WO2020192245A1 - 应用开启方法、装置和计算机系统及介质 - Google Patents

应用开启方法、装置和计算机系统及介质 Download PDF

Info

Publication number
WO2020192245A1
WO2020192245A1 PCT/CN2020/071154 CN2020071154W WO2020192245A1 WO 2020192245 A1 WO2020192245 A1 WO 2020192245A1 CN 2020071154 W CN2020071154 W CN 2020071154W WO 2020192245 A1 WO2020192245 A1 WO 2020192245A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
application
voice
server
prompt
Prior art date
Application number
PCT/CN2020/071154
Other languages
English (en)
French (fr)
Inventor
申昀弘
操灿
Original Assignee
北京京东尚科信息技术有限公司
科大讯飞股份有限公司
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 北京京东尚科信息技术有限公司, 科大讯飞股份有限公司 filed Critical 北京京东尚科信息技术有限公司
Publication of WO2020192245A1 publication Critical patent/WO2020192245A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00Speaker identification or verification techniques
    • G10L17/22Interactive procedures; Man-machine interfaces
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00Speaker identification or verification techniques
    • G10L17/22Interactive procedures; Man-machine interfaces
    • G10L17/24Interactive procedures; Man-machine interfaces the user being prompted to utter a password or a predefined phrase
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223Execution procedure of a spoken command

