JP6669951B2 - Voice response device - Google Patents

Description

Cross-reference of related applications

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

  The present invention relates to a voice response device that makes a response to input character information by voice.

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

Japanese Patent No. 4832097 Japanese Patent No. 4924950

In the above technology, it is set so that one answer specified by a dictionary is simply given to one question.
One aspect of the present invention is to improve the usability for a user in a voice response device that makes a response to input character information by voice.

In the invention of the first aspect,
A voice response device that makes a response to input character information by voice,
Response acquisition means for acquiring a plurality of different responses to the character information,
Sound output means for outputting the plurality of different responses in different voice colors,
It is characterized by having.

  According to such a voice response device, a plurality of responses can be output in different voices. Therefore, even when the solution to one character information cannot be specified as one, the user can output different solutions in different voices. Can be output easily. Therefore, the usability can be improved for the user.

  The voice response device of the present invention may be configured as, for example, a terminal device possessed by a user, or may be configured as a server that communicates with the terminal device. Further, the character information may be input using an input unit on a keyboard or the like, or may be input by converting voice into character information.

By the way, in the voice response device, as in the invention of the second aspect,
Voice input means for the user to input voice, and convert the input voice to character information,
An external device that generates a plurality of different responses to the character information and transmits the generated response to the voice response device;
With
The response acquiring unit may acquire the response from the external device.

  According to such a voice response device, the voice response device can input a voice, and thus can be configured to input character information by voice. In addition, since a 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 to character information” may be performed by a voice response device or may be performed by an external device.
Further, in the above voice response device, as in the invention of the third aspect,
The voice response device or the external device, for each of the plurality of character information, a response recording unit in which a plurality of different responses including a positive response and a negative response to each character information is recorded,
The response obtaining means obtains the positive response and the negative response as the plurality of different responses,
The audio output means may reproduce the voice in different voices for the positive response and the negative response.

  According to such a voice response device, responses in different positions, such as a positive response and a negative response, can be reproduced in different voices, so that voice can be reproduced as if another person is talking. Can be. Therefore, it is possible to make it difficult for the user who listens to the voice to feel uncomfortable.

  Note that the tone may be changed according to the type of response or the wording of the response. For example, when responding in a gentle tone, the voice may be reproduced with a calm female voice, and in responding with an intense tone, a brave male voice may be used. That is, the response content and the personality may be associated with each other, and the tone may be set according to the personality.

  Further, in the above-described voice response apparatus, as in the invention of the fourth aspect, it is possible to adopt a configuration in which it is used at the reception of a work place or a company, or alternatively, a configuration in which it is difficult for a user to directly tell someone.

  When using the voice response device at the reception, the name of the person coming to the sales and the company name are recorded in advance on the voice response device or an external device, and the person who came to the reception claims this name or the company name In such a case, the response may be generated so as to reproduce the voice of the rejection.

  In addition, in the case of a configuration in which something difficult to say is conveyed instead, for example, before the date, talking to the present device to say such a thing today can be performed at an appropriate timing (for example, a preset time or For example, when a certain period of time has elapsed since the conversation was interrupted), the voice response device may speak (reproduce the voice) instead.

  Alternatively, it may be configured to speak a word that triggers something difficult to say, such as "Did you say something to her?" That is, instead of outputting a response immediately, a response may be output when a reproduction condition is satisfied, such as after a certain period of time.

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

  In this case, the voice response device is provided with sensors for detecting position information, temperature, humidity, illuminance, noise level, and the like, and a database such as dictionary information, and extracts necessary information as required. What should I do?

  According to such a voice response device (external device), it is possible to obtain information for generating a response from another voice response device. In this case, information unique to another voice response device, such as the position of another voice response device, can be obtained.

Also, it is possible to transmit information unique to itself to another voice response device.
Further, in the above-described voice response device, as in the invention of the seventh aspect, a response (eg, a positive response or a negative response) output by the voice response device itself or another voice response device is input as character information, and the response to this response is input. A response for making a rebuttal may be generated. In other words, from the perspective of the employer, it is possible to hear discussions from both opinions in favor of and in favor of the opposite. Then, after hearing this discussion, the user can make a final decision.

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

In the eighth aspect of the invention,
A voice response device that makes a response to input character information by voice,
Personality information acquisition means for acquiring personality information that associates the personality of a person representing a user or a person related to the user according to a preset division,
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 the response candidates according to the personality information, and outputting the selected response;
It is characterized by having.

  According to such a voice response device, different responses can be made according to the characteristics of the user or a person (related person) related to the user. Therefore, usability can be improved for the user.

In the above-described voice response device, as in the ninth aspect of the invention,
A first personality information generating unit configured to generate personality information of the user or the related person based on answers to a plurality of questions set in advance;
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 the personality information, a well-known personality analysis technique (Rorschach test, Sondy test, or the like) may be used. When generating the personality information, an aptitude test technique used by a company or the like for an employment test may be used.

Further, in the above voice response device, as in the tenth aspect,
A second character information generating unit that generates character 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, personality information can be generated in a process in which a user uses the voice response device.
In the above-described voice response device, as in the eleventh aspect,
Preference information generating means for generating preference information indicating a preference tendency of the user or the related person based on a character string included in character information,
The audio output unit 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, a response can be made according to the preference of the user or the person concerned.
Further, in the above voice response apparatus, as in the twelfth aspect, learning (recording and analyzing) the user's actions (conversation, the place where the user has moved, and what is reflected on the camera), the user's conversation is performed. May be made up for the shortage of words.

  For example, if the user supplements the conversation "The curry is good" to the question "Is it okay to have a hamburger today?" But the reason why he said curry is good is conveyed.

Further, such a configuration can be implemented during a telephone call, or may be configured to participate in a conversation of the user without permission.
Further, in the above voice response device, as in the thirteenth aspect,
Response candidate obtaining means for obtaining a response candidate from a predetermined server or the Internet,
May be provided.

According to such a voice response device, response candidates can be obtained not only from the own device or an external device, but also from any device connected via the Internet, a dedicated line, or the like.
Further, in the voice response device, as in the fourteenth aspect,
Character information generating means for converting an operation by a user into character information,
May be provided.

Here, the motions according to the present invention correspond to motions caused by muscle motions such as conversation, handwriting of characters, or gestures (eg, sign language).
According to such a voice response device, the operation of the user can be converted into character information.

Further, in the voice response device, as in the fifteenth aspect,
The character information generation means converts the voice of the user's utterance into character information, and accumulates the habit (pronunciation in pronunciation) at the time of utterance as learning information (capturing the characteristic and recording this characteristic).
You may do so.

According to such a voice response device, the character information can be generated based on the learning information, so that the generation accuracy of the character information can be improved.
In the above-described voice response device, as in the sixteenth aspect,
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 the voice response device can be used. Therefore, even when another voice response device is used, the accuracy of generating character information can be improved.

  Further, in the above-described voice response device, as in the seventeenth aspect, any one of a user's action and operation may be detected, and learning information or personality information may be generated based on the detected action or operation. .

  According to such a voice response device, for example, when it is detected that the user jumps on the train for several consecutive days, the user is prompted to leave the house several minutes earlier from the next day, or the user is easily angry from the conversation. When it is detected that there is a tendency, it is possible to output sound or music that suppresses the mood.

In the above-described voice response device, as in the eighteenth aspect,
Another device information acquisition means for acquiring information recorded in another voice response device from another voice response device may be provided.

According to such a voice response device, a response can be generated based on information recorded in another voice response device.
Further, in the above voice response device, as in the invention of the nineteenth aspect,
When the character information is not input, a reproduction condition determination unit that determines whether the state of the voice response device matches a reproduction condition set in advance as a condition for outputting a voice,
A message playback unit that outputs a preset message when the playback condition is met;
May be provided.

  According to such a voice response device, it is possible to output voice even when character information is not input (that is, when the user does not speak). For example, by forcibly causing the user to speak, it can be used for measures to prevent drowsiness while driving a car. In addition, it is possible to confirm the safety by determining whether or not a person living alone responds.

Further, in the voice response device, as in the invention of the twentieth aspect,
The message reproducing means may acquire news information and output a message relating to the news in a question format for asking the user for an answer.

  According to such a voice response device, since conversation about news can be performed, it is possible to suppress that the same conversation is always performed. As the content of the conversation, for example, if information on the stock price of a certain company can be obtained, "the stock price of the company XX today has risen by XX yen. Did you know?" .

Further, in the voice response device, as in the invention of the twenty-first aspect,
The voice output means or the message reproducing means may be configured to add externally acquired information (news, environment (temperature, weather, position information, etc.)) separately acquired to a preset message and output the message.

