), and the corresponding song is acquired if the song is being played (S488).

Here, songs and lyrics are recorded in the karaoke DB 116 in association with each other, and when acquiring songs in this process, the songs with lyrics are acquired.
Subsequently, the broadcast program or music that the user listens to is specified (S490). Then, this broadcast program or music is acquired and prepared so that it can be reproduced in synchronism with the broadcast program or music viewed by the user (S492), and the broadcast music complementing process ends.

[Effects of the fifteenth embodiment]
In the voice response system 100, the server 90 acquires a broadcast program similar to the broadcast program viewed by the user, and when the broadcast program is interrupted, outputs the broadcast program acquired by itself to reproduce the interrupted broadcast program. Complement.

According to the voice response system 100 as described above, it is possible to compensate so that the broadcast program viewed by the user is not interrupted.
Further, in the voice response system 100, when the user sings a song without lyrics with lyrics added, the server 90 compares the song with lyrics with the lyrics added by the user, and only the lyrics of the user are compared. The lyrics are output by voice in the part where there is no .

According to the voice response system 100 as described above, it is possible to compensate for a portion (a portion where the lyrics are interrupted) that a user using a so-called karaoke machine cannot sing.
[16th embodiment]
[Processing of the 16th embodiment]
Next, the voice response system of the 16th embodiment will be described. In the voice response system of the 16th embodiment, when characters are included in a captured image and the terminal device 1 receives a question about how to read the characters from the user, the information on the characters is obtained from the outside, and the characters are read. The pronunciation of the characters included in the information is output by voice.

In this configuration, the character commentary process shown in FIG. 31 is executed as the details of S56 described above. In the character explanation process, as shown in FIG. 31, first, it is determined whether or not a reading question such as "how to read" is received (S502). If a question about the reading has been received (S502: YES), the reading of the image-recognized character is retrieved from another server or the like connected via the Internet network 85 (S504), and the obtained reading is set as the response. (S506), and the character commentary process ends.

If it is not a reading question (S502: NO), it is a question of "word meaning" such as the content described in a Japanese dictionary. is received (S508). If a question about the meaning has been received, the meaning of the image-recognized character (word) is retrieved from another server or the like connected via the Internet network 85 (S510), and the obtained meaning is set in the response ( S512), the character explanation process is terminated.

[Effects of the 16th embodiment]
According to the voice response system 100, the reading of the image-recognized character is retrieved from another server or the like, and the obtained reading is set as the response. can teach

[17th embodiment]
[Processing of the 17th embodiment]
Next, the voice response system of the seventeenth embodiment will be explained. In the voice response system of the seventeenth embodiment, the server 90 detects the abnormal behavior and state of the user of the terminal device 1 based on the sensor values detected by the terminal device 1, and reports when there is an abnormality. Take action.

Specifically, the terminal device 1 performs the action response terminal process shown in FIG. 32, and the server 90 performs the action response server process. In the action response terminal process, as shown in FIG. 32, first, outputs from various sensors mounted on the terminal device 1 are obtained (S522), and an image captured by the camera 41 is obtained (S524). Then, the acquired output from the various sensors and the captured image are transmitted in packets to the server 90 (S526), and the action response terminal processing is terminated.

Next, in the action response server process, as shown in FIG. 33, first, the above-described processes of S42 to S44 are performed. Subsequently, based on the location information of the terminal device 1 (detection result by the GPS receiver 27), behavior such as loitering is identified (S532), and the user's environment is determined based on the detection result by the temperature sensors 15, 19, etc. Detect (S534). Then, an abnormality is detected (S536).

In this process, abnormalities are detected based on changes in position information and the environment. For example, if the user does not move in a hot or cold place, or if the user is in a place where the user does not usually go, an abnormality is detected (S536). Alternatively, the position information and the environment are scored, and if the score is below a reference value (outside the reference range), it is determined to be abnormal.

Subsequently, it is determined whether or not an abnormality has been detected (S538). If no abnormality is detected (S538: NO), the action response server process is terminated. Also, if an abnormality is detected (S538: YES), a message to the effect that there is an abnormality is generated (S540), and a predetermined contact is notified (S542). Then, the processes of S62 to S68 (excluding S66) described above are performed, and the action response server process is terminated.

[Effects of the 17th embodiment]
In the voice response system 100, the server 90 detects the behavior of the user and the surrounding environment of the user, and generates a message according to the detected behavior and surrounding environment.

According to such a voice response system 100, it is possible to notify a dangerous place, a restricted area, and the like. Also, it is possible to detect that the user has an abnormal behavior.

Further, in the voice response system 100, the server 90 determines the health condition of the user based on the captured image of the user, and generates a message according to the health condition.
According to such a voice response system 100, it is possible to manage the health condition of the user.

Also, in the voice response system 100, the server 90 notifies a predetermined point of contact when the health condition falls below a reference value.
According to such a voice response system 100, it is possible to report when the health condition of the user is below the reference value. Therefore, it is possible to inform others of the abnormality at an earlier stage.

