阅读说明：本技术 一种车载语音操作系统人机互动方法及装置 (Human-computer interaction method and device for vehicle-mounted voice operating system ) 是由 胡凯文 胡世民 于 2021-07-26 设计创作，主要内容包括：本发明公开了一种车载语音操作系统人机互动方法及装置,通过语音唤醒,启动车载语音操作系统,在车内安装的多个语音收发器,用于收集多音源的声音,并将收集到的音频发送至音频处理器进行处理,得到用户语音数据；并对无法识别的语音进行重新匹配加入到新增语音指令中,便于以后人员再次使用该指令时,语音系统能够进行识别并作出相应动作,避免因用户使用方言而导致同一语句多次使用时系统无法解析而降低用户体验感,使得语音系统更加完善；在语音解析识别过程中,用户新增的语音指令数据保存在本地数据库中,具有较好的私密性；系统优先与本地数据进行比对,便于实现快速查询比对,提升运行效率。(The invention discloses a man-machine interaction method and a man-machine interaction device for a vehicle-mounted voice operating system, wherein the vehicle-mounted voice operating system is started through voice awakening, and a plurality of voice transceivers are arranged in a vehicle and used for collecting the sound of a plurality of sound sources and sending the collected audio to an audio processor for processing to obtain user voice data; the voice which cannot be recognized is re-matched and added into the newly added voice command, so that when the command is used again by later personnel, the voice system can recognize and make corresponding actions, the phenomenon that the system cannot be analyzed when the same statement is used for multiple times due to dialect use of a user is avoided, and the user experience is reduced, and the voice system is more perfect; in the voice analysis and recognition process, the newly added voice instruction data of the user is stored in the local database, so that the privacy is better; the system is preferentially compared with local data, so that quick query and comparison are conveniently realized, and the operation efficiency is improved.)

1. A man-machine interaction method for a vehicle-mounted voice operating system is characterized by comprising the following steps:

s1: voice awakening, wherein personnel in the vehicle starts a vehicle-mounted voice operating system by using an appointed awakening statement;

s2: a plurality of voice transceivers are arranged in the vehicle and used for collecting sound and sending collected audio to an audio processor for processing to obtain user voice data;

s3: recognizing and judging semantics of the user voice, executing S4 if the semantics recognition is successful, and setting the signal identification int _ flag _ a which cannot be recognized to be 0; if the semantics can not be identified, reminding the user to speak again, storing the speech data which can not be identified at this time into a local speech database, setting the signal identification int _ flag _ a which can not be identified to be 1, and returning to the step S2;

s4: displaying an instruction recognized by the vehicle-mounted voice operating system on a display, detecting a mark value of a signal which cannot be recognized, if a signal mark int _ flag _ a which cannot be recognized is 0, indicating that the system records no semantic meaning which cannot be recognized, and executing S6; if the signal identification int _ flag _ a which cannot be recognized is 1, the system records that the semantic meaning which cannot be recognized exists, and inquires whether to enter a voice instruction adding module or not;

s5: if the user selects to enter the voice instruction adding module in the step S4, the voice operating system matches and associates the unrecognized instruction stored in the current local voice database with the instruction successfully recognized this time and stores the unrecognized instruction in the online voice database, so as to expand the statement instruction, which is convenient for the system to complete recognition when the user uses the unrecognized statement instruction again next time; if the user chooses not to enter the voice command adding module in the S4, the voice operating system deletes the unrecognized command stored in the current local voice data and then executes the S6;

s6: the person determines whether to execute the identified command, and if so, executes S7; if not, this proceeds to S9;

s7: the voice system automatically matches the voice command with an action command in the system, and sends the matched action command to a central processing unit of the automobile;

s8: after receiving the action instruction, the central processing unit controls the relevant equipment to act;

s9: and finishing the voice operation, and enabling the vehicle-mounted voice operating system to enter a state to be awakened.

2. The human-computer interaction method of the vehicle-mounted voice operating system according to claim 1, wherein the audio processor is used for removing impurities and filtering, separating sounds of different sound sources, converting a voice file into a text file and displaying the text file on the display.