According to such a voice response device, it is possible to output a response in which a predetermined message and acquired information are combined.
Further, in the voice response device, as in the invention of the twenty-second aspect,
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 message.

  According to such a voice response device, it is difficult to reproduce a message with a high frequency of reproduction, thereby providing randomness at the time of message reproduction, or by repeatedly reproducing a message with a high frequency of reproduction to alert or store information. It can encourage retention.

Further, in the above voice response device, as in the invention of the twenty-third aspect,
When a response or a response to the message is not obtained, a non-response transmission unit that transmits information that specifies a user to a preset contact address and that no response was obtained,
May be provided.

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

According to such a voice response device, it is possible to confirm the memory ability of the user and to fix the memory.
Further, in the voice response device, as in the invention of the twenty-fifth aspect,
Utterance accuracy detecting means for detecting the accuracy of pronunciation and accent of voice input by the user,
An accuracy output means for outputting the detected accuracy,
May be provided.

According to such a voice response device, the accuracy of pronunciation and accent can be confirmed. This is effective, for example, when practicing a foreign language.
In the above-described voice response device, as in the twenty-sixth aspect,
The accuracy output means may output a sound including the closest word when the accuracy is equal to or less than a certain value.

According to such a voice response device, a user can confirm the accuracy of pronunciation and accent.
Further, in the voice response device, as in the invention of the twenty-seventh aspect,
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 exact answer can be obtained by outputting the same question.
Further, in the voice response device, as in the invention of the twenty-eighth aspect,
Connection control means for specifying a communication partner by the input character information and connecting the communication partner and the communication partner preset for each communication partner;
May be provided.

According to such a voice response device, it is possible to assist reception work and telephone correspondence.
In particular, in the voice response device, as in the invention of the twenty-ninth aspect,
The connection control means may identify a business activity (sales) and a visitor, and may reproduce a message refusing the business activity.

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

According to such a voice response device, it is possible to assist operations such as a telephone transfer and a call to a reception.
Further, in the above-described voice response apparatus, as in the invention of the thirty-first aspect, a requirement that the other party speaks may be recognized based on the keyword, and an outline of the other party speaking may be transmitted to the user.

According to such a voice response device, it is possible to assist the agency work with the customer.
Further, in the voice response device, as in the invention of the thirty-second aspect,
An emotion that reads an emotion from a voice of a voice input by a user and outputs which of the emotions including at least one of normal, anger, joy, confusion, sadness, and exaltation. Determination means may be provided.

According to such a voice response device, a response can be output according to the emotion of the user.
Next, the invention of the 33rd aspect is:
When the character information is input, response generation means for generating a response according to a captured image of the periphery of the voice response device,
Voice output means for outputting the response by voice,
It is characterized by having.

  According to such a voice response device, it is possible to output a response in voice according to the captured image. Therefore, usability can be improved as compared with a configuration in which a response is generated only from character information.

  As a specific configuration of the present invention, for example, a configuration in which text information is input so as to respond to what is recognized, and what (someone) is recognized from the captured image is output as a voice, or the like is given. .

By the way, in the voice response device, as in the invention of the thirty-fourth aspect,
Position specifying means searching 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;
Guiding means for guiding to the position of the object,
May be provided.

According to such a voice response device, a user can be guided to an object in a captured image.
Further, in the voice response device, as in the invention of the thirty-fifth aspect,
Voice input moving image obtaining means for obtaining a moving image capturing the shape of the user's mouth when inputting character information by voice,
The voice information is converted to character information, and, based on the moving image, character information conversion means for correcting the character information by estimating an unclear portion of the sound,
May be provided.

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

According to such a voice response device, when the user is frustrated or upset, these can be suppressed. Therefore, occurrence of trouble between the user and the surroundings can be suppressed.
Further, in the above voice response device, as in the thirty-seventh aspect,
In the case of providing guidance to the destination, it is provided with route information acquisition means for acquiring route information such as weather, temperature, humidity, traffic information, and road surface conditions to the destination,
The message reproducing means may output the route information by voice.

According to such a voice response device, the situation (route information) to the destination can be notified to the user by voice.
Further, in the above voice response device, as in the invention of the thirty-eighth aspect,
Gaze detection means for detecting the gaze of the user,
When the user's line of sight does not move to a predetermined position in response to the call by the message reproducing unit, a line of sight movement request transmitting unit that outputs a voice requesting that the line of sight move to the predetermined position,
May be provided.

According to such a voice response device, a user can be caused to see a specific position. Therefore, it is possible to surely confirm the safety at the time of driving the vehicle.
In the voice response device, as in the thirty-ninth aspect,
A change request transmission unit that observes the position of the body part and the facial expression and, when the change in response to the call is small, may output a voice requesting to change the position of the body part and the facial expression may be provided. .

  According to such a voice response device, it is possible to move the position of the body part of the user to a specific position or to guide the user to give a specific expression. INDUSTRIAL APPLICATION This invention can be utilized at the time of driving of a vehicle, a physical examination, etc.

Further, in the voice response device, as in the invention of the fortieth aspect,
Broadcast program acquisition means for acquiring a broadcast program similar to a broadcast program viewed by a user;
Broadcast program complementing means for complementing the interrupted broadcast program by outputting the broadcast program obtained by itself when the broadcast program is interrupted,
May be provided.

According to such a voice response device, it is possible to supplement a broadcast program viewed by a user so as not to be interrupted.
Further, in the voice response device, as in the invention of the forty-first aspect,
When a user sings a song without lyrics with lyrics, the song with lyrics is compared with the lyrics given by the user, and lyrics are added to output the lyrics as voice when there is only the lyrics of the user. Means.

According to such a voice response device, it is possible to supplement a portion of the so-called karaoke where the user cannot sing (a portion where lyrics are interrupted).
Further, in the voice response device, as in the invention of the forty-second aspect,
When a character is included in a captured image and a user receives a question about how to read the character, the information of the character is obtained from the outside, and the reading of the character included in the information is output as a voice. means,
May be provided.

According to such a voice response device, it is possible to teach a user how to read characters.
Further, in the voice response device, as in the invention of the forty-third aspect,
Equipped with behavior 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 action or the surrounding environment.

According to such a voice response device, it is possible to report a dangerous place, a restricted area, and the like. In addition, it is possible to detect that the user has abnormal behavior.
Further, in the voice response device, as in the invention of the forty-fourth aspect,
Health condition determination means for determining a health condition based on a captured image of the user,
Health message generating means for generating a message according to the health condition;
May be provided.

According to such a voice response device, the health condition of the user can be managed.
Further, in the above voice response device, as in the invention of the forty-fifth aspect,
Notification means for notifying predetermined contact points 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 equal to or less than the reference value. Therefore, the abnormality can be notified to another person earlier.
Furthermore, in the above-described voice response device, information on the user may be output in response to an inquiry from a person other than the user, as in the invention of the forty-sixth aspect.

  According to such a voice response device, for example, if the distance of a walk including a meal content of the user is detected, a question at a hospital or the like can be answered on behalf of the user. Moreover, you may make it learn, such as a health condition and self-introduction.

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

1 is a block diagram illustrating a schematic configuration of a voice response system to which the present invention has been applied. FIG. 2 is a block diagram illustrating a schematic configuration of a terminal device. It is a flowchart which shows the voice response terminal process which MPU of a terminal device performs. It is a flowchart which shows the voice response server process which an operation part of a server performs. It is explanatory drawing which shows an example of a response candidate DB. It is a flowchart which shows the automatic conversation terminal process which MPU of a terminal device performs. It is a flowchart which shows the automatic conversation server process which the calculation part of a server performs. 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 an operation part of a server performs. It is a flowchart which shows the guidance terminal process which MPU of a terminal device performs. It is a flowchart which shows the guidance server process which the calculation part of a server performs. It is a flowchart which shows the reception process which the calculation part of a server performs. It is a flowchart which shows the information provision terminal process which MPU of a terminal device performs. It is explanatory drawing which shows an example of a 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 a taste DB. 9 is a flowchart illustrating a preference information generation process executed by a calculation unit of the server. It is explanatory drawing which shows the example of a combination of a personality classification and a preference. It is a flowchart which shows the operation | movement character input process which the calculation part of a server performs. It is a flowchart which shows the other terminal use process which the calculation part of a server performs. It is a flowchart which shows the memory confirmation process which the calculation part of a server performs. 5 is a flowchart illustrating a sound generation determination process 1 executed by a calculation unit of the server. 9 is a flowchart illustrating a sound generation determination process 2 executed by a calculation unit of the server. 9 is a flowchart illustrating a sound generation determination process 3 executed by a calculation unit of the server. It is a flowchart which shows the emotion determination process which the calculation part of a server performs. It is a flowchart which shows the emotion response generation process which the calculation part of a server performs. It is a flowchart which shows the guidance process which the calculation part of a server performs. 6 is a flowchart illustrating a movement request process 1 executed by a calculation unit of the server. 9 is a flowchart illustrating a movement request process 2 executed by a calculation unit of the server. It is a flowchart which shows the broadcast music complement process performed by the calculation part of a server. It is a flowchart which shows the character commentary process which the calculation part of a server performs. It is a flowchart which shows the action response terminal process which the calculation part of a server performs. It is a flowchart which shows the action response server process which the calculation part of a server performs.

