CN115223556B - Self-feedback type vehicle voice control method and system - Google Patents
Self-feedback type vehicle voice control method and system Download PDFInfo
- Publication number
- CN115223556B CN115223556B CN202210680163.3A CN202210680163A CN115223556B CN 115223556 B CN115223556 B CN 115223556B CN 202210680163 A CN202210680163 A CN 202210680163A CN 115223556 B CN115223556 B CN 115223556B
- Authority
- CN
- China
- Prior art keywords
- voice control
- user
- vehicle
- intention
- instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000008569 process Effects 0.000 claims abstract description 25
- 238000012790 confirmation Methods 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000005484 gravity Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000007664 blowing Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Traffic Control Systems (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
Abstract
The invention relates to a self-feedback type vehicle voice control method and system, wherein the system comprises an instruction receiving module for receiving a voice control instruction by a user, an analysis module for analyzing the intention of the voice control instruction by the user, a sending module for sending an operation instruction corresponding to an intention result obtained by analysis to a vehicle machine Tbox by the user, and a cloud storage recording module for storing the whole process, the analysis result and data; according to the scheme, efficient and rapid vehicle voice control can be effectively achieved, meanwhile, the vehicle MCU can learn and store voice control instructions sent by a user in a self-feedback mode, so that the user can use the vehicle conveniently, and the use experience is improved.
Description
Technical Field
The invention relates to the technical field of vehicle voice control, in particular to a self-feedback vehicle voice control method and system.
Background
At present, in the development of intelligent network vehicles, when passengers or drivers use a voice control function to control a vehicle or a vehicle engine Tbox, the situation that the vehicle cannot be identified or the error is identified easily occurs, so that the use experience is affected. In general, the same semantics are often influenced by factors such as language habits of different users, the same semantics have different intentions, the sent control instructions have less to-be-sent context information, the acquired information is often insufficient for the voice control function of the vehicle, and dialects and the like exist at the same time, so that the current voice control function of the vehicle is difficult to meet the personalized use requirements of the users.
In the invention patent CN105825845B, namely, an autonomous learning method of a vehicle-mounted voice recognition module, the voice recognition operation is universal through the autonomous learning of the vehicle-mounted voice recognition module, and a specific gravity monitoring and eliminating mechanism is introduced in the new instruction learning process of the cloud server: recording the instruction in the voice recognition library to be formally used as the instruction when the specific gravity reaches the threshold value, moving the instruction to the alternative library when the specific gravity of the instruction in the voice recognition library is reduced below the threshold value, and deleting the instruction when the long-term specific gravity of the instruction in the alternative library is 0; thus, the storage pressure of the voice recognition library can be reduced, and the voice recognition library is convenient to manage.
However, in the above solution, only the autonomous learning process of the identification module is described in detail, and the above-mentioned problems cannot be solved without making a related description about the content to be learned and the instruction issued by the user at the user side.
In the published application CN113160807a, a corpus updating method, a system thereof and a voice control device, speech texts are identified by processing semantic information, first prompt information for requesting a user to perform action teaching is output for unrecognizable speech texts, a plurality of default corpora corresponding to task operation information are obtained, and a corpus relation is established between the plurality of default corpora and the speech texts, so that continuous new increase of personalized data and corpus corpora based on the user is realized.
It can be seen how the main content of the above solution is to obtain the voice text content for use, and in contrast to the cases described above, the semantic text content cannot be read in many cases, so the above solution still cannot solve the technical problem.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a self-feedback type vehicle voice control method and a system which can efficiently and accurately identify a voice control instruction sent by a user so as to improve the use experience of the user.
In order to solve the technical problems, the technical scheme provided by the invention is as follows: the self-feedback vehicle voice control method comprises the following steps:
(1) The user sends out a voice control instruction;
(2) The MCU receives the voice control instruction and judges whether the voice control instruction is intended, if so, the operation of the user and the further voice control instruction within the preset time after the response of the instruction are recorded, and if not, the voice control instruction is marked and history mark data are matched;
(3) The MCU controls the vehicle Tbox to execute operation;
(4) If the vehicle Tbox is in error operation, the MCU receives an operation cancellation instruction sent by the user and returns to the step (2) until the user does not send the cancellation instruction;
(5) The operation ends.
