CN117995191A - Voice instruction recommendation method, system and computer readable medium - Google Patents

Abstract

The invention provides a voice instruction recommending method, a voice instruction recommending system and a computer readable medium. The voice instruction recommendation method is suitable for a vehicle cabin and comprises the following steps: acquiring a wake-up instruction of a user; recommending at least one second voice instruction to the user based on the first voice instruction when the user sends the first voice instruction and the first voice instruction meets a first condition; acquiring current environment information and searching in a voice command library, and recommending at least one third voice command to a user when a callable voice command is searched based on the current environment information; acquiring user personalized information and searching in a voice command library, and recommending at least one fourth voice command to a user based on the user personalized information when a callable voice command is searched based on the user personalized information; the first condition is a multi-round dialogue condition, and the user personalized information is learned in advance based on the use habit of the user in the interaction of the vehicle and the machine.

Description

Voice instruction recommendation method, system and computer readable medium

Technical Field

The present invention relates generally to the field of vehicles, and more particularly, to a voice instruction recommendation method, system, and computer readable medium.

Background

With the development of the current vehicle-mounted system in an intelligent way, a user can perform man-machine interaction through voice, so that various devices and applications in the vehicle can be controlled, such as vehicle hardware, navigation, music, video and the like. Although the scope of speech control has now increased considerably and the scope of speech instruction support has increased considerably, it is not known to the user what the added instructions are nor how to speak them, nor is the added bulky instructions completely remembered. Therefore, although the voice command support range is richer for the user, the help and the improvement of the interaction convenience caused by the richer voice command are not experienced. Therefore, an innovative voice instruction recommending method is needed to solve the memory and use difficulties brought by a huge and continuously abundant voice instruction library to users, and guide the users to naturally, easily and efficiently use newly added voice instructions, so that the voice use efficiency of the users is improved, and the interactive convenience is brought.

Disclosure of Invention

The invention aims to provide a more intelligent and diversified voice instruction recommending method, a system and a computer readable medium.

In order to solve the technical problems, the invention provides a voice instruction recommending method which is applicable to a vehicle cabin and comprises the following steps: acquiring a wake-up instruction of a user; recommending at least one second voice instruction to the user based on the first voice instruction when the user sends the first voice instruction and the first voice instruction meets a first condition; acquiring current environment information and searching in a voice command library, and recommending at least one third voice command to a user when a callable voice command is searched based on the current environment information; acquiring user personalized information and searching in a voice command library, and recommending at least one fourth voice command to a user based on the user personalized information when a callable voice command is searched based on the user personalized information; the first condition is a multi-round dialogue condition, and the user personalized information is learned in advance based on the use habit of the user in the interaction of the vehicle and the machine.

In one embodiment of the present invention, recommending at least one second voice command to the user based on the first voice command comprises: converting the first voice instruction into text; constructing a word embedding model, and inputting a text into the word embedding model for processing to obtain an output vector; training a recommendation model, and inputting an output vector into the recommendation model to obtain a recommendation result; and searching in the voice command library according to the recommendation result, and recommending at least one second voice command to the user when the callable voice command is searched.

In an embodiment of the present invention, the voice command recommendation method further includes: when the user does not send out the second voice command within the first time threshold after receiving the second voice command, searching in a voice command library according to the recommendation result, and recommending at least one updated voice command to the user; wherein the first time threshold T satisfies: t is more than or equal to 5s and less than or equal to 10s; the updated voice command is different from the second voice command.

In an embodiment of the present invention, the voice command recommendation method further includes: and training the recommendation model according to the fifth voice command when the user sends the fifth voice command within the first time threshold after receiving the second voice command.

In one embodiment of the present invention, the current context information includes: driving scene information comprising time information, weather information and cabin hardware which can interact in a vehicle cabin; vehicle-mounted application information including interactive multimedia software displayed on at least one display device within a vehicle cabin; and multimedia information including interactive system settings modules displayed on at least one display device within the vehicle cabin.

In one embodiment of the invention, cabin hardware includes windows, seats, rearview mirrors, air conditioning and lighting systems.

In one embodiment of the present invention, recommending at least one third voice instruction to the user comprises: acquiring time information, wherein the third voice instruction is suitable for calling the lighting system according to the time information; and acquiring weather information, wherein the third voice instruction is suitable for calling the air conditioner according to the weather information.

