WO2023082649A1 - 语音对话提示方法、装置、设备及计算机可读存储介质 - Google Patents

语音对话提示方法、装置、设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2023082649A1
WO2023082649A1 PCT/CN2022/101106 CN2022101106W WO2023082649A1 WO 2023082649 A1 WO2023082649 A1 WO 2023082649A1 CN 2022101106 W CN2022101106 W CN 2022101106W WO 2023082649 A1 WO2023082649 A1 WO 2023082649A1
Authority
WO
WIPO (PCT)
Prior art keywords
current
word
application
prompt
wake
Prior art date
Application number
PCT/CN2022/101106
Other languages
English (en)
French (fr)
Inventor
聂亚梅
崔硕
黄桂容
姜洪亮
辛德全
Original Assignee
上汽通用五菱汽车股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上汽通用五菱汽车股份有限公司 filed Critical 上汽通用五菱汽车股份有限公司
Publication of WO2023082649A1 publication Critical patent/WO2023082649A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback

Definitions

  • the present application relates to the field of intelligent voice technology, and in particular to a voice dialogue prompt method, device, equipment and computer-readable storage medium.
  • the main purpose of the present application is to provide a voice dialogue prompt method, device, equipment and computer-readable storage medium, aiming to solve the technical problem in the prior art that prompt entries cannot be effectively displayed during voice dialogue.
  • the present application provides a voice dialogue prompt method, the voice dialogue prompt method comprising:
  • the step of calling the prompt word corresponding to the current focus application includes:
  • the step of acquiring the preset current wake-up word includes:
  • the step of detecting whether the input custom wake-up word is received it includes:
  • the default wake word is used as the current wake word.
  • the step of determining the current focus application according to the current application includes:
  • the main focus application is used as the current focus application.
  • the step of determining the main focus application in the current application includes:
  • the current application corresponding to the operation time node closest to the current time node is used as the main focus application.
  • the step of outputting and displaying the current wake-up word and the prompt word includes:
  • the present application also provides a voice dialogue prompt device, the voice dialogue prompt device includes an application management module, a voice skill management module, a wake-up word management module and a voice dialogue prompt management module, wherein,
  • the application management module is configured to determine the current application in the running state at the current moment, and determine the current focus application according to the current application;
  • the speech skill management module is configured to call prompt words corresponding to the current focus application
  • the wake-up word management module is configured to obtain a preset current wake-up word
  • the voice dialogue prompt management module is configured to output and display the current wake-up word and the prompt word.
  • the present application also provides a voice dialogue prompting device, the voice dialogue prompting device includes a memory, a processor, and a voice dialogue prompt stored in the memory and operable on the processor program, when the voice dialogue prompt program is executed by the processor, the steps of the above-mentioned voice dialogue prompt method are realized.
  • the present application also provides a computer-readable storage medium, on which a voice dialogue prompt program is stored, and when the voice dialogue prompt program is executed by a processor, the above-mentioned voice Steps in the dialog prompt method.
  • the present application provides a voice dialogue prompt method, device, equipment and computer-readable storage medium, which determine the current application in the running state at the current moment, determine the current focus application according to the current application, and call the prompt words corresponding to the current focus application to obtain The preset current wake-up word, outputting and displaying the current wake-up word and the prompt word.
  • the above method first determines the current application in use, determines the current focus application according to the current application, and then calls the prompt word corresponding to the current focus application, avoiding the problem that the prompt word does not correspond to the actual application, and at the same time, by obtaining the preset current Wake-up words, output and display the current wake-up words and reminder words together, provide users with more accurate wake-up words and reminder words, facilitate users to wake up the voice dialogue function and issue instructions, and realize the effective display of reminder entries.
  • Fig. 1 is a schematic diagram of the terminal structure of the hardware operating environment involved in the solution of the embodiment of the present application;
  • FIG. 2 is a schematic flow chart of the first embodiment of the voice dialog prompting method of the present application
  • FIG. 3 is a system schematic diagram of an application scenario involved in the solution of the embodiment of the present application.
  • FIG. 4 is a schematic diagram of the first application scenario involved in the solution of the embodiment of the present application.
  • FIG. 5 is a schematic diagram of a second application scenario involved in the solution of the embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a voice dialog prompting device according to an embodiment of the present application.
  • FIG. 1 is a schematic diagram of a terminal structure of a hardware operating environment involved in the solution of the embodiment of the present application.
  • the terminal in the embodiment of the present application may be a voice dialog prompting device, and the voice dialog prompting device may be a PC (personal computer, personal computer), portable computer, server and other terminal equipment.
  • PC personal computer, personal computer
  • portable computer portable computer
  • server server and other terminal equipment.
  • the voice dialogue prompting device may include: a processor 1001, such as a CPU (Central Processing Unit, central processing unit), communication bus 1002, user interface 1003, network interface 1004, memory 1005.
  • the communication bus 1002 is set to realize connection and communication between these components.
  • the user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 1005 can be a high-speed RAM memory, or a stable memory (non-volatile memory), such as disk storage.
  • the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .
  • terminal structure shown in FIG. 1 does not constitute a limitation on the terminal, and may include more or less components than those shown in the figure, or combine some components, or arrange different components.
  • the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a voice dialogue prompt program.
  • the network interface 1004 is mainly configured to connect to the background server and perform data communication with the background server;
  • the user interface 1003 is mainly configured to connect to the client (client) and perform data communication with the client;
  • the processor 1001 can be set to call the voice dialogue prompt program stored in memory 1005, and perform the following operations:
  • the present application provides a voice dialog prompting method.
  • FIG. 2 is a schematic flowchart of the first embodiment of the voice dialog prompting method of the present application.
  • the voice dialogue prompting method includes:
  • Step S10 determine the current application that is running at the current moment, and determine the current focus application according to the current application
  • the voice dialogue prompting method is applied to a voice dialogue prompting device.
  • the voice dialogue prompting device may be a vehicle-mounted multimedia device, and the vehicle-mounted multimedia device in this embodiment includes an application management module.
  • the application management module is used to determine the current application in the running state at the current moment, and determine the current focus application according to the current application, wherein the current application is the application currently being used or displayed by the vehicle multimedia, and the current application can be one or more.
  • the current focus application is the current application that needs to call the prompt words of the voice dialogue. For example, as shown in FIG. 3, the current application is first determined through multimedia, and the multimedia feeds back the current application to the application management module.
  • the application management module determines the current application that is currently running, and determines the current focus application based on the current application.
  • the in-vehicle multimedia application may include home page, navigation, system setting, vehicle setting, music, air conditioner, personal center and other applications.
  • Step S20 call the prompt words corresponding to the current focus application
  • the vehicle-mounted multimedia device further includes a voice skill management module, which is configured to call prompt words corresponding to the current focus application, wherein the prompt words are voice dialogue guidance prompt words to provide voice information to the user terminal.
  • Dialogue guidance prompts which in turn facilitate users to issue voice commands accurately.
  • the speech skill management module receives the application identifier corresponding to the current focus application sent by the application management module, and the speech skill management module retrieves the speech entries supported by the current focus application according to the application identifier, and transfers the speech entries supported by the current focus application to The entry is sent to the voice dialogue prompt management module.
