CN107122179A - The function control method and device of voice - Google Patents

Abstract

The present application provides a voice function control method, which is applied to the voice assistant of the terminal, including: determining an associated application program according to the recognition result of the voice input by the user; the associated application program is used to realize the function to be used by the user; The user's input voice is transmitted to the associated application program for the associated application program to recognize the user's input voice, and implement the function according to the recognition result. Through the technical solution of the present application, the functions required by the user can be completed more accurately and quickly, and the efficiency of voice function control can be improved.

Description

Voice function control method and device

technical field

The present application relates to the technical field of network communication, in particular to a voice function control method and device.

Background technique

Voice assistant is a kind of software running on the terminal, which can communicate with users by voice and assist users to realize various functions specified by them, such as information search and terminal operation. Since Apple launched its voice assistant Siri, users have greatly increased their attention and usage of voice assistant software, which has also brought impetus to the development of voice assistants.

At present, the voice assistant can be combined with the application program installed on the terminal. The user sends an instruction to the voice assistant to perform a certain task, and the voice assistant calls the corresponding application program to complete the task, thus greatly enriching the user's ability to use Voice assistant is a single entry to complete the function.

In the prior art, taking Siri as an example, Siri can cooperate with six types of application programs (taxi-hailing, communication, photo search, payment, Internet phone, fitness). When Siri receives the user's voice input, it judges the user's intention, and Decide whether to handle it yourself or the calling application. If it decides to call the application, Siri extracts relevant information from its own recognition results of the user's voice and gives it to the application. The application executes the function specified by the information according to the information provided by Siri.

It can be seen that the information provided by Siri is the basis for whether the task specified by the user can be completed correctly. When Siri does not recognize the input speech accurately enough, it is difficult for the user to control the functions through voice to a satisfactory level.

Contents of the invention

In view of this, this application provides a voice function control method, which is applied to the voice assistant of the terminal, including:

According to the recognition result of the voice input by the user, an associated application program is determined; the associated application program is used to realize the function to be used by the user;

The user's input voice is delivered to the associated application program for the associated application program to recognize the user's input voice, and implement the function according to the recognition result.

A voice function control method provided by this application is applied to a terminal application program used to realize functions other than voice assistant, including:

receive voice input from the user of the voice assistant;

Recognize the user's input voice, and realize the function that the user wants to use according to the recognition result.

The present application also provides a voice function control device, which is applied to the voice assistant of the terminal, including:

The associated application program unit is used to determine the associated application program according to the recognition result of the voice input by the user; the associated application program is used to realize the function to be used by the user;

The input voice transmission unit is used to transmit the user's input voice to the associated application program, so that the associated application program can recognize the user's input voice, and implement the function according to the recognition result.

A voice function control device provided by this application is applied to a terminal application program used to realize functions other than voice assistant, including:

Input voice receiving unit, is used for receiving the input voice from the user of voice assistant;

The function realization unit is used to recognize the input voice of the user, and realize the function to be used by the user according to the recognition result.

It can be seen from the above technical solutions that in the embodiment of the present application, after the voice assistant determines the associated application program based on the recognition result of the user's input voice, the user's input voice is passed to the associated application program, and the associated application program recognizes the input voice by itself. Execute the user's instructions; since the associated applications have their own exclusive application fields, such as the map and navigation field of Gaode map, the accuracy of speech recognition in the type of function it belongs to is higher than that of general use in most cases. The accuracy of the voice assistant of the function type, so that the functions required by the user can be completed more accurately and quickly, and the efficiency of voice function control can be improved.

Description of drawings

FIG. 1 is a flowchart of a voice function control method applied to a voice assistant of a terminal in an embodiment of the present application;

FIG. 2 is a flow chart of a voice function control method applied to an application program of a terminal in an embodiment of the present application;

Fig. 3 is a schematic diagram of the working principle of the application example of the present application;

FIG. 4 is a hardware structural diagram of a terminal;

FIG. 5 is a logical structure diagram of a voice function control device applied to a voice assistant of a terminal in an embodiment of the present application;

FIG. 6 is a logical structure diagram of a voice function control device applied to an application program of a terminal in an embodiment of the present application.

detailed description

In the prior art, many non-voice assistant application programs installed on the terminal itself also have the ability to receive user voice input, recognize and execute the user's voice command, and realize the functions that the user wants to use. For the sake of brevity, the applications of voice assistants are referred to as voice assistants below, and the application programs of non-voice assistants and used to implement functions other than voice assistants are referred to as applications.

