Vehicle navigation voice interaction method and device

Abstract

The invention discloses a vehicle navigation voice interaction method and device, and relates to the technical field of voice interaction, and the method comprises the following steps: S1, determining the identity of a user; s2, a user interacts with navigation; s3, inputting voice information at one time; s4, voice recognition; and S5, displaying the search navigation path. Through voiceprint identity verification, a user can be prevented from being interfered by other voice information in a vehicle when inputting the voice information to a voice interaction system, so that voice recognition in a vehicle-mounted navigation system is disturbed, accurate navigation information cannot be obtained, and the user can be prevented from being influenced in a voice navigation process. The voice instructions are analyzed at a time after being input, the navigation smoothness can be enhanced, a user can adjust the electronic map through the voice instructions, the number of times for a driver to view a screen is reduced, and potential safety hazards are reduced.

Description

Technical Field

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

[0002] Currently, in-vehicle navigation systems require users to manually select a destination while driving, and then choose the optimal route based on the destination. This affects driving and can easily pose a safety hazard. Chinese patent application number 202310472800.2 discloses a "vehicle navigation voice interaction method, device, electronic device, storage medium, and vehicle, including identifying a user voice request, generating a destination list based on the search results of the voice request; sorting the destination list based on the degree of match between the search results and the voice request; announcing the top search result and requesting user confirmation; and executing the top search result or re-sorting the destination list based on the user's confirmation."

[0003] The above-mentioned file can reduce the number of times the user checks the screen to select the correct address, thereby ensuring driving safety. However, during the voice navigation process, since there is not only the driver in the car, there may be other people talking, and their voices are recorded in the voice interaction system, interfering with the recognition of the in-vehicle navigation. In addition, in the existing technology, the system continuously feeds back the voice commands input by the driver, disturbing the driver so that he cannot output the voice commands at one time, increasing the number of times the driver checks the screen, affecting the driver's operation, and posing a safety hazard. Summary of the Invention

[0004] The object of the present invention is to provide a vehicle-mounted navigation voice interaction method and device to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a vehicle navigation voice interaction method, comprising the following steps:

[0006] S1. Determine user identity: Establish a voiceprint database, record the user's voice information multiple times through a recording device, extract audio feature parameters from the voice information for training, and store the training results in the voiceprint database. During identity recognition, the trained audio feature parameters are used as a reference template to match the audio feature parameters extracted from the user in real time to determine the user's identity;

[0007] S2. User-navigation interaction: The in-vehicle navigation system includes a voice interaction system, which includes a voice interaction service module, an audio task control module, a speech synthesis module, and a speech recognition module. The voice interaction system enables interaction between the user and the in-vehicle navigation system.

[0008] S3. One-time voice input: The user obtains access to the in-vehicle navigation voice interaction system through voice input training and selects a method to activate the voice interaction system based on the in-vehicle noise environment and driving conditions. The voice interaction service module calls the speech synthesis module to issue a voice prompt, prompting the user to input voice information about the navigation. The user then promptly inputs all voice information required for the navigation service.

[0009] S4. Speech Recognition: Endpoint detection technology is used to continuously detect the power of speech signals. The vehicle-mounted recording device continuously records speech, and stops recording after five seconds of speech silence. The received speech is collected and passed to the speech recognition module.

[0010] S5. Display the searched navigation route: Utilize the geographic information contained in the electronic map to plan the route, search for multiple routes from the starting point to the target point, and announce the optimal route. After the user confirms, the navigation mode is turned on.

[0011] Preferably, the step S1 includes the following steps:

[0012] S101, the process of extracting audio feature parameters is as follows: converting the speech signal into the frequency domain for analysis, analyzing the speech features through energy distribution, performing pre-emphasis, framing and windowing preprocessing on the speech signal, and then performing FFT transformation to convert the time domain signal into the power spectrum of the signal, and then obtaining the audio feature parameters through DCT transformation;

[0013] S102. Pre-emphasis refers to extracting the speaker's features from the high-frequency part of the speech information and enhancing the energy of the high-frequency part of the speech signal through filtering. Framing refers to segmenting the speech information to obtain speech frames and analyzing the speech features for each frame. Windowing refers to adding a window function to the speech frame to obtain continuous speech features.