In the above technical solution, a user first sends a required voice control command at any position in the vehicle, where the control command can be completed through the control of the vehicle engine Tbox, such as opening a vehicle door, a vehicle window, an audio device, and the like. Then, the audio receiver in the MCU is used for acquiring the voice control instruction, and the MCU analyzes the voice control instruction, so that the main analyzed content is the real intention of the voice control instruction. If the intention can be identified, the user operation and further voice control command within the preset time after the response of the start recording command can be started, so that the MCU can accurately control the vehicle Tbox to execute the operation when the same voice control command is received again. If the intention is not successfully identified, the MCU marks the voice control instruction and is matched with the marked historical mark data in the database, when the same voice control instruction is matched, a user is inquired whether the voice control instruction is matched in a display or audio mode, if yes, the intention is judged to be obtained through recognition, the new voice control instruction is recorded and is correspondingly matched with the original marked voice control instruction, and when the same voice control instruction is received again, the user can directly control the vehicle engine Tbox to execute operation without being inquired, so that the effect of self-feedback learning is achieved.
After confirming the intention of the user, the MCU can control the car machine Tbox to execute the operation. If the operation execution of the vehicle Tbox is wrong, the MCU can receive the operation cancellation command sent by the user, and the MCU firstly controls the vehicle technology Tbox to resume operation, and returns to the step (2) to perform intention recognition again until the user does not send the cancellation command.
Preferably, the MCU records the voice control instruction sent by the user, the recorded content comprises audio content, semantic text obtained through cloud analysis and a recognition result, the recognition result comprises intention, control rules and control quantity, the content recorded by the voice control instruction is limited, the audio content can be stored in a marked mode with the advantage of high matching performance, so that the audio content can be matched with a new voice control instruction sent by the user, the voice text can be stored in a marked mode with the advantage of high accuracy, and the user can be searched for intention confirmation permission in a text display mode when required.
In addition, in step (2), if the same voice control command is not matched, the user can choose to perform the method of manually controlling the vehicle machine Tbox to perform the purpose, and the MCU can record the execution process and match and save the recorded content with the sent voice control command, so that when the same voice control command is received again, the MCU stores the marked vehicle machine Tbox operation execution data, thereby facilitating the rapid completion of the voice control command sent by the user and achieving the final purpose.
Preferably, in the step (2), after the MCU identifies the intention of the user, the user may manually interact with the physical and mechanical device to confirm the intention, so as to ensure that the intention result obtained by the MCU analysis is identical to the intention of the user, thereby improving the use experience of the user.
If the MCU does not recognize the intention of the user, the user can also manually interact with the physical and mechanical equipment to enable the MCU to acquire the intention, and the MCU records the process, so that the MCU can confirm the intention of the user through other modes besides voice interaction, and the user can directly control the vehicle Tbox to execute operation without confirming when the user sends the same voice control instruction again.
Preferably, the physical and mechanical device comprises a vehicle central control button and a central control screen, so that a user can confirm intention by pressing the vehicle central control button, for example, when the MCU needs to confirm which button the intention of the user is to adjust, an inquiry request can be sent to the user, the user directly corresponds to the button needed for adjustment, the MCU records the process, when the same voice control instruction is sent again, the MCU can directly adjust the button, and in the central control screen, the user can adopt a touch option or a text input mode to enable the MCU to learn the correct intention.
Preferably, in step (2), the MCU records the scene information when the user issues the voice control command, where the scene information includes the geographic location, the vehicle speed, the distribution of personnel in the vehicle, the location of the user issuing the voice control command, the temperature inside and outside the vehicle, and the weather information, so as to further record each reference factor when the voice control command is issued, thereby improving accuracy and efficiency of analysis intention. For example, when users at different positions in the vehicle send out voice control instructions for opening the air conditioner to blow, the MCU needs to analyze which position of the air conditioner to blow, whether the air conditioner is just opened for blowing the air conditioner at the position of the user sending the voice control instructions is needed, and meanwhile, the user needs to carry out further interactive confirmation with the user by combining factors such as the temperature inside and outside the vehicle, the geographic position and the like, so that the use experience of the user can be greatly improved.