Definitions

  • the present disclosure relates to the field of Internet technology, and more specifically, to an application opening method, device, computer system and medium.
  • the inventor found that at least the following problems exist in the prior art: the smart speaker's opening and interaction process is cumbersome, which affects the user experience.
  • the present disclosure provides an application startup method, device, computer system and medium that can start smart voice devices without relying on operating devices with display screens, and have a simple interaction process.
  • One aspect of the present disclosure provides an application opening method, which is suitable for a server, the server is connected to at least one smart voice device, and the server provides services for at least one application supported by the at least one smart voice device,
  • the method may include the following operations: first, receiving the first voice information sent by the smart voice device, and then, in response to receiving the first voice information sent by the smart voice device, analyzing the first voice information, if the first voice information is The voice information includes the application name and the operation of opening the application, then it is determined according to the application name whether the server can provide services to the requesting application corresponding to the application name, and then, if the server can provide services to the requesting application , And the requesting application is not started, then first prompt information is sent to the smart voice device, and the first prompt information is used by the smart voice device to prompt the user whether to open the requested application, and then receive the smart voice device to send Then, in response to receiving the second voice information sent by the smart voice device, analyze the second voice information to obtain a user instruction.
  • the request is opened And send second prompt information to the smart voice device, where the second prompt information is used by the smart voice device to prompt the user that the requested application has been opened.
  • the activation of control skills (opening the applications required by users in the intelligent voice device server) can be realized by voice, and the opening of the management and control skills application can improve non-target applications' answers to questions and other questions.
  • the way to enable the application of management and control skills can avoid the need for users to use a client such as a mobile phone to enable the application of management and control skills.
  • Voice makes the interactive mode of the application opening process more concise and helps improve user experience.
  • the method may further include the following operations: if the server can provide services to the requesting application, and the requesting application has been started, sending third prompt information to the smart voice device , The third prompt information is used for the smart voice device to prompt the user that the requested application has been opened. In this way, when the requesting application is already started, the user's request can be quickly responded to, prompting the requesting application to be started.
  • the method may further include the following operations: if the server cannot provide services to the requested application, sending fourth prompt information to the smart voice device, and the fourth prompt information is used
  • the intelligent voice device prompts the user to any one or more of the following information: first preset information, the requested application information does not exist, recommended application name information, or first recommended operation information. In this way, it can first determine whether the skill that the user wants to turn on exists. If it does not exist, it can prompt the user in time, such as there is no corresponding application or recommend related operations, so as to meet the user's needs.
  • the method may further include the following operations: if the user instruction includes not opening the requesting application, not opening the requesting application, and sending fifth prompt information to the smart voice device,
  • the fifth prompt information is used by the smart voice device to prompt the user any one or more of the following information: second preset information, information that the requested application has not been opened, or information that the application process has been exited.
  • second preset information information that the requested application has not been opened
  • information that the application process has been exited information that the application process has been exited.
  • the method may further include the following operations: if opening the requested application fails, sending sixth prompt information to the smart voice device, where the sixth prompt information is used for prompting by the smart voice device User any one or more of the following information: third preset information, failure to open the requested application information, or please open the requested application information again. This can prompt the user to try to open the application again when the application fails to open, such as when the current network environment is poor and accidentally fails to open.
  • the server may include at least a smart voice device server and a voice cloud server, which can realize a distributed design, so that different service terminals bear different business logics and deployments.
  • the first voice information or the second voice information may include the following operations: after the smart voice device server receives the first voice information or the second voice information, it transfers the first voice information or the second voice information The second voice information is sent to the voice cloud server, and then the voice cloud server converts the first voice information or the second voice information into structured text, and sends the structured text to The smart voice device server, and then, the smart voice device server obtains the application name and the corresponding operation from the structured text.
  • the server includes at least a smart voice device server, a voice cloud server, and a third-party server.
  • the smart voice device is a smart speaker.
  • This embodiment can implement the smart speaker directly according to the received information.
  • sending the first prompt information or the second prompt information to the smart speaker may include the following operations: the smart voice device server obtains the application from the structured text After the name and the corresponding operation, the intelligent voice device server executes the corresponding operation, and sends the structured text and the operation result of the corresponding operation to the third-party server.
  • the The third-party server generates a logical processing result in response to the first voice information and/or the second voice information according to the structured text and the operation result, and sends the logical processing result to the intelligent voice Device server, the logical processing result is text information, and then, the intelligent voice device server sends the logical processing result to the voice cloud server, and then the voice cloud server processes according to the logic
  • the first prompt information or the second prompt information is synthesized and sent to the intelligent voice device server, where the first prompt information and the second prompt information are voice information, and then, the The intelligent voice device server sends the first prompt information and/or the second prompt information to the smart speaker for voice broadcast.
  • a distributed design can be realized, allowing different servers to undertake different business logic and deployment, which helps to improve response speed and performance.
  • the method may further include the following operations: before starting the requesting application, if the requesting application has an associated application, and the associated application has an account, then the requesting application is not bound
  • the seventh prompt information is sent to the smart voice device when the account is used.
  • the seventh prompt information is used by the smart voice device to prompt the user any one or more of the following information: fourth preset information, smart voice on the client
  • the account information or the second recommended operation information is bound to the device application.
  • the opening of the requesting application may include the following operations: if the associated application has been logged in with the account, then opening the requesting application, in addition, if all If the associated application does not use the account to log in, it sends eighth prompt information to the smart voice device, and the eighth prompt information is used by the smart voice device to prompt the user of any one or more of the following information: fifth preset Information, using the account to log in the associated application information or the third recommended operation information on the client.
  • the embodiments of the present disclosure can prompt the user to log in and bind the account, so that the application of the associated application with the account can be opened, and the application of the associated application with the account can be avoided every time the application is opened. Need to enter account number.
  • binding an account to the requesting application may include the following operations: firstly, receiving the account and password of the associated application input by the user in the smart voice device application sent by the client, and then connecting the associated application
  • the account and password of the associated application are sent to the server of the associated application for authentication, and then the authentication passed information sent by the server of the associated application is received, wherein the server of the associated application checks the account and password of the associated application Perform authentication, and if the authentication is passed, then send authentication passed information to the server.
  • the authentication passed information includes a permission activation identifier that allows the user to access the associated application through the smart voice device application, and then identifies the
  • the authentication pass information generates prompt information for permission activation, and sends the prompt information for permission activation to the smart voice device for broadcasting and/or displays the permission activation information in the smart voice device application. In this way, it is possible to bind the account of the associated application of the requesting application with the smart voice device application, and indirectly realize the binding of the account of the requesting application and the associated application.
  • the method may further include the following operations: On the one hand, after the requesting application is opened, if the requesting application needs to fill in information, sending ninth prompt information to the smart voice device, so The ninth prompt information is used by the smart voice device to prompt the user any one or more of the following information: sixth preset information, information filled in in the smart voice device application of the client, or fourth recommended operation information, on the other hand, After sending the first prompt information to the smart voice device, if the second voice information is not received within the first specified time period, the first prompt information is sent to the smart voice device again, and if the second voice information remains within the second specified time period If the second voice information is not received, the requesting application is not opened.
  • the request application is not opened.
  • the method may include the following Operation: First, receive the first voice information sent by the user. If the first voice information includes wake-up information, send the first voice information to the server, and then receive the first voice message sent by the server. Prompt information, and prompt, the first prompt information is used to prompt the user whether to open the requested application, and then receive a second voice information sent by the user, the second voice information includes the information to open the requested application, and then , Sending the second voice information to the server, and then receiving and prompting the second prompt information sent by the server, the second prompt information being used to prompt the user that the requested application has been opened.
  • the method may further include the following operations: prompting in response to receiving the third prompt information sent by the server, wherein the third prompt information is used for prompting the user by the smart voice device
  • the requesting application is already open.
  • the method may further include the following operations: in response to receiving the fourth prompt information sent by the server, prompting, wherein the fourth prompt information is used by the smart voice device to prompt the user to any of the following One or more types of information: first preset information, the requested application information does not exist, recommended application name information, or first recommended operation information.
  • the method may further include the following operations: in response to receiving the fifth prompt information sent by the server, prompting, wherein the fifth prompt information is used to prompt the user by the intelligent voice device to any of the following One or more types of information: second preset information, information that the requested application has not been opened, or information that the application flow has been exited.
  • the method may further include the following operations: in response to receiving the sixth prompt information sent by the server, prompting, wherein the sixth prompt information is used by the intelligent voice device to prompt the user to any of the following One or more types of information: third preset information, failure information to open the requested application, or please open the requested application information again.
  • the method may further include the following operations: in response to receiving the seventh prompt information sent by the server, prompting, wherein the seventh prompt information is used by the intelligent voice device to prompt the user to any of the following One or more types of information: the fourth preset information, the account information bound in the smart voice device application of the client, or the second recommended operation information.
  • the method may further include the following operations: in response to receiving the eighth prompt information sent by the server, prompting, wherein the eighth prompt information is used by the intelligent voice device to prompt the user to any of the following One or more types of information: fifth preset information, using the account to log in the associated application information or third recommended operation information on the client.
  • the method may further include the following operations: in response to receiving the ninth prompt information sent by the server, prompting, wherein the ninth prompt information is used by the intelligent voice device to prompt the user to any of the following One or more types of information: sixth preset information, information filled in the smart voice device application of the client, or fourth recommended operation information.
  • Another aspect of the present disclosure provides an application opening device suitable for a server, the server is connected to at least one intelligent voice device, and the server provides services for at least one application supported by the at least one intelligent voice device
  • the application opening device may include: a first receiving module, a first determining module, a first sending module, a second receiving module, and a second sending module.
  • the first receiving module is configured to receive first voice information sent by a smart voice device
  • the first determining module is configured to analyze the first voice information in response to receiving the first voice information sent by the smart voice device If the first voice information includes an application name and an application start operation, it is determined whether the server can provide services to the requesting application corresponding to the application name according to the application name, and the first sending module is configured to: If the server can provide services to the requested application, and the requested application is not started, first prompt information is sent to the smart voice device, and the first prompt information is used for the smart voice device to prompt the user whether to open
  • the second receiving module is configured to receive second voice information sent by a smart voice device
  • the second sending module is configured to analyze the first voice information in response to receiving the second voice information sent by the smart voice device. 2.
  • the voice information receives a user instruction. If the user instruction includes opening the requested application, the requested application is opened, and second prompt information is sent to the smart voice device. The second prompt information is used by the smart voice The device prompts the
  • the device may further include a third sending module configured to provide services to the requesting application if the server can provide services to the requesting application
  • the smart voice device sends third prompt information, and the third prompt information is used by the smart voice device to prompt the user that the requested application has been opened.
  • the apparatus may further include a fourth sending module configured to send a fourth prompt to the smart voice device if the server cannot provide services to the requested application Information, the fourth prompt information is used by the smart voice device to prompt the user any one or more of the following information: first preset information, the requested application information does not exist, recommended application name information, or first recommended operation information .
  • the device may further include a fifth sending module configured to not open the requesting application if the user instruction includes not opening the requesting application, and give the The smart voice device sends fifth prompt information, where the fifth prompt information is used by the smart voice device to prompt the user any one or more of the following information: second preset information, the requested application information has not been opened, or the application has been exited Process information.
  • a fifth sending module configured to not open the requesting application if the user instruction includes not opening the requesting application, and give the The smart voice device sends fifth prompt information, where the fifth prompt information is used by the smart voice device to prompt the user any one or more of the following information: second preset information, the requested application information has not been opened, or the application has been exited Process information.
  • the device may further include a sixth sending module configured to send sixth prompt information to the smart voice device if the request application fails to be opened.
  • the prompt information is used by the smart voice device to prompt the user any one or more of the following information: third preset information, failure information to open the requested application, or please open the requested application information again.
  • the server may include at least a smart voice device server and a voice cloud server.
  • the smart voice device server is used to receive the first voice information or the second voice After the information, the first voice information or the second voice information is sent to the voice cloud server, and the voice cloud server is used to convert the first voice information or the second voice information into Structured text, and send the structured text to the smart voice device server, and the smart voice device server is also used to obtain application names and corresponding operations from the structured text.
  • the server includes at least a smart voice device server, a voice cloud server, and a third-party server.
  • the smart voice device is a smart speaker. Accordingly, the smart voice device server is used for After obtaining the application name and the corresponding operation from the structured text, the smart voice device server executes the corresponding operation, and sends the structured text and the operation result of the corresponding operation to the A third-party server, the third-party server is used to generate a logical processing result that responds to the first voice information and/or the second voice information according to the structured text and the operation result, and to combine the The logical processing result is sent to the intelligent voice device server, the logical processing result is text information, and the intelligent voice device server is configured to send the logical processing result to the voice cloud server, and the voice cloud The server is configured to synthesize the first prompt information or the second prompt information according to the logical processing result, and send it to the intelligent voice device server, where the first prompt information and the second prompt The information is voice information, and the smart voice device server
  • the device may further include a seventh sending module configured to, before starting the requesting application, if the requesting application has an associated application, and the associated application has an account, Then, when the requesting application is not bound to the account, the seventh prompt information is sent to the smart voice device, and the seventh prompt information is used by the smart voice device to prompt the user of any one or more of the following information: fourth The preset information, the account information or the second recommended operation information is bound in the smart voice device application of the client, and accordingly, the smart voice device server is specifically configured to enable if the associated application has logged in with the account The requesting application, and if the associated application does not use the account to log in, sending eighth prompt information to the smart voice device, where the eighth prompt information is used by the smart voice device to prompt the user to any of the following Or multiple types of information: fifth preset information, using the account to log in the associated application information or third recommended operation information on the client.
  • a seventh sending module configured to, before starting the requesting application, if the requesting application has an associated application, and
  • the apparatus may further include a ninth sending module configured to send information to the smart voice device if the request application needs to fill in information after the request application is opened Ninth prompt information, the ninth prompt information is used by the smart voice device to prompt the user any one or more of the following information: sixth preset information, information to be filled in the smart voice device application of the client, or fourth recommended operation information , And/or, the first sending module is specifically configured to send the first prompt information to the smart voice device, if the second voice information is not received within the first specified period of time, then send it to the smart voice device again Send the first prompt information.
  • a ninth sending module configured to send information to the smart voice device if the request application needs to fill in information after the request application is opened Ninth prompt information
  • the ninth prompt information is used by the smart voice device to prompt the user any one or more of the following information: sixth preset information, information to be filled in the smart voice device application of the client, or fourth recommended operation information
  • the first sending module is specifically configured to send the first prompt information to the smart voice device, if
  • the request application is not opened, and/or the first sending module is specifically configured to send to the smart voice device After the first prompt information, if the received voice information does not include opening the request application, the first prompt information is sent to the smart voice device again, and if the received voice information still does not include opening the request application, then Do not start the requested application.
  • an application opening device which is suitable for a smart voice device
  • the smart voice device is connected to a server, and the server provides services for at least one application supported by the smart voice device.
  • the device may include: a third receiving module, a tenth sending module, a first prompting module, a fourth receiving module, an eleventh sending module, and a second prompting module.
  • the third receiving module is configured to receive the first voice information sent by the user, and the tenth sending module is configured to send the first voice information to the first voice information if the first voice information includes a wake-up word
  • the first prompt module is configured to receive and prompt the first prompt information sent by the server side, and the first prompt information is used to prompt the user whether to open the requested application
  • the fourth receiving module Used to receive second voice information sent by the user, the eleventh sending module is used to send the second voice information to the server, and the second prompt module is used to receive the first sent by the server 2. Prompt information and give a prompt.
  • the second prompt information is used by the smart voice device to prompt the user that the request application has been opened.
  • Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above-mentioned method when executed.
  • Another aspect of the present disclosure provides a computer program that includes computer-executable instructions, which are used to implement the above-mentioned method when executed.
  • FIG. 1A schematically shows an application scenario of an application opening method, device, computer system and medium according to an embodiment of the present disclosure
  • FIG. 1B schematically shows a block diagram of a system architecture suitable for an application opening method according to an embodiment of the present disclosure
  • Figure 2A schematically shows a flow chart of a method for using a smart speaker in the prior art
  • FIG. 2B schematically shows a flowchart of an application opening method according to an embodiment of the present disclosure
  • FIG. 2C schematically shows a flowchart of a method for using a smart speaker according to an embodiment of the present disclosure
  • Fig. 2D schematically shows a flowchart of an application opening method according to another embodiment of the present disclosure
  • FIG. 3 schematically shows a flowchart of an application opening method according to another embodiment of the present disclosure
  • Fig. 4A schematically shows a block diagram of an application opening device according to an embodiment of the present disclosure
  • FIG. 4B schematically shows a block diagram of an application opening device according to another embodiment of the present disclosure.
  • Fig. 5 schematically shows a block diagram of a computer system suitable for applying an opening method according to an embodiment of the present disclosure.
  • At least one of the “systems” shall include but not limited to systems having A alone, B alone, C alone, A and B, A and C, B and C, and/or systems having A, B, C, etc. ).
  • At least one of the “systems” shall include but not limited to systems having A alone, B alone, C alone, A and B, A and C, B and C, and/or systems having A, B, C, etc. ).
  • the embodiments of the present disclosure provide an application opening method, device, computer system and medium. This method realizes the opening of management and control applications by voice. Specifically, the design method of application skills can be opened in the voice environment of the smart voice device. It aims to ensure the user's simple and independent operation in the natural language environment. Provide a smoother experience.
  • Fig. 1A schematically shows an application scenario of an application opening method, device, computer system and medium according to embodiments of the present disclosure.
  • a smart voice device such as a smart speaker
  • the user speaks to the smart speaker.
  • “Ding Dong Ding Dong, open guess the song name” you can open the required application through the smart speaker in the way of voice interaction, without the need to use a client with a display screen, such as a mobile phone, through the specific Only by operating the smart speaker application can the specific application of the smart speaker, such as the application of guessing the song name, be opened, and during the period, it will not lead to the situation that the user’s intention is entangled by multiple applications and the answer is not answered.
  • FIG. 1B schematically illustrates an exemplary system architecture 100 that can be applied to an application opening method according to an embodiment of the present disclosure. It should be noted that FIG. 1B is only an example of the system architecture to which the embodiments of the present disclosure can be applied to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used for other Equipment, system, environment or scenario.
  • the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and servers 105, 106, 107.
  • the network 104 is used to provide a medium of communication links between the terminal devices 101, 102, 103 and the servers 105, 106, 107.
  • the network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables.
  • the user can use the terminal devices 101, 102, and 103 to interact with the servers 105, 106, and 107 through the network 104 to receive or send messages.
  • Various communication client applications may be installed on the terminal devices 101 and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).
  • the terminal devices 101 and 103 may be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and so on.
  • the terminal device 102 may be an electronic device with a sound sensor and a speaker, including but not limited to a smart speaker, a smart terminal capable of voice interaction, and the like.
  • the servers 105, 106, and 107 may be servers that provide various services, for example, a background management server that provides services for at least one application supported by at least one terminal device 101, 102, 103 (for example), and performs voice recognition and semantics on speech.
  • a server for understanding and/or speech synthesis a server for logically processing user questions or requests and giving answers to the content, etc.
  • the background management server may analyze and process the received user request and other data, and feed back the processing result (for example, webpage, information, or data obtained or generated according to the user request) to the terminal device.
  • the application opening method provided by the embodiment of the present disclosure may be executed by the server 105, 106, 107, or executed by the terminal device 101, 102, 103.
  • the application opening device provided in the embodiment of the present disclosure may generally be set in the servers 105, 106, 107, or may be set in the terminal devices 101, 102, 103.
  • the application opening method provided in the embodiments of the present disclosure can also be executed by a server or a server cluster that is different from the servers 105, 106, 107 and can communicate with the terminal devices 101, 102, 103 and/or the servers 105, 106, 107.
  • the application opening device provided by the embodiment of the present disclosure can also be set in a server or server cluster that is different from the servers 105, 106, 107 and can communicate with the terminal devices 101, 102, 103 and/or the servers 105, 106, 107 in.
  • terminal devices are merely illustrative. According to implementation needs, there can be any number of terminal devices, networks and servers.
  • Fig. 2A schematically shows a flow chart of a method for using a smart speaker in the prior art.
  • the skill activation phase is due to the use of the smart speaker
  • the skill use phase is due to the use of the smart speaker
  • which skills should be activated when using which skills to avoid non-target applications from making mistakes in user instructions In order to avoid the semantic entanglement of the user’s intentions and the occurrence of non-questioning situations, which skills should be activated when using which skills to avoid non-target applications from making mistakes in user instructions.
  • the shopping application thinks that the user needs to buy "Forget Worry Grass” and causes a misoperation. Therefore, in the prior art, the user is required to activate the corresponding skills in the skill center of the application APP (such as the speaker APP), such as the skill of guessing the song name.
  • the speaker APP of the client sends the user instructions to the server, such as the speaker cloud server and the speaker cloud. After receiving the user's instruction, the server turns on the song name guessing skill and returns the activation result. At this time, it can enter the skill use stage.
  • the user can use the song name guessing application, and the specific usage method can be supported by various existing technologies.
  • the smart speaker queries the skill content from the speaker cloud server, and the speaker cloud server returns the broadcast skill result.
  • the skill-opening operation in the prior art relies on the operation of the device with a display screen, and the interaction process is cumbersome, and the user has a high barrier to use; in addition, the existing skill-opening method restricts the further upgrade of the smart speaker product form. Also affected the user experience.
  • Fig. 2B schematically shows a flowchart of an application opening method according to an embodiment of the present disclosure.
  • This method is applicable to a server, the server is connected to at least one intelligent voice device, and the server provides services to at least one application supported by the at least one intelligent voice device. As shown in FIG. 2B, the method may include Operation S201 ⁇ operation S205.
  • the first voice information may be various voice information sent by the user to the smart voice device, for example, various voice commands during human-computer interaction.
  • the first first voice message sent by the smart voice device may contain wake-up information, such as a wake-up word, for example, "Ding Dong Ding Dong, open to guess the song name", where Ding Dong Ding Dong means wake up Words can prevent the intelligent voice device from sending too many useless voice messages to the server and causing waste of resources.
  • the first voice information does not necessarily include information for opening a certain application, and may also be voice information for interacting with other applications.
  • the first voice information is analyzed, and if the first voice information includes the application name and the operation to open the application, determine according to the application name Whether the server can provide services to the requesting application corresponding to the application name.
  • the smart voice device server has a list of applications that can provide services, etc.
  • the text result is obtained by analyzing the first voice information, and then it can be judged whether the text result includes the application name and the operation of opening the application.
  • the server includes at least an intelligent voice device server and a voice cloud server.
  • analyzing the first voice information may include the following operations.
  • the smart voice device server After receiving the first voice information, the smart voice device server sends the first voice information to the voice cloud server.
  • the voice cloud server converts the first voice information into structured text, and sends the structured text to the intelligent voice device server.
  • the intelligent voice device server obtains the application name and the corresponding operation from the structured text.
  • the user says “Ding Dong Ding Dong, open the song name guessing application”
  • the smart speaker is awakened by the wake word “Ding Dong Ding Dong”
  • the voice of "open the song name guessing application” is sent to the smart voice device server, and the smart voice device server will send the voice of "Dingdongdingdong, open the song name guessing application” or “open the song guessing application” to the voice cloud
  • the server performs speech recognition and semantic understanding, and converts the speech into structured text, such as the structured text of "open the operation, guess the song name by the application name”, and then send the structured text to the smart voice device server, smart voice device
  • the server extracts the application name from the structured text to guess the song name, and the operation is to open it.
