JP2022076399A - Control system - Google Patents

Abstract

To enable accuracy of voice recognition to be increased without adding a device for understanding of the intention of utterance, and to reflect a user's will in control of a function.SOLUTION: A control system 10 has a plurality of ECUs 20 connected to each other. Each of the ECUs 20 includes: a receiving unit that receives user's utterance as voice information; a calculation unit that calculates a priority coefficient set as a coefficient including at least a degree of certainty in a case in which a function associated with the voice information received by the receiving unit is executed in its own device; a notification unit that notifies other control devices of the calculated priority coefficient of the own device; a comparison unit that compares priority coefficients of the respective other control devices; and an execution unit that in a case in which the priority coefficient of the own device is the largest as a result of a comparison made by the comparison unit, causes the own device to execute the function.SELECTED DRAWING: Figure 1

Description

The present invention relates to a control system that is controlled by a plurality of control devices.

Patent Document 1 discloses a voice recognition control device that enables execution of a plurality of execution commands when a plurality of users simultaneously emit voice. The voice recognition control device includes a plurality of microphones arranged at different positions and a voice transmission control unit. Here, the voice transmission control unit stores data based on the voice input from each microphone and time data regarding the ranking between the microphones, and uses the time data based on a plurality of preset conditions. The microphones are ranked, and the voice data signal corresponding to the microphone is transmitted to the voice recognition execution control unit in the order of ranking. Then, the voice recognition execution control unit performs voice recognition processing according to the order of the voice data signals transmitted from the voice transmission control unit.

Japanese Unexamined Patent Publication No. 2014-203031

The voice recognition control device of Patent Document 1 is an invention in which voice recognition is performed by ordering utterances when there are a plurality of utterances by a plurality of users, and a plurality of devices are used for one utterance by one user. It does not perform voice recognition. Further, in the case of performing voice recognition based on an utterance, the utterance cannot be reflected in the operation of the function unless the intention of the utterance can be accurately understood by a device other than the device that acquires the utterance.

The present invention provides a control system capable of improving the accuracy of speech recognition without adding a device for understanding the intention of utterance and reflecting the intention of the user in the control of the function. The purpose.

The control system according to claim 1 is a control system having a plurality of control devices connected to each other, and the control device receives a user's speech as voice information and a reception unit. A calculation unit that calculates a priority coefficient that is quadratured by at least including the probability that a function related to the obtained voice information is executed in the own device, and another control device that calculates the calculated priority coefficient of the own device. As a result of comparison between the notification unit that notifies the user, the comparison unit that compares the priority coefficient of each control device, and the comparison unit, when the priority coefficient of the own device is the maximum, the function is performed in the own device. It has an execution unit to be executed.

The control system according to claim 1 has a plurality of control devices connected to each other. In the control system, when the reception unit receives the user's utterance as voice information, the calculation unit calculates the priority coefficient. Here, the priority coefficient includes at least the accuracy when the function related to the voice information received by the reception unit is executed by the control device which is the own device. Then, in each control device, when the notification unit notifies the other control devices of the priority coefficient, the comparison unit compares the priority coefficients acquired from each control device, and the execution unit has the maximum priority coefficient of its own device. In this case, the function related to the voice information received by the own device is executed. According to the control system, the understanding of the intention of the utterance and the execution of the function are completed in the control device. Therefore, the accuracy of voice recognition can be improved without adding a device for understanding the intention of utterance, and the intention of the user can be reflected in the control of the function.

According to the present invention, the accuracy of voice recognition can be improved without adding a device for understanding the intention of utterance, and the intention of the user can be reflected in the control of the function.

It is a figure which shows the schematic structure of the control system which concerns on 1st Embodiment. It is a block diagram which shows the hardware composition of the ECU and its peripheral device which concerns on 1st Embodiment. It is a block diagram which shows the functional structure of the ECU which concerns on 1st Embodiment. It is a flowchart which shows the flow of the process executed in the ECU which concerns on 1st Embodiment.

The control system of the present invention and a vehicle equipped with the control system will be described.

[First Embodiment]
As shown in FIG. 1, the control system 10 of the first embodiment is provided for the vehicle 12. The control system 10 includes a plurality of ECUs (Electronic Control Units) 20 as control devices. The ECU 20 includes a car navigation ECU 20A, an ADAS (Advanced Driver Assistance System) -ECU 20B, and a meter ECU 20C. The ECUs 20 are connected to each other via an external bus 14.

