Intelligent prompt word generation method and device for vehicle-mounted voice assistant

Abstract

The invention discloses an intelligent prompt generation method and device for a vehicle-mounted voice assistant. The method comprises the steps of judging whether an intelligent prompt needs to be output or not according to an intelligent prompt opportunity judgment strategy; when it is determined that the intelligent prompt words need to be output, the corresponding intelligent prompt words are output according to the user attributes and the scene attributes. In the voice interaction process, whether intelligent prompt words are output or not is determined according to an opportunity judgment strategy; when the intelligent prompt words need to be output, the corresponding prompt words are judged and output in combination with the user attributes and the scene attributes; therefore, the situation that the prompt words are too many in an existing method is greatly reduced, and meanwhile, the content of the intelligent prompt words is intelligently adjusted according to the actual requirements of the user, so that the intelligent prompt words are more convenient, more accurate and smoother during voice interaction.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a method and device for generating intelligent prompts for a vehicle-mounted voice assistant. Background Art

[0002] The in-car voice assistant is an intelligent assistance system that can provide voice interaction services in the car. It can understand the driver's instructions or questions through voice recognition technology and make corresponding answers or operations. For example, while driving, the voice assistant can be used for navigation, playing music, sending text messages, answering calls, etc., to help the driver drive more conveniently and safely. At the same time, the in-car voice assistant can also provide real-time driving advice and safety tips based on the driver's driving habits and road conditions, improving driving safety and comfort.

[0003] With the rapid development of intelligent voice, car owners pay more and more attention to the intelligent and personalized experience of in-car scenes. In order to make the conversation between users and in-car voice assistants smoother, intelligent prompts are added. When users wake up or fail to wake up the voice assistant, intelligent prompts are provided to users through screen display or voice prompts.

[0004] However, the current intelligent prompts for voice interaction randomly display voice command prompts based on the vertical category of voice interaction, without considering the timing and frequency of the prompts according to user needs. After the voice assistant is awakened, no matter what command the user says, the intelligent prompt will appear. The high frequency will cause unnecessary information burden to the user. At the same time, the user's attributes are not considered, and different intelligent prompts are not pushed to users based on different attributes. After voice awakening, it is pushed randomly, and different intelligent prompts cannot be matched according to the user's scenario.

[0005] Based on this, a new solution is needed. Summary of the invention

[0006] The main purpose of the present invention is to provide a method and device for generating intelligent prompts for a vehicle-mounted voice assistant, so as to make the intelligent prompts more accurate, personalized and intelligent.

[0007] To achieve the above object, the present invention provides a method for generating intelligent prompts for a vehicle-mounted voice assistant, comprising the following steps:

[0008] Determine whether to output the smart prompt according to the smart prompt timing judgment strategy; and

[0009] When it is determined that an intelligent prompt needs to be output, a corresponding intelligent prompt is output according to user attributes and scene attributes.

[0010] In the method for generating intelligent prompts for an in-vehicle voice assistant provided by the present invention, in the step of determining whether it is necessary to output an intelligent prompt according to the intelligent prompt timing determination strategy, if one or more of the following situations occur during the voice dialogue between the user and the in-vehicle voice assistant, it is determined that it is necessary to output an intelligent prompt:

[0011] During the detection of the current voice dialogue, it is detected that there is a rejection or the semantics is empty;

[0012] No user speech is detected within a first preset time after the in-vehicle voice assistant is awakened;

[0013] During the voice conversation, no new command input is detected within a second preset time after the previous command is executed;

[0014] It is detected that the user's command is a half-cut command;

[0015] Detects when the user opens a new app or switches apps.

[0016] In the intelligent prompt generation method for the in-vehicle voice assistant provided by the present invention, when it is determined that the intelligent prompt needs to be output, the step of outputting the corresponding intelligent prompt according to the user attributes and the scene attributes includes:

[0017] Select the corresponding voice vertical category based on the user's scenario and the system's preset priority;

[0018] Based on the number of times the user uses the voice assistant, determine whether the user is a novice user or an experienced user. If the user is a novice user, select the corresponding smart prompt output in the novice user instruction set according to the selected voice vertical category. If the user is an experienced user, select the corresponding smart prompt output in the experienced user instruction set according to the selected voice vertical category.

[0019] In the intelligent prompt generation method for the in-vehicle voice assistant provided by the present invention, the step of selecting the corresponding voice vertical category according to the user's scenario and the priority preset by the system includes:

[0020] Determine whether there is a scene that needs to be displayed first. If there is a scene that needs to be displayed first, select the corresponding voice vertical category according to the scene that needs to be displayed first.

