Vehicle-mounted voice engine system and interaction method thereof, vehicle and electronic equipment

Abstract

The invention provides a vehicle-mounted voice engine system and an interaction method thereof, a vehicle and electronic equipment, and the system comprises a first information interaction module group which is used for converting first voice information inputted by a voice receiving module into voice-text information, and transmitting the voice-text information to a target application program; the second information interaction module group is used for receiving feedback information output by the target application program according to the voice-text information and converting the feedback information into first text-voice information; and the voice output module is used for performing voice broadcast according to the first text-voice information. The technical problem solved by the invention is that a vehicle-mounted voice engine system (SDS) is deeply connected with a pre-installed voice assistant App, so that in the process of calling various pre-installed voice assistant App interfaces, the vehicle-mounted voice engine system needs to determine the return value of the interface to confirm the information broadcasted to a user, but the broadcast information is realized by the pre-installed voice assistant App, and the user experience is improved. Therefore, the vehicle-mounted voice engine system repeatedly develops the broadcasting function of the part, and resources are wasted.

Description

Technical Field

[0001] The present application relates to the field of vehicle-mounted technology, and in particular to a vehicle-mounted voice engine system and an interaction method thereof, a vehicle and an electronic device. Background Art

[0002] With the development of technology, cars are becoming more and more intelligent. For example, cars can realize automatic driving, which brings drivers a comfortable, convenient and safe driving experience. At the same time, drivers can also "interact" with cars, such as controlling the car's navigation, playing audio and video, etc. through the in-car voice engine system.

[0003] Specifically, in the existing technology, since the in-vehicle voice engine system is deeply connected to the pre-installed voice assistant application (Application, App), in the process of calling various pre-installed voice assistant App interfaces, the in-vehicle voice engine system needs to clarify the return value of the interface to confirm the information broadcast to the user, but this part of the broadcast information has been implemented by the pre-installed voice assistant App, resulting in the in-vehicle voice engine system repeatedly developing this part of the broadcast function, resulting in a waste of resources. Summary of the invention

[0004] The technical problem to be solved by this application is that since the in-vehicle voice engine system is deeply connected to the pre-installed voice assistant App, and in the process of calling various pre-installed voice assistant App interfaces, the in-vehicle voice engine system needs to clarify the return value of the interface to confirm the information broadcast to the user, but this part of the broadcast information has been realized by the pre-installed voice assistant App, resulting in the in-vehicle voice engine system repeatedly developing this part of the broadcast function, resulting in a waste of resources.

[0005] To solve the above problems, the present application provides a vehicle-mounted voice engine system, which is arranged in a vehicle-mounted system, and the vehicle-mounted system is connected to one or more third-party applications with voice assistant functions; the vehicle-mounted voice engine system includes: a voice receiving module, the voice receiving module is used to receive a first voice message input by a user; a first information interaction module group, the first information interaction module group is used to convert the first voice information input by the voice receiving module into voice-text information, and send the voice-text information to a target application; wherein the target application is at least one of one or more third-party applications associated with the voice-text information; a second information interaction module group, the second information interaction module group is used to receive feedback information output by the target application according to the voice-text information, and convert the feedback information into a first text-voice information; a voice output module, the voice output module is used to perform voice broadcast according to the first text-voice information.

[0006] Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: Different from the vehicle-mounted voice engine device in the related technical scheme, the technical scheme sets a first information interaction module group in the vehicle-mounted voice engine system, and uses the first information interaction module group to identify the first voice information. The specific identification content includes the identity information of one or more third-party applications that can execute the first voice information. After determining the identity information of the third-party application, the first voice information is converted into voice-text information and sent to the target application. The target application performs logical judgment on the voice-text information by its own internal logic. Finally, the generated feedback information is sent to the second information interaction module group, which converts it into the first text-voice information and then sends it to the voice output module. The voice output module broadcasts the feedback result obtained after the target application executes the first voice information.

[0007] It can be seen that the vehicle-mounted voice engine system, in the process of parsing the first voice information, can be understood as playing the role of distributing and relaying the feedback information of the target application, that is, the vehicle-mounted voice engine device in the existing technical solution is deeply involved in the logical processing process of docking with the third-party application. There is no need to re-process and judge the return value fed back by the corresponding interface of the target application, but to make full use of the target application's own processing logic, and only need to broadcast the final result of processing the first voice information through the voice output module through the target application. Thereby, the vehicle-mounted voice engine system is simplified, the logic module for docking and analyzing the return values ​​of various applications is omitted, the interaction process between the vehicle-mounted voice engine system and the third-party application is simplified, the resource utilization rate of the third-party application is improved, the difficulty of developing the vehicle-mounted voice engine system is reduced, and the information interaction capability of the vehicle-mounted voice engine system is improved to a certain extent.