At least a microphone 24 and a monitor 26 are connected to each ECU 20. A camera 28 is connected to the ADAS-ECU 20 in addition to the microphone 24 and the monitor 26.

As shown in FIG. 2, the ECU 20 includes a CPU (Central Processing Unit) 20A, a ROM (Read Only Memory) 20B, a RAM (Random Access Memory) 20C, an in-vehicle communication I / F (Inter Face) 20D, and an input / output I / O. It is configured to include F20F. The CPU 20A, ROM 20B, RAM 20C, in-vehicle communication I / F20D, and input / output I / O 20F are connected to each other so as to be communicable with each other via the internal bus 20G.

The CPU 20A is a central arithmetic processing unit that executes various programs and controls each unit. That is, the CPU 20A reads the program from the ROM 20B and executes the program using the RAM 20C as a work area.

The ROM 20B stores various programs and various data. The ROM 20B of the present embodiment stores a control program 100 for controlling the ECU 20.

The RAM 20C temporarily stores a program or data as a work area.

The in-vehicle communication I / F20D is an interface for connecting to another ECU 20. Ethernet® is applied to the interface. The communication standard based on the CAN protocol may be applied to the in-vehicle communication I / F20D. The in-vehicle communication I / F20D is connected to the external bus 14.

The input / output I / F 20F is an interface for communicating with the microphone 24, the monitor 26, the camera 28, and the vehicle equipment 30 mounted on the vehicle 12. As described above, the camera 28 is connected only to the ADAS-ECU 20B.

The microphone 24 as a voice input device is a device that collects the voice emitted by the occupant of the vehicle 12 who is the user. The microphone 24 is installed in the vicinity of the monitor 26 connected to each ECU 20. The microphone 24 of the present embodiment is a directional microphone having directivity.

The monitor 26 as a display device is a liquid crystal monitor for displaying an image related to the function of the vehicle 12 and an image related to the explanation of the function. As an example, the monitor 26 related to the car navigation ECU 20A is provided at the center of the instrument panel in the vehicle width direction. The monitor 26 according to the ADAS-ECU 20B is configured as a head-up display. Further, the monitor 26 related to the meter ECU 20C is configured as a meter display.

The camera 28 as an image pickup device is a device provided on the front pillar, the rearview mirror, the steering column, or the like of the vehicle 12 to take an image of the occupant of the vehicle 12. As described above, the camera 28 is provided only for the ADAS-ECU 20, but may be provided for another ECU 20.

The vehicle device 30 is a device for realizing the function of the vehicle 12. For example, a GPS device as a vehicle device 30 is connected to the car navigation ECU 20A. Further, for example, a throttle actuator, a brake actuator, or the like is connected to the ADAS-ECU 20B as a vehicle device. Further, a lighting device as a vehicle device 30 and a wiper device are connected to the meter ECU 20C.

As shown in FIG. 3, in the ECU 20 of the present embodiment, the CPU 20A functions as a reception unit 200, a calculation unit 210, a notification unit 220, a comparison unit 230, and an execution unit 240 by executing the control program 100.

The reception unit 200 receives the utterances of the occupants as voice information. Then, the reception unit 200 acquires the utterance command corresponding to the intention of the utterance based on the received voice information. This utterance command is a command for executing a function of the vehicle 12 related to voice information (hereinafter, referred to as "related function").

The calculation unit 210 calculates the priority coefficient. The priority coefficient is a coefficient of the following three elements.

(1) Accuracy when the related function is executed in the ECU 20 which is the own device In the present embodiment, the accuracy is higher as the direction of the occupant's utterance to the microphone 24 is correct. For example, when the occupant speaks toward the meter display, the accuracy of the meter ECU 20C is maximized. Then, the calculation unit 210 increases the priority coefficient as the accuracy increases.

(2) Amount of resources in the ECU 20 which is the own device In the present embodiment, the resource amounts of the CPU 20A, the RAM 20C, and the actuator which is the vehicle equipment 30 in each ECU 20 are acquired, and the calculation unit 210 obtains the resources necessary for executing the function. The shorter the time to completion, the higher the priority factor. For example, it is configured so that the priority coefficient becomes higher as the amount of resources is sufficient because other functions are not executed in the own device.