3. The human-computer interaction method and device of the vehicular voice operating system according to claim 1, wherein in the step S3, the semantic meaning is that the audio processor parses the segmented and integrated data, and if the integrated data can be formatted as a standard sentence, the semantic meaning is recognizable; if the integrated data can not be formatted into standard sentences, the semantics can not be identified, for example, the host vehicle system does not contain equipment needing action mentioned in the voice.

4. The man-machine interaction method of the vehicle-mounted voice operating system according to claim 1, wherein the voice command and the action command are in a many-to-one relationship, so that after a new voice command is added, the new voice command is used for controlling equipment to act.

5. The vehicle-mounted voice operating system human-computer interaction method according to claim 1, wherein the device action in step S8 is a response of a hardware device or a software stop/start operation.

6. A man-machine interaction device of a vehicle-mounted voice operating system is characterized by comprising a voice transceiver, a data memory, a display, a key, an audio processor, a network communicator based on an SIM card, a vehicle-mounted central controller and a background server.

7. The human-computer interaction device of claim 6, wherein the plurality of voice transceivers are at least four microphones distributed around the interior of the vehicle for receiving the sound signals from multiple locations.

8. The human-computer interaction device of claim 6, wherein the data storage comprises the following data categories: the voice database comprises a local database and an online database, wherein the local voice database is a temporary area and is used for storing voice data which cannot be identified in the operation process of the system, and the data in the temporary area is lost when power failure occurs; and the other area is a storage area which is used for storing newly added voice data after the matching is successful and participating in voice comparison traversal.

9. The vehicle-mounted voice operating system human-computer interaction device as claimed in any one of claims 6 to 8, wherein the number of the keys is at least five, the keys are all located on a steering wheel of a vehicle and have functions of page turning and confirmation, and the display is a touch screen.

Technical Field

The invention relates to the technical field of human-computer voice interaction systems, in particular to a human-computer interaction method and device for a vehicle-mounted voice operating system.

Background

The automobile operating system is used as the brain of an automobile, the related technology is continuously improved, but the automobile operating system on the market has not enough subversive user experience all the time, and the biggest reason is that a user needs to perform a plurality of manual operations, and the manual operations require the user to divert attention and time when the user drives the automobile, which is not only not convenient for the user, but also sometimes fatal to the behavior of driving, which particularly needs the user to pay attention.

The continuous maturity of voice recognition and control technology is more widely applied to various fields, and more intelligent operating systems of automobiles begin to use the voice recognition and control technology. However, there are still some problems to be solved when the existing speech recognition and control technology is applied to the operating system.

In order to solve the problems, people begin to research a vehicle-mounted man-machine voice interaction system, after a voice command sent by a person is processed by the vehicle-mounted voice interaction system, the system guides a vehicle-mounted device to perform relevant actions, so that the operation steps of the person are simplified, the actions of the person on hand are reduced, a driver can be more attentive to driving work, the attention is improved, and the probability of traffic accidents caused by distraction of the driver can be effectively reduced. However, the existing vehicle-mounted system has some disadvantages, because the vehicle-mounted voice operating system encodes voice information and compares the encoded voice information with a voice database to query out a related mechanical instruction after receiving a voice instruction of a person, so as to guide a machine to act, if a driver or other persons in the vehicle use dialects to perform human-computer interaction, the system often cannot make a corresponding action because the voice content cannot be recognized, and the use experience of the person is affected.

Disclosure of Invention

The invention aims to solve the defects in the prior art and provides a man-machine interaction method and a man-machine interaction device for a vehicle-mounted voice operating system.

The invention provides a man-machine interaction method of a vehicle-mounted voice operating system, which comprises the following steps:

s1: voice awakening, wherein personnel in the vehicle starts a vehicle-mounted voice operating system by using an appointed awakening statement;

s2: a plurality of voice transceivers are arranged in the vehicle and used for collecting sound and sending collected audio to an audio processor for processing to obtain user voice data;

s3: recognizing and judging semantics of the user voice, executing S4 if the semantics recognition is successful, and setting the signal identification int _ flag _ a which cannot be recognized to be 0; if the semantics can not be identified, reminding the user to speak again, storing the speech data which can not be identified at this time into a local speech database, setting the signal identification int _ flag _ a which can not be identified to be 1, and returning to the step S2;

