CN111724773A

CN111724773A - Application opening method and device, computer system and medium

Info

Publication number: CN111724773A
Application number: CN201910221856.4A
Authority: CN
Inventors: 申昀弘; 操灿
Original assignee: iFlytek Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Current assignee: iFlytek Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Priority date: 2019-03-22
Filing date: 2019-03-22
Publication date: 2020-09-29
Also published as: WO2020192245A1

Abstract

The present disclosure provides an application opening method, including: receiving first voice information sent by intelligent voice equipment; responding to the received first voice information sent by the intelligent voice equipment, analyzing the first voice information, and if the first voice information comprises an application name and an application starting operation, determining whether a service end can provide service for a request application corresponding to the application name or not according to the application name; if the server side can provide service for the request application and the request application is not started, first prompt information is sent to the intelligent voice equipment; receiving second voice information sent by the intelligent voice equipment; and responding to the received second voice information sent by the intelligent voice equipment, analyzing the second voice information to obtain a user instruction, if the user instruction comprises the opening of the request application, opening the request application, and sending second prompt information to the intelligent voice equipment. The present disclosure also provides an application opening device, a computer system and a medium.

Description

Application opening method and device, computer system and medium

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to an application opening method, an application opening device, a computer system, and a medium.

Background

With the rapid development of artificial intelligence, communication and computer technologies, smart speakers increasingly enter people's daily lives. In 2017, the sales volume of global intelligent sound boxes breaks through 3000 thousands of sound boxes, the market of the intelligent sound boxes is developing rapidly, and the voice interaction technology and the content service skills are also improved and grounded continuously.

When using smart speaker skill, because directive property, the ambiguity of user's language need to be distinguished to avoid the semantic of user's intention to twine, take place the condition that the answer was asked, prior art all adopts opening of management and control technical application, inject semantic distribution rule, when user's use skill promptly, need open required skill on smart speaker application (APP for short) on the cell-phone that smart speaker corresponds earlier, just so can use this skill on smart speaker.

In the course of implementing the disclosed concept, the inventors found that there are at least the following problems in the prior art: firstly, the operation of starting the technology in the prior art depends on the operation of equipment with a display screen, the interaction process is complicated, and the threshold for the use of a user is high; in addition, the existing way of starting the skill restricts the further upgrade of the product form of the intelligent sound box, and the user experience is also influenced.

Disclosure of Invention

In view of this, the present disclosure provides an application opening method, an application opening apparatus, a computer system, and a medium, which can open a skill of an intelligent voice device without depending on a device with a display screen to operate, and have a simple interaction process.

One aspect of the present disclosure provides an application opening method, which is applicable to a server, where 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, where the method may include the following operations: firstly, receiving first voice information sent by intelligent voice equipment, then, responding to the received first voice information sent by the intelligent voice equipment, analyzing the first voice information, if the first voice information comprises an application name and an application starting operation, determining whether a service end can provide service for a request application corresponding to the application name according to the application name, then, if the service end can provide service for the request application and the request application is not started, sending first prompt information to the intelligent voice equipment, wherein the first prompt information is used for prompting a user whether to start the request application by the intelligent voice equipment, then, receiving second voice information sent by the intelligent voice equipment, then, responding to the received second voice information sent by the intelligent voice equipment, analyzing the second voice information to obtain a user instruction, and if the user instruction comprises the request application, starting the request application, and sending second prompt information to the intelligent voice equipment, wherein the second prompt information is used for prompting the user that the request application is started by the intelligent voice equipment. Through this disclosed embodiment can realize opening of management and control skill through the mode of pronunciation (open the required application of user in the intelligent speech equipment server), open through management and control skill application and improve the question such as not asking for of answer of non-target application, the mode of pronunciation realizes that opening of management and control skill application can avoid the user to utilize the client side to realize opening of management and control skill application like the cell-phone, make the interactive mode of application opening process more succinct through pronunciation, help improving user experience.

According to an embodiment of the present disclosure, the method may further include the operations of: and if the server side can provide service for the request application and the request application is started, sending third prompt information to the intelligent voice equipment, wherein the third prompt information is used for prompting the user that the request application is started by the intelligent voice equipment. Therefore, when the request application is opened, the request of the user can be quickly responded, and the request application is prompted to be opened.

According to an embodiment of the present disclosure, the method may further include the operations of: if the server side can not provide service for the request application, sending fourth prompt information to the intelligent voice equipment, wherein the fourth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: the first preset information, the request application information which does not exist, the recommended application name information or the first recommended operation information. Therefore, whether the skill which the user wants to start exists or not can be judged firstly, if not, information can be prompted to the user in time, and corresponding application or operation related to recommendation does not exist so as to meet the requirements of the user.

According to an embodiment of the present disclosure, the method may further include the operations of: if the user instruction comprises that the request application is not started, and fifth prompt information is sent to the intelligent voice equipment, wherein the fifth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: second preset information, information that the requested application is not started or information that the application process is quitted to be started. Therefore, the process of opening the application can be timely ended when the user changes the intention and does not want to open the request application.

According to an embodiment of the present disclosure, the method may further include the operations of: if the request application is failed to be started, sixth prompt information is sent to the intelligent voice equipment, and the sixth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: third preset information, failure information for opening the request application or information for opening the request application again. Therefore, when the application fails to be started, for example, when the current network environment is poor and the accidental starting fails, the user is prompted to try to start the application again.

According to an embodiment of the present disclosure, the service end may include at least an intelligent voice device service end and a voice cloud service end, so that a distributed design may be implemented, so that different service ends bear different service logics and deployments, and accordingly, analyzing the first voice information or the second voice information may include the following operations: after receiving the first voice information or the second voice information, the intelligent voice equipment server sends the first voice information or the second voice information to the voice cloud server, then the voice cloud server converts the first voice information or the second voice information into a structured text and sends the structured text to the intelligent voice equipment server, and then the intelligent voice equipment server obtains an application name and corresponding operation from the structured text.

According to the embodiment of the disclosure, the server includes intelligent voice device server, pronunciation cloud server and third party server at least, intelligent voice device is intelligent audio amplifier, and this embodiment can realize that intelligent audio directly carries out voice broadcast so that the audio-visual suggestion information that acquires of user according to the information of receiving, wherein, give intelligent audio amplifier sends first suggestion information or second suggestion information can include following operation: after the intelligent voice equipment server acquires the application name and the corresponding operation from the structured text, the intelligent voice equipment server executes the corresponding operation and sends the structured text and the operation result of the corresponding operation to the third party server, then the third party server generates a logic processing result responding to the first voice information and/or the second voice information according to the structured text and the operation result and sends the logic processing result to the intelligent voice equipment server, the logic processing result is text information, then the intelligent voice equipment server sends the logic processing result to the voice cloud server, and then the voice cloud server synthesizes the first prompt information or the second prompt information according to the logic processing result, and sending to the intelligent voice equipment server, wherein the first prompt message and the second prompt message are voice messages, and then the intelligent voice equipment server sends the first prompt message and/or the second prompt message to the intelligent sound box so as to perform voice broadcast. Therefore, distributed design can be realized, different service ends bear different service logics and deployment, and response speed and performance are improved.

According to an embodiment of the present disclosure, the method may further include the operations of: before the request application is started, if the request application has a related application and the related application has an account, sending seventh prompt information to the intelligent voice device when the request application is not bound with the account, wherein the seventh prompt information is used for prompting a user of any one or more of the following information by the intelligent voice device: and fourth preset information, account information or second recommendation operation information is bound in the intelligent voice equipment application of the client. Accordingly, if the requesting application is bound to the account, the opening the requesting application may include the following operations: if the associated application is logged in by using the account, starting the request application, and if the associated application is not logged in by using the account, sending eighth prompt information to the intelligent voice equipment, wherein the eighth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: and fifth preset information, logging in the associated application information or the third recommended operation information by using the account at the client. When the application to be started has the associated application and the associated application has the account, the embodiment of the disclosure can prompt the user to perform account login and account binding, so that the application of the associated application with the account can be started, and the account is prevented from being input every time the application is started.

