Vehicle-mounted afterloading voice control interaction method

Abstract

The invention relates to the technical field of vehicle voice control, in particular to a vehicle-mounted after-loading voice control interaction method, which comprises the following steps of: acquiring voice information of a user through a voice AI robot, detecting whether the voice AI robot is in a networking state, and if so, executing a voice control process; if yes, corresponding local control information is determined in a local instruction and a cloud instruction according to the voice information, login is carried out through a mobile phone APP, corresponding cloud control information is obtained through an https request, control information is determined according to the local control information and the cloud control information, and if not, the control information is sent to the mobile phone APP; if yes, corresponding control information is determined in the local instructions according to the voice information, corresponding control instructions are sent to the vehicle through the CANBUS box according to the control information, corresponding voice information is sent and fed back through the voice AI robot, and therefore voice control over the vehicle is completed.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle voice control, and in particular to a vehicle-mounted aftermarket voice control interaction method. Background Art

[0002] At present, many cars on the market do not have voice assistant functions, or are equipped with simple voice assistant functions but are very difficult to use. They can control very few functions, often fail to correctly understand the user's instructions, and cannot provide relatively effective feedback. They cannot learn and adjust according to the user's language habits. If a command is wrong, the command may not be executed. Users generally cannot remember so many commands, and the overall experience is very rigid. Many products with voice recognition on the market have very simple commands. One command can only perform one operation, and cannot be arranged and combined according to the user's habits. The same command cannot be judged according to the current use environment and conditions, and then perform different functions. It is not flexible enough to customize. At present, many after-market products on the market have voice control functions, but they can only control the supporting products themselves, not the vehicle itself. For example, the after-market voice-controlled electric sunshade, the scope of voice control is limited to controlling the switch of the added sunshade, the function is very limited, and there is no signal communication with the vehicle itself. Summary of the invention

[0003] In view of this, an object of the present invention is to provide a vehicle-mounted aftermarket voice control interaction method to overcome the problems existing in the current prior art.

[0004] To achieve the above objectives, the present invention adopts the following technical solutions: On the one hand, the present application provides a vehicle-mounted aftermarket voice control interaction method, comprising: Obtain user's voice information through voice AI robot; Detecting whether the voice AI robot is connected to the Internet; If so, determining corresponding local control information in the local command cloud command respectively according to the voice information; Log in through the mobile phone APP and obtain the corresponding cloud control information through https request; Determining control information according to the local control information and the cloud control information; If not, determining corresponding control information in the local instructions respectively according to the voice information; According to the control information, corresponding control instructions are issued to the vehicle through the CANBUS box, and corresponding voice information is fed back through the voice AI robot.

[0005] Furthermore, in the above method, the step of obtaining the user's voice information through the voice AI robot includes: The user's voice information is denoised through a voice AI robot to obtain the user's voice information after noise reduction.

[0006] Furthermore, in the above method, the step of obtaining the user's voice information through the voice AI robot includes: Detect whether the user issues a wake-up voice command; If so, a corresponding wake-up voice feedback is issued, and the user's voice information within a preset time period is obtained.

[0007] Furthermore, the method described above, wherein logging in through a mobile phone APP and obtaining corresponding cloud control information through an https request, further includes: The voice AI robot sends the Bluetooth command corresponding to the voice information to the CANBUS box; The CANBUS box sends corresponding instructions to the mobile phone APP according to the Bluetooth instruction; The mobile phone APP logs in to the cloud and sends an https request to determine the cloud control information according to the corresponding instruction.

[0008] Furthermore, the method described above, wherein logging in through a mobile phone APP and obtaining corresponding cloud control information through an https request, further includes: The voice AI robot sends the Bluetooth instruction corresponding to the voice information to the mobile phone APP; The mobile phone APP logs in to the cloud and sends an https request according to the Bluetooth instruction to determine the cloud control information.

[0009] Furthermore, the above method further includes: The detection time of the wake-up voice command and user voice information of the voice AI robot is adjusted through the mobile phone APP.

[0010] Furthermore, the above method further includes: The local instructions and the cloud instructions are customized and adjusted through the mobile phone APP to determine the corresponding customized local instructions and customized cloud instructions.

[0011] Furthermore, the above method further includes: The local commands and cloud commands used by the voice AI robot are configured through the mobile phone APP.

[0012] Furthermore, the above method further includes: Check whether the version numbers of the vehicle and the cloud are consistent; If not, download the latest firmware package through the mobile phone APP to update the vehicle version locally.

[0013] Preferably, it also includes: The voice AI robot has a display screen; Acquire the vehicle status signal through the CANBUS box, and display the status signal to the user through the display screen of the voice AI robot; The voice information corresponding to the feedback sent by the voice AI robot also includes: The corresponding status reminder is fed back to the user through the display screen of the voice AI robot.

[0014] The beneficial effects of the present invention are: 1. The functions of the voice AI robot can be customized through the mobile phone APP. One instruction can execute multiple functions at the same time. You can also add many conditional judgments to the instructions. The same instruction can perform different functions in different environments and conditions. Compared with traditional products with set functions at the factory, users have more room for customization.

