Voice interaction method and device, equipment and medium

Through the voice cloud platform, the user's voice data is recognized and processed, and the execution object is judged and processed, the problem of the lack of voice big model dialogue capabilities of the vehicle computer system is solved, and the cloud language interaction capability of the vehicle computer system is realized, reducing the difficulty of driver operation and Improved driving safety.

CN119028345APending Publication Date: 2024-11-26ZHEJIANG GEELY HLDG GRP CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411134845.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Traditional car systems lack the ability to communicate with big voice models, which makes it difficult for drivers to control the on-board system through voice during driving, increasing operational difficulty and safety risks, and it is difficult to update and iterate software.

Method used

Provide a voice interaction method, which receives and recognizes user voice data through the voice cloud platform, determines that the execution object is a cloud server or a vehicle terminal, and performs corresponding processing, supports cloud-based large-model dialogue scenarios, reduces the difficulty of driver operation, and improves driving. Security.

Benefits of technology

It realizes that the car computer system has the language interaction ability of cloud language large models, reduces the difficulty of driver operation, improves driving safety, meets users' intelligent needs, and avoids hardware conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119028345A_ABST
    Figure CN119028345A_ABST
Patent Text Reader

Abstract

The invention discloses a voice interaction method and device, equipment and a medium, and relates to the technical field of cloud services. The method comprises the following steps: receiving voice data sent by a user through the voice cloud platform, and identifying the voice data to obtain a real intention of the user; an execution object corresponding to an execution instruction is judged through the voice cloud platform according to the real intention, wherein the execution object comprises a cloud server side and a vehicle machine side; and sending the execution instruction to the execution object for execution processing through the voice cloud platform. The method can support a cloud large model dialogue scene, and can carry out voice interaction with a vehicle-mounted system, thereby reducing the operation difficulty of a driver, improving the driving safety, and meeting the intelligent demands of a user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of cloud service technology, and in particular to a voice interaction method, device, equipment and medium. Background Art

[0002] At present, it is very common to use the intelligence of car computers to meet various user needs during driving. However, traditional car computers do not have the digital human function of large voice model dialogue ability. To realize these functions, it is usually necessary to integrate advanced hardware and software technologies. There are problems such as high cost, great technical difficulty in implementation, and difficult software update and iteration.

[0003] For the vehicle system, the voice control system is a very important module. Because the current traffic conditions on the road are very complicated, the driver can hardly manually control the vehicle system while driving. If the driver distracts his attention to operate the vehicle screen, it will bring great risks. In order to adapt to the ever-changing user needs and technological development, how to provide a voice cloud system that can support large-scale cloud model dialogue scenarios and can interact with the vehicle system by voice to reduce the driver's operating difficulty, improve driving safety and meet the user's intelligent needs is a technical problem that needs to be solved urgently. Summary of the invention

[0004] Based on this, it is necessary to provide a voice interaction method, device, equipment and medium for at least one of the technical problems mentioned in the above background technology, which can support large-scale cloud model dialogue scenarios and can interact with the vehicle-mounted system through voice to reduce the difficulty of driver operation, improve driving safety and meet the user's intelligent needs.

[0005] The specific technical solutions provided by the embodiments of this application are as follows:

[0006] In a first aspect, a voice interaction method is provided, the method being applied to a voice cloud system, the voice cloud system comprising a voice cloud platform, the method comprising:

[0007] Receiving voice data sent by the user through the voice cloud platform and identifying the voice data to obtain the user's true intention;

[0008] Determine, by the voice cloud platform, the execution object of the corresponding execution instruction according to the real intention, wherein the execution object includes the cloud service end and the vehicle end;

[0009] The execution instruction is sent to the execution object for execution processing through the voice cloud platform.

[0010] Furthermore, the method further comprises:

[0011] Performing speech recognition on the speech data through the speech cloud platform to generate a cloud recognition result;

[0012] The cloud recognition results are semantically understood through the voice cloud platform, and dialogue management is performed on the cloud recognition results and the results of the semantic understanding.

[0013] Furthermore, the voice cloud system further includes an intention analysis module, and the method further includes:

[0014] The intention analysis module analyzes the user's true intention to obtain an analysis result, and calls a cloud service that matches the analysis result based on the analysis result.