  • first prompt information is sent to the smart voice device, and the first prompt information is used for the smart voice
  • the device prompts the user whether to open the requested application.
  • the server can use the application name contained in the structured text to search in the list of supported application names. If there is a search result, it indicates that the server can provide services to the requested application.
  • the terminal can also store the status of each skill of each smart speaker connected to the server, such as whether the skill is in an on state or not. If the server can provide services to the requesting application, and the requesting application is not started, send first prompt information to the smart voice device.
  • the first prompt information may be voice information, text information, or indicator light Various sound and light information such as letter and ringing information. The sound and light information is used to prompt the user whether to activate the skill.
  • the first prompt information is prompt information in the form of voice broadcast, so that the user can obtain the prompt information more intuitively and make the voice interaction process smoother.
  • the server may include at least a smart voice device server, a voice cloud server, and a third-party server, the smart voice device is a smart speaker, and the first prompt information is a prompt in the form of a voice broadcast information.
  • sending the first prompt information to the smart speaker may include the following operations.
  • the smart voice device server After the smart voice device server obtains the application name and the corresponding operation from the structured text, the smart voice device server executes the corresponding operation, and combines the structured text and the corresponding operation The operation result of the operation is sent to the third-party server.
  • the third-party server generates a logical processing result in response to the first voice information according to the structured text and the operation result, and sends the logical processing result to the intelligent voice device server, so
  • the result of the logic processing is text information.
  • the intelligent voice device server sends the logical processing result to the voice cloud server.
  • the voice cloud server synthesizes the first prompt information according to the logical processing result, and sends it to the intelligent voice device server, where the first prompt information is voice information.
  • the smart voice device server sends the first prompt information to the smart speaker for voice broadcast.
  • a distributed design can be realized, allowing different servers to undertake different business logic and deployment, which helps to improve response speed and performance.
  • the smart voice device server receives the structured text of "Operation is open, app name guessing the song name", it is determined that the song name guessing application can be provided with services, and the song name guessing application is not opened , Therefore, the structured text of "open the operation, app name guessing the song name" and the state that the song name guessing application is not opened can be sent to the third-party server, and the third-party server performs a check on the received information.
  • Logic processing to get the result of the logic processing such as "You haven't activated XXXX (app name), do you apply” or "You haven't activated guess the song name, do you activate” text, and then send the text to the smart voice device
  • the smart voice device server will treat "You haven't activated XXXX (app name), do you want to activate”” as "You haven't activated Guess the song name, do you activate?”
  • the text of “name, whether to activate” is sent to the voice cloud server, and the voice of “you have not activated to guess the song name, do you activate” is synthesized and sent to the smart voice device server, the smart voice device server Send the voice message of "You haven't activated Guess the song name, do you activate” to the smart voice device for voice broadcast.
  • any one or more of speech recognition, semantic understanding, speech synthesis, and logic processing can also be performed on the smart voice device server or smart voice device. There is no limitation here. When the processing capacity of the intelligent voice device is limited, or higher quality results are required, the information can be processed by the corresponding remote server.
  • the second voice information may include or not include the wake-up word, and may also include or not include the application name.
  • the user For example, the user’s voice "Ding Dong Ding Dong, turn on song name guessing", “turn on song name guessing", "Yes (Of)/open/open/good (of)” etc.
  • the second voice information should have timeliness. For example, after sending the first prompt information to the smart voice device, if the second voice information is not received within the first specified period of time, the first prompt information is sent to the smart voice device again, if the second specified time If the second voice information is not received within the time period, the requesting application is not opened, and the process of starting the requesting application is exited. If the user does not speak for 5 seconds, 7 seconds, 10 seconds, or 20 seconds, they will ask again, and exit the process after asking twice.
  • the method may further include the following operations: after sending the first prompt information to the smart voice device, if the received voice information does not include opening the requesting application, then Sending the first prompt information to the smart voice device again, and if the received voice information still does not include the opening of the requesting application, the requesting application is not opened. This can effectively improve the accuracy of the operation without a wake-up word after the first voice interaction.
  • operation S205 in response to receiving the second voice information sent by the smart voice device, analyze the second voice information to obtain a user instruction, and if the user instruction includes opening the request application, start the request application and give The smart voice device sends second prompt information, and the second prompt information is used by the smart voice device to prompt the user that the request application has been opened.
  • the process of analyzing the second voice information can refer to the process of analyzing the first voice information.
  • the voice cloud server parses the second voice information into structured text and sends it to intelligent voice.
  • the device server side will not be repeated here.
  • the process of sending the second prompt information to the smart speaker can also refer to the above-mentioned process of sending the first prompt information to the smart speaker.
  • a third-party server provides a logical processing result to the smart voice device server.
  • the voice cloud server performs speech synthesis on the logical processing result and sends it to the intelligent voice device server, which will not be repeated here.
  • the server sends a voice message "opened/opened/entered application interaction process" to the smart speaker to facilitate the smart speaker to broadcast.
  • Fig. 2C schematically shows a flowchart of a method for using a smart speaker according to an embodiment of the present disclosure.
  • the application process may also be included, and the application process may be the same as the prior art, which will not be repeated here.
  • the application opening method provided by the present disclosure realizes the opening of the management skill application by voice, which can avoid the need for users to use a client such as a mobile phone to realize the opening of the management skill application, and the interaction of the application opening process is simplified through voice.
  • the present disclosure The provided application opening method can effectively avoid non-target applications' questions such as unanswered questions, and effectively improve the entanglement of the semantics of user intentions, which helps improve user experience.
  • the method may further include the following operations: if the server can provide services to the requesting application, and the requesting application has been started, sending third prompt information to the smart voice device , The third prompt information is used for the smart voice device to prompt the user that the requested application has been opened. In this way, when the requesting application is already started, the user's request can be quickly responded to, prompting the requesting application to be started.
  • the user sends a voice message to the smart speaker: "Dingdong Dingdong, enable/enable/enable XXXX (app name)", the smart speaker will send “Enable/enable/enable XXXX (app name)” to the server, and The smart speaker receives and broadcasts the voice prompt message: "XXXX has been opened for you/enter application interaction process”.
  • the method may further include the following operations: if the server cannot provide services to the requested application, sending fourth prompt information to the smart voice device, and the fourth prompt information is used
  • the intelligent voice device prompts the user to any one or more of the following information: first preset information, the requested application information does not exist, recommended application name information, or first recommended operation information. In this way, it can first determine whether the skill that the user wants to turn on exists. If it does not exist, it can prompt the user in time, such as there is no corresponding application or recommend related operations, so as to meet the user's needs.
  • the first preset information may include preset text information or voice information, and the following preset information is similar.
  • the user sends a voice message to the smart speaker: "Dingdong Dingdong, enable/enable/enable XXXX (app name)", the smart speaker will send “Enable/enable/enable XXXX (app name)” to the server, and The smart speaker receives and broadcasts the voice prompt message: "App not found, enter other processes/App not found, do you want to turn on Guess the singer/App not found? It is recommended to check the application list/App not found in the smart speaker APP on the mobile phone, whether Need to broadcast application list”.
  • the method may further include the following operations: if the user instruction includes not opening the request application, not opening the request application, and sending fifth prompt information to the smart voice device,
  • the fifth prompt information is used by the smart voice device to prompt the user any one or more of the following information: second preset information, information that the requested application has not been opened, or information that the application process has been exited. In this way, the process of opening the application can be ended in time when the user changes his intention and does not want to open the requested application.
  • the user sends a voice message to the smart speaker: "Dingdong Dingdong, enable/enable/enable XXXX (app name)", the smart speaker will send “Enable/enable/enable XXXX (app name)” to the server, and The smart speaker receives and broadcasts the voice prompt message: "You have not activated XXXX (application name), do you want to activate?"
  • the user sends out the voice "No (Yes)/No/Do not activate”
  • the smart speaker sends "No (Yes)/No/Do not activate” to the server, and the smart speaker receives and broadcasts the voice prompt message: "Not activated XXXX (application Name)/Exit the XXXX process opened/Closed XXXX (application name)”.
  • the method may further include the following operations: if opening the requested application fails, sending sixth prompt information to the smart voice device, where the sixth prompt information is used for prompting by the smart voice device User any one or more of the following information: third preset information, failure to open the requested application information, or please open the requested application information again. This can prompt the user to try to open the application again when the application fails to open, such as when the current network environment is poor and accidentally fails to open.
  • the user sends a voice message to the smart speaker: "Dingdong Dingdong, enable/enable/enable XXXX (app name)", the smart speaker will send “Enable/enable/enable XXXX (app name)” to the server, and The smart speaker receives and broadcasts the voice prompt message: "I seem to have slipped my account, and the activation is not successful. Can you, a kind host like you, try again?/The application has been activated. The amount of information is a bit large. Please wait a moment. Open XXXX (application name)".
  • Fig. 2D schematically shows a flowchart of an application opening method according to another embodiment of the present disclosure.
  • the method may further include the operations of detecting whether the requested application has an associated application, detecting whether the associated application has an account, and whether the associated application facilitates account login.
  • the operations may be made to the embodiments shown above, and only the different parts are described here.
  • the method may further include the following operations.
  • the smart voice device sends seventh prompt information, where the seventh prompt information is used by the smart voice device to prompt the user any one or more of the following information: fourth preset information, bound in the smart voice device application of the client Account information or second recommended operation information.
  • opening the requesting application may include the following operations.
  • the requesting application is started.
  • the eighth prompt information is sent to the smart voice device, and the eighth prompt information is used by the smart voice device to prompt the user to any one of the following One or more types of information: the fifth preset information, the associated application information or the third recommended operation information for logging in with the account on the client.
  • the requesting application needs to be bound to the account of the associated application before it can be started, it can be determined whether the user has already bound the account of the associated application. If it is not bound, the user can be prompted through the smart voice device to bind the account, and then Then open the requested application, for example, you can send a voice message to the smart speaker, "Please bind a JD account under the mobile client account, and then open XXXX (application name) / Please bind the account under the mobile client application platform , Then open XXXX (application name)".
  • binding an account to the requesting application may include the following operations.
  • the account and password of the associated application are sent to the server of the associated application for authentication.
  • the server of the associated application authenticates the account and password of the associated application, and if the authentication is passed, it sends the authentication passed to the server Information
  • the authentication passing information includes a permission activation identifier that allows the user to access the associated application through the smart voice device application.
  • the authentication passing information is recognized to generate prompt information for permission activation, and the prompt information for permission activation is sent to the smart voice device for broadcasting and/or the permission activation information is displayed in the smart voice device application.
  • the Jingdong Mall application has an account and password. If you do not log in to the Jingdong Mall application, you cannot make purchases. At this time, the user is required to enter the account and password of the associated application in the smart voice device application on the client for authentication and Bind.
  • Fig. 3 schematically shows a flowchart of an application opening method according to another embodiment of the present disclosure.
  • the application opening method is applicable to a smart voice device, the smart voice device is connected to a server, and the server provides services for at least one application supported by the smart voice device, as shown in FIG. 3,
  • the method may include operation S301 to operation S306.
  • first prompt information sent by the server is received and prompted, where the first prompt information is used to prompt the user whether to start the request application.
  • a second voice information sent by a user is received, where the second voice information includes information about starting the request application.
  • the second prompt information is used to prompt the user that the requested application has been started.
  • the method may further include the following operations.
  • a prompt is performed in response to receiving the third prompt information sent by the server, where the third prompt information is used to prompt the user that the requested application has been opened by the smart voice device.
  • a prompt is performed in response to receiving the fourth prompt information sent by the server, where the fourth prompt information is used for prompting the user with any one or more of the following information by the intelligent voice device: The preset information, the requested application information, the recommended application name information, or the first recommended operation information does not exist.
  • a prompt is performed in response to receiving the fifth prompt information sent by the server, wherein the fifth prompt information is used for prompting the user with any one or more of the following information by the intelligent voice device: The preset information, the requested application information has not been opened or the application flow information has been exited.
  • a prompt is performed in response to receiving the sixth prompt information sent by the server, where the sixth prompt information is used to prompt the user of any one or more of the following information by the intelligent voice device: third Preset information, failure information to open the requested application or please open the requested application information again.
  • a prompt is performed in response to receiving the seventh prompt information sent by the server, where the seventh prompt information is used to prompt the user of any one or more of the following information by the intelligent voice device:
  • the preset information, the account information or the second recommended operation information is bound in the smart voice device application of the client.
  • a prompt is performed in response to receiving the eighth prompt information sent by the server, where the eighth prompt information is used for prompting the user with any one or more of the following information by the intelligent voice device: The preset information, using the account to log in the associated application information or the third recommended operation information on the client.
  • a prompt is performed in response to receiving the ninth prompt information sent by the server, where the ninth prompt information is used to prompt the user of any one or more of the following information by the intelligent voice device: Preset information, fill in information or fourth recommended operation information in the smart voice device application of the client.
  • the detailed content of the first prompt information, the second prompt information, the third prompt information, the fourth prompt information, the fifth prompt information, the sixth prompt information, the seventh prompt information, the eighth prompt information, and the ninth prompt information You can refer to related descriptions on the server, such as the related descriptions on the first prompt information and the second prompt information in operations S201 to S205, which are not repeated here.
  • Fig. 4A schematically shows a block diagram of an application opening device according to an embodiment of the present disclosure.
  • the application opening device may be applicable to a server, the server is connected to at least one intelligent voice device, and the server provides a service for at least one application supported by the at least one intelligent voice device.
  • the application opening device 400 may include a first receiving module 410, a first determining module 420, a first sending module 430, a second receiving module 440, and a second sending module 450.
  • the first receiving module 410 is configured to receive first voice information sent by a smart voice device.
  • the first determining module 420 is configured to analyze the first voice information in response to receiving the first voice information sent by the smart voice device, and if the first voice information includes the application name and the operation of opening the application, according to the The application name determines whether the server can provide services to the requesting application corresponding to the application name.
  • the first sending module 430 is configured to send first prompt information to the smart voice device if the server can provide services to the requested application and the requested application is not started.
  • the intelligent voice device prompts the user whether to open the requested application.
  • the second receiving module 440 is configured to receive second voice information sent by the smart voice device.
  • the second sending module 450 is configured to, in response to receiving the second voice information sent by the smart voice device, analyze the second voice information to obtain a user instruction, and if the user instruction includes opening the requested application, open the Request an application, and send second prompt information to the smart voice device, where the second prompt information is used by the smart voice device to prompt the user that the requested application has been opened.
  • the device 400 may also include a third sending module, which is used to send the smart voice device to the smart voice device if the server can provide services to the requested application, and the requested application has been started. Sending third prompt information, where the third prompt information is used by the smart voice device to prompt the user that the requested application has been opened.
  • a third sending module which is used to send the smart voice device to the smart voice device if the server can provide services to the requested application, and the requested application has been started.
  • Sending third prompt information where the third prompt information is used by the smart voice device to prompt the user that the requested application has been opened.
  • the apparatus 400 may further include a fourth sending module, which is used to provide the smart voice device if the server cannot provide services to the requested application Send fourth prompt information, the fourth prompt information is used by the smart voice device to prompt the user any one or more of the following information: the first preset information, the requested application information does not exist, the recommended application name information, or the first One recommended operation information.
  • the device 400 may further include a fifth sending module, which is used to if the user instruction includes not opening the request Application, the requesting application is not opened, and fifth prompt information is sent to the smart voice device, and the fifth prompt information is used by the smart voice device to prompt the user any one or more of the following information: second preset Information, the requested application information has not been opened or the application flow information has been exited.
  • a fifth sending module which is used to if the user instruction includes not opening the request Application, the requesting application is not opened, and fifth prompt information is sent to the smart voice device, and the fifth prompt information is used by the smart voice device to prompt the user any one or more of the following information: second preset Information, the requested application information has not been opened or the application flow information has been exited.
  • the device 400 may further include a sixth sending module, which is used if the request application fails to be opened , The sixth prompt information is sent to the smart voice device, where the sixth prompt information is used by the smart voice device to prompt the user of any one or more of the following information: third preset information, failure to open the requested application Or please open the request application information again.
  • the server may include at least a smart voice device server and a voice cloud server.
  • the smart voice device server is used to receive the first voice information or the second voice information, The first voice information or the second voice information is sent to the voice cloud server, and the voice cloud server is used to convert the first voice information or the second voice information into structured text, and The structured text is sent to the smart voice device server, and the smart voice device server is also used to obtain the application name and the corresponding operation from the structured text.
  • the server includes at least a smart voice device server, a voice cloud server, and a third-party server, and the smart voice device is a smart speaker.
  • the smart voice device server After the smart voice device server is used to obtain the application name and the corresponding operation from the structured text, the smart voice device server executes the corresponding operation and combines the structured text and the corresponding operation The operation result of the operation is sent to the third-party server.
  • the third-party server is configured to generate a logical processing result in response to the first voice information and/or the second voice information according to the structured text and the operation result, and send the logical processing result to On the server side of the intelligent voice device, the logical processing result is text information.
  • the intelligent voice device server is used to send the logical processing result to the voice cloud server.
  • the voice cloud server is used to synthesize the first prompt information or the second prompt information according to the logical processing result, and send it to the intelligent voice device server, wherein the first prompt information and the The second prompt information is voice information.
  • the smart voice device server is used to send the first prompt information and/or the second prompt information to the smart speaker for voice broadcast.
  • the device 400 may also include a seventh sending module, which is used to, before opening the requested application, if the requested application has an associated application, and If the associated application has an account, when the requesting application is not bound to the account, the seventh prompt information is sent to the smart voice device, and the seventh prompt information is used by the smart voice device to prompt the user any one of the following or Various types of information: fourth preset information, binding account information or second recommended operation information in the smart voice device application of the client.
  • the smart voice device server is specifically configured to open the requesting application if the associated application has logged in with the account, and if the associated application has not logged in with the account, send The smart voice device sends eighth prompt information, which is used by the smart voice device to prompt the user of any one or more of the following information: fifth preset information, using the account to log in to the associated application on the client Information or third recommended action information.
  • the apparatus 400 may further include a ninth sending module, configured to send ninth prompt information to the smart voice device if the requesting application needs to fill in information after the requesting application is opened,
  • the ninth prompt information is used by the smart voice device to prompt the user any one or more of the following information: sixth preset information, information filled in the smart voice device application of the client, or fourth recommended operation information.
  • the first sending module 430 is specifically configured to send the first prompt information to the smart voice device, if the first specified duration If the second voice information is not received within, the first prompt information is sent to the smart voice device again, and if the second voice information is not received within the second specified time period, the request application is not started.
  • the first sending module 430 is specifically configured to After sending the first prompt information to the smart voice device, if the received voice information does not include opening the requested application, the first prompt information is sent to the smart voice device again, if the received voice information still does not include If the requesting application is opened, the requesting application is not opened.
  • Fig. 4B schematically shows a block diagram of an application opening device according to another embodiment of the present disclosure.
  • the present disclosure also provides an application activation device 700, which is suitable for a smart voice device, the smart voice device is connected to a server, and the server provides services for at least one application supported by the smart voice device, such as As shown in FIG. 4B, the apparatus 700 may include: a third receiving module 710, a tenth sending module 720, a first prompting module 730, a fourth receiving module 740, an eleventh sending module 750, and a second prompting module 760.
  • the third receiving module 710 is configured to receive the first voice information sent by the user.
  • the tenth sending module 720 is configured to send the first voice information to the server if the first voice information includes a wake-up word.
  • the first prompt module 730 is configured to receive and prompt the first prompt information sent by the server, where the first prompt information is used to prompt the user whether to start the request application.
  • the fourth receiving module 740 is configured to receive the second voice information sent by the user.
  • the eleventh sending module 750 is configured to send the second voice information to the server.
  • the second prompt module 760 is configured to receive second prompt information sent by the server, and perform prompts, where the second prompt information is used to prompt the user to have started the requested application by the smart voice device.
  • the device 700 may further include a third prompt module, a fourth prompt module, a fifth prompt module, a sixth prompt module, and a seventh prompt module (not shown), etc., each of which has a prompt for the first prompt
  • the three prompt information, the fourth prompt information, the fifth prompt information, the sixth prompt information, the seventh prompt information, etc., are not repeated here.
  • any number of modules, submodules, units, and subunits, or at least part of the functions of any number of them, may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be split into multiple modules for implementation.
  • any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), System-on-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or hardware or firmware in any other reasonable way that integrates or encapsulates the circuit, or can be implemented by software, hardware, and firmware. Any one of these implementations or an appropriate combination of any of them can be implemented.
  • FPGA field programmable gate array
  • PLA programmable logic array
  • ASIC application-specific integrated circuit
  • any one of these implementations or an appropriate combination of any of them can be implemented.
  • one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be at least partially implemented as a computer program module, and the computer program module may perform corresponding functions when it is executed.
  • any of the first receiving module 410, the first determining module 420, the first sending module 430, the second receiving module 440, and the second sending module 450 can be combined into one module, or any one of them Can be split into multiple modules. Or, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module.
  • At least one of the first receiving module 410, the first determining module 420, the first sending module 430, the second receiving module 440, and the second sending module 450 may be at least partially implemented as a hardware circuit, For example, a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or any other that can integrate or package the circuit It can be implemented in hardware or firmware in a reasonable manner, or implemented in any one of the three implementation methods of software, hardware, and firmware, or an appropriate combination of any of them.
  • FPGA field programmable gate array
  • PLA programmable logic array
  • ASIC application specific integrated circuit
  • At least one of the first receiving module 410, the first determining module 420, the first sending module 430, the second receiving module 440, and the second sending module 450 may be at least partially implemented as a computer program module, when the computer program When the module is running, it can perform corresponding functions.
  • FIG. 5 schematically shows a block diagram of a computer system suitable for implementing the method described above according to an embodiment of the present disclosure.
  • the computer system shown in FIG. 5 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • a computer system 500 includes a processor 501, which can be loaded into a random access memory (RAM) 503 according to a program stored in a read only memory (ROM) 502 or from a storage part 508 The program executes various appropriate actions and processing.
  • the processor 501 may include, for example, a general-purpose microprocessor (for example, a CPU), an instruction set processor and/or a related chipset and/or a special purpose microprocessor (for example, an application specific integrated circuit (ASIC)), and so on.
  • the processor 501 may also include on-board memory for caching purposes.
  • the processor 501 may include a single processing unit or multiple processing units for performing different actions of a method flow according to an embodiment of the present disclosure.
  • the processor 501 executes various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 502 and/or RAM 503. It should be noted that the program can also be stored in one or more memories other than ROM 502 and RAM 503. The processor 501 may also execute various operations of the method flow according to the embodiments of the present disclosure by executing programs stored in the one or more memories.
  • the system 500 may further include an input/output (I/O) interface 505, and the input/output (I/O) interface 505 is also connected to the bus 504.
  • the system 500 may also include one or more of the following components connected to the I/O interface 505: an input part 506 including a keyboard, a mouse, etc.; including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker
  • the output section 507 including the hard disk, etc.
  • the storage section 508 including a hard disk, etc.
  • the communication section 509 including a network interface card such as a LAN card, a modem, and the like.
  • the communication section 509 performs communication processing via a network such as the Internet.
  • the driver 610 is also connected to the I/O interface 505 as needed.
  • a removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that the computer program read from it is installed into the storage portion 508 as needed.
  • the method flow according to the embodiment of the present disclosure may be implemented as a computer software program.
  • the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication part 509, and/or installed from the removable medium 611.
  • the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed.
  • the above-described systems, devices, devices, modules, units, etc. may be implemented by computer program modules.
  • the present disclosure also provides a computer-readable storage medium.
  • the computer-readable storage medium may be included in the device/device/system described in the above embodiment; or it may exist alone without being assembled into the device/ In the device/system.
  • the aforementioned computer-readable storage medium carries one or more programs, and when the aforementioned one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but not limited to: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM) , Erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable storage medium may include one or more memories other than the ROM 502 and/or RAM 503 and/or ROM 502 and RAM 503 described above.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the above-mentioned module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions.
  • the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be It is realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Telephonic Communication Services (AREA)