[0014] Preferably, step S2 includes the following steps:

[0015] S201, the voice interaction service module prompts the user to output voice information through voice, recognizes the user's voice, and sends the recognition result to the car navigation application;

[0016] S202: The audio task control module is responsible for scheduling between audio tasks so that the voice interaction service is globally responded to and interference with other audio outputs is avoided;

[0017] S203, the speech synthesis module is responsible for synthesizing the speech output by the vehicle application between the speech interaction service module and the audio task module, and outputting the speech broadcast within the necessary time;

[0018] S204, the speech recognition module converts the speech input into speech commands to control the vehicle navigation after speech denoising and analysis.

[0019] Preferably, step S3 includes the following steps:

[0020] S301: When a user uses the vehicle navigation system for the first time, he or she first enters voice information in the voice interaction system, and then the user has the right to use the voice interaction system of the vehicle navigation system;

[0021] S302. While the user is driving, the in-vehicle navigation recording function is awakened by the user through a preset voice command. If there is music or other audio output at this time, the user directly activates the voice interaction system by clicking the button to enter the voice interaction system. At this time, all other audio information is turned off.

[0022] Preferably, the step S3 further comprises the following steps:

[0023] S303: When the user activates the voice interaction system and enters the voice interaction state, the voice interaction service module calls the voice synthesis module to issue a voice prompt, prompting the user to output a voice message about navigation. After the voice prompt is completed, the user speaks the voice message within five seconds.

[0024] S304: The user promptly inputs all voice information requesting navigation services as a condition for in-vehicle navigation input. If the voice interaction system exceeds five seconds, it will be closed and needs to be reactivated.

[0025] Preferably, step S4 includes the following steps:

[0026] S401: The analysis and processing flow in the voice recognition module is to identify the input voice to determine whether it is the user himself. If it is the user himself, the information is received and the processed voice is further extracted to obtain valid information. Otherwise, the voice information is not accepted.

[0027] S402: Match the valid information with the data in the template library. The data in the template library is generated in advance through a large amount of speech data training and classification. Compare the speech data with the data in the template library to find the template library file with the highest matching degree with the data, and return the similarity between the two files;

[0028] S403: If the similarity between the two files is greater than a preset confidence level, the data is received and a recognition result is output; if the similarity is not greater than the preset confidence level, the recognition fails;

[0029] S404: After the recognition result is obtained, the vehicle navigation application is called according to the recognition result. Otherwise, the voice interaction service module calls the voice synthesis module to announce the reason for the failure of recognition.

[0030] Preferably, step S5 includes the following steps:

[0031] S501. The vehicle navigation system obtains the current location of the vehicle through GPS positioning, and simultaneously shifts the center of the map to the current location of the vehicle, displays the area where the vehicle is currently located, and marks it on the map as the starting point;

[0032] S502: Transmitting the user's voice command to the in-vehicle navigation system, where the voice command must include the target location, performing route planning using geographic information contained in the electronic map, searching for multiple routes from the starting location to the target location, and marking the routes on the map;

[0033] S503: While the route is displayed on the in-vehicle navigation electronic map, the voice interaction service module calls the voice synthesis module to broadcast the route that best matches the user's needs and is closest, and starts the navigation mode after the user confirms;

[0034] S504. The user adjusts the electronic map according to actual needs. When the user needs to use the in-vehicle navigation, the user guides the in-vehicle navigation through voice commands to form a navigation route, zooms out the map to view the entire driving area, and zooms in the map to view detailed information on the route.

[0035] A vehicle-mounted navigation voice interaction device, comprising:

[0036] A user identity confirmation unit, which extracts audio feature parameters from voice information for training and stores the training results in a voiceprint library. During identity recognition, the trained audio feature parameters are used as a reference template to match the audio feature parameters extracted from the user in real time, thereby determining the user's identity;

[0037] A user navigation interaction unit, which enables interaction between the user and the in-vehicle navigation system through a voice interaction system in the in-vehicle navigation system. The voice interaction system includes a voice interaction service module, an audio task control module, a speech synthesis module, and a speech recognition module;

[0038] A voice information input unit, which selects a method for waking up the voice interaction system based on the in-vehicle noise environment and driving conditions. The voice interaction service module calls the voice synthesis module to issue a voice prompt, prompting the user to input voice information about navigation. The user then promptly inputs all voice information required for the navigation service.