  • the speech skill management module acquires the application identifier of the current focus application, searches for the prompt words corresponding to the application identifier according to the application identifier, that is, the prompt words corresponding to the current focus application, and then retrieves the prompt words corresponding to the current focus application.
  • the application identifier can be used to identify the uniquely corresponding application.
  • step S20 the refinement of the step of calling the prompt word corresponding to the current focus application includes:
  • Step A obtaining a preset relationship correspondence table between an application and a prompt word, and detecting whether there is an adapted prompt word adapted to the current focus application in the preset relationship correspondence table;
  • Step B if it exists, use the adapted prompt word as the prompt word corresponding to the current focus application.
  • the speech skill management module includes a storage unit, and the storage unit is configured to store a preset relationship correspondence table between applications and prompt words, and the default settings of applications and prompt words corresponding to them can be preset in the storage unit.
  • the relational correspondence table includes each application and an adaptation prompt word adapted to each application.
  • the adapted prompt words are voice prompt entries that match the application and are supported by the application, and one application may correspond to multiple prompt entries.
  • the preset relationship correspondence table includes navigation applications and adaptive prompt words corresponding to navigation applications (such as: "zoom in the map", "navigate home”, etc.), music applications and music application corresponding adaptive prompt words (such as: " Play Next", "Volume Up”, etc.).
  • the voice skill management module Obtain the preset relationship correspondence table between the application and the prompt word through the voice skill management module, and detect whether there is an adapted prompt word adapted to the current focus application in the relationship correspondence table, that is, to find the corresponding prompt word from the relationship correspondence table that is compatible with the current focus application. Further, if there is an adaptation prompt word adapted to the current focus application in the relationship correspondence table, then use the adaptation prompt word as the prompt word corresponding to the current focus application, and call the prompt word , so as to facilitate the subsequent step of outputting and displaying the prompt words.
  • step S30 is included, obtaining the preset current wake-up word, and outputting and displaying the current wake-up word and the prompt word.
  • the vehicle-mounted multimedia device also includes a wake-up word management module and a voice dialogue prompt management module, wherein the wake-up word management module is set to obtain a preset current wake-up word in real time, and the voice dialogue prompt management module is set to set the current wake-up word The prompt word output corresponding to the current focus application is displayed.
  • the wake-up word management module obtains the preset current wake-up word, and sends the current wake-up word to the voice dialogue prompt management module, and the voice dialogue prompt management module receives the wake-up word management module to send The current wake-up word, and receive the voice entry supported by the current application sent by the voice skill management module, and integrate the current wake-up word and prompt word into prompt content, output and display it in the voice dialog box.
  • the refinement of the step of outputting and displaying the current wake-up word and the prompt word includes:
  • Step C integrating the current wake-up word and the prompt word according to a preset combination method to obtain a voice guidance entry
  • Step D outputting and displaying the voice guidance entry to a preset designated position.
  • the voice dialog prompt management module includes a data integration unit and a data output unit.
  • the data integration unit is configured to integrate the current wake-up word and prompt word
  • the specific data integration method may be: integrate the current wake-up word and prompt word according to a preset combination method to obtain a voice guidance entry.
  • the preset combination method is a preset combination method.
  • the current wake-up word is "Hello Huaweing”
  • the prompt word is “Turn on Bluetooth”
  • the preset combination method is “Try to say: the current wake-up word, the prompt word ", then integrate the current wake-up word and prompt word according to the preset combination method
  • the obtained voice guidance entry is: “Try to say: Hello Huaweing, turn on Bluetooth”, and then output and display the obtained voice guidance entry to the preset position.
  • the specific manner of outputting and displaying the voice guidance entries may be to output and display the voice guidance entries according to the preset display rules.
  • different voice guidance entries corresponding to the current focus application may be displayed in turn or randomly.
  • the current focus application is a navigation application
  • the voice guidance entry corresponding to the navigation application includes "Try to say: Hello Xiao Ming, zoom in on the map” and "Try to say: Hello Xiao Ming, navigate home", etc. It can be displayed in turn or randomly according to the preset list order.
  • the user's operation habits may be analyzed based on the user's behavior history data collected, and the voice guidance entries frequently used by the user may be preferentially displayed.
  • the user behavior history data can be the number of times the user uses the voice guidance entry corresponding to the current focus application. According to the number of use of the voice guidance entry, the voice guidance entries are sorted according to the number of times of use, and the higher the number of use is displayed in turn. voice guidance entries for .
  • the preset display rule may also include a preset display position, that is, the voice guidance entry is displayed at a preset display position in the multimedia display interface. As shown in FIG. 5 , the voice guidance entry "Try to say: Hello Xiao Ming, enlarge the map" is displayed at a preset position in the navigation application interface.
  • the embodiment of the present application provides a voice dialogue prompt method.
  • the current focus application is determined according to the current application, and the prompt word corresponding to the current focus application is called through the preset relationship correspondence table to obtain the preset The current wake-up word, integrate the current wake-up word and prompt word, and output and display.
  • the above method first determines the current focus application being used, and retrieves the adaptive prompt words adapted to the current focus application according to the application identifier of the current focus application, avoiding the uncontrollability of the text list, which causes the voice prompt entry to be in the current application. Problems that cannot be effectively displayed, and then the current wake-up word and prompt word are integrated and displayed, providing a more accurate voice dialogue prompt for the user terminal.
  • step S30 the step of obtaining the preset current wake-up word includes:
  • Step E detecting whether an input custom wake-up word is received
  • Step e1 determining that the custom wake-up word is received, replacing the default wake-up word with the custom wake-up word, and using the custom wake-up word as the current wake-up word.
  • the interface includes a voice dialogue prompt box, Bluetooth setting, sound setting, display setting, voice setting and traffic setting in the vehicle multimedia system setting application , where the voice setting function is the entrance to customize the wake-up word.
  • the voice setting function includes the default wake-up word and the custom wake-up word.
  • the user can set the custom wake-up word in this interface. For example, in Figure 4, the user sets the custom wake-up word For "Hello Xiao Ming". This embodiment detects whether there is a custom wake-up word input by the user terminal.
  • the custom wake-up word is used as the current wake-up word, and the current wake-up word and prompt word are integrated in real time, and timely Update the voice guidance entry, display and output the latest voice guidance entry to the client, and improve the dynamic responsiveness. That is, as shown in Figure 4, before the user sets the custom wake-up word as "Hello Xiaoming", the content of the voice dialogue prompt box in the system setting interface is "Try to say: ⁇ , turn on Bluetooth". When it is detected that the user sets the custom wake-up word as "Hello Xiaoming”, the content in the voice dialogue prompt box is updated to "Try to say: Hello Xiaoming, turn on Bluetooth".
  • the default wake-up word displayed in the voice dialogue prompt box cannot be updated in time and the user-defined wake-up word cannot be displayed in time, resulting in the user being unable to Prompt content for voice interaction issues.
  • Step E after the step of detecting whether the input custom wake word is received, includes:
  • step e2 it is determined that no custom wake-up word has been received, and the default wake-up word is used as the current wake-up word.
  • the default wake-up word is used as the current wake-up word. Then, the default wake-up word and the prompt word are integrated to obtain the voice guidance entry, and the voice guidance entry corresponding to the default wake-up word is output.