Abstract

一种应用开启方法、开启装置及其计算机系统和存储介质,该方法包括:接收智能语音设备发送的第一语音信息(S201);响应于接收到智能语音设备发送的第一语音信息,分析该第一语音信息,如果第一语音信息包括应用名称及开启应用操作,则根据应用名称确定服务端是否能对应用名称对应的请求应用提供服务(S202);如果服务端能对请求应用提供服务,且请求应用未开启,则给智能语音设备发送第一提示信息(S203);接收智能语音设备发送的第二语音信息(S204);响应于接收到智能语音设备发送的第二语音信息,分析第二语音信息得到用户指令,如果用户指令包括开启该请求应用,则开启请求应用,并给智能语音设备发送第二提示信息(S205)。

Description

应用开启方法、装置和计算机系统及介质
本公开要求于2019-03-22递交的申请号为201910221856.4的中国申请的优先权,其内容一并在此作为参考。
技术领域
本公开涉及互联网技术领域,更具体地,涉及一种应用开启方法、装置和计算机系统及介质。
背景技术
随着人工智能、通信和计算机技术的快速发展,智能音箱越来越多地进入人们的日常生活中。
在使用智能音箱技能时,需要先在智能音箱对应的手机上的智能音箱应用(application,简称APP)上开启所需的技能,这样才能在智能音箱上使用该技能。
在实现本公开构思的过程中,发明人发现现有技术中至少存在如下问题:智能音箱的开启交互过程繁琐,影响了用户体验。
发明内容
有鉴于此,本公开提供了一种无需依赖于对有显示屏的设备进行操作即可开启智能语音设备的技能,且交互过程简洁的应用开启方法、装置和计算机系统及介质。
本公开的一个方面提供了一种应用开启方法,适用于服务端,所述服务端与至少一个智能语音设备相连,所述服务端对所述至少一个智能语音设备支持的至少一个应用提供服务,所述方法可以包括如下操作:首先,接收智能语音设备发送的第一语音信息,接着,响应于接收到智能语音设备发送的第一语音信息,分析所述第一语音信息,如果所述第一语音信息包括应用名称及开启应用操作,则根据所述应用名称确定所述服务端是否能对所述应用名称对应的请求应用提供服务,然后,如果所述服务端能对所述请求应用提供服务,且所述请求应用未开启,则给所述智能语音设备发送第一提示信息,所述第一提示信息用于由智能语音设备提示用户是否开启所述请求应用,接着,接收智能语音设备发送的第二语音信息,然后,响应于接收到智能语音设备发送的第二语音信息,分析所述第二语音信息得到用户指令,如果所述用户指令包括开启所述请求应用,则开启所述请求应用,并给所述智能语音设备发送第二提示信息,所述第二提示信息用于由智能语音设备提示用户已 开启所述请求应用。通过本公开的实施例可以通过语音的方式实现管控技能的开启(打开智能语音设备服务端中的用户所需的应用),通过管控技能应用的开启来改善非目标应用的答非所问等问题,语音的方式实现管控技能应用的开启可以避免用户需要利用客户端如手机来实现管控技能应用的开启,通过语音使得应用开启过程的交互方式更简洁,有助于改善用户体验。
根据本公开的实施例,所述方法还可以包括如下操作:如果所述服务端能对所述请求应用提供服务,且所述请求应用已开启,则给所述智能语音设备发送第三提示信息,所述第三提示信息用于由智能语音设备提示用户所述请求应用已开启。这样当所述请求应用已开启时,可以快速响应用户的请求,提示所述请求应用已开启。
根据本公开的实施例,所述方法还可以包括如下操作:如果所述服务端不能对所述请求应用提供服务,则给所述智能语音设备发送第四提示信息,所述第四提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第一预设信息、不存在所述请求应用信息、推荐的应用名称信息或第一推荐操作信息。这样可以首先判断用户希望开启的技能是否存在,如果不存在,则可以及时给用户提示信息,如不存在相应的应用或推荐相关的操作等,以便满足用户的需求。
根据本公开的实施例,所述方法还可以包括如下操作:如果所述用户指令包括不开启所述请求应用,则不开启所述请求应用,并给所述智能语音设备发送第五提示信息,所述第五提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第二预设信息、未开启所述请求应用信息或已退出开启应用流程信息。这样可以在用户改变意图,不希望开启所述请求应用时及时结束开启应用的流程。
根据本公开的实施例,所述方法还可以包括如下操作:如果开启所述请求应用失败,则给所述智能语音设备发送第六提示信息,所述第六提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第三预设信息、开启所述请求应用失败信息或请再次开启所述请求应用信息。这样可以在应用开启失败时,如当前网络环境较差导致偶然开启失败时,提示用户尝试再次开启应用等。
根据本公开的实施例,所述服务端可以至少包括智能语音设备服务端和语音云服务端,这样可以实现分布式设计,使得不同的服务端承担不同的业务逻辑和部署,相应地,分析所述第一语音信息或所述第二语音信息可以包括如下操作:所述智能语音设备服务端接收所述第一语音信息或所述第二语音信息之后,将所述第一语音信息或所述第二语音信息发送给所述语音云服务端,接着,所述语音云服务端将所述第一语音信息或所述第二语音信 息转换为结构化文本,并将所述结构化文本发送给所述智能语音设备服务端,然后,所述智能语音设备服务端从所述结构化文本中获取应用名称及对应的操作。
根据本公开的实施例,所述服务端至少包括智能语音设备服务端、语音云服务端和第三方服务端,所述智能语音设备为智能音箱,本实施例可以实现智能音响根据接收的信息直接进行语音播报以便于用户直观的获取提示信息,其中,给所述智能音箱发送第一提示信息或第二提示信息可以包括如下操作:所述智能语音设备服务端从所述结构化文本中获取应用名称及对应的操作之后,所述智能语音设备服务端执行所述对应的操作,并将所述结构化文本及所述对应的操作的操作结果发送给所述第三方服务端,接着,所述第三方服务端根据所述结构化文本及所述操作结果生成响应所述第一语音信息和/或所述第二语音信息的逻辑处理结果,并将所述逻辑处理结果发送给所述智能语音设备服务端,所述逻辑处理结果为文本信息,然后,所述智能语音设备服务端将所述逻辑处理结果发送给所述语音云服务端,接着,所述语音云服务端根据所述逻辑处理结果合成所述第一提示信息或所述第二提示信息,并发送给所述智能语音设备服务端,其中,所述第一提示信息和所述第二提示信息为语音信息,然后,所述智能语音设备服务端将所述第一提示信息和/或所述第二提示信息发送给所述智能音箱以便进行语音播报。这样可以实现分布式设计,使得不同的服务端承担不同的业务逻辑和部署,有助于提升响应速度和性能。
根据本公开的实施例,所述方法还可以包括如下操作:在开启所述请求应用之前,如果所述请求应用存在关联应用,且所述关联应用具有账号,则在所述请求应用未绑定所述账号时给所述智能语音设备发送第七提示信息,所述第七提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第四预设信息、在客户端的智能语音设备应用中绑定账号信息或第二推荐操作信息。相应地,如果所述请求应用已绑定所述账号,所述开启所述请求应用可以包括如下操作:如果所述关联应用已利用所述账号登陆,则开启所述请求应用,此外,如果所述关联应用未利用所述账号登陆,则给所述智能语音设备发送第八提示信息,所述第八提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第五预设信息、在客户端利用所述账号登陆所述关联应用信息或第三推荐操作信息。当要开启的应用具有关联应用,且该关联应用具有账号时,本公开的实施例可以提示用户进行账号登录及账号绑定,这样可以开启具有账号的关联应用的应用,且避免每次开启都需要输入账号。
根据本公开的实施例,给所述请求应用绑定账号可以包括如下操作:首先,接收客户端发送的智能语音设备应用中由用户输入的关联应用的账号和密码,然后,将所述关联应 用的账号和密码发送至所述关联应用的服务端进行认证,接着,接收所述关联应用的服务端发送的认证通过信息,其中,所述关联应用的服务端对所述关联应用的账号和密码进行认证,如果认证通过,则向所述服务端发送认证通过信息,所述认证通过信息包括允许所述用户通过所述智能语音设备应用访问所述关联应用的权限开通标识,然后,识别所述认证通过信息生成权限开通的提示信息,并将所述权限开通的提示信息发送至智能语音设备进行播报和/或在所述智能语音设备应用中显示权限开通信息。这样就可以实现将请求应用的关联应用的账号与智能语音设备应用进行绑定,间接实现了请求应用与关联应用的账号的绑定。
根据本公开的实施例,所述方法还可以包括如下操作:一方面,在开启所述请求应用之后,如果所述请求应用需要填写信息,则给所述智能语音设备发送第九提示信息,所述第九提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第六预设信息、在客户端的智能语音设备应用中填写信息或第四推荐操作信息,另一方面,在给所述智能语音设备发送第一提示信息之后,如果第一指定时长内未接收到所述第二语音信息,则再次给所述智能语音设备发送第一提示信息,如果第二指定时长内仍未接收到所述第二语音信息,则不开启所述请求应用,另一方面,在给所述智能语音设备发送第一提示信息之后,如果接收到的语音信息未包括开启所述请求应用,则再次给所述智能语音设备发送第一提示信息,如果接收到的语音信息仍未包括开启所述请求应用,则不开启所述请求应用。
本公开的另一个方面提供了一种适用于智能语音设备,所述智能语音设备与服务端相连,所述服务端对所述智能语音设备支持的至少一个应用提供服务,所述方法可以包括如下操作:首先,接收用户发出的第一语音信息,如果所述第一语音信息包括唤醒信息,则将所述第一语音信息发送给所述服务端,然后,接收所述服务端发送的第一提示信息,并进行提示,所述第一提示信息用于提示用户是否开启所述请求应用,接着,接收用户发出的第二语音信息,所述第二语音信息包括开启所述请求应用信息,然后,将所述第二语音信息发送给所述服务端,接着,接收所述服务端发送的第二提示信息,并进行提示,所述第二提示信息用于提示用户已开启所述请求应用。
根据本公开的实施例,所述方法还可以包括如下操作:响应于接收到服务端发送的第三提示信息,进行提示,其中,所述第三提示信息用于由智能语音设备提示用户所述请求应用已开启。
根据本公开的实施例,所述方法还可以包括如下操作:响应于接收到服务端发送的第四提示信息,进行提示,其中,所述第四提示信息用于由智能语音设备提示用户以下任意 一种或多种信息:第一预设信息、不存在所述请求应用信息、推荐的应用名称信息或第一推荐操作信息。
根据本公开的实施例,所述方法还可以包括如下操作:响应于接收到服务端发送的第五提示信息,进行提示,其中,所述第五提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第二预设信息、未开启所述请求应用信息或已退出开启应用流程信息。
根据本公开的实施例,所述方法还可以包括如下操作:响应于接收到服务端发送的第六提示信息,进行提示,其中,所述第六提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第三预设信息、开启所述请求应用失败信息或请再次开启所述请求应用信息。
根据本公开的实施例,所述方法还可以包括如下操作:响应于接收到服务端发送的第七提示信息,进行提示,其中,所述第七提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第四预设信息、在客户端的智能语音设备应用中绑定账号信息或第二推荐操作信息。
根据本公开的实施例,所述方法还可以包括如下操作:响应于接收到服务端发送的第八提示信息,进行提示,其中,所述第八提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第五预设信息、在客户端利用所述账号登陆所述关联应用信息或第三推荐操作信息。
根据本公开的实施例,所述方法还可以包括如下操作:响应于接收到服务端发送的第九提示信息,进行提示,其中,所述第九提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第六预设信息、在客户端的智能语音设备应用中填写信息或第四推荐操作信息。
本公开的另一个方面提供了一种应用开启装置,适用于服务端,所述服务端与至少一个智能语音设备相连,所述服务端对所述至少一个智能语音设备支持的至少一个应用提供服务,所述应用开启装置可以包括:第一接收模块、第一确定模块、第一发送模块、第二接收模块和第二发送模块。其中,所述第一接收模块用于接收智能语音设备发送的第一语音信息,所述第一确定模块用于响应于接收到智能语音设备发送的第一语音信息,分析所述第一语音信息,如果所述第一语音信息包括应用名称及开启应用操作,则根据所述应用名称确定所述服务端是否能对所述应用名称对应的请求应用提供服务,所述第一发送模块用于如果所述服务端能对所述请求应用提供服务,且所述请求应用未开启,则给所述智能语音设备发送第一提示信息,所述第一提示信息用于由智能语音设备提示用户是否开启所 述请求应用,所述第二接收模块用于接收智能语音设备发送的第二语音信息,所述第二发送模块用于响应于接收到智能语音设备发送的第二语音信息,分析所述第二语音信息得到用户指令,如果所述用户指令包括开启所述请求应用,则开启所述请求应用,并给所述智能语音设备发送第二提示信息,所述第二提示信息用于由智能语音设备提示用户已开启所述请求应用。
根据本公开的实施例,所述装置还可以包括第三发送模块,该第三发送模块用于如果所述服务端能对所述请求应用提供服务,且所述请求应用已开启,则给所述智能语音设备发送第三提示信息,所述第三提示信息用于由智能语音设备提示用户所述请求应用已开启。
根据本公开的实施例,所述装置还可以包括第四发送模块,该第四发送模块用于如果所述服务端不能对所述请求应用提供服务,则给所述智能语音设备发送第四提示信息,所述第四提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第一预设信息、不存在所述请求应用信息、推荐的应用名称信息或第一推荐操作信息。
根据本公开的实施例,所述装置还可以包括第五发送模块,该第五发送模块用于如果所述用户指令包括不开启所述请求应用,则不开启所述请求应用,并给所述智能语音设备发送第五提示信息,所述第五提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第二预设信息、未开启所述请求应用信息或已退出开启应用流程信息。
根据本公开的实施例,所述装置还可以包括第六发送模块,该第六发送模块用于如果开启所述请求应用失败,则给所述智能语音设备发送第六提示信息,所述第六提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第三预设信息、开启所述请求应用失败信息或请再次开启所述请求应用信息。
根据本公开的实施例,所述服务端可以至少包括智能语音设备服务端和语音云服务端,相应地,所述智能语音设备服务端用于接收所述第一语音信息或所述第二语音信息之后,将所述第一语音信息或所述第二语音信息发送给所述语音云服务端,所述语音云服务端用于将所述第一语音信息或所述第二语音信息转换为结构化文本,并将所述结构化文本发送给所述智能语音设备服务端,以及,所述智能语音设备服务端还用于从所述结构化文本中获取应用名称及对应的操作。
根据本公开的实施例,所述服务端至少包括智能语音设备服务端、语音云服务端和第三方服务端,所述智能语音设备为智能音箱,相应地,所述智能语音设备服务端用于从所述结构化文本中获取应用名称及对应的操作之后,所述智能语音设备服务端执行所述对应的操作,并将所述结构化文本及所述对应的操作的操作结果发送给所述第三方服务端,所 述第三方服务端用于根据所述结构化文本及所述操作结果生成响应所述第一语音信息和/或所述第二语音信息的逻辑处理结果,并将所述逻辑处理结果发送给所述智能语音设备服务端,所述逻辑处理结果为文本信息,所述智能语音设备服务端用于将所述逻辑处理结果发送给所述语音云服务端,所述语音云服务端用于根据所述逻辑处理结果合成所述第一提示信息或所述第二提示信息,并发送给所述智能语音设备服务端,其中,所述第一提示信息和所述第二提示信息为语音信息,以及所述智能语音设备服务端用于将所述第一提示信息和/或所述第二提示信息发送给所述智能音箱以便进行语音播报。
根据本公开的实施例,所述装置还可以包括第七发送模块,该第七发送模块用于在开启所述请求应用之前,如果所述请求应用存在关联应用,且所述关联应用具有账号,则在所述请求应用未绑定所述账号时给所述智能语音设备发送第七提示信息,所述第七提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第四预设信息、在客户端的智能语音设备应用中绑定账号信息或第二推荐操作信息,相应地,所述智能语音设备服务端具体用于如果所述关联应用已利用所述账号登陆,则开启所述请求应用,以及,如果所述关联应用未利用所述账号登陆,则给所述智能语音设备发送第八提示信息,所述第八提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第五预设信息、在客户端利用所述账号登陆所述关联应用信息或第三推荐操作信息。
根据本公开的实施例,所述装置还可以包括第九发送模块,该第九发送模块用于在开启所述请求应用之后,如果所述请求应用需要填写信息,则给所述智能语音设备发送第九提示信息,所述第九提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第六预设信息、在客户端的智能语音设备应用中填写信息或第四推荐操作信息,并且/或者,第一发送模块具体用于在给所述智能语音设备发送第一提示信息之后,如果第一指定时长内未接收到所述第二语音信息,则再次给所述智能语音设备发送第一提示信息,如果第二指定时长内仍未接收到所述第二语音信息,则不开启所述请求应用,并且/或者,第一发送模块具体用于在给所述智能语音设备发送第一提示信息之后,如果接收到的语音信息未包括开启所述请求应用,则再次给所述智能语音设备发送第一提示信息,如果接收到的语音信息仍未包括开启所述请求应用,则不开启所述请求应用。
本公开的另一个方面提供了一种应用开启装置,适用于智能语音设备,所述智能语音设备与服务端相连,所述服务端对所述智能语音设备支持的至少一个应用提供服务,所述装置可以包括:第三接收模块、第十发送模块、第一提示模块、第四接收模块、第十一发送模块和第二提示模块。其中,所述第三接收模块用于接收用户发出的第一语音信息,所 述第十发送模块用于如果所述第一语音信息包括唤醒词,则将所述第一语音信息发送给所述服务端,所述第一提示模块用于接收所述服务端发送的第一提示信息,并进行提示,所述第一提示信息用于提示用户是否开启所述请求应用,所述第四接收模块用于接收用户发出的第二语音信息,所述第十一发送模块用于将所述第二语音信息发送给所述服务端,所述第二提示模块用于接收所述服务端发送的第二提示信息,并进行提示,所述第二提示信息用于由智能语音设备提示用户已开启所述请求应用。
本公开的另一个方面提供了一种计算机系统,包括:一个或多个处理器,以及存储装置,该存储装置用于存储可执行指令,所述可执行指令在被所述处理器执行时,实现如上所述的方法。
本公开的另一方面提供了一种计算机可读存储介质,存储有计算机可执行指令,所述指令在被执行时用于实现如上所述的方法。
本公开的另一方面提供了一种计算机程序,所述计算机程序包括计算机可执行指令,所述指令在被执行时用于实现如上所述的方法。
根据本公开的实施例,可以通过管控技能应用的开启来改善非目标应用的答非所问等问题,语音的方式实现管控技能应用的开启可以避免用户需要利用客户端如手机来实现管控技能应用的开启,通过语音使得应用开启过程的交互更简洁,改善用户体验。
