Disclosure of Invention
Therefore, an intelligent voice control system and method for an electric vehicle, which meet the requirement of multi-terminal voice signal input and increase accuracy of voice recognition, are needed.
In order to achieve the purpose, the intelligent electric automobile voice control system comprises a vehicle-mounted host, a microphone, a mobile terminal and a cloud platform;
the microphone and the mobile terminal are connected with the vehicle-mounted host; the vehicle-mounted host and the mobile terminal are communicated with the cloud platform;
the microphone is used for acquiring user voice information and transmitting the user voice information to the vehicle-mounted host;
the mobile terminal is used for acquiring voice information of a user, analyzing the voice information, transmitting an analysis result to the vehicle-mounted host computer and transmitting the voice information to the cloud platform;
the vehicle-mounted host is used for analyzing the voice information acquired by the microphone, sending the voice information acquired by the microphone to the cloud platform, checking the analyzed voice information and the voice information analyzed by the cloud platform, and executing the voice information when the checking is consistent;
and the cloud platform is used for analyzing the received voice information and sending an analysis result to the vehicle-mounted host or the mobile terminal.
Further optimize, the mobile terminal is used for obtaining user voice information, analyzing the voice information, transmitting an analysis result to the vehicle-mounted host, and transmitting the voice information to the cloud platform specifically includes:
the mobile terminal is used for acquiring voice information of a user, analyzing the voice information and transmitting an analysis result to the vehicle-mounted host, the vehicle-mounted host judges the analyzed voice information, and when the vehicle-mounted host judges that the analyzed voice information can be executed, the vehicle-mounted host executes the analyzed voice information; and when the vehicle-mounted host judges that the analyzed voice information cannot be executed, the analyzed voice information is fed back to the mobile terminal, and the mobile terminal sends the voice information analyzed by the cloud platform to the vehicle-mounted host for execution.
Further optimizing, the vehicle-mounted host is also used for storing the sound characteristic value of the user in a local voice library when the user registers for the first time, and simultaneously sending the sound characteristic value to the cloud platform and storing the sound characteristic value in the cloud voice library.
Further optimization, the mobile terminal is connected with the vehicle-mounted host through a Bluetooth mode.
And further optimizing, wherein the mobile terminal and the vehicle-mounted host are communicated with the cloud platform through a 4G network.
Still provide another scheme an intelligent electric automobile speech control method, including:
the method comprises the steps that voice information of a user is obtained through a microphone or a mobile terminal, the microphone transmits the voice information to a vehicle-mounted host, the mobile terminal analyzes the voice information, transmits an analysis result to the vehicle-mounted host and transmits the voice information to a cloud platform;
the cloud platform analyzes the received voice information and sends an analysis result to the vehicle-mounted host or the mobile terminal;
the vehicle-mounted host analyzes the voice information acquired by the microphone, simultaneously sends the voice information acquired by the microphone to the cloud platform, proofreads the analyzed voice information and the voice information analyzed by the cloud platform, and executes the voice information when the proofreads are consistent.
Further optimize, "the mobile terminal analyzes voice information, and transmits the analysis result to the on-vehicle host computer, transmits voice information to the high in the clouds platform" simultaneously specifically includes:
the mobile terminal analyzes the voice information and transmits an analysis result to the vehicle-mounted host, the vehicle-mounted host judges the analyzed voice information, and when the vehicle-mounted host judges that the analyzed voice information can be executed, the vehicle-mounted host executes the analyzed voice information; and when the vehicle-mounted host judges that the analyzed voice information cannot be executed, the analyzed voice information is fed back to the mobile terminal, and the mobile terminal sends the voice information analyzed by the cloud platform to the vehicle-mounted host for execution.
Further optimizing, the vehicle-mounted host is also used for storing the sound characteristic value of the user in a local voice library when the user registers for the first time, and simultaneously sending the sound characteristic value to the cloud platform and storing the sound characteristic value in the cloud voice library.
Further optimization, the mobile terminal is connected with the vehicle-mounted host through a Bluetooth mode.
And further optimizing, wherein the mobile terminal and the vehicle-mounted host are communicated with the cloud platform through a 4G network.
Different from the prior art, the technical scheme can carry out voice input through the microphone, transmit the voice input to the vehicle-mounted host for analysis, simultaneously carry out voice input through the mobile terminal, and send the analyzed result to the vehicle-mounted host after the mobile terminal analyzes, so that a multi-element input mode is realized, the requirement of carrying out voice input at multiple ends of a user is met, and the voice input is flexible and diverse; and synchronous analysis is carried out through the cloud platform, and analysis results are corrected, so that the accuracy of voice recognition is improved, and the condition of voice recognition errors is reduced.
