JP2002144982A - Operating method and system for on-vehicle apparatus and control device for such apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accomplish an environment capable of comfortably performing operations on-vehicle apparatuses 42, 43 by voice, allowing the operation by voice substantially in the same operating environment even when it is applied to different vehicle, and achieve such a comfortable operating environment at a low cost. SOLUTION: An on-vehicle unit 1 transmits the voice of an operator fed to a microphone 44 via a communication device 41 to an information center MC, which acknowledges the voice and converts it into operation signals for the on-vehicle apparatuses 42 and 43 and transmits these signals to the on-board unit 1, and the unit 1 performs control of the apparatuses 42 and 43 in conformity to the operation signals.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method of operating an on-vehicle device by operating the on-vehicle device by voice, an operation system of the on-vehicle device enabling operation of the on-vehicle device by voice, and an on-vehicle device control device.

[0002]

2. Description of the Related Art Conventionally, there has been known an apparatus capable of operating a vehicle-mounted device mounted on a vehicle by voice (for example, see Japanese Patent Application Laid-Open No. 11-142165). In this device, the in-vehicle device control device that controls the in-vehicle device includes:
It is configured to recognize the voice input by the operator and control the in-vehicle equipment according to the recognition result.

[0003]

However, such an on-vehicle equipment control device is provided with a general-purpose voice pattern, and is configured to be able to recognize voices input by various types of operators. I have.

[0004] However, the provision of the above-mentioned general-purpose voice pattern ensures a certain level of voice recognition accuracy, but the recognition accuracy is such that all operators can comfortably perform voice operations. Not in. In other words, although the voice recognition accuracy can be improved by providing a voice pattern with high recognition accuracy, there is a problem that the in-vehicle device control device becomes extremely expensive. It has to be relatively low.

[0005] When a general-purpose voice pattern is used as described above, the accuracy of voice recognition must be reduced. For example, the voice pattern is stored in advance in an on-vehicle equipment control device by an operator, and this operation is performed. If the voice recognition is optimized using the voice pattern of the user, the accuracy of the voice recognition can be improved while configuring the in-vehicle equipment control device at a relatively low cost.

However, in this case, a more accurate voice recognition can be performed for an operator who stores the voice pattern, but a voice recognition of the operator who does not store the voice pattern can be performed. Accuracy does not improve. For this reason, for example, when the user is in his / her vehicle, his / her own voice pattern can be stored in the in-vehicle device control device in advance so that the in-vehicle device can be comfortably operated by voice. When the user gets on a car of another person that is not stored in the device control device, it becomes difficult to operate the vehicle-mounted device by voice, which is extremely inconvenient.

The present invention has been made in view of such circumstances, and an object of the present invention is to realize an environment in which a vehicle-mounted device can be comfortably operated by voice, and
An object of the present invention is to enable operation by voice in a similar operation environment even if the in-vehicle device control device is different, and to realize such a comfortable operation environment at low cost.

[0008]

According to a first aspect of the present invention, there is provided a method of operating an on-vehicle device, and more specifically, the method comprises the steps of:

That is, a first method of transmitting information of the voice of the operator from the vehicle to an information center is intended for a method of operating the vehicle-mounted device which operates the vehicle-mounted device mounted on the vehicle by the voice of the operator. A second step of receiving the voice information transmitted from the vehicle and recognizing the voice at the information center, and converting the voice information into an operation signal of the on-vehicle device according to a recognition result; A third step of transmitting the converted operation signal to the vehicle, and a third step of receiving the operation signal transmitted from the information center in the vehicle and controlling the on-vehicle device according to the operation signal. It is a specific matter to provide four steps.

According to the first aspect of the present invention, in the first step, the voice of the operator is transmitted from the vehicle to the information center as it is.

In the second step, the information center recognizes the voice transmitted from the vehicle and converts the voice into an operation signal of the on-vehicle device according to the recognition result.

In a third step, the information center transmits the converted operation signal to the vehicle, and in a fourth step, the vehicle controls the on-vehicle equipment according to the operation signal.

As described above, the recognition of the voice input by the operator is performed not in the vehicle but in the information center. Providing a voice pattern with high recognition accuracy in this information center can be performed easily and at a lower cost than providing it in a vehicle (for example, in a vehicle-mounted device control device that controls vehicle-mounted devices). Compared with the case, the accuracy of voice recognition in the information center is improved.
As a result, an environment in which the operation of the in-vehicle device by voice can be performed comfortably is realized. In addition, even if the vehicle is different (for example, if the in-vehicle device control device is different from a vehicle of another person), since the voice recognition is performed at the information center, the same voice operation environment can be obtained for the operator. .

[0014] Further, since the voice recognition is performed at the information center, it is not necessary to provide the vehicle with a voice pattern, or it is not necessary to provide a high-precision voice pattern. As a result, the in-vehicle device control device provided in the vehicle is reduced in cost, and an environment in which the operator can comfortably operate the in-vehicle device by voice can be obtained at low cost.

Further, for example, if the voice pattern of the operator is stored in the information center, voice recognition optimized for the operator can be performed in the information center.
The accuracy of voice recognition is greatly improved. In this case, even if the vehicle is different, since the voice recognition is performed using the voice pattern of the operator stored in the information center, it is possible to operate the on-vehicle device by voice in a highly accurate voice recognition environment. .

As described above, according to the first aspect of the present invention, an environment in which the in-vehicle device can be comfortably operated by voice can be realized, and the voice can be operated in the same operation environment even if the vehicle is different. And such a comfortable operation environment is realized at low cost.

According to the first aspect of the present invention, when the communication state between the vehicle and the information center is worse than a predetermined standard, for example, the second state is established.
Recognition of voice in the information center in the step may be prohibited. Here, “prohibition of voice recognition at the information center” may mean, for example, prohibiting transmission of voice information from the vehicle to the information center.