附图说明
通过以下参照附图对本公开实施例的描述,本公开的上述以及其他目的、特征和优点将更为清楚,在附图中:
图1A示意性示出了根据本公开实施例的应用开启方法、装置和计算机系统及介质的应用场景;
图1B示意性示出了根据本公开实施例的适用于应用开启方法的系统架构的框图;
图2A示意性示出了现有技术的智能音箱使用方法的流程图;
图2B示意性示出了根据本公开实施例的应用开启方法的流程图;
图2C示意性示出了根据本公开实施例的智能音箱使用方法的流程图;
图2D示意性示出了根据本公开另一实施例的应用开启方法的流程图;
图3示意性示出了根据本公开另一实施例的应用开启方法的流程图;
图4A示意性示出了根据本公开实施例的应用开启装置的框图;
图4B示意性示出了根据本公开另一实施例的应用开启装置的框图;以及
图5示意性示出了根据本公开实施例的适于应用开启方法的计算机系统的方框图。
具体实施方式
以下,将参照附图来描述本公开的实施例。但是应该理解,这些描述只是示例性的,而并非要限制本公开的范围。在下面的详细描述中,为便于解释,阐述了许多具体的细节以提供对本公开实施例的全面理解。然而,明显地,一个或多个实施例在没有这些具体细节的情况下也可以被实施。此外,在以下说明中,省略了对公知结构和技术的描述,以避免不必要地混淆本公开的概念。
在此使用的术语仅仅是为了描述具体实施例,而并非意在限制本公开。在此使用的术语“包括”、“包含”等表明了所述特征、步骤、操作和/或部件的存在,但是并不排除存在或添加一个或多个其他特征、步骤、操作或部件。
在此使用的所有术语(包括技术和科学术语)具有本领域技术人员通常所理解的含义,除非另外定义。应注意,这里使用的术语应解释为具有与本说明书的上下文相一致的含义,而不应以理想化或过于刻板的方式来解释。
在使用类似于“使、B和C等中至少一个”这样的表述的情况下,一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如,“具有A、B和C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。在使用类似于“系、B或C等中至少一个”这样的表述的情况下,一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如,“具有A、B或C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。
本公开的实施例提供了一种应用开启方法、装置和计算机系统及介质。该方法通过语音的方式实现管控应用的开启,具体地,在智能语音设备端的语音环境即可开通应用技能的设计方法,旨在保障用户在自然语言环境中的简洁、独立操作的特性,为用户提供更流畅的体验。
图1A示意性示出了根据本公开实施例的应用开启方法、装置和计算机系统及介质的应用场景。
如图1A所示,用户在使用智能语音设备,如智能音箱时,只需要对着智能音箱发出自然语音即可实现包括开启应用、使用应用的全过程,例如,用户对着智能音箱说语音, 如“叮咚叮咚,打开猜歌名”即可,以语音交互的方式通过智能音箱开启所需的应用,无需如现有技术中需要借助具有显示屏的客户端,如手机等通过对具体的智能音箱应用进行操作才能开启智能音箱的具体应用,如猜歌名应用,且期间不会导致如因多个应用对用户意图的语义进行缠绕,发生答非所问的情况。
图1B示意性示出了根据本公开实施例的可以应用于应用开启方法的示例性系统架构100。需要注意的是,图1B所示仅为可以应用本公开实施例的系统架构的示例,以帮助本领域技术人员理解本公开的技术内容,但并不意味着本公开实施例不可以用于其他设备、系统、环境或场景。
如图1B所示,根据该实施例的系统架构100可以包括终端设备101、102、103,网络104和服务器105、106、107。网络104用以在终端设备101、102、103和服务器105、106、107之间提供通信链路的介质。网络104可以包括各种连接类型,例如有线、无线通信链路或者光纤电缆等等。
用户可以使用终端设备101、102、103通过网络104与服务器105、106、107交互,以接收或发送消息等。终端设备101、103上可以安装有各种通讯客户端应用,例如购物类应用、网页浏览器应用、搜索类应用、即时通信工具、邮箱客户端、社交平台软件等(仅为示例)。终端设备101、103可以是具有显示屏并且支持网页浏览的各种电子设备,包括但不限于智能手机、平板电脑、膝上型便携计算机和台式计算机等等。
终端设备102可以是具有声音传感器和扬声器的电子设备,包括但不限于智能音箱、可进行语音交互的智能终端等。
服务器105、106、107可以是提供各种服务的服务器,例如对至少一个终端设备101、102、103支持的至少一个应用提供服务的后台管理服务器(仅为示例),对语音进行语音识别、语义理解和/或语音合成的服务器,对用户的提问或要求进行逻辑处理并给出答复内容的服务器等。后台管理服务器可以对接收到的用户请求等数据进行分析等处理,并将处理结果(例如根据用户请求获取或生成的网页、信息、或数据等)反馈给终端设备。
需要说明的是,本公开实施例所提供的应用开启方法可以由服务器105、106、107执行,或者由终端设备101、102、103执行。相应地,本公开实施例所提供的应用开启装置一般可以设置于服务器105、106、107中,或者可以设置于终端设备101、102、103中。本公开实施例所提供的应用开启方法也可以由不同于服务器105、106、107且能够与终端设备101、102、103和/或服务器105、106、107通信的服务器或服务器集群执行。相应地,本公开实施例所提供的应用开启装置也可以设置于不同于服务器105、106、107且能 够与终端设备101、102、103和/或服务器105、106、107通信的服务器或服务器集群中。
应该理解,终端设备、网络和服务器的数目仅仅是示意性的。根据实现需要,可以具有任意数目的终端设备、网络和服务器。
图2A示意性示出了现有技术的智能音箱使用方法的流程图。
如图2A所示,以所述智能语音设备为智能音箱为例进行说明,智能音箱的使用过程中存在两个阶段:开通技能阶段和使用技能阶段,其中,开通技能阶段是由于在使用智能音箱技能时,需要分辨用户语言的指向性、歧义性,为避免用户意图的语义进行缠绕,发生答非所问的情况,在使用哪个技能时才开启哪个技能,避免非目标的应用对用户的指令做出误操作,例如,用户在玩猜歌名的游戏过程中输入语音“忘忧草”时,购物应用以为用户需要购买“忘忧草”导致误操作。因此,现有技术中需要用户在应用APP(如音箱APP)的技能中心开启对应的技能,如猜歌名技能,客户端的音箱APP将用户指令发送给服务端,如音箱云服务端,音箱云服务端接收到该用户指令后开启猜歌名技能并返回开通结果,此时,可以进入使用技能阶段,如用户可以使用猜歌名应用,具体使用方法可以为各种现有技术所支持的方式,例如,智能音箱从音箱云服务端查询技能内容,音箱云服务端返回播报技能结果等。
然而,现有技术中开启技能的操作依赖于对有显示屏的设备进行操作,且交互过程繁琐,用户使用门槛高;此外,现有的开启技能的方式制约了智能音箱产品形态的进一步升级,也影响了用户体验。
图2B示意性示出了根据本公开实施例的应用开启方法的流程图。
该方法适用于服务端,所述服务端与至少一个智能语音设备相连,所述服务端对所述至少一个智能语音设备支持的至少一个应用提供服务,如图2B所示,所述方法可以包括操作S201~操作S205。
在操作S201,接收智能语音设备发送的第一语音信息。
在本实施例中,该第一语音信息可以为用户对智能语音设备发出的各种语音信息,例如,人机交互时的各种语音指令等。优选地,智能语音设备发送的第一个第一语音信息中可以包含唤醒信息,比如,唤醒词等,例如,“叮咚叮咚,打开猜歌名”,其中,叮咚叮咚即为唤醒词,可以避免智能语音设备将过多的无用语音信息发送给服务端造成资源浪费。需要说明的是,该第一语音信息不一定包含要打开某个应用的信息,还可以是在与其它应用进行交互的语音信息。
然后,在操作S202,响应于接收到智能语音设备发送的第一语音信息,分析所述第 一语音信息,如果所述第一语音信息包括应用名称及开启应用操作,则根据所述应用名称确定所述服务端是否能对所述应用名称对应的请求应用提供服务。
在本实施例中,各种技能可以只由智能语音设备服务端提供服务,也就是说各应用都安装在智能语音设备服务端,因此,智能语音设备服务端具有可以提供服务的应用的列表等,当接收到智能语音设备发送的第一语音信息,分析所述第一语音信息得到文本结果,接着可以判断文本结果中是否包括应用名称及开启应用操作。
在一个实施例中,所述服务端至少包括智能语音设备服务端和语音云服务端。相应地,分析所述第一语音信息可以包括如下操作。
首先,所述智能语音设备服务端接收所述第一语音信息之后,将所述第一语音信息发送给所述语音云服务端。
然后,所述语音云服务端将所述第一语音信息转换为结构化文本,并将所述结构化文本发送给所述智能语音设备服务端。
接着,所述智能语音设备服务端从所述结构化文本中获取应用名称及对应的操作。
在一个具体实施例中,用户说出“叮咚叮咚,打开猜歌名应用”,智能音箱被唤醒词“叮咚叮咚”唤醒,同时将“叮咚叮咚,打开猜歌名应用”或者“打开猜歌名应用”的语音发送给智能语音设备服务端,智能语音设备服务端将“叮咚叮咚,打开猜歌名应用”或者“打开猜歌名应用”的语音发送给语音云服务端进行语音识别、语义理解,将语音转换为结构化文本,如“操作打开,应用名称猜歌名”的结构化文本,然后将该结构化文本发送给智能语音设备服务端,智能语音设备服务端从该结构化文本中提取出应用名称为猜歌名,操作为打开。
在操作S203,如果所述服务端能对所述请求应用提供服务,且所述请求应用未开启,则给所述智能语音设备发送第一提示信息,所述第一提示信息用于由智能语音设备提示用户是否开启所述请求应用。
在本实施例中,服务端可以利用结构化文本中包含的应用名称在可以支持的应用名称列表中进行搜索,如果有搜索结果则表明所述服务端能对所述请求应用提供服务,该服务端还可以存储有与该服务端连接的各智能音箱的各技能的状态,如技能是否处于开启状态等。如果所述服务端能对所述请求应用提供服务,且所述请求应用未开启,则给所述智能语音设备发送第一提示信息,该第一提示信息可以为语音信息、文字信息、指示灯信、响铃信息等各种声光信息,该声光信息用于提示用户是否要开通该技能。优选地,该第一提示信息为语音播报形式的提示信息,以便于用户更加直观的得到该提示信息,且使得语音 交互过程更加流畅。
在一个实施例中,所述服务端可以至少包括智能语音设备服务端、语音云服务端和第三方服务端,所述智能语音设备为智能音箱,所述第一提示信息为语音播报形式的提示信息。具体地,给所述智能音箱发送第一提示信息可以包括如下所示的操作。
在所述智能语音设备服务端从所述结构化文本中获取应用名称及对应的操作之后,所述智能语音设备服务端执行所述对应的操作,并将所述结构化文本及所述对应的操作的操作结果发送给所述第三方服务端。
然后,所述第三方服务端根据所述结构化文本及所述操作结果生成响应所述第一语音信息的逻辑处理结果,并将所述逻辑处理结果发送给所述智能语音设备服务端,所述逻辑处理结果为文本信息。
接着,所述智能语音设备服务端将所述逻辑处理结果发送给所述语音云服务端。
然后,所述语音云服务端根据所述逻辑处理结果合成所述第一提示信息,并发送给所述智能语音设备服务端,其中,所述第一提示信息为语音信息。
接着,所述智能语音设备服务端将所述第一提示信息发送给所述智能音箱以便进行语音播报。这样可以实现分布式设计,使得不同的服务端承担不同的业务逻辑和部署,有助于提升响应速度和性能。
在一个具体实施例中,当智能语音设备服务端接收到“操作打开,应用名称猜歌名”的结构化文本之后,确定可以给猜歌名应用提供服务,且该猜歌名应用未被开启,因此,可以将“操作打开,应用名称猜歌名”的结构化文本以及该猜歌名应用未被开启的状态发送给所述第三方服务端,所述第三方服务端对接收的信息进行逻辑处理,得到逻辑处理结果,如“您还没有开通XXXX(应用名称),是否开通”或者“您还没有开通猜歌名,是否开通”的文本,然后将该文本发送给所述智能语音设备服务端,所述智能语音设备服务端将“您还没有开通XXXX(应用名称),是否开通”处理为“您还没有开通猜歌名,是否开通”,或者直接将“您还没有开通猜歌名,是否开通”的文本发送给所述语音云服务端,合成“您还没有开通猜歌名,是否开通”的语音,并发送给所述智能语音设备服务端,所述智能语音设备服务端将“您还没有开通猜歌名,是否开通”的语音信息发送给智能语音设备以进行语音播报。
需要说明的是,上述实施例仅为示例性说明,语音识别、语义理解、语音合成和逻辑处理等中的任意一种或多个操作也可以在智能语音设备服务端、智能语音设备上进行,在此不做限定。当智能语音设备的处理能力有限,或者需要更高质量的结果时,可以由相应 地远程服务端对信息进行处理。
在操作S204,接收智能语音设备发送的第二语音信息。
其中,该第二语音信息可以包括或不包括唤醒词,也可以包括或不包括应用名称,例如,用户发出的语音“叮咚叮咚,开启猜歌名”、“开启猜歌名”“是(的)/开通/开启/好(的)”等。但是当不包括应用名称时,该第二语音信息应该具有时效性。例如,在给所述智能语音设备发送第一提示信息之后,如果第一指定时长内未接收到所述第二语音信息,则再次给所述智能语音设备发送第一提示信息,如果第二指定时长内仍未接收到所述第二语音信息,则不开启所述请求应用、退出开启所述请求应用的流程。如用户5秒、7秒、10秒或20秒内不说话,则再次询问,询问两次之后退出流程。
此外,为了进一步减小误开启应用的概率,所述方法还可以包括如下操作:在给所述智能语音设备发送第一提示信息之后,如果接收到的语音信息未包括开启所述请求应用,则再次给所述智能语音设备发送第一提示信息,如果接收到的语音信息仍未包括开启所述请求应用,则不开启所述请求应用。这可以有效提升第一次语音交互之后无唤醒词的情形下的操作的准确度。
在操作S205,响应于接收到智能语音设备发送的第二语音信息,分析所述第二语音信息得到用户指令,如果所述用户指令包括开启所述请求应用,则开启所述请求应用,并给所述智能语音设备发送第二提示信息,所述第二提示信息用于由智能语音设备提示用户已开启所述请求应用。
在本实施例中,分析所述第二语音信息的过程可以参考上述分析所述第一语音信息的过程,例如,由语音云服务端将第二语音信息解析为结构化文本并发送给智能语音设备服务端,在此不再赘述。此外,给所述智能音箱发送第二提示信息的过程也可以参考上述给所述智能音箱发送第一提示信息的过程,例如,由第三方服务端给智能语音设备服务端提供逻辑处理结果,由语音云服务端对所述逻辑处理结果进行语音合成后发送给所述智能语音设备服务端,在此不再赘述。
例如,服务端给智能音箱发送语音信息“已开启/已开通/进入应用交互流程”等,以便于智能音箱进行播报。
图2C示意性示出了根据本公开实施例的智能音箱使用方法的流程图。
通过比对图2A和图2C,可以发现,本公开的实施例中,用户在音箱上开通新技能时,不需要借助客户端,如手机APP来进行辅助设置,直接通过智能语音设备就可以完成开通新技能。
需要说明的是,当开启了智能语音设备的应用之后,还可以包括应用的使用过程,该应用的使用过程可以同现有技术,在此不再赘述。
本公开提供的应用开启方法,通过语音的方式实现管控技能应用的开启可以避免用户需要利用客户端如手机来实现管控技能应用的开启,通过语音使得应用开启过程的交互更简洁,此外,本公开提供的应用开启方法可以有效避免非目标应用的答非所问等问题,且有效改善用户意图的语义发生缠绕的情况,有助于改善用户体验。
在另一个实施例中,所述方法还可以包括如下操作:如果所述服务端能对所述请求应用提供服务,且所述请求应用已开启,则给所述智能语音设备发送第三提示信息,所述第三提示信息用于由智能语音设备提示用户所述请求应用已开启。这样当所述请求应用已开启时,可以快速响应用户的请求,提示所述请求应用已开启。
例如,用户对智能音箱发出语音信息:“叮咚叮咚,开通/启用/开启XXXX(应用名称)”后,智能音箱将“开通/启用/开启XXXX(应用名称)”发送给服务端,以及智能音箱接收并播报语音提示信息:“已为您开通XXXX/进入应用交互流程”。
在另一个实施例中,所述方法还可以包括如下操作:如果所述服务端不能对所述请求应用提供服务,则给所述智能语音设备发送第四提示信息,所述第四提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第一预设信息、不存在所述请求应用信息、推荐的应用名称信息或第一推荐操作信息。这样可以首先判断用户希望开启的技能是否存在,如果不存在,则可以及时给用户提示信息,如不存在相应的应用或推荐相关的操作等,以便满足用户的需求。其中,第一预设信息可以包括预设的文本信息或语音信息等,以下预设信息相似。
例如,用户对智能音箱发出语音信息:“叮咚叮咚,开通/启用/开启XXXX(应用名称)”后,智能音箱将“开通/启用/开启XXXX(应用名称)”发送给服务端,以及智能音箱接收并播报语音提示信息:“未找到应用,进入其他流程/未找到应用,您是否希望开启猜歌手/未找到应用,建议在手机端的智能音箱APP中查看应用清单/未找到应用,是否需要播报应用清单”。
在另一个实施例中,所述方法还可以包括如下操作:如果所述用户指令包括不开启所述请求应用,则不开启所述请求应用,并给所述智能语音设备发送第五提示信息,所述第五提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第二预设信息、未开启所述请求应用信息或已退出开启应用流程信息。这样可以在用户改变意图,不希望开启所述请求应用时及时结束开启应用的流程。
例如,用户对智能音箱发出语音信息:“叮咚叮咚,开通/启用/开启XXXX(应用名称)”后,智能音箱将“开通/启用/开启XXXX(应用名称)”发送给服务端,以及智能音箱接收并播报语音提示信息:“您还没有开通XXXX(应用名称),是否开通”。用户发出语音“不(是)/否/不开通”,智能音箱将“不(是)/否/不开通”发送给服务端,以及智能音箱接收并播报语音提示信息:“未开通XXXX(应用名称)/退出开启XXXX流程/已关闭XXXX(应用名称)”。
在另一个实施例中,所述方法还可以包括如下操作:如果开启所述请求应用失败,则给所述智能语音设备发送第六提示信息,所述第六提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第三预设信息、开启所述请求应用失败信息或请再次开启所述请求应用信息。这样可以在应用开启失败时,如当前网络环境较差导致偶然开启失败时,提示用户尝试再次开启应用等。
例如,用户对智能音箱发出语音信息:“叮咚叮咚,开通/启用/开启XXXX(应用名称)”后,智能音箱将“开通/启用/开启XXXX(应用名称)”发送给服务端,以及智能音箱接收并播报语音提示信息:“我好像溜号了,没有开通成功,您这么善良的主人可以再试一次么/应用已经开通啦,信息量有点大,容我缓一缓,请您稍等下打开XXXX(应用名称)”。
图2D示意性示出了根据本公开另一实施例的应用开启方法的流程图。
如图2D所示,所述方法还可以包括检测所述请求应用是否具有关联应用、检测该关联应用是否具有账号的操作以及关联应用是否利于账号登陆的操作。其余操作可以参考如上所示的各实施例,在此仅对不同的部分进行说明。
在本实施例中,所述方法还可以包括如下操作。
在开启所述请求应用之前,如果所述请求应用存在关联应用,且所述关联应用具有账号(即绑定账号才能开通该请求应用),则在所述请求应用未绑定所述账号时给所述智能语音设备发送第七提示信息,所述第七提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第四预设信息、在客户端的智能语音设备应用中绑定账号信息或第二推荐操作信息。