[0015] 2. Users can OTA upgrade the voice AI robot and CANBUS box at any time through the mobile phone APP. Whether it is a vehicle version update or the addition of product functions, users can upgrade it when they return to the car without returning to the factory for upgrade, which is very convenient.

[0016] 3. All instructions will be compared and arbitrated through local instructions and cloud instructions, and then the optimal solution will be obtained, which can greatly improve the accuracy of instruction execution. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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 will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart provided by an embodiment of a vehicle-mounted aftermarket voice control interaction method of the present invention; Figure 2 It is a noise reduction algorithm diagram provided by an embodiment of a vehicle-mounted aftermarket voice control interaction method of the present invention. DETAILED DESCRIPTION

[0019] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0020] Figure 1 This is a flow chart provided by an embodiment of a vehicle-mounted aftermarket voice control interaction method of the present invention. Figure 1 , this embodiment may include the following steps: S1. Obtain the user's voice information through the voice AI robot; S2, detect whether the voice AI robot is connected to the Internet; S3. If yes, determine the corresponding local control information in the local command cloud command according to the voice information; S4. Log in through the mobile phone APP and obtain the corresponding cloud control information through https request; S5. Determine control information based on local control information and cloud control information; S6. If not, determine the corresponding control information in the local instructions according to the voice information; S7. According to the control information, the corresponding control instructions are issued to the vehicle through the CANBUS box, and the corresponding voice information is fed back through the voice AI robot.

[0021] It should be noted that the voice AI robot in this application has a display screen. When feedback is given to the control information, the corresponding voice information is fed back, and the corresponding picture information is also fed back. In addition to the solution of directly sending https requests through the voice AI robot, the voice AI robot can also send Bluetooth instructions to the CANBUS box, and then the CANBUS box sends instructions to the App, and the App sends https requests to implement the function of executing cloud instructions. Mobile App does not only refer to APP, but can also be small programs and other carriers to achieve the same function.

[0022] In some optional embodiments, the display screen of the voice AI robot is a touch screen, and virtual buttons with corresponding functions are provided on the touch screen, such as: air conditioning switch.

[0023] It is understandable that the voice recognition of the voice AI robot is mainly divided into offline recognition and online recognition. Because the environment inside the car is relatively complex, the car may be parked in some places with poor signals such as underground parking lots. At this time, online voice recognition cannot be performed. When the device is in an environment without a network, the user can use offline commands to issue instructions to the vehicle. When the device is in an environment with a network, the user issues instructions to the voice AI robot and the voice AI robot is awakened, the voice AI robot will perform offline and online recognition at the same time. When the instructions expressed by the user are not so accurate, for example, the command name is "turn on the air conditioner", but the user says "help me turn on the air conditioner", then the online recognition will perform semantic recognition, determine that the user wants to express the command to turn on the air conditioner, and then return the result to the voice AI robot end, arbitrate with the offline recognition result, and determine that the command is to execute "turn on the air conditioner", thereby greatly increasing the accuracy and fault tolerance of recognition.

[0024] It should be noted that when arbitrating the local control information through the cloud control information, it is detected whether the cloud control information is consistent with the local control information. If not, the cloud control information is given priority.

[0025] Preferably, step S1 comprises: The user's voice information is denoised through a voice AI robot to obtain the user's voice information after noise reduction.

[0026] It is understandable that if Figure 2 As shown, the sound environment inside the car is relatively complex. For example, music or navigation may be playing, or passengers may be talking loudly, or the windows may be open and the surrounding noise is very loud. However, it will not affect the robot's wake-up and recognition capabilities because a noise reduction algorithm is used in the recognition algorithm.

[0027] Preferably, step S1 comprises: Detect whether the user issues a wake-up voice command; If so, a corresponding wake-up voice feedback is issued, and the user's voice information within a preset time period is obtained.

[0028] Preferably, step S4 further includes: The voice AI robot sends the Bluetooth command corresponding to the voice information to the CANBUS box; The CANBUS box sends corresponding instructions to the mobile phone APP according to the Bluetooth instructions; The mobile phone APP logs in to the cloud and sends an https request according to the corresponding instructions to determine the cloud control information.

[0029] Preferably, step S4 further includes: The voice AI robot sends the Bluetooth command corresponding to the voice information to the mobile phone APP; The mobile phone APP logs in to the cloud and sends an https request according to the Bluetooth instruction to determine the cloud control information.

[0030] It is understandable that the car owner can selectively log in to the vehicle account. After logging in, he will obtain access_token and refresh_token. Access_token is the key used to control the vehicle, and refresh_token is the key used to refresh access_token. Access_token will automatically expire every 8 hours, and then the access_token and refresh_token can be stored locally. After logging in, the car owner can unlock the most comprehensive vehicle control functions.

[0031] Preferably, it also includes: Adjust the detection time of the voice AI robot's wake-up voice commands and user voice information through the mobile phone APP.

[0032] It is understandable that users can adjust the wake-up voice commands of the voice AI robot through the mobile phone APP, and adjust the time for the voice AI robot to detect user voice information after waking up.