[0015] Further, the intention analysis module includes a first dialogue module and a second dialogue module;

[0016] The first dialogue module is used to generate first request information according to the analysis result, send the first request information to the first content provider, and receive first request response information returned by the first content provider;

[0017] The second dialogue module is used to generate second request information according to the analysis result, send the second request information to the second content provider, and receive second request response information returned by the second content provider;

[0018] The intention analysis module is further used to perform arbitration according to the first request response information and the second request response information and generate an arbitration result.

[0019] Furthermore, the voice cloud system also includes a cloud vehicle machine, and the cloud vehicle machine includes: cloud voice middleware and cloud vehicle machine service;

[0020] The method further comprises:

[0021] The cloud voice middleware receives the cloud vehicle machine service request sent by the user and processes the request data in the cloud vehicle machine service request, and the cloud voice middleware calls the corresponding cloud vehicle machine service according to the request data.

[0022] Furthermore, the method further comprises:

[0023] Obtaining the operating status of the cloud vehicle computer through the voice cloud platform;

[0024] When the voice cloud platform detects that the operating state of the cloud vehicle computer is running and the execution object of the current execution instruction is the cloud vehicle computer, the cloud service provided by the cloud vehicle computer is called through the voice cloud platform.

[0025] Furthermore, the cloud vehicle machine service also includes a voice service, and the method further includes:

[0026] If the request data is a request for voice service, the digital human is called up through the cloud voice middleware, and the corresponding voice service is provided by the digital human.

[0027] Furthermore, the cloud vehicle machine service further includes an application service, the cloud vehicle machine further includes an application middleware, and the method further includes:

[0028] If the request data is a request for an application service, the cloud voice middleware sends a call instruction to the application middleware, and the application middleware invokes the corresponding application service according to the call instruction.

[0029] In a second aspect, a voice interaction device is provided, the device comprising:

[0030] A voice module, used to receive voice data sent by the user through the voice cloud platform and recognize the voice data to obtain the user's true intention;

[0031] A function arbitration module, used to determine the execution object of the corresponding execution instruction according to the real intention through the voice cloud platform, and the execution object includes a cloud service end and a vehicle end;

[0032] A processing module is used to send the execution instruction to the execution object for execution processing through the voice cloud platform.

[0033] According to a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0034] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program implements the steps of the above method when executed by a processor.

[0035] The embodiments of the present application have the following beneficial effects:

[0036] A voice interaction method, device, equipment and medium provided in the embodiments of the present application can be free from the hardware conditions of the vehicle-computer system, so that the vehicle-computer has the language interaction capability of the cloud-based language large model. A voice interaction method, device, equipment and medium can be provided, which can support the cloud-based large model dialogue scenario and can perform voice interaction with the vehicle-mounted system to reduce the driver's operating difficulty, improve driving safety and meet the user's intelligent needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 The following is a general flow chart of the voice interaction method provided by the embodiment of the present application;

[0039] Figure 2 A schematic diagram showing the interaction between a voice cloud platform, a vehicle terminal, and a cloud vehicle terminal according to an embodiment of the present application is shown;

[0040] Figure 3 A schematic diagram showing the structure of a voice interaction device provided in an embodiment of the present application is shown;

[0041] Figure 4 An exemplary system is shown that can be used to implement the various embodiments described in this application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] It should be understood that in the description of the present application, unless the context clearly requires otherwise, words such as "include", "comprises", and the like throughout the specification should be interpreted as including rather than being exclusive or exhaustive; that is, as including but not limited to.

[0044] It should also be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, "plurality" means two or more.

[0045] Embodiment 1

[0046] The present application provides a voice interaction method, which is applied to a voice cloud system, wherein the voice cloud system includes a voice cloud platform, Figure 1 , methods include:

[0047] S1. Receive the voice data sent by the user through the voice cloud platform and recognize the voice data to obtain the user's true intention;

[0048] S2, judging the execution object of the corresponding execution command according to the real intention through the voice cloud platform, and the execution object includes the cloud service end and the vehicle end;

[0049] S3. Send the execution instruction to the execution object through the voice cloud platform for execution processing.