  • the current wake-up word can be updated in time when a custom wake-up word is detected, and then the latest voice guidance entry is output and displayed to the user terminal, avoiding The problem that the user cannot perform voice interaction according to the displayed voice guidance entry because the voice guidance entry is not updated in time is solved, and the user experience is improved.
  • the refinement of the step of determining the current focus application according to the current application includes:
  • Step F judging whether there are multiple current applications
  • Step G determining that there are multiple current applications, and determining the main focus application in the current applications
  • Step H using the main focus application as the current focus application.
  • the application management module of this implementation judges whether there are multiple current applications, determines that there are multiple current applications, determines the main focus application in the current application, and uses the main focus application as the current focus application.
  • the main focus application is used as the current focus application, so as to output the voice guidance entries of the current focus application in a targeted manner.
  • the step of determining the main focus application in the current application includes:
  • Step g1 obtaining the operation time node corresponding to each current application, comparing each operation time node with the current time node, and obtaining the operation time node closest to the current time node;
  • Step g2 taking the current application corresponding to the operation time node closest to the current time node as the main focus application.
  • the specific process of determining the main focus application in the current application may be as follows: Obtain the operation time nodes corresponding to each current application through the application management module, compare each operation time node with the current time node, and obtain the current time node The operation time node closest to the node, the current application corresponding to the operation time node closest to the current time node is used as the main focus application.
  • the operation time node is the last operation time node corresponding to the application.
  • the current application includes a music application and a navigation application in split-screen mode. The music application operation time node is 5:00, the navigation application operation time node is 5:30, and the current time node is 5:40.
  • the application operation time node 5:00 and the navigation application operation time node 5:30 are compared with the current time node 5:40 by comparing the music application operation time node 5:00 and the navigation application operation time node 5:30 with the current time node 5:40 to obtain the current time
  • the closest operation time node to node 5:40 is the navigation application operation time node 5:30, and the navigation application corresponding to the navigation application operation time node 5:30 is used as the main focus application. That is, the main focus application is a navigation application, and the prompt word corresponding to the navigation application is called for the navigation application.
  • the most recently operated application is determined through the operation time node, so that the voice guidance entry corresponding to the application operated by the user last time is accurately displayed in the split-screen mode, which is more suitable for the customer's voice dialogue prompt requirements and improves the user experience.
  • the display accuracy of voice prompt words is more suitable for the customer's voice dialogue prompt requirements and improves the user experience.
  • the embodiment of the present application also provides a voice dialog prompting device, as shown in FIG. 6 , the voice dialog prompting device includes an application management module 2001, a voice Skill management module 2002, wake-up word management module 2003 and voice dialogue prompt management module 2004, wherein,
  • the application management module 2001 is configured to determine the current application in the running state at the current moment, determine the current focus application according to the current application, and send the identification information corresponding to the current focus application to the voice skill management module 2002;
  • the application management module 2001 is further configured to determine whether there are multiple current applications, and if there are multiple current applications, determine the main focus application in the current application, and use the main focus application as the current focus application;
  • the application management module 2001 is further configured to obtain the operation time node corresponding to each current application, compare each operation time node with the current time node, obtain the operation time node closest to the current time node, and compare the operation time node with the current time node
  • the current application corresponding to the operation time node closest to the current time node is used as the main focus application.
  • the voice skill management module 2002 is configured to receive the identification information corresponding to the current focus application, retrieve the prompt words corresponding to the current focus application, and send the prompt words to the voice dialog prompt management module 2004;
  • the voice skill management module 2002 is further configured to obtain a preset relationship correspondence table between applications and prompt words, and detect whether there is an adaptive prompt word adapted to the current focus application in the preset relationship correspondence table, and if there is , the adapted prompt word is used as the prompt word corresponding to the current focus application.
  • the speech skill management module 2002 includes: a storage unit,
  • the storage unit is configured to store a preset relationship correspondence table between applications and prompt words.
  • the wake-up word management module 2003 is configured to obtain a preset current wake-up word, and send the current wake-up word to the voice dialogue prompt management module 2004;
  • the wake-up word management module 2003 is also configured to detect whether an input custom wake-up word is received, and in response to receiving the custom wake-up word, replace the default wake-up word with the custom wake-up word, and The custom wake-up word is used as the current wake-up word, and the default wake-up word is used as the current wake-up word in response to the situation that the custom wake-up word is not received.
  • the voice dialog prompt management module 2004 is configured to receive the prompt word and the current wake-up word, and output and display the current wake-up word and the prompt word.
  • the voice dialogue prompt management module 2004 is also configured to integrate the current wake-up word and the prompt word according to a preset combination method to obtain a voice guidance entry, and output and display the voice guidance entry to a preset specified Location.
  • the voice dialog prompt management module 2004 includes: a data integration unit and a data output unit,
  • the data integration unit is configured to integrate the current wake-up word and prompt word
  • the data output unit is configured to output the current wake-up word and prompt word.
  • the voice dialogue prompting device of the present application adopts the voice dialogue prompting methods provided by the above-mentioned embodiments to solve the technical problem that the voice prompt entries cannot be effectively displayed during the voice dialogue.
  • the function of the voice dialogue prompting device provided by the embodiment of the present application is the same as that of the voice dialogue prompting method provided by the above-mentioned embodiments, and other technical features in the device are the same as those disclosed by the method of the above-mentioned embodiments The features are the same, and will not be repeated here.
  • the present application also provides a voice dialogue prompting device, the voice dialogue prompting device includes a memory, a processor, and a voice dialogue prompt program stored on the memory and operable on the processor, the voice dialogue prompting When the program is executed by the processor, the steps of the above-mentioned voice dialogue prompting method are realized.
  • the present application also provides a computer-readable storage medium, where a voice dialogue prompt program is stored on the computer-readable storage medium, and when the voice dialogue prompt program is executed by a processor, the voice dialogue as described in any of the above embodiments is realized. Steps in the dialog prompt method.
  • the term “comprises”, “comprises” or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or system comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or system. Without further limitations, an element defined by the phrase “comprising a " does not preclude the presence of additional identical elements in the process, method, article or system comprising that element.
  • the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.
  • the technical solution of the present application can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , magnetic disk, optical disk), including several instructions to make a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the methods described in various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本申请公开了一种语音对话提示方法、装置、设备及计算机可读存储介质，所述语音对话提示方法包括：确定当前时刻处于运行状态的当前应用，根据所述当前应用确定当前焦点应用；调取所述当前焦点应用对应的提示词；获取预设的当前唤醒词，将所述当前唤醒词和所述提示词输出显示。本申请能够解决现有技术中在语音对话时显示的语音提示词条准确性较低的技术问题。