The voice assistant is originally designed as a unified entrance for voice interaction with the user. In addition to recognizing the user's instructions that may involve all types of functions, it also needs to chat with the user. Therefore, the voice assistant lexicon has an extremely wide range of vocabulary, and its speech recognition algorithm Optimization must also take into account the recognition rate of all types of vocabulary. However, applications often focus on the realization of several main functions. For example, map-type applications focus on addressing, positioning and navigation, and shopping-type applications focus on commodities and transactions. When users adopt these applications, their intentions are basically Make sure to use the application-focused features. The vocabulary range of the thesaurus used for speech recognition in the application is thus also focused on its dedicated functional area, as is the optimization of the speech recognition algorithm.

The waiting time from sending out the voice command to waiting for the terminal to give a response will greatly affect the user experience, so the time available for voice recognition is very limited. In a limited period of time, in any specific functional area, the voice assistant's recognition of the user's input voice intended to use a certain function in this area is difficult to catch up with the recognition of applications belonging to this functional area in terms of accuracy.

For example, in terms of location names, the thesaurus of AutoNavi Maps is more comprehensive and accurate than that of Siri; at the same time, due to the accumulation of long-term searches on locations, the recognition algorithm of AutoNavi Maps is also more accurate than Siri in recognizing place names. In order to be accurate, Siri does not have more reliable data such as place names and locations as a reference in the application scenario of navigation to optimize its recognition algorithm.

It can be seen that in the prior art, the voice assistant transmits the recognition result to the application program. In fact, the party who is not good at a certain job completes the work, and the inaccurate work result is handed over to the other party who is good at the job. One party has to perform tasks on the basis of poor work results, and it is naturally difficult to achieve good results.

Based on the above ideas, the embodiment of the present application proposes a new voice function control method. The voice assistant determines the associated application program that realizes the user's intention through the recognition of the user's input voice, and then passes the input voice to the associated application program. After the associated application program recognizes the voice by itself, it realizes the functions that the user wants to use, so that the application program executes the user's instructions based on the original input voice, and can execute based on the result of self-recognition instead of the unsatisfactory recognition result of the voice assistant. In order to accurately and quickly complete the functions required by users, so as to solve the problems existing in the prior art.

In the embodiment of the present application, both the voice assistant and the application program run on the user's terminal. The voice assistant can run at the operating system level of the terminal, or as an application on the upper layer of the operating system, without limitation. The user's terminal can be any device with voice input, calculation and storage functions, such as mobile phone, tablet computer, PC (Personal Computer, personal computer), notebook, server, etc., which is also not limited.

In the embodiment of the present application, the flow of the voice function control method applied to the voice assistant is shown in FIG. 1 , and the flow of the method applied in the application program is shown in FIG. 2 .

On the voice assistant, in step 110, the associated application program is determined according to the recognition result of the voice input by the user. The associated application program is used to realize the function to be used by the user.

When the voice assistant receives the user's voice input, it recognizes the user's voice. If the user's instruction does not involve the use of any function, or the function that the user wants to use is executed by the voice assistant, the voice assistant will reply to the user's input based on the recognition result. , or execute user commands. If the recognition result of the voice assistant is that the user intends to use a function performed by an application program, the voice assistant determines an associated application program that implements the function.

The user may specify the desired application in the voice input. In this case, the voice assistant can extract the application program name from the recognition result of the user's input voice, and use the application program (ie, the application program specified by the user in the input voice) as an associated application program. For example, the user says to the voice assistant, "Use Didi to help me call a car home", and the voice assistant recognizes the application name "Didi", and uses the application Didi as the associated application.