[0039] A speech recognition unit that continuously detects the power of the speech signal, continuously records the speech through the vehicle recording device, collects the received speech and transmits the speech information to the speech recognition module;

[0040] The navigation path broadcasting unit uses the geographic information contained in the electronic map to plan the path, searches for multiple paths from the starting point to the target point, and broadcasts the optimal path, and starts the navigation mode after the user confirms it.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. The present invention uses voiceprint authentication to prevent users from being interfered with by other voice information in the car when inputting voice information into the voice interaction system, thereby disrupting the voice recognition in the car navigation and failing to obtain accurate navigation information. During the voice navigation process, due to the need to continuously input voice commands, the commands are always in a broadcast state. After all the voice commands are input, they are analyzed at once, which can enhance the smoothness of navigation. Users can adjust the electronic map through voice commands. When the user needs to use the car navigation, the user uses voice commands to guide the car navigation to form a navigation route, zoom out to view the entire driving area, and zoom in to view detailed information on the route. This avoids manual adjustments by the driver while driving, reduces the number of times the driver checks the screen, and reduces safety hazards.

[0043] 2. When extracting audio feature parameters, the present invention transfers the voice signal to the frequency domain for analysis, which can enhance the stability of voice feature extraction. By pre-emphasis, framing and windowing the voice signal, the recognition effect of voice information is improved. The mutual cooperation of the voice interaction service module, audio task control module, voice synthesis module and voice recognition module realizes good interactivity between the in-vehicle navigation and the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of the overall method flow provided by an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of the overall device flow is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0047] See also Figures 1 to 2 The present invention provides a technical solution: a vehicle navigation voice interaction method, comprising the following steps:

[0048] S1. Determine user identity: Establish a voiceprint database, record the user's voice information multiple times through a recording device, extract audio feature parameters from the voice information for training, and store the training results in the voiceprint database. During identity recognition, the trained audio feature parameters are used as a reference template to match the audio feature parameters extracted from the user in real time to determine the user's identity;

[0049] S2. User-navigation interaction: The in-vehicle navigation system includes a voice interaction system, which includes a voice interaction service module, an audio task control module, a speech synthesis module, and a speech recognition module. The voice interaction system enables interaction between the user and the in-vehicle navigation system.

[0050] S3. One-time voice input: The user obtains access to the in-vehicle navigation voice interaction system through voice input training and selects a method to activate the voice interaction system based on the in-vehicle noise environment and driving conditions. The voice interaction service module calls the speech synthesis module to issue a voice prompt, prompting the user to input voice information about the navigation. The user then promptly inputs all voice information required for the navigation service.

[0051] S4. Speech Recognition: Endpoint detection technology is used to continuously detect the power of speech signals. The vehicle-mounted recording device continuously records speech, and stops recording after five seconds of speech silence. The received speech is collected and passed to the speech recognition module.

[0052] S5. Display the searched navigation route: Utilize the geographic information contained in the electronic map to plan the route, search for multiple routes from the starting point to the target point, and announce the optimal route. After the user confirms, the navigation mode is turned on.

[0053] Step S1 includes the following steps:

[0054] S101, the process of extracting audio feature parameters is as follows: converting the speech signal into the frequency domain for analysis, analyzing the speech features through energy distribution, performing pre-emphasis, framing and windowing preprocessing on the speech signal, and then performing FFT transformation to convert the time domain signal into the power spectrum of the signal, and then obtaining the audio feature parameters through DCT transformation;

[0055] The audio feature parameter extraction formula is:

[0056]

[0057] Wherein, m represents the coefficient of the audio feature parameter, m=1,2···M, X(m) represents the spectrum energy value after filtering by the triangular filter, π represents pi, which is a constant, M represents the number of coefficients of the audio feature parameter, and C represents the extracted audio feature parameter;

[0058] S102, pre-emphasis refers to extracting speaker features from the high-frequency part of the voice information, and enhancing the energy of the high-frequency part of the voice signal through filtering. Framing refers to segmenting the voice information to obtain voice frames, and analyzing the voice features of each frame. Windowing refers to adding a window function to the voice frame to obtain continuous voice features.