That is, when the communication state is worse than a predetermined standard, for example, when the electric field intensity received by the communication means in the vehicle is lowered, the voice transmitted from the vehicle and received by the information center is used. The information may be inaccurate, and therefore, the operation signal converted from the audio information may be erroneous. Therefore, by prohibiting the voice recognition in the information center as described in claim 2, erroneous control of the in-vehicle device by an erroneous operation signal is avoided beforehand.

Further, for example, when the communication state between the vehicle and the information center is worse than a predetermined criterion or when the communication is impossible, the vehicle is notified of the fact. The operator may be notified.

As described above, when the communication state is worse than a predetermined reference or when communication is not possible (for example, when the communication means cannot transmit or receive radio waves because the vehicle is traveling in a tunnel). Then, by notifying the operator to that effect, the operator does not operate the vehicle-mounted device by voice. Therefore, erroneous control of the in-vehicle device due to an erroneous operation signal is prevented from being performed, and, for example, an operation of the in-vehicle device different from the operator's intention is performed, so that the operator may feel uncomfortable. Is prevented.

Further, when the communication state between the vehicle and the information center is worse than a predetermined standard or when the communication is impossible, the vehicle in the first step may receive a signal from the vehicle. Instead of transmitting the voice information to the information center, the vehicle may recognize the voice and convert the voice into an operation signal of the vehicle-mounted device, and may control the vehicle-mounted device according to the operation signal. .

[0022] This makes it impossible for the information center to perform accurate speech recognition, such as when the communication state between the vehicle and the information center is worse than a predetermined standard or when communication is impossible. When possible, voice recognition and conversion to operating signals take place in the vehicle. Therefore, the operator can operate the in-vehicle device by voice, and the convenience for the operator is improved.

In the communication state according to the second aspect of the present invention, the test voice information is transmitted from the vehicle to the information center, and the test voice information is transmitted from the information center to the information center in the vehicle. The determination may be made based on whether or not an operation signal corresponding to the voice information is received.

By performing the test on the communication state as described above, it is possible to determine whether or not the speech recognition is correctly performed in the information center and the conversion into the operation signal is performed accurately, in addition to the communication state.

When the voice of the operator can be recognized and converted into an operation signal in the vehicle, the voice information is not transmitted from the vehicle to the information center in the first step. , While recognizing the voice in the vehicle and converting it into an operation signal of the on-board equipment,
The on-vehicle device may be controlled according to the operation signal.

That is, according to the invention described in claim 4, the voice recognition is performed in the vehicle only when the communication state between the vehicle and the information center is worse than a predetermined standard or when communication is impossible. The present invention according to claim 6 first determines whether or not the vehicle can appropriately perform voice recognition, and if it can, performs conversion to the voice recognition and operation signal. Is performed in the vehicle to control the in-vehicle equipment, and only when the voice recognition cannot be appropriately performed in the vehicle, the voice information is transmitted to the information center and the voice recognition using the information center is performed. Performs conversion to operation signals. For this reason, transmission of voice information and reception of operation signals in the vehicle are minimized, and communication costs are reduced.

In the information center, voice recognition may be performed by an authentication system that performs user authentication using voiceprint data.

As described above, by using the authentication system of the information center for both user authentication and voice recognition, it is not necessary to provide a new voice recognition means in the information center, and the information center can perform voice recognition. Is realized at low cost. In addition, by performing voice recognition using voiceprint data in the authentication system, the accuracy of voice recognition can be further improved.

Further, in the first step, a vehicle type code for specifying the type of the vehicle is transmitted from the vehicle to the information center together with the information of the voice of the operator, and in the second step, the information is transmitted to the information center. The center may convert the recognition result of the voice and the operation signal of the vehicle-mounted device according to the vehicle type code.

That is, the type and configuration of the on-vehicle equipment mounted differ depending on the vehicle type. For this reason, when transmitting the voice information from the vehicle to the information center, by transmitting the vehicle type code specifying the vehicle type together, the information center receiving the voice information and the vehicle type code transmits the voice information and the vehicle type. With the code, conversion into an operation signal according to the type and configuration of the vehicle-mounted device becomes possible. As a result, the operation of the on-vehicle device by voice is more accurately performed.

According to a second aspect of the present invention, there is provided an operation system of an on-vehicle device, and more specifically, an operation system of an on-vehicle device for operating an on-vehicle device mounted on a vehicle by a voice of an operator. And a voice input means for inputting the voice of the operator, an external communication means for communicating with the information center, and an on-vehicle equipment control means for controlling the on-vehicle equipment.

The on-vehicle equipment control means transmits the information of the operator's voice input to the voice input means to the information center via the external communication means and receives the information via the external communication means. The information center is configured to control the in-vehicle device in response to an operation signal from the information center, and the information center receives the voice information transmitted through the external communication means and recognizes the voice. At the same time, it is a specific matter that the system is configured to convert the operation signal into an operation signal of the on-vehicle device according to the recognition result and transmit the operation signal to the on-vehicle device control means.

According to the ninth aspect, the same operation and effect as those of the first aspect can be obtained.

According to a third aspect of the present invention, there is provided an in-vehicle device control apparatus for controlling an in-vehicle apparatus mounted on a vehicle by a voice of an operator. And voice input means for inputting the voice of the operator, and external communication means for communicating with the information center.

The information of the operator's voice input to the voice input means is transmitted to the information center via the external communication means, and the operation signal from the information center received via the external communication means is received. The control of the above-mentioned in-vehicle device is performed according to a specific matter.

According to the tenth aspect, the first aspect is provided.
An on-vehicle device control device optimal for the on-vehicle device operation method according to (1) or the on-vehicle device operation system according to (9) is configured, and voice recognition and conversion into operation signals are performed in the information center. The device does not need to include an audio pattern, or need not include a high-precision audio pattern. For this reason, although more accurate voice recognition can be used, the cost of the in-vehicle device control device can be reduced.

