Method for processing user voice request and related device

Abstract

Embodiments of the present application provide a method for processing a user voice request and a related device, which is applied to a vehicle terminal of a voice control system, the voice control system comprising a cloud server and the vehicle terminal, the cloud server and the vehicle terminal being in communication connection, and the method comprising the following steps: sending received voice information to the cloud server; obtaining first feedback information from the cloud server; determining whether a function indicated by the target text is supported; if not, sending the demand reference text to the cloud server; obtaining second feedback information from the cloud server, the second feedback information comprising operation information of the function indicated by the demand reference text; and displaying the operation information so that the user can realize the function indicated by the demand reference text according to the operation information. In this way, the flexibility of the user in controlling the vehicle through voice information can be enhanced, and the user experience can be improved.

Description

Technical Field

[0001] This application belongs to the field of general data processing technology in the Internet industry, and specifically relates to a method and related apparatus for processing user voice requests. Background Technology

[0002] Currently, with the continuous development of intelligent voice control in vehicles, more and more users are choosing to use intelligent voice to control some functions of their vehicles. However, this requires users to input precise control voice commands. If the user's input is inaccurate, the vehicle will not respond, which makes voice control of the vehicle less flexible and results in a poor user experience. Summary of the Invention

[0003] This application provides a method and related apparatus for processing user voice requests, aiming to enhance the flexibility of vehicle control via voice and improve the user experience.

[0004] In a first aspect, embodiments of this application provide a method for processing user voice requests, applied to an in-vehicle terminal of a voice control system. The voice control system includes a cloud server and the in-vehicle terminal, which are communicatively connected. The method includes the following steps:

[0005] The received voice information is sent to the cloud server, and the voice information is used to instruct control commands for the hardware of the vehicle corresponding to the in-vehicle terminal.

[0006] Obtain first feedback information from the cloud server. The first feedback information includes target text and requirement reference text. The target text is used to indicate user requirements. The target text is associated with the voice information. The requirement reference text is associated with the target text.

[0007] Determine whether the function of the target text indication is supported;

[0008] If not, the required reference text will be sent to the cloud server;

[0009] Obtain second feedback information from the cloud server, the second feedback information including operation information of the function indicated by the requirement reference text;

[0010] The operation information is displayed so that the user can implement the function of the required reference text instruction based on the operation information.

[0011] Secondly, embodiments of this application provide a method for processing user voice requests, applied to a cloud server of a voice control system. The voice control system includes the cloud server and an in-vehicle terminal, which are communicatively connected. The method includes the following steps:

[0012] Acquire voice information from the vehicle terminal, the voice information being used to instruct control commands for the hardware of the vehicle corresponding to the vehicle terminal;

[0013] Analyze the voice information to obtain first feedback information, which includes target text and requirement reference text. The target text is used to indicate the user's requirements and is associated with the voice information. The requirement reference text is associated with the target text.

[0014] If the vehicle terminal does not support the function corresponding to the target semantics, the requirement reference text is obtained from the vehicle terminal.

[0015] Determine the second feedback information corresponding to the requirement reference text, wherein the second feedback information includes the operation information of the function indicated by the requirement reference text;

[0016] The second feedback information is sent to the vehicle terminal, enabling the user to perform the function corresponding to the required reference text based on the operation information.

[0017] Thirdly, embodiments of this application provide an apparatus for processing user voice requests, applied to an in-vehicle terminal of a voice control system. The voice control system includes a cloud server and the in-vehicle terminal, the cloud server and the in-vehicle terminal being communicatively connected. The apparatus includes:

[0018] The first sending unit is used to send the received voice information to the cloud server, wherein the voice information is used to indicate control commands for the hardware of the vehicle corresponding to the vehicle terminal.

[0019] The first acquisition unit is used to acquire first feedback information from the cloud server. The first feedback information includes target text and requirement reference text. The target text is used to indicate user requirements. The target text is associated with the voice information. The requirement reference text is associated with the target text.

[0020] A determining unit is used to determine whether the function of the target text indication is supported;

[0021] The second sending unit is used to send the requirement reference text to the cloud server if no;

[0022] The second acquisition unit is used to acquire second feedback information from the cloud server, the second feedback information including operation information of the function indicated by the requirement reference text;

[0023] The display unit is used to display the operation information, enabling the user to implement the function of the required reference text instruction based on the operation information.