If the user does not specify the desired application in the input voice, the voice assistant can determine the function that the user wants to use based on the recognition result of the user input voice, and then determine the association among the applications installed on the terminal according to the function that the user wants to use application. The method for the voice assistant to determine the function to be used by the user from the recognition result can be realized by referring to various existing technologies. For example, several keywords of each function can be preset. If the recognition result of the user's voice hits a certain function keyword , you can know which function the user wants to use.

The manner in which the associated application program is determined by the function to be used by the user may be determined according to the needs of the actual application scenario, and the following two implementation manners are taken as examples for illustration.

In the first implementation manner, after the voice assistant recognizes the function to be used by the user, one or more applications installed on the terminal that can realize the function to be used by the user and support voice input can be used as Alternate applications, display the names of alternative applications to the user for selection. After receiving the user's selection result, the voice assistant uses the application selected by the user as an associated application.

In the second implementation manner, the mapping relationship between the functions to be used and the application programs can be maintained on the terminal. After identifying the function to be used by the user, the voice assistant may use an application having a mapping relationship with the function to be used by the user as an associated application. In the aforementioned example of using function keywords to reflect the functions that users want to use, a mapping relationship table between function keywords and applications can be saved on the terminal, and the voice assistant can extract the function keys from the recognition results of the user's input voice. After the word, the application program that has a mapping relationship with the function keyword can be used as the associated application program.

In the second implementation, the mapping relationship between the function to be used and the application program can be set and/or modified by the user, or generated by a voice assistant or an operating system, and these methods can also be applied at the same time. The embodiments of the present application do not Do limited. In one example, the user can set the mapping relationship between the function to be used and the associated application program during voice input in the setting item provided by the voice assistant or the operating system (one to multiple functions corresponds to one application program). In another example, when a certain function is to be implemented, the application program most frequently used by the user may be used as the application program having a mapping relationship with the function; specifically, if there is only one application program installed on the terminal to implement a certain function , then the application program is used as the application program that has a mapping relationship with the function; if there is more than one application program, the frequency of using each application program that implements the function can be used according to the statistics of the operating system, and the one with the highest frequency is used as the application program that has the mapping relationship with the function. An application with a mapping relationship. In the third example, the user can also set the application program as the application program that has a mapping relationship with the function during voice input in the application program that implements a certain function. After the application program receives the user's setting instruction, Submit the mapping relationship between this application and the function to be used to the voice assistant; if the user sets the voice input in the AutoNavi map, and has a mapping relationship with the function keyword "navigation", AutoNavi will submit the setting item according to the user's operation For Siri, Siri saves this mapping relationship, and when the user voice inputs "where to navigate", Siri will follow the mapping relationship and use AutoNavi Maps as the associated application.

It should be noted that the above two manners for determining associated application programs may also be applied in combination. For example, after the voice assistant determines the function to be used by the user, query the mapping relationship between the saved function and the application program, and if the application program that has a mapping relationship with the function to be used can be found, determine the associated application program according to the mapping relationship; If it cannot be found, the user can select an application program on the terminal that can realize the function to be used and supports voice input, and determine the associated application program according to the user's selection. After the user chooses, the user can be asked to set the default associated application of the function. If the user sets it, the mapping relationship between the function and the application set by the user will be saved; if no setting is made, the voice assistant can also select an application after the user After the number and frequency of implementing a certain function exceed the set threshold, the mapping relationship between the application program and the function is saved. For example, the mapping relationship between the function and the application program maintained by Siri does not include the mapping relationship of the function of "navigation". , Baidu Maps and Sogou Maps application names are displayed to the user, and the user chooses which application to use for navigation; if the user selects Gaode Map 4 times, Siri will map the "navigation" function with Gaode Map The relationship is saved in the mapping relationship table; when the user gives voice instructions for navigation, Siri will directly use Gaode Map as the associated application.

On the voice assistant, in step 120, the user's input voice is transmitted to the associated application program, so that the associated application program can recognize the user's input voice, and realize the function according to the recognition result.

On the associated application program, step 210, receive input voice from the user of the voice assistant.