Further, if a voice pattern is stored in the information center, a voice pattern corresponding to the operator can always be used without storing a voice pattern in the vehicle-mounted device control means.

According to the present invention, when the communication state between the external communication means and the information center is worse than a predetermined standard or when the communication is impossible, Without transmitting voice information to the information center, it recognizes voice input to voice input means, converts the voice into an operation signal of the vehicle-mounted device, and controls the vehicle-mounted device according to the operation signal. May be configured. Thus, the same operation and effect as the fourth aspect of the invention can be obtained.

Further, when the voice of the operator input to the voice input means can be recognized and converted into an operation signal, the voice information is not transmitted to the information center. In addition to recognizing the voice input to the voice input unit, the voice input unit may be configured to convert the voice into an operation signal of the vehicle-mounted device and control the vehicle-mounted device according to the operation signal. Thereby, the same operation and effect as the invention according to claim 6 are obtained.
The effect is obtained.

[0040]

As described above, according to the operation method of the vehicle-mounted device, the operation system of the vehicle-mounted device, and the vehicle-mounted device control device of the present invention, it is relatively easy and inexpensive to provide a voice pattern with high recognition accuracy. Since the voice recognition is performed in the information center where it can be performed, the accuracy of the voice recognition is improved, and an environment in which the in-vehicle device can be comfortably operated by voice can be realized at relatively low cost. Further, even when the on-board equipment control means (device) is different, for example, when the user gets on a car of another person, since the voice recognition is performed at the information center, the operator can obtain the same operation environment.

Further, since the on-vehicle equipment control means (device) does not need to be provided with a voice pattern or does not need to have a high-precision voice pattern, the cost of the on-vehicle equipment control means (device) can be reduced. Therefore, the operator can inexpensively obtain an environment in which the operation of the in-vehicle device by voice can be comfortably performed.

Furthermore, if the voice pattern of the operator is stored in the information center, voice recognition according to the operator becomes possible, and the accuracy of voice recognition can be greatly improved. In this case, even if it is different from the in-vehicle device control means (apparatus) which is normally used, since the voice recognition is performed using the voice pattern of the operator stored in the information center, the optimized voice In-vehicle equipment can be operated by voice in the recognition environment.

[0043]

Embodiments of the present invention will be described below with reference to the drawings.

<First Embodiment> FIG. 1 shows an operation system A of an in-vehicle device according to an embodiment of the present invention, which comprises various kinds of in-vehicle devices mounted on a vehicle V by voice (shown in FIG. 1). This is a system that enables operation of audio equipment and navigation equipment that omit the above.

The operation system A of the on-vehicle equipment includes an on-vehicle equipment 1 as on-vehicle equipment control means (device) mounted on the vehicle V for controlling the various on-vehicle equipment. The data can be transferred to and from an information center MC that provides various types of information (contents and e-mail data). Specifically, the information center M
A wireless communication antenna 31 is connected to a communication line 32 such as a telephone line connected to C, and a signal is wirelessly transmitted and received between the information center MC and the vehicle-mounted device 1 via the wireless communication antenna 31. .

The voice operation of various on-vehicle devices in the on-vehicle device operation system A can be performed by two voice operations, ie, a voice operation performed on the on-vehicle device 1 and a voice operation using the information center MC. .

Next, a description will be given of each device constituting the operation system A of the on-vehicle device. As shown in FIG. 2, the on-vehicle device CP performs a control process of various signals as shown in FIG.
U11 is provided. A ROM 12 for storing a control program and the like and a non-volatile RAM 13 for storing various data are connected to the on-vehicle device CPU 11 so that signals can be transmitted and received. The on-vehicle device CPU 11 has a wireless communication antenna 31 connected to the information center MC.
A communication device 41 as an external communication means for transmitting and receiving data signals to and from the vehicle is connected to be able to exchange signals. The communication device 41 may be, for example, a mobile phone.

The in-vehicle device CPU 11 further includes an audio device 42 and a navigation device 43 as in-vehicle devices to be operated by voice, and a microphone (hereinafter abbreviated as microphone) as voice input means for inputting voice of an operator. ) 44, an operation switch 45 operated when inputting voice to the microphone 44, a display 46 for displaying various information on a screen, and a speaker 47 for notifying various information, music and the like by voice. Are connected so that signals can be exchanged.

The navigation device 43 has a function of detecting the current position of the vehicle based on a GPS signal from a GPS satellite, a steering angle of the vehicle V, a traveling speed of the vehicle V, an azimuth of the vehicle V, and the like.

The microphones 44 are provided corresponding to respective seats (driver's seat and passenger seat, and right and left rear seats) provided in the vehicle. Note that only one microphone 44 may be provided.

The operation switch 45 is a manual switch for specifying a voice input to be subjected to voice recognition, and is operated when the operator issues a voice related to the voice operation (for example, a voice is emitted. The operation is continued during the operation or the sound is emitted immediately after the operation). The operation switch 45 is provided corresponding to the microphone 44.
In the case where the voice input to be subjected to voice recognition can be specified without operating the operation switch 45, the operation switch 45 may not be provided.

A voice pattern memory 14 is connected to the on-vehicle device CPU 11 so that signals can be transmitted and received. The on-vehicle device 1 is constituted by the on-vehicle device CPU 11, the ROM 12, the RAM 13, and the voice pattern memory 14. . The in-vehicle device 1 includes the in-vehicle device CPU 11 described above.
ROM 12, RAM 13, and voice pattern memory 1
4 and the communication device 41 and the microphone 44.