其中,如果所述请求应用已绑定所述账号,所述开启所述请求应用可以包括如下操作。
如果所述关联应用已利用所述账号登陆,且接收到用户的开通指令,则开启所述请求应用。
如果所述关联应用未利用所述账号登陆,且接收到用户的开通指令,则给所述智能语音设备发送第八提示信息,所述第八提示信息用于由智能语音设备提示用户以下任意一种 或多种信息:第五预设信息、在客户端利用所述账号登陆所述关联应用信息或第三推荐操作信息。
例如,当所述请求应用需要绑定关联应用的账号才能开启时,首先可以确定用户是否已经绑定关联应用的账号,如果没有绑定,则可以通过智能语音设备提示用户进行账号绑定,然后再开通所述请求应用,例如,可以给智能音箱发送语音信息“请您在手机客户端账户下绑定京东账号,再开通XXXX(应用名称)/请您在手机客户端应用平台下绑定账号,再开通XXXX(应用名称)”。如果所述关联应用已利用所述账号登陆,则可以开启所述请求应用,如果所述关联应用未利用所述账号登陆,则可以给智能音箱发送语音信息“请您在手机客户端应用平台下找到XXXX(应用名称)登录账号后再开通该请求应用”。
在一个实施例中,给所述请求应用绑定账号可以包括如下操作。
首先,接收客户端发送的智能语音设备应用中由用户输入的关联应用的账号和密码。
然后,将所述关联应用的账号和密码发送至所述关联应用的服务端进行认证。
接着,接收所述关联应用的服务端发送的认证通过信息,其中,所述关联应用的服务端对所述关联应用的账号和密码进行认证,如果认证通过,则向所述服务端发送认证通过信息,所述认证通过信息包括允许所述用户通过所述智能语音设备应用访问所述关联应用的权限开通标识。
然后,识别所述认证通过信息生成权限开通的提示信息,并将所述权限开通的提示信息发送至智能语音设备进行播报和/或在所述智能语音设备应用中显示权限开通信息。
例如,开启京东商城,该京东商城应用具有账号和密码,如果不登陆京东商城应用则无法进行购物,此时,需要用户在客户端的智能语音设备应用中输入关联应用的账号和密码以便进行认证和绑定。
图3示意性示出了根据本公开另一实施例的应用开启方法的流程图。
在本实施例中,该应用开启方法适用于智能语音设备,所述智能语音设备与服务端相连,所述服务端对所述智能语音设备支持的至少一个应用提供服务,如图3所示,所述方法可以包括操作S301~操作S306。
在操作S301中,接收用户发出的第一语音信息。
在操作S302中,如果所述第一语音信息包括唤醒信息,则将所述第一语音信息发送给所述服务端。
在操作S303中,接收所述服务端发送的第一提示信息,并进行提示,所述第一提示信息用于提示用户是否开启所述请求应用。
在操作S304中,接收用户发出的第二语音信息,所述第二语音信息包括开启所述请求应用信息。
在操作S305中,将所述第二语音信息发送给所述服务端。
在操作S306中,接收所述服务端发送的第二提示信息,并进行提示,所述第二提示信息用于提示用户已开启所述请求应用。
这样就可以实现通过智能语音设备,如智能音箱以语音交互的方式开启应用,且有效避免导致用户意图的语义缠绕,有效减少发生答非所问的情况。
在其它实施例中,所述方法还可以包括如下操作。
在一个实施例中,响应于接收到服务端发送的第三提示信息,进行提示,其中,所述第三提示信息用于由智能语音设备提示用户所述请求应用已开启。
在另一个实施例中,响应于接收到服务端发送的第四提示信息,进行提示,其中,所述第四提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第一预设信息、不存在所述请求应用信息、推荐的应用名称信息或第一推荐操作信息。
在另一个实施例中,响应于接收到服务端发送的第五提示信息,进行提示,其中,所述第五提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第二预设信息、未开启所述请求应用信息或已退出开启应用流程信息。
在另一个实施例中,响应于接收到服务端发送的第六提示信息,进行提示,其中,所述第六提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第三预设信息、开启所述请求应用失败信息或请再次开启所述请求应用信息。
在另一个实施例中,响应于接收到服务端发送的第七提示信息,进行提示,其中,所述第七提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第四预设信息、在客户端的智能语音设备应用中绑定账号信息或第二推荐操作信息。
在另一个实施例中,响应于接收到服务端发送的第八提示信息,进行提示,其中,所述第八提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第五预设信息、在客户端利用所述账号登陆所述关联应用信息或第三推荐操作信息。
在另一个实施例中,响应于接收到服务端发送的第九提示信息,进行提示,其中,所述第九提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第六预设信息、在客户端的智能语音设备应用中填写信息或第四推荐操作信息。
其中,关于第一提示信息、第二提示信息、第三提示信息、第四提示信息、第五提示信息、第六提示信息、第七提示信息、第八提示信息和第九提示信息的详细内容可以参考 关于服务端中的相关描述,如在操作S201~操作S205中关于第一提示信息和第二提示信息的相关描述,在此不再赘述。
图4A示意性示出了根据本公开实施例的应用开启装置的框图。
该应用开启装置可以适用于服务端,所述服务端与至少一个智能语音设备相连,所述服务端对所述至少一个智能语音设备支持的至少一个应用提供服务。如图4A所示,应用开启装置400可以包括第一接收模块410、第一确定模块420、第一发送模块430、第二接收模块440和第二发送模块450。
其中,所述第一接收模块410用于接收智能语音设备发送的第一语音信息。
所述第一确定模块420用于响应于接收到智能语音设备发送的第一语音信息,分析所述第一语音信息,如果所述第一语音信息包括应用名称及开启应用操作,则根据所述应用名称确定所述服务端是否能对所述应用名称对应的请求应用提供服务。
所述第一发送模块430用于如果所述服务端能对所述请求应用提供服务,且所述请求应用未开启,则给所述智能语音设备发送第一提示信息,所述第一提示信息用于由智能语音设备提示用户是否开启所述请求应用。
所述第二接收模块440用于接收智能语音设备发送的第二语音信息。
所述第二发送模块450用于响应于接收到智能语音设备发送的第二语音信息,分析所述第二语音信息得到用户指令,如果所述用户指令包括开启所述请求应用,则开启所述请求应用,并给所述智能语音设备发送第二提示信息,所述第二提示信息用于由智能语音设备提示用户已开启所述请求应用。
此外,所述装置400还可以包括第三发送模块,该第三发送模块用于如果所述服务端能对所述请求应用提供服务,且所述请求应用已开启,则给所述智能语音设备发送第三提示信息,所述第三提示信息用于由智能语音设备提示用户所述请求应用已开启。
为了应对存在不支持的应用的情况,所述装置400还可以包括第四发送模块,该第四发送模块用于如果所述服务端不能对所述请求应用提供服务,则给所述智能语音设备发送第四提示信息,所述第四提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第一预设信息、不存在所述请求应用信息、推荐的应用名称信息或第一推荐操作信息。
在另一个实施例中,用户需求改变而不需要开启所述请求应用时,所述装置400还可以包括第五发送模块,该第五发送模块用于如果所述用户指令包括不开启所述请求应用,则不开启所述请求应用,并给所述智能语音设备发送第五提示信息,所述第五提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第二预设信息、未开启所述请求应 用信息或已退出开启应用流程信息。
为了应对可能存在由于网络状态不好等情形导致开通失败而需要重新开通所述请求应用时,所述装置400还可以包括第六发送模块,该第六发送模块用于如果开启所述请求应用失败,则给所述智能语音设备发送第六提示信息,所述第六提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第三预设信息、开启所述请求应用失败信息或请再次开启所述请求应用信息。
其中,所述服务端可以至少包括智能语音设备服务端和语音云服务端,相应地,所述智能语音设备服务端用于接收所述第一语音信息或所述第二语音信息之后,将所述第一语音信息或所述第二语音信息发送给所述语音云服务端,所述语音云服务端用于将所述第一语音信息或所述第二语音信息转换为结构化文本,并将所述结构化文本发送给所述智能语音设备服务端,以及,所述智能语音设备服务端还用于从所述结构化文本中获取应用名称及对应的操作。
当所述提示信息为语音信息时,所述服务端至少包括智能语音设备服务端、语音云服务端和第三方服务端,所述智能语音设备为智能音箱。
所述智能语音设备服务端用于从所述结构化文本中获取应用名称及对应的操作之后,所述智能语音设备服务端执行所述对应的操作,并将所述结构化文本及所述对应的操作的操作结果发送给所述第三方服务端。
所述第三方服务端用于根据所述结构化文本及所述操作结果生成响应所述第一语音信息和/或所述第二语音信息的逻辑处理结果,并将所述逻辑处理结果发送给所述智能语音设备服务端,所述逻辑处理结果为文本信息。
所述智能语音设备服务端用于将所述逻辑处理结果发送给所述语音云服务端。
所述语音云服务端用于根据所述逻辑处理结果合成所述第一提示信息或所述第二提示信息,并发送给所述智能语音设备服务端,其中,所述第一提示信息和所述第二提示信息为语音信息。
所述智能语音设备服务端用于将所述第一提示信息和/或所述第二提示信息发送给所述智能音箱以便进行语音播报。
另外,由于部分应用存在关联应用,且该关联应用具有账号时,所述装置400还可以包括第七发送模块,用于在开启所述请求应用之前,如果所述请求应用存在关联应用,且所述关联应用具有账号,则在所述请求应用未绑定所述账号时给所述智能语音设备发送第七提示信息,所述第七提示信息用于由智能语音设备提示用户以下任意一种或多种信息: 第四预设信息、在客户端的智能语音设备应用中绑定账号信息或第二推荐操作信息。
相应地,所述智能语音设备服务端具体用于如果所述关联应用已利用所述账号登陆,则开启所述请求应用,以及,如果所述关联应用未利用所述账号登陆,则给所述智能语音设备发送第八提示信息,所述第八提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第五预设信息、在客户端利用所述账号登陆所述关联应用信息或第三推荐操作信息。
在其它实施例中,所述装置400还可以包括第九发送模块,用于在开启所述请求应用之后,如果所述请求应用需要填写信息,则给所述智能语音设备发送第九提示信息,所述第九提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第六预设信息、在客户端的智能语音设备应用中填写信息或第四推荐操作信息。
此外,在用户发出第一语音信息后长时间不给出第二语音信息时,所述第一发送模块430具体用于在给所述智能语音设备发送第一提示信息之后,如果第一指定时长内未接收到所述第二语音信息,则再次给所述智能语音设备发送第一提示信息,如果第二指定时长内仍未接收到所述第二语音信息,则不开启所述请求应用。
在用户发出第一语音信息后,在交互阶段发出与开启所述请求应用不相关的语音信息时,如聊天等,则可以退出开启应用流程,例如,所述第一发送模块430具体用于在给所述智能语音设备发送第一提示信息之后,如果接收到的语音信息未包括开启所述请求应用,则再次给所述智能语音设备发送第一提示信息,如果接收到的语音信息仍未包括开启所述请求应用,则不开启所述请求应用。
图4B示意性示出了根据本公开另一实施例的应用开启装置的框图。
相应地,本公开还提供了一种应用开启装置700,适用于智能语音设备,所述智能语音设备与服务端相连,所述服务端对所述智能语音设备支持的至少一个应用提供服务,如图4B所示,所述装置700可以包括:第三接收模块710、第十发送模块720、第一提示模块730、第四接收模块740、第十一发送模块750和第二提示模块760。
第三接收模块710用于接收用户发出的第一语音信息。
第十发送模块720用于如果所述第一语音信息包括唤醒词,则将所述第一语音信息发送给所述服务端。
第一提示模块730用于接收所述服务端发送的第一提示信息,并进行提示,所述第一提示信息用于提示用户是否开启所述请求应用。
第四接收模块740用于接收用户发出的第二语音信息。
第十一发送模块750用于将所述第二语音信息发送给所述服务端。
第二提示模块760用于接收所述服务端发送的第二提示信息,并进行提示,所述第二提示信息用于由智能语音设备提示用户已开启所述请求应用。
需要说明的是,所述装置700还可以进一步包括第三提示模块、第四提示模块、第五提示模块、第六提示模块和第七提示模块(未图示)等,分别拥有提示所述第三提示信息、所述第四提示信息、所述第五提示信息、所述第六提示信息、所述第七提示信息等,在此不再赘述。
根据本公开的实施例的模块、子模块、单元、子单元中的任意多个、或其中任意多个的至少部分功能可以在一个模块中实现。根据本公开实施例的模块、子模块、单元、子单元中的任意一个或多个可以被拆分成多个模块来实现。根据本公开实施例的模块、子模块、单元、子单元中的任意一个或多个可以至少被部分地实现为硬件电路,例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC),或可以通过对电路进行集成或封装的任何其他的合理方式的硬件或固件来实现,或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者,根据本公开实施例的模块、子模块、单元、子单元中的一个或多个可以至少被部分地实现为计算机程序模块,当该计算机程序模块被运行时,可以执行相应的功能。
例如,第一接收模块410、第一确定模块420、第一发送模块430、第二接收模块440和第二发送模块450中的任意多个可以合并在一个模块中实现,或者其中的任意一个模块可以被拆分成多个模块。或者,这些模块中的一个或多个模块的至少部分功能可以与其他模块的至少部分功能相结合,并在一个模块中实现。根据本公开的实施例,第一接收模块410、第一确定模块420、第一发送模块430、第二接收模块440和第二发送模块450中的至少一个可以至少被部分地实现为硬件电路,例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC),或可以通过对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现,或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者,第一接收模块410、第一确定模块420、第一发送模块430、第二接收模块440和第二发送模块450中的至少一个可以至少被部分地实现为计算机程序模块,当该计算机程序模块被运行时,可以执行相应的功能。
图5示意性示出了根据本公开实施例的适于实现上文描述的方法的计算机系统的方 框图。图5示出的计算机系统仅仅是一个示例,不应对本公开实施例的功能和使用范围带来任何限制。
如图5所示,根据本公开实施例的计算机系统500包括处理器501,其可以根据存储在只读存储器(ROM)502中的程序或者从存储部分508加载到随机访问存储器(RAM)503中的程序而执行各种适当的动作和处理。处理器501例如可以包括通用微处理器(例如CPU)、指令集处理器和/或相关芯片组和/或专用微处理器(例如,专用集成电路(ASIC)),等等。处理器501还可以包括用于缓存用途的板载存储器。处理器501可以包括用于执行根据本公开实施例的方法流程的不同动作的单一处理单元或者是多个处理单元。
在RAM 503中,存储有系统500操作所需的各种程序和数据。处理器501、ROM 502以及RAM 503通过总线504彼此相连。处理器501通过执行ROM 502和/或RAM 503中的程序来执行根据本公开实施例的方法流程的各种操作。需要注意,所述程序也可以存储在除ROM 502和RAM 503以外的一个或多个存储器中。处理器501也可以通过执行存储在所述一个或多个存储器中的程序来执行根据本公开实施例的方法流程的各种操作。
根据本公开的实施例,系统500还可以包括输入/输出(I/O)接口505,输入/输出(I/O)接口505也连接至总线504。系统500还可以包括连接至I/O接口505的以下部件中的一项或多项:包括键盘、鼠标等的输入部分506;包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分507;包括硬盘等的存储部分508;以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分509。通信部分509经由诸如因特网的网络执行通信处理。驱动器610也根据需要连接至I/O接口505。可拆卸介质611,诸如磁盘、光盘、磁光盘、半导体存储器等等,根据需要安装在驱动器610上,以便于从其上读出的计算机程序根据需要被安装入存储部分508。
根据本公开的实施例,根据本公开实施例的方法流程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括承载在计算机可读存储介质上的计算机程序,该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信部分509从网络上被下载和安装,和/或从可拆卸介质611被安装。在该计算机程序被处理器501执行时,执行本公开实施例的系统中限定的上述功能。根据本公开的实施例,上文描述的系统、设备、装置、模块、单元等可以通过计算机程序模块来实现。
本公开还提供了一种计算机可读存储介质,该计算机可读存储介质可以是上述实施例中描述的设备/装置/系统中所包含的;也可以是单独存在,而未装配入该设备/装置/系统中。 上述计算机可读存储介质承载有一个或者多个程序,当上述一个或者多个程序被执行时,实现根据本公开实施例的方法。
根据本公开的实施例,计算机可读存储介质可以是非易失性的计算机可读存储介质,例如可以包括但不限于:便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。例如,根据本公开的实施例,计算机可读存储介质可以包括上文描述的ROM 502和/或RAM 503和/或ROM 502和RAM 503以外的一个或多个存储器。
附图中的流程图和框图,图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图或流程图中的每个方框、以及框图或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
本领域技术人员可以理解,本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合,即使这样的组合或结合没有明确记载于本公开中。特别地,在不脱离本公开精神和教导的情况下,本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合。所有这些组合和/或结合均落入本公开的范围。
以上对本公开的实施例进行了描述。但是,这些实施例仅仅是为了说明的目的,而并非为了限制本公开的范围。尽管在以上分别描述了各实施例,但是这并不意味着各个实施例中的措施不能有利地结合使用。本公开的范围由所附权利要求及其等同物限定。不脱离本公开的范围,本领域技术人员可以做出多种替代和修改,这些替代和修改都应落在本公开的范围之内。