[0021] When there is no scene that needs to be displayed first, determine whether the current scene is in navigation or music playing. If the scene is in navigation or music playing, select the navigation vertical category or the music vertical category;

[0022] When not in navigation or music playing, determine whether there is a pop-up window of the voice assistant. If there is a pop-up window of the voice assistant, select the corresponding voice vertical category according to the pop-up window of the voice assistant. If there is no pop-up window of the voice assistant, select the corresponding voice vertical category according to the foreground application.

[0023] In addition, to achieve the above-mentioned purpose, the present invention also provides an intelligent prompt generation device for a vehicle-mounted voice assistant, comprising:

[0024] A judgment module, used to judge whether it is necessary to output the intelligent prompt according to the intelligent prompt timing judgment strategy; and

[0025] The output module is used to output the corresponding intelligent prompt according to the user attributes and the scene attributes when it is determined that the intelligent prompt needs to be output.

[0026] In the intelligent prompt generating device for the in-vehicle voice assistant provided by the present invention, the judging module judges that the intelligent prompt needs to be output if one or more of the following situations occur during the voice dialogue between the user and the in-vehicle voice assistant:

[0027] During the detection of the current voice dialogue, it is detected that there is a rejection or the semantics is empty;

[0028] No user speech is detected within a first preset time after the in-vehicle voice assistant is awakened;

[0029] During the voice conversation, no new command input is detected within a second preset time after the previous command is executed;

[0030] It is detected that the user's command is a half-cut command;

[0031] Detects when the user opens a new app or switches apps.

[0032] In the intelligent prompt generating device for the vehicle-mounted voice assistant provided by the present invention, the output module includes:

[0033] A selection unit, used to select a corresponding voice vertical category according to the user's scenario and the system preset priority;

[0034] The output unit is used to determine whether the user is a novice user or an experienced user based on the number of times the user uses the voice assistant. When the user is a novice user, the corresponding intelligent prompt output is selected in the novice user instruction set according to the selected voice vertical category; when the user is an experienced user, the corresponding intelligent prompt output is selected in the experienced user instruction set according to the selected voice vertical category.

[0035] In the intelligent prompt generating device for the vehicle-mounted voice assistant provided by the present invention, the selection unit is used for:

[0036] Determine whether there is a scene that needs to be displayed first. If there is a scene that needs to be displayed first, select the corresponding voice vertical category according to the scene that needs to be displayed first.

[0037] When there is no scene that needs to be displayed first, determine whether the current scene is in navigation or music playing. If the scene is in navigation or music playing, select the navigation vertical category or the music vertical category;

[0038] When not in navigation or music playing, determine whether there is a pop-up window of the voice assistant. If there is a pop-up window of the voice assistant, select the corresponding voice vertical category according to the pop-up window of the voice assistant. If there is no pop-up window of the voice assistant, select the corresponding voice vertical category according to the foreground application.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also provides an intelligent prompt generation device for a vehicle-mounted voice assistant, comprising:

[0040] Memory for storing computer programs;

[0041] A processor is used to implement the steps of the method for generating intelligent prompts for an in-vehicle voice assistant as described above when executing the computer program.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method for generating intelligent prompts for an in-vehicle voice assistant as described above.

[0043] In the present invention, during the voice interaction process, whether to output the intelligent prompt is determined based on the timing judgment strategy; when the intelligent prompt needs to be output, the corresponding prompt is determined based on the user attributes and the scene attributes; thereby, the situation in which there are too many prompts in the existing method is greatly reduced, and at the same time, the content of the intelligent prompt is intelligently adjusted according to the actual needs of the user, making the intelligent prompt more convenient, more accurate, and more fluent during voice interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the provided drawings without creative work:

[0045] Figure 1 The figure is a flow chart of a method for generating intelligent prompts for an in-vehicle voice assistant provided in accordance with the first embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Typical embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0048] The general idea of ​​the present invention is: in view of the fact that the existing intelligent prompts do not consider the timing and frequency of occurrence according to user needs, nor do they consider the application scenarios and user attributes, a method and device for generating intelligent prompts for a vehicle-mounted voice assistant are provided. During the voice interaction process, a timing judgment strategy is used to determine whether to output the intelligent prompts; when it is necessary to output the intelligent prompts, the corresponding prompts are output in combination with user attributes and scenario attributes; thereby, the situation of too many prompts in the existing methods is greatly reduced, and at the same time, the content of the intelligent prompts is intelligently adjusted according to the actual needs of the user, so that the intelligent prompts are more convenient, more accurate, and more fluent during voice interaction.