An embodiment according to the present invention will be described below with reference to the drawings.
[First Embodiment]
[Configuration of the present embodiment]
The voice response system 100 to which the present invention is applied is a system configured to generate an appropriate response in the server 90 in response to voice input in the terminal device 1 and output the response in voice in the terminal device 1. It is. Specifically, as shown in FIG. 1, the 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 and an Internet network 85.

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

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

Next, as shown in FIG. 2, the terminal device 1 includes a behavior sensor unit 10, a communication unit 50, a notification unit 60, and an operation unit 70 provided in a predetermined housing.
The behavior sensor unit 10 includes a well-known MPU 31 (microprocessor unit), a memory 39 such as a ROM and a RAM, and various sensors. The MPU 31 is configured such that sensor elements constituting various sensors determine an inspection target (humidity, wind speed, etc.). For example, processing such as driving a heater for optimizing the temperature of the sensor element is performed so that the detection can be performed well.

  The behavior sensor unit 10 includes, as various sensors, a three-dimensional acceleration sensor 11 (3DG sensor), a three-axis gyro sensor 13, a temperature sensor 15 disposed on the back of the housing, and a humidity disposed on the back of the housing. A sensor 17, a temperature sensor 19 disposed on the front of the housing, a humidity sensor 21 disposed on the front of the housing, an illuminance sensor 23 disposed on the front of the housing, and a rear surface of the housing. A wet 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 electrocardiographic sensor 33, a heart sound sensor 35, a microphone 37, and a camera 41 as various sensors. Each of the temperature sensors 15 and 19 and each of the humidity sensors 17 and 21 measure the temperature or humidity of the outside air of the housing as an inspection target.

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

  The three-axis gyro sensor 13 detects, as angular velocities applied to the terminal device 1, a vertical direction (Z direction), and any two directions perpendicular to the vertical direction (width direction (Y direction) of the housing, and Angular acceleration in the thickness direction (X direction) (each counterclockwise speed in each direction is positive) is detected, and the detection result is output.

  The temperature sensors 15 and 19 include, for example, a thermistor element whose electric resistance changes according to the temperature. In the present embodiment, the temperature sensors 15 and 19 detect the temperature in degrees Celsius, and the temperature display described below is performed in degrees Celsius.

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

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

  The heart sound sensor 35 is configured as a vibration sensor that captures vibration due to the pulsation of the user's heart, and the MPU 31 considers the vibration due to the pulsation in consideration of the detection result of the heart sound sensor 35 and the heart sound input from the microphone 37. Identify noise from other vibrations and noise.

The wetting sensor 25 detects a water drop on the housing surface, and the electrocardiographic sensor 33 detects a user's beating.
The camera 41 is arranged inside the housing of the terminal device 1 so that the outside of the terminal device 1 is set as an imaging range.

  The communication unit 50 includes a well-known MPU 51, a wireless 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 unit 50 executes a process according to a detection result by the behavior sensor unit 10, an input signal input via the operation unit 70, and a program stored in a ROM (not shown).

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

  The wireless telephone unit 53 is configured to be able to communicate with a base station of a mobile phone, for example, and the MPU 51 of the communication unit 50 outputs a processing result by the MPU 51 to the notifying unit 60, or outputs the result through the wireless telephone unit 53. To a preset destination.

  The contact memory 55 functions as a storage area for storing positional information of the visit destination of the user. In the contact memory 55, information on contact information (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 composed of, for example, LEDs capable of emitting seven colors, and a speaker 65. The components of the notification unit 60 are 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 rescue request lever 77.
The touch pad 71 outputs a signal corresponding to a position or pressure touched by a user (a user, a guardian of the user, or the like).

  The confirmation button 73 is configured so that the contact of a built-in switch is closed when pressed by the user, so that the communication unit 50 can detect that the confirmation button 73 is pressed. I have.

  The fingerprint sensor 75 is a well-known fingerprint sensor, and is configured to be able to read a fingerprint using, for example, an optical sensor. In place of the fingerprint sensor 75, a unit capable of recognizing human physical characteristics such as a sensor for recognizing the shape of a palm vein (a unit capable of performing biometrics authentication: identifying an individual) Any means that can be used).

Also provided is a rescue request lever 77 which is connected to a predetermined contact when operated.
[Processing of this embodiment]
The processing performed in the voice response system 100 will be described below.

  The voice response terminal process performed by the terminal device 1 is a process of receiving a voice input by a user, transmitting the voice to the server 90, and reproducing a response from the server 90 when receiving a response to be output from the server 90. . This process is started when the user inputs a command to input a voice through the operation unit 70.

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

  If there is no voice input (S6: NO), it is determined whether a timeout has occurred (S8). Here, the time-out indicates that the allowable time for waiting for processing has been exceeded, and the allowable time is set to, for example, about 5 seconds.

If a timeout has occurred (S8: YES), the process proceeds to S30 described below. If the timeout has not occurred (S8: NO), the process returns to S6.
If there is a voice input (S6: YES), the voice is recorded in the memory (S10), and it is determined whether or not the voice input has been completed (S12). Here, it is determined that the input of the voice has ended when the voice has been interrupted for a certain period of time or longer, or when an instruction to end the voice input has been input via the operation unit 70.

  If the voice input has not been completed (S12: NO), the process returns to S10. If the input of the voice has been completed (S12: YES), the data of the ID for specifying itself, the voice, and the captured image is transmitted to the server 90 by packet (S14). The process of transmitting data may be performed between S10 and S12.

Subsequently, it is determined whether or not the data transmission has been completed (S16). If the transmission has not been completed (S16: NO), the process returns to S14.
If the transmission has been completed (S16: YES), it is determined whether or not the data (packet) transmitted in the voice response server process described later has been received (S18). If data has not been received (S18: NO), it is determined whether or not a timeout has occurred (S20).

If the time-out has occurred (S20: YES), the process proceeds to S30 described later. If the timeout has not occurred (S20: NO), the process returns to S18.
If data has been received (S18: YES), a packet is received (S22). In this process, one or a plurality of different responses to the character information are associated with different voices.

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

  If the reception has been completed (S24: YES), a response based on the received packet is output from the speaker 65 by voice (S28). In this processing, when a plurality of responses are reproduced, the plurality of responses are reproduced in different voices. When such processing ends, the voice response terminal processing ends.

  Next, the voice response server process performed by the server 90 (external device) will be described with reference to FIG. The voice response server process is a process of receiving a voice from the terminal device 1, performing voice recognition for converting the voice into character information, generating a response to the voice, and returning the response to the terminal device 1. In particular, in the present embodiment, a plurality of responses may be transmitted in association with voices of different timbres.

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

  If a packet has been 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.

  Subsequently, the voice contained in the packet is recognized (S46). Here, in the voice recognition DB 102, many voice waveforms are associated with many characters. The prediction conversion DB 103 is associated with a word that is likely to be used following a certain word.

Therefore, in this process, a well-known voice recognition process is performed by referring to the voice recognition DB 102 and the prediction conversion DB 103, and the voice is converted into character information.
Subsequently, an object in the captured image is specified by performing image processing on the captured image (S48). Then, the emotion of the user is determined based on the waveform of the voice, the ending of the word, and the like (S50).

  In this process, the user refers to the emotion determination DB 114 in which the waveform of voice (voice color), the ending of words, and the like, and the classification of emotions, such as normal, anger, joy, confusion, sadness, and exaltation, are referred to. Is determined in any of the categories, and the determination result is recorded in the memory. Subsequently, by referring to the learning DB 107, a word frequently spoken by the user is searched, and a portion where the character information generated by voice recognition is ambiguous is corrected.

  In the learning DB 107, characteristics of the user such as words often spoken by the user and habits at the time of pronunciation are recorded for each user. In addition, in the conversation with the user, data is added or corrected to the learning DB 107.

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

  For example, as shown in the first row of FIG. 5, when the character information of "Today's * weather" is input, the first output of "Today's * weather is *" is the voice of woman 1. Output in association. However, the part of “*” is acquired by accessing the weather DB 110 in which the area name is associated with the weather forecast for several days in the area.