According to an embodiment of the present disclosure, binding an account to the requesting application may include the following operations: firstly, receiving an account and a password of an associated application input by a user in an intelligent voice device application sent by a client, then, the account and the password of the associated application are sent to a server side of the associated application for authentication, and then authentication passing information sent by the server side of the associated application is received, wherein the service end of the associated application authenticates the account and the password of the associated application, if the authentication is passed, authentication passing information is sent to the server side, the authentication passing information comprises an authority opening identification allowing the user to access the associated application through the intelligent voice equipment application, and then, identifying the authentication passing information to generate prompt information of permission opening, and sending the prompt information of permission opening to the intelligent voice equipment for broadcasting and/or displaying permission opening information in the application of the intelligent voice equipment. Therefore, the account of the associated application of the request application can be bound with the intelligent voice equipment application, and the binding of the request application and the account of the associated application is indirectly realized.

According to an embodiment of the present disclosure, the method may further include the operations of: on one hand, after the request application is started, if the request application needs to fill in information, ninth prompting information is sent to the intelligent voice device, and the ninth prompting information is used for prompting the user of any one or more of the following information by the intelligent voice device: filling writing information or fourth recommended operation information in the intelligent voice equipment application of the client, on the other hand, after sending the first prompt information to the intelligent voice equipment, if the second voice information is not received within a first specified time length, sending the first prompt information to the intelligent voice equipment again, if the second voice information is not received within a second specified time length, not starting the request application, on the other hand, after sending the first prompt information to the intelligent voice equipment, if the received voice information does not include starting the request application, sending the first prompt information to the intelligent voice equipment again, and if the received voice information does not include starting the request application, not starting the request application.

Another aspect of the present disclosure provides a method for an intelligent voice device, where the intelligent voice device is connected to a server, and the server provides a service to at least one application supported by the intelligent voice device, where the method includes the following operations: the method comprises the steps of firstly, receiving first voice information sent by a user, sending the first voice information to a server if the first voice information comprises awakening information, then receiving first prompt information sent by the server, and prompting, wherein the first prompt information is used for prompting whether the user starts the request application, then receiving second voice information sent by the user, the second voice information comprises the request application starting information, then sending the second voice information to the server, then receiving second prompt information sent by the server, and prompting, wherein the second prompt information is used for prompting the user to start the request application.

According to an embodiment of the present disclosure, the method may further include the operations of: and responding to the received third prompt message sent by the server to prompt, wherein the third prompt message is used for prompting the user that the request application is started by the intelligent voice equipment.

According to an embodiment of the present disclosure, the method may further include the operations of: responding to a fourth prompt message sent by a server, and prompting, wherein the fourth prompt message is used for prompting a user of any one or more of the following messages by an intelligent voice device: the first preset information, the request application information which does not exist, the recommended application name information or the first recommended operation information.

According to an embodiment of the present disclosure, the method may further include the operations of: responding to a fifth prompt message sent by a server, and prompting, wherein the fifth prompt message is used for prompting a user of any one or more of the following messages by an intelligent voice device: second preset information, information that the requested application is not started or information that the application process is quitted to be started.

According to an embodiment of the present disclosure, the method may further include the operations of: responding to a received sixth prompt message sent by the server, and prompting, wherein the sixth prompt message is used for prompting the user of any one or more of the following messages by the intelligent voice device: third preset information, failure information for opening the request application or information for opening the request application again.

According to an embodiment of the present disclosure, the method may further include the operations of: responding to a seventh prompt message sent by the server, and prompting, wherein the seventh prompt message is used for prompting the user of any one or more of the following messages by the intelligent voice device: and fourth preset information, account information or second recommendation operation information is bound in the intelligent voice equipment application of the client.

According to an embodiment of the present disclosure, the method may further include the operations of: responding to the received eighth prompt message sent by the server, and prompting, wherein the eighth prompt message is used for prompting the user of any one or more of the following messages by the intelligent voice device: and fifth preset information, logging in the associated application information or the third recommended operation information by using the account at the client.

According to an embodiment of the present disclosure, the method may further include the operations of: responding to a ninth prompt message sent by a server, and prompting, wherein the ninth prompt message is used for prompting a user of any one or more of the following messages by an intelligent voice device: and filling writing information or fourth recommended operation information in the intelligent voice equipment application of the client.

Another aspect of the present disclosure provides an application opening apparatus, adapted to a server, where the server is connected to at least one intelligent voice device, and the server provides a service to at least one application supported by the at least one intelligent voice device, where the application opening apparatus may include: the device comprises 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 used for receiving first voice information sent by the intelligent voice equipment, the first determining module is used for analyzing the first voice information in response to receiving the first voice information sent by the intelligent voice equipment, if the first voice information comprises an application name and an application starting operation, whether the service end can provide service for a request application corresponding to the application name is determined according to the application name, the first sending module is used for sending first prompt information to the intelligent voice equipment if the service end can provide service for the request application and the request application is not started, the first prompt information is used for prompting a user whether to start the request application by the intelligent voice equipment, the second receiving module is used for receiving second voice information sent by the intelligent voice equipment, and the second sending module is used for responding to receiving the second voice information sent by the intelligent voice equipment, and analyzing the second voice information to obtain a user instruction, if the user instruction comprises the step of starting the request application, and sending second prompt information to the intelligent voice equipment, wherein the second prompt information is used for prompting the user that the request application is started by the intelligent voice equipment.

According to the embodiment of the present disclosure, the apparatus may further include a third sending module, where the third sending module is configured to send a third prompt message to the intelligent voice device if the server is capable of providing a service for the request application and the request application is already started, where the third prompt message is used for prompting, by the intelligent voice device, that the request application is already started.

According to an embodiment of the present disclosure, the apparatus may further include a fourth sending module, configured to send a fourth prompting message to the intelligent voice device if the server cannot provide a service for the requesting application, where the fourth prompting message is used for prompting, by the intelligent voice device, the user of any one or more of the following information: the first preset information, the request application information which does not exist, the recommended application name information or the first recommended operation information.

According to an embodiment of the present disclosure, the apparatus may further include a fifth sending module, where the fifth sending module is configured to not start the request application if the user instruction includes that the request application is not started, and send a fifth prompt message to the intelligent voice device, where the fifth prompt message is used for prompting, by the intelligent voice device, the user of any one or more of the following information: second preset information, information that the requested application is not started or information that the application process is quitted to be started.

According to an embodiment of the present disclosure, the apparatus may further include a sixth sending module, where the sixth sending module is configured to send a sixth prompt message to the intelligent voice device if the request application fails to be started, where the sixth prompt message is used for prompting, by the intelligent voice device, the user of any one or more of the following information: third preset information, failure information for opening the request application or information for opening the request application again.

According to the embodiment of the disclosure, the service end may at least include an intelligent voice device service end and a voice cloud service end, and accordingly, after the intelligent voice device service end is configured to receive the first voice information or the second voice information, the intelligent voice device service end sends the first voice information or the second voice information to the voice cloud service end, the voice cloud service end is configured to convert the first voice information or the second voice information into a structured text and send the structured text to the intelligent voice device service end, and the intelligent voice device service end is further configured to obtain an application name and a corresponding operation from the structured text.