[0024] Fourthly, embodiments of this application provide an apparatus for processing user voice requests, applied to a cloud server of a voice control system. The voice control system includes the cloud server and an in-vehicle terminal, the cloud server and the in-vehicle terminal being communicatively connected. The apparatus includes:

[0025] The first acquisition unit is used to acquire voice information from the vehicle terminal, the voice information being used to instruct control commands for the hardware of the vehicle corresponding to the vehicle terminal.

[0026] An analysis unit is configured to analyze the voice information to obtain first feedback information, the first feedback information including target text and requirement reference text, the target text being used to indicate user requirements, the target text being associated with the voice information, and the requirement reference text being associated with the target text;

[0027] The second acquisition unit is used to acquire the requirement reference text from the vehicle terminal when the vehicle terminal does not support the function corresponding to the target semantics.

[0028] A determining unit is used to determine the second feedback information corresponding to the requirement reference text, wherein the second feedback information includes operation information of the function indicated by the requirement reference text;

[0029] The sending unit is used to send the second feedback information to the vehicle terminal, so that the user can realize the function corresponding to the required reference text according to the operation information.

[0030] Fifthly, embodiments of this application provide an electronic device including a processor, a memory, a communication interface, and one or more programs, the one or more programs being stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the first or second aspects of embodiments of this application.

[0031] In a sixth aspect, embodiments of this application provide a computer storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first or second aspect of this embodiment.

[0032] In a seventh aspect, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first or second aspects of embodiments of this application. The computer program product may be a software installation package.

[0033] As can be seen, in this example, the in-vehicle terminal first sends the received voice information to the cloud server. The voice information is used to instruct control commands for the vehicle's hardware corresponding to the in-vehicle terminal. Then, it obtains first feedback information from the cloud server, which includes target text and a requirement reference text. The target text indicates the user's requirement and is associated with the voice information. The requirement reference text is associated with the target text. Then, it determines whether the function indicated by the target text is supported. If not, the requirement reference text is sent to the cloud server. Next, it obtains second feedback information from the cloud server, which includes operation information for the function indicated by the requirement reference text. Finally, it displays the operation information, enabling the user to implement the function indicated by the requirement reference text. This allows the user to perform the corresponding operation even if they cannot directly control the vehicle based on the user's voice information, while still providing a corresponding operation method. This not only enhances the flexibility of controlling the vehicle via voice information but also improves the user experience. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1a This is a schematic diagram of the composition of a voice control system provided in an embodiment of this application;

[0036] Figure 1b This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0037] Figure 2a This is a flowchart illustrating a method for processing user voice requests provided in an embodiment of this application;

[0038] Figure 2b This is a schematic diagram of the interface of an in-vehicle terminal provided in an embodiment of this application;

[0039] Figure 3 This is a block diagram of the functional units of a device for processing user voice requests provided in an embodiment of this application;

[0040] Figure 4 This is a block diagram of the functional units of another device for processing user voice requests provided in an embodiment of this application;

[0041] Figure 5 This is a block diagram of the functional units of another device for processing user voice requests provided in an embodiment of this application;

[0042] Figure 6 This is a block diagram of the functional units of another device for processing user voice requests provided in an embodiment of this application. Detailed Implementation

[0043] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0044] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0045] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0046] If the user's needs in the voice request cannot be met, the current system will either respond with something like "I don't understand what you're saying" or not respond to the user's needs at all. This approach is rather simplistic and results in a poor user experience, especially for novice users, as it increases the difficulty of operating the system.

[0047] To address the aforementioned issues, this application provides a method and related apparatus for processing user voice requests. The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0048] Please see Figure 1a , Figure 1a This is a schematic diagram of the composition of a voice control system provided in an embodiment of this application. As shown in the figure, the voice control system 10 includes an in-vehicle terminal 101 and a cloud server 102, which are communicatively connected. The cloud server 102 can perform semantic analysis on the voice information from the in-vehicle terminal 101 to obtain the user's control requirements, and send the corresponding semantic analysis results to the in-vehicle terminal 101. The in-vehicle terminal 101 can perform corresponding operations based on the obtained semantic analysis results.

