Vehicle dialogue system

Abstract

To provide a vehicle dialogue system that can operate an in-vehicle device by voice and can give a natural response to an utterance, such as a small talk, that is not intended to operate the in-vehicle device.SOLUTION: A voice dialogue unit 42 determines whether or not text data converted by a voice recognition unit 41 indicates an operation instruction for an in-vehicle device 11. If the voice dialogue unit 42 determines that the text data indicates the operation instruction for the in-vehicle device 11, the voice dialogue unit controls the in-vehicle device 11 in accordance with the operation instruction. If the voice dialogue unit 42 determines that the text data does not indicate the operation instruction for the in-vehicle device 11, the voice dialogue unit inputs the text data of the voice to dialogue AI 10 as input information S1.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a dialogue system for a vehicle. [Background technology]

[0002] A voice agent service has been proposed that responds by voice when a user speaks (Patent Document 1). The voice agent service of Patent Document 1 is a system that responds only to predetermined speech data and returns a reply. For this reason, when an utterance other than the predetermined content is made, the voice agent service of Patent Document 1 responds with "I don't know" or replies by linking it to the closest predetermined utterance, so the response does not come out as natural as when conversing with a person.

[0003] In recent years, conversational AI (generative AI) such as ChatGPT has been proposed, which can learn from the vast amount of information available on the Internet and have more natural conversations. However, while such conversational AI is suitable for casual conversations, it does not have the ability to operate in-vehicle devices. This poses a problem in that it cannot respond when the driver makes utterances intended to operate devices. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-98844 Summary of the Invention [Problem to be solved by the invention]

[0005] The present invention has been made in consideration of the above-mentioned circumstances, and its object is to provide a dialogue system for a vehicle that allows operation of in-vehicle equipment by voice and that can respond naturally to utterances that are not intended to operate the in-vehicle equipment, such as casual conversation. [Means for solving the problem]

[0006] In order to achieve the above-mentioned object, the vehicle dialogue system according to the present invention has the following features. A vehicle dialogue system using an interactive AI that outputs response information made up of text data when input information made up of text data is input, a voice input unit for inputting voice spoken by the driver; a voice recognition unit that converts the voice input by the voice input unit into text data; an equipment control unit that, when it is determined that the text data converted by the voice recognition unit indicates an operation instruction for an in-vehicle device, controls the in-vehicle device in accordance with the operation instruction; a speech synthesis unit that converts the response information output from the interactive AI into speech in response to the input information consisting of the text data converted by the speech recognition unit when it is determined that the input information does not indicate an operation instruction for the in-vehicle device; and a voice output unit that outputs the voice converted by the voice synthesis unit; a second input control unit that inputs the text data converted by the voice recognition unit, a command to determine whether the text data indicates an operation instruction for the in-vehicle device, and a command to transmit the response information corresponding to the text data if the text data does not indicate the operation instruction, as the input information to the interactive AI; the device control unit, upon receiving the response information indicating an operation instruction for the in-vehicle device from the interactive AI, controls the in-vehicle device in accordance with the operation instruction; When the response information indicating that the response information does not indicate an operation instruction for the in-vehicle device is input from the dialogue AI, the speech synthesis unit converts the response information according to the text data into speech. It is a dialogue system for vehicles. [Effects of the Invention]

[0007] The vehicle dialogue system according to the present invention has the advantage that it is possible to operate vehicle-mounted equipment using voice, and that it is possible to provide natural responses to utterances that are not intended to operate vehicle-mounted equipment, such as casual conversation.

[0008] The present invention has been briefly described above. The details of the present invention will become clearer by reading the following detailed description of the invention (hereinafter referred to as "embodiments") with reference to the accompanying drawings. [Brief explanation of the drawings]