[0059] The windowed function is:

[0060] Y(n)=S(n)*W(n);

[0061]

[0062] Where N is the number of samples of the speech frame, S(n) is the speech frame signal, W(n) is the window function, Y(n) is the windowed function, a is a constant with a value of 0.46, π is the circumference of a circle with a value of a constant, and n is the speech frame.

[0063] Step S2 includes the following steps:

[0064] S201, the voice interaction service module prompts the user to output voice information through voice, recognizes the user's voice, and sends the recognition result to the car navigation application;

[0065] S202: The audio task control module is responsible for scheduling between audio tasks so that the voice interaction service is globally responded to and interference with other audio outputs is avoided;

[0066] S203, the speech synthesis module is responsible for synthesizing the speech output by the vehicle application between the speech interaction service module and the audio task module, and outputting the speech broadcast within the necessary time;

[0067] S204, the voice recognition module converts the voice input into voice commands to control the vehicle navigation after voice denoising and analysis processing;

[0068] Step S3 includes the following steps:

[0069] S301: When a user uses the vehicle navigation system for the first time, he or she first enters voice information in the voice interaction system, and then the user has the right to use the voice interaction system of the vehicle navigation system;

[0070] S302: While the user is driving, the in-vehicle navigation recording function is activated by the user through a preset voice command. If music or other audio output is present at this time, the user directly activates the voice interaction system by clicking the button to enter the voice interaction system. At this time, all audio information is muted.

[0071] Step S3 further includes the following steps:

[0072] S303: When the user activates the voice interaction system and enters the voice interaction state, the voice interaction service module calls the voice synthesis module to issue a voice prompt, prompting the user to output a voice message about navigation. After the voice prompt is completed, the user speaks the voice message within five seconds.

[0073] S304: The user promptly inputs all voice messages requesting navigation services as a condition for in-vehicle navigation input. If the voice interaction system exceeds five seconds, it will be closed and needs to be reactivated.

[0074] Step S4 includes the following steps:

[0075] S401: The analysis and processing flow in the voice recognition module is to identify the input voice to determine whether it is the user himself. If it is the user himself, the information is received and the processed voice is further extracted to obtain valid information. Otherwise, the voice information is not accepted.

[0076] S402: Match the valid information with the data in the template library. The data in the template library is generated in advance through a large amount of speech data training and classification. Compare the speech data with the data in the template library to find the template library file with the highest matching degree with the data, and return the similarity between the two files;

[0077] S403: If the similarity between the two files is greater than a preset confidence level, the data is received and a recognition result is output; if the similarity is not greater than the preset confidence level, the recognition fails;

[0078] S404: After the recognition result is obtained, the vehicle navigation application is called according to the recognition result. Otherwise, the voice interaction service module calls the voice synthesis module to announce the reason for the failure of recognition;

[0079] Step S5 includes the following steps:

[0080] S501. The vehicle navigation system obtains the current location of the vehicle through GPS positioning, and simultaneously shifts the center of the map to the current location of the vehicle, displays the area where the vehicle is currently located, and marks it on the map as the starting point;

[0081] S502: Transmitting the user's voice command to the in-vehicle navigation system, where the voice command must include the target location, performing route planning using geographic information contained in the electronic map, searching for multiple routes from the starting location to the target location, and marking the routes on the map;

[0082] S503: While the route is displayed on the in-vehicle navigation electronic map, the voice interaction service module calls the voice synthesis module to broadcast the route that best matches the user's needs and is closest, and starts the navigation mode after the user confirms;

[0083] S504. The user adjusts the electronic map according to actual needs. When the user needs to use the in-vehicle navigation, the user guides the in-vehicle navigation through voice commands to form a navigation route, zooms out the map to view the entire driving area, and zooms in the map to view detailed information on the route.