[0049] Please see Figure 1b , Figure 1b This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. As shown in the figure, the electronic device 110 can be the aforementioned vehicle-mounted terminal 101 or the aforementioned cloud server 102. The electronic device 110 includes a processor 120, a memory 130, a communication interface 140, and one or more programs 131. The one or more programs 131 are stored in the aforementioned memory 130 and configured to be executed by the aforementioned processor 120. The one or more programs 131 include instructions for performing any step in the following method embodiments. In specific implementation, the processor 120 is used to perform any step performed by the electronic device in the following method embodiments, and when performing data transmission such as sending, the communication interface 140 can be selectively invoked to complete the corresponding operation.

[0050] Please see Figure 2a , Figure 2a This is a flowchart illustrating a method for processing user voice requests according to an embodiment of this application. The method for processing user voice requests includes a voice control system comprising a cloud server and an in-vehicle terminal, the cloud server and the in-vehicle terminal being communicatively connected, and the method comprising the following steps:

[0051] Step 201: The vehicle terminal sends the received voice information to the cloud server.

[0052] The cloud server acquires voice information from the in-vehicle terminal. This voice information is used to instruct the vehicle's hardware to respond to the in-vehicle terminal. The in-vehicle terminal can be in sleep mode during use, only acquiring ambient voice information upon detecting a wake-up word or action.

[0053] Step 202: The cloud server analyzes the voice information and obtains the first feedback information.

[0054] The in-vehicle terminal receives first feedback information from the cloud server. This first feedback information includes target text and requirement reference text. The target text indicates the user's requirements and is associated with the voice information. The requirement reference text is associated with the target text.

[0055] In one possible instance, the analysis of the voice information to obtain first feedback information includes: performing semantic analysis on the voice information to obtain the target text; acquiring the vehicle's configuration information; and determining the requirement reference text based on the configuration information and the target text.

[0056] Semantic analysis of voice information includes converting voice information into text information, extracting keywords from the text information, and generating target text based on the keywords. For example, if the voice information is "Can you open the sunroof?", the keywords in the text information are "sunroof" and "open", and the target text "open sunroof" can be generated accordingly. Converting the user's voice information into target text increases the success rate of subsequent command recognition by the in-vehicle terminal, improving the intelligence of voice-controlled vehicles. The vehicle's configuration information includes the configuration of the vehicle's hardware devices. The requirement reference text includes control instructions for the hardware corresponding to the user's requirement or control instructions for other hardware related to the user's requirement. This requirement reference text is a standard question format for controlling the vehicle and is set by the developers and stored on a cloud server. When determining the requirement text, first identify the target hardware involved in the target text, then determine whether the vehicle configuration information includes other hardware that has a similar function in the vehicle. If so, obtain the control requirements for the target hardware in the target text, determine whether the other hardware can meet the control requirements, and if so, determine the requirement text based on the control requirements and other hardware.

[0057] For different vehicles, the corresponding reference text for the same target text may differ. For example, if the vehicle's configuration information indicates that it only includes a sunroof and not a panoramic sunroof, then when the target text is "open the panoramic sunroof," the corresponding reference text should be "how to adjust the sunroof." However, if the vehicle's configuration information indicates that it includes a panoramic sunroof, then the corresponding reference text would be "how to adjust the panoramic sunroof." In other words, under specific circumstances, the target text and the reference text are the same. In practice, vehicles can store their configuration information in a cloud server's database, allowing the cloud server to query the database for the configuration information of each connected vehicle, or the in-vehicle terminal can send the vehicle's configuration information to the cloud server simultaneously when sending voice messages.

[0058] As can be seen, in this example, determining the required reference text based on the vehicle's configuration information ensures that even when the in-vehicle terminal does not support the target text function, the obtained operation information can best meet the user's actual needs and improve the user experience.

[0059] Step 203: The vehicle terminal determines whether it supports the function of the target text instruction.

[0060] Specifically, the fact that the in-vehicle terminal supports the function of indicating the target text means that the in-vehicle terminal can control the hardware indicated in the user's voice information and meet the user's control needs for that hardware. For example, if the user's voice information is "rearview mirror heating", and the vehicle supports the rearview mirror heating function via voice, it means that the in-vehicle terminal supports this function. Conversely, if the in-vehicle terminal cannot recognize the target text, or if the in-vehicle terminal does not include a rearview mirror, or if the rearview mirror does not have a heating function, it means that the function of indicating the target text is not supported.