Preferably, in step (2), after the history flag data is matched, the intention of the voice control instruction is re-identified according to the newly matched history flag data rule, so that a self-feedback learning process can be realized, and the rule redefinition is completed.
Preferably, in step (4), after the user issues the cancel instruction twice, the user may choose to terminate the voice control operation and choose to manually control the vehicle Tbox, and the MCU records the manual control process and adds the manual control process to the history flag data rule, so that the user's autonomous selection operability can be improved.
The self-feedback vehicle voice control system comprises an instruction receiving module, an analysis module, a sending module and a cloud storage recording module which are arranged in the MCU.
The instruction receiving module is used for receiving a voice control instruction sent by a user and sending the instruction to the analysis module;
The analysis module analyzes the received voice control instruction to obtain an intention result of a user, and displays the intention result obtained by analysis to the user sending the voice control instruction for confirmation, if the intention result is confirmed, the analysis module records the operation of the user and the further voice control instruction within a preset time after the instruction is responded, and simultaneously sends confirmation information and the intention result to the sending module, and if the intention result is not confirmed, the analysis module marks the voice control instruction and matches historical mark data;
the sending module sends an operation instruction corresponding to the intention result to the vehicle-mounted machine Tbox for execution;
The cloud storage recording module stores the voice control instruction sent by the user, the intention result obtained through analysis by the analysis module and the execution content of the vehicle Tbox.
In the above technical solution, a user can send a voice control instruction to the MCU through the instruction receiving module, the analysis module in the MCU analyzes the received voice control instruction to obtain an intention result of the user, and repeatedly confirms the intention result with the user, if the recognition intention is incorrect, the history data can be matched through the internal marked record, and finally the sending module sends an operation instruction corresponding to the intention result to the vehicle engine Tbox for execution, and the cloud storage recording module stores the voice control instruction sent by the user, the intention result obtained by the analysis module and the execution content of the vehicle engine Tbox, so that after the user sends the same voice control instruction, the MCU can quickly react and control the vehicle engine Tbox to execute operation.
Preferably, the instruction receiving module is further configured to receive an operation cancellation instruction sent by the user, the instruction receiving module sequentially sends the operation cancellation information to the sending module after receiving the operation cancellation instruction, the sending module sends the information of canceling the operation to the vehicle Tbox to finish the operation, and the cloud storage recording module records the process, so that the user can control the voice control process in an autonomous selection manner, whether the voice control process is manually executed or not is selected according to the requirement, and the operation habit of the user is reserved in a manner recorded by the cloud storage recording module, so that the next reaction of the MCU is facilitated.
Preferably, the analysis module classifies the received voice control instruction into three types of identifiable, unrecognizable and erroneous voice recognition, and the cloud storage recording module correspondingly classifies the voice control instruction stored and recorded, so that the analysis module can conveniently search the voice control instruction marked by the history.
The analysis module is used for matching the content of the manual control vehicle Tbox with the previously sent voice control instruction after the voice control is canceled by the user, sending a request for matching or not to the user in a request mode, if the user selects the voice control instruction, the cloud storage recording module is used for storing the voice control instruction in correspondence with the content of the manual control vehicle Tbox, and if the user selects the voice control instruction, the cloud storage recording module is used for storing the content of the manual control vehicle Tbox.
Compared with the prior art, the scheme has the remarkable advantages that:
1. the scheme can effectively realize high-efficiency and rapid vehicle voice control, and improves the use experience of users;
2. In the scheme, the vehicle MCU can learn and store the voice control instruction sent by the user in a self-feedback mode, so that the repeated use of the user is facilitated, and the use experience is also improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of method steps of the present invention;
Fig. 2 is a block diagram of a system module according to the present invention.
Detailed Description
The following description of preferred embodiments of the present invention is provided in connection with the accompanying drawings, and it is to be understood that the preferred embodiments described herein are for the purpose of illustration and explanation only and are not intended to limit the invention thereto.
As shown in fig. 1, the self-feedback vehicle voice control method of the present invention includes the following steps:
(1) The user sends out a voice control instruction.