In addition, when the character information “Today's * weather” is input, the weather at the timing when today's weather changes is also obtained from the weather DB 110, and the second output “However, * is *.” It is output in association with one voice. If today's Tokyo weather is fine and tomorrow's weather is rainy, and if "Today's Tokyo weather" is entered, the voice of Woman 1 will output "Today's Tokyo weather is fine." The voice of Man 1 will output "However, it will rain tomorrow."

  In the present embodiment, a case has been described in which a plurality of responses are output. However, when there is only one response to an input, there is only one response. For this reason, it is determined whether there is one response (S58). If there is only one response (S58: YES), the process proceeds to S62 described later.

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

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

Then, the generated response (voice) is transmitted as a packet to the communication partner terminal device 1 (S64). The packet may be transmitted while generating the voice of the response content.
Subsequently, the conversation contents are 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 voice recognition DB 102) included in the conversation contents and features at the time of pronunciation are recorded in the learning DB 107.

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

  According to such a voice response system 100, a plurality of responses can be output in different voices. Therefore, even when a solution for one character information cannot be specified as one, different solutions are used in different voices. Output can be easily understood by the user. Therefore, the usability can be improved for the user.

  Further, in the voice response system 100, the terminal device 1 inputs a voice of the user via the microphone 37, and the server 90 (the arithmetic unit 101) converts the input voice into character information, and A plurality of different responses are generated and transmitted to the terminal device 1. Then, the terminal device 1 acquires a response from the server 90.

  According to such a voice response system 100, since voice can be input in the terminal device 1, it is possible to adopt a configuration in which character information is input by voice. In addition, since the server 90 can generate a response, the processing load on the voice response system 100 can be reduced.

  Further, in the voice response system 100, the server 90 converts the voice of the user's utterance into character information, and accumulates the habit (pronunciation in pronunciation) at the time of utterance as learning information. Record it).

According to such a voice response system 100, since character information can be generated based on learning information, the generation accuracy of character information can be improved.
Further, in the voice response system 100, the server 90 reads the emotion from the voice of the voice input by the user, and selects one of emotions including at least one of normal, anger, joy, confusion, sadness, and exaltation. , Which emotion is applicable.

According to such a voice response system 100, a response can be output according to the emotion of the user.
[Modification of First Embodiment]
In the present embodiment, voice recognition is used as a configuration for inputting character information. However, the present invention is not limited to voice recognition, and input may be performed using input means (operation unit 70) such as a keyboard or a touch panel. Further, the operation of “converting the input voice into character information” is performed by the server 90, but may be performed by the terminal device 1.

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

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

  According to such a voice response system 100, responses in different positions, such as a positive response and a negative response, can be reproduced in different voices, so that voice is reproduced as if another person is speaking. Can be. Therefore, it is possible to make it difficult for the user who listens to the voice to feel uncomfortable.

  Note that the tone may be changed according to the type of response or the wording of the response. For example, when responding in a gentle tone, the voice may be reproduced with a calm female voice, and in responding with an intense tone, a brave male voice may be used. That is, the response content and the personality may be associated with each other, and the tone may be set according to the personality.

  Further, in the voice response system 100, a response (for example, a positive response or a negative response) output from the terminal device 1 of itself or another terminal device 1 is input as character information, and a response is made to the response. May be generated. In other words, from the perspective of the employer, it is possible to hear discussions from both opinions in favor of and in favor of the opposite. Then, after hearing this discussion, the user can make a final decision.

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

  Further, in the voice response system 100, the arithmetic unit 101 learns (records and analyzes) the user's actions (conversation, the place where the user has moved, what is reflected on the camera), and makes up for the lack of words in the user's conversation. You may do so.

For example, if the user supplements the conversation "The curry is good" to the question "Is it okay to have a hamburger today?" But the reason why he said curry is good is conveyed.

Further, such a configuration can be implemented during a telephone call, or may be configured to participate in a conversation of the user without permission.
Further, in the voice response system 100, the server 90 may acquire a response candidate from a predetermined server or the Internet.

According to such a voice response system 100, response candidates can be obtained not only from the server 90 but also from any device connected via the Internet or a dedicated line.
[Second embodiment]
[Process of Second Embodiment]
Next, another type of voice response system will be described. This Embodiment (Second Embodiment) In the following embodiments, only portions different from the voice response system 100 of the first embodiment will be described in detail, and portions similar to those of the voice response system 100 of the first embodiment will be the same. And the description is omitted.

  In the voice response system of the second embodiment, voice is output even when the user does not input character information. Specifically, the terminal device 1 performs an automatic conversation terminal process 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 performing the automatic conversation has been turned ON (S82). It should be noted that whether or not to have an automatic conversation can be set by the user via the operation unit 70 or by inputting a voice.

  If the automatic conversation is OFF (S82: NO), the automatic conversation terminal process ends. If the automatic conversation is ON (S82: YES), the automatic transmission mode is transmitted to the server 90 together with an ID for identifying itself (S84).

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

  Further, the server 90 executes an automatic conversation server process 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 thereafter is repeatedly executed.

  In the automatic conversation server process, first, it is determined whether or not the fact that the automatic conversation mode has been set has been received from the terminal device 1 (S92). If the fact 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 has been received (S92: YES), the terminal device 1 as a communication partner is specified based on the ID included in the received packet (S94), and the communication partner is identified. The automatic conversation is set (S96). Subsequently, it is determined whether or not the reproduction condition is satisfied for each of the terminal devices 1 set to have the automatic conversation (S98).

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

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

  Here, the latest and the message in accordance with the playback conditions are, for example, "Good morning." Or "Hello." May be a fixed sentence such as, obtained from the news DB109 the latest news is automatically updated May be related to news. When a message related to the latest news is used as a message, for example, if information on the stock price of a certain company can be obtained, the message “The stock price of company XX today has risen by XX yen. Did you know? And so on.

  When this process ends, the processes in S42 to S54 described above are performed. Then, when the process of S54 is completed, it is determined whether a predetermined answer has been obtained from the terminal device 1 as the communication partner (S112). Here, the predetermined answer may be, for example, some kind of voice or a specific answer. The specific answer is, for example, for the question "Do you know?", The answer is "Know" or "Do not know", and for the question "How is the weather today?" On the other hand, those containing words indicating the weather, such as "rainy" and "sunny", are applicable.

  If there is a predetermined answer (S112: YES), the automatic conversation server process ends. If there is no predetermined answer (S112: NO), the message transmitted in S100 is retransmitted (S114). When the message is retransmitted in this way, the tone is changed, and a voice with a strong tone and a severe tone is generated.

  Subsequently, by referring to the report destination DB 117 in which the terminal device 1 and the report destination are associated in advance, it transmits that there is no answer to the predetermined report destination (S116). When such processing ends, the automatic conversation server processing ends.

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

  According to such a voice response system 100, it is possible to output voice even when character information is not input (that is, when the user does not speak). For example, by forcibly causing the user to speak, it can be used for measures to prevent drowsiness while driving a car. In addition, it is possible to confirm the safety by determining whether or not a person living alone responds.

Further, in the voice response system 100, the server 90 acquires news information and causes a message relating to the news to be output in a question format for asking the user for an answer.
According to such a voice response system 100, since conversation about news can be performed, it is possible to suppress that the same conversation is always performed.

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

According to such a voice response system 100, a response in which a predetermined message and acquired information are combined can be output.
Further, in the voice response system 100, when a response or a response to the message is not obtained, the server 90 informs the preset contact information of the user and information indicating that the response was not obtained. Send.

  According to such a voice response system 100, when an answer cannot be obtained, it is possible to notify a contact. Therefore, for example, an abnormality of an elderly person living alone can be reported early.

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

  According to such a voice response system 100, by making it difficult to reproduce a message with a high frequency of reproduction, a randomness at the time of message reproduction is exhibited, or a message with a high frequency of reproduction is intentionally reproduced repeatedly to alert or store information. Or encourage the establishment of the image.

[Third embodiment]
[Processing of Third Embodiment]
Next, in the voice response system according to the third embodiment, the terminal device 1 is configured to notify the user that it is difficult to directly tell someone. For example, if you talk to the device today to say this before the date, at an appropriate timing (for example, at a preset time or when a certain period of time has elapsed since the conversation was interrupted) The voice response system 100 speaks (reproduces voice) instead.

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

  In the message terminal process, as shown in FIG. 8, first, it is determined whether 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 processes of S2 to S8 are performed, and if an affirmative determination is made in S6, the message mode flag in the memory of the terminal device 1 is turned on. Is set (S134). Then, the processing of S10 to S16 is performed.