The voice pattern memory 14 stores the vehicle-mounted device 1
, And is composed of two types, a voice pattern for each operator ID and a general-purpose voice pattern. The voice pattern for each operator ID is a voice pattern stored in the voice pattern memory 14 by inputting voice (sample) in advance for each operator, and is operated according to the voice pattern for each operator ID. The speech recognition is optimized for each person. On the other hand, the general-purpose voice pattern is a voice pattern that can recognize voices of various types of operators. When the operator ID is specified, the voice pattern for each operator ID is used as the voice pattern for each operator ID, while the voice pattern for each operator ID is used. Switching such as use is performed. It should be noted that the present invention is not limited to this. For example, first, all voice patterns for each operator ID may be tried, and if voice recognition fails, a general-purpose voice pattern may be used. Speech recognition may be attempted using a general-purpose speech pattern, and if speech recognition fails, a speech pattern for each operator ID may be sequentially tried.

With this configuration, in the vehicle V, by manually operating various switches (not shown) provided on the audio device 42, the navigation device 43, and the like, the on-vehicle devices 42, 43 are operated. Controlled (manual operation). The in-vehicle device 1 recognizes the voice input by the operator to the microphone 44 by using the voice pattern memory 14, and based on the recognition result, the audio device 42 and the navigation device 43.
(Voice operation performed in the vehicle-mounted device 1). Furthermore, from the onboard unit 1 to the communication device 4
1, the voice information is transmitted to the information center MC, the voice recognition is performed at the information center MC, and the converted operation signal is received via the communication device 41, and the audio device 42 is transmitted in response to the operation signal. And the navigation device 43 (voice operation using the information center MC).

Further, the on-vehicle device 1 is connected to the information center M
As a normal communication control with C, a request signal based on voice or manual operation is transmitted to the information center MC, information from the information center MC is received, and the information is transmitted to the information center MC through the display 46 and the speaker 47. It is also provided to the operator.

On the other hand, the information center MC includes an information center CPU 2 to which the wireless communication antenna 31 is connected. The information center CPU 2 has a ROM 21 for storing a control program and the like and a non-volatile memory for storing various data. The RAM 22 is connected so that signals can be exchanged. The information center MC includes a content database 51 in which content data to be provided to users of the information center MC is stored.
A mail database 52 in which e-mail data of users of C are stored is provided, and these databases 51 and 52 are also provided in the information center C, respectively.
It is connected to PU2 so that signals can be exchanged.

The information center MC is provided with an audio pattern memory 23, and the audio pattern memory 23 is also connected to the information center CPU 2 so that signals can be transmitted and received. The voice pattern memory 23 of the information center MC, like the voice pattern memory 14 of the in-vehicle device 1, is composed of two voice patterns, one for each operator ID and a general-purpose voice pattern. The general-purpose voice pattern in the MC has higher voice recognition accuracy (higher recognition rate) than the general-purpose voice pattern in the in-vehicle device 1.

With this configuration, the communication center MC receives the voice information transmitted from the vehicle-mounted device 1 via the communication device 41, performs the voice recognition, and converts the voice information into an operation signal. Then, the converted operation signal is transmitted to the in-vehicle device 1 (voice operation using the information center MC).

The information center MC receives a request signal transmitted from the on-vehicle device 1 via the wireless communication antenna 31 as a communication control with the normal vehicle V (on-vehicle device 1). Is transmitted through the wireless communication antenna 31 to provide information to the occupant of the vehicle V.

Next, the method of operating the vehicle-mounted device according to the first embodiment will be described with reference to FIG. 2. The method of operating the vehicle-mounted device includes the following six steps. That is, when a voice input is made to the vehicle-mounted device 1, voice recognition is performed in the vehicle-mounted device 1, and the vehicle-mounted devices 42 and 43 are controlled according to the recognition result. When the above-mentioned voice recognition fails (when voice recognition cannot be performed), an operation request signal including voice information is transmitted to the information center MC. Information center MC that received the operation request signal
Performs voice recognition and converts it into an operation signal according to the recognition result. If the conversion into the operation signal is performed, the information center M
C transmits an operation signal including the vehicle-mounted device ID (included in the operation request signal) to the vehicle-mounted device 1. When the in-vehicle device 1 receives the operation signal or the like, the in-vehicle devices 42 and 43 are controlled according to the operation signal.

As described above, in the method of operating the on-vehicle device in the first embodiment, first, the voice operation on the on-vehicle device 1 is performed, and if the voice operation performed on the on-vehicle device 1 fails, the voice using the information center MC is used. The operation is to be performed.

The operation request signal includes voice information as voice information input by the operator, an in-vehicle device ID, an operator ID, and a vehicle type ID. Here, the in-vehicle device ID is an ID set for each in-vehicle device 1, and is used for collating transmitted voice information with a received operation signal. The operator ID is stored in the voice pattern memory 23.
Are used to specify a voice pattern for each operator ID in. The vehicle type ID is used at the time of conversion from voice information to an operation signal because the type or configuration of the vehicle-mounted devices 42 and 43 differs for each vehicle type. Note that the operator ID may be excluded from the operation request signal as long as the operator ID is transmitted for user authentication at the time of starting use (login) between the vehicle-mounted device 1 and the information center MC.

Next, the processing control in the on-vehicle device CPU 11 will be described with reference to FIG.
At the start, a flag F (information center MC
The flag F which is turned ON (becomes 1) when a request for voice recognition is made is OFF (has been made 0).

In step S11, it is determined whether or not a voice input to the microphone 44 has been made under the operation of the operation switch 45. YES when there was voice input
In the case of, the process proceeds to step S12, while in the case of no voice input being NO, the process proceeds to step S113 (FIG. 4B). Note that, as described above, when a voice input to be subjected to voice recognition can be specified without operating the operation switch 45, the condition “under operation of the operation switch 45” may be omitted. Good.

The above step S12 is a routine for specifying the operator (the person who has input the voice). Specifically, as shown in FIG. The ID of the operator may be calculated according to (a form in which the ID is input by voice or a form in which the ID is input by an operation switch).

In this case, the person who has input the voice is specified by inputting the ID of the operator in advance. However, the present invention is not limited to this. For example, the operation switch 45 for inputting the voice is used. By setting different operation modes for each operator, the voice input person may be specified based on the operation mode of the operation switch 45. Further, for example, the operator may be specified only by voice input using a voice print or the like.