According to the embodiment of the disclosure, the service end at least includes an intelligent voice device service end, a voice cloud service end and a third party service end, the intelligent voice device is an intelligent sound box, correspondingly, the intelligent voice device service end is used for acquiring an application name and a corresponding operation from the structured text, the intelligent voice device service end executes the corresponding operation and sends the structured text and an operation result of the corresponding operation to the third party service end, the third party service end is used for generating a logic processing result responding to the first voice information and/or the second voice information according to the structured text and the operation result and sending the logic processing result to the intelligent voice device service end, the logic processing result is text information, and the intelligent voice device service end is used for sending the logic processing result to the voice cloud service end, the voice cloud server is used for synthesizing the first prompt information or the second prompt information according to the logic processing result and sending the first prompt information or the second prompt information to the intelligent voice equipment server, wherein the first prompt information and the second prompt information are voice information, and the intelligent voice equipment server is used for sending the first prompt information and/or the second prompt information to the intelligent sound box so as to perform voice broadcasting.

According to an embodiment of the present disclosure, the apparatus may further include a seventh sending module, where before the requesting application is started, if the requesting application has an associated application and the associated application has an account, sending a seventh prompt message to the intelligent voice device when the requesting application does not bind the account, where the seventh prompt message is used for prompting, by the intelligent voice device, the user of any one or more of the following information: the intelligent voice device server is specifically configured to start the request application if the associated application is logged in by using the account, and send eighth prompt information to the intelligent voice device if the associated application is not logged in by using the account, where the eighth prompt information is used for prompting the user of any one or more of the following information: and fifth preset information, logging in the associated application information or the third recommended operation information by using the account at the client.

According to an embodiment of the present disclosure, the apparatus may further include a ninth sending module, configured to send, after the requesting application is started, ninth prompt information to the intelligent voice device if the requesting application needs to fill in information, where the ninth prompt information is used for prompting, by the intelligent voice device, the user of any one or more of the following information: sixth preset information, filling writing information or fourth recommended operation information in the intelligent voice device application of the client, and/or the first sending module is specifically configured to, after sending the first prompt message to the intelligent voice device, if the second voice message is not received within the first specified time, the first prompt message is sent to the intelligent voice equipment again, if the second voice message is not received within a second specified time, the requesting application is not started, and/or the first sending module is specifically configured to, after sending the first prompt message to the intelligent voice device, if the received voice information does not comprise the opening of the request application, sending the first prompt information to the intelligent voice equipment again, and if the received voice information does not comprise the opening of the request application, not opening the request application.

Another aspect of the present disclosure provides an application opening apparatus, adapted to an intelligent voice device, where the intelligent voice device is connected to a server, and the server provides a service to at least one application supported by the intelligent voice device, where the apparatus may include: the device comprises 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 used for receiving first voice information sent by a user, the tenth sending module is used for sending the first voice information to the server if the first voice information comprises a wakeup word, the first prompting module is used for receiving the first prompting information sent by the server and prompting, the first prompting information is used for prompting whether the user starts the request application, the fourth receiving module is used for receiving second voice information sent by the user, the eleventh sending module is used for sending the second voice information to the server, the second prompting module is used for receiving the second prompting information sent by the server and prompting, and the second prompting information is used for prompting the user to start the request application by intelligent voice equipment.

Another aspect of the present disclosure provides a computer system comprising: one or more processors, and a storage device for storing executable instructions that, when executed by the processors, implement a method as described above.

Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions for implementing the method as described above when executed.

Another aspect of the disclosure provides a computer program comprising computer executable instructions for implementing the method as described above when executed.

According to the embodiment of the disclosure, the questions such as question answering and question asking of non-target application can be improved through the opening of the control technology application, the opening of the control technology application can be realized in a voice mode, the user can be prevented from needing to utilize a client side such as a mobile phone to realize the opening of the control technology application, the interaction of the application opening process is enabled to be simpler through voice, and the user experience is improved.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

FIG. 1A schematically illustrates an application scenario of an application launching method, apparatus, computer system and medium according to an embodiment of the present disclosure;

FIG. 1B schematically illustrates a block diagram of a system architecture suitable for applying the opening method according to an embodiment of the present disclosure;

FIG. 2A is a flow chart that schematically illustrates a prior art method of using a smart sound box;

FIG. 2B schematically illustrates a flow chart of an application opening method according to an embodiment of the present disclosure;

FIG. 2C schematically illustrates a flow chart of a method of using a smart sound box according to an embodiment of the present disclosure;

FIG. 2D schematically illustrates a flow chart of an application opening method according to another embodiment of the present disclosure;

FIG. 3 schematically illustrates a flow chart of an application launching method according to another embodiment of the present disclosure;

FIG. 4A schematically illustrates a block diagram of an application opening device according to an embodiment of the present disclosure;

FIG. 4B schematically illustrates a block diagram of an application opening device according to another embodiment of the present disclosure; and

FIG. 5 schematically shows a block diagram of a computer system adapted to apply the opening method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

The embodiment of the disclosure provides an application starting method, an application starting device, a computer system and a medium. The method realizes the starting of the control application in a voice mode, particularly, a design method that the application skill can be opened in the voice environment of the intelligent voice equipment end aims to ensure the characteristics of simple and independent operation of a user in a natural language environment and provide smoother experience for the user.

Fig. 1A schematically illustrates an application scenario of an application opening method, an application opening apparatus, a computer system and a medium according to an embodiment of the present disclosure.

As shown in fig. 1A, when a user uses an intelligent voice device, such as an intelligent sound box, the whole process including opening an application and using the application can be realized only by sending a natural voice to the intelligent sound box, for example, the user speaks a voice to the intelligent sound box, such as dingdong, and opens a song name guessing, the required application is opened through the intelligent sound box in a voice interaction manner, and it is not necessary to operate a specific application of the intelligent sound box, such as a song name guessing application, by means of a client with a display screen, such as a mobile phone, and the like, by operating the specific intelligent sound box application, and during the period, the situation that the answer is not asked because a plurality of applications wind the semantics of the user's intention is not caused.

Fig. 1B schematically illustrates an exemplary system architecture 100 that may be applied to the application opening method according to an embodiment of the present disclosure. It should be noted that fig. 1B is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1B, the system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104, and

servers

105, 106, 107. The network 104 is used to provide a medium for communication links between the

terminal devices

101, 102, 103 and the

servers

105, 106, 107. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the

servers

105, 106, 107 via the network 104 to receive or send messages or the like. The

terminal devices

101, 103 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only). The

terminal devices

101, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The terminal device 102 may be an electronic device having 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, 107 may be servers providing various services, such as a background management server (by way of example only) providing services to at least one application supported by at least one

terminal device

101, 102, 103, a server performing speech recognition, semantic understanding and/or speech synthesis on speech, a server logically processing questions or requirements of users and giving content of replies, and so on. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the application starting method provided by the embodiment of the present disclosure may be executed by the

servers

105, 106, 107, or executed by the

terminal devices

101, 102, 103. Accordingly, the application opening device provided by the embodiment of the present disclosure may be generally disposed in the

servers

105, 106, 107, or may be disposed in the

terminal devices

101, 102, 103. The application starting method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster different from the

servers

105, 106, 107 and capable of communicating with the

terminal devices

101, 102, 103 and/or the

servers

105, 106, 107. Correspondingly, the application starting apparatus provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the

servers

105, 106, 107 and capable of communicating with the

terminal devices

101, 102, 103 and/or the

servers

105, 106, 107.

It should be understood that the number of terminal devices, networks, and servers are merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Fig. 2A schematically shows a flowchart of a method for using a smart sound box in the prior art.

As shown in fig. 2A, taking the intelligent voice device as an intelligent sound box for explanation, two stages exist in the use process of the intelligent sound box: the technical skill switching-on stage and the technical skill using stage are provided, wherein the technical skill switching-on stage is that when the intelligent sound box technical skill is used, the directivity and the ambiguity of the language of a user need to be distinguished, in order to avoid the situation that the meaning of the intention of the user is intertwined and the answer is not asked, which technical skill is switched on when the technical skill is used, and the misoperation of the instruction of the user by a non-target application is avoided, for example, when the user inputs the voice 'forgetting about grass' in the game process of guessing the name of a song, the shopping application considers that the user needs to purchase 'forgetting about grass' to cause the misoperation. Therefore, in the prior art, a user needs to start a corresponding skill, such as a song name guessing skill, in a skill center of an application APP (such as a sound box APP), the sound box APP of a client sends a user instruction to a server, such as a sound box cloud server, the sound box cloud server starts the song name guessing skill and returns an opening result after receiving the user instruction, at this time, a skill using stage can be entered, such as a user can use the song name guessing application, a specific use method can be a mode supported by various prior arts, for example, an intelligent sound box queries skill content from the sound box cloud server, and the sound box cloud server returns a broadcasting skill result and the like.