Claims (23)

  1. 一种应用开启方法,适用于服务端,所述服务端与至少一个智能语音设备相连,所述服务端对所述至少一个智能语音设备支持的至少一个应用提供服务,所述方法包括:
    接收智能语音设备发送的第一语音信息;
    响应于接收到智能语音设备发送的第一语音信息,分析所述第一语音信息,如果所述第一语音信息包括应用名称及开启应用操作,则根据所述应用名称确定所述服务端是否能对所述应用名称对应的请求应用提供服务;
    如果所述服务端能对所述请求应用提供服务,且所述请求应用未开启,则给所述智能语音设备发送第一提示信息,所述第一提示信息用于由智能语音设备提示用户是否开启所述请求应用;
    接收智能语音设备发送的第二语音信息;以及
    响应于接收到智能语音设备发送的第二语音信息,分析所述第二语音信息得到用户指令,如果所述用户指令包括开启所述请求应用,则开启所述请求应用,并给所述智能语音设备发送第二提示信息,所述第二提示信息用于由智能语音设备提示用户已开启所述请求应用。
  2. 根据权利要求1所述的方法,还包括:
    如果所述服务端能对所述请求应用提供服务,且所述请求应用已开启,则给所述智能语音设备发送第三提示信息,所述第三提示信息用于由智能语音设备提示用户所述请求应用已开启。
  3. 根据权利要求1所述的方法,还包括:
    如果所述服务端不能对所述请求应用提供服务,则给所述智能语音设备发送第四提示信息,所述第四提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第一预设信息、不存在所述请求应用信息、推荐的应用名称信息或第一推荐操作信息。
  4. 根据权利要求1所述的方法,还包括:
    如果所述用户指令包括不开启所述请求应用,则不开启所述请求应用,并给所述智能语音设备发送第五提示信息,所述第五提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第二预设信息、未开启所述请求应用信息或已退出开启应用流程信息。
  5. 根据权利要求1所述的方法,还包括:
    如果开启所述请求应用失败,则给所述智能语音设备发送第六提示信息,所述第六提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第三预设信息、开启所述请求应用失败信息或请再次开启所述请求应用信息。
  6. 根据权利要求1所述的方法,其中:
    所述服务端至少包括智能语音设备服务端和语音云服务端;
    分析所述第一语音信息或所述第二语音信息包括:
    所述智能语音设备服务端接收所述第一语音信息或所述第二语音信息之后,
    将所述第一语音信息或所述第二语音信息发送给所述语音云服务端;
    所述语音云服务端将所述第一语音信息或所述第二语音信息转换为结构化文本,并将所述结构化文本发送给所述智能语音设备服务端;
    所述智能语音设备服务端从所述结构化文本中获取应用名称及对应的操作。
  7. 根据权利要求6所述的方法,其中:
    所述服务端至少包括智能语音设备服务端、语音云服务端和第三方服务端,所述智能语音设备为智能音箱;
    给所述智能音箱发送第一提示信息或第二提示信息包括:
    所述智能语音设备服务端从所述结构化文本中获取应用名称及对应的操作之后,所述智能语音设备服务端执行所述对应的操作,并将所述结构化文本及所述对应的操作的操作结果发送给所述第三方服务端;
    所述第三方服务端根据所述结构化文本及所述操作结果生成响应所述第一语音信息和/或所述第二语音信息的逻辑处理结果,并将所述逻辑处理结果发送给所述智能语音设备服务端,所述逻辑处理结果为文本信息;
    所述智能语音设备服务端将所述逻辑处理结果发送给所述语音云服务端;
    所述语音云服务端根据所述逻辑处理结果合成所述第一提示信息或所述第二提示信息,并发送给所述智能语音设备服务端,其中,所述第一提示信息和所述第二提示信息为语音信息;
    所述智能语音设备服务端将所述第一提示信息和/或所述第二提示信息发送给所述智能音箱以便进行语音播报。
  8. 根据权利要求1所述的方法,还包括:
    在开启所述请求应用之前,如果所述请求应用存在关联应用,且所述关联应用具有账号,则在所述请求应用未绑定所述账号时给所述智能语音设备发送第七提示信息,所述第 七提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第四预设信息、在客户端的智能语音设备应用中绑定账号信息或第二推荐操作信息;
    如果所述请求应用已绑定所述账号,所述开启所述请求应用包括:
    如果所述关联应用已利用所述账号登陆,则开启所述请求应用;
    如果所述关联应用未利用所述账号登陆,则给所述智能语音设备发送第八提示信息,所述第八提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第五预设信息、在客户端利用所述账号登陆所述关联应用信息或第三推荐操作信息。
  9. 根据权利要求8所述的方法,其中,给所述请求应用绑定账号包括:
    接收客户端发送的智能语音设备应用中由用户输入的关联应用的账号和密码;
    将所述关联应用的账号和密码发送至所述关联应用的服务端进行认证;
    接收所述关联应用的服务端发送的认证通过信息,其中,所述关联应用的服务端对所述关联应用的账号和密码进行认证,如果认证通过,则向所述服务端发送认证通过信息,所述认证通过信息包括允许所述用户通过所述智能语音设备应用访问所述关联应用的权限开通标识;
    识别所述认证通过信息生成权限开通的提示信息,并将所述权限开通的提示信息发送至智能语音设备进行播报和/或在所述智能语音设备应用中显示权限开通信息。
  10. 根据权利要求1所述的方法,还包括:
    在开启所述请求应用之后,如果所述请求应用需要填写信息,则给所述智能语音设备发送第九提示信息,所述第九提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第六预设信息、在客户端的智能语音设备应用中填写信息或第四推荐操作信息;
    并且/或者
    在给所述智能语音设备发送第一提示信息之后,如果第一指定时长内未接收到所述第二语音信息,则再次给所述智能语音设备发送第一提示信息,如果第二指定时长内仍未接收到所述第二语音信息,则不开启所述请求应用;
    并且/或者
    在给所述智能语音设备发送第一提示信息之后,如果接收到的语音信息未包括开启所述请求应用,则再次给所述智能语音设备发送第一提示信息,如果接收到的语音信息仍未包括开启所述请求应用,则不开启所述请求应用。
  11. 一种应用开启方法,适用于智能语音设备,所述智能语音设备与服务端相连,所述服务端对所述智能语音设备支持的至少一个应用提供服务,所述方法包括:
    接收用户发出的第一语音信息;
    如果所述第一语音信息包括唤醒信息,则将所述第一语音信息发送给所述服务端;
    接收所述服务端发送的第一提示信息,并进行提示,所述第一提示信息用于提示用户是否开启所述请求应用;
    接收用户发出的第二语音信息,所述第二语音信息包括开启所述请求应用信息;
    将所述第二语音信息发送给所述服务端;
    接收所述服务端发送的第二提示信息,并进行提示,所述第二提示信息用于提示用户已开启所述请求应用。
  12. 一种应用开启装置,适用于服务端,所述服务端与至少一个智能语音设备相连,所述服务端对所述至少一个智能语音设备支持的至少一个应用提供服务,所述应用开启装置包括:
    第一接收模块,用于接收智能语音设备发送的第一语音信息;
    第一确定模块,用于响应于接收到智能语音设备发送的第一语音信息,分析所述第一语音信息,如果所述第一语音信息包括应用名称及开启应用操作,则根据所述应用名称确定所述服务端是否能对所述应用名称对应的请求应用提供服务;
    第一发送模块,用于如果所述服务端能对所述请求应用提供服务,且所述请求应用未开启,则给所述智能语音设备发送第一提示信息,所述第一提示信息用于由智能语音设备提示用户是否开启所述请求应用;
    第二接收模块,用于接收智能语音设备发送的第二语音信息;以及
    第二发送模块,用于响应于接收到智能语音设备发送的第二语音信息,分析所述第二语音信息得到用户指令,如果所述用户指令包括开启所述请求应用,则开启所述请求应用,并给所述智能语音设备发送第二提示信息,所述第二提示信息用于由智能语音设备提示用户已开启所述请求应用。
  13. 根据权利要求12所述的装置,还包括:
    第三发送模块,用于如果所述服务端能对所述请求应用提供服务,且所述请求应用已开启,则给所述智能语音设备发送第三提示信息,所述第三提示信息用于由智能语音设备提示用户所述请求应用已开启。
  14. 根据权利要求12所述的装置,还包括:
    第四发送模块,用于如果所述服务端不能对所述请求应用提供服务,则给所述智能语音设备发送第四提示信息,所述第四提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第一预设信息、不存在所述请求应用信息、推荐的应用名称信息或第一推荐操作信息。
  15. 根据权利要求12所述的装置,还包括:
    第五发送模块,用于如果所述用户指令包括不开启所述请求应用,则不开启所述请求应用,并给所述智能语音设备发送第五提示信息,所述第五提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第二预设信息、未开启所述请求应用信息或已退出开启应用流程信息。
  16. 根据权利要求12所述的装置,还包括:
    第六发送模块,用于如果开启所述请求应用失败,则给所述智能语音设备发送第六提示信息,所述第六提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第三预设信息、开启所述请求应用失败信息或请再次开启所述请求应用信息。
  17. 根据权利要求12所述的装置,其中,所述服务端至少包括智能语音设备服务端和语音云服务端;
    所述智能语音设备服务端用于接收所述第一语音信息或所述第二语音信息之后,将所述第一语音信息或所述第二语音信息发送给所述语音云服务端;
    所述语音云服务端用于将所述第一语音信息或所述第二语音信息转换为结构化文本,并将所述结构化文本发送给所述智能语音设备服务端;
    所述智能语音设备服务端还用于从所述结构化文本中获取应用名称及对应的操作。
  18. 根据权利要求17所述的装置,其中,所述服务端至少包括智能语音设备服务端、语音云服务端和第三方服务端,所述智能语音设备为智能音箱;
    所述智能语音设备服务端用于从所述结构化文本中获取应用名称及对应的操作之后,所述智能语音设备服务端执行所述对应的操作,并将所述结构化文本及所述对应的操作的操作结果发送给所述第三方服务端;
    所述第三方服务端用于根据所述结构化文本及所述操作结果生成响应所述第一语音信息和/或所述第二语音信息的逻辑处理结果,并将所述逻辑处理结果发送给所述智能语音设备服务端,所述逻辑处理结果为文本信息;
    所述智能语音设备服务端用于将所述逻辑处理结果发送给所述语音云服务端;
    所述语音云服务端用于根据所述逻辑处理结果合成所述第一提示信息或所述第二提示信息,并发送给所述智能语音设备服务端,其中,所述第一提示信息和所述第二提示信息为语音信息;
    所述智能语音设备服务端用于将所述第一提示信息和/或所述第二提示信息发送给所述智能音箱以便进行语音播报。
  19. 根据权利要求12所述的装置,还包括:
    第七发送模块,用于在开启所述请求应用之前,如果所述请求应用存在关联应用,且所述关联应用具有账号,则在所述请求应用未绑定所述账号时给所述智能语音设备发送第七提示信息,所述第七提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第四预设信息、在客户端的智能语音设备应用中绑定账号信息或第二推荐操作信息;
    所述智能语音设备服务端具体用于如果所述关联应用已利用所述账号登陆,则开启所述请求应用,以及,如果所述关联应用未利用所述账号登陆,则给所述智能语音设备发送第八提示信息,所述第八提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第五预设信息、在客户端利用所述账号登陆所述关联应用信息或第三推荐操作信息。
  20. 根据权利要求12所述的装置,还包括:
    第九发送模块,用于在开启所述请求应用之后,如果所述请求应用需要填写信息,则给所述智能语音设备发送第九提示信息,所述第九提示信息用于由智能语音设备提示用户以下任意一种或多种信息:第六预设信息、在客户端的智能语音设备应用中填写信息或第四推荐操作信息;
    并且/或者
    第一发送模块具体用于在给所述智能语音设备发送第一提示信息之后,如果第一指定时长内未接收到所述第二语音信息,则再次给所述智能语音设备发送第一提示信息,如果第二指定时长内仍未接收到所述第二语音信息,则不开启所述请求应用;
    并且/或者
    第一发送模块具体用于在给所述智能语音设备发送第一提示信息之后,如果接收到的语音信息未包括开启所述请求应用,则再次给所述智能语音设备发送第一提示信息,如果接收到的语音信息仍未包括开启所述请求应用,则不开启所述请求应用。
  21. 一种应用开启装置,适用于智能语音设备,所述智能语音设备与服务端相连,所述服务端对所述智能语音设备支持的至少一个应用提供服务,所述装置包括:
    第三接收模块,用于接收用户发出的第一语音信息;
    第十发送模块,用于如果所述第一语音信息包括唤醒词,则将所述第一语音信息发送给所述服务端;
    第一提示模块,用于接收所述服务端发送的第一提示信息,并进行提示,所述第一提示信息用于提示用户是否开启所述请求应用;
    第四接收模块,用于接收用户发出的第二语音信息;
    第十一发送模块,用于将所述第二语音信息发送给所述服务端;
    第二提示模块,用于接收所述服务端发送的第二提示信息,并进行提示,所述第二提示信息用于由智能语音设备提示用户已开启所述请求应用。
  22. 一种计算机系统,包括:
    一个或多个处理器;
    存储装置,用于存储可执行指令,所述可执行指令在被所述处理器执行时,实现根据权利要求1~11中任一项所述的方法。
  23. 一种计算机可读存储介质,其上存储有可执行指令,该指令被处理器执行时实现根据权利要求1~11中任一项所述的方法。
PCT/CN2020/071154 2019-03-22 2020-01-09 应用开启方法、装置和计算机系统及介质 WO2020192245A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910221856.4A CN111724773A (zh) 2019-03-22 2019-03-22 应用开启方法、装置和计算机系统及介质
CN201910221856.4 2019-03-22