[0050] Specifically, the system for providing in-vehicle voice service proposed in the embodiment of the present invention includes a voice cloud system and a vehicle terminal, and the voice cloud system and the vehicle terminal perform voice interaction and cooperate to provide in-vehicle voice service. The system includes a voice cloud platform. First, the vehicle terminal obtains voice data and vehicle information, performs noise elimination on the voice data, and uploads the noise-eliminated voice data and vehicle information to the voice cloud system. The voice cloud system receives the voice data sent by the vehicle terminal, identifies the voice data, and obtains the real intention of the user on the vehicle terminal. The voice cloud system determines the execution object of the corresponding execution instruction according to the real intention of the user. First, the execution object is determined. The execution object includes the cloud service terminal (i.e., the cloud or the voice cloud system or the cloud service under the cloud) and the vehicle terminal, that is, whether it needs to be executed on the cloud service terminal or on the vehicle terminal. If it is executed on the vehicle terminal, the corresponding execution instruction is sent to the vehicle terminal for the vehicle terminal to execute the corresponding execution instruction; if it is executed on the cloud service terminal, the corresponding execution instruction is sent to the corresponding cloud service, and the corresponding execution instruction is executed by calling the cloud service. By adopting such a technical solution, the vehicle computer can be equipped with the language interaction capability of the cloud language large model without being restricted by the hardware conditions of the vehicle computer system. It can provide an in-vehicle intelligent voice interaction solution and support cloud large model dialogue scenarios to reduce the driver's operating difficulty, improve driving safety and meet the user's intelligent needs.

[0051] In some embodiments, the method further comprises:

[0052] Perform speech recognition on the speech data through the speech cloud platform to generate cloud recognition results;

[0053] The cloud recognition results are semantically understood through the voice cloud platform, and dialogue management is performed on the cloud recognition results and the results of semantic understanding.

[0054] Specifically, the voice cloud platform can implement the above method through a voice module. Figure 2 The speech module includes an automatic speech recognition module, a natural language understanding module and a dialogue management module; wherein the automatic speech recognition module is used to perform speech recognition on speech data and generate cloud recognition results; the natural language understanding module is used to perform semantic understanding on the cloud recognition results, and the dialogue management module is used to perform dialogue management on the cloud recognition results and the results of semantic understanding.

[0055] The role of the Dialog Management (DM) module in a multi-turn dialogue system is to control and manage the process of human-computer dialogue, including dialogue state tracking (DST), understanding and responding to user input, task-driven dialogue process, exception handling and failure recovery, and evaluation and optimization. Among them, DST is an important part of DM, which is mainly responsible for maintaining and updating the dialogue state. At every moment of the dialogue, DST will record and update information about the dialogue state, including user needs, intentions, and the current response of the system. DM understands and processes user input through the Natural Language Understanding (NLU) module, and DM will extract the user's intention. After understanding the user's intention, DM will guide and promote the dialogue according to the preset tasks and processes. DM is also responsible for handling abnormal situations that may occur during the dialogue, such as unclear user input and system errors. It needs to design the dialogue process to adapt to these situations and can effectively resume the dialogue to ensure the continuity of the user experience. DM also needs to evaluate the effectiveness of the dialogue and identify possible improvements, such as improved natural language processing capabilities and optimized task processes. The voice cloud platform can integrate ASR (Automatic Speech Recognition), NLU (Natural Language Understanding) and TTS (Text To Speech) modules. The ASR engine is used for text recognition, that is, inputting voice and outputting text information. The NLU engine is used for semantic recognition, and outputs information such as intention. The TTS engine converts text into a voice for playback. By adopting such a technical solution, the voice cloud platform can integrate the functions of the dialogue management module, automatic speech recognition module, natural language understanding module and voice-to-text conversion module, so as to facilitate the recognition of voice data and accurately analyze the real intention of the user on the vehicle side.

[0056] In some implementations, the voice cloud system further includes an intent analysis module, and the method further includes:

[0057] The intention analysis module analyzes the user's true intention to obtain an analysis result, and calls a cloud service that matches the analysis result based on the analysis result.