[0061] In one possible instance, the function corresponding to the target text is determined not to be supported if any of the following conditions exist: the vehicle terminal supports parsing the target text, but the hardware associated with the user's needs does not support voice control; or the vehicle terminal supports parsing the target text, but the vehicle does not include the hardware associated with the user's needs; or the vehicle terminal does not support parsing the target text.

[0062] In this solution, the vehicle does not include the hardware associated with the user's requirements. This not only means the main hardware device is missing, but also that specific control over that hardware is not included. For example, if the target text is "heated rearview mirror," but the vehicle does not have a heated rearview mirror function, it can only adjust the rearview mirror, and therefore does not support this function.

[0063] Determining whether the in-vehicle terminal supports parsing the target text means determining whether the in-vehicle terminal can recognize the target text. If the in-vehicle terminal can recognize it, it means that the corresponding control commands in the in-vehicle terminal include the content corresponding to the target text. The control commands corresponding to the in-vehicle terminal can be updated synchronously with the version update of the in-vehicle terminal. That is, if the in-vehicle terminal cannot recognize the target text, the corresponding control commands do not include the function corresponding to the target text, possibly because the version of the in-vehicle terminal has not been updated, and therefore the in-vehicle terminal cannot recognize the target text. For example, for the target text "open the sunroof", if the sunroof of the in-vehicle terminal does not support adjustment via voice and can only be adjusted manually by the user, then the in-vehicle terminal does not support the function corresponding to the target text. If the in-vehicle terminal does not have a sunroof, then the vehicle corresponding to the in-vehicle terminal does not include the hardware mentioned in the target text, and therefore does not support the corresponding function.

[0064] In one possible instance, the method further includes: if the vehicle terminal does not support parsing the target text, the operation information further includes a first prompt message, the first prompt message being used to prompt the user to update the version of the target application in the vehicle terminal to support parsing the target text.

[0065] The target application refers to the application installed on the in-vehicle terminal for controlling the vehicle; that is, the user can control certain functions of the vehicle via voice through the target application. If the target application is not updated, the target text obtained after analyzing and recognizing the user's voice information may be unrecognizable by the terminal, meaning the target application cannot recognize it, thus preventing the user's control needs from being met.

[0066] As can be seen, in this example, when the vehicle terminal does not support parsing the target text, prompting the user to update the version of the target application can prevent the user from misunderstanding that the vehicle cannot perform the corresponding function through voice, thus improving the user experience.

[0067] Step 204: If not, the vehicle terminal will send the required reference text to the cloud server.

[0068] Step 205: The cloud server determines the second feedback information corresponding to the required reference text;

[0069] Step 206: The cloud server sends the second feedback information to the vehicle terminal.

[0070] The in-vehicle terminal receives second feedback information from the cloud server. This second feedback information includes operational information for the function indicated in the requirement reference text. The user can then use this operational information to understand how to control the target hardware, which refers to the hardware corresponding to the requirement reference text. This operational information can be presented in the form of images, text, videos, or animated GIFs. This operational information is stored in the cloud by the developers, and each piece of operational information has corresponding text information. When the requirement reference text matches the text information of a certain operational information, the corresponding operational information is returned to the in-vehicle terminal.

[0071] Step 207: The vehicle terminal displays the operation information.

[0072] As can be seen, in this example, the in-vehicle terminal first sends the received voice information to the cloud server. The voice information is used to instruct control commands for the vehicle's hardware corresponding to the in-vehicle terminal. Then, it obtains first feedback information from the cloud server, which includes target text and a requirement reference text. The target text indicates the user's requirement and is associated with the voice information. The requirement reference text is associated with the target text. Then, it determines whether the function indicated by the target text is supported. If not, the requirement reference text is sent to the cloud server. Next, it obtains second feedback information from the cloud server, which includes operation information for the function indicated by the requirement reference text. Finally, it displays the operation information, enabling the user to implement the function indicated by the requirement reference text. This allows the user to perform the corresponding operation even if they cannot directly control the vehicle based on the user's voice information, while still providing a corresponding operation method. This not only enhances the flexibility of controlling the vehicle via voice information but also improves the user experience.