s4: displaying an instruction recognized by the vehicle-mounted voice operating system on a display, detecting a mark value of a signal which cannot be recognized, if a signal mark int _ flag _ a which cannot be recognized is 0, indicating that the system records no semantic meaning which cannot be recognized, and executing S6; if the signal identification int _ flag _ a which cannot be recognized is 1, the system records that the semantic meaning which cannot be recognized exists, and inquires whether to enter a voice instruction adding module or not;

s5: if the user selects to enter the voice instruction adding module in the step S4, the voice operating system matches and associates the unrecognized instruction stored in the current local voice database with the instruction successfully recognized this time and stores the unrecognized instruction in the online voice database, so as to expand the statement instruction, which is convenient for the system to complete recognition when the user uses the unrecognized statement instruction again next time; if the user chooses not to enter the voice command adding module in the S4, the voice operating system deletes the unrecognized command stored in the current local voice data and then executes the S6;

s6: the person determines whether to execute the identified command, and if so, executes S7; if not, this proceeds to S9;

s7: the voice system automatically matches the voice command with an action command in the system, and sends the matched action command to a central processing unit of the automobile;

s8: after receiving the action instruction, the central processing unit controls the relevant equipment to act;

s9: and finishing the voice operation, and enabling the vehicle-mounted voice operating system to enter a state to be awakened.

Preferably, the audio processor is used for removing impurity and filtering, separating sounds of different sound sources, and converting the voice file into a text file to be displayed on the display.

Preferably, in step S3, the semantics is that the audio processor parses the segmented and integrated data, and if the integrated data can be formatted into a standard sentence, it indicates that the semantics are recognizable; if the integrated data can not be formatted into standard sentences, the semantics can not be identified.

Preferably, the voice command and the action command are in a many-to-one relationship, so that after a new voice command is added, the new voice command is used for controlling the equipment to act.

Preferably, the device action in step S8 is a response by the hardware device or a software stop/start operation.

A man-machine interaction device of a vehicle-mounted voice operating system comprises a voice transceiver, a data memory, a display, a key, an audio processor, a network communicator based on an SIM card, a vehicle-mounted central controller and a background server.

Preferably, the voice transceivers are microphones, and the number of the microphones is at least four, and the microphones are distributed and installed around the inside of the vehicle.

Preferably, the data store contains the following data categories: the voice database comprises a local database and an online database, wherein the local voice database is a temporary area and is used for storing voice data which cannot be identified in the operation process of the system, and the data in the temporary area is lost when power failure occurs; and the other area is a storage area which is used for storing newly added voice data after the matching is successful and participating in voice comparison traversal.

Preferably, the number of the keys is at least five, the keys are all positioned on a steering wheel of the vehicle, and the display is a touch screen.

The invention has the beneficial effects that:

the vehicle-mounted voice operating system is started through the voice awakening function of the personnel, and the plurality of voice transceivers arranged in the vehicle are used for collecting the sound of a plurality of sound sources and sending the collected audio to the audio processor for processing to obtain the voice data of the user; the voice which cannot be recognized is re-matched and added into the newly added voice command, so that when the command is used again by later personnel, the voice system can recognize and make corresponding actions, the phenomenon that the system cannot be analyzed when the same statement is used for multiple times due to dialect use of a user is avoided, and the user experience is reduced, and the voice system is more perfect; in the voice analysis and recognition process, the user can give up semantic matching to achieve selectivity of the system, newly-added voice instruction data of the user are stored in the local database, the privacy is good, the system is preferentially compared with the local data during data comparison, fast query comparison is achieved conveniently, and operation efficiency is improved.

Drawings

FIG. 1 is a flowchart illustrating a man-machine interaction method of a vehicle-mounted voice operating system according to the present invention;

FIG. 2 is a block diagram of a human-computer interaction device of a vehicle-mounted voice operating system according to the present invention;

fig. 3 is a database block diagram of a vehicle-mounted voice operating system human-computer interaction device according to the present invention.

Detailed Description

Reference will now be made in detail to embodiments of the present patent, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present patent and are not to be construed as limiting the present patent.