  When an affirmative determination is made in S16, it is determined whether a packet from the server 90 has been received (S136). If the packet has not been received (S136: NO), the process of S136 is repeated. If a packet has been received (S136: YES), the processes in S24 to S30 are performed, and the message terminal process 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 thereafter repeatedly executed. Specifically, first, it is determined whether a packet has been received from any of the terminal devices 1 (S142). If a packet has not been received (S142: NO), the process proceeds to S156 described later.

  If a packet has been received (S142: YES), the communication partner terminal device 1 is specified (S44), and it is determined whether the packet includes 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 communication partner terminal device 1 to the ON state (S146). For example, if the message mode flag corresponds to the message mode, the processes of S46 to S152 described later are performed. If the message mode flag corresponds to the guidance mode flag described later, 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 in the ON state (S148: YES), the processes of S46 to S54 are performed, and subsequently, message playback conditions are extracted (S150).

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

  Subsequently, the message and the voice (voice color) are associated with each other and recorded in the memory (S152), and the process proceeds to S156. If the message flag is in the OFF state (S148: NO), processing relating to another mode 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 process ends immediately. If it is the playback timing (S156: YES), the processes of S62 to S64 are performed, and the message server process ends.

[Effects of Third Embodiment]
According to the voice response system of the third embodiment, the voice input by the user can be reproduced when the message reproduction condition is satisfied after a certain period of time, instead of immediately reproducing the voice.

  For example, as shown in the third row of FIG. 5, when "Please tell OO to say XX" is input, the text to be conveyed is made after OO's voice is recognized (after hearing). Will be played.

[Modification of Third Embodiment]
In the third embodiment, the content spoken by the user is configured to be reproduced. However, a word that triggers the difficulty of saying, for example, "Did you say something to her?" Such a structure may be used to speak such words. Specifically, the terminal device 1 performs the guidance terminal process illustrated in FIG. 10, and the server 90 performs the guidance server process illustrated in FIG. 11.

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

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

  If the guidance mode has been set (S162: YES), the processing of S2 to S8 is performed, and if an affirmative determination is made in S6, the guidance mode flag in the memory of the terminal device 1 is turned on. Is set to (S164). Then, the processing of S10 to S16 is performed.

  If an affirmative determination is made in S16, it is determined whether a packet from the server 90 has been received (S166). If the packet has not been received (S166: NO), the process of S166 is repeated. If a packet has been received (S166: YES), the processes in S24 to S30 are performed, and the guidance terminal process 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 thereafter is repeatedly executed. Specifically, the processing of S142 to S146 described above is executed. Then, it is determined whether or not the guidance flag is ON (S172).

If the guidance flag is ON (S172: YES), the processing of S46 to S54 is performed, and subsequently, the guidance reproduction condition is extracted (S174).
Here, similarly to the message playback condition, the user can set the guidance playback condition via the operation unit 70 of the terminal device 1 in advance, for example, the time and the position. The guidance reproduction condition is transmitted to the server 90 at the time of transmitting the message terminal processing packet.

  Subsequently, the guidance content is generated, and the guidance content is associated with the voice (voice color) and recorded in the memory (S176). Here, as the guidance contents, for example, a search is made for words representing desires such as “want” and “desired” included in the input character information, and keywords before these words are extracted to derive these keywords. The words registered as words are output as guidance contents. The keywords and the words indicating the guidance contents are recorded in the response candidate DB 105 in association with each other in advance.

  Subsequently, the above-described processing of S156 and subsequent steps are performed, and the server processing ends. If the guidance flag is in the OFF state (S172: NO), a process related to another mode is performed (S154), and the processes from S156 are performed, and the server process ends.

According to the configuration of the modified example of the third embodiment, it is possible to guide the user to speak the desired word, instead of directly outputting the desired word.
[Fourth embodiment]
[Process of Fourth Embodiment]
Next, an example in which the terminal device 1 is used for reception work will be described. In the present embodiment, the terminal device 1 is installed at a reception of a company or the like. In addition, it can also be adopted for telephone reception such as a company's representative telephone and telephone banking. Here, this embodiment is realized by replacing the processing of S56 in the first embodiment with the reception processing shown in FIG.

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

  If the character information does not include the company name or the personal name (S192: YES), a response for asking for the company name and the personal name is generated (S194), and the reception process ends. In this process, for example, a response such as "Please tell us your name and business requirements" is generated.

If the character information includes the company name or the personal name (S192: NO), the company name or the personal name is extracted from the sales DB 118 and the client DB 119 (S196). Here, in the sales DB 118, the names of companies and persons in charge who have come to the sales in the past, or the names of the complainers who speak only complaints are recorded. In the client DB 119, a company name, a person in charge of the company, a person in charge of the user of the terminal device 1 (own company side), a schedule such as scheduled visit time, and contact information are recorded in association with each person in charge. ing.

  Subsequently, it is determined whether or not the company name or the individual name has been extracted from the sales DB 118, that is, whether or not the company name or the individual name included in the character information has been included in the sales DB 118 (S198). If the company name or the individual name has been extracted from the sales DB 118 (S198: YES), a sales refusal response (response refusing the agency) to reject the sales is generated (S200), and the reception process ends.

  If the company name or the individual name has not been extracted from the sales DB 118 (S198: NO), the person who came to the reception visits the client DB 119 at a close time (for example, within one hour before and after the current time) in the schedule in the client DB 119. It is determined whether or not the person is the person who does (S202). If the visitor comes at a close 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 and the person who came to the reception can talk. , And connects to this person in charge (S204). In this process, it is only necessary to connect to the extension phone, mobile phone, or the like of the person in charge.

  Subsequently, an acceptance response for the client is generated (S206). Here, as a reception response for the client, for example, a response such as “Thank you very much, please wait for a while because we are connected to the person in charge” is generated. When such processing ends, the reception processing ends.

  If the visitor is not a visitor at a close time (S202: NO), the user is connected to a preset reception contact so that the person in charge and the visitor can have a conversation. A connection is made to the receptionist (S208). Then, a normal reception response is generated (S210).

  Here, as the normal reception response, for example, a response such as “Please wait for a while since we are connected to the reception” is generated. When such processing ends, the reception processing ends.

[Effects of Fourth Embodiment]
The voice response system 100 is configured to be used at a work place or a company reception. In this configuration, the name of the person coming to the sales and the company name are recorded in the sales DB 118 of the server 90 in advance, and if the person who comes to the reception gives the name or the company name, the voice of the complaint to refuse is output. Generate a response to play.

Further, in the voice response system 100, the server 90 specifies the communication partner based on the input character information, and connects the communication partner preset for each communication partner with the communication partner.
According to such a voice response system 100, reception work and telephone correspondence can be assisted. Further, according to such a voice response system 100, it is possible to eliminate a person who may interfere with the work of the user without coping 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 the connection destination to which the keyword corresponds. In addition, for example, a keyword such as the name of the other party and its connection destination are associated in advance.

According to such a voice response system 100, it is possible to assist operations such as telephone transfer and call to reception.
[Modification of Fourth Embodiment]
In the above embodiment, the connection destination is set according to the destination. However, by applying this technology, for example, in a telephone reception such as telephone banking or telephone shopping, requirements (keywords included in character information) are set. Recognition may be performed and the connection destination may be changed according to requirements.

Further, in the voice response system 100, the server 90 may recognize a requirement that the other party speaks based on the keyword, and inform the user of the outline spoken by the other party.
According to such a voice response system 100, it is possible to assist the agency work with the customer.

[Fifth Embodiment]
[Processing of Fifth Embodiment]
Next, the terminal device 1 may receive the request from the other terminal device 1 and provide the information required by the other terminal device 1.

  In the case of such a configuration, in the process of S56, the server 90 requests necessary information from the other terminal device 1, obtains necessary information from the other terminal device 1, and generates a response. Then, in the terminal device 1 that provides necessary information, an information providing terminal process illustrated 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 an information providing destination (S222). The information providing destination indicates another terminal device 1 requesting information, and an ID for specifying the other terminal device 1 is included in the request from the server 90.

  Subsequently, it is determined whether or not the user is a partner who is permitted to provide information (S224). Here, in the terminal information DB 113, the ID of a partner who is permitted to provide information, such as a family member or a friend, is recorded in advance. In this process, the determination is made by referring to the terminal information DB 113.

  If it is a partner to whom the provision of information is permitted (S224: YES), the requested information is acquired from its own memory 39, various sensors, and the like (S226), and this data is transmitted to the server 90 (S228). If it is not a partner to whom the provision of the information is not permitted (S224: NO), a message to the effect that the provision of the information is rejected 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?", The server 90 requests the position information from Mr. XX's terminal device 1. Then, the terminal device 1 returns the position information.