Description

语音对话提示方法、装置、设备及计算机可读存储介质
本申请要求于2021年11月12号申请的、申请号为202111344352.5的中国专利申请的优先权，其全部内容通过引用结合于此。
技术领域
本申请涉及智能语音技术领域，尤其涉及一种语音对话提示方法、装置、设备及计算机可读存储介质。
 背景技术
随着汽车技术和车联网的快速发展，语音技术在车载多媒体中的应用越来越多，语音交互内容也越来越丰富，车辆乘员可通过交互式语音应答技术在旅途中完成对车载多媒体的使用。为提示用户进行语音唤醒，目前常规的方式是：将预存的语音提示文本输出至显示屏进行显示以提示用户进行语音对话。但不同的应用支持的语音词条不同，采用上述方式容易出现用于提示的语音词条在当前应用中无法生效的问题。因此，现有技术存在在语音对话时提示词条无法有效显示的技术问题。
 技术问题
本申请的主要目的在于提供一种语音对话提示方法、装置、设备及计算机可读存储介质，旨在解决现有技术中在语音对话时提示词条无法有效显示的技术问题。
 技术解决方案
为实现上述目的，本申请提供一种语音对话提示方法，所述语音对话提示方法包括：
确定当前时刻处于运行状态的当前应用，根据所述当前应用确定当前焦点应用；
调取所述当前焦点应用对应的提示词；
获取预设的当前唤醒词，将所述当前唤醒词和所述提示词输出显示。
在一实施方式中，所述调取所述当前焦点应用对应的提示词的步骤，包括：
获取应用与提示词的预设关系对应表，检测所述预设关系对应表中是否存在和所述当前焦点应用适配的适配提示词；
确定所述预设关系对应表中存在和所述当前焦点应用适配的适配提示词，将所述适配提示词作为当前焦点应用对应的提示词。
在一实施方式中，所述获取预设的当前唤醒词的步骤，包括：
检测是否接收到输入的自定义唤醒词；
响应于接收到所述自定义唤醒词的情况，将默认唤醒词替换为所述自定义唤醒词，并将所述自定义唤醒词作为当前唤醒词。
在一实施方式中，所述检测是否接收到输入的自定义唤醒词的步骤之后，包括：
响应于未接收到自定义唤醒词的情况，将默认唤醒词作为当前唤醒词。
在一实施方式中，所述根据所述当前应用确定当前焦点应用的步骤，包括：
判断是否存在多个所述当前应用；
确定存在多个所述当前应用，确定所述当前应用中的主焦点应用；
将所述主焦点应用作为当前焦点应用。
在一实施方式中，所述确定所述当前应用中的主焦点应用的步骤，包括：
获取各当前应用对应的操作时间节点，将各所述操作时间节点与当前时间节点进行比较，得到与当前时间节点最接近的操作时间节点；
将所述与当前时间节点最接近的操作时间节点对应的当前应用作为主焦点应用。
在一实施方式中，所述将所述当前唤醒词和所述提示词输出显示的步骤包括：
按照预设组合方式将所述当前唤醒词和所述提示词进行整合，得到语音引导词条；
将所述语音引导词条输出显示至预设指定位置。
此外，为实现上述目的，本申请还提供一种语音对话提示设备，所述语音对话提示设备包括应用管理模块、语音技能管理模块、唤醒词管理模块和语音对话提示管理模块，其中，
所述应用管理模块，设置为确定当前时刻处于运行状态的当前应用，根据所述当前应用确定当前焦点应用；
所述语音技能管理模块，设置为调取所述当前焦点应用对应的提示词；
所述唤醒词管理模块，设置为获取预设的当前唤醒词；
所述语音对话提示管理模块，设置为将所述当前唤醒词和所述提示词输出显示。
此外，为实现上述目的，本申请还提供一种语音对话提示装置，所述语音对话提示装置包括存储器、处理器、以及存储在所述存储器上并可在所述处理器上运行的语音对话提示程序，所述语音对话提示程序被处理器执行时实现如上述的语音对话提示方法的步骤。
此外，为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有语音对话提示程序，所述语音对话提示程序被处理器执行时实现如上述的语音对话提示方法的步骤。
 有益效果
本申请提供一种语音对话提示方法、装置、设备及计算机可读存储介质，确定当前时刻处于运行状态的当前应用，根据当前应用确定当前焦点应用，并调取当前焦点应用对应的提示词，获取预设的当前唤醒词，将所述当前唤醒词和所述提示词输出显示。上述方式首先通过确定正在使用的当前应用，根据当前应用确定当前焦点应用，进而调取当前焦点应用对应的提示词，避免了提示词与实际应用不对应的问题，同时，通过获取预设的当前唤醒词，将当前唤醒词和提示词一起输出显示，为用户提供了较为准确的唤醒词和提示词，方便用户进行唤醒语音对话功能及下达指令，实现了提示词条的有效显示。
 附图说明
图1是本申请实施例方案涉及的硬件运行环境的终端结构示意图；
图2为本申请语音对话提示方法第一实施例的流程示意图；
图3为本申请实施例方案涉及的一应用场景的系统示意图；
图4为本申请实施例方案涉及的第一应用场景示意图；
图5为本申请实施例方案涉及的第二应用场景示意图；
图6为本申请实施例涉及的语音对话提示设备结构示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
 本发明的实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请的一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
参照图1，图1为本申请实施例方案涉及的硬件运行环境的终端结构示意图。
本申请实施例终端可以为语音对话提示设备，所述语音对话提示设备可以为PC（personal computer，个人计算机）、便携计算机、服务器等终端设备。
如图1所示，该语音对话提示设备可以包括：处理器1001，例如CPU（Central Processing Unit，中央处理器），通信总线1002，用户接口1003，网络接口1004，存储器1005。其中，通信总线1002设置为实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选的用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口（如WI-FI接口）。存储器1005可以是高速RAM存储器，也可以是稳定的存储器（non-volatile memory），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解，图1中示出的终端结构并不构成对终端的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及语音对话提示程序。
在图1所示的终端中，网络接口1004主要设置为连接后台服务器，与后台服务器进行数据通信；用户接口1003主要设置为连接客户端（用户端），与客户端进行数据通信；而处理器1001可以设置为调用存储器1005中存储的语音对话提示程序，并执行以下操作：
确定当前时刻处于运行状态的当前应用，根据所述当前应用确定当前焦点应用；
调取所述当前焦点应用对应的提示词；
获取预设的当前唤醒词，将所述当前唤醒词和所述提示词输出显示。
基于上述硬件结构，提出本申请语音对话提示方法各个实施例。
本申请提供一种语音对话提示方法。
参照图2，图2为本申请语音对话提示方法第一实施例的流程示意图。
在本实施例中，所述语音对话提示方法包括：