[Other embodiments]
Embodiments of the present invention are not limited to the above-described embodiments, and can take various forms as long as they fall within the technical scope of the present invention.

For example, voice response system 100 may mediate bilateral and multiparty interactions. Specifically, when it is necessary to yield to each other at an intersection or the like, the terminal devices 1 may negotiate which vehicle should enter the intersection first. In this case, each terminal device 1 transmits to the server 90 information about the direction of movement when approaching the intersection and the speed at which the intersection is approached. The order of priority can be set, and a voice such as "Stop" or "Approach possible" is generated and output according to the order of priority.

In addition, when the terminal device 1 accepts an incoming call (incoming call) for communication that requires a real-time response, such as voice communication, the incoming call may be accepted only when it is convenient for the user. Specifically, when the user's face can be imaged by the camera 41, it may be regarded as convenient for the user and the incoming call may be accepted.

Furthermore, some people feel uncomfortable if they do not respond to a call to another party during voice communication or the like. In order to suppress such emotions, the user who is waiting for a response from the other party may be notified of the situation of the other party. For example, if the user's schedule is managed in the terminal device 1 and the user does not respond to an incoming call, search for what the user is doing or the free time in the user's schedule, It is conceivable to let the user know when they can respond.

Also, if the user does not answer the incoming call, the user's location may be communicated to the caller. For example, if the user is connected to the Internet or the like via a smartphone or a personal computer, it can be known which terminal is being operated. From this information, it is conceivable to specify the user's location and transmit it to the caller.

Furthermore, whether or not the user can respond to an incoming call may be determined using location information using GPS or the like. Based on the location information, it can be determined whether the user is in a car or at home. It should be determined that the incoming call cannot be answered by judging that it is medium. When the user cannot answer the incoming call in this way, it is conceivable to inform the caller of what the user is doing as described above.

In order to acquire position information, a configuration using a security camera is also conceivable. In recent years, security cameras have been installed in various locations, and these security cameras can be used to recognize the location of the user by using a configuration for identifying the person, such as face recognition. . In addition, a security camera may be used to determine what the user is doing (whether or not the user can answer the phone). Whether or not the incoming call can be answered can also be determined based on the condition of whether or not another fixed-line phone is being used (an incoming call cannot be answered while the fixed-line phone is in use).

Furthermore, when the user of the terminal device 1 wants to have a conversation with someone, the user's personality learning result is used to call a terminal device that is presumed to be compatible with each other among an unspecified number of users. good too. In such a case, a topic that is likely to be exciting (a topic that both users are interested in (extracted using learning results)) may be spoken to the users.

Also, when the voice response device is not used for a long time (when the user does not speak for a reference time or longer), the voice response device may say something to the user.
At this time, the words to be spoken may be selected using location information such as GPS.

[Relationship between each means (the present invention) described in the scope of claims or the means for solving the problem and the configuration in the embodiment]
The terminal device 1 and the server 90 in the above embodiment correspond to an example of the voice response device of the present invention. Also, the processing of 22 and S56 in the above embodiment corresponds to an example of the response obtaining means of the present invention.

Furthermore, the processing of S28, S60, and S64 in the above embodiment corresponds to an example of the audio output means of the present invention. Also, the processing of S2 and S6 in the above embodiment corresponds to an example of the voice input means of the present invention.

Furthermore, the processing of S14 in the above embodiment corresponds to an example of the voice transmitting means of the present invention. Further, the response candidate DB 105 in the above embodiment corresponds to an example of the response recording means of the present invention.

Furthermore, the processing of S56 in the above embodiment corresponds to an example of the personality information acquiring means of the present invention. Also, the processing of S22 and S56 in the above embodiment corresponds to an example of the response acquisition means of the present invention.

Furthermore, the processing of S28, S60, and S64 in the above embodiment corresponds to an example of the audio output means of the present invention. Also, the processing of S254, S258, and S260 in the above embodiment corresponds to an example of the first personality information generating means and the second personality information generating means of the present invention. Also, the processing of S56 in the above embodiment corresponds to an example of the personality information acquiring means of the present invention.

Furthermore, the processing of S22 and S56 in the above embodiment corresponds to the response acquisition means of the present invention. Also, the processing of S28, S60, and S64 in the above embodiment corresponds to an example of the audio output means of the present invention.

Furthermore, the processing of S254, S258, and S260 in the above embodiment corresponds to an example of the first personality information generating means and the second personality information generating means of the present invention.
Furthermore, the processing of S48 and S56 in the above embodiment corresponds to an example of the response generating means of the present invention. Also, the processing of S28, S60, and S64 in the above embodiment corresponds to an example of the audio output means of the present invention.

Further, the modified example of the above embodiment: the process of S48 corresponds to an example of the voice input moving image acquiring means of the present invention. Also, the processing of S52 in the above embodiment corresponds to an example of the character information conversion means of the present invention.