[0008] In one example of the present application, the first information interaction module group includes a first conversion module and an information allocation module; the first conversion module is used to recognize the first voice information to obtain voice-text information; the information allocation module is used to allocate the voice-text information to the target application after receiving the voice-text information; and / or The second information interaction module group includes a second conversion module and an information transfer module; the information transfer module is used to receive feedback information and send the feedback information to the second conversion module; the second conversion module is used to convert the feedback information into first text-voice information.

[0009] Compared with the prior art, the technical effect achieved by adopting this technical solution is: further improving the interaction efficiency between the in-vehicle voice engine system and multiple applications, so as to improve the resource utilization of the applications.

[0010] In one example of the present application, the voice output module is also used to perform voice broadcast based on the second text-voice information after the first information interaction module group determines that the first voice information cannot be matched with one or more third-party applications, wherein the second text-voice information is obtained based on the first voice information.

[0011] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: by broadcasting the second text-voice information by the voice output module, the effect of human-computer interaction is achieved, avoiding the situation where the user has to wait for a long time due to failure to match the target application after outputting the first voice information.

[0012] In one example of the present application, the vehicle-mounted voice engine system includes a noise reduction module, which is used to perform noise reduction processing on the first voice information.

[0013] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: by setting a noise reduction module, the accuracy of the first voice information during the transmission process is improved.

[0014] On the other hand, the present application also provides an interaction method for an in-vehicle voice engine system, which is used for an in-vehicle voice engine system such as in any of the above examples; the interaction method includes: when a first information interaction module group receives a first voice message, the first information interaction module group identifies the first voice message to obtain a recognition result, and determines whether the recognition result matches a target application in one or more third-party applications; if it is determined that the recognition result matches the target application in one or more third-party applications, the first information interaction module group converts the first voice message into a voice-text message and sends it to the target application; when the target application executes a running function instruction that matches the voice-text information according to the voice-text information, the second information interaction module group receives feedback information associated with the running function instruction output by the target application; the second information interaction module group converts the feedback information into a first text-voice message; and the voice output module performs voice broadcasting according to the first text-voice message.

[0015] Compared with the prior art, the technical effect achieved by adopting this technical solution is that the vehicle-mounted voice engine system, in the process of parsing the first voice information, can be understood as playing the role of allocating and relaying the feedback information of the target application, that is, the in-depth participation of the vehicle-mounted voice engine device in the prior art solution in the logical processing process of docking with the third-party application is omitted, and there is no need to re-process and judge the return value fed back by the corresponding interface of the target application, but to make full use of the target application's own processing logic, and only need to broadcast the final result of processing the first voice information through the voice output module through the target application. Thus, the vehicle-mounted voice engine system is simplified, the logical module for docking and analyzing the return values ​​of various applications is omitted, the interaction process between the vehicle-mounted voice engine system and the third-party application is simplified, the resource utilization rate of the third-party application is improved, the difficulty of developing the vehicle-mounted voice engine system is reduced, and the information interaction capability of the vehicle-mounted voice engine system is improved to a certain extent.

[0016] In one example of the present application, when the first information interaction module group receives the first voice information, the first information interaction module group recognizes the first voice information, including: before sending the first voice information to the first information interaction module group, the noise reduction module of the vehicle-mounted voice engine system performs noise reduction processing on the first voice information to obtain the second voice information, and sends the second voice information to the first information interaction module group.

[0017] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: by setting a noise reduction module, the accuracy of the first voice information during the transmission process is improved.

[0018] In one example of the present application, feedback information associated with an execution function instruction output by a target application is received by a second information interaction module group, including: when a voice-text module of the target application receives voice-text information, the target application executes the execution function instruction; and the text-voice module in the target application generates feedback information associated with the execution function instruction.

[0019] In one example of the present application, the interaction method also includes: if it is determined that the recognition result does not match the target application in one or more third-party applications, the vehicle-mounted voice engine system obtains second text-voice information based on the first voice information; and the voice output module performs voice broadcast based on the second text-voice information.