When only one microphone 44 is provided, the condition "for each microphone" is not required.

When the operator ID is calculated in this way, in step S13, the voice pattern memory 1 of the vehicle-mounted device 1
The voice pattern corresponding to the operator ID is specified from the voice pattern for each operator ID in 4 and the input voice is recognized using the voice pattern. If the operator ID cannot be calculated in step S12, the input voice is recognized in step S13 using the general-purpose voice pattern in the voice pattern memory 14 of the vehicle-mounted device 1.

In step S14, conversion into an operation signal is performed in accordance with the result of the voice recognition in step S13. In step S15, it is determined whether or not the conversion into the operation signal is NG (voice recognition). Is unsuccessful). If not NG, step S
On the other hand, if the determination is NG, the process proceeds to step S17.

In step S16, the audio device 42 and the navigation device 43 are controlled in accordance with the converted operation signal (voice operation performed in the vehicle-mounted device 1), and the process proceeds to step S113.

On the other hand, when the process proceeds to step S17, it means that the speech recognition has failed.
Speech recognition using is performed. This step S
At 17, a message indicating that "remote voice recognition is being executed" is displayed on the display 46, and the process proceeds to step S18.

Step S18 is a routine for detecting a communication state. Specifically, as shown in FIG. 6, it is determined in step S31 whether or not the wireless telephone can communicate. This may be determined based on the electric field strength or the like received by the communication device 41 (for example, when the electric field strength is weak and communication with the information center MC may be interrupted, it is determined that the communication state is degraded. Do). Communication is possible YES
In the case of, the process proceeds to step S32, and it is determined that the communication state is good. On the other hand, when the communication is not possible, in the case of NO, the process proceeds to step S33 to determine that the communication state is deteriorated.

Note that, unlike the above, the communication state detection routine may be performed by determining whether or not connection to the information center MC is possible. Here, the case where connection to the information center is impossible is, for example, the case where the vehicle is traveling in a tunnel and transmission / reception of radio waves is impossible, and the case where the vehicle cannot physically connect to the information center MC. There are cases where the connection line is already full and a new connection cannot be made.

In order to determine the deterioration of the communication state, for example, since the information (content data and mail data) from the information center MC has already been received and the communication amount has reached the limit, the operation request signal is transmitted. If the operation signal cannot be received or the operation signal cannot be received, it may be determined that the communication state is deteriorated.

When the communication state detection routine is completed, it is determined in step S19 whether the communication state has deteriorated. If YES, step S11
Step 9 if NO
Go to 10.

In step S119, a message indicating "speech recognition failure" is displayed on the display 46, and a buzzer sounds from the speaker 47 to notify the operator that "speech recognition has failed". That is, it is a case where both the voice recognition in the on-vehicle device 1 and the voice recognition using the information center cannot be performed. In this case, the operator operates the in-vehicle devices 42 and 43 by manual operation.

On the other hand, step S110 is a routine for specifying the operator.
2 is the same as that performed in step 2, and the description thereof is omitted.

Next, in step S111, an operation request signal (on-vehicle device ID, input voice information,
The operator ID and the vehicle type ID are transmitted to the information center MC via the communication device 41. If the operator ID is not calculated in step S110, the operator ID
Is not sent.

Then, in step S112, the voice recognition request flag F for the information center MC is set to 1, and the flow advances to step S113.

In step S113, it is determined whether or not flag F is 1. When the flag F is 1 (YES) (when a voice recognition request has been issued to the information center MC), the process proceeds to step S114, while when the flag F is not 1 (NO), the process proceeds to step S114.
If no voice recognition request has been made to C), the process proceeds to step S120.

In step S114, it is determined whether a predetermined time has elapsed since the transmission of the operation request signal in step S111. The predetermined time may be set to, for example, about one second. If the predetermined time has elapsed, the process proceeds to step S117, while
If the predetermined time has not elapsed, if NO, step S1
Proceed to 15.

In step S117, the flag F
Is set to 0, and the process proceeds to step S119. This is the case where there is no response (return of the operation signal) from the information center MC even after transmitting the operation request signal, and the case where voice recognition using the information center MC has failed (as will be described later). If the voice recognition fails at the information center MC, no signal is transmitted to the vehicle-mounted device 1). For this reason, in step S119, a message indicating "speech recognition failure" is displayed on the display 46, and a buzzer is sounded from the speaker 47 to notify the operator (operator) of the message "speech recognition failure". I do. Then, the process proceeds to step S120. In this case, the operator operates the in-vehicle devices 42 and 43 by manual operation.

On the other hand, in step S115, it is determined whether or not an operation signal including its own vehicle-mounted device ID has been received (information center MC is configured to transmit an operation signal including the vehicle-mounted device ID). ing). When the operation signal has been received (YES), the process proceeds to step S116, whereas when the operation signal has not been received (NO), the process proceeds to step S120.

In step S116, the flag F
Is set to 0, and the process proceeds to step S118. Then, in step S118, the audio device 42 or the navigation device 43 is controlled according to the received operation signal (voice operation using the information center MC), and step S120 is performed.
Proceed to.

Step S120 is a step of performing a communication control routine with the information center MC other than the voice recognition and the like. For example, voice input (transmission) to the content database 51, the mail database 52, and the like of the information center MC, and Output notification (reception) from the information center MC is performed.

Step S121 is a normal control routine for the audio device 42 and the navigation device 43. In addition to the operation by voice, there are various switches provided in the audio device 42 and the navigation device 43 and the like. Control by manual operation by the user.

Next, processing control in the information center CPU 2 will be described with reference to FIG.

First, in step S41, it is determined whether an operation request signal has been received. Received Y
In the case of ES, the process proceeds to step S42, while in the case of NO where the information is not received, the process proceeds to step S46.