[0049] In order to better understand the above-mentioned technical scheme, the above-mentioned technical scheme will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0050] Embodiment 1

[0051] Reference Figure 1 , Figure 1 The flowchart of an embodiment of a method for generating intelligent prompts for an in-vehicle voice assistant of the present invention is shown in FIG. In one embodiment, the method for generating intelligent prompts for an in-vehicle voice assistant includes:

[0052] Step S10, judging whether it is necessary to output the intelligent prompt according to the intelligent prompt timing judgment strategy.

[0053] Specifically, in one embodiment of the present invention, during the conversation between the user and the in-vehicle voice assistant, the timing of outputting the intelligent prompt is determined by the following aspects:

[0054] 1. Detect whether there is a rejection or empty semantics in the current voice conversation. Rejection refers to the situation where the voice assistant refuses to recognize. In the in-vehicle voice conversation strategy, some specific conversations will be blocked to maintain a good voice interaction experience; empty semantics means that a human voice is detected, but the returned semantic field is NULL. By pushing intelligent prompts when rejection or empty semantics is detected in the current voice conversation, a good voice interaction experience can be maintained;

[0055] 2. Detect whether the user does not speak or the human voice is not detected within a period of time after the in-vehicle voice assistant is awakened. For example, if no one is detected speaking within 2 seconds after the in-vehicle voice assistant is awakened, it means that the user may not know what to say at this time. By outputting smart prompts when the user is not detected speaking within the first preset time after the in-vehicle voice assistant is awakened, frequent push of smart prompts can be avoided, thereby improving the user experience;

[0056] 3. During the voice conversation between the user and the in-vehicle voice assistant, there is no new command input within a period of time after the last command is executed. For example, in the voice conversation, the user first says "turn on the music", and then no new command is detected within 3 seconds. This means that the user may not be familiar with the command. By outputting an intelligent prompt when no new command input is detected within the second preset time after the last command is executed, the prompt push timing can be made more accurate;

[0057] 4. Whether the terminal status has changed. When the user opens a new application (including manual clicks during a continuous conversation) or switches applications, the application here does not include the in-vehicle voice assistant. For example, during a voice conversation between a user and an in-vehicle voice assistant, the user manually clicks another application on the screen. By outputting an intelligent prompt when the terminal status changes, the prompt push can be smoother.

[0058] 5. When detecting whether the user's instruction is a half-instruction, a half-instruction set is preset in the system (for example, I want to listen, I want to watch). After the user triggers it, the cloud will return a field to tell the end side what vertical category the half-instruction belongs to, and give an intelligent prompt based on the vertical category and priority. By presetting the half-instruction set, users can have more choices, and through training, the prompt push can be made more accurate and personalized, thereby improving the user experience.

[0059] Therefore, in step S10, during the voice conversation between the user and the in-vehicle voice assistant, if one or more of the following situations occur, it is determined that the intelligent prompt needs to be output: rejection or empty semantics is detected during the detection of the current voice conversation; the user is not detected speaking within the first preset time after the in-vehicle voice assistant is awakened; during the voice conversation, no new command input is detected within the second preset time after the execution of the previous command; the user's command is detected to be a half-cut command; the user is detected to open a new application or switch applications. During the voice conversation, if any one or more of the above situations occur, the intelligent prompt is output; if any of the above situations do not occur, the intelligent prompt does not need to be displayed at this moment of the conversation, and the intelligent prompt is output until at least one of the above situations occurs in the next moment or the next conversation. In this way, frequent push of intelligent prompts can be avoided, the existing situation of too many intelligent prompts can be improved, and the timing of intelligent prompts can be more in line with user needs, improving the user experience.

[0060] Step S20: When it is determined that an intelligent prompt needs to be output, a corresponding intelligent prompt is output according to user attributes and scene attributes.

[0061] Specifically, in one embodiment of the present invention, after determining that the intelligent prompt needs to be output, it is also necessary to select the prompt to be output in combination with the priority of the scene in which the user is located and the user's own attributes. Among them, the priority of the scene in which the user is located refers to the system pre-setting some scene priorities according to the user's usage scenario, and different scene priorities correspond to different voice vertical categories; the user's own attributes refer to the frequency of the user's use of the in-vehicle voice assistant, and different user attributes correspond to different instruction sets. Therefore, step S20 includes:

[0062] Step S210: Select a corresponding voice vertical category according to the user's scenario and the system's preset priority;

[0063] Step S220: Determine whether the user is a novice user or an experienced user based on the number of times the user uses the voice assistant. If the user is a novice user, select the corresponding intelligent prompt output in the novice user instruction set according to the selected voice vertical category. If the user is an experienced user, select the corresponding intelligent prompt output in the experienced user instruction set according to the selected voice vertical category.