However, in the prior art, the operation of starting the technology depends on the operation of the device with the display screen, the interaction process is complicated, and the threshold for the user to use is high; in addition, the existing way of starting the skill restricts the further upgrade of the product form of the intelligent sound box, and the user experience is also influenced.

Fig. 2B schematically shows a flowchart of an application opening method according to an embodiment of the present disclosure.

The method is applicable to a server, where the server is connected to at least one intelligent voice device, and the server provides a service 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 to operation S205.

In operation S201, first voice information transmitted by a smart voice device is received.

In this embodiment, the first voice message may be various voice messages sent by the user to the intelligent voice device, for example, various voice commands during human-computer interaction, and the like. Preferably, the first voice message sent by the intelligent voice device may include wake-up information, such as a wake-up word, for example, "ding-dong, turn on guessing the name of the song", where the ding-dong is the wake-up word, which may avoid that the intelligent voice device sends too much useless voice message to the service end to cause resource waste. It should be noted that the first voice message does not necessarily include information to open a certain application, and may also be a voice message interacting with another application.

Then, in operation S202, in response to receiving first voice information sent by the intelligent voice device, the first voice information is analyzed, and if the first voice information includes an application name and an application opening operation, whether the service end can provide a service for a requested application corresponding to the application name is determined according to the application name.

In this embodiment, various skills may be provided by only the service end of the intelligent voice device, that is, each application is installed in the service end of the intelligent voice device, so that the service end of the intelligent voice device has a list of applications that can provide services, and when receiving the first voice information sent by the intelligent voice device, the service end of the intelligent voice device analyzes the first voice information to obtain a text result, and then may determine whether the text result includes an application name and an application opening operation.

In one embodiment, the service end at least comprises an intelligent voice equipment service end and a voice cloud service end. Accordingly, analyzing the first voice information may include the following operations.

Firstly, after receiving the first voice information, the intelligent voice equipment server sends the first voice information to the voice cloud server.

And then, the voice cloud service end converts the first voice information into a structured text and sends the structured text to the intelligent voice equipment service end.

And then, the intelligent voice equipment server side acquires the application name and the corresponding operation from the structured text.

In a specific embodiment, a user says ' ding-dong ', opens a song guessing name application ', an intelligent sound box is awakened by an awakening word ' ding-dong ', and meanwhile, the voice of ' ding-dong ', opening a song guessing name application ' or ' opening a song guessing name application ' is sent to an intelligent voice equipment service end, the intelligent voice equipment service end sends the voice of ' ding-dong ', opening a song guessing name application ' or ' opening a song guessing name application ' to a voice cloud service end for voice recognition and semantic understanding, the voice is converted into a structured text, such as a structured text of ' operation opening, application name guessing song name ', and then the structured text is sent to the intelligent voice equipment service end, and the intelligent voice equipment service end extracts the application name from the structured text as the song guessing name and operates as opening.

In operation S203, if the service end can provide a service for the requested application and the requested application is not started, a first prompt message is sent to the intelligent voice device, where the first prompt message is used for prompting, by the intelligent voice device, whether the user starts the requested application.

In this embodiment, the server may search in the application name list that can be supported by using the application name included in the structured text, and if there is a search result, it indicates that the server can provide a service for the requested application, and the server may further store states of skills of each smart speaker connected to the server, such as whether the skills are in an on state. If the server side can provide service for the request application and the request application is not started, first prompt information is sent to the intelligent voice device, the first prompt information can be various sound and light information such as voice information, character information, indicator light information and ringing information, and the sound and light information is used for prompting a user whether to activate the skill. Preferably, the first prompt message is a prompt message in a voice broadcast form, so that the user can obtain the prompt message more intuitively, and the voice interaction process is smoother.

In one embodiment, the service end may at least include an intelligent voice device service end, a voice cloud service end and a third party service end, the intelligent voice device is an intelligent sound box, and the first prompt information is prompt information in a voice broadcast form. Specifically, sending the first prompt message to the smart sound box may include the following operations.

After the intelligent voice equipment server acquires the application name and the corresponding operation from the structured text, the intelligent voice equipment server executes the corresponding operation and sends the structured text and the operation result of the corresponding operation to the third-party server.

And then, the third-party server generates a logic processing result responding to the first voice information according to the structured text and the operation result, and sends the logic processing result to the intelligent voice equipment server, wherein the logic processing result is text information.

And then, the intelligent voice equipment server side sends the logic processing result to the voice cloud server side.

And then, the voice cloud server synthesizes the first prompt information according to the logic processing result and sends the first prompt information to the intelligent voice equipment server, wherein the first prompt information is voice information.

And then, the intelligent voice equipment server sends the first prompt message to the intelligent sound box so as to carry out voice broadcast. Therefore, distributed design can be realized, different service ends bear different service logics and deployment, and response speed and performance are improved.

In one embodiment, after the intelligent voice equipment server receives the structured text of ' operation open, application name guess song name ', it is determined that the song guessing name application can be provided with service, and the song guessing name application is not opened, so that the structured text of ' operation open, application name guess song name ' and the state that the song guessing name application is not opened can be sent to the third party server, the third party server performs logic processing on the received information to obtain logic processing results, such as ' you have not opened XXXX (application name), whether open ' or ' you have not opened song name ', whether open ' text, and then sends the text to the intelligent voice equipment server, the intelligent voice equipment server processes ' you have not opened XXXX (application name), whether open ' into ' you have not opened song name ', and whether the song name is opened or not is judged, or a text of whether the song name is opened or not is directly sent to the voice cloud service end, voices of whether the song name is opened or not is judged, and the voices are synthesized and sent to the intelligent voice equipment service end, and the voice information of whether the song name is opened or not is sent to the intelligent voice equipment for voice broadcasting.

It should be noted that the foregoing embodiments are merely exemplary, and any one or more operations of speech recognition, semantic understanding, speech synthesis, and logic processing may also be performed on the smart speech device server and the smart speech device, which is not limited herein. When the processing power of the intelligent voice device is limited or higher quality results are required, the information can be processed by the corresponding remote service end.

In operation S204, second voice information transmitted by the smart voice device is received.

The second voice message may or may not include a wakeup word, or may not include an application name, for example, a voice "ding dong, start guessing song name", "yes/open/good" uttered by the user, and the like. But the second voice message should be time-efficient when the application name is not included. For example, after sending the first prompt message to the intelligent voice device, if the second voice message is not received within the first specified duration, the first prompt message is sent to the intelligent voice device again, and if the second voice message is not received within the second specified duration, the process of opening the request application is not started and the process of opening the request application is exited. If the user does not speak within 5 seconds, 7 seconds, 10 seconds or 20 seconds, the inquiry is made again, and the process exits after the inquiry is made twice.

In addition, in order to further reduce the probability of false opening of the application, the method may further include the following operations: after the first prompt message is sent to the intelligent voice equipment, if the received voice message does not include the opening of the request application, the first prompt message is sent to the intelligent voice equipment again, and if the received voice message does not include the opening of the request application, the request application is not opened. This may effectively improve the accuracy of the operation in the case of no wake-up word after the first voice interaction.

In operation S205, in response to receiving second voice information sent by the intelligent voice device, analyzing the second voice information to obtain a user instruction, if the user instruction includes starting the request application, and sending second prompt information to the intelligent voice device, where the second prompt information is used for prompting, by the intelligent voice device, that the user has started the request application.