[0073] In one possible instance, before sending the requirement reference text to the cloud server, the method further includes: if the in-vehicle terminal supports parsing the target text, but the vehicle does not include hardware associated with the user's requirement, outputting a second prompt message, the second prompt message including the requirement reference text; obtaining user feedback information, the feedback information being used to indicate the user's final requirement; and if the user's final requirement matches the requirement indicated by the reference requirement text, sending the requirement reference text to the cloud server.

[0074] Since the requirement reference text is generated based on both the target text and the vehicle's configuration information, if the vehicle does not include the hardware associated with the user's requirements, the operation instructions indicated by the requirement reference text will not be for the hardware associated with the user's requirements. Therefore, when sending the requirement reference text to the cloud server, the user can be asked first whether they want to execute the instructions in the requirement reference text. For example... Figure 2b As shown, the target text is "Open the sunroof". However, since the vehicle's configuration information does not include a sunroof, but it does include a sunroof with a similar function, the required reference text is "How to adjust the sunroof". A second prompt message can be generated based on the required reference text, which could be "This vehicle does not have a sunroof. Do you want to open the sunroof?" If the user confirms, the required reference text will be sent to the cloud server, and the corresponding operation information will be fed back to the electronic device.

[0075] As can be seen, in this example, outputting the second prompt to the user can indirectly inform the user that the vehicle does not have the hardware the user mentioned, while at the same time understanding the user's real needs, avoiding the inability to recognize the user's needs due to the user's mispronunciation, and improving the flexibility of controlling the vehicle by voice.

[0076] In one possible instance, before sending the requirement reference text to the cloud server, the method further includes: determining whether the function corresponding to the requirement reference text is supported; if not, sending the requirement reference text to the cloud server; if yes, performing operations to implement the function corresponding to the requirement reference text.

[0077] The in-vehicle terminal supports the functions corresponding to the required reference text, including recognizing the required reference text, including hardware associated with the user's required needs, and the hardware supporting voice control. If the user confirms that the actual user need corresponds to the content in the required reference text, and if the function of that need can be controlled by voice, and the in-vehicle terminal has already received the text corresponding to that need, it's equivalent to the user sending the voice information corresponding to the actual user need to the in-vehicle terminal. In this case, the function can be executed directly without the user repeating the request. When implementing the function corresponding to the required reference text, the hardware entity and the operation content on that hardware entity in the required reference text are first determined. It is then determined whether the operation content is consistent with the operation content in the target text. If they are inconsistent, an execution statement is generated based on the operation content in the target text and the hardware in the required reference text, and the operation corresponding to the execution statement is executed. For example, if the target text is "open the skylight", then the operation content here is "open". However, if the requirement reference text is "how to adjust the skylight", then the hardware entity is "skylight" and the operation content is "adjust". It can be seen that the operation content in the requirement reference text is different from the operation content in the target text. Therefore, when executing the function corresponding to the requirement reference text, the actual execution statement is "open the skylight".

[0078] As can be seen in this example, if the function corresponding to the requirement reference text can be controlled by voice, it is not necessary to send the operation information to the cloud server. Instead, the vehicle terminal can directly control the vehicle based on the requirement reference text. This means that even if the user's initial voice command is incorrect, as long as the user confirms the correct command later, the user's needs can be met without repeating the command. This improves the intelligence of voice-controlled vehicles and enhances the user experience.

[0079] In one possible instance, the method further includes: if the user's final requirement matches the requirement indicated by the target text, outputting a third prompt message, the third prompt message being used to prompt the user that the vehicle does not support the function corresponding to the user's final requirement.

[0080] In this scenario, after providing the second prompt to the user, if the user insists on requesting the function corresponding to the target text, and the vehicle does not support this function, a third prompt is needed to inform the user that the vehicle does not support this function, in order to avoid the user inputting incorrect voice information again or to prevent the user from perceiving a vehicle malfunction. For example, if the target text is "Open the sunroof," but the vehicle configuration only includes a panoramic sunroof, the determined reference text for the request is "How to adjust the sunroof." The second prompt to the user based on this reference text would be "Do you want to open the panoramic sunroof?" If the user's response is negative, indicating that the user confirms the request is "Open the sunroof," then a third prompt is needed to inform the user that the vehicle currently only has a panoramic sunroof and no sunroof. Therefore, after providing the third prompt, the second prompt can be provided to the user again.

[0081] As can be seen, in this example, when a user insists on controlling hardware not included in the vehicle, informing the user through a third prompt message that the hardware is not included can prevent the user from entering incorrect commands later, and can also help the user correct any misconceptions about the hardware included in the current vehicle, thereby improving the user experience.