[0058] In some embodiments, the intent analysis module includes a first dialogue module and a second dialogue module; wherein the first dialogue module is used to generate a first request message according to the analysis result, send the first request message to the first content provider, and receive a first request response message returned by the first content provider; the second dialogue module is used to generate a second request message according to the analysis result, send the second request message to the second content provider, and receive a second request response message returned by the second content provider; the intent analysis module is also used to arbitrate according to the first request response message and the second request response message and generate an arbitration result.

[0059] Specifically, the function arbitration module can be used to perform arbitration for different / multi-party voice services, that is, to select the party with a more reliable result. Exemplarily, the first dialogue module and the second dialogue module can correspond to the first cloud service and the second cloud service, respectively. The first cloud service can be a cloud service provided by a third-party cloud service end, and the second cloud service can be a cloud service provided by a private cloud deployment service end, which is not limited here. The automatic speech recognition module of the first cloud service can be used to perform speech recognition on the user voice audio file to generate a cloud recognition result, and then the first language understanding module and the first dialogue module generate a first request information according to the cloud recognition result, send the first request information to the first content provider, and receive the first request response information returned by the first content provider. The first dialogue module is also used to send the first request response information to the function arbitration module. In the second cloud service, the second request information is generated according to the cloud recognition result by the second language understanding module and the second dialogue module, and the second request information is sent to the second content provider, and the second request response information returned by the second content provider is received, and the second request response information is sent to the function arbitration module. In the function arbitration module, for the received first request response information and the second request response information, arbitration is performed according to the confidence level to generate an arbitration result. The more reliable party can be determined based on the arbitration result, and the more reliable result can be used to provide the user with the corresponding cloud service. In addition, the first dialogue module and the second dialogue module can also correspond to different application scenarios respectively. For example, the first dialogue module can be applied to the video scene to call the corresponding video cloud service, and the second dialogue module can be applied to the audio scene to call the corresponding audio cloud service. It should be noted that the above is only an exemplary description, and it can also be adjusted according to the actual application of the user to match different cloud service combinations and call cloud services that are more suitable for the current user's usage scenario to enhance the user's experience and satisfaction.

[0060] In some implementations, the voice cloud system further includes a cloud vehicle machine, and the cloud vehicle machine includes: cloud voice middleware and cloud vehicle machine service. Based on this, the method further includes:

[0061] The cloud voice middleware receives the cloud vehicle machine service request sent by the user and processes the request data in the cloud vehicle machine service request, and calls the corresponding cloud vehicle machine service according to the request data through the cloud voice middleware.

[0062] In some embodiments, the method further comprises:

[0063] Obtain the operating status of the cloud vehicle computer through the voice cloud platform;

[0064] When the voice cloud platform detects that the operating status of the cloud car machine is running and the execution object of the current execution instruction is the cloud car machine, the cloud service provided by the cloud car machine is called through the voice cloud platform.

[0065] In some implementations, the cloud vehicle service further includes a voice service, and the method further includes:

[0066] If the requested data is for voice service, the digital human is invoked through the cloud voice middleware, and the corresponding voice service is provided through the digital human.

[0067] In some implementations, the cloud vehicle machine service further includes an application service, the cloud vehicle machine further includes an application middleware, and the method further includes:

[0068] If the request data is for requesting an application service, the call instruction is sent to the application middleware through the cloud voice middleware, and the corresponding application service is invoked by the application middleware according to the call instruction.

[0069] For example, the user calls the wake-up word in the car and says: Hello "Xiao Ji". The car-side voice assistant obtains the recording data from the voice receiving medium (such as a microphone), and performs echo cancellation and noise reduction on the sound through the echo cancellation module and the noise reduction processing module. Then, after the car-side voice assistant recognizes the wake-up word, it sends the processed sound to the cloud server, establishes a voice channel between the car and the cloud through the voice cloud platform of the cloud server, and returns a response message to the car computer, prompting the user to continue voice input. After receiving the prompt, the user calls "open the window". The sound is echo-cancelled and noise-reduced on the car side, and the data is sent to the cloud server. The voice cloud platform recognizes the voice data through the integrated dialogue management module, automatic speech recognition module, natural language understanding module, and speech-to-text conversion module, and analyzes the real intention of the car-side user "the user needs to open the window on the car computer". The function arbitration module determines the execution instruction of "open the window" and determines that the execution object is the car computer. After receiving the reply, the voice assistant on the vehicle side sends the data to the voice middleware on the vehicle side. The voice middleware will send the execution command to the vehicle control window middleware. The window middleware will send the command to the corresponding ECU (Electronic Control Unit), and the ECU will execute the specific window opening command.