In one embodiment of the present invention, recommending at least one third voice instruction to the user comprises: and acquiring vehicle-mounted application information, wherein the third voice instruction is suitable for adjusting the volume, brightness, playing speed and display definition of the multimedia software according to the vehicle-mounted application information.

In one embodiment of the present invention, recommending at least one third voice instruction to the user comprises: the multimedia information is acquired, and the third voice instruction is suitable for carrying out custom modification on the system setting module according to the multimedia information.

The invention also provides a voice instruction recommending system, which comprises: a memory for storing instructions executable by the processor; and a processor for executing instructions to implement the method of any of the previous embodiments.

The invention also provides a computer readable medium storing computer program code which, when executed by a processor, implements the method of any of the previous embodiments.

Compared with the prior art, the invention has the following advantages: the method can accurately analyze the interaction history, the current context and the behavior mode of the user under the situation of multiple rounds of conversations, understand the intention and the requirement of the user, and provide the optimal instruction recommendation related to the context based on the intention and the requirement; the recommendation based on the current environment information can identify the current specific requirements and recommend the voice instructions related to the current specific requirements according to the application programs and functions commonly used by the user and according to the scene and environment where the user is located, so that the user can quickly acquire the instructions required by the user under the specific scene, and the efficiency of voice interaction is improved; recommendation based on personalized information can realize personalized instruction recommendation by analyzing preference and behavior patterns of users, and personalized requirements of the users are met.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the accompanying drawings:

FIG. 1 is a flowchart of a voice command recommendation method according to an embodiment of the invention.

FIG. 2 is a flow chart of recommending at least one second voice command according to an embodiment of the invention.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is apparent to those of ordinary skill in the art that the present application may be applied to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

The relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present application unless it is specifically stated otherwise. Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description. Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but should be considered part of the specification where appropriate. In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

In the description of the present application, it should be understood that the azimuth or positional relationships indicated by the azimuth terms such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal", and "top, bottom", etc., are generally based on the azimuth or positional relationships shown in the drawings, merely to facilitate description of the present application and simplify the description, and these azimuth terms do not indicate and imply that the apparatus or elements referred to must have a specific azimuth or be constructed and operated in a specific azimuth, and thus should not be construed as limiting the scope of protection of the present application; the orientation word "inner and outer" refers to inner and outer relative to the contour of the respective component itself.

Spatially relative terms, such as "above … …," "above … …," "upper surface on … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial location relative to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "above" or "over" other devices or structures would then be oriented "below" or "beneath" the other devices or structures. Thus, the exemplary term "above … …" may include both orientations "above … …" and "below … …". The device may also be positioned in other different ways (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.

In addition, the terms "first", "second", etc. are used to define the components, and are only for convenience of distinguishing the corresponding components, and the terms have no special meaning unless otherwise stated, and therefore should not be construed as limiting the scope of the present application. Furthermore, although terms used in the present application are selected from publicly known and commonly used terms, some terms mentioned in the present specification may be selected by the applicant at his or her discretion, the detailed meanings of which are described in relevant parts of the description herein. Furthermore, it is required that the present application is understood, not simply by the actual terms used but by the meaning of each term lying within.

A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously. At the same time, other operations are added to or removed from these processes.

FIG. 1 is a flowchart of a voice command recommendation method according to an embodiment of the invention. Referring to fig. 1, the present invention provides a voice command recommendation method 10, which is applicable to a vehicle cabin, and includes the following steps:

S11: and obtaining a wake-up instruction of the user.

S12: when the user sends out the first voice command and the first voice command meets the first condition, at least one second voice command is recommended to the user based on the first voice command.

S13: the current environment information is obtained and retrieved in a voice command library, and when a callable voice command is retrieved based on the current environment information, at least one third voice command is recommended to the user.

S14: and acquiring the user personalized information and searching in the voice command library, and recommending at least one fourth voice command to the user based on the user personalized information when the callable voice command is searched based on the user personalized information.

Specifically, the wake-up instruction in step S11 may be a voice instruction, for example, the user may turn on the voice instruction by speaking a wake-up word, and in other embodiments, the user may also turn on the voice instruction by interacting with a button or directly with a switch on the touch screen, which is not limited herein. After receiving the wake-up instruction, a voice instruction function in the vehicle cabin is started, and the method proceeds to step S12, and whether the user sends out a first voice instruction is judged, and when the user sends out the first voice instruction and the first voice instruction meets a first condition, at least one second voice instruction is recommended to the user based on the first voice instruction.