(2) The MCU receives the voice control instruction and judges whether the voice control instruction is intended, if so, the operation of the user and the further voice control instruction within the preset time after the response of the instruction are recorded, and if not, the voice control instruction is marked and the history mark data are matched.
The MCU records the voice control instruction sent by the user, the recorded content comprises audio content, semantic text obtained through cloud analysis and a recognition result, the recognition result comprises intention, control rules and control quantity, the content recorded by the voice control instruction is limited, the audio content can be stored in a marked mode with the advantage of high matching performance, the audio content can be matched with a new voice control instruction sent by the user, the voice text can be stored in a marked mode with the advantage of high accuracy, and the user can be searched for intention confirmation permission in a word display mode when needed.
If the same voice control instruction is not matched, the user can select to finish the purpose by manually controlling the execution mode of the vehicle machine Tbox, meanwhile, the MCU can record the execution process and match and save the recorded content with the sent voice control instruction, so that when the same voice control instruction is received again, the marked vehicle machine Tbox operation execution data are stored in the MCU, thereby being convenient for quickly finishing the voice control instruction sent by the user and achieving the final intention.
After the MCU identifies the intention of the user, the user can manually interact with the physical and mechanical equipment to confirm the intention, so that the intention result obtained by the MCU analysis is identical to the intention of the user, and the use experience of the user is improved.
If the MCU does not recognize the intention of the user, the user can also manually interact with the physical and mechanical equipment to enable the MCU to acquire the intention, and the MCU records the process, so that the MCU can confirm the intention of the user through other modes besides voice interaction, and the user can directly control the vehicle Tbox to execute operation without confirming when the user sends the same voice control instruction again. In addition, the physical and mechanical equipment comprises a vehicle central control button and a central control screen, so that a user can confirm intention by pressing the vehicle central control button, for example, when the MCU needs to confirm which button the intention of the user is to adjust, a query request can be sent to the user, the user directly corresponds to the button needed for adjustment, the MCU records the process, when the same voice control instruction is sent again, the MCU can directly adjust the button, and in the central control screen, the user can adopt a touch option or a text input mode to enable the MCU to learn the correct intention.
The MCU records scene information when a user sends out a voice control instruction, wherein the scene information comprises geographic positions, vehicle speeds, personnel distribution in a vehicle, the positions of the user sending out the voice control instruction, the temperature inside and outside the vehicle and weather information, so that various reference factors when the voice control instruction is sent out are further recorded, and the accuracy and the efficiency of analysis intention are improved. For example, when users at different positions in the vehicle send out voice control instructions for opening the air conditioner to blow, the MCU needs to analyze which position of the air conditioner to blow, whether the air conditioner is just opened for blowing the air conditioner at the position of the user sending the voice control instructions is needed, and meanwhile, the user needs to carry out further interactive confirmation with the user by combining factors such as the temperature inside and outside the vehicle, the geographic position and the like, so that the use experience of the user can be greatly improved.
After the history mark data is matched, the intention of the voice control instruction is re-identified according to the newly matched history mark data rule, so that a self-feedback learning process can be realized, and the rule is redefined.
(3) The MCU controls the vehicle Tbox to perform operations.
(4) If the vehicle Tbox is in error, the MCU receives the operation cancellation command sent by the user and returns to the step (2) until the user does not send the cancellation command.
After the user sends the cancellation command twice, the user can select to terminate the voice control operation and select to control the vehicle Tbox in a manual mode, and the MCU records the manual control process and adds the manual control process into the history mark data rule, so that the autonomous selection operability of the user can be improved.
(5) The operation ends.
In the above technical solution, a user first sends a required voice control command at any position in the vehicle, where the control command can be completed through the control of the vehicle engine Tbox, such as opening a vehicle door, a vehicle window, an audio device, and the like. Then, the audio receiver in the MCU is used for acquiring the voice control instruction, and the MCU analyzes the voice control instruction, so that the main analyzed content is the real intention of the voice control instruction. If the intention can be identified, the user operation and further voice control command within the preset time after the response of the start recording command can be started, so that the MCU can accurately control the vehicle Tbox to execute the operation when the same voice control command is received again. If the intention is not successfully identified, the MCU marks the voice control instruction and is matched with the marked historical mark data in the database, when the same voice control instruction is matched, a user is inquired whether the voice control instruction is matched in a display or audio mode, if yes, the intention is judged to be obtained through recognition, the new voice control instruction is recorded and is correspondingly matched with the original marked voice control instruction, and when the same voice control instruction is received again, the user can directly control the vehicle engine Tbox to execute operation without being inquired, so that the effect of self-feedback learning is achieved.