[0009] [Figure 1]FIG. 1 is a block diagram showing an embodiment of a vehicle dialogue system according to the present invention. [Figure 2] FIG. 2 is a diagram showing an example of a data table stored in the ROM shown in FIG. [Figure 3] FIG. 3 is a diagram showing the periphery of an instrument panel of a vehicle equipped with the vehicular dialogue system shown in FIG. [Figure 4] FIG. 4 is a flowchart showing a processing procedure of the microcomputer constituting the vehicle communication system shown in FIG. 1 in the first embodiment. [Figure 5] FIG. 5 is an explanatory diagram for explaining the operation in Sp5 of FIG. [Figure 6] FIG. 6 is a flowchart showing a processing procedure of the microcomputer constituting the vehicle communication system shown in FIG. 1 in the second embodiment. [Figure 7] FIG. 7 is a block diagram of a vehicle dialogue system according to another embodiment. [Figure 8] FIG. 8 is a block diagram of a vehicle dialogue system according to another embodiment. [Figure 9] FIG. 9 is a block diagram of a vehicle dialogue system according to another embodiment. [Figure 10] FIG. 10 is a diagram showing another example of the data table stored in the ROM shown in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0010] (First embodiment) A first embodiment of the present invention will be described below with reference to the drawings.

[0011] The vehicle dialogue system 1 of the first embodiment is a system that is mounted on a vehicle and that dialogues with the driver using a dialogue type AI (Artificial Intelligence) 10. The dialogue type AI 10 is configured, for example, by ChatGPT, and when input information S1 made up of text data is input, it outputs response information S2 made up of text data.

[0012] The vehicle dialogue system 1 includes a microphone 2 as a voice input unit, a communication module 3, a microcomputer 4 (hereinafter abbreviated as "microcomputer 4"), a speaker 5 as a voice output unit, a display 6, and a ROM (Read Only Memory) 7 (storage unit). The microphone 2 inputs the voice uttered by the driver to the microcomputer 4. The communication module 3 is for communicating with an interactive AI 10 via an Internet communication network (not shown), and is composed of a circuit, an antenna, etc. for connecting to the Internet communication network. In this embodiment, the communication module 3, the microcomputer 4, and a ROM 7 (described later) are mounted on the same control board 100.

[0013] The microcomputer 4 has a memory such as a RAM (Random Access Memory) or a ROM, and a CPU (Central Processing Unit) that operates according to a program stored in the memory, and controls the entire vehicle dialogue system 1.

[0014] The microcomputer 4 has a voice recognition unit 41, a voice dialogue unit 42, a voice synthesis unit 44, and a drawing processing unit 45. The voice recognition unit 41 converts the voice input by the microphone 2 into text data and inputs it to the voice dialogue unit 42. The voice dialogue unit 42 inputs the text data converted by the voice recognition unit 41 to the interactive AI 10 as input information S1.

[0015] Vehicle information S3 and person information S4 are also input to the voice dialogue unit 42. The microcomputer 4 is connected to sensors and devices mounted on the vehicle via a communication network such as a CAN (Controller Area Network) provided on the vehicle. The vehicle information S3 is information indicating the state of the vehicle obtained from the sensors and devices mounted on the vehicle.

[0016] As shown in Fig. 2, the ROM 7 stores a data table consisting of operation instructions for the in-vehicle device 11, instruction text data corresponding to the operation instructions for the in-vehicle device 11, and response text data corresponding to the instruction text data. In the example shown in Fig. 2, one instruction text data is stored for one operation instruction, but this is not limited to this. A plurality of instruction text data may be stored for one operation instruction. For example, the operation instruction "air conditioner ON" may be associated with instruction text data such as "hot" and "cold" in addition to "turn on the air conditioner."

[0017] In addition, the voice dialogue unit 42 receives input of human information S4, which is the detection result from a driver monitor that detects the driver's state (whether the driver is dozing, driving aimlessly, or looking away from the road) based on an image of the driver's face.

[0018] The voice dialogue unit 42 is also connected to an in-vehicle device 11 mounted on the vehicle, and can control the in-vehicle device 11. The in-vehicle device 11 may be, for example, an air conditioner mounted on the vehicle, a motor for opening and closing windows, a headlight, an ECU (Electronic Control Unit) for controlling an ACC (Adaptive Cruise Control) function, and the like.

[0019] The voice dialogue unit 42 functions as a determination unit, and compares the text data converted by the voice recognition unit 41 with the instruction text data shown in Fig. 2, and if there is a match, determines that the text data converted by the voice recognition unit 41 indicates an operation instruction for the in-vehicle device 11. If there is no match, the voice dialogue unit 42 determines that the text data converted by the voice recognition unit 41 does not indicate an operation instruction for the in-vehicle device 11.