Specifically, the first condition is a multi-turn dialogue condition, and the step can be understood as voice instruction recommendation according to the context: if the first voice command meets the multi-round dialogue condition and the recommended result content exists in the voice command library, recommending the second voice command to the user. In this embodiment, the recommendation process may be presented through a UI. For example, the user says what is the weather today in Shanghai, at this time, the intention and the requirement of the user are understood according to the context recommendation, and the user is shown to the user through the display screen in the cabin if it is judged that the user possibly needs to know the weather in the recent Shanghai at the same time: you can try to say "skyhook".

FIG. 2 is a flow chart of recommending at least one second voice command according to an embodiment of the invention. Referring to fig. 1-2 in combination, in a preferred embodiment of the present invention, the method of recommending at least one second voice command to the user based on the first voice command in step S12 specifically includes the following steps:

S15: the first voice instruction is converted into text.

S16: and constructing a word embedding model, and inputting the text into the word embedding model for processing to obtain an output vector.

S17: training a recommendation model, and inputting the output vector into the recommendation model to obtain a recommendation result.

S18: and searching in the voice instruction library according to the recommendation result, and recommending at least one voice instruction to the user when the callable voice instruction is searched.

S19: and judging whether the user sends out the second voice command within the first time threshold after receiving the second voice command, and if not, executing the step S20.

S20: and searching in the voice command library according to the recommendation result, and recommending at least one updated voice command to the user.

S21: and judging whether the user sends out a fifth voice command within a first time threshold after receiving the second voice command, if so, executing the step S22.

S22: training a recommendation model according to the fifth voice instruction.

The specific implementation core of the step S12 is to accurately understand the intention and the requirement of the user through a deep learning algorithm and an NLP natural language processing technology, and provide voice instruction recommendation and guidance related to the context for the user, which specifically comprises the following steps:

(1) Data collection and pretreatment: it is first necessary to collect relevant data including user history, such as search history, browsing records, playing records, etc. of the user. The data is suitably pre-processed, such as data cleansing, deduplication, format conversion, etc., while the first voice instruction is converted to text for subsequent model training and recommendation.

(2) Constructing a word embedding model: using a context-aware word embedding model, such as Bi-LSTM or transfomer, etc., to convert text data into a continuous vector representation, resulting in an output vector, a technical implementation of this step includes: inputting the preprocessed text data into the word embedding model through data input; learning a semantic representation of text data using a word embedding model, mapping words or phrases into a continuous vector space; and capturing semantic relationships between words and contextual information in a word embedding model using the contextual information to facilitate a better understanding of the user's history and preferences.

(3) Training a recommendation model: using the vectors generated by the user history and word embedding models (i.e., output vectors) as inputs, a recommendation model is trained, which may use deep learning techniques such as CNN or RNN, etc. The technical implementation of this step generally comprises: inputting vectors generated by the user history record and the word embedding model into a recommendation model; training a recommendation model by using a proper loss function and an optimizer so that the recommendation model can learn the interest preference and the behavior mode of the user; according to the current behavior and the history of the user, personalized recommendation results are generated by using a recommendation model, and the recommendation results can be optimized according to different business requirements, such as adding a current event hot spot and the like, so that the recommendation accuracy is improved.

In order to increase the diversity of the recommendation, there may be a plurality of second voice instructions recommended to the user in step S18, which may be on the display screen at the same time, giving the user a richer choice. However, it will be understood that the confidence level of the initial recommendation result may be poor, and in this case, the plurality of second voice commands may not meet the user' S requirement, that is, in step S19, the user may not issue the second voice command within the first time threshold, and at this time, the priority of the second voice command just recommended in the decision logic may be reduced again, and searching in the voice command library may be performed again, so as to recommend at least one updated voice command different from the second voice command to the user. In this embodiment, the first time threshold T satisfies: t is more than or equal to 5s and less than or equal to 10s.