[0084] A vehicle-mounted navigation voice interaction device, comprising:

[0085] A user identity confirmation unit, which extracts audio feature parameters from voice information for training and stores the training results in a voiceprint library. During identity recognition, the trained audio feature parameters are used as a reference template to match the audio feature parameters extracted from the user in real time, thereby determining the user's identity;

[0086] A user navigation interaction unit, which enables interaction between the user and the in-vehicle navigation system through a voice interaction system in the in-vehicle navigation system. The voice interaction system includes a voice interaction service module, an audio task control module, a speech synthesis module, and a speech recognition module;

[0087] A voice information input unit, which selects a method for waking up the voice interaction system based on the in-vehicle noise environment and driving conditions. The voice interaction service module calls the voice synthesis module to issue a voice prompt, prompting the user to input voice information about navigation. The user then promptly inputs all voice information required for the navigation service.

[0088] A speech recognition unit that continuously detects the power of the speech signal, continuously records the speech through the vehicle recording device, collects the received speech and transmits the speech information to the speech recognition module;

[0089] The navigation path broadcasting unit uses the geographic information contained in the electronic map to plan the path, searches for multiple paths from the starting point to the target point, and broadcasts the optimal path, and starts the navigation mode after the user confirms it.

[0090] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0091] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A vehicle navigation voice interaction method, characterized in that: The method comprises the following steps: S1. Determine the user's identity: Establish a voiceprint database, record the user's voice information multiple times through a recording device, extract audio feature parameters from the voice information for training, and store the training results in the voiceprint database. When identifying the user, the trained audio feature parameters are used as a reference template to match the audio feature parameters extracted from the user in real time, thereby determining the user's identity; S2. User-navigation interaction: The in-vehicle navigation includes a voice interaction system, which includes a voice interaction service module, an audio task control module, a voice synthesis module, and a voice recognition module. The voice interaction system enables the user to interact with the in-vehicle navigation. S3, one-time input of voice information: the user obtains the right to use the voice interaction system of the in-vehicle navigation through voice input training, and chooses the way to wake up the voice interaction system according to the noise environment in the car and the driving conditions. The voice interaction service module calls the voice synthesis module to issue a voice prompt, prompting the user to input voice information about the navigation, and then the user promptly inputs all the voice information required for the navigation service; S4, speech recognition: Use endpoint detection technology to continuously detect the power of the speech signal, continuously record the speech through the vehicle recording device, stop recording after the speech disappears for five seconds, collect the received speech and pass the speech information to the speech recognition module; S5. Display the searched navigation route: Use the geographic information contained in the electronic map to plan the route, search for multiple routes from the starting point to the target point, and broadcast the optimal route. After the user confirms, start the navigation mode.

2. The vehicle navigation voice interaction method according to claim 1, characterized in that: The step S1 comprises the following steps: S101, the process of extracting audio feature parameters is as follows: converting the speech signal to the frequency domain for analysis, analyzing the speech feature through the energy distribution, performing FFT transformation after pre-emphasis, framing and windowing pre-processing on the speech signal, thereby transforming the time domain signal into the power spectrum of the signal, and then obtaining the audio feature parameters through DCT transformation; S102, pre-emphasis refers to extracting the speaker's features from the high-frequency part of the voice information, and enhancing the energy of the high-frequency part of the voice signal through filtering. Framing refers to segmenting the voice information to obtain voice frames, and analyzing the voice features for each frame. Windowing refers to adding a window function to the voice frame to obtain continuous voice features.

3. The vehicle navigation voice interaction method according to claim 1, characterized in that: The step S2 comprises the following steps: S201, the voice interaction service module prompts the user to output voice information through voice, recognizes the user's voice, and sends the recognition result to the in-vehicle navigation application; S202, the audio task control module is responsible for the scheduling between audio tasks, so that the voice interaction service is responded to globally and avoids interference from other audio outputs; S203, the speech synthesis module is responsible for synthesizing the speech output by the vehicle-mounted application between the speech interaction service module and the audio task module, and outputting the speech broadcast within the necessary time; S204, the voice recognition module converts the voice input into voice commands to control the vehicle navigation after voice denoising and analysis processing.