[0070] For example, the user calls the wake-up word in the car and says: Hello "Xiao Ji". The car-side voice assistant obtains the recording data from the voice receiving medium (such as a microphone), and performs echo cancellation and noise reduction on the sound through the echo cancellation module and the noise reduction processing module. Then, after the car-side voice assistant recognizes the wake-up word, it sends the processed sound to the cloud server, establishes a voice channel between the car and the cloud through the voice cloud platform of the cloud server, and returns a response message to the car-side, prompting the user to continue voice input. After receiving the prompt, the user says "I am in a bad mood today, talk to me about something happy", and the sound is echo-cancelled and noise-reduced on the car side, and the data is sent to the cloud. The voice cloud platform recognizes the voice data through the integrated dialogue management module, automatic speech recognition module, natural language understanding module, and speech-to-text conversion module, and analyzes the real intention of the car-side user "The user is in a bad mood and needs to call the large model chat skill to chat with the user". The function arbitration module determines that the language large model cloud service needs to be called, and the execution object is the cloud server. The cloud service is called through the voice cloud platform of the cloud server, and the corresponding large language model is called through the cloud service. The big model generates reply content according to user needs and returns it to the arbitration module of the voice cloud platform through the interface. The arbitration module returns the reply content to the car-side voice assistant. By adopting such a technical solution, it is possible to distinguish the different execution actions that need to be performed on the car-side and the cloud service side, and meet the user's intelligent needs in different scenarios.

[0071] Exemplarily, after the car-side voice assistant receives a reply, the data is given to the car-machine voice middleware. The voice middleware determines that the reply content needs to be responded to on the cloud-car-machine side according to "Cloud-A", and gives the content to the cloud-car-machine base application. The cloud-car-machine base application gives the voice text content to the cloud voice middleware of the cloud-car-machine based on the voice communication protocol through the voice channel software development kit. The cloud voice middleware parses the communication protocol and processes TTS to evoke the digital human, who interacts with the user through lip syncing and VPA (Virtual Personal Assistant) drive. It should be noted that if the user is triggered to call an application, the cloud voice middleware will give the instruction to the application middleware, and the corresponding application will be evoked through the application middleware. By adopting such a technical solution, it is also possible to distinguish whether the request data is a request for voice service or a request for application service, further refine the cloud service scenario, and meet the user's intelligent needs in more scenarios.

[0072] In this embodiment, the vehicle computer can be equipped with the language interaction capability of the cloud language large model without being restricted by the hardware conditions of the vehicle computer system. A voice interaction method, device, equipment and medium can be provided to support the cloud large model dialogue scenario. At the same time, voice interaction can be performed with the vehicle-mounted system to reduce the difficulty of driver operation, improve driving safety and meet the user's intelligent needs.

[0073] Embodiment 2

[0074] Corresponding to the above embodiment, refer to Figure 3 The present application also provides a voice interaction device, including a voice module, a function arbitration module and a processing module. The voice module is used to receive the voice data sent by the user through the voice cloud platform and identify the voice data to obtain the user's true intention; the function arbitration module is used to determine the execution object of the corresponding execution instruction according to the true intention through the voice cloud platform, and the execution object includes a cloud service end and a vehicle end; the processing module is used to send the execution instruction to the execution object through the voice cloud platform for execution processing.

[0075] Furthermore, the voice module is also used to perform voice recognition on the voice data through the voice cloud platform to generate cloud recognition results; and to perform semantic understanding of the cloud recognition results through the voice cloud platform, and to perform dialogue management on the cloud recognition results and semantic understanding results.