Further, the user may not only send out the second voice command but also send out a fifth voice command different from the second voice command within the first time threshold, and at this time, training the recommendation model according to the fifth voice command, optimizing the model, and improving the semantic representation capability and recommendation performance of the model so as to adapt to the change of the interests and behaviors of the user.

Unlike step S12, steps S13 and S14 may make a voice instruction recommendation without receiving a user voice instruction, that is, as long as the user issues a wake-up instruction, the system will make a relevant recommendation if the conditions of steps S13 and S14 are satisfied even if the first voice instruction is not given. It should be noted, however, that this is not equivalent to steps S13 and S14 being performed only if the first voice command is not received.

In one embodiment of the present invention, the current context information includes: the driving scene information, the vehicle-mounted application information and the multimedia information correspond to the scene recommendation, the application recommendation and the page recommendation respectively, and the three situations are described in detail below.

In particular, the driving scene information in the case of scene recommendation includes time information, weather information, and cabin hardware that can interact in the cabin of the vehicle, and in an embodiment of the present application, the cabin hardware includes windows, seats, rearview mirrors, air conditioning, and lighting systems. The system judges whether a situation that scene recommendation can be carried out exists in a period of time after a user wakes up the voice command function, and if the situation is met and the recommended result content exists in the voice command library, a recommendation command is generated and displayed. For example: the user has already started the air conditioner, and the system judges that the air conditioner has been started, then the instruction of "opening the air conditioner" is not required to be recommended again, other related instructions are recommended at the moment, and the display is performed: you can try to say "air conditioner temperature up", "air conditioner wind speed down", etc. In other embodiments, recommending at least one third voice command to the user further comprises obtaining time information, the third voice command being adapted to invoke the lighting system, etc., based on the time information, the application is not limited in this regard.

In the case of application recommendation, the in-vehicle application information includes interactive multimedia software, such as a video player, a music player, etc., displayed on at least one display device within the vehicle cabin. For example: the system detects that a user frequently opens a video player to watch a television in a certain time period, and when the video player is in a callable state, the system displays: you can try to say "open video player", if the system judges that the video player is already playing video, then recommend the relevant instruction of operation, facilitate user's operation, demonstrate: you can try to say "1.5 times speed play", "sharpness up", "pause play", "i want to see the next set", etc. In an embodiment of the present application, recommending at least one third voice command to the user further includes adjusting the volume, brightness, playing speed and display definition of the multimedia software according to the vehicle-mounted application information, which is not particularly limited herein.

In the case of page recommendations, the multimedia information includes interactive system settings modules displayed on at least one display device within the vehicle cabin. For example: the system detects that a user sets a page in voice, and a user-defined wake-up word modification button is arranged on the page, and then a voice instruction for modifying the user-defined wake-up word is recommended and displayed according to a page recommendation flow: you can try to say "give you a name of white". In one embodiment of the present application, recommending at least one third voice instruction to the user comprises: the method for obtaining the multimedia information includes the steps that the third voice instruction is suitable for carrying out custom modification on the system setting module according to the multimedia information, and is not limited to the setting of wake-up words, and the application is not limited in particular.

Step S14 may be understood as personalized recommendation, wherein the user personalized information is learned in advance based on the usage habit of the user in the interaction of the vehicle and the machine. For example: the system detects that the user frequently listens to the song of a singer, then a new song is sent to the singer or the cold song of the singer is never heard by the user, and then a corresponding song instruction is recommended.

It should be noted that, in the foregoing, five recommendation strategies are mentioned in total, including context recommendation, scene recommendation, application recommendation, page recommendation, and personalized recommendation, and these five recommendation modes may be performed together. However, in some cases, such as where the voice instruction recommendation method 10 is implemented by computer program code, the steps may be prioritized, where the priority is to be recommended in the flow order.

Still further, in a preferred embodiment of the present invention, the voice command recommending method 10 further includes stopping the continued recommendation of a certain command recorded in the voice command library when it has been recommended a certain number of times or used a certain number of times by the user.

The invention also provides a voice instruction recommending system, which comprises: a memory for storing instructions executable by the processor; and a processor for executing instructions to implement the method of any of the previous embodiments.

Some aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. The processor may be one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital signal processing devices (DAPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or a combination thereof. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media. For example, computer-readable media can include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, magnetic strips … …), optical disks (e.g., compact disk CD, digital versatile disk DVD … …), smart cards, and flash memory devices (e.g., card, stick, key drive … …).