[0033] Preferably, it also includes: Customize local commands and cloud commands through the mobile phone APP to determine the corresponding custom local commands and custom cloud commands.

[0034] It is understandable that users can customize the voice command function according to their preferences, arrange and combine multiple commands to execute some linked functions, or add some judgments based on the current environment, such as the current vehicle speed, current time, etc. to add different functions to the same command. The overall experience is very customized and personalized.

[0035] Preferably, it also includes: Configure the local and cloud commands used by the voice AI robot through the mobile phone APP.

[0036] It is understandable that through the user's customized adjustments to local commands and cloud commands, multiple customized local commands and customized cloud commands are generated. The user can configure the voice AI robot in the mobile phone APP and select one or more local commands and cloud commands to install the voice AI robot.

[0037] Preferably, it also includes: Check whether the version numbers of the vehicle and the cloud are consistent; If not, download the latest firmware package through the mobile phone APP to update the vehicle version locally.

[0038] It is understandable that users can determine whether there is the latest firmware available for upgrade based on the comparison of the local and cloud firmware version numbers. If the cloud firmware version number is greater than the local version number, the latest firmware package can be downloaded to the local mobile phone App through the App, and then transmitted to the CANBUS box via Bluetooth for upgrading. It is very convenient and is an over-the-air upgrade without the need for any wiring harness.

[0039] Preferably, it also includes: The voice AI robot has a display screen; Acquire the vehicle status signal through the CANBUS box, and display the status signal to the user through the display screen of the voice AI robot; The voice information corresponding to the feedback sent by the voice AI robot also includes: The corresponding status reminder is fed back to the user through the display screen of the voice AI robot.

[0040] It is understandable that the display screen of the voice AI robot will obtain the vehicle status signal from the CANBUS box in real time and display it on the screen. For example, the driver says to the robot "turn on the air conditioner", and when the robot successfully turns on the vehicle's air conditioner, the robot will give a feedback sound "The air conditioner has been successfully turned on", and display the status reminder that the air conditioner has been successfully turned on on the screen, making the overall human-computer interaction very close to real-life communication. In addition, the screen can also display vehicle information such as speed and endurance obtained from the CANBUS box, and the robot can also be used as a stopwatch.

[0041] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0042] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0043] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0044] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0045] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0046] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0047] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0048] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0049] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0050] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A vehicle-mounted aftermarket voice control interaction method, characterized in that: include: Obtain user's voice information through voice AI robot; Detecting whether the voice AI robot is connected to the Internet; If so, determining corresponding local control information in the local command cloud command respectively according to the voice information; Log in through the mobile phone APP and obtain the corresponding cloud control information through https request; Determining control information according to the local control information and the cloud control information; If not, determining corresponding control information in the local instructions respectively according to the voice information; According to the control information, corresponding control instructions are issued to the vehicle through the CANBUS box, and corresponding voice information is fed back through the voice AI robot.

2. The method according to claim 1, characterized in that The method of obtaining the user's voice information through the voice AI robot includes: The user's voice information is denoised through a voice AI robot to obtain the user's voice information after noise reduction.

3. The method according to claim 2, characterized in that The method of obtaining the user's voice information through the voice AI robot includes: Detect whether the user issues a wake-up voice command; If so, a corresponding wake-up voice feedback is issued, and the user's voice information within a preset time period is obtained.

4. The method according to claim 3, characterized in that The method of logging in through the mobile phone APP and obtaining the corresponding cloud control information through https request also includes: The voice AI robot sends the Bluetooth command corresponding to the voice information to the CANBUS box; The CANBUS box sends corresponding instructions to the mobile phone APP according to the Bluetooth instruction; The mobile phone APP logs in to the cloud and sends an https request to determine the cloud control information according to the corresponding instruction.

5. The method according to claim 4, characterized in that The method of logging in through the mobile phone APP and obtaining the corresponding cloud control information through https request also includes: The voice AI robot sends the Bluetooth instruction corresponding to the voice information to the mobile phone APP; The mobile phone APP logs in to the cloud and sends an https request according to the Bluetooth instruction to determine the cloud control information.

6. The method according to claim 5, characterized in that Also includes: The detection time of the wake-up voice command and user voice information of the voice AI robot is adjusted through the mobile phone APP.

7. The method according to claim 6, characterized in that Also includes: The local instructions and the cloud instructions are customized and adjusted through the mobile phone APP to determine the corresponding customized local instructions and customized cloud instructions.

8. The method according to claim 7, characterized in that Also includes: The local commands and cloud commands used by the voice AI robot are configured through the mobile phone APP.

9. The method according to claim 8, characterized in that Also includes: Check whether the version numbers of the vehicle and the cloud are consistent; If not, download the latest firmware package through the mobile phone APP to update the vehicle version locally.

10. The method according to claim 9, characterized in that Also includes: The voice AI robot has a display screen; Acquire the vehicle status signal through the CANBUS box, and display the status signal to the user through the display screen of the voice AI robot; The voice information corresponding to the feedback sent by the voice AI robot also includes: The corresponding status reminder is fed back to the user through the display screen of the voice AI robot.

Images