[0082] For examples consistent with the above embodiments, please refer to... Figure 3 , Figure 3This is a block diagram of the functional units of a device for processing user voice requests provided in an embodiment of this application. The device 30 for processing user voice requests is applied to an in-vehicle terminal of a voice control system. The voice control system includes a cloud server and the in-vehicle terminal, which are communicatively connected. The device 30 includes: a first sending unit 301, used to send received voice information to the cloud server, the voice information being used to indicate control commands for the hardware of the vehicle corresponding to the in-vehicle terminal; a first acquiring unit 302, used to acquire first feedback information from the cloud server, the first feedback information including target text and requirement reference text, the target text being used to indicate user requirements, the target text being associated with the voice information, and the requirement reference text being associated with the target text; a determining unit 303, used to determine whether the function indicated by the target text is supported; a second sending unit 304, used to send the requirement reference text to the cloud server if not supported; a second acquiring unit 305, used to acquire second feedback information from the cloud server, the second feedback information including operation information for the function indicated by the requirement reference text; and a display unit 306, used to display the operation information, enabling the user to implement the function indicated by the requirement reference text according to the operation information.

[0083] In one possible instance, the function corresponding to the target text is determined not to be supported if any of the following conditions exist: the vehicle terminal supports parsing the target text, but the hardware associated with the user's needs does not support voice control; or the vehicle terminal supports parsing the target text, but the vehicle does not include the hardware associated with the user's needs; or the vehicle terminal does not support parsing the target text.

[0084] In one possible instance, the device 30 is further configured to: when the vehicle terminal does not support parsing the target text, the operation information further includes a first prompt message, the first prompt message being used to prompt the user to update the version of the target application in the vehicle terminal to support parsing the target text.

[0085] In one possible instance, before sending the requirement reference text to the cloud server, the device 30 is further configured to: output a second prompt message, the second prompt message including the requirement reference text, if the vehicle terminal supports parsing the target text but the vehicle does not include hardware associated with the user requirement; obtain user feedback information, the feedback information being used to indicate the user's final requirement; and send the requirement reference text to the cloud server if the user's final requirement matches the requirement indicated by the reference requirement text.

[0086] In one possible instance, before sending the requirement reference text to the cloud server, the device 30 is further configured to: determine whether the function corresponding to the requirement reference text is supported; if not, send the requirement reference text to the cloud server; if yes, perform operations to implement the function corresponding to the requirement reference text.

[0087] In one possible instance, the device 30 is further configured to: output a third prompt message when the user's final requirement matches the requirement indicated by the target text, the third prompt message being used to prompt the user that the vehicle does not support the function corresponding to the user's final requirement.

[0088] It is understood that since the method embodiments and the device embodiments are different presentations of the same technical concept, the content of the method embodiment section in this application should be adapted to the device embodiment section in a synchronous manner, and will not be repeated here.

[0089] In the case of using integrated units, please refer to Figure 4 , Figure 4 This is a functional unit block diagram of another device for processing user voice requests provided in an embodiment of this application. Figure 4 The apparatus 400 for processing user voice requests includes a processing module 412 and a communication module 411. The processing module 412 controls and manages the actions of the apparatus for processing user voice requests, for example, executing the steps of the first sending unit 301, the first acquiring unit 302, the determining unit 303, the second sending unit 304, the second acquiring unit 305, and the display unit 306, and / or executing other processes of the technology described herein. The communication module 411 handles the interaction between the apparatus for processing user voice requests and other devices. Figure 4 As shown, the apparatus for processing user voice requests may further include a storage module 413, which is used to store program code and data of the apparatus for processing user voice requests.

[0090] The processing module 412 can be a processor or controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication module 411 can be a transceiver, RF circuitry, or a communication interface, etc. The storage module 413 can be a memory.

[0091] All relevant content in each scenario involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here. The above-mentioned device 400 for processing user voice requests can perform the above-mentioned... Figure 2a The method shown is for handling user voice requests.