As shown in fig. 2, the self-feedback vehicle voice control system provided by the invention comprises an instruction receiving module, an analysis module, a sending module and a cloud storage recording module which are arranged in an MCU.
The instruction receiving module is used for receiving a voice control instruction sent by a user and sending the instruction to the analysis module; in addition, the instruction receiving module is further used for receiving an operation cancellation instruction sent by a user, the instruction receiving module sequentially sends operation cancellation information to the sending module after receiving the operation cancellation instruction, the sending module sends the operation cancellation information to the vehicle Tbox to finish operation, the cloud storage recording module records the process, and therefore the user can control the voice control process in an autonomous selection mode, whether the voice control process is manually executed or not is selected according to the requirement, and the operation habit of the user is reserved in a mode recorded by the cloud storage recording module, so that the next MCU reaction is facilitated.
The analysis module analyzes the received voice control instruction to obtain an intention result of the user, and displays the intention result obtained by analysis to the user sending the voice control instruction for confirmation, if the intention result is confirmed, the analysis module records the operation of the user and the further voice control instruction within a preset time after the instruction is responded, and simultaneously sends confirmation information and the intention result to the sending module, and if the intention result is not confirmed, the analysis module marks the voice control instruction and matches historical mark data.
The analysis module divides the received voice control instructions into three types of identifiable, unrecognizable and erroneous voice recognition, and the cloud storage recording module correspondingly classifies the voice control instructions stored and recorded, so that the analysis module can conveniently search the voice control instructions marked by the history.
The analysis module is used for matching the content of the manual control vehicle Tbox with the previously sent voice control instruction after the voice control is canceled by the user, sending a request for matching or not to the user in a request mode, if the user selects the voice control instruction, the cloud storage recording module is used for storing the voice control instruction in correspondence with the content of the manual control vehicle Tbox, and if the user selects the voice control instruction, the cloud storage recording module is used for storing the content of the manual control vehicle Tbox.
The sending module sends the operation instruction corresponding to the intention result to the car machine Tbox for execution.
The cloud storage recording module stores the voice control instruction sent by the user, the intention result obtained through analysis by the analysis module and the execution content of the vehicle Tbox.
In the above technical solution, a user can send a voice control instruction to the MCU through the instruction receiving module, the analysis module in the MCU analyzes the received voice control instruction to obtain an intention result of the user, and repeatedly confirms the intention result with the user, if the recognition intention is incorrect, the history data can be matched through the internal marked record, and finally the sending module sends an operation instruction corresponding to the intention result to the vehicle engine Tbox for execution, and the cloud storage recording module stores the voice control instruction sent by the user, the intention result obtained by the analysis module and the execution content of the vehicle engine Tbox, so that after the user sends the same voice control instruction, the MCU can quickly react and control the vehicle engine Tbox to execute operation.
Finally, it should be noted that: the foregoing is merely a preferred example of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method for controlling the voice of a self-feedback vehicle, comprising the steps of:
(1) The user sends out a voice control instruction;
(2) The MCU receives the voice control instruction and judges whether the intention is recognized, if the intention is recognized, the operation of the user and the further voice control instruction within the preset time after the response of the instruction is recorded, if the intention is not recognized, the voice control instruction is marked and history mark data are matched, when the same voice control instruction is matched, the user is inquired whether the voice control instruction is matched, if the intention is recognized, the voice control instruction is judged to be recognized and is matched and stored, and if the intention is not recognized, the history mark data are continuously matched; the MCU records a voice control instruction sent by a user, wherein the recorded content comprises audio content, semantic text obtained through cloud analysis and a recognition result, and the recognition result comprises intention, control rules and control quantity; if the same voice control instruction is not matched, the user can select to manually control the vehicle-mounted machine Tbox to execute, and record the executing process and match and store the voice control instruction;
(3) The MCU controls the vehicle Tbox to execute operation;
(4) If the vehicle Tbox is in error operation, the MCU receives an operation cancellation instruction sent by the user and returns to the step (2) until the user does not send the cancellation instruction;
(5) The operation ends.