After the voice assistant determines the associated application that executes the function that the user wants to use, it opens the associated application (including starting the associated application, placing the associated application in the foreground, etc.), and transmits the user's input voice to the associated application.

On the associated application program, in step 220, the input voice of the user is recognized, and the function to be used by the user is realized according to the recognition result.

The associated application program recognizes the user's input voice from the voice assistant, and runs the business processing logic of the associated application program according to the recognition result to realize the functions that the user wants to use. The associated application program can perform speech recognition and function realization according to the existing technology, and details will not be repeated here.

In an example, the voice assistant can transmit its own recognition result of the user's input voice and the user's input voice to the associated application program. The associated application program recognizes the user's input voice by itself, and realizes the function that the user wants to use according to the recognition result of the associated application program itself and the recognition result from the voice assistant. The recognition result of the voice assistant can be used as a reference for the associated application program in speech recognition, further increasing the accuracy of recognition.

It can be seen that in the embodiment of the present application, the voice assistant determines the associated application program that realizes the function that the user wants to use by recognizing the voice input by the user, and passes the input voice to the associated application program, and the associated application program recognizes the input voice by itself and then executes it. Instructions from the user, so that the more accurate voice recognition results of the application program in its function type can be used to complete the functions required by the user more accurately and quickly, and improve the efficiency of voice function control.

In an application example of the present application, the user's Apple terminal is installed with voice assistant Siri and several application programs capable of completing various types of functions. A mapping relationship table between function keywords and application programs is stored in Siri. An example of a mapping relationship table is shown in Table 1:

Table 1

The working principle of this application example is shown in Figure 3. After receiving the user’s input voice, Siri recognizes the input voice. Assuming that the functions that the user wants to use need to be realized with the help of other applications, Siri extracts the description from the recognition result The user wants to use the function keyword of the function, and use the function keyword to look up the mapping relationship table. If an application program corresponding to the function keyword is found, the application program is used as an associated application program. If the function keyword is not found in the table, Siri will display the names of all applications installed on the terminal that can realize the function and support voice input to the user, and ask the user to select which application program to use. Siri uses the user-selected app as an associated app.

Siri puts the associated application in the foreground and transmits the user's input voice to the associated application through the operating system. The associated application program recognizes the user's input voice, and completes the tasks instructed by the user according to its own recognition results and business processes.

For example, the user says to Siri, "Transfer 2000 to Zhang San". Siri recognizes the function keyword "transfer", and inquires from Table 1 that the associated application is Alipay. Siri opens Alipay and passes the user's input voice to Alipay. Alipay recognizes the input voice, starts the transfer business process, and displays "Payee: Zhang San" and "Transfer Amount: 2000" to the user. After the user enters the password or verifies the fingerprint, the transfer can be completed.

Corresponding to the implementation of the above process, the embodiment of the present application also provides a voice function control device applied to a terminal voice assistant, and a voice function control device applied to a terminal application program. These two devices can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by reading corresponding computer program instructions into the memory through the CPU (Central Process Unit, central processing unit) of the terminal to run. From the perspective of hardware, in addition to the CPU, memory, and non-volatile memory shown in Figure 4, the terminal where the voice function control device is located usually includes other hardware such as a chip for wireless signal transmission and reception, and/or Other hardware such as boards and cards used to realize network communication functions.

Figure 5 shows a voice function control device provided by the embodiment of the present application, which is applied to the voice assistant of the terminal, and includes an associated application program unit and an input voice transfer unit, wherein: the associated application program unit is used to The voice recognition result determines the associated application program; the associated application program is used to realize the function that the user wants to use; the input voice transfer unit is used to transmit the user's input voice to the associated application program for the associated application program to The user's input voice is recognized, and the function is realized according to the recognition result.

In one example, the terminal maintains a mapping relationship between the function to be used and the application program; the associated application program unit is specifically used to: determine the function to be used by the user according to the recognition result of the user's input voice, and associate with the user The function to be used has an application with a mapping relationship as an associated application.

In the above example, the mapping relationship between the function to be used and the application program includes: the mapping relationship between the function keyword and the application program; the associated application program unit is specifically used to: extract the function in the recognition result of the user input voice keywords, and use the application program that has a mapping relationship with the function keyword as an associated application program.