4. The vehicle navigation voice interaction method according to claim 1, characterized in that: The step S3 comprises the following steps: S301, when a user uses the vehicle navigation system for the first time, the user first enters voice information in the voice interaction system, and then the user has the right to use the voice interaction system of the vehicle navigation system; S302. When the user is driving, the in-vehicle navigation recording function is awakened by the user through a preset voice command. If there is music or other audio output at this time, the user directly starts the voice interaction system by clicking a button to enter the voice interaction system. At this time, all other audio information is turned off.

5. The vehicle navigation voice interaction method according to claim 4, characterized in that: The step S3 further comprises the following steps: S303, when the user starts the voice interaction system to enter the voice interaction state, the voice interaction service module calls the voice synthesis module to issue a voice prompt, prompting the user to output voice information about navigation. After the voice prompt is completed, the user speaks the voice information within five seconds; S304: The user promptly inputs all voice information for the navigation service as a condition for the vehicle navigation input. If the voice interaction system exceeds five seconds, it will be closed and needs to be reactivated.

6. The vehicle navigation voice interaction method according to claim 1, characterized in that: The step S4 comprises the following steps: S401, the analysis and processing flow in the voice recognition module is to identify the input voice to determine whether it is the user himself. If it is the user himself, the information is received and the processed voice is further extracted to obtain valid information. Otherwise, the voice information is not accepted; S402, matching the valid information with the data in the template library, the data in the template library is generated in advance by training and classifying a large amount of voice data, comparing the voice data with the data in the template library, finding the file in the template library with the highest matching degree with the data, and returning the similarity between the two files; S403, if the similarity between the two files is greater than a preset confidence level, receiving the data and outputting a recognition result; if the similarity is not greater than the preset confidence level, the recognition fails; S404: After the recognition result is obtained, the vehicle navigation application is called according to the recognition result, otherwise the voice interaction service module calls the voice synthesis module to announce the reason for the failure of recognition.

7. The vehicle navigation voice interaction method according to claim 1, characterized in that: The step S5 comprises the following steps: S501, the vehicle navigation obtains the current location of the vehicle through GPS positioning, and at the same time shifts the center of the map to the current location of the vehicle, displays the current area of ​​the vehicle, and marks it on the map as the starting point; S502, transmitting the voice command output by the user to the in-vehicle navigation system, wherein the voice command must include the target location, and performing route planning using the geographic information contained in the electronic map, searching for multiple routes from the starting location to the target location, and marking them on the map; S503, while the route is displayed on the in-vehicle navigation electronic map, the voice interaction service module calls the voice synthesis module to broadcast the route that best matches the user's needs and is closest, and starts the navigation mode after the user confirms; S504: The user adjusts the electronic map according to actual needs. When the user needs to use the in-vehicle navigation, the user guides the in-vehicle navigation through voice commands to form a navigation route, zooms out the map to view the entire driving area, and zooms in the map to view detailed information on the route.

8. A vehicle navigation voice interaction device, the vehicle navigation voice interaction device having a vehicle navigation voice interaction method according to any one of 1 to 7, characterized in that: include: A user identity confirmation unit, which extracts audio feature parameters from voice information for training and stores the training results in a voiceprint library. During identity recognition, the trained audio feature parameters are used as reference templates to match the audio feature parameters extracted from the user in real time to determine the user's identity; A user navigation interaction unit, wherein the user navigation interaction unit enables the user to interact with the in-vehicle navigation through a voice interaction system in the in-vehicle navigation, wherein the voice interaction system includes a voice interaction service module, an audio task control module, a voice synthesis module, and a voice recognition module; A voice information input unit, wherein the voice information input unit selects a method of waking up the voice interaction system according to the noise environment in the vehicle and the driving conditions, and the voice interaction service module calls the voice synthesis module to issue a voice prompt, prompting the user to input voice information about navigation, and then the user promptly outputs all voice information requiring navigation services; A speech recognition unit, which continuously detects the power of the speech signal, continuously records the speech through the vehicle recording device, collects the received speech and transmits the speech information to the speech recognition module; The navigation path broadcasting unit uses the geographic information contained in the electronic map to plan the path, searches for multiple paths from the starting point to the target point, and broadcasts the optimal path, and starts the navigation mode after the user confirms.

Images