In the description of this patent, it is to be understood that the terms "center," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in the orientations and positional relationships indicated in the drawings for the convenience of describing the patent and for the simplicity of description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are not to be considered limiting of the patent.

In the description of this patent, it is noted that unless otherwise specifically stated or limited, the terms "mounted," "connected," and "disposed" are to be construed broadly and can include, for example, fixedly connected, disposed, detachably connected, disposed, or integrally connected and disposed. The specific meaning of the above terms in this patent may be understood by those of ordinary skill in the art as appropriate.

Referring to fig. 1-3, a man-machine interaction method for a vehicle-mounted voice operating system includes the following steps:

s1: voice awakening, wherein personnel in the vehicle starts a vehicle-mounted voice operating system by using an appointed awakening statement;

s2: a plurality of voice transceivers are arranged in the vehicle and used for collecting sound and sending collected audio to an audio processor for processing to obtain user voice data;

s3: recognizing and judging semantics of the user voice, executing S4 if the semantics recognition is successful, and setting the signal identification int _ flag _ a which cannot be recognized to be 0; if the semantics can not be identified, reminding the user to speak again, storing the speech data which can not be identified at this time into a local speech database, setting the signal identification int _ flag _ a which can not be identified to be 1, and returning to the step S2;

s4: displaying an instruction recognized by the vehicle-mounted voice operating system on a display, detecting a mark value of a signal which cannot be recognized, if a signal mark int _ flag _ a which cannot be recognized is 0, indicating that the system records no semantic meaning which cannot be recognized, and executing S6; if the signal identification int _ flag _ a which cannot be recognized is 1, the system records that the semantic meaning which cannot be recognized exists, and inquires whether to enter a voice instruction adding module or not;

s5: if the user selects to enter the voice instruction adding module in the step S4, the voice operating system matches and associates the unrecognized instruction stored in the current local voice database with the instruction successfully recognized this time and stores the unrecognized instruction in the online voice database, so as to expand the statement instruction, which is convenient for the system to complete recognition when the user uses the unrecognized statement instruction again next time; if the user chooses not to enter the voice command adding module in the S4, the voice operating system deletes the unrecognized command stored in the current local voice data and then executes the S6;

s6: the person determines whether to execute the identified command, and if so, executes S7; if not, this proceeds to S9;

s7: the voice system automatically matches the voice command with an action command in the system, and sends the matched action command to a central processing unit of the automobile;

s8: after receiving the action instruction, the central processing unit controls the relevant equipment to act;

s9: and finishing the voice operation, and enabling the vehicle-mounted voice operating system to enter a state to be awakened.

In the invention, the audio processor is used for removing impurities and filtering, separating the sounds of different sound sources, converting a voice file into a text file and displaying the text file on the display.

In the invention, the semantics in the step S3 is that the audio processor analyzes the segmented and integrated data, and if the integrated data can be formatted into standard sentences, the semantics can be identified; if the integrated data can not be formatted into standard sentences, the semantics can not be identified, for example, the host vehicle system does not contain equipment needing action mentioned in the voice.

In the invention, the voice command and the action command are in a many-to-one relationship, so that the new voice command is used for controlling the equipment to act after the new voice command is added.

In the present invention, the device action in step S8 is a response by the hardware device or a software stop/start operation.

A man-machine interaction device of a vehicle-mounted voice operating system comprises a voice transceiver, a data memory, a display, a key, an audio processor, a network communicator based on an SIM card, a vehicle-mounted central controller and a background server.

In the invention, the voice transceivers are microphones, and the number of the microphones is at least four, and the microphones are distributed and installed around the interior of the vehicle and used for receiving sound signals of multiple positions.

In the present invention, the data storage includes the following data categories: the voice database comprises a local database and an online database, wherein the local voice database is a temporary area and is used for storing voice data which cannot be identified in the operation process of the system, and the data in the temporary area is lost when power failure occurs; and the other area is a storage area which is used for storing newly added voice data after the matching is successful and participating in voice comparison traversal.

In the invention, the number of the keys is at least five, the keys are all positioned on a steering wheel of a vehicle and have the functions of browsing and confirming, and the display is a touch screen.

The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.