In the above example, the mapping relationship between the function to be used and the application program includes: the mapping relationship between the function to be used and the application program set by the user; A frequently used application program is an application program having a mapping relationship with the function to be used; and/or, a mapping relationship between the application program and the function to be used submitted by a certain application program.

Optionally, the associated application program unit is specifically configured to: determine the function to be used by the user according to the recognition result of the voice input by the user, and link several application programs on the terminal that can realize the function and support voice input The name is displayed to the user for selection, with the application selected by the user as the associated application.

Optionally, the associated application program unit is specifically configured to: extract the application program name in the recognition result of the voice input by the user, and use the application program specified in the input voice as the associated application program.

Optionally, the input speech transfer unit is specifically configured to: transfer the recognition result and the user's input speech to the associated application, so that the associated application can recognize the user's input speech, and The recognition result of the program and the recognition result of the voice assistant realize the function.

Figure 6 shows a voice function control device provided by the embodiment of the present application, which is applied to a terminal application program used to realize functions other than voice assistant, and includes an input voice receiving unit and a function realization unit, wherein: input voice The receiving unit is used to receive the user's input voice from the voice assistant; the function realization unit is used to recognize the user's input voice, and realize the function that the user wants to use according to the recognition result.

Optionally, the input voice receiving unit is specifically configured to: receive the input voice from the user of the voice assistant, and the recognition result of the input voice by the voice assistant; the function realization unit is specifically configured to: recognize the user’s input voice , realize the function that the user wants to use according to the recognition result of oneself and the recognition result from the voice assistant.

In an example, the device further includes: a mapping relationship submitting unit, configured to submit the mapping relationship between the application program and the function to be used to the voice assistant according to the user's instruction.

In the above example, the mapping relationship between the application program and the functions to be used includes: the mapping relationship between the application program and function keywords.

The above is only a preferred embodiment of the application, and is not intended to limit the application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the application should be included in the application. within the scope of protection.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-permanent storage in computer readable media, in the form of random access memory (RAM) and/or nonvolatile memory such as read only memory (ROM) or flash RAM. Memory is an example of computer readable media.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, tape magnetic disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.

It should also be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes Other elements not expressly listed, or elements inherent in the process, method, commodity, or apparatus are also included. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Claims (22)