  Then, the server 90 recognizes the action of Mr. XX based on the position information. For example, if you are moving on a railroad at a speed faster than the speed at which a person runs, it is determined that you are moving on a train, and "Mr. XX is on the train. It looks like you are returning home." And a response will be generated.

[Effects of Fifth Embodiment]
In the voice response system 100, the server 90 acquires information recorded in another terminal device 1 from another terminal device 1 different from the requesting terminal device 1, and provides the information to the other terminal device 1. That is, in the voice response system 100, the server 90 obtains information for generating a response to the character information from another 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.
Further, in the voice response system 100, when the terminal device 1 is requested from another terminal device 1 for information for generating a response to the character information, the terminal device 1 returns information corresponding to the request.

  In this configuration, the terminal device 1 is provided with sensors for detecting position information, temperature, humidity, illuminance, noise level, and the like, and a database such as dictionary information, and extracts necessary information as required.

  According to such a voice response system 100, information unique to another terminal device 1, such as the position of another terminal device 1, can be acquired. In addition, information unique to itself can be transmitted to another terminal device 1.

[Sixth embodiment]
[Process of Sixth Embodiment]
Next, in the voice response system of the sixth embodiment, a personality DB 106 in which personality information in which the personality of a user or a person who is related to the user is associated in accordance with a preset division is prepared. ing. In the personality DB 106, for example, as shown in FIG. 14, the names of users and related persons are recorded in association with the personality classifications of these persons.

  In the personality DB 106 shown in FIG. 14, a personality test is performed on a user or a related person, and the test result is also recorded. Here, when generating the personality information, a well-known personality analysis technique (Rorschach test, Sondy test, etc.) may be used. When generating the personality information, an aptitude test technique used by a company or the like for an employment test may be used.

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

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

Subsequently, it is determined whether or not a response has been made by voice from the target person (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 the ending of the word and the 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), the personality analysis is performed by answering the four-choice question (S254), and the personality analysis is performed using the conversation parameters (S256). Here, in the personality analysis using conversation parameters, those who are confident in themselves tend to have strong endings, those who are not confident tend to have weak endings, impatient people have high conversation speed, and unfriendly people have low conversation speed It is possible to capture trends and the like.

  Subsequently, these personality analysis results are comprehensively analyzed, such as by weighted averaging (S258), and are assigned to personality categories (S260). Specifically, the personality of the subject obtained by the test is scored and assigned to the personality classification for each score.

  Subsequently, the target person and the personality category are associated with each other (S262) and recorded in the personality DB 106 (S264). That is, the relationship between the subject and the personality classification is transmitted to the server 90. At this time, the test result is also transmitted to the server 90, and the server 90 constructs the character 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, a response candidate DB 105 that prepares a correspondence between a personality classification and a different response is prepared. Then, in the process of S56, the server 90 acquires response candidates representing a plurality of 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 in S60 and S64. Output the selected response.

[Effects of Sixth Embodiment]
In the voice response system 100, the terminal device 1 generates personality information of a user or a related person based on answers to a plurality of questions set in advance, and acquires the generated personality information.

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

According to such a voice response system 100, the user can generate personality information in the process of using the voice response system 100.
Further, according to such a voice response system 100, different responses can be made according to the character of the user or a person (related person) related to the user. Therefore, usability can be improved for the user.

[Modification of Sixth Embodiment]
In the sixth embodiment, the response may be output after being narrowed down to one according to the personality, or a plurality of responses may be output in association with voices of different timbres.

  Further, the processing of S248 and S254 to S264 in the personality information generation processing may be performed in the server 90. In this case, as in the first embodiment and the like, the server 90 may specify the terminal device 1 and exchange voices and problems between the terminal device 1 and the server 90.

  Further, in the voice response system 100, the server 90 may detect any one of a user's action and operation, and generate learning information or personality information based on the detected action or operation.

  According to such a voice response system 100, for example, when it is detected that the user jumps on the train for several consecutive days, the user is prompted to leave the house several minutes earlier from the next day, or the user is angry from the conversation. When it is detected that there is a tendency to be easy, voice or music that suppresses the mood can be output.

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

  In particular, for food preferences, sweets (sweet), spicy (spicy), and averages between them, and for color preferences, warm colors (warm), cool colors (cold), intermediates, and hobbies Are categorized as indoor hobbies (inside), outdoor hobbies (outside), and both indoor and outdoor hobbies (inside and outside).

When constructing such a preference DB 108, for example, a preference information generation process shown in FIG. 17 is executed. The preference information generation processing is performed, for example, between S48 and S54.
More specifically, as shown in FIG. 17, a keyword related to taste is extracted from the character information (S282), and an object related to taste is extracted from the objects identified by the image processing (S284). In the preference DB 108, the preference type is associated with the type of the preference and the category (such as sweet, average, spicy, etc. for food preference) in the preference DB 108, and is extracted in these processes. When a keyword or an object is included in the preference DB 108, it is extracted as one related to the preference.

  Subsequently, the counter is incremented for each group of keywords relating to preferences (S288). For example, when the type of preference is “food preference” and a type of “spicy” is extracted, such as kimchi, the counter corresponding to “food preference” and “spicy” is incremented. .

  Then, the preference information (preference DB 108) is updated based on the counter value (S290). That is, for each “type of preference”, the “type” having the largest counter value matches the preference and is recorded in the preference DB 108 as a characteristic of the preference of the user or the related person. When such processing ends, the preference information generation processing ends.

  When the preference DB 108 generated in this way is used, a response associated with a different response for each preference is prepared in the response candidate DB 105, and the server 90 performs a plurality of different responses to the character information in the process of S56. A response candidate representing the response is obtained, a response to be output from the response candidate is selected according to the preference information, and the selected response is output in the processes of S60 and S64.

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

  According to such a voice response system 100, a response can be made according to the preference of a user or a related person. For example, when the user asks the terminal device 1 "What do you want?" When buying a present of a related person, a response corresponding to the preference information can be obtained.

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

For example, in the example shown in FIG. 18, personality categories and color preferences are associated with each other, and products that can be presumed to be enjoyed by women as gifts are arranged in a matrix.
In the process of S56, a response can be generated in consideration of both the personality and the preference.

[Eighth Embodiment]
[Process of Eighth Embodiment]
In the above embodiment, the voice is converted to character information. However, the operation by the user may be converted to character information.

  Specifically, the terminal device 1 captures a user's operation as a captured image and transmits the captured image to the server 90, and the server 90 may execute an operation character input process illustrated in FIG. 19, for example. The motion character input process is a process that is started when the body part of the user is displayed in the captured image in the process of S48.

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

  In these processes, for example, when the upper body of the user is shown together with the face in the captured image, it is determined that characters are to be input in sign language, and the user's face is not displayed in the captured image. If the hand is reflected, it is determined that a character is to be input by handwriting.

  If a character is to be input by handwriting (S304: YES), the behavior of the fingertip or the 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, the behavior when the character is handwritten and the character are associated with each other, and the movement of the hand and the character represented by the sign language are associated with each other. In the process of S312, 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 content of the sign language is recognized with reference to the handwritten character / sign language DB 112, and the processing of S312 is performed. If the user does not intend to input characters by handwriting or sign language (S308: NO), input processing by another method is performed (S314).

  Subsequently, the character input by the operation is associated with the character input by voice, and whether or not there is a similar voice (whether or not the matching degree between the reference waveform based on the character and the pronunciation waveform is equal to or higher than the reference value Is determined (S316). If there is such a 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 the operation character input processing is performed. To end.

If there is no such voice input (S316: NO), the operation character input process ends.
[Effects of Eighth Embodiment]
In the voice response system 100, since the operation by the user is converted into character information, the user can input the character information without speaking.

[Modification of Eighth Embodiment]
The operation according to the present embodiment may be not only handwritten characters or gestures (for example, sign language), but also operations caused by muscle movements.

[Ninth embodiment]
[Process of Ninth Embodiment]
When the user uses another terminal device 1 different from the terminal device 1 that the user normally uses, the contents of the learning DB 107 may be made available to the other terminal device 1. In this case, the ID and password of the terminal device 1 that is usually used are transmitted to the server 90 together with the use request from the other terminal device 1.

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 an ID and a password have been input (S332). If the ID and the password have not been input (S332: NO), the process of S332 is repeated.

  If the ID and the password have been input (S332: YES), it is determined whether the authentication based on the ID and the password has been completed (S334). If the authentication has been completed (S334: YES), the fact that the authentication has been completed 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 the password. It is set to be used (S338).

If the authentication is not completed (S334: NO), an error message is transmitted to the other terminal device 1 (S340), and the other terminal use process ends.
[Effects of the Ninth Embodiment]
In the voice response system 100, the server 90 transfers the learning information of one terminal device 1 to another terminal device 1.