The invention also provides a computer readable medium storing computer program code which, when executed by a processor, implements the method of any of the previous embodiments.

The computer readable medium may comprise a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer readable medium can be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer readable medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signals, or the like, or a combination of any of the foregoing.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements and adaptations of the application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within the present disclosure, and therefore, such modifications, improvements, and adaptations are intended to be within the spirit and scope of the exemplary embodiments of the present disclosure.

Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.

Similarly, it should be noted that in order to simplify the description of the present disclosure and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure does not imply that the subject application requires more features than are set forth in the claims. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations in some embodiments for use in determining the breadth of the range, in particular embodiments, the numerical values set forth herein are as precisely as possible.

While the application has been described with reference to the specific embodiments presently, it will be appreciated by those skilled in the art that the foregoing embodiments are merely illustrative of the application, and various equivalent changes and substitutions may be made without departing from the spirit of the application, and therefore, all changes and modifications to the embodiments are intended to be within the scope of the appended claims.

Claims (11)

1. The voice instruction recommending method is suitable for a vehicle cabin and is characterized by comprising the following steps of:

Acquiring a wake-up instruction of a user;

Recommending at least one second voice instruction to a user based on a first voice instruction when the user sends the first voice instruction and the first voice instruction meets a first condition;

Acquiring current environment information and searching in a voice command library, and recommending at least one third voice command to the user when a callable voice command is searched based on the current environment information;

Acquiring user personalized information and searching in the voice command library, and recommending at least one fourth voice command to the user based on the user personalized information when a callable voice command is searched based on the user personalized information; wherein,

The first condition is a multi-round dialogue condition, and the user personalized information is learned in advance based on the use habit of the user in the interaction of the vehicle and the machine.

2. The voice command recommending method of claim 1, wherein recommending at least one second voice command to the user based on the first voice command comprises:

Converting the first voice instruction into text;

Constructing a word embedding model, and inputting the text into the word embedding model for processing to obtain an output vector;

Training a recommendation model, and inputting the output vector into the recommendation model to obtain a recommendation result; and

And searching in the voice instruction library according to the recommendation result, and recommending at least one second voice instruction to the user when the callable voice instruction is searched.

3. The voice command recommending method of claim 2, further comprising:

When the user does not send out the second voice command within a first time threshold after receiving the second voice command, searching in the voice command library according to the recommendation result, and recommending at least one updated voice command to the user; wherein,

The first time threshold T satisfies: t is more than or equal to 5s and less than or equal to 10s;

the update voice command is different from the second voice command.

4. The voice command recommending method of claim 3, further comprising: and training the recommendation model according to a fifth voice command when the user sends the fifth voice command within a first time threshold after receiving the second voice command.

5. The voice command recommending method of claim 1, wherein the current environmental information comprises:

driving scene information comprising time information, weather information and cabin hardware which can interact in the vehicle cabin;

vehicle-mounted application information comprising interactive multimedia software displayed on at least one display device in the vehicle cabin; and

Multimedia information comprising an interactive system settings module displayed on at least one display device within the vehicle cabin.

6. The voice command recommendation method of claim 5, wherein the cabin hardware comprises windows, seats, rearview mirrors, air conditioning and lighting systems.

7. The voice command recommending method of claim 6, wherein recommending at least one third voice command to the user comprises:

acquiring the time information, wherein the third voice instruction is suitable for calling the lighting system according to the time information;

and acquiring the weather information, wherein the third voice instruction is suitable for calling the air conditioner according to the weather information.

8. The voice command recommending method of claim 5, wherein recommending at least one third voice command to the user comprises: and acquiring the vehicle-mounted application information, wherein the third voice instruction is suitable for adjusting the volume, brightness, playing speed and display definition of the multimedia software according to the vehicle-mounted application information.

9. The voice command recommending method of claim 5, wherein recommending at least one third voice command to the user comprises: and acquiring the multimedia information, wherein the third voice instruction is suitable for carrying out custom modification on the system setting module according to the multimedia information.

10. A voice command recommendation system, comprising:

a memory for storing instructions executable by the processor; and

A processor for executing the instructions to implement the method of any one of claims 1-9.

11. A computer readable medium storing computer program code, which when executed by a processor implements the method of any one of claims 1-9.