[0092] For examples consistent with the above embodiments, please refer to... Figure 5 , Figure 5 This is a block diagram of the functional units of a device for processing user voice requests provided in an embodiment of this application. The device 50 for processing user voice requests is applied to a cloud server of a voice control system. The voice control system includes the cloud server and an in-vehicle terminal, which are communicatively connected. The device 50 includes: a first acquisition unit 501, used to acquire voice information from the in-vehicle terminal, the voice information being used to indicate control commands for the hardware of the vehicle corresponding to the in-vehicle terminal; an analysis unit 502, used to analyze the voice information to obtain first feedback information, the first feedback information including target text and requirement reference text, the target text being used to indicate user requirements, the target text being associated with the voice information, and the requirement reference text being associated with the target text; a second acquisition unit 503, used to acquire the requirement reference text from the in-vehicle terminal when the in-vehicle terminal does not support the function corresponding to the target semantics; a determination unit 504, used to determine second feedback information corresponding to the requirement reference text, the second feedback information including operation information of the function indicated by the requirement reference text; and a sending unit 505, used to send the second feedback information to the in-vehicle terminal, enabling the user to implement the function corresponding to the requirement reference text according to the operation information.

[0093] In one possible instance, regarding the analysis of the voice information to obtain the first feedback information, the analysis unit 502 is specifically configured to: perform semantic analysis on the voice information to obtain the target text; acquire the vehicle's configuration information; and determine the requirement reference text based on the configuration information and the target text.

[0094] It is understood that since the method embodiments and the device embodiments are different presentations of the same technical concept, the content of the method embodiment section in this application should be adapted to the device embodiment section in a synchronous manner, and will not be repeated here.

[0095] In the case of using integrated units, please refer to Figure 6 , Figure 6 This is a functional unit block diagram of another device for processing user voice requests provided in an embodiment of this application. Figure 6The apparatus 600 for processing user voice requests includes a processing module 612 and a communication module 611. The processing module 612 controls and manages the actions of the apparatus for processing user voice requests, for example, executing the steps of the first acquisition unit 501, the analysis unit 502, the second acquisition unit 503, the determination unit 504, and the sending unit 505, and / or performing other processes of the technology described herein. The communication module 611 is used for interaction between the apparatus for processing user voice requests and other devices. Figure 4 As shown, the apparatus for processing user voice requests may further include a storage module 613, which is used to store program code and data of the apparatus for processing user voice requests.

[0096] The processing module 612 can be a processor or controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication module 611 can be a transceiver, RF circuitry, or a communication interface, etc. The storage module 613 can be a memory.

[0097] All relevant content in each scenario involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here. The above-mentioned device 600 for processing user voice requests can perform the above-mentioned... Figure 2a The method shown is for handling user voice requests.

[0098] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes the corresponding hardware structure and software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0099] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0100] This application also provides a chip, wherein the chip includes a processor for calling and running a computer program from a memory, causing a device on which the chip is installed to perform some or all of the steps described in the above method embodiments of the electronic device.

[0101] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0102] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0103] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0104] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0106] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0107] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0108] If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0109] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0110] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0111] While this application discloses the above information, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of this application, and can make various alterations and modifications, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of this application.

Claims

1. A method for processing user voice requests, characterized in that, An in-vehicle terminal for a voice control system, the voice control system including a cloud server and the in-vehicle terminal, the cloud server and the in-vehicle terminal being communicatively connected, the method including the following steps: The received voice information is sent to the cloud server, and the voice information is used to instruct control commands for the hardware of the vehicle corresponding to the in-vehicle terminal. Obtain first feedback information from the cloud server. The first feedback information includes target text and requirement reference text. The target text is used to indicate user requirements. The target text is associated with the voice information. The requirement reference text is associated with the target text. Determine whether the function of the target text indication is supported; If not, the required reference text will be sent to the cloud server; Obtain second feedback information from the cloud server, the second feedback information including operation information of the function indicated by the requirement reference text; The operation information is displayed so that the user can implement the function of the required reference text instruction based on the operation information.

2. The method according to claim 1, characterized in that, If any of the following conditions exist, then the function corresponding to the target text is determined to be unsupported: The in-vehicle terminal supports parsing the target text, but the hardware associated with the user's needs does not support voice control; or The in-vehicle terminal supports parsing the target text, but the vehicle does not include the hardware associated with the user's needs; or The vehicle-mounted terminal does not support parsing the target text.

3. The method according to claim 2, characterized in that, The method further includes: If the vehicle terminal does not support parsing the target text, the operation information also includes a first prompt message, which prompts the user to update the version of the target application in the vehicle terminal to support parsing the target text.

