CN113223535A - Vehicle-mounted voice skill real-time recommendation downloading system and method - Google Patents
Vehicle-mounted voice skill real-time recommendation downloading system and method Download PDFInfo
- Publication number
- CN113223535A CN113223535A CN202110301358.8A CN202110301358A CN113223535A CN 113223535 A CN113223535 A CN 113223535A CN 202110301358 A CN202110301358 A CN 202110301358A CN 113223535 A CN113223535 A CN 113223535A
- Authority
- CN
- China
- Prior art keywords
- voice
- skill
- voice skill
- module
- vehicle
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000004044 response Effects 0.000 claims description 36
- 238000013507 mapping Methods 0.000 claims description 23
- 239000000284 extract Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 abstract description 3
- 230000004069 differentiation Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- General Physics & Mathematics (AREA)
- Electrically Operated Instructional Devices (AREA)
- Navigation (AREA)
Abstract
The invention relates to the field of vehicle-mounted voice control, and particularly discloses a system and a method for downloading vehicle-mounted voice skill real-time recommendation, wherein through real-time intelligent recommendation of voice skill, a user can find a new function which cannot be identified by original voice control in time, effective guidance of the user for using the voice control is realized, and the intelligence and the practicability of a product are improved; the new requirements of the user can be accurately identified, more choices of personalized experience are provided for the user in real time, and the personalized experience of the product is improved; the real-time recommendation of the voice skills can also effectively solve the problem that the dynamic change requirements of users cannot be met due to the fact that the existing vehicle-mounted voice control system cannot update versions timely, and the differentiation competitiveness of products is improved; and a plurality of high-quality voice skill resources are aggregated, so that the value added value of operation is brought to the car factory.
Description
Technical Field
The invention relates to the field of vehicle-mounted voice control, in particular to a system and a method for recommending and downloading vehicle-mounted voice skills in real time.
Background
Along with the wide application of voice technology, at present in the vehicle control field, the application of voice assistant in the car is more and more common, and people rely on pronunciation to accomplish some simple vehicle control, brings the convenience of operation, but current on-vehicle voice control system has several problems: the existing vehicle-mounted voice control depends on an SDK or API interface, the number of functions for realizing the voice control is limited, and individual users often have various personalized requirements, so that the phenomenon that the individual users cannot recognize is often encountered when the vehicle-mounted voice control is used; the existing vehicle-mounted voice control system is difficult to update independently and timely after leaving factory, so that a user cannot experience a new function timely, if the new function needs to be added, the vehicle-mounted voice control system needs to be upgraded by means of OTA (over the air) and the like, and the cost for the user to use the new voice function is too high; different user preferences are different, the existing vehicle-mounted voice control function is fixed, a new function acquisition entrance does not exist, the new function is difficult to find and use in time, and personalized and diversified selection is lacked; even if the existing vehicle-mounted voice recognition system updates the function, the existing vehicle-mounted voice recognition system only aims at updating the voice command, but lacks the voice skill, namely the updating of voice control.
Disclosure of Invention
The invention provides a system and a method for recommending and downloading vehicle-mounted voice skills in real time, and solves the technical problems that the number of functions of an existing vehicle-mounted voice control system is limited, the existing vehicle-mounted voice control system is difficult to update after leaving a factory, and diversified choices are lacked. In order to solve the technical problems, the invention provides a vehicle-mounted voice skill real-time recommendation downloading system, which comprises: the system comprises a vehicle-end voice skill recommendation system and a background voice skill management center;
the vehicle-mounted voice skill recommendation system is used for identifying a voice instruction request of a user, judging whether the voice instruction request belongs to downloaded local voice skills, analyzing and matching the corresponding local downloaded voice skills if the voice instruction belongs to the downloaded local voice skills, sending the voice instruction to the background voice skill management center if the voice instruction does not belong to the downloaded local voice skills, receiving a voice skill recommendation result of the background voice skill management center, recommending cloud voice skills in real time, responding to the download request of the user, updating and storing the downloaded voice skills, and executing the downloaded voice skills;
the background voice skill management center is used for receiving a voice instruction request of the vehicle-mounted voice recommendation system, judging whether the voice instruction belongs to the downloaded voice skill, analyzing the voice skill, if the voice instruction belongs to the downloaded voice skill, sending an analysis result to the vehicle-mounted voice skill recommendation system, if the voice instruction does not belong to the downloaded voice skill, matching the cloud voice skill, generating a voice skill recommendation result, and sending the voice skill recommendation result to the vehicle-mounted voice skill recommendation system.