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Referring to fig. 1, the intelligent electric vehicle voice control system of the present embodiment includes a vehicle-mounted host 120, a microphone 140, a mobile terminal 130, and a cloud platform 110; the microphone 140 and the mobile terminal 130 are connected with the vehicle-mounted host computer 120; the in-vehicle host 120 and the mobile terminal 130 communicate with the cloud platform 110; the microphone 140 is used for acquiring user voice information and transmitting the user voice information to the on-board host 120; the mobile terminal 130 is configured to obtain voice information of a user, analyze the voice information, transmit an analysis result to the vehicle-mounted host 120, and transmit the voice information to the cloud platform 110; the on-board host 120 is configured to analyze the voice information acquired by the microphone 140, send the voice information acquired by the microphone 140 to the cloud platform 110, collate the analyzed voice information with the voice information analyzed by the cloud platform 110, and execute the voice information when the collation is consistent; the cloud platform 110 is configured to analyze the received voice information, and send an analysis result to the in-vehicle host 120 or the mobile terminal 130.
When the user uses the voice recognition method for the first time, in the process of registration, the voice characteristic value of the user is stored in a local voice library of the vehicle-mounted host 120 and a cloud voice library of the cloud platform 110, wherein the local voice library and the cloud voice library are deployed for voice storage at the same time; when a user inputs voice through the microphone 140, the microphone 140 transmits an acquired voice signal to the vehicle-mounted host 120, the vehicle-mounted host 120 analyzes the voice signal and sends the voice signal to the cloud platform 110, the cloud platform 110 simultaneously analyzes the voice signal, and after the vehicle-mounted host 120 analyzes the voice signal, a local voice feature code is extracted from a local voice library according to an analysis result; after the cloud platform 110 analyzes the voice signal, extracting a cloud voice feature code from a cloud voice library according to an analysis result, sending the extracted cloud voice feature code to the vehicle-mounted host 120 by the cloud platform 110, comparing the local voice feature code with the cloud feature code by the vehicle-mounted host 120, and executing the vehicle-mounted host 120 according to the voice feature code when the local voice feature code is consistent with the cloud feature code; when the two are not consistent, the on-board host 120 makes a re-acquisition choice. When a user inputs voice through the mobile terminal 130, the mobile terminal 130 acquires a voice signal of the user, analyzes the voice signal at the mobile terminal 130, and simultaneously uploads the voice signal to the cloud platform 110 for analysis, the cloud platform 110 sends an analysis result to the mobile terminal 130, the mobile terminal 130 sends the analysis result of the voice signal and the analysis result of the cloud platform 110 to the vehicle-mounted host 120, and the vehicle-mounted host 120 executes the analysis according to the two results.
The voice input is carried out through the microphone 140 and is transmitted to the vehicle-mounted host computer 120 for analysis, meanwhile, the voice input can also be carried out through the mobile terminal 130, after the analysis is carried out through the mobile terminal 130, the analyzed result is transmitted to the vehicle-mounted host computer 120, a multi-input mode is realized, the requirement of carrying out the voice input at multiple ends of a user is met, and the voice input is flexible and various; and the synchronous analysis of the cloud platform 110 is performed, and the analysis result is corrected, so that the accuracy of voice recognition is improved, and the condition of voice recognition errors is reduced.
In the embodiment, in order to improve the execution of the voice recognition of the mobile terminal 130, the situation that the recognition is not accurate due to insufficient voice storage of the voice library of the mobile terminal 130 itself is avoided. The step of "the mobile terminal 130 is configured to acquire the voice information of the user, analyze the voice information, transmit an analysis result to the vehicle-mounted host 120, and transmit the voice information to the cloud platform 110" specifically includes: the mobile terminal 130 is configured to acquire user voice information, parse the voice information, and transmit a parsing result to the on-board host 120, where the on-board host 120 determines the parsed voice information, and when the on-board host 120 determines that the parsed voice information can be executed, the on-board host 120 executes the parsed voice information; when the in-vehicle host 120 determines that the analyzed voice information cannot be executed, the analyzed voice information is fed back to the mobile terminal 130, and the mobile terminal 130 sends the voice information analyzed by the cloud platform 110 to the in-vehicle host 120 for execution. Because of the limitation of the self storage of the mobile terminal 130, the voice storage of the mobile terminal 130 is not rich in the voice library of the cloud terminal platform 110, and a situation of recognition error through the mobile terminal 130 may occur, when the vehicle-mounted host 120 recognizes that the voice signal analyzed by the mobile terminal 130 cannot be executed, the voice signal is fed back to the mobile terminal 130, the mobile terminal 130 reacts, the voice analysis result of the cloud terminal platform 110 is sent to the vehicle-mounted host 120 to be executed, and the situation of voice recognition error caused by the limitation of the mobile terminal 130 is avoided.
In this embodiment, for the convenience of the user to perform voice input through the mobile terminal 130, the mobile terminal 130 includes a smart phone or a tablet computer. With the popularization of smart phones and tablet computers, users can conveniently input voice through software installed on the smart phones or the tablet computers and hardware of the smart phones or the tablet computers.