[0020] If the voice dialogue unit 42 determines that the text data indicates an operation instruction for the in-vehicle device 11, it functions as a device control unit and controls the in-vehicle device 11 in accordance with the operation instruction corresponding to the compared instruction text data. Also, if the voice dialogue unit 42 determines that the text data indicates an operation instruction for the in-vehicle device 11, it inputs response text data corresponding to the matched instruction text data to the voice synthesis unit 44.

[0021] If the voice dialogue unit 42 determines that the response text data does not indicate an instruction to operate the in-vehicle device 11, it transmits a prompt including the text data converted by the voice recognition unit 41 as input information S1 to the interactive AI 10. The voice dialogue unit 42 receives response information S2 from the interactive AI 10 and outputs the received response information S2 to the voice synthesis unit 44. The voice synthesis unit 44 converts the response text data and the response information S2 into voice and outputs it to the speaker 5. The speaker 5 outputs the voice converted by the voice synthesis unit 44.

[0022] While the voice dialogue unit 42 is outputting voice from the speaker 5, it outputs a display request to the drawing processing unit 45 to display a character on the display 6. The display 6 is disposed on the instrument panel between the driver's seat and the passenger seat, as shown in Fig. 3. The drawing processing unit 45 outputs to the display 6 an image that makes it appear as if the character is speaking the voice output from the speaker 5.

[0023] Next, the operation of the vehicle dialogue system 1 configured as described above will be described with reference to the flowchart shown in Fig. 4. When the microcomputer 4 detects that the vehicle dialogue system 1 is turned on, such as when the ignition is turned on, it starts the processing shown in Fig. 4. First, the microcomputer 4 enters a standby state until the driver starts speaking (Sp1). When the driver speaks (Y in Sp2), the microcomputer 4 performs a voice recognition process to convert the driver's voice into text data (Sp3).

[0024] If the speech has not ended (N in Sp4), the microcomputer 4 returns to Sp3 and continues the speech recognition process. On the other hand, if the speech has ended (Y in Sp4), the microcomputer 4 performs a determination process to determine whether the text data of the speech converted by the speech recognition process indicates an operation instruction for the in-vehicle device 11 (Sp5).

[0025] In the determination process, the microcomputer 4 compares the voice text data with the plurality of instruction text data shown in Fig. 2 one by one. For example, if the voice text data is "Turn on the ACC," the microcomputer 4 compares it with the instruction text data "Turn on the air conditioner," "Open the windows," "Turn on the headlights," and "Turn on the ACC" in order, as shown in Fig. 5.

[0026] If there is instruction text data that matches the text data of the voice, the microcomputer 4 determines that the text data of the voice indicates an operation instruction for the in-vehicle device 11. The microcomputer 4 is not limited to determining that the text data matches perfectly, and may determine that the text data matches when the word matching rate is equal to or greater than a certain value.

[0027] Next, if the microcomputer 4 determines through the determination process that the text data of the voice indicates an operation instruction for the in-vehicle device 11 (Y in Sp6), it controls the in-vehicle device 11 according to the operation instruction corresponding to the matching instruction text data (Sp7). For example, if the microcomputer 4 determines through the determination process that the text data of the voice matches the instruction text data "Turn on the ACC function," it transmits a request to turn on the ACC function to the ECU that controls the ACC function according to the operation instruction.

[0028] Next, the microcomputer 4 obtains response text data corresponding to the matched instruction text data from the data table (Sp8). Next, the microcomputer 4 performs speech synthesis processing to convert the obtained response text data into voice and output it from the speaker 5, and after reading out the response text data (Sp9), proceeds to Sp10. For example, if the voice text data matches the instruction text data "Turn on the ACC function" in the determination processing, the microcomputer 4 obtains response text data in Sp8 that reads out "ACC has been turned on. The speed is set to XX km / h and the vehicle distance is set to close," and the response text data is read out from the speaker 5.

[0029] On the other hand, if the microcomputer 4 determines through the determination process that the text data of the voice does not indicate an operation instruction for the in-vehicle device 11 (N in Sp6), it creates a prompt including the text data of the voice (Sp11). In Sp11, the microcomputer 4 may create only the text data of the voice as the prompt, or may create a prompt by adding text data corresponding to the vehicle information S3 and the person information S4 to the text data of the voice.

[0030] Next, the microcomputer 4 functions as a first input control unit and sends the created prompt as input information S1 to the interactive AI 10 (Sp12). When the microcomputer 4 receives response information S2 from the interactive AI 10 (Y in Sp13), it converts the received response information S2 into voice and outputs it from the speaker 5, reading out the response information S2 (Sp14), and then proceeds to Sp10.

[0031] In Sp10, if the microcomputer 4 detects that the vehicle dialogue system 1 is off, such as when the ignition is off (Y in Sp10), it ends the process. If the microcomputer 4 does not detect that the vehicle dialogue system 1 is off (N in Sp10), it returns to Sp1 and waits for the driver to speak again.

[0032] According to the above-described embodiment, the microcomputer 4 determines whether the text data of the voice indicates an operation instruction for the in-vehicle device 11, and if it determines that the text data of the voice indicates an operation instruction for the in-vehicle device 11, it controls the in-vehicle device 11 in accordance with the operation instruction. If the microcomputer 4 determines that the text data does not indicate an operation instruction for the in-vehicle device 11, it transmits a prompt including the text data of the voice to the interactive AI 10. This allows the vehicular dialogue system 1 to operate the in-vehicle device 11 by voice, and furthermore, it can respond naturally to utterances that are not intended to operate the in-vehicle device 11, such as casual conversation.

[0033] According to the above-described embodiment, instruction text data is stored in the ROM 7. The microcomputer 4 compares the instruction text data with the voice text data, and determines whether the instruction text data indicates an operation instruction for the in-vehicle device 11 based on whether there is matching instruction text data. This allows the microcomputer 4 to easily determine whether the voice text data indicates an operation instruction for the in-vehicle device 11.

[0034] According to the above-described embodiment, response text data is stored in the ROM 7. When the microcomputer 4 determines that the response text data indicates an operation instruction for the in-vehicle device 11, the microcomputer 4 converts the response text data corresponding to the matching instruction text data into voice and reads it out loud. This allows the microcomputer 4 to respond appropriately when the driver issues an operation instruction to the in-vehicle device 11.

[0035] (Second embodiment) Next, a second embodiment will be described.

[0036] The vehicle dialogue system 1 of the second embodiment has the same configuration as the vehicle dialogue system 1 of the first embodiment shown in Fig. 1, so a detailed description thereof will be omitted here. In the first embodiment, the voice dialogue unit 42 functions as the determination unit, but in the second embodiment, the dialogue AI 10 functions as the determination unit.

[0037] Next, the operation of the vehicle dialogue system 1 of the second embodiment will be described with reference to the flowchart shown in Fig. 6. When the microcomputer 4 detects that the vehicle dialogue system 1 is turned on, such as when the ignition is turned on, the microcomputer 4 starts the processing shown in Fig. 6. First, the microcomputer 4 acquires information about the on-board devices installed in the vehicle (on-board device information) from vehicle information S3 acquired from a CAN (Controller Area Network) or the like (Sp21). Next, the microcomputer 4 generates and transmits a prompt to notify the acquired on-board device information to the interactive AI 10 (Sp22).

[0038] An example of a prompt sent by SP22 will be described. The microcomputer 4 converts the acquired in-vehicle device information into text data. Then, the microcomputer 4 generates a prompt by adding the converted text data of the in-vehicle device information between, for example, a standard phrase: "You are now in a car. The vehicle is equipped with... functions. Please answer the following questions taking this information into consideration," and the standard phrase: "You are now in a car. The vehicle is equipped with... functions. Please answer the following questions taking this information into consideration," and the text data is sent to the conversational AI 10.

[0039] Thereafter, the microcomputer 4 enters a standby state until the driver starts speaking (Sp23). When the driver speaks (Y in Sp24), the microcomputer 4 performs a voice recognition process to convert the driver's voice into text data (Sp25).

[0040] If the speech has not ended (N in Sp26), the microcomputer 4 returns to Sp25 and continues the speech recognition process. On the other hand, when the speech has ended (Y in Sp26), the microcomputer 4 functions as a second input control unit, generates a prompt including text data of the speech converted by the speech recognition process, a command to determine whether the text data indicates an operation instruction for the in-vehicle device 11, and, if the text data does not indicate an operation instruction, a command to send response information corresponding to the text data (Sp27), and transmits the generated prompt (Sp28).

[0041] An example of a prompt sent by SP28 is explained below. Microcontroller 4 generates and sends a prompt with the following text data added to the voice text data: "Is this content intended for operation? If it is intended for operation, answer 'A'. If not, answer so that the conversation can proceed. However, please do not answer 'No'."

[0042] When the microcomputer 4 receives response information S2 from the interactive AI 10 (Y in Sp29), it determines whether to indicate an operation instruction based on the response information S2 (Sp30). For example, if the microcomputer 4 sends a prompt in Sp28 saying, "Is 'Turn on the wipers' intended to be an operation? If it is intended to be an operation, answer 'A'. If not, please answer in a way that will establish a conversation. However, please do not answer 'No'," and receives response information S2 of 'A' in response, the microcomputer 4 determines that it is an operation instruction (Y in S30).

[0043] If it is determined to be an operation instruction (Y in Sp30), the microcomputer 4 compares the text data converted by the voice recognition unit 41 with the instruction text data shown in Fig. 2, and controls the in-vehicle device 11 according to the operation instruction corresponding to the matching instruction text data (Sp31). Next, the microcomputer 4 obtains response text data corresponding to the matching instruction text data from the data table in Fig. 2 (Sp32). The microcomputer 4 performs a voice synthesis process to convert the obtained response text data into voice and output it from the speaker 5, and reads out the response text data (Sp33), after which the process proceeds to Sp35.

[0044] For example, if microcomputer 4 sends a prompt in Sp28 saying, "Hello. Is this content intended for operation? If it is intended for operation, answer "A." If it is not, answer so that a conversation can be established. However, please do not answer "No."," and receives response information S2 saying, "Hello. I'm happy to talk to you. Is there anything I can ask you or help you with?", microcomputer 4 will determine that this is not an operation instruction (N in S30).

[0045] If the microcomputer 4 determines that the received response information S2 is not an operation instruction, it converts the received response information S2 into voice and outputs it from the speaker 5, reading out the response information S2 (Sp34), and then proceeds to Sp35.

[0046] In Sp35, if the microcomputer 4 detects that the vehicle dialogue system 1 is off, such as when the ignition is off (Y in Sp35), it ends the process. If the microcomputer 4 does not detect that the vehicle dialogue system 1 is off (N in Sp35), it returns to Sp23 and waits for the driver to speak again.

[0047] According to the above-described embodiment, the interactive AI 10 functions as a determination unit. In the first embodiment, whether the text data uttered by the driver is an operation instruction or not, it needs to be compared with each instruction text data in the data table shown in Fig. 2. In contrast, according to the second embodiment, if the text data uttered by the driver is not an operation instruction, it is not necessary to compare it with the instruction text data in the data table shown in Fig. 2, which improves the processing speed and the response speed to the driver's utterances.

[0048] The present invention is not limited to the above-described embodiments, and can be appropriately modified, improved, etc. Furthermore, the material, shape, size, number, location, etc. of each component in the above-described embodiments are arbitrary and not limited as long as they can achieve the present invention.

[0049] According to the above-described embodiment, in the vehicle dialogue system 1 shown in Fig. 1, the dialogue AI 10 communicates with the vehicle dialogue system 1 via the Internet communication network, but this is not limited to this. As in the vehicle dialogue system 1B shown in Fig. 7, the dialogue AI 10B consisting of a microcomputer may be mounted on the control board 100. The vehicle dialogue system 1B shown in Fig. 7 allows dialogue even in a poor communication environment.

[0050] In the vehicle dialogue systems 1 and 1B shown in Figures 1 and 7, the microcomputer 4 functions as a voice recognition unit, but this is not limited to this. As in the vehicle dialogue systems 1C and 1D shown in Figures 8 and 9, the microcomputer 4 may be configured to communicate with a server 12 that functions as a voice recognition unit and a determination unit. The server 12 can access a database (DB) 13 that stores the data table shown in Figure 2.

[0051] In this case, the microcomputer 4 transmits the voice input from the microphone 2 to the server 12. The server 12 converts the received voice into text data and determines whether the voice indicates an instruction to operate the in-vehicle device 11 by referring to a data table stored in the DB 13. The server 12 also transmits the determination result and the voice text data to the microcomputer 4. This eliminates the need for the microcomputer 4 to have the determination functions of the voice recognition unit 41 and the voice dialogue unit 42, thereby reducing the processing load.

[0052] 8 and 9, the microcomputer 4 does not have the speech recognition unit 41, but it may have the speech recognition unit 41. In this case, the microcomputer 4 converts part of the speech into text data in the speech recognition unit 41, and converts the rest of the speech into text data in the server 12. In this case, the processing load on the microcomputer 4 can be reduced compared to when all speech recognition is performed by the microcomputer 4.

[0053] According to the first and second embodiments described above, the microcomputer 4 compares the voice text data with the multiple instruction text data shown in FIG. 2 one by one to determine whether the text data is for operation purposes and, if so, the content of the instruction, but this is not limited to this.

[0054] 10, a data table consisting of operation instructions for the in-vehicle device 11, instruction keywords corresponding to the operation instructions for the in-vehicle device 11, and response text data corresponding to the instruction keywords is stored in the ROM 7. The microcomputer 4 extracts keywords from the text data of the voice, compares the extracted keywords with the instruction keywords, and if there is a match, determines that the purpose of the operation is an operation, and executes the operation instruction corresponding to the matching instruction keyword.

[0055] Here, the features of the above-described embodiment of the vehicle dialogue system according to the present invention will be briefly summarized and listed below in [1] to [5].

[0056] [1] A vehicle dialogue system (1, 1B, 1C, 1D) using a dialogue type AI (10) that outputs response information (S2) made up of text data when input information (S1) made up of text data is input, a voice input unit (2) for inputting voice spoken by the driver; a voice recognition unit (12) that converts the voice input by the voice input unit (2) into text data; an equipment control unit (42) that controls the in-vehicle equipment (11) in response to the operation instruction when the text data converted by the voice recognition unit (12) is determined to represent an operation instruction for the in-vehicle equipment (11); a voice synthesis unit (44) that converts the response information (S2) output from the interactive AI (10) into voice in response to the input information (S1) consisting of the text data converted by the voice recognition unit (12) when it is determined that the input information does not indicate an operation instruction for the in-vehicle device (11); and a voice output unit (5) that outputs the voice converted by the voice synthesis unit (44). Vehicle dialogue system (1, 1B, 1C, 1D).

[0057] According to the vehicle dialogue system (1, 1B, 1C, 1D) having the configuration [1] above, the vehicle-mounted device (11) can be operated by voice, and furthermore, natural responses can be made to utterances that are not intended to operate the vehicle-mounted device (11), such as casual conversation.

[0058] [2] In the vehicle dialogue system (1, 1B, 1C, 1D) described in [1], a determination unit (42, 12) that determines whether the text data converted by the voice recognition unit (12) indicates an operation instruction for the in-vehicle device (11); a first input control unit (42) that inputs the text data converted by the voice recognition unit (12) to the interactive AI (10) as the input information (S1) when the determination unit (42, 12) determines that the text data does not indicate an operation instruction for the in-vehicle device (11), Vehicle dialogue system (1, 1B, 1C, 1D).

[0059] According to the vehicle dialogue system (1, 1B, 1C, 1D) having the configuration [2] above, the determination unit (42, 12) can input text data that does not indicate operational instructions to the dialogue AI (10).

[0060] [3] In the vehicle dialogue system (1, 1B, 1C, 1D) described in [1], a second input control unit (42) that inputs the text data converted by the voice recognition unit (12), a command to determine whether the text data indicates an operation instruction for the in-vehicle device (11), and a command to transmit the response information (S2) corresponding to the text data if the text data does not indicate the operation instruction, as the input information (S1) to the interactive AI (10); When the response information (S2) indicating an operation instruction for the in-vehicle device (11) is input from the interactive AI (10), the device control unit (42) controls the in-vehicle device (11) according to the operation instruction, When the speech synthesis unit (44) receives the response information (S2) from the interactive AI (10) indicating that the response information (S2) does not indicate an operation instruction for the in-vehicle device (11), the speech synthesis unit (44) converts the response information (S2) corresponding to the text data into speech. Vehicle dialogue system (1, 1B, 1C, 1D).