In step S42, if the operation request signal includes the operator ID, the voice recognition is performed using the voice pattern of the corresponding operator ID in the voice pattern memory 23. When the operation request signal does not include the operator ID (for example, the on-vehicle device 1
When the operator is not specified in the step (1), the voice recognition is performed using the general-purpose voice pattern in the voice pattern memory 23.

Next, in step S43, the operation signal is converted into an operation signal according to the recognition result in step S42 and the vehicle type ID included in the operation request signal. Thereby, it is converted into an operation signal according to the type and configuration of the on-vehicle devices 42 and 43.

In step S44, it is determined whether or not the conversion into the operation signal is NG (whether or not the voice recognition has failed). If the determination is NG, the process proceeds to step S46. If the determination is NO, the process proceeds to step S45. In other words, if it is NG, no signal is transmitted to the vehicle-mounted device 1.

In step S45, an operation signal including the in-vehicle device ID included in the operation request signal is transmitted to the in-vehicle device 1, and the flow advances to step S46.

Step S46 is performed at the normal information center MC.
This is a step corresponding to step S120 in FIG. 4B. Here, the content database 5 of the information center MC
The voice input (reception) and the result output (transmission) to the mail database 1 and the mail database 52 are performed.

As described above, in the first embodiment, the voice recognition is first performed in the vehicle-mounted device 1. If the voice recognition fails, the voice recognition is performed in the information center MC. Since this information center MC is equipped with a voice pattern with high recognition accuracy,
Speech recognition in the information center MC is performed with higher accuracy than in the case where the in-vehicle device 1 performs speech recognition. This makes it possible to realize an environment in which the in-vehicle devices 42 and 43 can be operated comfortably by voice. Moreover, since the information center MC also stores a voice pattern for each operator ID, the information center MC can perform voice recognition in accordance with the operator, and greatly improves the accuracy of voice recognition. be able to. It is to be noted that providing the information center MC with a voice pattern having high recognition accuracy can be performed easily and at low cost as compared with the case where the information center MC is provided with the on-vehicle device 1.

Further, by enabling voice recognition using the information center MC, the voice pattern of the vehicle-mounted device 1 does not have to be of high precision. As a result, the cost of the vehicle-mounted device 1 is reduced, and the operator can use the voice to control the vehicle-mounted devices 42 and 4.
An environment in which operation 3 can be performed comfortably can be obtained at low cost. Further, even if the on-vehicle device 1 is different (for example, even when the user gets on another person's car), the operator can always obtain the same operation environment by performing the voice recognition at the information center MC. In particular, when performing voice recognition using a voice pattern for each operator ID stored in the information center MC, the operator can always obtain a highly accurate voice recognition environment.

Further, when the communication state is worse than the predetermined reference, the conversion from the voice information to the operation signal in the information center MC is not performed (steps S18 and S19 in FIG. 4A). Thus, it is possible to prevent the erroneous control of the in-vehicle devices 42 and 43 due to the erroneous operation signal beforehand. When the communication state is worse than the predetermined reference, the operator is notified through the display 46 and the speaker (step S119 in FIG. 4B). As a result, the operator does not operate the in-vehicle devices 42 and 43 by voice, and it is possible to prevent the operator from feeling uncomfortable due to, for example, erroneous control of the in-vehicle devices 42 and 43.

In addition, when voice recognition is possible in the vehicle-mounted device 1, transmission of voice information (transmission of an operation request signal) to the information center MC is not performed, so that communication costs can be reduced. it can.

Therefore, according to the operation method, the operation system A, and the in-vehicle device 1 of the in-vehicle device according to the first embodiment, an environment in which the in-vehicle devices 42 and 43 can be comfortably operated by voice is realized, and the in-vehicle device is realized. Even if 1 is different, it is possible to operate by voice in the same operation environment, and such a comfortable operation environment can be realized at low cost.

<Second Embodiment> FIG. 8 shows a conceptual diagram of a method of operating a vehicle-mounted device according to a second embodiment of the present invention.
This is different from the first embodiment in that the voice recognition is performed first using the information center MC, and when the voice recognition in the information center MC fails, the voice recognition is performed in the vehicle-mounted device 1. It is configured as follows. That is, when a voice input is made to the vehicle-mounted device 1, an operation request signal including voice information is transmitted to the information center MC. Information center MC that received the operation request signal
Performs voice recognition and converts it into an operation signal according to the recognition result. If the conversion into the operation signal is performed, the information center M
C transmits an operation signal including the vehicle-mounted device ID to the vehicle-mounted device 1. When the in-vehicle device 1 receives the operation signal or the like, the in-vehicle devices 52 and 43 are controlled based on the operation signal. When no operation signal or the like is received (when the voice recognition cannot be performed at the information center MC), the voice recognition is performed in the vehicle-mounted device 1 and the vehicle-mounted device 4 according to the recognition result.
The configurations of the various devices 1, 41 to 47 mounted on the vehicle V and the configuration of the information center MC are the same as those of the first embodiment. The same reference numerals are given and the description is omitted.

Next, the control in the on-vehicle device CPU 11 will be described with reference to the flowchart shown in FIG.

First, in step S51, a communication state detection routine is performed. This is the same as that shown in FIG.

Then, in a step S52, it is determined whether or not the communication state is deteriorated. YES
In the case of, while proceeding to step S57, N
In the case of O, the process proceeds to step S53.

In step S53, it is determined whether or not a voice has been input from the microphone 44 under the operation of the operation switch 45. If YES in step S54, the flow advances to step S54.
In the case of O, the process proceeds to step S515 (see FIG. 9B).
Note that the condition "under operation of the operation switch 45" is not essential, as in the first embodiment.

In step S54, an operator specific routine is performed. This is the same as that shown in FIG.

Then, in step S55, the vehicle-mounted device ID, voice information, operator ID, vehicle type ID, and vehicle-mounted device ID
Is transmitted to the information center MC. Then, the flag F is set to 1 in step S56, and the process proceeds to step S515.