步骤S10，确定当前时刻处于运行状态的当前应用，根据所述当前应用确定当前焦点应用；
在本实施例中，语音对话提示方法应用于语音对话提示设备，该语音对话提示设备可以为车载多媒体设备，本实施例车载多媒体设备中包括有应用管理模块。该应用管理模块用于确定当前时刻处于运行状态的当前应用，并根据当前应用确定当前焦点应用，其中，当前应用为车载多媒体当前正在使用或正在显示的应用，当前应用可以为一个或多个，当前焦点应用为需调取语音对话提示词的当前应用。例如，如图3所示，首先通过多媒体确定当前应用，多媒体将当前应用反馈至应用管理模块，应用管理模块确定当前时刻处于运行状态的当前应用，并根据当前应用确定得出当前焦点应用。本实施例中车载多媒体应用可以包括首页、导航、系统设置、车辆设置、音乐、空调、个人中心等应用。
步骤S20，调取所述当前焦点应用对应的提示词；
在本实施例中，车载多媒体设备还包括有语音技能管理模块，该语音技能管理模块设置为调取当前焦点应用对应的提示词，其中提示词为语音对话引导提示词，以向用户端提供语音对话引导提示，进而便于用户准确地进行语音指令下达。如图3所示，语音技能管理模块接收应用管理模块发送的当前焦点应用对应的应用标识，语音技能管理模块根据应用标识调取当前焦点应用支持的语音词条，并将当前焦点应用支持的语音词条发送至语音对话提示管理模块。在一实施例中，语音技能管理模块获取当前焦点应用的应用标识，根据应用标识查找应用标识对应的提示词，也即当前焦点应用对应的提示词，进而调取当前焦点应用对应的提示词。其中应用标识能够用于识别与其唯一对应的应用。在本实施例中，不同应用支持的语音词条存在差异，首先确定正在使用的当前焦点应用，根据当前焦点应用的应用标识调取适配当前焦点应用的适配提示词，避免了由于文本清单的不可控性，造成的语音提示词条在当前应用无法有效显示的问题。
具体的，步骤S20中，调取所述当前焦点应用对应的提示词的步骤的细化包括：
步骤A，获取应用与提示词的预设关系对应表，检测所述预设关系对应表中是否存在和所述当前焦点应用适配的适配提示词；
步骤B，若存在，则将所述适配提示词作为当前焦点应用对应的提示词。
在本实施例中，语音技能管理模块中包括存储单元，存储单元设置为存储应用与提示词的预设关系对应表，可通过在该存储单元中预先设置应用及与其对应的提示词的预设关系对应表，预设关系对应表包括各个应用和与各应用适配的适配提示词。其中，适配提示词为与应用匹配且应用支持的语音提示词条，一个应用可对应多个提示词条。例如预设关系对应表中包括导航应用和导航应用对应的适配提示词（如：“放大地图”、“导航回家”等）、音乐应用和音乐应用对应的适配提示词（如：“播放下一首”、“调大音量”等）。通过语音技能管理模块获取应用与提示词的预设关系对应表，检测该关系对应表中是否存在和当前焦点应用适配的适配提示词，也就是从关系对应表中查找与当前焦点应用适配的适配提示词，进一步地，若关系对应表中存在和当前焦点应用适配的适配提示词，则将该适配提示词作为当前焦点应用对应的提示词，并调取该提示词，以便于后续进行将提示词输出显示的步骤。
在步骤步骤S20之后，包括步骤S30，获取预设的当前唤醒词，将所述当前唤醒词和所述提示词输出显示。
在本实施例中，车载多媒体设备还包括有唤醒词管理模块和语音对话提示管理模块，其中唤醒词管理模块设置为实时获取预设的当前唤醒词，语音对话提示管理模块设置为将当前唤醒词和当前焦点应用对应的提示词输出显示。其中当前唤醒词可实时确定，如图3所示，唤醒词管理模块获取预设的当前唤醒词，并将当前唤醒词发送至语音对话提示管理模块，语音对话提示管理模块接收唤醒词管理模块发送的当前唤醒词，并接收语音技能管理模块发送的当前应用支持的语音词条，并将当前唤醒词和提示词整合为提示内容输出显示至语音对话框。
具体地，上述步骤S30中，将所述当前唤醒词和所述提示词输出显示的步骤的细化包括：
步骤C，按照预设组合方式将所述当前唤醒词和所述提示词进行整合，得到语音引导词条；
步骤D，将所述语音引导词条输出显示至预设指定位置。
在本实施例中，语音对话提示管理模块中包括数据整合单元和数据输出单元。其中数据整合单元设置为将当前唤醒词和提示词进行整合，具体的数据整合方式可以为：将当前唤醒词和提示词按照预设组合方式进行整合，得到语音引导词条。其中，预设组合方式为预先设置好的组合方式，例如，当前唤醒词为“你好小明”，提示词为“打开蓝牙”，预设组合方式为“试试说：当前唤醒词，提示词”，则按照该预设组合方式将当前唤醒词和提示词进行整合，得到的语音引导词条为：“试试说：你好小明，打开蓝牙”，进而将获得的语音引导词条输出显示至预设指定位置。具体地，将语音引导词条输出显示的具体方式可以为，按照预设显示规则将语音引导词条输出显示，作为一种实施方式可以将当前焦点应用对应不同的语音引导词条轮流显示或随机显示，例如，当前焦点应用为导航应用，且导航应用对应的语音引导词条包括“试试说：你好小明，放大地图”和“试试说：你好小明，导航回家”等，此时可按照预设列表顺序进行轮流显示或随机显示。
另一种可选的实施例中，可以通过采集用户的行为历史数据，根据用户行为历史数据，分析用户的操作习惯，优先显示用户常用的语音引导词条。例如，用户行为历史数据可以为用户使用当前焦点应用对应的语音引导词条的使用次数，按照语音引导词条的使用次数，对语音引导词条按照使用次数高低进行排序，依次显示使用次数较高的语音引导词条。
进一步地，预设显示规则还可以包括预设显示位置，即可将语音引导词条显示在多媒体显示界面中的预设显示位置。如图5所示，将语音引导词条“试试说：你好小明，放大地图”显示至导航应用界面中的预设位置处。
本申请实施例提供一种语音对话提示方法，通过确定当前时刻处于运行状态的当前应用，根据当前应用确定当前焦点应用，通过预设关系对应表调取当前焦点应用对应的提示词，获取预设的当前唤醒词，将当前唤醒词和提示词进行整合，并输出显示。上述方式首先确定正在使用的当前焦点应用，根据当前焦点应用的应用标识调取适配当前焦点应用的适配提示词，避免了由于文本清单的不可控性，造成的语音提示词条在当前应用无法有效显示的问题，进而将当前唤醒词与提示词进行整合显示，为用户端提供了较为准确的语音对话提示。
进一步地，基于上述第一实施例，提出本申请语音对话提示方法的第二实施例。
在本实施例中，上述步骤S30，获取预设的当前唤醒词的步骤的细化包括：
步骤E，检测是否接收到输入的自定义唤醒词；
步骤e1，确定接收到所述自定义唤醒词，将默认唤醒词替换为所述自定义唤醒词，并将所述自定义唤醒词作为当前唤醒词。
在本实施例中，可参照图4，图4 为设置唤醒词后的系统设置界面，界面包括语音对话提示框，车载多媒体系统设置应用中蓝牙设置、声音设置、显示设置、语音设置及流量设置，其中语音设置功能是唤醒词自定义的入口，语音设置功能中包括默认唤醒词和自定义唤醒词，用户可在此界面中设置自定义唤醒词，例如，图4中用户设置自定义唤醒词为“你好小明”。本实施例检测是否有接收到用户端输入的自定义唤醒词，若接收到自定义唤醒词，则将自定义唤醒词作为当前唤醒词，实时地根据当前唤醒词和提示词进行整合，以及时更新语音引导词条，将最新的语音引导词条显示输出至用户端，提高了动态响应性。即如图4所示，在用户设置自定义唤醒词为“你好小明”之前，系统设置界面中的语音对话提示框中的内容为“试试说：××××，打开蓝牙”，此时检测到用户设置自定义唤醒词为“你好小明”，则将语音对话提示框中的内容更新为“试试说：你好小明，打开蓝牙”。