In this embodiment, the process of analyzing the second voice information may refer to the process of analyzing the first voice information, for example, the voice cloud server analyzes the second voice information into a structured text and sends the structured text to the intelligent voice device server, which is not described herein again. In addition, the process of sending the second prompt information to the smart sound box may refer to the process of sending the first prompt information to the smart sound box, for example, a third-party server provides a logic processing result to a smart voice device server, and a voice cloud server performs voice synthesis on the logic processing result and sends the result to the smart voice device server, which is not described herein again.

For example, the server sends a voice message "started/entered application interaction flow" to the smart speaker, so that the smart speaker can broadcast the voice message.

Fig. 2C schematically shows a flowchart of a smart sound box using method according to an embodiment of the present disclosure.

By comparing fig. 2A and fig. 2C, it can be found that, in the embodiment of the present disclosure, when the user opens a new skill on the sound box, the user does not need to use the client, for example, the mobile phone APP performs auxiliary setting, and the opening of the new skill can be directly completed through the intelligent voice device.

It should be noted that, after the application of the intelligent voice device is started, the application use process may be further included, and the application use process may be the same as that in the prior art, and is not described herein again.

According to the application opening method, the control technology application is opened in a voice mode, so that the situation that a user needs to use a client side such as a mobile phone to open the control technology application can be avoided, interaction in the application opening process is simpler through voice, in addition, the application opening method can effectively avoid the problems of question answering and the like of non-target application, effectively improves the condition that semantics of user intention are intertwined, and is beneficial to improving user experience.

In another embodiment, the method may further comprise the operations of: and if the server side can provide service for the request application and the request application is started, sending third prompt information to the intelligent voice equipment, wherein the third prompt information is used for prompting the user that the request application is started by the intelligent voice equipment. Therefore, when the request application is opened, the request of the user can be quickly responded, and the request application is prompted to be opened.

For example, the user utters voice information to the smart speaker: after 'ding-dong, opening/enabling/starting XXXX (application name)', the intelligent sound box sends 'opening/enabling/starting XXXX (application name)' to the service end, and the intelligent sound box receives and broadcasts voice prompt information: "you have already opened XXXX/enter application interaction flow".

In another embodiment, the method may further comprise the operations of: if the server side can not provide service for the request application, sending fourth prompt information to the intelligent voice equipment, wherein the fourth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: the first preset information, the request application information which does not exist, the recommended application name information or the first recommended operation information. Therefore, whether the skill which the user wants to start exists or not can be judged firstly, if not, information can be prompted to the user in time, and corresponding application or operation related to recommendation does not exist so as to meet the requirements of the user. The first preset information may be preset text information or voice information, and the following preset information is similar to the preset information.

For example, the user utters voice information to the smart speaker: after 'ding-dong, opening/enabling/starting XXXX (application name)', the intelligent sound box sends 'opening/enabling/starting XXXX (application name)' to the service end, and the intelligent sound box receives and broadcasts voice prompt information: the method comprises the steps of 'finding no application, entering other processes/finding no application, judging whether a user wants to start a singer guessing/finding no application, suggesting to check an application list/finding no application in an intelligent sound box APP at a mobile phone end, and whether the application list needs to be broadcasted'.

In another embodiment, the method may further comprise the operations of: if the user instruction comprises that the request application is not started, and fifth prompt information is sent to the intelligent voice equipment, wherein the fifth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: second preset information, information that the requested application is not started or information that the application process is quitted to be started. Therefore, the process of opening the application can be timely ended when the user changes the intention and does not want to open the request application.

For example, the user utters voice information to the smart speaker: after 'ding-dong, opening/enabling/starting XXXX (application name)', the intelligent sound box sends 'opening/enabling/starting XXXX (application name)' to the service end, and the intelligent sound box receives and broadcasts voice prompt information: "you have not yet turned on XXXX (application name), whether it is on". The user sends out voice 'no (yes)/no on', the intelligent sound box sends 'no (yes)/no on' to the server, and the intelligent sound box receives and broadcasts voice prompt information: "not open XXXX (application name)/exit to open XXXX flow/closed XXXX (application name)".

In another embodiment, the method may further comprise the operations of: if the request application is failed to be started, sixth prompt information is sent to the intelligent voice equipment, and the sixth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: third preset information, failure information for opening the request application or information for opening the request application again. Therefore, when the application fails to be started, for example, when the current network environment is poor and the accidental starting fails, the user is prompted to try to start the application again.

For example, the user utters voice information to the smart speaker: after 'ding-dong, opening/enabling/starting XXXX (application name)', the intelligent sound box sends 'opening/enabling/starting XXXX (application name)' to the service end, and the intelligent sound box receives and broadcasts voice prompt information: "i seem like a horn you have without success in opening, and your good owner can try again/apply you have opened cheer, the information amount is a little big, hold me slowly, ask you open XXXX (application name) slightly etc.

Fig. 2D schematically shows a flowchart of an application opening method according to another embodiment of the present disclosure.

As shown in fig. 2D, the method may further include an operation of detecting whether the requesting application has an associated application, an operation of detecting whether the associated application has an account, and an operation of whether the associated application facilitates account login. The remaining operations may be referred to the embodiments shown above, and only the different parts will be described here.

In this embodiment, the method may further include the following operations.

Before the request application is started, if the request application has a related application and the related application has an account (that is, a bound account can only open the request application), sending a seventh prompt message to the smart voice device when the request application is not bound with the account, where the seventh prompt message is used for prompting a user of any one or more of the following information: and fourth preset information, account information or second recommendation operation information is bound in the intelligent voice equipment application of the client.

If the requesting application is bound to the account, the opening of the requesting application may include the following operations.

And if the associated application is logged in by using the account and an opening instruction of a user is received, opening the request application.

If the associated application does not utilize the account number for login and receives an opening instruction of a user, sending eighth prompt information to the intelligent voice equipment, wherein the eighth prompt information is used for prompting the user to any one or more of the following information by the intelligent voice equipment: and fifth preset information, logging in the associated application information or the third recommended operation information by using the account at the client.

For example, when the requesting application needs to bind an account of the associated application to start, it may be determined whether the user has bound the account of the associated application, and if not, the user may be prompted to perform account binding through the smart voice device, and then the requesting application is opened, for example, a voice message "please bind a kyoto account under an account of a mobile phone client, then open XXXX (application name)/please bind the account under an application platform of the mobile phone client", and then open XXXX (application name) "may be sent to the smart speaker. If the associated application is logged in by using the account, the request application can be started, and if the associated application is not logged in by using the account, a voice message 'please find a XXXXXX (application name) login account under a mobile phone client application platform and then open the request application' can be sent to the smart speaker box.

In one embodiment, binding an account to the requesting application may include the following operations.

Firstly, an account and a password of an associated application input by a user in an intelligent voice device application sent by a client are received.

And then, the account and the password of the associated application are sent to a server side of the associated application for authentication.

And then, receiving authentication passing information sent by a server side of the associated application, wherein the server side of the associated application authenticates the account and the password of the associated application, and if the account and the password of the associated application pass the authentication, sending the authentication passing information to the server side, wherein the authentication passing information comprises an authority opening identifier allowing the user to access the associated application through the intelligent voice equipment application.

And then, identifying the authentication passing information to generate prompt information of permission opening, and sending the prompt information of permission opening to the intelligent voice equipment for broadcasting and/or displaying permission opening information in the application of the intelligent voice equipment.

For example, a kyoto mall is opened, the application has an account and a password, and if the user does not log in the kyoto mall, the user cannot make a purchase, and at this time, the user is required to input the account and the password of the associated application in the smart voice device application of the client for authentication and binding.

Fig. 3 schematically shows a flowchart of an application opening method according to another embodiment of the present disclosure.

In this embodiment, the application starting method is applicable to an intelligent voice device, the intelligent voice device is connected to a server, and the server provides a service for at least one application supported by the intelligent voice device, as shown in fig. 3, where the method may include operation S301 to operation S306.

In operation S301, first voice information uttered by a user is received.

In operation S302, if the first voice message includes wakeup information, the first voice message is sent to the server.

In operation S303, receiving first prompt information sent by the server, and prompting, where the first prompt information is used to prompt a user whether to start the request application.

In operation S304, second voice information sent by the user is received, where the second voice information includes information for starting the requested application.

In operation S305, the second voice information is sent to the server.

In operation S306, second prompt information sent by the server is received and prompted, where the second prompt information is used to prompt the user that the request application is started.

Therefore, the application can be started in a voice interaction mode through intelligent voice equipment, such as an intelligent sound box, semantic winding which leads to user intention is effectively avoided, and the situation of asking questions for answers is effectively reduced.

In other embodiments, the method may further include the following operations.

In one embodiment, the prompt is performed in response to receiving third prompt information sent by the server, wherein the third prompt information is used for prompting the user that the request application is started by the intelligent voice device.

In another embodiment, the prompt is performed in response to receiving a fourth prompt message sent by the server, where the fourth prompt message is used for prompting the user of any one or more of the following information by the intelligent voice device: the first preset information, the request application information which does not exist, the recommended application name information or the first recommended operation information.

In another embodiment, the prompt is performed in response to receiving a fifth prompt message sent by the server, where the fifth prompt message is used for prompting the user of any one or more of the following messages by the intelligent voice device: second preset information, information that the requested application is not started or information that the application process is quitted to be started.

In another embodiment, the prompt is performed in response to receiving a sixth prompt message sent by the server, where the sixth prompt message is used for prompting the user of any one or more of the following messages by the intelligent voice device: third preset information, failure information for opening the request application or information for opening the request application again.

In another embodiment, the prompting is performed in response to receiving a seventh prompting message sent by the server, wherein the seventh prompting message is used for prompting the user of any one or more of the following information by the intelligent voice device: and fourth preset information, account information or second recommendation operation information is bound in the intelligent voice equipment application of the client.

In another embodiment, in response to receiving eighth prompt information sent by the server, prompting is performed, where the eighth prompt information is used for prompting the user by the intelligent voice device for any one or more of the following information: and fifth preset information, logging in the associated application information or the third recommended operation information by using the account at the client.

In another embodiment, the prompting is performed in response to receiving ninth prompting information sent by the server, wherein the ninth prompting information is used for prompting the user of any one or more of the following information by the intelligent voice device: and filling writing information or fourth recommended operation information in the intelligent voice equipment application of the client.

For details 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, reference may be made to a relevant description in the server, for example, the relevant description about the first prompt information and the second prompt information in operations S201 to S205, which is not described herein again.

Fig. 4A schematically illustrates a block diagram of an application opening device according to an embodiment of the present disclosure.

The application opening device can be applied to a server side, the server side is connected with at least one intelligent voice device, and the server side provides services for at least one application supported by the at least one intelligent voice device. As shown in fig. 4A, the application opening apparatus 400 may include a first receiving module 410, a first determining module 420, a first transmitting module 430, a second receiving module 440, and a second transmitting module 450.

The first receiving module 410 is configured to receive first voice information sent by an intelligent voice device.

The first determining module 420 is configured to analyze first voice information sent by an intelligent voice device in response to receiving the first voice information, and determine whether the server can provide a service for a requested application corresponding to an application name according to the application name if the first voice information includes the application name and an application opening operation.

The first sending module 430 is configured to send first prompt information to the intelligent voice device if the server can provide a service for the requested application and the requested application is not started, where the first prompt information is used for prompting, by the intelligent voice device, a user whether to start the requested application.

The second receiving module 440 is configured to receive second voice information sent by the intelligent voice device.

The second sending module 450 is configured to, in response to receiving second voice information sent by the intelligent voice device, analyze the second voice information to obtain a user instruction, if the user instruction includes starting the request application, start the request application, and send second prompt information to the intelligent voice device, where the second prompt information is used for prompting, by the intelligent voice device, that the user has started the request application.

In addition, the apparatus 400 may further include a third sending module, configured to send a third prompt message to the intelligent voice device if the server can provide a service for the requested application and the requested application is already started, where the third prompt message is used for prompting, by the intelligent voice device, that the requested application is already started.

In order to deal with the situation that there is an unsupported application, the apparatus 400 may further include a fourth sending module, configured to send a fourth prompt message to the intelligent voice device if the server cannot provide a service for the requested application, where the fourth prompt message is used for prompting, by the intelligent voice device, the user with any one or more of the following information: the first preset information, the request application information which does not exist, the recommended application name information or the first recommended operation information.

In another embodiment, when the user requirement changes without starting the requesting application, the apparatus 400 may further include a fifth sending module, configured to not start the requesting application if the user instruction includes not to start the requesting application, and send a fifth prompt message to the intelligent voice device, where the fifth prompt message is used for prompting the user of any one or more of the following information: second preset information, information that the requested application is not started or information that the application process is quitted to be started.

In order to deal with the situation that the opening fails due to a poor network state and the like, and when the request application needs to be opened again, the apparatus 400 may further include a sixth sending module, where the sixth sending module is configured to send a sixth prompt message to the intelligent voice device if the opening of the request application fails, where the sixth prompt message is used for prompting the user of any one or more of the following information by the intelligent voice device: third preset information, failure information for opening the request application or information for opening the request application again.

The service end can at least comprise an intelligent voice equipment service end and a voice cloud service end, correspondingly, the intelligent voice equipment service end is used for sending the first voice information or the second voice information to the voice cloud service end after receiving the first voice information or the second voice information, the voice cloud service end is used for converting the first voice information or the second voice information into a structured text and sending the structured text to the intelligent voice equipment service end, and the intelligent voice equipment service end is further used for obtaining an application name and corresponding operation from the structured text.

When the prompt information is voice information, the server at least comprises an intelligent voice equipment server, a voice cloud server and a third party server, and the intelligent voice equipment is an intelligent sound box.

And the intelligent voice equipment server is used for executing the corresponding operation after acquiring the application name and the corresponding operation from the structured text, and sending the structured text and the operation result of the corresponding operation to the third-party server.

The third-party server is used for generating a logic processing result responding to the first voice information and/or the second voice information according to the structured text and the operation result, and sending the logic processing result to the intelligent voice equipment server, wherein the logic processing result is text information.

And the intelligent voice equipment server is used for sending the logic processing result to the voice cloud server.

The voice cloud server is used for synthesizing the first prompt information or the second prompt information according to the logic processing result and sending the first prompt information or the second prompt information to the intelligent voice equipment server, wherein the first prompt information and the second prompt information are voice information.

The intelligent voice equipment server is used for sending the first prompt message and/or the second prompt message to the intelligent sound box so as to perform voice broadcasting.

In addition, because some applications have associated applications, and the associated applications have accounts, the apparatus 400 may further include a seventh sending module, configured to send, before starting the requesting application, seventh prompt information to the smart voice device when the requesting application does not bind the account, where the seventh prompt information is used for prompting, by the smart voice device, a user of any one or more of the following information: and fourth preset information, account information or second recommendation operation information is bound in the intelligent voice equipment application of the client.

Correspondingly, the intelligent voice device server is specifically configured to, if the associated application has logged in with the account, start the request application, and if the associated application has not logged in with the account, send eighth prompt information to the intelligent voice device, where the eighth prompt information is used by the intelligent voice device to prompt a user of any one or more of the following information: and fifth preset information, logging in the associated application information or the third recommended operation information by using the account at the client.

In other embodiments, the apparatus 400 may further include a ninth sending module, configured to send, after the requesting application is started, a ninth prompt message to the smart voice device if the requesting application needs to fill in information, where the ninth prompt message is used for prompting the user by the smart voice device for any one or more of the following information: and filling writing information or fourth recommended operation information in the intelligent voice equipment application of the client.