[0020] On the other hand, the present application also provides a vehicle, which includes an in-vehicle voice engine system as in any of the above examples, or the vehicle executes each step of the interaction method as in any of the above examples.

[0021] Compared with the prior art, the technical effect achieved by adopting this technical solution is: it can achieve the corresponding technical effect in any of the above examples, which will not be repeated here.

[0022] On the other hand, the present application also provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement each step of the interaction method in any of the above examples.

[0023] Compared with the prior art, the technical effect achieved by adopting this technical solution is: it can achieve the corresponding technical effect in any of the above examples, which will not be repeated here.

[0024] After adopting the technical solution of this application, the following technical effects can be achieved: (1) In the above-mentioned process of parsing the first voice information, the vehicle-mounted voice engine system can be understood as playing the role of distributing and relaying the feedback information of the target application, that is, the in-depth involvement of the vehicle-mounted voice engine device in the existing technical solution in the logical processing process of docking with the third-party application is omitted, and there is no need to re-process and judge the return value fed back by the corresponding interface of the target application. Instead, the target application's own processing logic is fully utilized, and the final result of processing the first voice information only needs to be broadcast through the voice output module through the target application. Thereby, the vehicle-mounted voice engine system is simplified, the logical module for docking and analyzing the return values ​​of various applications is omitted, the interaction process between the vehicle-mounted voice engine system and the third-party application is simplified, the resource utilization rate of the third-party application is improved, the difficulty of developing the vehicle-mounted voice engine system is reduced, and the information interaction capability of the vehicle-mounted voice engine system is improved to a certain extent; (2) By setting a noise reduction module, the accuracy of the first voice information during the transmission process is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings to be used in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. Figure 1 A schematic diagram of module connections of a vehicle-mounted voice engine system provided in an embodiment of the present application; Figure 2 A flowchart of an interaction method of an in-vehicle voice engine system provided in an embodiment of the present application.

[0026] Description of reference numerals: 100, vehicle voice engine system; 101, voice receiving module; 102, voice output module; 10, first conversion module; 20, information distribution module; 30, second conversion module; 40, information transfer module; 50, noise reduction module; 200. Third-party applications. DETAILED DESCRIPTION

[0027] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0028] See also Figure 1 , which is a module connection diagram of a vehicle-mounted voice engine system 100 provided in an embodiment of the present application. Specifically, the vehicle-mounted voice engine system 100 is arranged in a vehicle-mounted system, and the vehicle-mounted system is connected to one or more third-party applications 200 with voice assistant functions; the vehicle-mounted voice engine system 100, for example, includes a voice receiving module 101, a first information interaction module group, a second information interaction module group and a voice output module 102. The voice receiving module 101 is used to receive a first voice message input by a user; the first information interaction module group is used to convert the first voice message input by the voice receiving module 101 into voice-text information, and send the voice-text information to a target application; wherein the target application is at least one of the one or more third-party applications 200 associated with the voice-text information; the second information interaction module group is used to receive feedback information output by the target application according to the voice-text information, and convert the feedback information into a first text-voice information; the voice output module 102 is used to broadcast the first text-voice information.

[0029] Specifically, the vehicle-mounted voice engine system in the present application may be a speech dialogue system (Spoken Dialogue System, SDS), or may be a vehicle-mounted module or vehicle-mounted system with SDS function, and the present application is not limited to this.

[0030] In a specific example, the plurality of third-party applications 200 may include at least one of the following: a map navigation voice assistant App, an air conditioning voice assistant App, and a music playback voice assistant App. In the existing technical solution, the vehicle-mounted voice engine device and each third-party application 200 are deeply connected, which is specifically manifested in that after the vehicle-mounted voice engine device starts to receive the voice input by the user, in order to ensure that the instructions in the voice content are effectively executed by the relevant third-party application 200, the vehicle-mounted voice engine device and the relevant third-party application 200 need to interact multiple times to realize the effective instruction information in the voice content.

[0031] Specifically, take the third-party application 200 as a map navigation voice assistant App, for example, the voice content sent by the user to the in-vehicle voice engine device is "I want to navigate to destination A". Therefore, the in-vehicle voice engine device calls multiple interfaces between it and the map navigation voice assistant App, and the multiple interfaces include, for example, a first interface, a second interface, and a third interface. Among them, the first interface specifically includes calculating the distance from the current location to destination A; the second interface specifically includes deriving multiple planned routes to reach destination A based on the calculation results of the first interface; the third interface specifically includes starting navigation based on the execution route output according to the selected route feedback from the second interface.

