Information processing system and information processing method
Patent Information
- Application Number
- CN202310087474.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2022-08-24
- Filing Date
- 2023-01-28
- Publication Date
- 2026-10-27
- Estimated Expiration
- 2043-01-28
AI Technical Summary
[0019]根据本发明,能够提供一种提高了隐私的保护性能的信息处理系统。
Smart Images

Figure CN116778952B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to information processing systems and information processing methods. Background Technology
[0002] Patent document 1 discloses an information processing device equipped with multiple voice agent functions (voice assistant functions) and hands-free calling functions.
[0003] Existing technical documents
[0004] Patent documents
[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-144712 Summary of the Invention
[0006] The problem that the invention aims to solve
[0007] Voice proxy functions are typically activated when the voice received from the microphone contains a wake-up word that serves as a predefined statement. Therefore, the voice received from the microphone is usually always assigned and input to the various voice proxy function units.
[0008] Therefore, for example, during hands-free calls, the voice received from the microphone is also input to the voice proxy function unit. If the call voice contains a wake word, the voice proxy function unit corresponding to that wake word can be activated. In this case, the call content is accidentally input into the already activated voice proxy function unit, which is not preferable from a privacy protection point of view.
[0009] This invention provides an information processing system that improves privacy protection.
[0010] Methods for solving problems
[0011] One aspect of the present invention is an information processing system comprising: a voice acquisition unit that acquires voice; a voice distribution unit that inputs the voice acquired by the voice acquisition unit to a plurality of voice processing units, the plurality of voice processing units receiving and processing the voice; a detection unit that detects the operating state of at least one of the voice processing units; and a control unit that controls the operation of the voice distribution unit, wherein when the detection unit detects a predetermined operating state of a pre-set voice processing unit, the control unit stops the input of voice to at least a portion of the other voice processing units.
[0012] According to other aspects of the invention, at least a portion of the other voice processing units is a proxy function unit that provides voice proxy services by communicating with an external server.
[0013] According to another aspect of the invention, the voice processing unit is a call processing unit for handling hands-free calls, and when the start of a hands-free call is detected in the call processing unit, the control unit stops the input of voice to at least a portion of the other voice processing units.
[0014] According to another aspect of the present invention, when the call processing unit performs the hands-free call, the control unit displays information from the voice processing unit that has received the voice input from the voice distribution unit on a display device.
[0015] According to another aspect of the invention, when the call processing unit performs the hands-free call, the control unit switches the on / off state of the voice input from the voice distribution unit for each of the voice processing units based on a switching instruction input by the user.
[0016] According to another aspect of the invention, the voice processing unit includes a recording unit that records voice in a vehicle-mounted dashcam, and while the call processing unit is performing the hands-free call, the control unit still causes the voice distribution unit to continue inputting the voice to the recording unit.
[0017] Another aspect of the present invention is an information processing method executed by a computer, the information processing method comprising: an acquisition step of acquiring speech; a detection step of detecting the operational state of at least one of a plurality of speech processing units, wherein the plurality of speech processing units receive and process speech; and an input step of inputting the speech acquired in the acquisition step into the speech processing units, wherein in the input step, when a predetermined operational state of one of the speech processing units is detected in the detection step, input of the speech to at least a portion of the other speech processing units is stopped.
[0018] The effects of the invention
[0019] According to the present invention, an information processing system with improved privacy protection performance can be provided. Attached Figure Description
[0020] Figure 1 This is a diagram illustrating the structure of a vehicle control system 1 that includes an information processing system according to an embodiment of the present invention.
[0021] Figure 2 This is a diagram illustrating the structure of an information processing system according to one embodiment of the present invention.
[0022] Figure 3 This is a diagram showing an example of a priority table.
[0023] Figure 4This is an example of a screen displaying voice input information.
[0024] Figure 5 This is a flowchart illustrating the steps of voice assignment processing in an information processing system.
[0025] Label Explanation
[0026] 1: Control system; 2: Central ECU; 3: Communication line; 5: In-vehicle connection link; 6: IVI; 8: Speaker; 9: Microphone; 12: TCU; 15: Touch panel; 16: Display; 17: Touch sensor; 38: Dashcam; 40: Information processing system; 50: First processor; 51: First memory; 52: Camera; 53: Recording unit; 60: Second processor; 61: Second memory; 62: Information providing unit; 63: Voice acquisition unit; 64: Voice distribution unit; 65: Voice... Processing Unit; 65a: Recording Unit; 65b: Proxy Function Unit; 65b1: First Proxy Function Unit; 65b2: Second Proxy Function Unit; 65b3: Third Proxy Function Unit; 65c: Call Processing Unit; 66: Detection Unit; 67: Control Unit; 68: Priority Table; 70: Communication Network; 71, 71a, 71b, 71c: Proxy Server; 72: Voice Input Information Screen; 73a, 73b, 73c, 73d, 73e: Labels; 74a, 74b, 74c, 74d, 74e: Buttons. Detailed Implementation
[0027] Figure 1 This is a diagram showing the vehicle's control system 1.
[0028] The control system 1 includes a central ECU 2 for overall vehicle control and information processing. The central ECU 2 may also have the function of performing OTA (Over-The-Air) management. OTA management includes control related to the following processes: downloading updates for the vehicle's onboard devices from an external server, and applying the downloaded updates to the onboard devices.
[0029] The central ECU2 is connected to communication line 3. Communication line 3 consists of a bus for communication following standards such as CAN and Ethernet (registered trademark), or a communication line for P2P (Peer-to-Peer) communication. Furthermore, communication line 3 can consist of multiple communication lines following the same standard, or multiple communication lines following different standards.
[0030] Communication line 3 connects to the IVI (In-Vehicle Infotainment) system 6, speaker 8, and microphone 9 via in-vehicle connection link 5. Additionally, in-vehicle connection link 5 connects to the TCU (Telematics Control Unit) 12 and touch panel 15. TCU 12 is a wireless communication device conforming to mobile communication system communication standards. Touch panel 15 includes a display 16 and touch sensor 17.
[0031] The IVI6 uses speakers 8, microphones 9, and touch panels 15 to provide various information and entertainment to the vehicle's occupants.
[0032] The in-vehicle connection link 5 consists of multiple communication transmission paths conforming to various communication standards. For example, the in-vehicle connection link 5 may also include multiple network transmission paths. In this case, the multiple network transmission paths can be interconnected via a device with gateway functionality, etc. Additionally, the in-vehicle connection link 5 may also include transmission paths for P2P communication. Various communication buses conforming to various standards can be used for network communication on the network transmission paths. Examples of such standards include CAN, Ethernet, USB (Universal Serial Bus), LIN (Local Interconnect Network), LVDS (Low Voltage Differential Signaling), and other standards.
[0033] The control system 1 also includes a dashcam 38. The dashcam 38 is connected to the in-vehicle connection link 5, and acquires and records the voice received by the microphone 9 via the IVI 6. Hereinafter, the vehicle equipped with the control system 1 will be referred to as "this vehicle", and the user of this vehicle will be referred to as "vehicle user".
[0034] The information processing system 40 of this embodiment includes Figure 1 The control system 1 shown includes IVI6, speaker 8, microphone 9, TCU12, touch panel 15, and dashcam 38.
[0035] Figure 2 This is a diagram showing the structure of the IVI6 and the dashcam 38 in the information processing system 40.
[0036] The dashcam 38 has a first processor 50, a first memory 51, and a camera 52. The first memory 51 is, for example, composed of volatile and / or non-volatile semiconductor memory. The camera 52 acquires images of the vehicle's surrounding environment, including the environment in front of the vehicle.
[0037] The first processor 50 is, for example, a computer equipped with a CPU. The first processor 50 includes a recording unit 65a and a recording unit 53 as functional elements or units. These functional elements can be implemented by executing programs through the first processor 50, which is a computer. Furthermore, the aforementioned computer program can be pre-stored in any computer-readable storage medium. Alternatively, all or part of the aforementioned functional elements of the first processor 50 can be constituted by hardware that each includes one or more electronic circuit components.
[0038] The recording unit 65a acquires and records the speech received by the microphone 9 via the IVI6. Specifically, the recording unit 65a stores the acquired speech data in the first memory 51. Here, the recording unit 65a is equivalent to one of the multiple speech processing units that receive and process speech in this disclosure.
[0039] The recording unit 53 acquires images of the vehicle's surrounding environment as captured by the camera 52. The recording unit 53 then associates the acquired dynamic image data with the audio data acquired by the recording unit 65a and stores it in the first memory 51. Thus, the recording unit 53 records the aforementioned images of the surrounding environment.
[0040] In this embodiment, in addition to providing information and entertainment to the occupants of the vehicle, the IVI6 also functions as an information processing device that controls the distribution of voice acquired from the microphone 9.
[0041] The IVI6 includes a second processor 60 and a second memory 61. The second memory 61 is, for example, composed of volatile and / or non-volatile semiconductor memory. The second processor 60 is, for example, a computer equipped with a CPU. The second processor 60 includes an information providing unit 62, a voice acquisition unit 63, and a voice distribution unit 64 as functional elements or functional units. In addition, the second processor 60 includes a first agent function unit 65b1, a second agent function unit 65b2, a third agent function unit 65b3, and a call processing unit 65c as functional elements or functional units. The second processor 60 also includes a detection unit 66 and a control unit 67 as functional elements or functional units.
[0042] These functional elements can be implemented by executing programs, for example, stored in a second memory 61, through a second processor 60, which functions as a computer. Furthermore, the aforementioned computer program can be pre-stored in any computer-readable storage medium. Alternatively, all or part of the aforementioned functional elements of the second processor 60 can be constituted by hardware that includes one or more electronic circuit components.
[0043] Here, the first proxy function unit 65b1, the second proxy function unit 65b2, the third proxy function unit 65b3, and the call processing unit 65c, together with the aforementioned recording unit 65a, correspond to the multiple voice processing units that receive and process voice in this disclosure. Hereinafter, the first proxy function unit 65b1, the second proxy function unit 65b2, and the third proxy function unit 65b3 will also be collectively referred to as proxy function unit 65b. Furthermore, the recording unit 65a, the proxy function unit 65b, and the call processing unit 65c will be collectively referred to as voice processing unit 65.
[0044] The information providing unit 62 of the second processor 60, according to existing technology, communicates with various network servers (not shown) via the TCU 12 through a communication network 70 such as the Internet, and provides various information and entertainment to the occupants of the vehicle via the speaker 8 and touch panel 15. In addition, the information providing unit 62 communicates with, for example, a GNSS sensor (not shown) to obtain the vehicle's location information, and provides route guidance via the touch panel 15.
[0045] The voice acquisition unit 63 acquires the sounds inside the vehicle, including the voice of the vehicle user, from the microphone 9.
[0046] The voice distribution unit 64 distributes and inputs the voice acquired by the voice acquisition unit 63 to multiple voice processing units 65. In this embodiment, in particular, the voice distribution unit 64, under the control of the control unit 67 (described later), switches the on / off state of the input of the aforementioned voice to each voice processing unit 65. As described above, in this embodiment, the multiple voice processing units 65 are the recording unit 65a, the first proxy function unit 65b1, the second proxy function unit 65b2, the third proxy function unit 65b3, and the call processing unit 65c of the dashcam 38.
[0047] The first agent function unit 65b1, the second agent function unit 65b2, and the third agent function unit 65b3 cooperate with agent servers 71a, 71b, and 71c, which are communicatively connected via a communication network 70 such as the TCU12 and the Internet, to provide voice agent services to vehicle users. Hereinafter, agent servers 71a, 71b, and 71c will also be collectively referred to as agent server 71. In this context, agent servers 71a, 71b, and 71c are equivalent to external servers in this disclosure.
[0048] Voice proxy services, also known as voice assistant services, refer to functions or services that combine speech recognition processing, natural language processing, and other processing methods to appropriately answer user inquiries or requests based on spoken language and perform requested actions. The proxy function unit 65b functions as the user interface for the voice proxy service, for example. In each proxy server 71, speech recognition, text comprehension, response selection, and / or instruction execution are performed on the speech input from the corresponding proxy function unit 65b, and the results are returned to that proxy function unit 65b.
[0049] The first proxy function unit 65b1, the second proxy function unit 65b2, and the third proxy function unit 65b3 cooperate with proxy servers 71a, 71b, and 71c respectively to provide different voice proxy services in accordance with existing technologies. For example, the first proxy function unit 65b1, the second proxy function unit 65b2, and the third proxy function unit 65b3 respectively provide Google Assistant (registered trademark), Alexa (registered trademark), and CarPlay (registered trademark) as voice proxy services.
[0050] Different wake-up words are set in the voice proxy services provided by the first proxy function unit 65b1, the second proxy function unit 65b2, and the third proxy function unit 65b3. When the vehicle user issues the wake-up word of the voice proxy service they wish to use, the proxy function unit 65b corresponding to that voice proxy service begins processing the voice proxy function.
[0051] The call processing unit 65c, in accordance with existing technology, cooperates with the speaker 8, microphone 9, and TCU 12 to provide the vehicle user with hands-free telephone functionality. In this embodiment, in particular, the call processing unit 65c acquires the vehicle user's call voice acquired by the microphone 9 via the voice acquisition unit 63 and the voice distribution unit 64, thereby performing hands-free call processing.
[0052] The detection unit 66 detects the operational status of at least one voice processing unit 65 among the recording unit 65a, the first proxy function unit 65b1, the second proxy function unit 65b2, the third proxy function unit 65b3, and the call processing unit 65c of the dashcam 38. Here, for the recording unit 65a of the dashcam 38, the operational status may include recording execution and recording stop states. Furthermore, for the proxy function unit 65b, the operational status may include a wake-word reception standby state and a voice proxy service execution state after the wake-word is received. Additionally, for the call processing unit 65c, the operational status may include a call in progress state and a call standby state.
[0053] The control unit 67 controls the operation of the voice distribution unit 64 based on the operating state of the voice processing unit 65 detected by the detection unit 66. In this embodiment, in particular, when the detection unit 66 detects a predetermined operating state of a pre-set voice processing unit 65, the control unit 67 stops the input of voice to at least a portion of the other voice processing units 65. Here, at least a portion of the other voice processing units 65 may include at least a portion of the proxy function unit 65b that provides voice proxy services.
[0054] Specifically, when the detection unit 66 detects the start of a call in the call processing unit 65c, i.e., the start of a call in progress, the control unit 67 instructs the voice distribution unit 64 to stop inputting voice to the first proxy function unit 65b1, the second proxy function unit 65b2, and the third proxy function unit 65b3. Therefore, in the information processing system 40, even if the user's voice during a hands-free call provided by the call processing unit 65c contains any of the aforementioned wake words, it is possible to prevent the corresponding proxy function unit 65b from starting processing and transmitting the user's voice outside the vehicle. Thus, the privacy protection performance of the information processing system 40 can be improved.
[0055] Furthermore, in this embodiment, even when the detection unit 66 detects the start and continuation of a call in the call processing unit 65c, the control unit 67 instructs the voice distribution unit 64 to continue inputting voice to the recording unit 65a of the dashcam 38. Thus, in the information processing system 40, for the dashcam 38, which needs to continuously record voice, voice recording can be continuously performed even during hands-free calls.
[0056] For example, the control unit 67 can determine other voice processing units 65 that should stop voice input when any voice processing unit 65 starts operating, based on the priority table 68 pre-stored in the second memory 61. Figure 3 This is a diagram illustrating an example of priority table 68. Figure 3 In the diagram, the first line (excluding the top header line) indicates the priority of the recording unit 65a of the dashcam 38, and the second line indicates the priority of the call processing unit 65c. Furthermore, the third to fifth lines indicate the priorities of the three proxy function units 65b1, 65b2, and 65b3, respectively.
[0057] exist Figure 3 In the example shown, the recording unit 65a of the dashcam 38 is assigned the highest priority "1", and the call processing unit 65c is assigned the second highest priority "2". In addition, the three proxy function units 65b are each assigned the same priority "3".
[0058] When the detection unit 66 detects the start of an action in any voice processing unit 65, the control unit 67 refers to the priority table 68 to determine the priority assigned to the voice processing unit 65 that has started the action, and instructs the voice allocation unit 64 to stop inputting voice to voice processing units 65 that have been assigned the same or lower priority. Thus, in addition to the actions described above, the control unit 67, for example, when the detection unit 66 detects the start of an action in the first proxy function unit 65b1, instructs the voice allocation unit 64 to stop inputting voice to other second proxy function units 65b2 and third proxy function units 65b3.
[0059] In addition, when the call processing unit 65c performs call processing, the control unit 67 displays the information of the voice processing unit 65, which has received voice input from the voice distribution unit, on the touch panel 15, which is a display device. Figure 4 This is an example of a voice input information screen displayed by the control unit 67 on the display 16 of the touch panel 15.
[0060] exist Figure 4 In the voice input information screen 72 shown, labels 73a, 73b, 73c, 73d, and 73e, corresponding to the recording unit 65a, call processing unit 65c, first agent function unit 65b1, second agent function unit 65b2, and third agent function unit 65b3 of the dashcam 38, are displayed with the words "Dashcam", "Hands-free calling", "First agent", "Second agent", and "Third agent". Furthermore, labels 73c, 73d, and 73e corresponding to the first agent function unit 65b1, second agent function unit 65b2, and third agent function unit 65b3, which are not currently receiving voice input from the voice distribution unit 64, are displayed in gray (shown as grid lines in the illustration).
[0061] As a result, vehicle users can confirm the input status of the voice input to each voice processing unit 65, so they don't have to worry about the call being leaked outside the vehicle and can make calls with peace of mind.
[0062] In addition, Figure 4 In the voice input information screen 72 shown, to the right of the illustrations for labels 73a, 73b, 73c, 73d, and 73e, buttons 74a, 74b, 74c, 74d, and 74e are displayed, respectively, for switching the state of voice input from the voice distribution unit 64 to the corresponding voice processing unit 65. Vehicle users can input an on / off switching instruction for voice input to the corresponding voice processing unit 65 by operating these buttons.
[0063] Therefore, when the call processing unit 65c performs call processing, the control unit 67 can switch the on / off state of voice input from the voice distribution unit 64 for each voice processing unit 65 according to the switching instruction input by the vehicle user. For example, if the vehicle user wants to use any voice proxy service during a hands-free call, they can temporarily mute the hands-free call and enable voice input to the desired proxy function unit 65b by using the switching instruction on the button.
[0064] Next, the sequence of actions for allocating voice data from the voice acquisition unit 63 to the voice processing unit 65 in the information processing system 40 will be explained. Figure 5 This is a flowchart illustrating the sequence of voice allocation processing in the information processing system 40. Figure 5 The processing was repeated.
[0065] When processing begins, firstly, the voice distribution unit 64 starts inputting voice data acquired by the voice acquisition unit 63 from the microphone 9 to the voice processing unit 65 (S100). Next, the detection unit 66 determines whether the start of a hands-free call in the call processing unit 65c has been detected (S102). Then, if the start of a call is detected (S102, yes), the control unit 67, referring to the priority table 68, stops the input of voice data to the proxy function unit 65b, which has a priority lower than that assigned to the call processing unit 65c (S104). The control unit 67 instructs the voice distribution unit 64 to stop the voice input.
[0066] Next, the control unit 67 displays the voice input information (i.e., the voice input information) from the voice processing unit 65, which has received the voice input from the voice distribution unit, on the touch panel 15 (S106). This display is, for example, transmitted by the control unit 67. Figure 4 The voice input information screen 72 shown is displayed on the touch panel 15 for input.
[0067] Next, the control unit 67 determines whether the vehicle user has entered a switching instruction for voice input (S108). This switching instruction can be entered, for example, through... Figure 4 The operation of buttons 74a, 74b, 74c, 74d, and 74e on the voice input information screen 72 shown is performed. Then, when a switching instruction is input in step S108 (S108, Yes), the control unit 67 switches the on / off state of the voice input of the corresponding voice processing unit 65 according to the input switching instruction (S110).
[0068] Next, the detection unit 66 determines whether the call has ended (S112). Then, when the call ends (S112, yes), the control unit 67 enables voice input for all voice processing units 65 (S114) and ends the processing.
[0069] On the other hand, if no switching instruction is input in step S108 (S108, No), the process is transferred to step S112. On the other hand, if the call has not ended in step S112 (S112, No), the detection unit 66 returns the process to step S108.
[0070] On the other hand, if no hands-free call is detected to have started in step S102 (S102, No), the detection unit 66 determines whether the operation of any proxy function unit 65b has started (S116). Then, if the operation of the proxy function unit 65b has not started (S116, No), the detection unit 66 returns to step 102 and repeats the process.
[0071] On the other hand, when any agent function unit 65b starts operating (S116: Yes), the control unit 67 refers to the priority table 68 and stops the input of voice to other agent function units 65b (S118).
[0072] Next, the control unit 67 displays the voice input information (i.e., the voice input information) from the voice distribution unit 64 to the voice processing unit 65 on the touch panel 15 (S120). Then, the control unit 67 determines whether the vehicle user has entered a switching instruction for voice input (S122). If a switching instruction has been entered (S122, Yes), the control unit 67 switches the on / off state of the corresponding voice input of the voice processing unit 65 according to the entered switching instruction (S124).
[0073] Next, the detection unit 66 determines whether the action in the proxy function unit 65b, which started in step S116, has ended (S126). Then, if the above action has ended (S126, yes), the control unit 67 transfers the processing to step S114.
[0074] On the other hand, if no switching instruction is input in step S122 (S122, No), the process is transferred to step S126. On the other hand, if the action in the proxy function unit 65b that started in step S116 has not ended in step S126 (S126, No), the detection unit 66 causes the process to return to step S122.
[0075] Furthermore, the present invention is not limited to the structure of the embodiments described above, and can be implemented in various ways without departing from its spirit.
[0076] [Structures supported by the above embodiments]
[0077] The above implementation supports the following structure.
[0078] (Structure 1) An information processing system comprising: a voice acquisition unit that acquires voice; a voice distribution unit that inputs the voice acquired by the voice acquisition unit to a plurality of voice processing units, the plurality of voice processing units receiving and processing the voice; a detection unit that detects the operating state of at least one of the voice processing units; and a control unit that controls the operation of the voice distribution unit, wherein when the detection unit detects a predetermined operating state of a pre-set voice processing unit, the control unit stops the input of the voice to at least a portion of the other voice processing units.
[0079] According to the information processing system of Structure 1, when a voice processing unit starts operating, it is possible to prevent voice from being accidentally input to other voice processing units, thereby improving the privacy protection performance of the information processing system.
[0080] (Structure 2) The information processing system of Structure 1, wherein at least a portion of the other voice processing units is a proxy function unit that provides voice proxy services by communicating with an external server.
[0081] The information processing system according to Structure 2 includes, for example, a proxy server that can prevent user voice from being accidentally leaked outside the vehicle.
[0082] (Structure 3) The information processing system of Structure 1 or 2, wherein the voice processing unit is a call processing unit for handling hands-free calls, and when the start of a hands-free call is detected in the call processing unit, the control unit stops the input of the voice to at least a portion of the other voice processing units.
[0083] According to the information processing system of Structure 3, it is possible to prevent the accidental leakage of vehicle users' private calls to the outside of the vehicle when using a telephone.
[0084] (Structure 4) The information processing system of Structure 3, wherein when the call processing unit performs the hands-free call, the control unit displays the information of the voice processing unit that has received the voice input from the voice distribution unit on the display device.
[0085] According to the information processing system of Structure 4, vehicle users can confirm the input status of voice input to each voice processing unit, so they do not have to worry about the call being leaked to the outside of the vehicle and can make calls with peace of mind.
[0086] (Structure 5) The information processing system of Structure 3 or 4, wherein, when the call processing unit performs the hands-free call, the control unit switches the on / off state of the voice input from the voice distribution unit for each of the voice processing units according to the switching instruction input by the user.
[0087] According to the information processing system of Structure 5, vehicle users can use the desired voice agent service at the desired time, for example, while making a hands-free call.
[0088] (Structure 6) An information processing system of any of the structures 3 to 5, wherein the voice processing unit includes a recording unit that records voice in a vehicle-mounted dashcam, and while the call processing unit is performing the hands-free call, the control unit still causes the voice distribution unit to continue inputting the voice to the recording unit.
[0089] According to the information processing system of Structure 6, even during hands-free calls, the dashcam that needs to record voice continuously can continue to record voice.
[0090] (Structure 7) An information processing method executed by a computer, the information processing method comprising: an acquisition step of acquiring speech; a detection step of detecting the operational state of at least one of a plurality of speech processing units, wherein the plurality of speech processing units receive and process speech; and an input step of inputting the speech acquired in the acquisition step into the speech processing units, wherein in the input step, when a predetermined operational state of one of the speech processing units is detected in the detection step, inputting the speech into at least a portion of the other speech processing units is stopped.
[0091] According to the information processing method of Structure 7, when a voice processing unit starts operating, it is possible to prevent voice from being accidentally input to other voice processing units, thereby improving the privacy protection performance of the information processing system.
Claims
1. An information processing system, comprising: The voice acquisition unit acquires voice data. A voice distribution unit inputs the voice acquired by the voice acquisition unit to multiple voice processing units, which receive and process the voice. The detection unit detects the operational state of at least one of the speech processing units; The control unit controls the operation of the voice distribution unit; The memory pre-stores a priority table that assigns a priority to each of the plurality of speech processing units. When the detection unit detects that a pre-set voice processing unit has started operating, the control unit refers to the priority table, determines the priority assigned to the voice processing unit that has started operating, and stops the input of voice to other voice processing units that have been assigned the same or lower priority as the voice processing unit that has started operating. The voice processing unit includes a recording unit and a proxy function unit. The recording unit records voice messages in a dashcam installed in the vehicle, and the proxy function unit provides voice proxy services by communicating with an external server. The aforementioned voice processing unit is a call processing unit that handles hands-free calls. When a hands-free call is detected to have started in the call processing unit, the control unit refers to the priority table and stops the input of voice to the proxy function unit, which is assigned a lower priority than that assigned to the call processing unit. While the call processing unit is executing the hands-free call, the control unit still causes the voice distribution unit to continue inputting the voice to the recording unit, which is assigned a higher priority than that assigned to the call processing unit.
2. The information processing system according to claim 1, wherein, When the call processing unit performs the hands-free call, the control unit displays the information of the voice processing unit, which has received the voice input from the voice distribution unit, on the display device.
3. The information processing system according to claim 1, wherein, When the call processing unit performs the hands-free call, the control unit switches the on / off state of the voice input from the voice distribution unit for each of the voice processing units according to the switching instruction input by the user.
4. An information processing method, wherein the information processing method is executed by a computer. The information processing method includes: Steps for obtaining voice recordings; A detection step for detecting the operational state of at least one of a plurality of speech processing units, wherein the plurality of speech processing units receive and process speech. as well as The voice obtained in the acquisition step is input into the input step of the voice processing unit. In the input step, when a pre-defined voice processing unit is detected to have started operating in the detection step, a priority table pre-stored in the memory, which assigns a priority to each of the plurality of voice processing units, is used to determine the priority assigned to the voice processing unit that has started operating. Input of voice to other voice processing units assigned the same or lower priority as the one assigned to the voice processing unit is then stopped. The voice processing unit includes a recording unit and a proxy function unit. The recording unit records voice messages in a dashcam installed in the vehicle, and the proxy function unit provides voice proxy services by communicating with an external server. The aforementioned voice processing unit is a call processing unit that handles hands-free calls. When a hands-free call is detected to have started in the call processing unit, the input of voice to the proxy function unit, which is assigned a lower priority than that assigned to the call processing unit, is stopped with reference to the priority table. However, while the call processing unit is executing the hands-free call, the voice continues to be input to the recording unit, which is assigned a higher priority than that assigned to the call processing unit.
Citation Information
Patent Citations
Agent device, control method of agent device, and program
JP2020144712A
Unified microphone pre-processing system and method
CN102595281A
Telephone device having operation function by voice input
US20050100141A1
Pausing functions of an assistant device during an active telephone call
US20180242219A1
Voice interaction method and vehicle using the same
US20210358492A1