(3) Priority order of related functions In this embodiment, the priority order of executing related functions is calculated based on other information, and the higher the priority order is, the higher the priority coefficient is configured. There is. For example, when rain is confirmed by a raindrop sensor or the like, the calculation unit 210 raises the priority order in the meter ECU 20C to which the raindrop sensor is connected. When receiving that the weather forecast is rain, the calculation unit 210 raises the priority order in the car navigation ECU 20A that has received the weather forecast.

Based on the above factors (1) to (3), an example of calculating the priority coefficient when operating the "wiper" will be illustrated. First, regarding the accuracy of (1), the calculation unit 210 is so high that the direction of utterance is directed toward each microphone 24, for example, the car navigation ECU 20A has 2 points, the ADAS-ECU 20B has 6 points, and the meter ECU 20C has 8 points. Is given. Further, regarding the resource amount of (2), the calculation unit 210 is as high as the ECU 20A in which other functions are not executed. For example, the car navigation ECU 20A is given 4 points, the ADAS-ECU 20B is given 4 points, and the meter ECU 20C is given 8 points. Suppose. Further, regarding the priority order of (3), the calculation unit 210 is higher as the ECU 20 is more likely to execute the related function, for example, the car navigation ECU 20A has 5 points, the ADAS-ECU 20B has 0 points, and the meter ECU 20C has 10 points. Is given.

As described above, when the points of each element are integrated, the car navigation ECU 20A has 11 points, the ADAS-ECU 20B has 10 points, and the meter ECU 20C has 26 points, and the priority coefficient of the meter ECU 20C is the highest.

The notification unit 220 has a function of notifying another ECU 20 of the calculated priority coefficient.

The comparison unit 230 has a function of comparing the priority coefficients acquired from each ECU 20.

The execution unit 240 has a function of executing an utterance command in the ECU 20 when the priority coefficient of the ECU 20 which is the own device is the maximum as a result of the comparison in the comparison unit 230.

(Control flow)
The flow of processing executed in the control system 10 of the present embodiment will be described with reference to the flowchart of FIG. FIG. 4 illustrates the processing in one ECU 20, but the same processing is executed in the other ECU 20. The process shown in the figure is realized by the CPU 20A functioning as a reception unit 200, a calculation unit 210, a notification unit 220, a comparison unit 230, and an execution unit 240.

In step S100 of FIG. 4, the CPU 20A receives the utterance of the occupant. As a result, when the CPU 20A can understand the intention of the utterance, the CPU 20A acquires the utterance command corresponding to the intention.

In step S101, the CPU 20A calculates the recognition coefficient.

In step S102, the CPU 20A transmits the recognition coefficient to each ECU 20.

In step S103, the CPU 20A receives the recognition coefficient from each ECU 20.

In step S104, the CPU 20A determines whether or not the recognition coefficient of the ECU 20 which is its own device is the maximum. When the CPU 20A determines that the recognition coefficient of the ECU 20 which is its own device is the maximum (YES in step S104), the CPU 20A proceeds to step S105. On the other hand, when the CPU 30A determines that the recognition coefficient of the ECU 20 which is its own device is not the maximum (NO in step S104), the CPU 30A returns to step S100.

In step S105, the CPU 20A executes an utterance command. This will perform the relevant function. Then, the process returns to step S100.

(Summary of the first embodiment)
The control system 10 of the present embodiment has a plurality of ECUs 20 connected to each other. In the control system 10, when the reception unit 200 receives the user's utterance as voice information, the calculation unit 210 calculates the priority coefficient in each ECU 20. Then, in each ECU 20, when the notification unit 220 notifies the other ECUs of the priority coefficient, the comparison unit 230 compares the priority coefficients acquired from each ECU 20, and the execution unit 240 has the maximum priority coefficient of its own device. In some cases, perform related functions.

According to the control system 10 of the present embodiment, the understanding of the intention of the utterance and the execution of the function are completed in each ECU 20. Therefore, the accuracy of voice recognition can be improved without adding a device for understanding the intention of utterance, and the intention of the occupant can be reflected in the control of the function. Further, according to the present embodiment, it is not necessary to make the intention of the utterance understood by an external device, and it is possible to enhance the real-time property of executing the function for the utterance.

The priority coefficient in this embodiment includes at least the accuracy when the related function is executed in the ECU 20 which is the own device. When calculating the priority coefficient based on the accuracy, the calculation unit 210 adds the directionality of the utterance by the occupant to the microphone 24 corresponding to the own device to the calculation of the priority coefficient. That is, according to the present embodiment, the accuracy of voice recognition can be further improved by specifying the target ECU 20 to which the occupant has spoken.