[0032] Further, in combination with the above content, since the vehicle-mounted voice engine device needs to identify and judge the information content fed back by any interface in the map navigation voice assistant App during the process of calling the above-mentioned multiple interfaces, for example, when the information content fed back by the first interface to the vehicle-mounted voice engine device includes "cannot be calculated", the vehicle-mounted voice engine device needs to perform logical operation and calculation on the "cannot be calculated" to determine the actual meaning of the "cannot be calculated", and then draw a summary based on the "cannot be calculated", such as defining it as "navigation failure", and then output it to the user through the voice output module 102 of the vehicle-mounted voice engine device, or broadcast the voice of "navigation failure".

[0033] Of course, the information content fed back by the first interface to the vehicle-mounted voice engine device includes "calculation successful". At this time, the vehicle-mounted voice engine device needs to perform logical operation calculations on the "calculation successful" to determine the actual meaning of "calculation successful". When it is calculated that the statement of "calculation successful" can trigger the second interface, the second interface is called again.

[0034] It can be seen that in the process of implementing the above-mentioned voice command "I want to navigate to destination A", the vehicle-mounted voice engine device makes logical judgments on the return values ​​of various interfaces in different third-party applications 200 connected to it, and the processing of the logical judgment occupies the main memory of the vehicle-mounted voice engine device, which increases the load pressure on the operation of the vehicle-mounted voice engine device. When the voice command received by the vehicle-mounted voice engine device includes complex logic, such as starting or triggering multiple third-party applications 200 at the same time, the load pressure of the vehicle-mounted voice engine device is further increased, such as prone to downtime, which reduces the response rate of the vehicle-mounted voice engine device, thereby reducing the user experience.

[0035] Furthermore, it should be noted that each third-party application 200 is a common voice assistant App on the market, which has logical statements associated with each interface storage. That is to say, for example, in the map navigation voice assistant App, the process of developing the map navigation voice assistant App is completed from extracting the information content in the voice command as the beginning to the final feedback of statements such as "navigation for you", "navigation failed", "navigation successful", etc. as the ending. The in-vehicle voice engine device only calls the third-party application 200. Among them, due to the different expression content of the return value of the same third-party application 200 connected to the in-vehicle voice engine device, the relevant technical solution also needs to customize the corresponding logical judgment according to the different return values ​​of various pre-installed voice assistant apps.

[0036] Therefore, in combination with the content of the present technical solution, which is different from the vehicle-mounted voice engine device in the related technical solution, the present technical solution sets a first information interaction module group in the vehicle-mounted voice engine system 100, and uses the first information interaction module group to identify the first voice information. The specific identification content includes identifying the identity information of the third-party application 200 that can execute the first voice information. After determining the identity information of the relevant third-party application 200, the first voice information is converted into voice-text information and sent to the target application. The target application then performs logical judgment on the voice-text information based on its own internal logic. Finally, the generated feedback information is sent to the second information interaction module group, which converts it into the first text-voice information and then sends it to the voice output module 102. The voice output module 102 broadcasts the feedback result obtained after the target application executes the first voice information.

[0037] It can be seen that the vehicle-mounted voice engine system 100, in the process of parsing the first voice information, can be understood as only playing the role of allocating and relaying the feedback information of the target application, that is, the in-depth participation of the vehicle-mounted voice engine device in the existing technical solution in the logical processing process of docking with the third-party application 200 is omitted, and there is no need to re-process and judge the return value fed back by the corresponding interface of the target application, but to make full use of the target application's own processing logic, and only need to broadcast the final result of processing the first voice information through the voice output module 102 through the target application. In this way, the vehicle-mounted voice engine system 100 is simplified, the logical module for docking and analyzing the return values ​​of various third-party applications 200 is omitted, the interaction process between the vehicle-mounted voice engine system 100 and multiple third-party applications 200 is simplified, the resource utilization rate of the third-party application 200 is improved, the difficulty of developing the vehicle-mounted voice engine system 100 is reduced, and the information interaction capability of the vehicle-mounted voice engine system 100 is improved to a certain extent.