In addition, when the user does not give the second voice message for a long time after sending the first voice message, the first sending module 430 is specifically configured to, after sending the first prompt message to the intelligent voice device, send the first prompt message to the intelligent voice device again if the second voice message is not received within the first specified time, and not start the request application if the second voice message is not received within the second specified time.

After the user sends the first voice message, when sending the voice message unrelated to the opening of the request application in the interaction stage, such as chat, the process of opening the application may be exited, for example, the first sending module 430 is specifically configured to, after sending the first prompt message to the intelligent voice device, send the first prompt message to the intelligent voice device again if the received voice message does not include the opening of the request application, and not open the request application if the received voice message does not include the opening of the request application.

Fig. 4B schematically illustrates a block diagram of an application opening device according to another embodiment of the present disclosure.

Accordingly, the present disclosure also provides an application opening apparatus 700, which is suitable for an intelligent voice device, where the intelligent voice device is connected to a server, and the server provides a service for at least one application supported by the intelligent voice device, as shown in fig. 4B, the apparatus 700 may include: a third receiving module 710, a tenth transmitting module 720, a first prompting module 730, a fourth receiving module 740, an eleventh transmitting module 750, and a second prompting module 760.

The third receiving module 710 is used for receiving the first voice message sent by the user.

The tenth sending module 720 is configured to send the first voice message to the server if the first voice message includes a wakeup word.

The first prompt module 730 is configured to receive first prompt information sent by the server and prompt, where the first prompt information is used to prompt a user whether to start the request application.

The fourth receiving module 740 is configured to receive a second voice message 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 prompt the server, where the second prompt information is used for prompting, by the intelligent voice device, that the user has started the request application.

It should be noted that the apparatus 700 may further include a third prompt module, a fourth prompt module, a fifth prompt module, a sixth prompt module, a seventh prompt module (not shown), and the like, which respectively have the functions of prompting the third prompt information, the fourth prompt information, the fifth prompt information, the sixth prompt information, the seventh prompt information, and the like, and are not described herein again.

Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure 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 implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as 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 may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.

For example, any plurality of the first receiving module 410, the first determining module 420, the first transmitting module 430, the second receiving module 440, and the second transmitting module 450 may be combined in one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first receiving module 410, the first determining module 420, the first transmitting module 430, the second receiving module 440, and the second transmitting module 450 may be at least partially implemented as a hardware circuit, such as 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 may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the first receiving module 410, the first determining module 420, the first transmitting module 430, the second receiving module 440 and the second transmitting module 450 may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.

FIG. 5 schematically illustrates a block diagram of a computer system suitable for implementing the above-described method according to an embodiment of the present disclosure. The computer system illustrated in FIG. 5 is only one example and should not impose any limitations on the scope of use or functionality of embodiments of the disclosure.

As shown in fig. 5, a computer system 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. The processor 501 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 501 may also include onboard memory for caching purposes. Processor 501 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.

In the RAM 503, various programs and data necessary for the operation of the system 500 are stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. The processor 501 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 502 and/or the RAM 503. Note that the programs may also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 may also perform various operations of method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, system 500 may also include an input/output (I/O) interface 505, input/output (I/O) interface 505 also being connected to bus 504. The system 500 may also include one or more of the following components connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or 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 necessary. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.

According to embodiments of the present disclosure, method flows according to embodiments of the present disclosure may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 611. The computer program, when executed by the processor 501, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM 502 and/or RAM 503 and/or one or more memories other than ROM 502 and RAM 503 described above.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. An application opening method is applicable to a server, the server is connected with 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, and the method comprises the following steps:

receiving first voice information sent by intelligent voice equipment;

responding to first voice information sent by intelligent voice equipment, analyzing the first voice information, and if the first voice information comprises an application name and an application starting operation, determining whether the service end can provide service for a request application corresponding to the application name according to the application name;

if the server can provide service for the request application and the request application is not started, sending first prompt information to the intelligent voice equipment, wherein the first prompt information is used for prompting a user whether to start the request application or not by the intelligent voice equipment;

receiving second voice information sent by the intelligent voice equipment; and

responding to the received second voice information sent by the intelligent voice equipment, analyzing the second voice information to obtain a user instruction, if the user instruction comprises the request application, starting the request application, and sending second prompt information to the intelligent voice equipment, wherein the second prompt information is used for prompting the user that the request application is started by the intelligent voice equipment.

2. The method of claim 1, further comprising:

and if the server side can provide service for the request application and the request application is started, sending third prompt information to the intelligent voice equipment, wherein the third prompt information is used for prompting the user that the request application is started by the intelligent voice equipment.

3. The method of claim 1, further comprising:

if the server side can not provide service for the request application, sending fourth prompt information to the intelligent voice equipment, wherein the fourth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: the first preset information, the request application information which does not exist, the recommended application name information or the first recommended operation information.

4. The method of claim 1, further comprising:

if the user instruction comprises that the request application is not started, and fifth prompt information is sent to the intelligent voice equipment, wherein the fifth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: second preset information, information that the requested application is not started or information that the application process is quitted to be started.

5. The method of claim 1, further comprising:

if the request application is failed to be started, sixth prompt information is sent to the intelligent voice equipment, and the sixth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: third preset information, failure information for opening the request application or information for opening the request application again.

6. The method of claim 1, wherein:

the server side at least comprises an intelligent voice equipment server side and a voice cloud server side;

analyzing the first voice information or the second voice information includes:

after receiving the first voice information or the second voice information, the intelligent voice equipment server sends the first voice information or the second voice information to the voice cloud server;

the voice cloud server converts the first voice information or the second voice information into a structured text and sends the structured text to the intelligent voice equipment server;

and the intelligent voice equipment server side acquires the application name and the corresponding operation from the structured text.

7. The method of claim 6, wherein:

the server side at least comprises an intelligent voice equipment server side, a voice cloud server side and a third party server side, and the intelligent voice equipment is an intelligent sound box;

sending first prompt information or second prompt information to the intelligent sound box comprises the following steps:

after the intelligent voice equipment server acquires the application name and the corresponding operation from the structured text, the intelligent voice equipment server executes the corresponding operation and sends the structured text and the operation result of the corresponding operation to the third-party server;

the third-party server generates a logic processing result responding to the first voice information and/or the second voice information according to the structured text and the operation result, and sends the logic processing result to the intelligent voice equipment server, wherein the logic processing result is text information;

the intelligent voice equipment server side sends the logic processing result to the voice cloud server side;

the voice cloud server synthesizes the first prompt message or the second prompt message according to the logic processing result and sends the first prompt message or the second prompt message to the intelligent voice equipment server, wherein the first prompt message and the second prompt message are voice messages;

and the intelligent voice equipment server sends the first prompt message and/or the second prompt message to the intelligent sound box so as to perform voice broadcast.

8. The method of claim 1, further comprising:

before the request application is started, if the request application has a related application and the related application has an account, sending seventh prompt information to the intelligent voice device when the request application is not bound with the account, wherein the seventh prompt information is used for prompting a user of any one or more of the following information by the intelligent voice device: fourth preset information, account information or second recommended operation information is bound in the intelligent voice equipment application of the client;

if the account is bound to the request application, the opening the request application comprises:

if the associated application is logged in by using the account, starting the request application;

if the associated application does not utilize the account to log in, sending eighth prompt information to the intelligent voice equipment, wherein the eighth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice equipment: and fifth preset information, logging in the associated application information or the third recommended operation information by using the account at the client.