4. The method according to claim 2 or 3, characterized in that, Before sending the requirement reference text to the cloud server, the method further includes: If the vehicle terminal supports parsing the target text, but the vehicle does not include hardware associated with the user's needs, a second prompt message is output, which includes the reference text for the needs. Obtain user feedback information, which is used to indicate the user's final needs; If the user's final requirements match the requirements indicated by the requirement reference text, the requirement reference text will be sent to the cloud server.

5. The method according to claim 4, characterized in that, Before sending the requirement reference text to the cloud server, the method further includes: Determine whether the function corresponding to the aforementioned requirement reference text is supported; If not, the required reference text will be sent to the cloud server; If so, then perform the operation to implement the function corresponding to the required reference text.

6. The method according to claim 4, characterized in that, The method further includes: If the user's final requirement matches the requirement indicated by the target text, a third prompt message is output. The third prompt message is used to inform the user that the vehicle does not support the function corresponding to the user's final requirement.

7. A method for processing user voice requests, characterized in that, A cloud server is used in a voice control system, the voice control system including the cloud server and an in-vehicle terminal, the cloud server and the in-vehicle terminal being communicatively connected, the method including the following steps: Acquire voice information from the vehicle terminal, the voice information being used to instruct control commands for the hardware of the vehicle corresponding to the vehicle terminal; Analyze the voice information to obtain first feedback information, which includes target text and requirement reference text. The target text is used to indicate the user's requirements and is associated with the voice information. The requirement reference text is associated with the target text. If the vehicle terminal does not support the function corresponding to the target text, the required reference text is obtained from the vehicle terminal. Determine the second feedback information corresponding to the requirement reference text, wherein the second feedback information includes the operation information of the function indicated by the requirement reference text; The second feedback information is sent to the vehicle terminal, enabling the user to perform the function corresponding to the required reference text based on the operation information.

8. The method according to claim 7, characterized in that, The analysis of the voice information to obtain first feedback information includes: Semantic analysis is performed on the speech information to obtain the target text; Obtain the configuration information of the vehicle; The requirement reference text is determined based on the configuration information and the target text.

9. An apparatus for processing user voice requests, characterized in that, An in-vehicle terminal for a voice control system, the voice control system including a cloud server and the in-vehicle terminal, the cloud server and the in-vehicle terminal being communicatively connected, the device comprising: The first sending unit is used to send the received voice information to the cloud server, wherein the voice information is used to indicate control commands for the hardware of the vehicle corresponding to the vehicle terminal. The first acquisition unit is used to acquire first feedback information from the cloud server. The first feedback information includes target text and requirement reference text. The target text is used to indicate user requirements. The target text is associated with the voice information. The requirement reference text is associated with the target text. A determining unit is used to determine whether the function of the target text indication is supported; The second sending unit is used to send the requirement reference text to the cloud server if no; The second acquisition unit is used to acquire second feedback information from the cloud server, the second feedback information including operation information of the function indicated by the requirement reference text; The display unit is used to display the operation information, enabling the user to implement the function of the required reference text instruction based on the operation information.

10. An apparatus for processing user voice requests, characterized in that, A cloud server for a voice control system, the voice control system including the cloud server and an in-vehicle terminal, the cloud server and the in-vehicle terminal being communicatively connected, the device comprising: The first acquisition unit is used to acquire voice information from the vehicle terminal, the voice information being used to instruct control commands for the hardware of the vehicle corresponding to the vehicle terminal. An analysis unit is configured to analyze the voice information to obtain first feedback information, the first feedback information including target text and requirement reference text, the target text being used to indicate user requirements, the target text being associated with the voice information, and the requirement reference text being associated with the target text; The second acquisition unit is used to acquire the required reference text from the vehicle terminal when the vehicle terminal does not support the function corresponding to the target text. A determining unit is used to determine the second feedback information corresponding to the requirement reference text, wherein the second feedback information includes operation information of the function indicated by the requirement reference text; The sending unit is used to send the second feedback information to the vehicle terminal, so that the user can realize the function corresponding to the required reference text according to the operation information.

11. An electronic device, characterized in that, It includes a processor, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in any one of claims 1-8.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that causes a computer to execute in order to implement the method as described in any one of claims 1-8.

Images