Furthermore, the preference information generating process in the above embodiment corresponds to an example of the preference information generating means of the present invention. Also, the process of S56 in the above embodiment corresponds to an example of the response candidate acquiring means of the present invention.

Furthermore, the action character input process in the above embodiment corresponds to an example of the character information generating means of the present invention. Further, the other device information acquisition means and the other terminal use processing in the above embodiment correspond to an example of the transfer means of the present invention.

Furthermore, the processing of S98 in the above embodiment corresponds to an example of the reproduction condition determining means of the present invention. Also, the processing of S100 in the above embodiment corresponds to an example of the message reproducing means of the present invention.

Furthermore, the process of S116 in the above embodiment corresponds to an example of the non-response transmitting means of the present invention. Also, the processing of S372 in the above embodiment corresponds to an example of the speech accuracy detection means of the present invention.

Furthermore, the processing of S374 in the above embodiment corresponds to an example of accuracy level output means of the present invention. Also, the processing of S204 in the above embodiment corresponds to an example of the connection control means of the present invention.

Furthermore, the processing of S50 in the above embodiment corresponds to an example of the emotion determination means of the present invention. Also, the process of S438 in the above embodiment corresponds to an example of the route information acquisition means of the present invention.

Furthermore, the processing of S462 in the above embodiment corresponds to an example of the line-of-sight detection means of the present invention. Also, the process of S464 in the above embodiment corresponds to an example of the line-of-sight movement request transmitting means of the present invention.

Furthermore, the processing of S464 in the above embodiment corresponds to an example of the change request transmitting means of the present invention. Also, the processing of S486 in the above embodiment corresponds to an example of the broadcast program acquiring means of the present invention.

Furthermore, the process of S484 in the above embodiment corresponds to an example of the broadcast program complementing means and lyrics adding means of the present invention. Also, the processing of S504 and S506 in the above embodiment corresponds to an example of the reading output means of the present invention. Also, the processing of S522 and S524 in the above embodiment corresponds to an example of the action environment detection means of the present invention.

Furthermore, the processing of S538 in the above embodiment corresponds to an example of the health condition determination means of the present invention. Also, the processing of S540 in the above embodiment corresponds to an example of the health message generating means of the present invention.

Furthermore, the processing of S542 in the above embodiment corresponds to an example of reporting means of the present invention.

DESCRIPTION OF SYMBOLS 1... Terminal device 10... Action sensor unit 11... Dimensional acceleration sensor 13... Axis gyro sensor 15... Temperature sensor 17... Humidity sensor 19... Temperature sensor 21... Humidity sensor 23... Illuminance sensor 25... Wetness sensor 27 GPS receiver 29 wind sensor 33 electrocardiogram sensor 35 heart sound sensor 37 microphone 39 memory 41 camera 50 communication unit 53 radio telephone unit 55 Contact memory 60 Notification unit 61 Display 63 Illumination 65 Speaker 70 Operation unit 71 Touch pad 73 Confirmation button 75 Fingerprint sensor 77 Help request lever 80 Communication base station 85 Internet network 90 Server 100 Voice response system 101 Operation unit 102 Voice recognition DB 103 Predictive conversion DB 104 Voice DB 105 Response candidate DB 106 Personality DB, 107... Learning DB, 108... Preference DB, 109... News DB, 110... Weather DB, 111... Playback condition DB, 112... Handwritten character/sign language DB, 113... Terminal information DB, 114... Emotion determination DB, 115... Health judgment DB, 116... Karaoke DB, 117... Report destination DB, 118... Sales DB, 119... Client DB.

Claims (3)

A voice response system comprising: a request source device that requests a request; a provider device that provides information; and a server capable of communicating with the request source device and the provider device,
The provision source device is configured to be able to set whether to permit information provision,
The server acquires a request from the requesting device, and if the request includes a request specifying the providing source device, transmits the request to the specified providing source device, an information acquisition unit configured to acquire provided information provided from the provider device when the provision is permitted;
a providing unit configured to generate a voice response based on the provided information as a response to a request from the requesting device and to provide the response to the requesting device;
A voice response system with A voice response system according to claim 1,
The request source device performs speech recognition by converting voice including the request into character information, and sends the character information as the request to the server.
A voice response system configured to: a request source terminal device that requests a request;
a provider terminal device serving as an information provider;
a voice response device server configured as a server capable of communicating with the request source terminal device and the provider terminal device;
A voice response system comprising:
The provider terminal device
a permission determination unit configured to determine, upon receipt of a request from the voice response device server, whether or not it is set to permit provision of information;
When the information provision is permitted, the requested information is acquired from the memory or various sensors of the provider terminal device, and the information is transmitted to the voice response device server as provision information. an information transmission unit;
with
The voice response device server includes:
acquiring a request from the request source terminal device, and when the request includes a request specifying the provision source terminal device, transmitting the request to the specified provision source device; an information acquisition unit configured to acquire provided information provided from
a provision unit configured to generate a voice response based on the provided information as a response to a request from the request source terminal device and to provide the response to the request source terminal device;
A voice response system with

Images