9. The method of claim 8, wherein binding an account to the requesting application comprises:

receiving an account and a password of an associated application input by a user in an intelligent voice device application sent by a client;

sending the account and the password of the associated application to a server of the associated application for authentication;

receiving authentication passing information sent by a server side of the associated application, wherein the server side of the associated application authenticates an account and a password of the associated application, and if the account and the password of the associated application pass the authentication, the server side sends the authentication passing information to the server side, and the authentication passing information comprises an authority opening identifier allowing the user to access the associated application through the intelligent voice equipment application;

and identifying the authentication passing information to generate prompt information of permission opening, and sending the prompt information of permission opening to the intelligent voice equipment for broadcasting and/or displaying the permission opening information in the application of the intelligent voice equipment.

10. The method of claim 1, further comprising:

after the request application is started, if the request application needs to fill in information, ninth prompt information is sent to the intelligent voice device, and the ninth prompt information is used for prompting the user of any one or more of the following information by the intelligent voice device: filling writing information or fourth recommendation operation information in the intelligent voice equipment application of the client;

and/or

After sending the first prompt message to the intelligent voice equipment, if the second voice message is not received within a first specified time length, sending the first prompt message to the intelligent voice equipment again, and if the second voice message is not received within a second specified time length, not starting the request application;

and/or

After the first prompt message is sent to the intelligent voice equipment, if the received voice message does not include the opening of the request application, the first prompt message is sent to the intelligent voice equipment again, and if the received voice message does not include the opening of the request application, the request application is not opened.

11. An application opening method is applicable to intelligent voice equipment, the intelligent voice equipment is connected with a server, and the server provides services for at least one application supported by the intelligent voice equipment, and the method comprises the following steps:

receiving first voice information sent by a user;

if the first voice information comprises awakening information, sending the first voice information to the server;

receiving first prompt information sent by the server and prompting, wherein the first prompt information is used for prompting a user whether to start the request application;

receiving second voice information sent by a user, wherein the second voice information comprises the information for starting the request application;

sending the second voice information to the server;

and receiving second prompt information sent by the server and prompting, wherein the second prompt information is used for prompting a user that the request application is started.

12. An application opening device, adapted to a server, where 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 includes:

the first receiving module is used for receiving first voice information sent by the intelligent voice equipment;

the first determining module is used for responding to the received first voice information sent by the intelligent voice equipment, analyzing the first voice information, and if the first voice information comprises an application name and an application starting operation, determining whether the service terminal can provide service for a request application corresponding to the application name according to the application name;

a first sending module, configured to send first prompt information to the intelligent voice device if the server can provide a service for the requested application and the requested application is not started, where the first prompt information is used for prompting, by the intelligent voice device, a user whether to start the requested application;

the second receiving module is used for receiving second voice information sent by the intelligent voice equipment; and

and the second sending module is used for responding to the received second voice information sent by the intelligent voice equipment, analyzing the second voice information to obtain a user instruction, if the user instruction comprises the opening of the request application, opening the request application, and sending second prompt information to the intelligent voice equipment, wherein the second prompt information is used for prompting the user that the request application is opened by the intelligent voice equipment.

13. The apparatus of claim 12, further comprising:

and the third sending module is used for sending third prompt information to the intelligent voice equipment if the server can provide service for the request application and the request application is started, wherein the third prompt information is used for prompting the user that the request application is started by the intelligent voice equipment.

14. The apparatus of claim 12, further comprising:

a fourth sending module, configured to send fourth prompt information to the intelligent voice device if the server cannot provide a service for the requested application, where the fourth prompt information is used for prompting, by the intelligent voice device, a user of any one or more of the following information: the first preset information, the request application information which does not exist, the recommended application name information or the first recommended operation information.

15. The apparatus of claim 12, further comprising:

a fifth sending module, configured to, if the user instruction includes that the request application is not started, not start the request application, and send fifth prompt information to the intelligent voice device, where the fifth prompt information is used for prompting, by the intelligent voice device, a user of any one or more of the following information: second preset information, information that the requested application is not started or information that the application process is quitted to be started.

16. The apparatus of claim 12, further comprising:

a sixth sending module, configured to send a sixth prompt message to the intelligent voice device if the request application fails to be started, where the sixth prompt message is used for prompting, by the intelligent voice device, a user of any one or more of the following information: third preset information, failure information for opening the request application or information for opening the request application again.

17. The apparatus of claim 12, wherein the service side comprises at least a smart voice device service side and a voice cloud service side;

the intelligent voice equipment server is used for sending the first voice information or the second voice information to the voice cloud server after receiving the first voice information or the second voice information;

the voice cloud server is used for converting the first voice information or the second voice information into a structured text and sending the structured text to the intelligent voice equipment server;

and the intelligent voice equipment server is also used for acquiring an application name and corresponding operation from the structured text.

18. The apparatus according to claim 17, wherein the service end at least comprises an intelligent voice device service end, a voice cloud service end and a third party service end, and the intelligent voice device is an intelligent sound box;

the intelligent voice equipment server is used for executing the corresponding operation after acquiring the application name and the corresponding operation from the structured text, and sending the structured text and the operation result of the corresponding operation to the third-party server;

the third-party server is used for generating a logic processing result responding to the first voice information and/or the second voice information according to the structured text and the operation result, and sending the logic processing result to the intelligent voice equipment server, wherein the logic processing result is text information;

the intelligent voice equipment server is used for sending the logic processing result to the voice cloud server;

the voice cloud server is used for synthesizing the first prompt information or the second prompt information according to the logic processing result and sending the first prompt information or the second prompt information to the intelligent voice equipment server, wherein the first prompt information and the second prompt information are voice information;

19. The apparatus of claim 12, further comprising:

a seventh sending module, configured to, before the request application is started, send a seventh prompt message to the smart voice device when the request application is not bound to the account if the request application has an associated application and the associated application has an account, where the seventh prompt message is used for prompting, by the smart voice device, a user of any one or more of the following information: fourth preset information, account information or second recommended operation information is bound in the intelligent voice equipment application of the client;

the intelligent voice device server is specifically configured to, if the associated application has logged in with the account, start the request application, and if the associated application has not logged in with the account, send eighth prompt information to the intelligent voice device, where the eighth prompt information is used for prompting, by the intelligent voice device, a user of any one or more of the following information: and fifth preset information, logging in the associated application information or the third recommended operation information by using the account at the client.

20. The apparatus of claim 12, further comprising:

a ninth sending module, configured to send, after the request application is started, ninth prompt information to the intelligent voice device if the request application needs to fill in information, where the ninth prompt information is used for prompting, by the intelligent voice device, a user of any one or more of the following information: filling writing information or fourth recommendation operation information in the intelligent voice equipment application of the client;

and/or

The first sending module is specifically configured to, after sending the first prompt message to the intelligent voice device, send the first prompt message to the intelligent voice device again if the second voice message is not received within a first specified duration, and not start the request application if the second voice message is not received within a second specified duration;

and/or

The first sending module is specifically configured to, after sending the first prompt message to the intelligent voice device, send the first prompt message to the intelligent voice device again if the received voice message does not include starting the request application, and not start the request application if the received voice message does not include starting the request application.

21. An application opening device, which is suitable for an intelligent voice device, wherein the intelligent voice device is connected with a server, and the server provides services for at least one application supported by the intelligent voice device, and the device comprises:

the third receiving module is used for receiving the first voice information sent by the user;

a tenth sending module, configured to send the first voice message to the server if the first voice message includes a wakeup word;

the first prompt module is used for receiving and prompting first prompt information sent by the server, wherein the first prompt information is used for prompting a user whether to start the request application;

the fourth receiving module is used for receiving second voice information sent by the user;

an eleventh sending module, configured to send the second voice information to the server;

and the second prompt module is used for receiving and prompting second prompt information sent by the server, and the second prompt information is used for prompting the user that the request application is started by the intelligent voice equipment.

22. A computer system, comprising:

one or more processors;

a storage device for storing executable instructions which, when executed by the processor, implement the method of any one of claims 1 to 11.

23. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, implement a method according to any one of claims 1 to 11.