[0076] Furthermore, the voice interaction device also includes an intention analysis module, which is used to analyze the user's true intention to obtain an analysis result, and call a cloud service that matches the analysis result based on the analysis result.

[0077] Further, the intention analysis module includes a first dialogue module and a second dialogue module;

[0078] The first dialogue module is used to generate first request information according to the analysis result, send the first request information to the first content provider, and receive first request response information returned by the first content provider;

[0079] The second dialogue module is used to generate second request information according to the analysis result, send the second request information to the second content provider, and receive second request response information returned by the second content provider;

[0080] The intention analysis module is further used to perform arbitration according to the first request response information and the second request response information and generate an arbitration result.

[0081] Furthermore, the processing module is also used to receive the cloud vehicle machine service request sent by the user through the cloud voice middleware and process the request data in the cloud vehicle machine service request, and call the corresponding cloud vehicle machine service according to the request data through the cloud voice middleware.

[0082] Furthermore, the processing module is also used to obtain the operating status of the cloud car computer through the voice cloud platform; and when the voice cloud platform detects that the operating status of the cloud car computer is running and the execution object of the current execution instruction is the cloud car computer, the cloud service provided by the cloud car computer is called through the voice cloud platform.

[0083] Furthermore, the processing module is also used to wake up the digital human through the cloud voice middleware if the request data is a request for voice service, and provide the corresponding voice service through the digital human.

[0084] Furthermore, the processing module is also used to send a call instruction to the application middleware through the cloud voice middleware if the request data is a request for an application service, and to invoke the corresponding application service according to the call instruction through the application middleware.

[0085] For the specific definition of the voice interaction device, please refer to the definition of the voice interaction method above, which will not be repeated here. Each module in the above-mentioned voice interaction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0086] Embodiment 3

[0087] Corresponding to the above embodiments, the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above voice interaction method can be implemented.

[0088] like Figure 4 As shown, in some embodiments, the system can be used as any of the above-mentioned computer devices for the vehicle-mounted intelligent voice interaction method in each of the embodiments. In some embodiments, the system may include one or more computer-readable media (e.g., system memory or NVM / storage device) having instructions and one or more processors (e.g., (one or more) processors) coupled to the one or more computer-readable media and configured to execute instructions to implement the module to perform the actions described in this application.

[0089] For one embodiment, the system control module may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) and / or any suitable device or component in communication with the system control module.

[0090] The system control module may include a memory controller module to provide an interface to the system memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0091] The system memory may be used, for example, to load and store data and / or instructions for the system. For one embodiment, the system memory may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the system memory may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0092] For one embodiment, the system control module may include one or more input / output (I / O) controllers to provide interfaces to the NVM / storage devices and communication interface(s).

[0093] For example, the NVM / storage device may be used to store data and / or instructions. The NVM / storage device may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0094] The NVM / storage device may include storage resources that are physically part of the device on which the system is installed, or it may be accessible to the device without being part of the device. For example, the NVM / storage device may be accessed over a network via (one or more) communication interfaces.

[0095] The communication interface(s) may provide an interface for the system to communicate over one or more networks and / or with any other suitable device. The system may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and / or protocols.

[0096] For one embodiment, at least one of the processor(s) may be packaged together with the logic of one or more controllers of a system control module (e.g., a memory controller module). For one embodiment, at least one of the processor(s) may be packaged together with the logic of one or more controllers of a system control module to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) may be integrated on the same die with the logic of one or more controllers of a system control module. For one embodiment, at least one of the processor(s) may be integrated on the same die with the logic of one or more controllers of a system control module to form a system on chip (SoC).

[0097] In various embodiments, the system may be, but is not limited to: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the system may have more or fewer components and / or a different architecture. For example, in some embodiments, the system includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (ASIC), and a speaker.

[0098] It should be noted that the present application can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0099] In addition, a part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes but is not limited to source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0100] Communication media include media by which communication signals containing, for example, computer readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media may include guided transmission media such as cables and wires (e.g., fiber optic, coaxial, etc.) and wireless (unguided transmission) media that can propagate energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied as a modulated data signal in, for example, a wireless medium such as a carrier wave or similar mechanism such as embodied as part of spread spectrum technology. The term "modulated data signal" refers to a signal whose one or more characteristics are changed or set in such a manner as to encode information in the signal. Modulation may be analog, digital, or a hybrid modulation technique.