Further, in the present embodiment, the resource amounts of the CPU 20A, the RAM 20C, and the actuator of the vehicle device 30 in each ECU 20 are added to the calculation of the priority coefficient. That is, according to the present embodiment, the accuracy of voice recognition can be further improved by identifying the ECU 20 that is not in operation.

[Second Embodiment]
In the second embodiment, the method of calculating the priority coefficient is different from that in the first embodiment. Hereinafter, the differences from the first embodiment will be described. Since the hardware configuration is the same as that of the first embodiment, the description thereof is omitted.

The calculation unit 210 of the present embodiment is characterized in that the gaze degree of the occupant to each monitor 26 acquired based on the image captured by the camera 28 connected to the ADAS-ECU 20 is added to the calculation of the priority coefficient. For example, when the occupant is gazing at the monitor 26 of the car navigation system when speaking, the degree of gazing in the car navigation ECU 20A is high. In this case, the calculation unit 210 increases the priority coefficient of the car navigation ECU 20A as the gaze level increases.

According to the present embodiment, the accuracy of voice recognition can be further improved by specifying the target ECU 20 that the occupant gazes at.

[Third Embodiment]
In the third embodiment, the method of calculating the priority coefficient is different from that of the first and second embodiments. Hereinafter, the differences from the first embodiment will be described. Since the hardware configuration is the same as that of the first embodiment, the description thereof is omitted.

The calculation unit 210 of the present embodiment is configured so that the weighting of each element used for calculating the priority coefficient can be changed. As described above, each element includes (1) the accuracy when the related function is executed in the own device ECU 20, (2) the amount of resources in the own device ECU 20, and (3) the priority order of the related functions. .. The weighting of each element is changed in the setting menu displayed on the monitor 26. The weighting of each element may be changed by a device outside the vehicle 12, for example, a server connected to the vehicle 12 or a vehicle diagnostic machine which is a diagnostic tool.

According to the present embodiment, it is possible to optimize voice recognition when the function is activated based on the utterance.
In addition, when weighting each element, the preference of the occupant may be reflected. For example, when an occupant who prefers a driving system function such as ACC (Adaptive Cruise Control) is on board and the related function is a driving system function, the priority coefficient may be set to be high. ..

[remarks]
In each of the above embodiments, the related function is executed by the utterance command in the ECU 20 having the highest priority coefficient, but when the function to be executed is a device related to the running of the vehicle 12, the operation of the function is proposed before the execution. You may.

In each of the above embodiments, the microphone 24 is provided for each ECU 20, but the present invention is not limited to this, and any microphone 24 having high directivity may be used.

In addition, various processors other than the CPU may execute various processes executed by the CPU 20A by reading the software (program) in the above embodiment. In this case, the processor includes a PLD (Programmable Logic Device) whose circuit configuration can be changed after manufacturing an FPGA (Field-Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), and the like. An example is a dedicated electric circuit or the like, which is a processor having a circuit configuration designed exclusively for it. Further, the above-mentioned processing may be executed by one of these various processors, or a combination of two or more processors of the same type or different types (for example, a plurality of FPGAs and a combination of a CPU and an FPGA). Etc.). Further, the hardware-like structure of these various processors is, more specifically, an electric circuit in which circuit elements such as semiconductor elements are combined.

Further, in the above embodiment, each program has been described in a manner in which each program is stored (installed) in a non-temporary recording medium readable by a computer in advance. For example, the control program 100 in the ECU 20 is stored in the ROM 20B in advance. However, the present invention is not limited to this, and each program is recorded on a non-temporary recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versaille Disc Read Only Memory), and a USB (Universal Serial Bus) memory. May be provided in the form provided. Further, the program may be downloaded from an external device via a network.

10 Control system 20 ECU (control device)
200 Reception Department 210 Calculation Department 220 Notification Department 230 Comparison Department 240 Execution Department

Claims (1)

A control system that has multiple control devices connected to each other.
The control device is
A reception unit that accepts user utterances as voice information,
A calculation unit that calculates a priority coefficient that is coefficiented by including at least the accuracy when a function related to voice information received by the reception unit is executed in the own device.
A notification unit that notifies other control devices of the calculated priority coefficient of the own device, and
A comparison unit that compares the priority coefficients of each of the control devices,
As a result of comparison in the comparison unit, when the priority coefficient of the own device is the maximum, the execution unit for executing the function in the own device and the execution unit.
Control system with.

Images