1. A function control method of voice, applied to the voice assistant of the terminal, characterized in that, comprising: According to the recognition result of the voice input by the user, an associated application program is determined; the associated application program is used to realize the function to be used by the user; The user's input voice is delivered to the associated application program for the associated application program to recognize the user's input voice, and implement the function according to the recognition result. 2. The method according to claim 1, wherein the terminal maintains a mapping relationship between functions to be used and application programs; The determining the associated application program according to the recognition result of the user's input voice includes: determining the function to be used by the user according to the recognition result of the user's input voice, and using the application program that has a mapping relationship with the function to be used by the user as the associated application program. 3. The method according to claim 2, wherein the mapping relationship between the function to be used and the application program includes: the mapping relationship between the function keyword and the application program; The determining the associated application program according to the recognition result of the user input voice includes: extracting the function keyword in the recognition result of the user input voice, and using the application program having a mapping relationship with the function keyword as the associated application program. 4. The method according to claim 2 or 3, wherein the mapping relationship between the function to be used and the application program includes: The mapping relationship between the functions to be used and the application program set by the user; and/or, When realizing the function to be used, the application program most frequently used by the user is the application program having a mapping relationship with the function to be used; and/or, Submitted by an application, the mapping relationship between the application and the function to be used. 5. The method according to claim 1, wherein the determining the associated application program according to the recognition result of the voice input by the user comprises: determining the function to be used by the user according to the recognition result of the voice input by the user, and On the terminal, the names of several application programs that can realize the described functions and support voice input are displayed to the user for selection, and the application program selected by the user is used as an associated application program. 6. The method according to claim 1, wherein said determining the associated application program according to the recognition result of the user input voice comprises: extracting the name of the application program in the recognition result of the user input voice, and converting the input voice The application specified in as the associated application. 7. The method according to claim 1, wherein the transmitting the user's input voice to the associated application program comprises: transmitting the recognition result and the user's input voice to the associated application program, The associated application program is used to recognize the user's input voice, and the function is implemented according to the recognition result of the associated application program and the recognition result of the voice assistant. 8. A function control method of voice, applied to a terminal application program for realizing other functions except voice assistant, characterized in that, comprising: receive voice input from the user of the voice assistant; Recognize the user's input voice, and realize the function that the user wants to use according to the recognition result. 9. The method according to claim 8, wherein the receiving the input voice from the user of the voice assistant comprises: receiving the input voice from the user of the voice assistant, and the recognition result of the input voice by the voice assistant ; The recognition of the user's input voice and the realization of the user's desired function according to the recognition result include: recognizing the user's input voice and realizing the user's desired function according to the own recognition result and the recognition result from the voice assistant. 10. The method according to claim 8, further comprising: submitting the mapping relationship between the application program and the function to be used to the voice assistant according to the user's instruction. 11. The method according to claim 10, wherein the mapping relationship between the application program and the functions to be used comprises: the mapping relationship between the application program and function keywords. 12. A voice function control device, applied to a terminal voice assistant, characterized in that it comprises: The associated application program unit is used to determine the associated application program according to the recognition result of the voice input by the user; the associated application program is used to realize the function to be used by the user; The input voice transmission unit is used to transmit the user's input voice to the associated application program, so that the associated application program can recognize the user's input voice, and implement the function according to the recognition result. 13. The device according to claim 12, wherein the terminal maintains a mapping relationship between functions to be used and applications; The associated application program unit is specifically configured to: determine the function to be used by the user according to the recognition result of the user's input voice, and use the application program that has a mapping relationship with the function to be used by the user as the associated application program. 14. The device according to claim 13, wherein the mapping relationship between the function to be used and the application program includes: the mapping relationship between the function keyword and the application program; The associated application program unit is specifically configured to: extract a functional keyword in a recognition result of the user input voice, and use an application program having a mapping relationship with the functional keyword as an associated application program. 15. The device according to claim 13 or 14, wherein the mapping relationship between the function to be used and the application program includes: The mapping relationship between the functions to be used and the application program set by the user; and/or, When realizing the function to be used, the application program most frequently used by the user is the application program having a mapping relationship with the function to be used; and/or, Submitted by an application, the mapping relationship between the application and the function to be used. 16. The device according to claim 12, wherein the associated application program unit is specifically configured to: determine the function to be used by the user according to the recognition result of the voice input by the user, and implement the functions and support voice input, the names of several application programs are displayed to the user for selection, and the application program selected by the user is used as the associated application program. 17. The device according to claim 12, wherein the associated application program unit is specifically configured to: extract the application program name in the recognition result of the voice input by the user, and use the application program specified in the input voice as the associated application program program. 18. The device according to claim 12, wherein the input voice transmission unit is specifically configured to: transmit the recognition result and the user's input voice to the associated application program for the associated application program to The user's input voice is recognized, and the function is realized according to the recognition result of the associated application program and the recognition result of the voice assistant. 19. A function control device for voice, which is applied to a terminal application program for realizing functions other than voice assistant, characterized in that it comprises: Input voice receiving unit, is used for receiving the input voice from the user of voice assistant; The function realization unit is used to recognize the input voice of the user, and realize the function to be used by the user according to the recognition result. 20. The device according to claim 19, wherein the input voice receiving unit is specifically configured to: receive an input voice from a user of the voice assistant, and a recognition result of the input voice by the voice assistant; The function realization unit is specifically configured to: recognize the user's input voice, and realize the function that the user wants to use according to its own recognition result and the recognition result from the voice assistant. 21. The device according to claim 19, further comprising: a mapping relationship submitting unit, configured to submit the mapping relationship between the application program and the function to be used to the voice assistant according to the user's instruction. 22. The device according to claim 21, wherein the mapping relationship between the application program and the function to be used comprises: a mapping relationship between the application program and function keywords.