On the other hand, if it is determined in step S52 that the communication state is deteriorating, the process proceeds to step S57.
Performs voice recognition. First, in step S57, "remote voice recognition is impossible at this time" is displayed on the display 46.
Is displayed.

Next, in step S58, it is determined whether or not a voice has been input from the microphone 44 under the operation switch 45. If YES in step S59, the process proceeds to step S59. If NO in step S515, the process proceeds to step S515.

In step S59, an operator specific routine is performed (see FIG. 5). Then, step S510
, When the operator is specified, the voice recognition is performed using the voice pattern corresponding to the operator ID in the voice pattern memory 14. When the operator is not specified, the voice recognition is performed using the general-purpose voice pattern in the voice pattern memory 14.

Next, in step S511, conversion to an operation signal is performed in accordance with the result of voice recognition, and in step S512, it is determined whether or not conversion to the operation signal was NG. If the determination is NG, the process proceeds to step S513, whereas if the determination is NO, the process proceeds to step S514.

In step S513, a message indicating that "vehicle-mounted voice recognition has failed" is displayed on the display 46, and a buzzer is sounded by the speaker 47 to notify the operator that "vehicle-mounted voice recognition has also failed". Do. In this case, the operator manually operates the in-vehicle devices 42 and 43.

On the other hand, in step S514, the case where the conversion into the operation signal is correctly performed is performed, and the audio device 42 or the navigation device 43 is controlled in accordance with the operation signal (the voice operation performed in the vehicle-mounted device 1). ).
Then, the process proceeds to step S515.

In the step S515, it is determined whether or not the flag F is "1". If the flag F is 1 (YES), the process proceeds to step S516, while if the flag F is not 1 (0), the process proceeds to step S516.
Proceed to 521.

In step S516, it is determined whether or not a predetermined time (for example, one second) has elapsed after transmitting the operation request signal. YE after a predetermined time
In the case of S, the process proceeds to step S520, the flag F is set to 0, and the process returns to step S59. That is, the information center M
Since voice recognition using C has failed, the vehicle-mounted device 1 attempts voice recognition.

On the other hand, if it is determined in step S516 that the predetermined time has not elapsed (NO in step S516), the flow advances to step S517. In step S517, it is determined whether an operation signal including its own vehicle-mounted device ID has been received. Received Y
In the case of ES, the process proceeds to step S518 to set the flag to 0, and then proceeds to step S519. On the other hand, if NO has not been received, the process proceeds to step S521.

In step S519, the audio device 42 or the navigation device 43 is controlled according to the received operation signal (voice operation using the information center MC).

The above steps S521 and S52
Steps 2 are the same as steps S120 and S121 in FIG.

The control by the CPU on the information center side is the same as in the first embodiment, and a description thereof will be omitted.

As described above, also in the second embodiment, similarly to the operation method of the in-vehicle device, the operation system A and the in-vehicle device 1 according to the first embodiment, the in-vehicle device 42,
An environment that allows comfortable operation of 43 is realized,
Even if the in-vehicle device 1 is different, it is possible to operate by voice in the same operation environment, and such a comfortable operation environment can be realized at low cost.

In the second embodiment, first, the voice recognition using the information center MC is performed.
, Speech recognition with higher accuracy is performed first.
Therefore, the control of the in-vehicle devices 42 and 43 by voice can be performed more comfortably.

<Other Embodiments> It should be noted that the present invention is not limited to the above-described embodiments, but includes various other embodiments. That is, the communication state detection routine (step S51) in the second embodiment may be, for example, as shown in FIG.

That is, in step S61, it is determined whether a predetermined period has elapsed. YES
In the case of, the process proceeds to step S62, while in the case of NO where it has not elapsed, the process ends.

In step S62, a dummy operation request signal (test signal) is transmitted to the information center. This dummy operation request signal includes predetermined voice information, predetermined operator ID, and in-vehicle device ID stored in advance.
And vehicle type ID.

In step S63, it is determined whether an operation signal corresponding to the dummy operation request signal has been received within a predetermined time. YE received
In the case of S, the process proceeds to step S64, while in the case of NO where the information is not received, the process proceeds to step S65.

In step S64, it is determined that the communication state is good, whereas in step S65, it is determined that the communication state is deteriorated.

As described above, in the communication state detection routine, the test voice signal (dummy operation request signal) is transmitted to the information center MC at a predetermined cycle, and the operation corresponding to the test voice information from the information center MC is performed. The determination may be made based on whether the vehicle-mounted device 1 receives the signal. In this case, it is possible to determine not only the communication state but also whether or not the voice recognition is correctly performed in the information center MC and the conversion into the operation signal is performed accurately.

Also, different from the above embodiment, the speech recognition using the information center MC is performed by the information center MC.
The authentication may be performed by an authentication system that performs user authentication using voiceprint data at the start of use (at the time of login).

As a result, by using the authentication system of the information center MC for both user authentication and voice recognition, it is not necessary to provide a new voice recognition means in the information center MC, and the information center MC is not required. Voice recognition can be realized at low cost. In addition, by performing voice recognition using voiceprint data in the authentication system, the accuracy of voice recognition can be further improved.

Incidentally, as the operation system A of the vehicle-mounted device,
The voice recognition may be performed only at the information center MC so that the vehicle-mounted device 1 does not include the voice pattern memory 14. The voice pattern for each operator ID in the voice pattern memories 14 and 23 is not essential.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram showing an operation system of a vehicle-mounted device.

FIG. 2 is a block diagram showing an operation system of the vehicle-mounted device.

FIG. 3 is a conceptual diagram illustrating an operation method of the on-vehicle device according to the first embodiment.

FIG. 4A is a part of a flowchart showing processing control of the on-vehicle device according to the first embodiment.

FIG. 4B is a part of a flowchart showing processing control of the on-vehicle device according to the first embodiment.

FIG. 5 is a flowchart illustrating an operator identification routine.

FIG. 6 is a flowchart illustrating a communication state detection routine.

FIG. 7 is a flowchart showing processing control of the information center.

FIG. 8 is a view corresponding to FIG. 3 and showing a method of operating an in-vehicle device according to a second embodiment.

FIG. 9A is a part of a flowchart showing processing control of the on-vehicle device according to the second embodiment.

FIG. 9B is a part of a flowchart showing processing control of the on-vehicle device according to the second embodiment.

FIG. 10 is a flowchart illustrating a communication state detection routine according to another embodiment.

[Explanation of symbols]

Reference Signs List 1 in-vehicle device (in-vehicle device control means, in-vehicle device control device) 41 communication device (outside vehicle communication device) 42 audio device (in-vehicle device) 43 navigation device (in-vehicle device) 44 microphone (speech input means) A in-vehicle device operation system MC Information Center V Vehicle

Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat II (reference) G10L 15/10 H04M 3/42 P 5K024 15/00 3/50 A 15/28 G10L 3/00 531K H04M 3/42 551A 3/50 551J 571K (72) Inventor Masao Ushio 3-1 Shinchi, Fuchu-cho, Aki-gun, Hiroshima Mazda F-term (reference) 2F029 AA02 AB01 AB07 AB13 AC02 AC09 AC13 AC18 3D020 BA02 BA04 BB01 BC01 BD03 BE03 5D015 KK01 KK02 5H180 AA01 BB05 FF05 FF13 FF22 FF32 5K015 AA06 AA07 GA07 5K024 AA74 BB01 EE09 GG01

Claims (12)

[Claims] 1. A method of operating an in-vehicle device that operates an in-vehicle device mounted on a vehicle by a voice of an operator, the method comprising transmitting information of the voice of the operator from the vehicle to an information center. A second step of receiving the voice information transmitted from the vehicle and recognizing the voice at the information center, and converting the voice information into an operation signal of the on-vehicle device according to a recognition result; A third step of transmitting the converted operation signal to the vehicle from a third step of receiving the operation signal transmitted from the information center and controlling the in-vehicle device according to the operation signal in the vehicle. A method for operating an in-vehicle device, comprising four steps. 2. The method according to claim 1, wherein when the communication state between the vehicle and the information center is worse than a predetermined criterion, the voice recognition in the information center in the second step is prohibited. How to operate onboard equipment. 3. The vehicle according to claim 1, wherein when the communication state between the vehicle and the information center is worse than a predetermined standard or when the communication is not possible, the operator informs the vehicle of the fact. A method of operating an in-vehicle device, which is notified to a user. 4. The vehicle according to claim 1, wherein when the communication state between the vehicle and the information center is worse than a predetermined standard or when communication is not possible, the information from the vehicle in the first step is output from the vehicle. Without transmitting voice information to the center, while recognizing voice in the vehicle and converting it to an operation signal of onboard equipment,
A method for operating an in-vehicle device, comprising controlling the in-vehicle device according to the operation signal. 5. The communication state according to claim 2, wherein the communication state includes transmitting test voice information from the vehicle to the information center, and performing an operation corresponding to the test voice information from the information center on the vehicle. A method for operating an in-vehicle device, characterized by determining whether a signal is received or not. 6. The vehicle according to claim 1, wherein when the vehicle can recognize the voice of the operator and convert the voice into an operation signal, the voice information is not transmitted from the vehicle to the information center in the first step. A method for operating a vehicle-mounted device, comprising recognizing a voice in a vehicle, converting the voice into an operation signal of the vehicle-mounted device, and controlling the vehicle-mounted device according to the operation signal. 7. The method according to claim 1, wherein in the information center, voice recognition is performed by an authentication system that performs user authentication using voiceprint data. 8. The information processing system according to claim 1, wherein in the first step, a vehicle type code for specifying a vehicle type of the vehicle is transmitted from the vehicle to the information center together with information on the voice of the operator. A method of operating an in-vehicle device, wherein the method converts the signal into an operation signal of an in-vehicle device according to the recognition result of the voice and the vehicle type code. 9. An operation system of an on-vehicle device for operating an on-vehicle device mounted on a vehicle by a voice of an operator, wherein the voice input means for inputting the voice of the operator and a communication with an information center. And an on-vehicle device control unit for controlling the on-vehicle device, wherein the on-vehicle device control unit transmits the information of the operator's voice input to the voice input unit via the out-of-vehicle communication unit. The information center transmits the information to the information center and controls the on-vehicle device in response to an operation signal from the information center received via the external communication means. Receiving the audio information transmitted through the means, recognizes the audio,
An operation system for an in-vehicle device, wherein the operation system is configured to convert the operation signal into an operation signal of the in-vehicle device according to a recognition result and transmit the operation signal to the in-vehicle device control means. 10. An operation of an on-vehicle device mounted on a vehicle,
An in-vehicle device control device that is performed by a voice of an operator, comprising: a voice input unit that inputs the voice of the operator; and an external communication unit that communicates with an information center. Transmitting voice information of the operator to the information center via the external communication means, and controlling the on-vehicle equipment in response to an operation signal from the information center received via the external communication means; An in-vehicle device control device characterized in that: 11. The voice information to the information center according to claim 10, wherein the communication state between the outside communication means and the information center is worse than a predetermined standard or when communication is impossible. , Without recognizing the voice input to the voice input means, converting the voice into an operation signal of the in-vehicle device, and controlling the in-vehicle device according to the operation signal. Characteristic in-vehicle equipment control device. 12. The voice input device according to claim 10, wherein when the voice of the operator input to the voice input means can be recognized and converted into an operation signal, the voice information is not transmitted to the information center. An on-vehicle device control device characterized in that it is configured to recognize a voice input to the means, convert the voice into an operation signal of the on-vehicle device, and control the on-vehicle device according to the operation signal.