2. The method according to claim 1, wherein in step (2), after the MCU recognizes the user's intention, the user performs intention confirmation by manually interacting with a physical mechanical device; if the MCU does not recognize the intention of the user, the user also interacts with the physical and mechanical equipment manually so that the MCU acquires the intention of the user, and the MCU records the process.
3. The method for controlling the voice of the self-feedback vehicle according to claim 2, wherein the physical and mechanical equipment comprises a vehicle central control button and a central control screen.
4. The method according to claim 1, wherein in the step (2), the MCU records scene information when the user issues the voice control command, the scene information including a geographical location, a vehicle speed, a distribution of personnel in the vehicle, a location of the user issuing the voice control command, an in-vehicle temperature, and weather information.
5. The self-feedback type vehicle voice control method according to claim 1, wherein in step (2), after the history flag data is matched, the intention of the voice control instruction is re-recognized according to the history flag data rule newly matched.
6. The voice control method of a self-feedback type vehicle according to claim 1, wherein in step (4), after the user issues a cancel command twice, the user can select to terminate the voice control operation and select to manually operate the vehicle Tbox, and the MCU records the manual operation and adds the manual operation to the history flag data rule.
7. The self-feedback vehicle voice control system is characterized by comprising an instruction receiving module, an analysis module, a sending module and a cloud storage recording module which are arranged in an MCU;
The instruction receiving module is used for receiving a voice control instruction sent by a user and sending the instruction to the analysis module;
The analysis module is used for analyzing the received voice control instruction to obtain an intention result of a user, displaying the intention result obtained by analysis to the user sending the voice control instruction for confirmation, if the intention result is confirmed, recording the operation of the user and further voice control instruction within a preset time after the instruction response by the analysis module, simultaneously sending confirmation information and the intention result to the sending module, if the intention result is not confirmed, marking the voice control instruction and matching historical marking data by the analysis module, and if the intention result is matched with the same voice control instruction, inquiring whether the user matches the voice control instruction by the MCU, if the intention result is confirmed, judging that the voice control instruction is recognized and matching and storing, and if the intention result is not confirmed, continuously matching the historical marking data; if the same voice control instruction is not matched, the user can select to manually control the vehicle Tbox to execute, and the MCU records the execution process and matches and stores the voice control instruction;
The sending module is used for sending an operation instruction corresponding to the intention result to the vehicle-mounted machine Tbox for execution;
the cloud storage recording module is used for storing a voice control instruction sent by a user, an intention result obtained by analysis of the analysis module and execution content of the vehicle Tbox;
The instruction receiving module is further configured to receive an operation cancellation instruction sent by a user, the instruction receiving module sequentially sends operation cancellation information to the sending module after receiving the operation cancellation instruction, the sending module sends information of cancellation operation to the vehicle Tbox to finish operation, and the cloud storage recording module records the process.