[0038] Preferably, the first information interaction module group includes a first conversion module 10 and an information allocation module 20; the first conversion module 10 is used to recognize the first voice information to obtain voice-text information; the information allocation module 20 is used to allocate the voice-text information to the target application after receiving the voice-text information.

[0039] And / or, the second information interaction module group includes a second conversion module 30 and an information transfer module 40; the information transfer module 40 is used to receive the result information and send the result information to the second conversion module 30; the second conversion module 30 is used to convert the result information into the first text-voice information.

[0040] Among them, the speech-text information is represented by speech converted into text information, and in contrast, the first text-speech information is represented by text converted into speech information. For example, the first conversion module 10 is an automatic speech recognition (Automatic Speech Recognition, ASR) module, that is, a module with the function of converting speech into text, and the information allocation module 20 is also a module with the function of converting speech into text. To facilitate the distinction between the two, the information allocation module 20 can be represented by a general ASR module. In contrast, the second conversion module 30 is a text-to-speech (Text To Speech, TTS) module, that is, a module with the function of converting text into speech, and the information transfer module 40 is also a module with the function of converting text into speech. To facilitate the distinction between the two, the information transfer module 40 can be represented by a general TTS module.

[0041] Preferably, the voice output module 102 is also used to perform voice broadcast according to the second text-voice information after the first information interaction module group determines that the first voice information cannot be matched with one or more third-party applications 200, wherein the second text-voice information is obtained based on the first voice information.

[0042] Preferably, the vehicle-mounted voice engine system 100 includes a noise reduction module 50, and the noise reduction module 50 is used to perform noise reduction processing on the first voice information.

[0043] In another specific example, the target application is, for example, a music playing voice assistant App. The interaction between the in-vehicle voice engine system 100 and the music playing voice assistant App is as follows: the in-vehicle voice engine system 100 obtains the user's voice recording data, that is, the first voice information, the specific content of the first voice information is "I want to listen to today's private sharing in Kugou Music", and after the voice recording data is processed by ECNR noise reduction, it is transmitted to the first conversion module 10, and the first conversion module 10 recognizes the audio of the voice recording data, and transmits the recognition result, for example, including "I want to listen to today's private sharing in Kugou Music" to the information distribution module 20, and the information distribution module 20 distributes the result to the ASR module of the music playing voice assistant App, and then the music playing voice assistant App starts to play "Today's Private Sharing", and then the music playing voice assistant App transmits the TTS text that it needs to broadcast, for example, "OK, it has been played for you" back to the information transfer module 40, and then the information transfer module 40 transmits the TTS text to the second conversion module 30, and then the second conversion module 30 broadcasts "OK, it has been played for you".

[0044] On the other hand, the embodiment of the present application also provides an interactive method of the vehicle-mounted voice engine system 100. Specifically, the interactive method is used for the vehicle-mounted voice engine system 100 in the above embodiment; Figure 2 , the interaction methods include, for example: S1, when the first information interaction module group receives the first voice information, the first information interaction module group recognizes the first voice information to obtain a recognition result, and determines whether the recognition result matches a target application in one or more third-party applications 200; S2, if it is determined that the recognition result matches the target application in one or more third-party applications 200, the first information interaction module group converts the first voice information into a voice-text information and sends it to the target application; S3, when the target application executes the running function instruction matched thereto according to the voice-text information, the second information interaction module group receives feedback information associated with the running function instruction output by the target application; S4, the second information interaction module group converts the feedback information into first text-voice information; S5, the voice output module 102 performs voice broadcasting according to the first text-voice information.

[0045] Preferably, when the first information interaction module group receives the first voice information, the first information interaction module group identifies the first voice information, specifically including: In S11, before sending the first voice information to the first information interaction module group, the noise reduction module 50 of the vehicle voice engine system 100 performs noise reduction processing on the first voice information to obtain the second voice information, and sends the second voice information to the first information interaction module group.

[0046] Preferably, the second information interaction module group receives feedback information associated with the running function instruction output by the target application, specifically including: S31, when the voice-text module of the target application receives the voice-text information, the target application executes the running function instruction. In conjunction with the above-mentioned specific example of the music playing voice assistant App, the content of the second text-voice information specifically includes "this function is not supported yet".

[0047] S32, the text-speech module in the target application generates feedback information associated with the running function instruction.

[0048] Preferably, the interaction method further comprises: S21, if it is determined that the recognition result does not match the target application in one or more third-party applications 200, the vehicle voice engine system 100 obtains second text-voice information according to the first voice information. For example, the second text-voice information includes text content such as "recognition failed" or "recognition announcement".