[0061] According to the configuration [3] above, the interactive AI (10) can determine whether the text data indicates an operation instruction, thereby improving the processing capacity.

[0062] [4] In the vehicle dialogue system (1, 1B, 1C, 1D) described in [2], a storage unit (7, 13) for storing instruction text data corresponding to an operation instruction for the in-vehicle device (11); The determination unit (42, 12) compares the instruction text data stored in the storage unit with the text data converted by the voice recognition unit (12), and makes the determination based on whether or not there is any instruction text data that matches. Vehicle dialogue system (1, 1B, 1C, 1D).

[0063] According to the vehicle dialogue system (1, 1B, 1C, 1D) having the configuration [4] above, the determination unit (42, 12) can easily determine whether the text data of the voice indicates an operation instruction for the in-vehicle device (11).

[0064] [5] In the vehicle dialogue system (1, 1B, 1C, 1D) described in [4], The storage unit (7, 13) further stores response text data corresponding to the instruction text data, When the determination unit (42, 12) determines that the instruction text data indicates an operation instruction for the in-vehicle device (11), the determination unit (42, 12) converts the response text data corresponding to the matched instruction text data into the voice by the voice synthesis unit (44). Vehicle dialogue system (1, 1B, 1C, 1D).

[0065] According to the vehicle dialogue system (1, 1B, 1C, 1D) having the above configuration [5], when the driver issues an instruction to operate the in-vehicle device (11), it is possible to respond appropriately. [Explanation of symbols]

[0066] 1,1B,1C,1D Vehicle dialogue system 2 Microphone (audio input) 5. Speaker (audio output section) 7 ROM (memory section) 10 Conversational AI 11 In-vehicle equipment 12 Server (voice recognition unit, judgment unit) 13 DB (storage unit) 41 Voice Recognition Unit 42 Voice dialogue unit (determination unit, device control unit, first input control unit, second input control unit) 44 Speech synthesis unit

Claims

1. A vehicle dialogue system using an interactive AI that outputs response information made up of text data when input information made up of text data is input, a voice input unit for inputting voice spoken by the driver; a voice recognition unit that converts the voice input by the voice input unit into text data; an equipment control unit that, when it is determined that the text data converted by the voice recognition unit indicates an operation instruction for an in-vehicle device, controls the in-vehicle device in accordance with the operation instruction; a speech synthesis unit that converts the response information output from the interactive AI into speech in response to the input information consisting of the text data converted by the speech recognition unit when it is determined that the input information does not indicate an operation instruction for the in-vehicle device; and a voice output unit that outputs the voice converted by the voice synthesis unit; a second input control unit that inputs the text data converted by the voice recognition unit, a command to determine whether the text data indicates an operation instruction for the in-vehicle device, and a command to transmit the response information corresponding to the text data if the text data does not indicate the operation instruction, as the input information to the interactive AI; the device control unit, upon receiving the response information indicating an operation instruction for the in-vehicle device from the interactive AI, controls the in-vehicle device in accordance with the operation instruction; When the speech synthesis unit receives the response information from the interactive AI indicating that the response information does not indicate an operation instruction for the in-vehicle device, the speech synthesis unit converts the response information according to the text data into speech. Vehicle dialogue system.

2. 2. The vehicle dialogue system according to claim 1, a determination unit that determines whether the text data converted by the voice recognition unit indicates an operation instruction for the in-vehicle device; and a first input control unit that, when the determination unit determines that the text data does not indicate an operation instruction for the in-vehicle device, inputs the text data converted by the voice recognition unit as the input information to the interactive AI. Vehicle dialogue system.

3. 3. The vehicle dialogue system according to claim 2, a storage unit for storing instruction text data corresponding to the operation instructions for the in-vehicle device; the determination unit compares the instruction text data stored in the storage unit with the text data converted by the voice recognition unit, and makes the determination based on whether or not there is any instruction text data that matches the instruction text data. Vehicle dialogue system.

4. 4. The vehicle dialogue system according to claim 3, the storage unit further stores response text data corresponding to the instruction text data; When the determination unit determines that the instruction text data indicates an operation instruction for the in-vehicle device, the determination unit converts the response text data corresponding to the matched instruction text data into the voice by the voice synthesis unit. Vehicle dialogue system.

Images