在本实施例中，通过实时更新当前唤醒词，可解决在用户自定义唤醒词后，语音对话提示框中显示的默认唤醒词不能及时更新以及不能及时显示用户自定义唤醒词，导致用户无法根据提示内容进行语音交互的问题。
步骤E，检测是否接收到输入的自定义唤醒词的步骤之后，包括：
步骤e2，确定未接收到自定义唤醒词，将默认唤醒词作为当前唤醒词。
在本实施例中，检测是否接收到输入的自定义唤醒词，确定未接收到自定义唤醒词，表明用户端并未进行自定义唤醒词的设置，此时将默认唤醒词作为当前唤醒词，进而将默认唤醒词和提示词进行整合，得到语音引导词条，输出显示默认唤醒词对应的语音引导词条。
在本实施例中，通过实时地检测用户端是否设置自定义唤醒词，在检测到自定义唤醒词时可及时地更新当前唤醒词，进而将最新的语音引导词条输出显示至用户端，避免了由于语音引导词条未及时更新，导致用户无法根据显示的语音引导词条进行语音交互的问题，提高了用户的使用体验。
进一步地，基于上述第一和第二实施例，提出本申请语音对话提示方法的第三实施例。
在本实施例中，在上述步骤S10，根据所述当前应用确定当前焦点应用的步骤的细化，包括：
步骤F，判断是否存在多个所述当前应用；
步骤G，确定存在多个所述当前应用，确定所述当前应用中的主焦点应用；
步骤H，将所述主焦点应用作为当前焦点应用。
在本实施例中，可能存在多个当前应用下需确定一个当前焦点应用的情况，例如同时存在两个应用的分屏模式，此时需要确定其中的一个应用为当前焦点应用，以针对性输出当前焦点应用的语音引导词条。本实施应用管理模块在接收到当前应用之后，判断是否存在多个当前应用，确定存在多个当前应用，确定当前应用中的主焦点应用，并将主焦点应用作为当前焦点应用。
本实施对于同时存在两个应用的分屏模式的情况，通过确定出主焦点应用，将主焦点应用作为当前焦点应用，以针对性地输出当前焦点应用的语音引导词条。
进一步地，上述步骤G，确定所述当前应用中的主焦点应用的步骤的细化，包括：
步骤g1，获取各当前应用对应的操作时间节点，将各所述操作时间节点与当前时间节点进行比较，得到与当前时间节点最接近的操作时间节点；
步骤g2，将所述与当前时间节点最接近的操作时间节点对应的当前应用作为主焦点应用。
在本实施例中，确定当前应用中的主焦点应用的具体过程可以为：通过应用管理模块获取各个当前应用对应的操作时间节点，将各操作时间节点与当前时间节点进行比较，得到与当前时间节点最接近的操作时间节点，将与当前时间节点最接近的操作时间节点对应的当前应用作为主焦点应用。其中，操作时间节点为应用对应的最后一次操作时间节点。例如，当前应用包括分屏模式下的音乐应用和导航应用两个应用，音乐应用操作时间节点为5:00，导航应用操作时间节点为5:30，当前时间节点为5:40，则获取音乐应用操作时间节点5:00和导航应用操作时间节点5:30，将音乐应用操作时间节点5:00，导航应用操作时间节点5:30分别与当前时间节点5:40进行比较，得到与当前时间节点5:40最接近的操作时间节点，即导航应用操作时间节点5:30，将导航应用操作时间节点5:30对应的导航应用作为主焦点应用。即主焦点应用为导航应用，进而针对导航应用调取导航应用对应的提示词。
本实施例中，通过操作时间节点确定最近一次操作的应用，使得在分屏模式下准确地显示出用户上一次操作的应用对应的语音引导词条，更贴合客户语音对话提示需求，提高了语音提示词的显示精准度。
与上述实施例一、实施例二及第三实施例相对应的，本申请实施例还提供一种语音对话提示设备，如图6所示，所述语音对话提示设备包括应用管理模块2001、语音技能管理模块2002、唤醒词管理模块2003和语音对话提示管理模块2004，其中，
所述应用管理模块2001，设置为确定当前时刻处于运行状态的当前应用，根据所述当前应用确定当前焦点应用，并将所述当前焦点应用对应的标识信息发送至语音技能管理模块2002；
所述应用管理模块2001，还设置为判断是否存在多个所述当前应用，若存在多个所述当前应用，则确定所述当前应用中的主焦点应用，将所述主焦点应用作为当前焦点应用；
所述应用管理模块2001，还设置为获取各当前应用对应的操作时间节点，将各所述操作时间节点与当前时间节点进行比较，得到与当前时间节点最接近的操作时间节点，将所述与当前时间节点最接近的操作时间节点对应的当前应用作为主焦点应用。
所述语音技能管理模块2002，设置为接收所述当前焦点应用对应的标识信息，调取所述当前焦点应用对应的提示词，并将所述提示词发送至语音对话提示管理模块2004；
所述语音技能管理模块2002，还设置为获取应用与提示词的预设关系对应表，检测所述预设关系对应表中是否存在和所述当前焦点应用适配的适配提示词，若存在，则将所述适配提示词作为当前焦点应用对应的提示词。
在一实施方式中，所述语音技能管理模块2002包括：存储单元，
所述存储单元，设置为存储应用与提示词的预设关系对应表。
所述唤醒词管理模块2003，设置为获取预设的当前唤醒词，并将所述当前唤醒词发送至语音对话提示管理模块2004；
所述唤醒词管理模块2003，还设置为检测是否接收到输入的自定义唤醒词，响应于接收到所述自定义唤醒词的情况，将默认唤醒词替换为所述自定义唤醒词，并将所述自定义唤醒词作为当前唤醒词，响应于未接收到自定义唤醒词的情况，将默认唤醒词作为当前唤醒词。
所述语音对话提示管理模块2004，设置为接收所述提示词和所述当前唤醒词，并将所述当前唤醒词和所述提示词输出显示。
所述语音对话提示管理模块2004，还设置为按照预设组合方式将所述当前唤醒词和所述提示词进行整合，得到语音引导词条，将所述语音引导词条输出显示至预设指定位置。
在一实施方式中，所述语音对话提示管理模块2004包括：数据整合单元和数据输出单元，
所述数据整合单元，设置为将当前唤醒词和提示词进行整合；
所述数据输出单元，设置为将当前唤醒词和提示词进行输出。
其中，本申请实施例中，与实施例一、实施例二及第三实施相同或相应的内容，请参考上文介绍，后续不再赘述。
本申请语音对话提示设备，采用上述各实施例提供的语音对话提示方法，解决了在语音对话时语音提示词条无法有效显示的技术问题。与现有技术相比，本申请实施例提供的语音对话提示设备的功能与上述各实施例提供的语音对话提示方法的功能相同，且该设备中的其他技术特征与上述各实施例方法公开的特征相同，在此不做赘述。
本申请还提供一种语音对话提示装置，所述语音对话提示装置包括存储器、处理器、以及存储在所述存储器上并可在所述处理器上运行的语音对话提示程序，所述语音对话提示程序被处理器执行时实现如上述的语音对话提示方法的步骤。
本申请计算机可读存储介质的具体实施例与上述语音对话提示方法各实施例基本相同，在此不作赘述。
本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有语音对话提示程序，所述语音对话提示程序被处理器执行时实现如以上任一项实施例所述的语音对话提示方法的步骤。
本申请计算机可读存储介质的具体实施例与上述语音对话提示方法各实施例基本相同，在此不作赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的可选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (10)