Further, the vehicle-end voice skill recommendation system comprises a vehicle-end voice skill request module, a local voice skill arbitration module, a local voice skill analysis module, a voice skill real-time recommendation module, a vehicle-end voice skill response module and a vehicle-end voice skill downloading management module;
the vehicle-end voice skill request module is used for receiving and extracting a voice instruction request which cannot be identified by a user;
the local voice skill arbitration module is used for distributing local voice skill requests and arbitrating whether downloaded local voice skills are directly used or cloud voice skills are requested;
the local voice skill analysis module is used for identifying local downloaded voice skills corresponding to the voice instructions;
the voice skill real-time recommendation module is used for analyzing and converting the voice command into a voice skill result in real time and recommending the voice skill result to a user;
the voice skill downloading module is used for responding to a downloading request of a user;
the vehicle-end voice skill response module is used for executing the downloaded voice skill of the local or cloud end;
the vehicle-end voice skill downloading management module is used for processing a downloading request of a user and updating and storing a downloaded voice skill mapping table;
further, the background voice skill management center comprises a background voice skill request module, a background voice skill arbitration module, a background voice skill analysis module, a background voice skill download management module, a recommended voice skill generation module, and a background voice skill response module, wherein:
the background voice skill request module is used for responding to a voice instruction request at the vehicle end;
the background voice skill arbitration module is used for distributing a background voice skill request, arbitrating and recommending a new skill or responding to a downloaded skill;
the background voice skill analysis module is used for identifying the background supported voice skill corresponding to the voice instruction;
the background voice skill downloading management module is used for downloading a voice skill mapping table;
the recommendation voice skill generation module is used for generating a voice skill recommendation result;
and the background voice skill response module is used for returning the voice skill recommendation result or the voice skill recognition result to the vehicle-end voice skill recommendation system.
Furthermore, the local voice skill arbitration module is further configured to distribute relevant cloud voice skill requests.
Furthermore, the voice skill downloading module is also used for completing personalized voice skill configuration.
The invention also provides a method for recommending and downloading the vehicle-mounted voice skills in real time, which comprises the following steps:
s1, the vehicle-mounted voice skill recommendation system identifies a voice instruction request of a user, judges whether the voice instruction request belongs to downloaded local voice skills, analyzes and matches corresponding local downloaded voice skills if the voice instruction belongs to the downloaded local voice skills, responds to the voice skills, and sends the voice instruction to the background voice skill management center if the voice instruction does not belong to the downloaded local voice skills;
s2, the background voice skill management center receives a voice instruction request of the vehicle-mounted voice recommendation system, judges whether the voice instruction belongs to downloaded voice skills, analyzes the voice skills, sends an analysis result to the vehicle-mounted voice skill recommendation system if the voice instruction belongs to the downloaded voice skills, matches cloud voice skills if the voice instruction does not belong to the downloaded voice skills, generates a voice skill recommendation result and sends the voice skill recommendation result to the vehicle-mounted voice skill recommendation system;
and S3, the vehicle-mounted voice skill recommendation system receives the voice skill recommendation result of the background voice skill management center, recommends the cloud voice skill in real time, responds to the downloading request of the user, and updates and stores the downloaded voice skill.
Further, the step S1 specifically includes:
s1-1, the vehicle-mounted voice assistant sends the voice instruction which cannot be recognized to the vehicle-mounted voice skill request module, and the vehicle-mounted voice skill request module extracts the voice instruction and sends the voice instruction to the local voice skill arbitration module;
s1-2, the local voice skill arbitration module firstly distributes a voice instruction to the local voice skill analysis module, the local voice skill analysis module searches for a corresponding local voice skill, and returns an analysis result to the local voice skill arbitration module;
s1-3, if the returned result is the downloaded voice skill, the local voice skill arbitration module calls the vehicle-end voice skill response module to execute the local voice skill; and if the returned result is that the voice command cannot be identified, the local voice skill arbitration module distributes the voice command to a background voice skill request module of the background voice skill management center at the cloud end.