  According to such a voice response system 100, even when a user who uses a certain terminal device 1 uses another terminal device 1, the learning information recorded in the certain terminal device 1 (the learning information recorded in the server 90). Learning information) can be used. Therefore, even when another terminal device 1 is used, the accuracy of generating character information can be improved. This is particularly effective when the user has a plurality of terminal devices 1.

Further, 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, if the distance of a walk including a meal content of the user is detected, a question at a hospital or the like can be answered on behalf of the user. Moreover, you may make it learn, such as a health condition and self-introduction.

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

[Tenth embodiment]
[Process of Tenth Embodiment]
In the voice response system according to the tenth embodiment, the server 90 stores the conversation content and asks a question for obtaining the same content as the content heard. More specifically, in S100 of the automatic conversation server process shown in FIG. 7, the storage confirmation process shown in FIG. 21 is executed.

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

In the memory confirmation processing, for example, a question such as "What was the dinner menu yesterday?" Or "Where did you go three days ago?"
[Effects of the Tenth Embodiment]
According to such a voice response system 100, it is possible to confirm the memory ability of the user and to fix the memory. It is also considered to be effective in suppressing the progress of dementia in the elderly.

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

  More specifically, a sound generation determination process 1 shown in FIG. 22, a sound generation determination process 2 shown in FIG. 23, and a sound generation determination process 3 shown in FIG. 24 are sequentially executed. However, the server 90 executes one of the sound determination processes 1 to 3 each time the voice response server process (FIG. 2) is performed. Each of the sound generation determination processes 1 to 3 is executed as the above-described process of S56.

  First, in the pronunciation determination processing 1, as shown in FIG. 22, a response to instruct to input a predetermined sentence by voice is generated (S362). In this process, for example, a sentence serving as an example of a foreign language is generated, and the user is prompted to imitate the sentence following the example. When this processing ends, the sound generation determination processing 1 ends.

  Next, when a voice is input along with the pronunciation determination process 1, a pronunciation determination process 2 is performed. In the pronunciation determination processing 2, as shown in FIG. 23, the accuracy of pronunciation and accent is converted into a score (point) (S372). In this process, the voice is captured as a waveform, and the degree of coincidence between the waveform and the sentence used as a model at this time is scored.

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

  If the score is less than the threshold (S382: YES), a response is generated again to instruct to input a similar sentence (S384). In this process, for example, a response is generated again to prompt the user to speak imitatively following the example.

  If the score is equal to or greater than the threshold value (S382: NO), a response to the effect that the pronunciation is good and a prompt to input the next sentence are generated (S386). For example, a response such as "Good pronunciation. Let's go next."

When such processing ends, the sound generation determination processing 3 ends.
[Effects of Eleventh Embodiment]
In the voice response system 100, the server 90 detects the accuracy of pronunciation and accent of the voice input by the user, and outputs the detected accuracy.

According to such a voice response system 100, the accuracy of pronunciation and accent can be confirmed. This is effective, for example, when practicing a foreign language.
Further, in the voice response system 100, the server 90 causes the same question to be output 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.
[Modification of Eleventh Embodiment]
In the voice response system 100, the server 90 may output a voice including a word closest to the pronunciation performed by the user for confirmation when the accuracy is equal to or less than a certain value.

According to such a voice response system 100, the user can confirm the accuracy of pronunciation and accent.
[Twelfth embodiment]
[Processing in Twelfth Embodiment]
Next, a voice response system according to a twelfth embodiment will be described. In the voice response system according to the twelfth embodiment, the emotion of the user is detected from the voice input by the user, and a response that heals the user is generated according to the emotion.

  In detail, the emotion determination process shown in FIG. 25 and the emotion response generation process shown in FIG. 26 are executed. The emotion determination process is performed as the details of the above-described process of S50. As shown in FIG. 25, first, emotions are scored based on voice tone, strength of sentence ending, length of one sentence, conversation speed, unexpected words, and the like. Then, the emotions are classified according to the score and recorded in the memory (S394).

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

  If the emotion category is anger (S412: anger), a sentence for calming the other party's emotion, such as "Did you bother you?", Is generated as a response (S416). Further, if the emotion classification is joy (S412: joy), a greeting with a nuance brighter than a normal greeting is generated as a response, such as "I'm happy today" (S418).

  If the emotion classification is puzzled (S412: puzzled), a greeting, such as "How did you do?" When such processing ends, the emotion response generation processing ends.

[Effects of the Twelfth Embodiment]
In the voice response system 100, the server 90 detects a user's frustration or sway by detecting a voice uttered unexpectedly, and generates a message for suppressing the frustration or sway.

  According to such a voice response system 100, when the user is frustrated or upset, these can be suppressed. Therefore, it is possible to suppress the occurrence of trouble between the user and the surroundings.

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

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

  Then, based on the sound (character information) and the image processing, a target object is specified from among the objects in the captured image, and this position is specified (S434). In this processing, the position of the object is specified in the map information (may be acquired from the outside or may be held by the server 90) based on the shape, relative position, and the like of the object. For example, when the tower is reflected 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 obtained (S438). This processing can be realized using the same processing as the processing in a well-known cloud type navigation device.

Then, a response for guiding the route is generated (S440). In this process, a response similar to the guidance provided by the navigation device may be generated.
When such processing ends, the guidance processing ends. When the guidance process is performed while the user is moving, the message may be reproduced using the automatic conversation server process under the reproduction condition that the user reaches a 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 corresponding to a captured image of the surroundings of the voice response system 100, and outputs the response as voice.

  According to such a voice response system 100, a response can be output by voice according to a captured image. Therefore, usability can be improved as compared with a configuration in which a response is generated 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, specifies the position of the searched object, and provides guidance to the position of the object.

According to such a voice response system 100, a user can be guided to an object in a captured image.
Further, in the voice response system 100, when providing guidance to the destination, the server 90 obtains route information such as weather, temperature, humidity, traffic information, and road surface conditions to the destination, and outputs the route information by voice. Output.

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

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

According to such a voice response system 100, since the utterance content can be estimated from the shape of the mouth, an unclear portion of the voice can be satisfactorily estimated.
[Fourteenth embodiment]
[Processing of Fourteenth Embodiment]
Next, a voice response system according to a fourteenth embodiment will be described. In the voice response system according to the fourteenth embodiment, a predetermined operation is requested from the user, and it is determined whether the user has performed the operation 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. It is performed in order.

  First, when the processing of S54 is completed, the movement request processing 1 is started. In the movement request processing 1, as shown in FIG. 28, a response (message) indicating that the gaze or the head is moved to a predetermined position is output. (S452). When this process ends, the transfer request process 1 ends.

  Subsequently, when the processing of S54 is completed next, the movement request processing 2 is started. In the movement request processing 2, as shown in FIG. 29, it is determined whether or not the line of sight or the position of the head has moved as instructed ( S462). In this process, image processing of an image captured by a camera is performed, and the operation of the user is detected using detection results obtained by various sensors of the terminal device 1. In the case where the line of sight is detected by image processing, a well-known line of sight recognition technology may be employed.

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

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

According to such a voice response system 100, it is possible to make a user see a specific position. Therefore, it is possible to surely confirm the safety at the time of driving the vehicle.
In the voice response system 100, the server 90 observes the position of the body part and the facial expression, and outputs a voice requesting to change the position of the body part and the facial expression when there is little change in response to the call. I do.

  According to such a voice response system 100, it is possible to move the position of the body part of the user to a specific position or to guide the user to give a specific expression. INDUSTRIAL APPLICATION This invention can be utilized at the time of driving of a vehicle, a physical examination, etc.

[Fifteenth Embodiment]
[Processing in Fifteenth Embodiment]
Next, a voice response system according to a fifteenth embodiment will be described. In the voice response system according to the fifteenth embodiment, when a user inputs a broadcast program or music as voice, a process for complementing the broadcast program or music when it is interrupted is performed.

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

  If it is interrupted (S482: YES), a broadcast program or music synchronized in the processing of S492 described later is set as the response content (S484), and the broadcast music complement processing ends. If the broadcast is not interrupted (S482: NO), the broadcast program is acquired if the broadcast program is being viewed (S486), and if the music is being played, the corresponding music is acquired (S488).

Here, in the karaoke DB 116, music and lyrics are recorded in association with each other. When music is acquired in this process, music with lyrics is acquired.
Next, a broadcast program or a song to be viewed by the user is specified (S490). Then, the broadcast program or the song is acquired, and the broadcast program or the song is prepared so as to be reproduced in synchronization with the broadcast program or the song to be viewed by the user (S492), and the broadcast song complementing process ends.