Publications (1)

Publication Number Publication Date
WO2020192245A1 true WO2020192245A1 (zh) 2020-10-01

Family

ID=72563529

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/071154 WO2020192245A1 (zh) 2019-03-22 2020-01-09 应用开启方法、装置和计算机系统及介质

Country Status (2)

Country Link
CN (1) CN111724773A (zh)
WO (1) WO2020192245A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112242141B (zh) * 2020-10-15 2022-03-15 广州小鹏汽车科技有限公司 一种语音控制方法、智能座舱、服务器、车辆和介质

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105553799A (zh) * 2016-02-29 2016-05-04 深圳市广佳乐新智能科技有限公司 一种基于语音识别的智能家居系统
CN106448664A (zh) * 2016-10-28 2017-02-22 魏朝正 一种通过语音控制智能家居设备的系统及方法
CN107277272A (zh) * 2017-07-25 2017-10-20 深圳市芯中芯科技有限公司 一种基于软件app的蓝牙设备语音交互方法及系统
CN108173721A (zh) * 2017-12-18 2018-06-15 华南师范大学 基于iOS的语音控制智能家居系统及语音识别控制方法
CN108366319A (zh) * 2018-03-30 2018-08-03 京东方科技集团股份有限公司 智能音箱及其语音控制方法
CN108389098A (zh) * 2017-02-03 2018-08-10 北京京东尚科信息技术有限公司 语音购物方法以及系统
CN108494641A (zh) * 2018-03-28 2018-09-04 合肥隆延科技有限公司 基于物联网的智能家居系统的控制方法
CN108737933A (zh) * 2018-05-30 2018-11-02 上海与德科技有限公司 一种基于智能音箱的对话方法、装置及电子设备
CN108737172A (zh) * 2018-05-11 2018-11-02 四川斐讯信息技术有限公司 一种基于智能音箱的自动修改路由器Wi-Fi密码的方法及系统
CN108847233A (zh) * 2018-06-26 2018-11-20 上海早糯网络科技有限公司 一种语音控制手机充电的方法及系统
CN108901056A (zh) * 2018-06-21 2018-11-27 百度在线网络技术(北京)有限公司 用于交互信息的方法和装置

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040230637A1 (en) * 2003-04-29 2004-11-18 Microsoft Corporation Application controls for speech enabled recognition
US7403898B2 (en) * 2004-08-20 2008-07-22 At&T Delaware Intellectual Property, Inc., Methods, systems, and storage mediums for implementing voice-commanded computer functions
CN105072133B (zh) * 2015-08-28 2018-07-10 北京金山安全软件有限公司 一种应用程序的登录方法及装置
CN108109618A (zh) * 2016-11-25 2018-06-01 宇龙计算机通信科技(深圳)有限公司 语音交互方法、系统以及终端设备
CN106681160A (zh) * 2016-12-12 2017-05-17 北京云知声信息技术有限公司 智能设备控制方法及装置
CN107645486B (zh) * 2016-12-28 2018-08-21 平安科技(深圳)有限公司 登录认证方法和装置
CN107370649B (zh) * 2017-08-31 2020-09-11 广东美的制冷设备有限公司 家电控制方法、系统、控制终端、及存储介质
CN107528858B (zh) * 2017-09-29 2021-04-06 广州视睿电子科技有限公司 基于网页的登录方法、装置、设备及存储介质
CN107833574B (zh) * 2017-11-16 2021-08-24 百度在线网络技术(北京)有限公司 用于提供语音服务的方法和装置
CN108932946B (zh) * 2018-06-29 2020-03-13 百度在线网络技术(北京)有限公司 客需服务的语音交互方法和装置
CN109036396A (zh) * 2018-06-29 2018-12-18 百度在线网络技术(北京)有限公司 一种第三方应用的交互方法及系统
CN109271130B (zh) * 2018-09-12 2021-12-17 网易(杭州)网络有限公司 音频播放方法、介质、装置和计算设备

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105553799A (zh) * 2016-02-29 2016-05-04 深圳市广佳乐新智能科技有限公司 一种基于语音识别的智能家居系统
CN106448664A (zh) * 2016-10-28 2017-02-22 魏朝正 一种通过语音控制智能家居设备的系统及方法
CN108389098A (zh) * 2017-02-03 2018-08-10 北京京东尚科信息技术有限公司 语音购物方法以及系统
CN107277272A (zh) * 2017-07-25 2017-10-20 深圳市芯中芯科技有限公司 一种基于软件app的蓝牙设备语音交互方法及系统
CN108173721A (zh) * 2017-12-18 2018-06-15 华南师范大学 基于iOS的语音控制智能家居系统及语音识别控制方法
CN108494641A (zh) * 2018-03-28 2018-09-04 合肥隆延科技有限公司 基于物联网的智能家居系统的控制方法
CN108366319A (zh) * 2018-03-30 2018-08-03 京东方科技集团股份有限公司 智能音箱及其语音控制方法
CN108737172A (zh) * 2018-05-11 2018-11-02 四川斐讯信息技术有限公司 一种基于智能音箱的自动修改路由器Wi-Fi密码的方法及系统
CN108737933A (zh) * 2018-05-30 2018-11-02 上海与德科技有限公司 一种基于智能音箱的对话方法、装置及电子设备
CN108901056A (zh) * 2018-06-21 2018-11-27 百度在线网络技术(北京)有限公司 用于交互信息的方法和装置
CN108847233A (zh) * 2018-06-26 2018-11-20 上海早糯网络科技有限公司 一种语音控制手机充电的方法及系统

Also Published As

Publication number Publication date
CN111724773A (zh) 2020-09-29

Similar Documents

Publication Publication Date Title
US11688402B2 (en) Dialog management with multiple modalities
US11671826B2 (en) Voice control and telecommunications service integration
US10311877B2 (en) Performing tasks and returning audio and visual answers based on voice command
US10129720B1 (en) Conversation assistant
JP6093040B2 (ja) サービスを提供するための装置、方法、コンピュータプログラム及び記憶媒体
WO2019000871A1 (zh) 用于提供语音服务的方法、装置和服务器
CN106416195B (zh) 一种处理器实现方法、一种通信网络连接的系统和有形的计算机可读存储媒体
US20160294806A1 (en) Account information management method and apparatus in smart tv
US11935521B2 (en) Real-time feedback for efficient dialog processing
KR20130112885A (ko) 음성-가능 응용프로그램에 입력을 제공하는 방법 및 장치
US11270690B2 (en) Method and apparatus for waking up device
US20210319347A1 (en) Fast and scalable multi-tenant serve pool for chatbots
US11169992B2 (en) Cognitive program suite for a cognitive device and a mobile device
WO2019228138A1 (zh) 音乐播放方法、装置、存储介质及电子设备
US11758087B2 (en) Multimedia conference data processing method and apparatus, and electronic device
WO2021047197A1 (zh) 一种语音处理方法、装置、设备和计算机存储介质
WO2020192245A1 (zh) 应用开启方法、装置和计算机系统及介质
US20190347067A1 (en) User interface interaction channel
WO2017193544A1 (zh) 资源下载方法、装置及电子设备
CN112837159B (zh) 基于场景要素的交易引导方法、装置、电子设备及介质
CN110351602B (zh) 用于电子设备的方法、信息处理系统和电子设备
CN112597022A (zh) 远程诊断方法、装置、存储介质及电子设备
US10885911B2 (en) Voice endpoint to chatbot bridge interface
US11722572B2 (en) Communication platform shifting for voice-enabled device
US20230259317A1 (en) Systems and methods for providing indications during online meetings

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: 20778723

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16.02.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20778723

Country of ref document: EP

Kind code of ref document: A1