Further, the step S2 specifically includes:
s2-1, the background voice skill request module extracts the voice command and sends the voice command to the background voice skill arbitration module;
s2-2, the background voice skill arbitration module firstly distributes the voice instruction to the background voice skill analysis module, the background voice skill analysis module searches for the voice skill corresponding to the background, and returns the recognition result to the background voice skill arbitration module;
s2-3, if the returned result can be identified as background voice skill, the background voice skill arbitration module calls a background voice skill download management module to obtain the downloaded voice skill configuration of the user or the equipment, and if the identified voice skill belongs to the downloaded voice skill, the voice skill analysis result is directly sent to the background voice skill response module; if the skill does not belong to the downloaded voice skill, sending the identified one or more voice skill information to the recommended voice skill generation module; if the returned result does not hit the background voice skill, the background voice skill arbitration module sends a recognition failure message to the background voice skill response module;
s2-4, if the downloaded voice skill or the missed background voice skill is recognized in the last step, the background voice skill response module returns the skill recognition result to the vehicle-end voice skill response module for execution; if the downloaded voice skill is not recognized in the last step but other background voice skills are hit, the recommended voice skill generation module converts the recognized voice skill into a recommended voice skill list and sends the recommended voice skill list to the background voice skill response module;
s2-5, the background voice skill response module sends a pushed voice skill list to the vehicle end voice skill real-time recommendation module;
further, the step S3 specifically includes:
s3-1, the vehicle end voice skill real-time recommendation module is used for inquiring whether the user needs to download new skills in real time, and if the user chooses not to download, the process is ended; if the downloading recommendation skill is selected, the voice skill real-time recommendation module calls a voice skill downloading module to respond to a voice skill downloading request of a user and update a downloaded voice skill mapping table, and sends the mapping table to a vehicle-end voice skill downloading management module;
and S3-2, updating and storing the downloaded voice skill mapping table by the vehicle-end voice skill downloading management module, prompting a user to finish downloading, synchronizing the latest voice skill mapping table to the cloud background voice skill downloading management module, and ending the process.
Further, the step S2-3 further includes:
and if the voice skill identified by the background voice skill arbitration module belongs to the downloaded voice skill and a plurality of identification results exist, sending the voice skill analysis result with the highest identification credibility to the background voice skill response module.
According to the vehicle-mounted voice skill real-time recommendation downloading system and method provided by the embodiment of the invention, through real-time intelligent recommendation of voice skills, a user can find a new function which cannot be identified by original voice control in time, effective guidance of the user on using the voice control is realized, and the intelligence and the practicability of a product are improved; the new requirements of the user can be accurately identified, more choices of personalized experience are provided for the user in real time, and the personalized experience of the product is improved; the real-time recommendation of the voice skills can also effectively solve the problem that the dynamic change requirements of users cannot be met due to the fact that the existing vehicle-mounted voice control system cannot update versions timely, and the differentiation competitiveness of products is improved; and a plurality of high-quality voice skill resources are aggregated, so that the value added value of operation is brought to the car factory.
Drawings
FIG. 1 is a block diagram of a vehicle-mounted real-time speech skill recommendation system according to an embodiment of the present invention;
fig. 2 is a flowchart of a real-time vehicle-mounted voice skill recommendation method according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, which are given solely for the purpose of illustration and are not to be construed as limitations of the invention, including the drawings which are incorporated herein by reference and for illustration only and are not to be construed as limitations of the invention, since many variations thereof are possible without departing from the spirit and scope of the invention.
As shown in fig. 1, a block diagram of a vehicle-mounted voice skill real-time recommendation system provided in an embodiment of the present invention includes: the system comprises a vehicle-end voice skill recommendation system and a background voice skill management center;
the vehicle-mounted voice skill recommendation system is used for identifying a voice instruction request of a user, judging whether the voice instruction request belongs to downloaded local voice skills, analyzing and matching the corresponding local downloaded voice skills if the voice instruction belongs to the downloaded local voice skills, sending the voice instruction to the background voice skill management center if the voice instruction does not belong to the downloaded local voice skills, receiving a voice skill recommendation result of the background voice skill management center, recommending cloud voice skills in real time, responding to the download request of the user, updating and storing the downloaded voice skills, and executing the downloaded voice skills; the local downloaded voice skill refers to a skill supporting local instruction matching or semantic analysis;
the background voice skill management center is used for receiving a voice instruction request of the vehicle-mounted voice recommendation system, judging whether the voice instruction belongs to the downloaded voice skill, analyzing the voice skill, if the voice instruction belongs to the downloaded voice skill, sending an analysis result to the vehicle-mounted voice skill recommendation system, if the voice instruction does not belong to the downloaded voice skill, matching the cloud voice skill, generating a voice skill recommendation result, and sending the voice skill recommendation result to the vehicle-mounted voice skill recommendation system.
Further, the vehicle-end voice skill recommendation system comprises a vehicle-end voice skill request module, a local voice skill arbitration module, a local voice skill analysis module, a voice skill real-time recommendation module, a vehicle-end voice skill response module and a vehicle-end voice skill downloading management module;
the vehicle-end voice skill request module is used for receiving and extracting a voice instruction request which cannot be identified by a user;
the local voice skill arbitration module is used for distributing local voice skill requests and arbitrating whether downloaded local voice skills are directly used or cloud voice skills are requested;
the local voice skill analysis module is used for identifying local downloaded voice skills corresponding to the voice instructions;
the voice skill real-time recommendation module is used for analyzing and converting the voice command into a voice skill result in real time and recommending the voice skill result to a user;
the voice skill downloading module is used for responding to a downloading request of a user;
the vehicle-end voice skill response module is used for executing the downloaded voice skill of the local or cloud end;
the vehicle-end voice skill downloading management module is used for processing a downloading request of a user and updating and storing a downloaded voice skill mapping table;
further, the background voice skill management center comprises a background voice skill request module, a background voice skill arbitration module, a background voice skill analysis module, a background voice skill download management module, a recommended voice skill generation module, and a background voice skill response module, wherein:
the background voice skill request module is used for responding to a voice instruction request at the vehicle end;
the background voice skill arbitration module is used for distributing a background voice skill request, arbitrating and recommending a new skill or responding to a downloaded skill;
the background voice skill analysis module is used for identifying the background supported voice skill corresponding to the voice instruction;
the background voice skill downloading management module is used for downloading a voice skill mapping table;
the recommendation voice skill generation module is used for generating a voice skill recommendation result;
and the background voice skill response module is used for returning the voice skill recommendation result or the voice skill recognition result to the vehicle-end voice skill recommendation system.
Furthermore, the local voice skill arbitration module is further configured to distribute relevant cloud voice skill requests.
Furthermore, the voice skill downloading module is also used for completing personalized voice skill configuration.
As shown in fig. 2, the workflow of one embodiment of the scheme of the present invention is as follows, taking recommending and downloading a charging skill to a user as an example, and the original vehicle-mounted voice does not support the charging skill:
s1, the vehicle-mounted voice skill recommendation system identifies a voice instruction request of a user, judges whether the voice instruction request belongs to downloaded local voice skills, analyzes and matches corresponding local downloaded voice skills if the voice instruction belongs to the downloaded local voice skills, responds to the voice skills, and sends the voice instruction to the background voice skill management center if the voice instruction does not belong to the downloaded local voice skills;
s2, the background voice skill management center receives a voice instruction request of the vehicle-mounted voice recommendation system, judges whether the voice instruction belongs to downloaded voice skills, analyzes the voice skills, sends an analysis result to the vehicle-mounted voice skill recommendation system if the voice instruction belongs to the downloaded voice skills, matches cloud voice skills if the voice instruction does not belong to the downloaded voice skills, generates a voice skill recommendation result and sends the voice skill recommendation result to the vehicle-mounted voice skill recommendation system;
and S3, the vehicle-mounted voice skill recommendation system receives the voice skill recommendation result of the background voice skill management center, recommends the cloud voice skill in real time, responds to the downloading request of the user, and updates and stores the downloaded voice skill.
Further, the step S1 specifically includes:
s1-1, the vehicle-mounted voice assistant sends the voice instruction which cannot be recognized to the vehicle-mounted voice skill request module, and the vehicle-mounted voice skill request module extracts the voice instruction and sends the voice instruction to the local voice skill arbitration module;
such as: the vehicle-mounted voice assistant receives a command of 'i want to charge' of a user, and if the original skill cannot be identified, the command is sent to a vehicle-end voice skill recommendation system;
s1-2, the local voice skill arbitration module firstly distributes a voice instruction to the local voice skill analysis module, the local voice skill analysis module searches for a corresponding local voice skill, and returns an analysis result to the local voice skill arbitration module;
such as: the user does not download the overcharge skill before, the local voice skill analysis module does not find the corresponding local voice skill, and the vehicle end still is the result which cannot be identified;
s1-3, if the returned result is the downloaded voice skill, the local voice skill arbitration module calls the vehicle-end voice skill response module to execute the local voice skill; and if the returned result is that the voice command cannot be identified, the local voice skill arbitration module distributes the voice command to a background voice skill request module of the background voice skill management center at the cloud end.
Such as: if the front vehicle end does not recognize any local downloaded voice skill (the charging skill belongs to the background voice skill), a user instruction request is sent to the cloud background voice skill management center, and the request comprises a user finger, a conversation context, a user account, equipment and other unique identifiers.
Further, the step S2 specifically includes:
s2-1, the background voice skill request module extracts the voice command and sends the voice command to the background voice skill arbitration module;
such as: the cloud background voice skill management center firstly performs authentication and request information extraction after receiving a user request;
s2-2, the background voice skill arbitration module firstly distributes the voice instruction to the background voice skill analysis module, the background voice skill analysis module searches for the voice skill corresponding to the background, and returns the recognition result to the background voice skill arbitration module;
such as: the background firstly resolves 'i want to go to charge', the charging and map skills are matched, and the confidence coefficient of the charging skill is higher than the map skill;
s2-3, if the returned result can be identified as background voice skill, the background voice skill arbitration module calls a background voice skill download management module to obtain the downloaded voice skill configuration of the user or the equipment, and if the identified voice skill belongs to the downloaded voice skill, the voice skill analysis result is directly sent to the background voice skill response module; if a plurality of recognition results exist, returning a result with highest reliability of downloaded voice skill recognition; if the skill does not belong to the downloaded voice skill, sending the identified one or more voice skill information to the recommended voice skill generation module; if the returned result does not hit the background voice skill, the background voice skill arbitration module sends a recognition failure message to the background voice skill response module;
such as: then obtaining a downloaded skill information mapping table stored in the background of the user or the equipment, wherein the charging skill and the map skill do not belong to the downloaded voice skill of the user or the equipment;
s2-4, if the downloaded voice skill or the missed background voice skill is recognized in the last step, the background voice skill response module returns the skill recognition result to the vehicle-end voice skill response module for execution; if the downloaded voice skill is not recognized in the last step but other background voice skills are hit, the recommended voice skill generation module converts the recognized voice skill into a recommended voice skill list and sends the recommended voice skill list to the background voice skill response module;
such as: the recommended voice skill generation module converts the charging skill and map skill recognition result into a recommended skill list and sends the recommended skill list to the background voice skill response module;
s2-5, the background voice skill response module sends a pushed voice skill list to the vehicle end voice skill real-time recommendation module;
further, the step S3 specifically includes:
s3-1, the vehicle end voice skill real-time recommendation module is used for inquiring whether the user needs to download new skills in real time, and if the user chooses not to download, the process is ended; if the downloading recommendation skill is selected, the voice skill real-time recommendation module calls a voice skill downloading module to respond to a voice skill downloading request of a user and update a downloaded voice skill mapping table, and sends the mapping table to a vehicle-end voice skill downloading management module;
such as: the user answers 'download first' (charging skill), the vehicle end starts background voice skill downloading, a downloaded voice skill mapping table is newly built and updated locally, and then the downloaded voice skill mapping table is uploaded to the cloud for synchronization.
S3-2, the vehicle-end voice skill downloading management module updates and stores the downloaded voice skill mapping table, prompts a user to finish downloading, synchronizes the latest voice skill mapping table to the background voice skill downloading management module at the cloud end, and finishes the process;
such as: the cloud end receives the voice skill mapping table to be synchronized, newly builds and updates the voice skill mapping table of the user or the equipment, and feeds back newly built and updated results to the vehicle end, and the vehicle end receives the results and feeds back 'the downloaded results are successful, you can try at once' to the user.
According to the vehicle-mounted voice skill real-time recommendation downloading system and method provided by the embodiment of the invention, through real-time intelligent recommendation of voice skills, a user can find a new function which cannot be identified by original voice control in time, effective guidance of the user on using the voice control is realized, and the intelligence and the practicability of a product are improved; the new requirements of the user can be accurately identified, more choices of personalized experience are provided for the user in real time, and the personalized experience of the product is improved; the real-time recommendation of the voice skills can also effectively solve the problem that the dynamic change requirements of users cannot be met due to the fact that the existing vehicle-mounted voice control system cannot update versions timely, and the differentiation competitiveness of products is improved; and a plurality of high-quality voice skill resources are aggregated, so that the value added value of operation is brought to the car factory.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. An on-board voice skill real-time recommendation downloading system, comprising: the system comprises a vehicle-end voice skill recommendation system and a background voice skill management center;
the vehicle-mounted voice skill recommendation system is used for identifying a voice instruction request of a user, judging whether the voice instruction request belongs to downloaded local voice skills, analyzing and matching the corresponding local downloaded voice skills if the voice instruction belongs to the downloaded local voice skills, sending the voice instruction to the background voice skill management center if the voice instruction does not belong to the downloaded local voice skills, receiving a voice skill recommendation result of the background voice skill management center, recommending cloud voice skills in real time, responding to the download request of the user, updating and storing the downloaded voice skills, and executing the downloaded voice skills;
the background voice skill management center is used for receiving a voice instruction request of the vehicle-mounted voice recommendation system, judging whether the voice instruction belongs to the downloaded voice skill, analyzing the voice skill, if the voice instruction belongs to the downloaded voice skill, sending an analysis result to the vehicle-mounted voice skill recommendation system, if the voice instruction does not belong to the downloaded voice skill, matching the cloud voice skill, generating a voice skill recommendation result, and sending the voice skill recommendation result to the vehicle-mounted voice skill recommendation system.
2. The vehicle-mounted voice skill real-time recommendation downloading system of claim 1, wherein: the vehicle-end voice skill recommendation system comprises a vehicle-end voice skill request module, a local voice skill arbitration module, a local voice skill analysis module, a voice skill real-time recommendation module, a vehicle-end voice skill response module and a vehicle-end voice skill downloading management module;
the vehicle-end voice skill request module is used for receiving and extracting a voice instruction request which cannot be identified by a user;
the local voice skill arbitration module is used for distributing local voice skill requests and arbitrating whether downloaded local voice skills are directly used or cloud voice skills are requested;
the local voice skill analysis module is used for identifying local downloaded voice skills corresponding to the voice instructions;
the voice skill real-time recommendation module is used for analyzing and converting the voice command into a voice skill result in real time and recommending the voice skill result to a user;
the voice skill downloading module is used for responding to a downloading request of a user;
the vehicle-end voice skill response module is used for executing the downloaded voice skill of the local or cloud end;
and the vehicle-end voice skill downloading management module is used for processing a downloading request of a user and updating and storing a downloaded voice skill mapping table.
3. The vehicle-mounted voice skill real-time recommendation downloading system of claim 2, wherein: the background voice skill management center comprises a background voice skill request module, a background voice skill arbitration module, a background voice skill analysis module, a background voice skill download management module, a recommended voice skill generation module and a background voice skill response module, wherein:
the background voice skill request module is used for responding to a voice instruction request at the vehicle end;
the background voice skill arbitration module is used for distributing a background voice skill request, arbitrating and recommending a new skill or responding to a downloaded skill;
the background voice skill analysis module is used for identifying the background supported voice skill corresponding to the voice instruction;
the background voice skill downloading management module is used for downloading a voice skill mapping table;
the recommendation voice skill generation module is used for generating a voice skill recommendation result;
and the background voice skill response module is used for returning the voice skill recommendation result or the voice skill recognition result to the vehicle-end voice skill recommendation system.
4. The vehicle-mounted voice skill real-time recommendation downloading system of claim 2, wherein: the local voice skill arbitration module is further used for distributing relevant cloud voice skill requests.
5. The vehicle-mounted voice skill real-time recommendation downloading system of claim 2, wherein: the voice skill downloading module is also used for completing personalized voice skill configuration.
6. A vehicle-mounted voice skill real-time recommendation downloading method is characterized by comprising the following steps:
s1, the vehicle-mounted voice skill recommendation system identifies a voice instruction request of a user, judges whether the voice instruction request belongs to downloaded local voice skills, analyzes and matches corresponding local downloaded voice skills if the voice instruction belongs to the downloaded local voice skills, responds to the voice skills, and sends the voice instruction to the background voice skill management center if the voice instruction does not belong to the downloaded local voice skills;
s2, the background voice skill management center receives a voice instruction request of the vehicle-mounted voice recommendation system, judges whether the voice instruction belongs to downloaded voice skills, analyzes the voice skills, sends an analysis result to the vehicle-mounted voice skill recommendation system if the voice instruction belongs to the downloaded voice skills, matches cloud voice skills if the voice instruction does not belong to the downloaded voice skills, generates a voice skill recommendation result and sends the voice skill recommendation result to the vehicle-mounted voice skill recommendation system;
and S3, the vehicle-mounted voice skill recommendation system receives the voice skill recommendation result of the background voice skill management center, recommends the cloud voice skill in real time, responds to the downloading request of the user, and updates and stores the downloaded voice skill.
7. The vehicle-mounted voice skill real-time recommendation downloading method according to claim 6, wherein the step S1 specifically includes:
s1-1, the vehicle-mounted voice assistant sends the voice instruction which cannot be recognized to the vehicle-mounted voice skill request module, and the vehicle-mounted voice skill request module extracts the voice instruction and sends the voice instruction to the local voice skill arbitration module;
s1-2, the local voice skill arbitration module firstly distributes a voice instruction to the local voice skill analysis module, the local voice skill analysis module searches for a corresponding local voice skill, and returns an analysis result to the local voice skill arbitration module;
s1-3, if the returned result is the downloaded voice skill, the local voice skill arbitration module calls the vehicle-end voice skill response module to execute the local voice skill; and if the returned result is that the voice command cannot be identified, the local voice skill arbitration module distributes the voice command to a background voice skill request module of the background voice skill management center at the cloud end.
8. The vehicle-mounted voice skill real-time recommendation downloading method according to claim 7, wherein the step S2 specifically includes:
s2-1, the background voice skill request module extracts the voice command and sends the voice command to the background voice skill arbitration module;
s2-2, the background voice skill arbitration module firstly distributes the voice instruction to the background voice skill analysis module, the background voice skill analysis module searches for the voice skill corresponding to the background, and returns the recognition result to the background voice skill arbitration module;
s2-3, if the returned result can be identified as background voice skill, the background voice skill arbitration module calls a background voice skill download management module to obtain the downloaded voice skill configuration of the user or the equipment, and if the identified voice skill belongs to the downloaded voice skill, the voice skill analysis result is directly sent to the background voice skill response module; if the skill does not belong to the downloaded voice skill, sending the identified one or more voice skill information to the recommended voice skill generation module; if the returned result does not hit the background voice skill, the background voice skill arbitration module sends a recognition failure message to the background voice skill response module;
s2-4, if the downloaded voice skill or the missed background voice skill is recognized in the last step, the background voice skill response module returns the skill recognition result to the vehicle-end voice skill response module for execution; if the downloaded voice skill is not recognized in the last step but other background voice skills are hit, the recommended voice skill generation module converts the recognized voice skill into a recommended voice skill list and sends the recommended voice skill list to the background voice skill response module;
and S2-5, the background voice skill response module sends the pushed voice skill list to the vehicle-end voice skill real-time recommendation module.
9. The vehicle-mounted voice skill real-time recommendation downloading method according to claim 8, wherein the step S3 specifically includes:
s3-1, the vehicle end voice skill real-time recommendation module is used for inquiring whether the user needs to download new skills in real time, and if the user chooses not to download, the process is ended; if the downloading recommendation skill is selected, the voice skill real-time recommendation module calls a voice skill downloading module to respond to a voice skill downloading request of a user and update a downloaded voice skill mapping table, and sends the mapping table to a vehicle-end voice skill downloading management module;
and S3-2, updating and storing the downloaded voice skill mapping table by the vehicle-end voice skill downloading management module, prompting a user to finish downloading, synchronizing the latest voice skill mapping table to the cloud background voice skill downloading management module, and ending the process.
10. The vehicle-mounted voice skill real-time recommendation downloading method according to claim 8, wherein the step S2-3 further comprises:
and if the voice skill identified by the background voice skill arbitration module belongs to the downloaded voice skill and a plurality of identification results exist, sending the voice skill analysis result with the highest identification credibility to the background voice skill response module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110301358.8A CN113223535B (en) | 2021-03-22 | 2021-03-22 | Vehicle-mounted voice skill real-time recommendation and downloading system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110301358.8A CN113223535B (en) | 2021-03-22 | 2021-03-22 | Vehicle-mounted voice skill real-time recommendation and downloading system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113223535A true CN113223535A (en) | 2021-08-06 |
CN113223535B CN113223535B (en) | 2024-04-05 |
Family
ID=77084116
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110301358.8A Active CN113223535B (en) | 2021-03-22 | 2021-03-22 | Vehicle-mounted voice skill real-time recommendation and downloading system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113223535B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105551494A (en) * | 2015-12-11 | 2016-05-04 | 奇瑞汽车股份有限公司 | Mobile phone interconnection-based vehicle-mounted speech recognition system and recognition method |
CN105825856A (en) * | 2016-05-16 | 2016-08-03 | 四川长虹电器股份有限公司 | Independent learning method for vehicle-mounted speech recognition module |
CN106098062A (en) * | 2016-06-16 | 2016-11-09 | 杭州古北电子科技有限公司 | Intelligent sound control system for identifying that processing locality is combined with wireless network and method |
CN107545892A (en) * | 2016-06-24 | 2018-01-05 | 中兴通讯股份有限公司 | The control method of equipment, apparatus and system |
US20200007656A1 (en) * | 2018-06-29 | 2020-01-02 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for sending information |
CN111292750A (en) * | 2020-03-09 | 2020-06-16 | 成都启英泰伦科技有限公司 | Local voice recognition method based on cloud improvement |
CN111627435A (en) * | 2020-04-30 | 2020-09-04 | 长城汽车股份有限公司 | Voice recognition method and system and control method and system based on voice instruction |
-
2021
- 2021-03-22 CN CN202110301358.8A patent/CN113223535B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105551494A (en) * | 2015-12-11 | 2016-05-04 | 奇瑞汽车股份有限公司 | Mobile phone interconnection-based vehicle-mounted speech recognition system and recognition method |
CN105825856A (en) * | 2016-05-16 | 2016-08-03 | 四川长虹电器股份有限公司 | Independent learning method for vehicle-mounted speech recognition module |
CN106098062A (en) * | 2016-06-16 | 2016-11-09 | 杭州古北电子科技有限公司 | Intelligent sound control system for identifying that processing locality is combined with wireless network and method |
CN107545892A (en) * | 2016-06-24 | 2018-01-05 | 中兴通讯股份有限公司 | The control method of equipment, apparatus and system |
US20200007656A1 (en) * | 2018-06-29 | 2020-01-02 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for sending information |
CN111292750A (en) * | 2020-03-09 | 2020-06-16 | 成都启英泰伦科技有限公司 | Local voice recognition method based on cloud improvement |
CN111627435A (en) * | 2020-04-30 | 2020-09-04 | 长城汽车股份有限公司 | Voice recognition method and system and control method and system based on voice instruction |
Also Published As
Publication number | Publication date |
---|---|
CN113223535B (en) | 2024-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107004410A (en) | Voice and connecting platform | |
CN105791931A (en) | Smart television and voice control method of the smart television | |
CN103294460B (en) | User-interface application layout adjustment method, server device and terminal unit | |
US9854320B2 (en) | Method and system for accessing TV programs and applications on smart TV | |
CN105069363A (en) | Intelligent robot account number distribution and management method and system based on artificial intelligence | |
CN103810005B (en) | Adjusting method and system for voice system | |
CN114913856B (en) | Voice interaction method, server and storage medium | |
CN105894099A (en) | Vehicle scheduling method and system for uniformly processing real-time and reservation requests | |
CN109996026B (en) | Video special effect interaction method, device, equipment and medium based on wearable equipment | |
CN102736923B (en) | Software customization installation method and system | |
CN106020916A (en) | Method for updating application, terminal equipment and server | |
CN110009059A (en) | Method and apparatus for generating model | |
CN109377990A (en) | A kind of information processing method and electronic equipment | |
CN108172221A (en) | The method and apparatus of manipulation aircraft based on intelligent terminal | |
WO2013044630A1 (en) | Location sharing and road condition recognition system and method | |
CN113223535B (en) | Vehicle-mounted voice skill real-time recommendation and downloading system and method | |
CN104021186A (en) | Dynamic intelligent flight information query system and method based on voice recognition | |
CN105528358B (en) | Track of vehicle inquiry system and querying method | |
CN106843882B (en) | Information processing method and device and information processing system | |
CN109635543A (en) | Automobile shows information individual character matching system and method | |
CN105991825A (en) | Voice control method, device and system | |
CN114974248A (en) | Vehicle voice interaction method, server and storage medium | |
CN114090911A (en) | Interface processing method and device, computer equipment and computer readable storage medium | |
CN115620710A (en) | Speech recognition method, speech recognition device, storage medium and electronic device | |
CN111105795B (en) | Method and device for training offline voice firmware of smart home |
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 |