  1. 一种语音对话提示方法，包括以下步骤：
    确定当前时刻处于运行状态的当前应用，根据所述当前应用确定当前焦点应用；
    调取所述当前焦点应用对应的提示词；
    获取预设的当前唤醒词，将所述当前唤醒词和所述提示词输出显示。
  2. 如权利要求1所述的语音对话提示方法，其中，所述调取所述当前焦点应用对应的提示词的步骤，包括：
    获取应用与提示词的预设关系对应表，检测所述预设关系对应表中是否存在和所述当前焦点应用适配的适配提示词；
    确定所述预设关系对应表中存在和所述当前焦点应用适配的适配提示词，将所述适配提示词作为当前焦点应用对应的提示词。
  3. 如权利要求1所述的语音对话提示方法，其中，所述获取预设的当前唤醒词的步骤，包括：
    检测是否接收到输入的自定义唤醒词；
    响应于接收到所述自定义唤醒词的情况，将所述自定义唤醒词作为当前唤醒词。
  4. 如权利要求3所述的语音对话提示方法，其中，所述检测是否接收到输入的自定义唤醒词的步骤之后，包括：
    响应于未接收到自定义唤醒词的情况，将默认唤醒词作为当前唤醒词。
  5. 如权利要求1所述的语音对话提示方法，其中，所述根据所述当前应用确定当前焦点应用的步骤，包括：
    判断是否存在多个所述当前应用；
    确定存在多个所述当前应用，确定所述当前应用中的主焦点应用；
    将所述主焦点应用作为当前焦点应用。
  6. 如权利要求5所述的语音对话提示方法，其中，所述确定所述当前应用中的主焦点应用的步骤，包括：
    获取各当前应用对应的操作时间节点，将各所述操作时间节点与当前时间节点进行比较，得到与当前时间节点最接近的操作时间节点；
    将所述与当前时间节点最接近的操作时间节点对应的当前应用作为主焦点应用。
  7. 如权利要求1至6中任一项所述的语音对话提示方法，其中，所述将所述当前唤醒词和所述提示词输出显示的步骤包括：
    将所述当前唤醒词和所述提示词进行整合，得到语音引导词条；
    将所述语音引导词条输出显示至预设指定位置。
  8. 一种语音对话提示装置，所述语音对话提示装置包括应用管理模块、语音技能管理模块、唤醒词管理模块和语音对话提示管理模块，其中，
    所述应用管理模块，设置为确定当前时刻处于运行状态的当前应用，根据所述当前应用确定当前焦点应用；
    所述语音技能管理模块，设置为调取所述当前焦点应用对应的提示词；
    所述唤醒词管理模块，设置为获取预设的当前唤醒词；
    所述语音对话提示管理模块，设置为将所述当前唤醒词和所述提示词输出显示。
  9. 一种语音对话提示设备，其中，所述语音对话提示设备包括存储器、处理器、以及存储在所述存储器上并可在所述处理器上运行的语音对话提示程序，所述语音对话提示程序被处理器执行时实现如权利要求1至7中任一项所述的语音对话提示方法的步骤。
  10. 一种计算机可读存储介质，其中，所述计算机可读存储介质上存储有语音对话提示程序，所述语音对话提示程序被处理器执行时实现如权利要求1至7中任一项所述的语音对话提示方法的步骤。
PCT/CN2022/101106 2021-11-12 2022-06-24 语音对话提示方法、装置、设备及计算机可读存储介质 WO2023082649A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111344352.5A CN114115790A (zh) 2021-11-12 2021-11-12 语音对话提示方法、装置、设备及计算机可读存储介质
CN202111344352.5 2021-11-12