In the present embodiment, in order to make the connection between the
mobile terminal 130 and the in-
vehicle host 120 smooth and enable quick information transmission therebetween, the
mobile terminal 130 is connected to the in-
vehicle host 120 through a bluetooth mode. Bluetooth
The wireless technology standard can realize short-distance data exchange (using UHF radio waves of ISM wave band of 2.4-2.485 GHz) between fixed equipment, mobile equipment and a building personal area network. The standard for bluetooth is IEEE802.15, operating in the 2.4GHz band, with a bandwidth of 1 Mb/s. The
mobile terminal 130 and the in-
vehicle host 120 can be smoothly connected, so that information can be rapidly transmitted therebetween.
In this embodiment, in order to enable the in-vehicle host 120 and the mobile terminal 130 to quickly perform information transmission with the cloud platform 110, the mobile terminal 130 and the in-vehicle host 120 communicate with the cloud platform 110 through a 4G network. The 4G integrates 3G and WLAN, and can quickly transmit data, high-quality audio, video, images and the like. 4G can be downloaded at a rate of over 100Mbps, 25 times faster than current home broadband ADSL (4 megabits).
Referring to fig. 2, another embodiment of the voice control method for an intelligent electric vehicle includes: the method comprises the steps that voice information of a user is obtained through a microphone or a mobile terminal, the microphone transmits the voice information to a vehicle-mounted host, the mobile terminal analyzes the voice information, transmits an analysis result to the vehicle-mounted host and transmits the voice information to a cloud platform;
the cloud platform analyzes the received voice information and sends an analysis result to the vehicle-mounted host or the mobile terminal;
the vehicle-mounted host analyzes the voice information acquired by the microphone, simultaneously sends the voice information acquired by the microphone to the cloud platform, proofreads the analyzed voice information and the voice information analyzed by the cloud platform, and executes the voice information when the proofreads are consistent.
When the user uses the voice recognition method for the first time, in the process of registering, the voice characteristic value of the user is stored in a local voice library of the vehicle-mounted host and a cloud voice library of the cloud platform, wherein the local voice library and the cloud voice library are deployed for voice storage at the same time; when a user inputs voice through the microphone, the microphone transmits an acquired voice signal to the vehicle-mounted host, the vehicle-mounted host analyzes the voice signal and sends the voice signal to the cloud platform, the cloud platform analyzes the voice signal at the same time, and after the vehicle-mounted host analyzes the voice signal, a local voice feature code is extracted from a local voice library according to an analysis result; after the cloud platform analyzes the voice signal, extracting a cloud voice feature code from a cloud voice library according to an analysis result, sending the extracted cloud voice feature code to the vehicle-mounted host by the cloud platform, comparing the local voice feature code with the cloud feature code by the vehicle-mounted host, and executing the vehicle-mounted host according to the voice feature code when the local voice feature code is consistent with the cloud feature code; when the two are not consistent, the vehicle-mounted host computer makes a re-acquisition selection. When a user inputs voice through the mobile terminal, the mobile terminal acquires a voice signal of the user, analyzes the voice signal at the mobile terminal, and simultaneously uploads the voice signal to the cloud end platform for analysis, the cloud end platform sends an analyzed result to the mobile terminal, the mobile terminal sends the analyzed result of the voice signal and the analyzed result of the cloud end platform to the vehicle-mounted host, and the vehicle-mounted host executes the voice signal according to the two results.
The voice input is carried out through the microphone, and the voice input can also be carried out through the mobile terminal, so that the voice input is abundant, and the requirements of different conditions are met; and the voice signals are corrected through the cloud platform, so that the accuracy of voice recognition is improved.
In this embodiment, "the mobile terminal analyzes the voice message, and transmits the analysis result to the on-vehicle host computer, and transmits the voice message to the cloud platform" specifically includes: the mobile terminal analyzes the voice information and transmits an analysis result to the vehicle-mounted host, the vehicle-mounted host judges the analyzed voice information, and when the vehicle-mounted host judges that the analyzed voice information can be executed, the vehicle-mounted host executes the analyzed voice information; and when the vehicle-mounted host judges that the analyzed voice information cannot be executed, the analyzed voice information is fed back to the mobile terminal, and the mobile terminal sends the voice information analyzed by the cloud platform to the vehicle-mounted host for execution.
In this embodiment, the mobile terminal includes a smart phone or a tablet computer.
In this embodiment, the mobile terminal is connected to the vehicle-mounted host through a bluetooth mode.
In this embodiment, the mobile terminal and the in-vehicle host communicate with the cloud platform through a 4G network.
Although the embodiments have been described, once the basic inventive concept is obtained, other variations and modifications of these embodiments can be made by those skilled in the art, so that the above embodiments are only examples of the present invention, and not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes using the contents of the present specification and drawings, or any other related technical fields, which are directly or indirectly applied thereto, are included in the scope of the present invention.