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

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

According to such a voice response system 100, it is possible to supplement a portion where a user using a so-called karaoke apparatus cannot sing (a portion where lyrics are interrupted).
[Sixteenth embodiment]
[Processing of Sixteenth Embodiment]
Next, a voice response system according to a sixteenth embodiment will be described. In the voice response system according to the sixteenth embodiment, in a case where a character is included in a captured image, when the user receives a question about how to read the character in the terminal device 1, the information of the character is obtained from the outside, and The voice of the character included in the information is output.

  In this configuration, a character explanation process shown in FIG. 31 is performed as 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 has been received, for example, “how to read” (S502). If a reading question has been received (S502: YES), the reading of the image-recognized character is searched from another server or the like connected via the Internet 85 (S504), and the obtained reading is set as a response. (S506), and ends the character explanation processing.

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

[Effects of Sixteenth Embodiment]
According to such a voice response system 100, for a character whose image has been recognized, the reading is retrieved from another server or the like, and the obtained reading is set as a response. Can teach.

[Seventeenth embodiment]
[Processing of Seventeenth Embodiment]
Next, a voice response system according to a seventeenth embodiment will be described. In the voice response system according to the seventeenth embodiment, the server 90 detects an abnormal behavior or a fine state of the user of the terminal device 1 based on the sensor value detected by the terminal device 1, and reports when there is an abnormality. Perform processing.

  Specifically, the terminal device 1 performs the action response terminal processing shown in FIG. 32, and the server 90 performs the action response server processing. 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 outputs from the various sensors and the captured images are transmitted as packets to the server 90 (S526), and the action response terminal process ends.

  Next, in the action response server process, as shown in FIG. 33, first, the processes of S42 to S44 described above are performed. Subsequently, an action such as wandering is specified based on the position information of the terminal device 1 (the detection result by the GPS receiver 27) (S532), and the environment of the user is determined based on the detection result by the temperature sensors 15, 19 and the like. It is detected (S534). Then, an abnormality is detected (S536).

  In this process, an abnormality is detected based on the change in the position information and the environment. For example, when the user does not move in a place where the temperature is high or low, or when the user exists in a place where the user does not usually go, it is detected that there is an abnormality (S536). Alternatively, the position information and the environment are scored, and when the score is lower than the reference value (out of the reference range), it is determined that there is an abnormality.

  Subsequently, it is determined whether an abnormality has been detected (S538). If no abnormality is detected (S538: NO), the action response server process ends. If an abnormality has been detected (S538: YES), a message indicating that there is an abnormality is generated (S540), and notification is made to a predetermined contact (S542). Then, the processes of S62 to S68 (excluding S66) are performed, and the action response server process ends.

[Effects of Seventeenth 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 the surrounding environment.

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

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

In the voice response system 100, the server 90 notifies a predetermined contact when the health condition is lower than the reference value.
According to such a voice response system 100, it is possible to make a report when the user's health condition is equal to or less than the reference value. Therefore, the abnormality can be notified to another person earlier.

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

  For example, the voice response system 100 may mediate exchanges between two parties and between multiple parties. Specifically, when it is necessary to give way at an intersection or the like, the terminal devices 1 may negotiate which vehicle will enter the intersection first. In this case, each terminal device 1 transmits to the server 90 the information of the moving direction when approaching the intersection and the approach speed to the intersection, and the server 90 sends the information to each terminal device 1 according to the moving direction and the approach speed. A priority may be set, and a sound such as “stop” or “enterable” may be generated and output according to the priority.

  In addition, when the terminal device 1 receives an incoming call (incoming call) of a communication that needs to respond in real time, such as voice communication, the incoming call may be received only at the convenience of the user. Specifically, when an image of the user's face can be captured by the camera 41, the incoming call may be accepted as a convenient time for the user.

  Further, in voice communication or the like, there is a person who is unpleasant if he does not answer even if he calls the other party. In order to suppress such feelings, the situation of the partner may be transmitted to the user waiting for a response from the partner. For example, the user's schedule is managed in the terminal device 1, and when the user does not respond to the incoming call, the user searches for what the user is doing or the free time of the user's schedule, It is conceivable to tell when the user can respond.

  If the user does not respond to the incoming call, the location of the user may be notified to the caller. For example, if the user is connected to the Internet or the like via a smartphone or a personal computer, it is possible to know which terminal is being operated. It is conceivable that the location of the user is specified from this information and transmitted to the caller.

  Further, whether or not the user can respond to the incoming call may be determined using position information using GPS or the like. Based on the location information, it can be determined whether or not the user is in a car or at home. For example, if the user is moving or on a bed, the publicity is high or sleeping. What is necessary is just to determine that it is medium and cannot respond to an incoming call. If the call cannot be answered in this way, it is conceivable to inform the caller of what the user is doing as described above.

  In order to acquire the position information, a configuration using a security camera is also conceivable. In recent years, various location security cameras have been attached, so that these security cameras can be used to recognize the position of the user using a configuration for identifying the user such as face authentication. . Further, a situation determination such as what the user is doing (whether or not the user can answer the phone) may be performed using the security camera. Whether or not a call can be answered can also be determined based on conditions such as whether another fixed telephone is used (the call cannot be answered while the fixed telephone is being used).

  Further, when the user of the terminal device 1 wants to have a conversation with somebody, the terminal device which is estimated to be compatible with the user among a large number of unspecified people is used by using the character learning result of the user. Is also good. In such a case, topics that are likely to be exciting (topics that both users are interested in (extracted using learning results)) may be addressed to the users.

Further, when the voice response device has not been used for a long time (when the user is not speaking for a reference time or more), the voice response device may give the user some words.
At this time, words to be spoken may be selected using position information such as GPS.

[Relationship between each means described in the claims or means for solving the problem (the present invention) 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. Further, the processing of S22 and S56 in the above embodiment corresponds to an example of the response acquisition unit of the present invention.

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

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

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

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

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

Further, the processing of S254, S258, and S260 in the above embodiment corresponds to an example of a first character information generating unit and a second character information generating unit of the present invention.
Further, the processing of S48 and S56 in the above embodiment corresponds to an example of the response generation unit of the present invention. Further, the processing of S28, S60, and S64 in the above embodiment corresponds to an example of the audio output unit of the present invention.

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

  Further, the preference information generation processing in the above embodiment corresponds to an example of the preference information generation means of the present invention. Further, the processing of S56 in the above embodiment corresponds to an example of a response candidate acquiring unit of the present invention.

  Further, the operation character input processing in the above embodiment corresponds to an example of the character information generating means of the present invention. Other device information acquisition means The other terminal use processing in the above embodiment corresponds to an example of the transfer means of the present invention.

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

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

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

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

  Further, the processing of S462 in the above embodiment corresponds to an example of the visual line detection means of the present invention. Further, the processing of S464 in the above embodiment corresponds to an example of a gaze movement request transmitting unit of the present invention.

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

  Further, the processing of S484 in the above embodiment corresponds to an example of the broadcast program supplementing means and the lyrics adding means of the present invention. Further, the processing of S504 and S506 in the above embodiment corresponds to an example of the reading output means of the present invention. Further, the processing of S522 and S524 in the above embodiment corresponds to an example of the behavior environment detecting means of the present invention.

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

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

  DESCRIPTION OF SYMBOLS 1 ... Terminal device, 10 ... Behavior sensor unit, 11 ... Dimensional acceleration sensor, 13 ... Shaft 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 speed sensor, 33 Electrocardiographic sensor, 35 Heart sound sensor, 37 Microphone, 39 Memory, 41 Camera, 50 Communication unit, 53 Wireless 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 ... rescue request lever, 80 ... Communication base station, 85 Internet network, 90 server, 100 voice response system, 101 arithmetic unit, 102 voice recognition DB, 103 prediction conversion DB, 04: voice DB, 105: response candidate DB, 106: personality DB, 107: learning DB, 108: preference DB, 109: news DB, 110: weather DB, 111: reproduction condition DB, 112: handwritten character / sign language DB, 113: terminal information DB, 114: emotion judgment DB, 115: health judgment DB, 116: karaoke DB, 117: report destination DB, 118: sales DB, 119: client DB.

Claims (1)

A response acquisition unit configured to acquire a plurality of different responses to one input voice, the responses having different wording;
An audio output unit configured to sequentially output the plurality of different responses by audio,
A voice activation unit configured to turn on automatic conversation by voice;
An ID transmission unit configured to transmit an ID for identifying itself to a server configured to transmit a message to an ID transmission source;
When the automatic conversation is turned on, a transmitting / receiving unit configured to acquire a message according to a reproduction condition from the server,
A voice response device comprising:

Images