Publications (1)

Publication Number Publication Date
WO2023082649A1 true WO2023082649A1 (zh) 2023-05-19

Family

ID=80396005

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/101106 WO2023082649A1 (zh) 2021-11-12 2022-06-24 语音对话提示方法、装置、设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN114115790A (zh)
WO (1) WO2023082649A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114115790A (zh) * 2021-11-12 2022-03-01 上汽通用五菱汽车股份有限公司 语音对话提示方法、装置、设备及计算机可读存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107277225A (zh) * 2017-05-04 2017-10-20 北京奇虎科技有限公司 语音控制智能设备的方法、装置和智能设备
CN110148414A (zh) * 2019-05-21 2019-08-20 大众问问(北京)信息科技有限公司 一种语音说法引导方法和装置
CN110493123A (zh) * 2019-09-16 2019-11-22 腾讯科技（深圳）有限公司 即时通讯方法、装置、设备及存储介质
CN111949240A (zh) * 2019-05-16 2020-11-17 阿里巴巴集团控股有限公司 交互方法、存储介质、服务程序和设备
CN112231021A (zh) * 2019-06-28 2021-01-15 百度在线网络技术（北京）有限公司 软件新功能的引导方法和装置
US20210027774A1 (en) * 2019-07-23 2021-01-28 Cdw Llc Automated graphical user interface control methods and systems using voice commands
CN112581946A (zh) * 2019-09-29 2021-03-30 百度在线网络技术（北京）有限公司 语音控制方法、装置、电子设备和可读存储介质
CN114115790A (zh) * 2021-11-12 2022-03-01 上汽通用五菱汽车股份有限公司 语音对话提示方法、装置、设备及计算机可读存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107146612B (zh) * 2017-04-10 2020-05-15 北京猎户星空科技有限公司 语音引导方法、装置、智能设备及服务器
US10402149B2 (en) * 2017-12-07 2019-09-03 Motorola Mobility Llc Electronic devices and methods for selectively recording input from authorized users
US11848016B2 (en) * 2018-08-07 2023-12-19 Huawei Technologies Co., Ltd. Voice control command generation method and terminal
CN108986814A (zh) * 2018-09-04 2018-12-11 出门问问信息科技有限公司 一种唤醒应用服务的方法及装置
CN109375768A (zh) * 2018-09-21 2019-02-22 北京猎户星空科技有限公司 互动式引导方法、装置、设备和存储介质
CN110503970B (zh) * 2018-11-23 2021-11-23 腾讯科技（深圳）有限公司 一种音频数据处理方法、装置及存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107277225A (zh) * 2017-05-04 2017-10-20 北京奇虎科技有限公司 语音控制智能设备的方法、装置和智能设备
CN111949240A (zh) * 2019-05-16 2020-11-17 阿里巴巴集团控股有限公司 交互方法、存储介质、服务程序和设备
CN110148414A (zh) * 2019-05-21 2019-08-20 大众问问(北京)信息科技有限公司 一种语音说法引导方法和装置
CN112231021A (zh) * 2019-06-28 2021-01-15 百度在线网络技术（北京）有限公司 软件新功能的引导方法和装置
US20210027774A1 (en) * 2019-07-23 2021-01-28 Cdw Llc Automated graphical user interface control methods and systems using voice commands
CN110493123A (zh) * 2019-09-16 2019-11-22 腾讯科技（深圳）有限公司 即时通讯方法、装置、设备及存储介质
CN112581946A (zh) * 2019-09-29 2021-03-30 百度在线网络技术（北京）有限公司 语音控制方法、装置、电子设备和可读存储介质
CN114115790A (zh) * 2021-11-12 2022-03-01 上汽通用五菱汽车股份有限公司 语音对话提示方法、装置、设备及计算机可读存储介质

Also Published As

Publication number Publication date
CN114115790A (zh) 2022-03-01

Similar Documents

Publication Publication Date Title
US11676601B2 (en) Voice assistant tracking and activation
US10522146B1 (en) Systems and methods for recognizing and performing voice commands during advertisement
US9809185B2 (en) Method and apparatus for subjective command control of vehicle systems
CN107112013B (zh) 用于创建可定制对话系统引擎的平台
US9188456B2 (en) System and method of fixing mistakes by going back in an electronic device
CN111661068B (zh) 智能体装置、智能体装置的控制方法及存储介质
EP3622390B1 (en) Multiple digital assistant coordination in vehicular environments
US20120183221A1 (en) Method and system for creating a voice recognition database for a mobile device using image processing and optical character recognition
EP2160915B1 (en) Automatic contact information entry via location sensing
JP2015528140A (ja) サードパーティサービスをデジタルアシスタントと統合するシステム及び方法
CN110019740B (zh) 车载终端的交互方法、车载终端、服务器和存储介质
US20160004502A1 (en) System and method for correcting speech input
WO2023082649A1 (zh) 语音对话提示方法、装置、设备及计算机可读存储介质
CN111681651B (zh) 智能体装置、智能体系统、服务器装置、智能体装置的控制方法及存储介质
KR20220143683A (ko) 전자 개인 비서 조정
JP2002123283A (ja) 音声認識操作装置
CN111667823B (zh) 智能体装置、智能体装置的控制方法及存储介质
CN111661065B (zh) 智能体装置、智能体装置的控制方法及存储介质
KR20210095569A (ko) 에이전트 시스템, 서버 및 컴퓨터 판독 가능한 기록 매체
CN115361473B (zh) 基于用户语音信息的代驾呼叫方法及相关产品
JP2021156994A (ja) 音声出力の制御方法および音声出力制御装置
CN111583918A (zh) 语音控制方法、车载终端及车辆
CN111739524B (zh) 智能体装置、智能体装置的控制方法及存储介质
US11893996B1 (en) Supplemental content output
CN112995270B (zh) 智能体系统、智能体系统的控制方法及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22891458

Country of ref document: EP

Kind code of ref document: A1