[0049] The voice output module 102 performs voice broadcasting according to the second text-voice information.

[0050] On the other hand, an embodiment of the present application further provides a vehicle. Specifically, the vehicle, for example, includes the in-vehicle voice engine system 100 as in the above embodiment, or executes each step of the interaction method as in the above embodiment.

[0051] On the other hand, an embodiment of the present application also provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the various steps of the interaction method in the above embodiment.

[0052] Specifically, the memory can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a third-party application 200 required for the function, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0053] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A vehicle-mounted voice engine system, wherein the vehicle-mounted voice engine system is arranged in a vehicle-mounted system, and the vehicle-mounted system is connected to one or more third-party applications with voice assistant functions; characterized in that: The vehicle-mounted voice engine system comprises: A voice receiving module, the voice receiving module is used to receive first voice information input by a user; A first information interaction module group, the first information interaction module group is used to convert the first voice information input by the voice receiving module into voice-text information, and send the voice-text information to a target application; wherein the target application is at least one of the one or more third-party applications associated with the voice-text information; a second information interaction module group, the second information interaction module group being used to receive feedback information output by the target application according to the voice-text information, and to convert the feedback information into first text-voice information; A voice output module is used to perform voice broadcasting according to the first text-voice information.

2. The vehicle-mounted voice engine system according to claim 1, characterized in that: The first information interaction module group includes a first conversion module and an information distribution module; The first conversion module is used to recognize the first voice information to obtain the voice-text information; The information distribution module is used to distribute the voice-text information to the target application after receiving the voice-text information; and / or The second information interaction module group includes a second conversion module and an information transfer module; The information transfer module is used to receive the feedback information and send the feedback information to the second conversion module; The second conversion module is used to convert the feedback information into the first text-speech information.

3. The vehicle-mounted voice engine system according to claim 2, characterized in that: The voice output module is also used to perform voice broadcast according to second text-voice information after the first information interaction module group determines that the first voice information cannot be matched with the one or more third-party applications, wherein the second text-voice information is obtained based on the first voice information.

4. The vehicle-mounted voice engine system according to any one of claims 1 to 3, characterized in that: The vehicle-mounted voice engine system further includes a noise reduction module, which is used to perform noise reduction processing on the first voice information.

5. An interactive method for a vehicle-mounted voice engine system, characterized in that: The interaction method is used for the vehicle-mounted voice engine system according to any one of claims 1 to 4; the interaction method comprises: When the first information interaction module group receives the first voice information, the first information interaction module group recognizes the first voice information to obtain a recognition result, and determines whether the recognition result matches a target application in the one or more third-party applications; If it is determined that the recognition result matches a target application among the one or more third-party applications, the first information interaction module group converts the first voice information into the voice-text information and sends it to the target application; When the target application executes the running function instruction matched therewith according to the voice-text information, the second information interaction module group receives the feedback information associated with the running function instruction output by the target application; The second information interaction module group converts the feedback information into the first text-voice information; The voice output module performs voice broadcasting according to the first text-voice information.

6. The interactive method according to claim 5, characterized in that: When the first information interaction module group receives the first voice information, the first information interaction module group recognizes the first voice information, including: Before sending the first voice information to the first information interaction module group, the noise reduction module of the vehicle-mounted voice engine system performs noise reduction processing on the first voice information to obtain second voice information, and sends the second voice information to the first information interaction module group.

7. The interactive method according to claim 5, characterized in that: The receiving, by the second information interaction module group, the feedback information associated with the running function instruction output by the target application program includes: When the speech-text module of the target application receives the speech-text information, the target application executes the running function instruction; The feedback information associated with the execution function instruction is generated by a text-to-speech module in the target application.

8. The interactive method according to any one of claims 5 to 7, characterized in that: The interaction method further comprises: If it is determined that the recognition result does not match the target application in the one or more third-party applications, the in-vehicle voice engine system obtains second text-voice information according to the first voice information; The voice output module performs voice broadcasting according to the second text-voice information.

9. A vehicle, characterized in that: The vehicle includes the in-vehicle voice engine system as described in any one of claims 1-4; or, the vehicle executes each step of the interaction method as described in any one of claims 5-8.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement each step of the interaction method as described in any one of claims 5-8.

Images