[0101] Here, according to an embodiment of the present application, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to run the methods and / or technical solutions based on the aforementioned multiple embodiments of the present application.

[0102] Embodiment 4

[0103] Corresponding to the above embodiments, the present application also provides a computer-readable storage medium storing computer-executable instructions, and the computer-executable instructions are used to execute the voice interaction method.

[0104] In this embodiment, the computer-readable storage medium may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory, such as random access memory (RAM, DRAM, SRAM); and non-volatile memory, such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, magnetic tapes, CDs, DVDs); or other media now known or developed in the future that can store computer-readable information / data for use by computer systems.

[0105] Although preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they understand the basic creative concepts.

[0106] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A voice interaction method, It is characterized in that The method is applied to a voice cloud system, the voice cloud system includes a voice cloud platform, and the method includes: Receiving voice data sent by the user through the voice cloud platform and identifying the voice data to obtain the user's true intention; Determine, by the voice cloud platform, the execution object of the corresponding execution instruction according to the real intention, wherein the execution object includes the cloud service end and the vehicle end; The execution instruction is sent to the execution object for execution processing through the voice cloud platform.

2. The voice interaction method according to claim 1, It is characterized in that The method further comprises: Performing speech recognition on the speech data through the speech cloud platform to generate a cloud recognition result; The cloud recognition results are semantically understood through the voice cloud platform, and dialogue management is performed on the cloud recognition results and the results of the semantic understanding.

3. The voice interaction method according to claim 1, It is characterized in that The voice cloud system further includes an intention analysis module, and the method further includes: The intention analysis module analyzes the user's true intention to obtain an analysis result, and calls a cloud service that matches the analysis result based on the analysis result.

4. The voice interaction method according to claim 3, It is characterized in that The intention analysis module includes a first dialogue module and a second dialogue module; The first dialogue module is used to generate first request information according to the analysis result, send the first request information to the first content provider, and receive first request response information returned by the first content provider; The second dialogue module is used to generate second request information according to the analysis result, send the second request information to the second content provider, and receive second request response information returned by the second content provider; The intention analysis module is further used to perform arbitration according to the first request response information and the second request response information and generate an arbitration result.

5. The voice interaction method according to claim 1, It is characterized in that The voice cloud system also includes a cloud vehicle machine, and the cloud vehicle machine includes: cloud voice middleware and cloud vehicle machine service; The method further comprises: The cloud voice middleware receives the cloud vehicle machine service request sent by the user and processes the request data in the cloud vehicle machine service request, and the cloud voice middleware calls the corresponding cloud vehicle machine service according to the request data.

6. The voice interaction method according to claim 5, It is characterized in that The method further comprises: Obtaining the operating status of the cloud vehicle computer through the voice cloud platform; When the voice cloud platform detects that the operating state of the cloud vehicle computer is running and the execution object of the current execution instruction is the cloud vehicle computer, the cloud service provided by the cloud vehicle computer is called through the voice cloud platform.

7. The voice interaction method according to claim 5, It is characterized in that The cloud vehicle machine service also includes a voice service, and the method further includes: If the request data is a request for voice service, the digital human is called up through the cloud voice middleware, and the corresponding voice service is provided by the digital human.

8. The voice interaction method according to claim 5, It is characterized in that The cloud vehicle machine service further includes an application service, the cloud vehicle machine further includes an application middleware, and the method further includes: If the request data is a request for an application service, the cloud voice middleware sends a call instruction to the application middleware, and the application middleware invokes the corresponding application service according to the call instruction.

9. A voice interaction device, It is characterized in that The device comprises: A voice module, used to receive voice data sent by the user through the voice cloud platform and recognize the voice data to obtain the user's true intention; A function arbitration module, used to determine the execution object of the corresponding execution instruction according to the real intention through the voice cloud platform, and the execution object includes a cloud service end and a vehicle end; A processing module is used to send the execution instruction to the execution object for execution processing through the voice cloud platform.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.