8. The self-feedback vehicle voice control system according to claim 7, wherein the analysis module classifies the received voice control command into three types of recognizable, unrecognizable and erroneous voice recognition, and the cloud storage recording module classifies the stored and recorded voice control command correspondingly;
The analysis module matches the content of the manual control vehicle Tbox with the previously sent voice control instruction after the user cancels the voice control, and sends a request for matching to the user in a request mode, if the user selects yes, the cloud storage recording module correspondingly stores the voice control instruction and the content of the manual control vehicle Tbox, and if the user selects no, the cloud storage recording module only stores the content of the manual control vehicle Tbox.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210680163.3A CN115223556B (en) | 2022-06-15 | 2022-06-15 | Self-feedback type vehicle voice control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210680163.3A CN115223556B (en) | 2022-06-15 | 2022-06-15 | Self-feedback type vehicle voice control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115223556A CN115223556A (en) | 2022-10-21 |
| CN115223556B true CN115223556B (en) | 2024-05-14 |
Family
ID=83607366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210680163.3A Active CN115223556B (en) | 2022-06-15 | 2022-06-15 | Self-feedback type vehicle voice control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115223556B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103982982A (en) * | 2014-05-05 | 2014-08-13 | 美的集团股份有限公司 | Control method of air conditioner, and air conditioner |
| CN108942925A (en) * | 2018-06-25 | 2018-12-07 | 珠海格力智能装备有限公司 | The control method and device of robot |
| CN112069015A (en) * | 2020-11-10 | 2020-12-11 | 鹏城实验室 | Instruction execution method and device for instruction simulator, terminal equipment and storage medium |
| FR3098631A1 (en) * | 2019-07-10 | 2021-01-15 | Do You Dream Up | Method and device for learning natural language at least one automated conversational device |
| WO2021180062A1 (en) * | 2020-03-09 | 2021-09-16 | 华为技术有限公司 | Intention identification method and electronic device |
| CN113611305A (en) * | 2021-09-06 | 2021-11-05 | 云知声（上海）智能科技有限公司 | Voice control method, system, device and medium in autonomous learning home scene |
-
2022
- 2022-06-15 CN CN202210680163.3A patent/CN115223556B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103982982A (en) * | 2014-05-05 | 2014-08-13 | 美的集团股份有限公司 | Control method of air conditioner, and air conditioner |
| CN108942925A (en) * | 2018-06-25 | 2018-12-07 | 珠海格力智能装备有限公司 | The control method and device of robot |
| FR3098631A1 (en) * | 2019-07-10 | 2021-01-15 | Do You Dream Up | Method and device for learning natural language at least one automated conversational device |
| WO2021180062A1 (en) * | 2020-03-09 | 2021-09-16 | 华为技术有限公司 | Intention identification method and electronic device |
| CN112069015A (en) * | 2020-11-10 | 2020-12-11 | 鹏城实验室 | Instruction execution method and device for instruction simulator, terminal equipment and storage medium |
| CN113611305A (en) * | 2021-09-06 | 2021-11-05 | 云知声（上海）智能科技有限公司 | Voice control method, system, device and medium in autonomous learning home scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115223556A (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108346430B (en) | Dialogue system, vehicle having dialogue system, and dialogue processing method | |
| US6598018B1 (en) | Method for natural dialog interface to car devices | |
| US9626966B2 (en) | Voice recognition query response systems and methods for generating query responses using information from a vehicle | |
| US10733994B2 (en) | Dialogue system, vehicle and method for controlling the vehicle | |
| WO2022057152A1 (en) | Voice interaction method, server, and computer-readable storage medium | |
| US10997974B2 (en) | Dialogue system, and dialogue processing method | |
| US10950233B2 (en) | Dialogue system, vehicle having the same and dialogue processing method | |
| US10991368B2 (en) | Dialogue system and dialogue processing method | |
| JP2000315096A (en) | Man-machine system provided with voice recognition device | |
| US10861460B2 (en) | Dialogue system, vehicle having the same and dialogue processing method | |
| CN113990299B (en) | Voice interaction method and device, server and readable storage medium thereof | |
| CN104603871B (en) | Method and apparatus for running the information system of for motor vehicle voice control | |
| CN108657186B (en) | Intelligent cockpit interaction method and device | |
| US20200258514A1 (en) | Dialogue system and dialogue processing method | |
| CN110503949A (en) | Conversational system, the vehicle with conversational system and dialog process method | |
| CN113696904B (en) | Processing method, device, equipment and medium for controlling vehicle based on gestures | |
| JP4749923B2 (en) | Voice guidance device | |
| CN110503947A (en) | Conversational system, the vehicle including it and dialog process method | |
| CN115223556B (en) | Self-feedback type vehicle voice control method and system | |
| CN113409117B (en) | Order processing method, device, server, vehicle terminal and readable storage medium | |
| CN110211576B (en) | Voice recognition method, device and system | |
| KR102487669B1 (en) | Dialogue processing apparatus, vehicle having the same and dialogue processing method | |
| CN116052671B (en) | Intelligent translator and translation method | |
| CN114550713A (en) | Dialogue system, vehicle, and dialogue system control method | |
| WO2022217621A1 (en) | Speech interaction method and apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |