Vehicle machine voice interaction method and system and storage medium

Abstract

The invention discloses a vehicle voice interaction method and system and a storage medium, and the method comprises the steps: obtaining a voice instruction sent by a user, extracting voiceprint information and semantics according to the voice instruction, and obtaining a current user position based on the voice instruction; the user permission level is recognized according to the voiceprint information, the semantics and the user position, the voiceprint information is used for verifying the voiceprint permission, the semantics is used for verifying the wake-up permission, the user position is used for verifying the priority permission, and when the voiceprint information passes the verification of the voiceprint permission, verification of the wake-up permission is executed. After the semantics pass the verification of the wake-up permission, executing priority permission verification, and outputting the user permission level; and generating a control instruction based on the user permission level, wherein the control instruction is used for controlling the vehicle machine to execute an operation corresponding to the user permission level.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-machine voice interaction authority verification, and in particular to a vehicle-machine voice interaction method, system and storage medium. Background Art

[0002] With the rapid development of voice interaction today, many vehicle functions can be controlled by voice commands. Some functions involve the safety of the vehicle and its passengers. Corresponding permission control is required for related functional interactions to prevent unauthorized people from affecting vehicle safety through voice commands.

[0003] At present, voiceprint and other voice interaction-related biometric technologies have made great progress. Voiceprint recognition technology has been successfully applied in many fields, including security control. Therefore, there is corresponding technical support for the identity recognition and verification of the voice waker in voice interaction. On the other hand, the smart cockpit provides a variety of sensors for receiving sound signals from inside and outside the car, so related equipment can also be used to identify the identity of the voice interactor, control the authority of the voice interactor, and other related functions to protect the privacy and personal safety of vehicle users. Summary of the invention

[0004] To solve at least one aspect of the above problems, the present invention provides a vehicle-computer voice interaction method, comprising: obtaining a voice command issued by a user, extracting voiceprint information and semantics according to the voice command, and obtaining the current user location based on the voice command; identifying the user authority level according to the voiceprint information, the semantics and the user location, the voiceprint information is used to verify the voiceprint authority, the semantics is used to verify the wake-up authority, and the user location is used to verify the priority authority, when the voiceprint information passes the voiceprint authority verification, the wake-up authority verification is performed, when the semantics passes the wake-up authority verification, the priority authority verification is performed, and the user authority level is output; based on the user authority level, a control instruction is generated, and the control instruction is used to control the vehicle-computer to perform operations corresponding to the user authority level.

[0005] Preferably, the user authority level includes a voiceprint authority level, a wake-up word authority level and a location authority level.

[0006] Preferably, the user location includes an outside vehicle position, an inside vehicle position, a main driver position and a co-driver position, and the location authority levels include outside vehicle position authority, inside vehicle position authority, main driver position authority and co-driver position authority, the inside vehicle position authority is greater than the outside vehicle position authority, and the main driver position authority is greater than the co-driver position authority.

[0007] On the other hand, a vehicle-machine voice interaction system is provided, comprising: a voice acquisition module, the voice acquisition module is used to obtain voice commands issued by a user, and extract voiceprint information and semantics based on the voice commands, the voice acquisition module identifies the current user location based on the received voice commands; an authority identification module, the authority identification module identifies the user authority level according to the voiceprint information, the semantics and the user location, the voiceprint information is used to verify the voiceprint authority, the semantics is used to verify the wake-up authority, and the user location is used to verify the priority authority, when the voiceprint information passes the voiceprint authority verification, the wake-up authority verification is performed, when the semantics passes the wake-up authority verification, the priority authority verification is performed, and the user authority level is output; a control module, the control module receives the user authority level through the authority identification module, and generates a control instruction based on the user authority level, the control instruction is used to control the vehicle-machine to perform operations corresponding to the user authority level.

[0008] Preferably, the user authority level includes a voiceprint authority level, a wake-up word authority level and a location authority level.

[0009] Preferably, the user location includes an outside vehicle position, an inside vehicle position, a main driver position and a co-driver position, and the location authority levels include outside vehicle position authority, inside vehicle position authority, main driver position authority and co-driver position authority, the inside vehicle position authority is greater than the outside vehicle position authority, and the main driver position authority is greater than the co-driver position authority.

[0010] A computer-readable storage medium is also provided, on which computer instructions are stored, and when the instructions are executed by a processor, the method described in any of the above items is implemented.

[0011] The vehicle-machine voice interaction method and system of the embodiments of the present invention have the following beneficial effects: through authority control and identity recognition in voice interaction, some security issues caused by voice control of vehicle functions existing in the prior art are solved; through the verification process of user authority levels, key voice command authorities can be controlled by as few people as possible, thereby minimizing the problems caused by the proliferation of voice control. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to better understand the above and other purposes, features, advantages and functions of the present invention, reference may be made to the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings refer to the same components. It should be understood by those skilled in the art that the accompanying drawings are intended to schematically illustrate the preferred embodiments of the present invention and have no limiting effect on the scope of the present invention, and the components in the drawings are not drawn to scale.

[0013] Figure 1 A flow chart of a vehicle-machine voice interaction method according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0014] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0015] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part on". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0016] In order to at least partially solve one or more of the above-mentioned problems and other potential problems, an embodiment of the present disclosure proposes a vehicle-machine voice interaction method, including: step S1, obtaining a voice command issued by a user, extracting voiceprint information and semantics according to the voice command, and obtaining the current user location based on the voice command.

[0017] Specifically, the user issues a voice command, and the vehicle-mounted voice interaction system receives the voice command through the vehicle microphone. The vehicle-mounted voice interaction system uses existing voiceprint extraction technology and semantic recognition technology to extract voiceprint information and semantic information based on the voice command. The vehicle-mounted voice interaction system also recognizes the current user location in response to the received voice command.

[0018] Step S2, identifying the user authority level according to the voiceprint information, semantics and user location, the voiceprint information is used to verify the voiceprint authority, the semantics is used to verify the wake-up authority, the user location is used to verify the priority authority, when the voiceprint information passes the voiceprint authority verification, the wake-up authority verification is performed, when the semantics passes the wake-up authority verification, the priority authority verification is performed, and the user authority level is output.

[0019] Specifically, the user authority level includes the voiceprint authority level, the wake-up word authority level and the location authority level. The voiceprint authority level includes the user voiceprint authority level including unauthorized, partially authorized and fully authorized. The wake-up authority includes the first wake-up word, the second wake-up word, etc., and each wake-up word corresponds to a different controller module. The user position includes the position outside the car, the position inside the car, the main driver's position and the co-driver's position. The position authority level includes the position outside the car, the position inside the car, the main driver's position authority and the co-driver's position authority. The position authority inside the car is greater than the position authority outside the car, and the main driver's position authority is greater than the co-driver's position authority.

[0020] Step S3, generating a control instruction based on the user authority level, the control instruction is used to control the vehicle computer to perform an operation corresponding to the user authority level.

[0021] Specifically, if the voiceprint is not authorized, the car computer will not respond. If the voiceprint is partially authorized, the car computer will partially respond, for example, only the in-car entertainment system is authorized. Fully authorized voiceprints can realize voice interaction with any voice-supported controller of the car computer. For example, by entering the voiceprint information of the vehicle owner, driver, and other trusted drivers and passengers, the owner can personalize the permission level and permission range of each voiceprint information, and confirm the necessity of the current command voice response according to the corresponding configuration. Key functions do not support voice control of unrecognizable voiceprint information or low-authority voiceprint information; secondly, voice wake-up can be performed by setting a special wake-up word that only the relevant people in the vehicle know. Different wake-up words can reflect the authority of the wake-up person. The voice system distinguishes the identity information and authority of the wake-up person by identifying and distinguishing whether the semantics is a wake-up word, thereby confirming the response range of the voice interaction. The direction of the sound can be used to determine whether to execute relevant commands. In-vehicle commands are given relatively higher priority, while out-of-vehicle commands require more identity authentication measures to ensure vehicle safety. At the same time, the main driver's commands and the co-driver's commands also have their own priorities. Operation instructions involving vehicle privacy and driving safety should only respond to the main driver's voice commands.

[0022] like Figure 1 As shown, the user issues a voice command, voiceprint information and semantics are extracted through the voice command, and the user location is determined based on the voice command. The voiceprint permission is determined based on the voiceprint information, the wake-up word permission is determined based on the wake-up word corresponding to the semantic information, and the user location permission is determined based on the user location. The user permission level is determined by combining the voiceprint permission, wake-up word permission, and user location permission. Permission decisions are made based on the user permission level. If the current user does not have the permission for the command, the voice command will not be executed. If the current user has the permission for the command, the voice command will be executed.

[0023] By dividing the permissions of all voice functions and reasonably allocating them to the owners of corresponding permissions, the abuse of voice functions can be limited. At the same time, the above three recognition schemes work together to basically cover the complex voice interaction environment during parking and driving, avoiding the loopholes and defects of using a single permission distinction method.

[0024] On the other hand, a vehicle-machine voice interaction system is provided, including: a voice acquisition module, an authority identification module and a control module. Figure 1 As shown, the voice collection module and the authority identification module are communicatively connected, and the voice collection module and the authority identification module are communicatively connected to the control module respectively.

[0025] The voice collection module is used to obtain the voice commands issued by the user and extract voiceprint information and semantics based on the voice commands. The voice collection module identifies the current user location based on the received voice commands.

[0026] Specifically, the voice collection module includes a plurality of vehicle-mounted microphones, which are respectively arranged at preset positions of the vehicle, for receiving voice commands issued by the user. The voice collection module also includes a voiceprint extraction unit and a semantic extraction unit, the voiceprint extraction unit extracts the user's voiceprint information based on the voice command, and the voice extraction unit extracts the user's semantics based on the voice command. The voice collection module also includes a user position recognition unit, which is used for the position recognition unit to recognize the user's position based on the voice command, for example, by judging the relative distance between each microphone and the user through the audio intensity of the voice command received by each microphone, thereby determining the user's position.

[0027] The permission identification module identifies the user permission level based on voiceprint information, semantics and user location. Voiceprint information is used to verify voiceprint permission, semantics is used to verify wake-up permission, and user location is used to verify priority permission. When the voiceprint information passes the voiceprint permission verification, the wake-up permission verification is performed. When the semantics passes the wake-up permission verification, the priority permission verification is performed and the user permission level is output.

[0028] Specifically, the authority identification module is used to identify voiceprint authority, wake-up authority and priority authority according to voiceprint information, semantics and user location. In some embodiments, the user authority level includes voiceprint authority level, wake-up word authority level and location authority level. For example, by entering the voiceprint information of the vehicle owner, driver and other trusted drivers and passengers, the owner can personalize the authority level and authority range of each voiceprint information, and confirm the necessity of the current command voice response according to the corresponding configuration. The key function does not support voice control of unrecognizable voiceprint information or low-authority voiceprint information; secondly, by setting a special wake-up word that only the relevant person of the vehicle knows, voice wake-up is performed. Different wake-up words can reflect the authority of the wake-up person, and the identity information and authority of the wake-up person are distinguished by the recognized semantics, thereby confirming the response range of voice interaction. In some embodiments, the user location includes the outside position, the inside position, the main driving position and the co-driver position, and the location authority level includes the outside position authority, the inside position authority, the main driving position authority and the co-driver position authority. The inside position authority is greater than the outside position authority, and the main driving position authority is greater than the co-driver position authority. The direction of the sound is used to determine whether to execute the relevant commands. In-vehicle commands are given relatively higher priority, while out-of-vehicle commands require more identity authentication measures to ensure vehicle safety. At the same time, the main driver's commands and the co-driver's commands also have their own priorities. Operation instructions involving vehicle privacy and driving safety should only respond to the main driver's voice commands.

[0029] By dividing the permissions of all voice functions and reasonably allocating them to the owners of corresponding permissions, the abuse of voice functions can be limited. At the same time, the above three recognition schemes work together to basically cover the complex voice interaction environment during parking and driving, avoiding the loopholes and defects of using a single permission distinction method.

[0030] The control module receives the user authority level through the authority identification module and generates a control instruction based on the user authority level. The control instruction is used to control the vehicle computer to perform operations corresponding to the user authority level.

[0031] Specifically, the control module is a controller of the vehicle voice interaction system, for example, a vehicle entertainment system controller, an auxiliary driving controller, etc. The control module outputs control instructions corresponding to the user authority level to achieve voice interaction.

[0032] A computer-readable storage medium is also provided, on which computer instructions are stored, and when the instructions are executed by a processor, any of the above methods is implemented.

[0033] Specifically, computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs 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, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0034] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the present invention.

Claims

1. A vehicle-machine voice interaction method, characterized in that: include: Acquire a voice command issued by a user, extract voiceprint information and semantics according to the voice command, and acquire a current user location based on the voice command; Identify the user authority level according to the voiceprint information, the semantics and the user location, the voiceprint information is used to verify the voiceprint authority, the semantics is used to verify the wake-up authority, and the user location is used to verify the priority authority, and perform the wake-up authority verification after the voiceprint information passes the voiceprint authority verification, and perform the priority authority verification after the semantics passes the wake-up authority verification, and output the user authority level; A control instruction is generated based on the user authority level, and the control instruction is used to control the vehicle computer to perform an operation corresponding to the user authority level.

2. The method according to claim 1, characterized in that The user permission level includes a voiceprint permission level, a wake-up word permission level, and a location permission level.

3. The method according to claim 2, characterized in that The user location includes the position outside the vehicle, the position inside the vehicle, the main driver's position and the co-driver's position. The location authority levels include the position authority outside the vehicle, the position authority inside the vehicle, the main driver's position authority and the co-driver's position authority. The position authority inside the vehicle is greater than the position authority outside the vehicle, and the main driver's position authority is greater than the co-driver's position authority.

4. A vehicle-machine voice interaction system, characterized in that: include: A voice acquisition module, the voice acquisition module is used to obtain the voice command issued by the user, and extract voiceprint information and semantics based on the voice command, and the voice acquisition module identifies the current user position based on the received voice command; a permission identification module, wherein the permission identification module identifies the user permission level according to the voiceprint information, the semantics and the user location, wherein the voiceprint information is used to verify the voiceprint permission, the semantics is used to verify the wake-up permission, and the user location is used to verify the priority permission. When the voiceprint information passes the voiceprint permission verification, the wake-up permission verification is performed, and when the semantics passes the wake-up permission verification, the priority permission verification is performed, and the user permission level is output; A control module receives the user authority level through the authority identification module and generates a control instruction based on the user authority level, wherein the control instruction is used to control the vehicle computer to perform an operation corresponding to the user authority level.

5. The system according to claim 4, characterized in that The user permission level includes a voiceprint permission level, a wake-up word permission level, and a location permission level.

6. The system according to claim 5, characterized in that The user location includes the position outside the vehicle, the position inside the vehicle, the main driver's position and the co-driver's position. The location authority levels include the position authority outside the vehicle, the position authority inside the vehicle, the main driver's position authority and the co-driver's position authority. The position authority inside the vehicle is greater than the position authority outside the vehicle, and the main driver's position authority is greater than the co-driver's position authority.

7. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images