[0064] Furthermore, in one embodiment of the present invention, according to the user usage scenario, the system presets multiple scene priorities, including high, play, naving, normal, fg and floatwindow. Among them, high refers to the scene where some smart prompts need to be displayed first. For example, according to the system date, today is a holiday, so some smart prompts related to this holiday will be displayed first. However, if these prompts have been displayed many times on the same day, the priority of this scene that needs to be displayed first will be reduced to normal according to the number of displays; play refers to the playback, for music and radio stations are broadcasting; naving refers to navigation; floatwindow refers to the pop-up window of the voice assistant; fg refers to the application that is currently opened in the foreground; normal refers to all scenes except the above. When judging the scene, the system will determine whether the above situation exists in turn to select the corresponding voice vertical category. By setting the scene priority, it can ensure that the output voice vertical category is more accurate and efficient. Therefore, step S210 includes:

[0065] Step S2101, determine whether there is a scene that needs to be displayed first, if yes, proceed to step S2102, if not, proceed to step S2103;

[0066] Step S2102: Select the corresponding voice vertical category according to the scene that needs to be displayed first;

[0067] Step S2103, determining whether the current state is in navigation or music playing, if yes, proceeding to step S2104, if not, proceeding to step S2105;

[0068] Step S2104: Select a navigation vertical category or a music vertical category;

[0069] Step S2105: Determine whether there is a pop-up window of the voice assistant. If yes, proceed to step S2106; if no, proceed to step S2107;

[0070] Step S2106: Select the corresponding voice vertical category according to the pop-up window of the voice assistant;

[0071] Step S2107, determine whether there is an application in the current foreground, if yes, proceed to step S2108, if not, proceed to step S2109;

[0072] Step S2108: Select a corresponding voice vertical category according to the foreground application;

[0073] Step S2109: The system randomly selects a voice vertical category.

[0074] Further, in one embodiment of the present invention, it is determined whether the user is a novice user or an experienced user based on the number of times the user uses the in-vehicle voice assistant, wherein the user is converted into an experienced user after the number of times the user wakes up the voice assistant exceeds a certain number, such as 5,000 times. After the corresponding voice vertical category is determined according to the scenario, the novice user instruction set Newer is called for the novice user, and the experienced user instruction set Proficient is called for the experienced user. Among them, there are relatively few instructions in the novice user instruction set Newer, which only contains some high-frequency vertical categories, such as navigation, telephone, car control, music, etc., and each vertical category contains relatively few instructions, which are all elementary high-frequency instructions. Through the novice user instruction set Newer, the frequency of high-frequency instructions can be increased as much as possible, allowing users to quickly learn voice functions. The instructions in the experienced user instruction set Proficient cover all supported voice vertical categories, such as schedules, stocks, and vertical categories including third parties. The instructions included will be more complete, and the purpose is to allow users to gradually understand the deeper voice functions of the car machine and use the voice function more.

[0075] The following is a specific example to explain in detail the intelligent prompt generation process of the present invention. Assume that the system is currently on the Launcher page, music is playing, and the in-vehicle voice assistant is awakened at this time:

[0076] ① After the voice assistant is awakened, it determines whether a prompt needs to be pushed based on the prompt timing judgment strategy: for example, if the user does not speak within 2 seconds after awakening, it indicates that the user may not know what to say, so it is determined that an intelligent prompt needs to be pushed;

[0077] ② Determine the scene the user is currently in: For example, if the user is currently on the Launcher (application) page and music is playing, according to the rule, music playing belongs to the "play" scene > foreground application (Launcher), so you need to select the prompt in the "play" scene of the music vertical category;

[0078] ③ Determine whether the user is a novice user or an experienced user based on the number of wake-up times: For example, if the number of wake-up times is less than 5,000, then take the intelligent prompt from the novice user command set Newer; so we take the prompt in the "play" scene of the music vertical category from the novice user command set Newer, for example, the defined prompts are as follows:

[0079] "Pause playback & turn off music & I want to listen to Andy Lau's song & play a Jay Chou song & play Bluetooth music & broadcast USB music & play local music & open local music & previous song & next song & volume up & volume down";

[0080] 2 or 3 commands are randomly pushed from it, such as "pause play", "previous song" and "next song" and displayed on the car screen.

[0081] At this point, the first prompt judgment and output process is completed.

[0082] If the user says "pause playback" according to the smart prompt, the scene will change and it will be necessary to re-determine whether a smart prompt is needed and what the prompt should be.

[0083] Embodiment 2

[0084] The present invention also provides an intelligent prompt generation device for a vehicle-mounted voice assistant, comprising:

[0085] A judgment module, used to judge whether it is necessary to output the intelligent prompt according to the intelligent prompt timing judgment strategy; and

[0086] The output module is used to output the corresponding intelligent prompt according to the user attributes and the scene attributes when it is determined that the intelligent prompt needs to be output.

[0087] Specifically, in one embodiment of the present invention, the judgment module determines that an intelligent prompt needs to be output if one or more of the following situations occur during the voice conversation between the user and the in-vehicle voice assistant: rejection of recognition or empty semantics is detected during the current voice conversation; the user is not detected speaking within the first preset time after the in-vehicle voice assistant is awakened; during the voice conversation, no new command input is detected within the second preset time after the previous command is executed; the user's command is detected to be a half-cut command; the user is detected to open a new application or switch applications.

[0088] Specifically, in one embodiment of the present invention, the output module includes: a selection unit, used to select a corresponding voice vertical category according to the scenario in which the user is located and the priority preset by the system; an output unit, used to determine whether the user is a novice user or an experienced user according to the number of times the user uses the voice assistant, and when the user is a novice user, the corresponding intelligent prompt output is selected in the novice user instruction set according to the selected voice vertical category; when the user is an experienced user, the corresponding intelligent prompt output is selected in the experienced user instruction set according to the selected voice vertical category.

[0089] Further, in one embodiment of the present invention, the selection unit is used to: determine whether there is a scene that needs to be displayed first, and if there is a scene that needs to be displayed first, select a corresponding voice vertical category according to the scene that needs to be displayed first; when there is no scene that needs to be displayed first, determine whether it is currently in navigation or music playing, and if it is in navigation or music playing, select the navigation vertical category or the music vertical category; when it is not in navigation or music playing, determine whether there is a pop-up window of the voice assistant, and if there is a pop-up window of the voice assistant, select the corresponding voice vertical category according to the pop-up window of the voice assistant, and if there is no pop-up window of the voice assistant, select the corresponding voice vertical category according to the foreground application.

[0090] Those skilled in the art will appreciate that the above is an embodiment of an intelligent prompt generation device for a vehicle-mounted voice assistant provided in an embodiment of the present invention, and the system and device belong to the same inventive concept as the above-mentioned intelligent prompt generation method for a vehicle-mounted voice assistant. For details not fully described in the embodiment of the intelligent prompt generation device for a vehicle-mounted voice assistant, reference can be made to the embodiment of the above-mentioned intelligent prompt generation method for a vehicle-mounted voice assistant.

[0091] The embodiment of the present invention further provides an intelligent prompt generation device for a vehicle-mounted voice assistant, which may include:

[0092] Memory for storing computer programs;

[0093] The processor can implement the following steps when executing the computer program stored in the above memory:

[0094] According to the smart prompt timing judgment strategy, it is judged whether the smart prompt needs to be output; and when it is determined that the smart prompt needs to be output, the corresponding smart prompt is output according to the user attributes and the scene attributes.

[0095] The embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps can be implemented;

[0096] According to the smart prompt timing judgment strategy, it is judged whether the smart prompt needs to be output; and when it is determined that the smart prompt needs to be output, the corresponding smart prompt is output according to the user attributes and the scene attributes.

[0097] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM)> a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0098] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0099] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0100] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition they can be divided into multiple submodules or subunits or subassemblies. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification and all processes or units of any method or device disclosed in this manner can be combined in any combination. Unless otherwise clearly stated, each feature disclosed in this specification can be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0101] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, any one of the claimed embodiments may be used in any combination.

[0102] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0103] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware including a number of different elements and by means of a suitably programmed computer. Several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A method for generating intelligent prompts for a vehicle-mounted voice assistant, characterized in that: The following steps are involved: According to the smart prompt timing judgment strategy, determine whether it is necessary to output the smart prompt; as well as When it is determined that an intelligent prompt needs to be output, a corresponding intelligent prompt is output according to user attributes and scene attributes.

2. The method for generating intelligent prompts for a vehicle-mounted voice assistant according to claim 1, characterized in that: In the step of determining whether to output the intelligent prompt according to the intelligent prompt timing determination strategy, if one or more of the following situations occur during the voice dialogue between the user and the in-vehicle voice assistant, it is determined that the intelligent prompt needs to be output: During the detection of the current voice dialogue, it is detected that there is a rejection or the semantics is empty; No user speech is detected within a first preset time after the in-vehicle voice assistant is awakened; During the voice conversation, no new command input is detected within a second preset time after the previous command is executed; It is detected that the user's command is a half-cut command; Detects when the user opens a new app or switches apps.

3. The method for generating intelligent prompts for a vehicle-mounted voice assistant according to claim 2, characterized in that: When it is determined that an intelligent prompt needs to be output, the step of outputting a corresponding intelligent prompt according to user attributes and scene attributes includes: Select the corresponding voice vertical category based on the user's scenario and the system's preset priority; Based on the number of times the user uses the voice assistant, determine whether the user is a novice user or an experienced user. If the user is a novice user, select the corresponding smart prompt output in the novice user instruction set according to the selected voice vertical category. If the user is an experienced user, select the corresponding smart prompt output in the experienced user instruction set according to the selected voice vertical category.

4. The method for generating intelligent prompts for a vehicle-mounted voice assistant according to claim 3, characterized in that: According to the user's scenario and the system's preset priority, the steps for selecting the corresponding voice vertical category include: Determine whether there is a scene that needs to be displayed first. If there is a scene that needs to be displayed first, select the corresponding voice vertical category according to the scene that needs to be displayed first. When there is no scene that needs to be displayed first, determine whether the current scene is in navigation or music playing. If the scene is in navigation or music playing, select the navigation vertical category or the music vertical category; When not in navigation or music playing, determine whether there is a pop-up window of the voice assistant. If there is a pop-up window of the voice assistant, select the corresponding voice vertical category according to the pop-up window of the voice assistant. If there is no pop-up window of the voice assistant, select the corresponding voice vertical category according to the foreground application.

5. An intelligent prompt generation device for a vehicle-mounted voice assistant, characterized in that: include: A judgment module, used to judge whether it is necessary to output the intelligent prompt according to the intelligent prompt timing judgment strategy; as well as The output module is used to output the corresponding intelligent prompt according to the user attributes and the scene attributes when it is determined that the intelligent prompt needs to be output.

6. The intelligent prompt generating device for a vehicle-mounted voice assistant according to claim 5, characterized in that: The judgment module determines that an intelligent prompt needs to be output if one or more of the following situations occur during the voice dialogue between the user and the in-vehicle voice assistant: During the detection of the current voice dialogue, it is detected that there is a rejection or the semantics is empty; No user speech is detected within a first preset time after the in-vehicle voice assistant is awakened; During the voice conversation, no new command input is detected within a second preset time after the previous command is executed; It is detected that the user's command is a half-cut command; Detects when the user opens a new app or switches apps.

7. The intelligent prompt generating device for a vehicle-mounted voice assistant according to claim 6, characterized in that: The output module comprises: A selection unit, used to select a corresponding voice vertical category according to the user's scenario and the system preset priority; The output unit is used to determine whether the user is a novice user or an experienced user based on the number of times the user uses the voice assistant. When the user is a novice user, the corresponding intelligent prompt output is selected in the novice user instruction set according to the selected voice vertical category; when the user is an experienced user, the corresponding intelligent prompt output is selected in the experienced user instruction set according to the selected voice vertical category.

8. The intelligent prompt generating device for a vehicle-mounted voice assistant according to claim 7, characterized in that: The selection unit is used to: Determine whether there is a scene that needs to be displayed first. If there is a scene that needs to be displayed first, select the corresponding voice vertical category according to the scene that needs to be displayed first. When there is no scene that needs to be displayed first, determine whether the current scene is in navigation or music playing. If the scene is in navigation or music playing, select the navigation vertical category or the music vertical category; When not in navigation or music playing, determine whether there is a pop-up window of the voice assistant. If there is a pop-up window of the voice assistant, select the corresponding voice vertical category according to the pop-up window of the voice assistant. If there is no pop-up window of the voice assistant, select the corresponding voice vertical category according to the foreground application.

9. An intelligent prompt generation device for a vehicle-mounted voice assistant, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the method for generating intelligent prompts for an in-vehicle voice assistant as described in any one of claims 1 to 4 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for generating intelligent prompts for an in-vehicle voice assistant as described in any one of claims 1 to 4 are implemented.

Images