CN108777142A - A kind of interactive voice recognition methods and interactive voice robot based on airport environment - Google Patents
A kind of interactive voice recognition methods and interactive voice robot based on airport environment Download PDFInfo
- Publication number
- CN108777142A CN108777142A CN201810581590.XA CN201810581590A CN108777142A CN 108777142 A CN108777142 A CN 108777142A CN 201810581590 A CN201810581590 A CN 201810581590A CN 108777142 A CN108777142 A CN 108777142A
- Authority
- CN
- China
- Prior art keywords
- flight
- phrase
- module
- interactive voice
- text message
- 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.)
- Pending
Links
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
- G10L15/26—Speech to text systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/0005—Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The interactive voice recognition methods and interactive voice robot, method that the present invention provides a kind of based on airport environment include：According to speech recognition library, the voice messaging got in interactive voice is converted into text message；According to the semantic understanding to the text message, in flight semantic base, the corresponding flight phrase of the text message is found out；According to the semantic understanding to the flight phrase, judge whether contain flight number in the flight phrase；If so, then according to Flight Information system, inquires and show the corresponding Flight Information of the flight number.The discrimination to flight number during robot is interacted with user speech can be improved through the invention, provide more accurately Flight Information inquiry service to the user.
Description
Technical field
Identify field the present invention relates to robot voice, espespecially a kind of interactive voice recognition methods based on airport environment and
Interactive voice robot.
Background technology
With the development of science and technology intelligent robot has obtained development at full speed, they can help people to complete many works
Make, such as sweeping robot can help user's cleaning, transportation robot that user can be solved to releasing from hard work
Come, service humanoid robot can be interacted with user, provide help and service to the user.
On airport it can be seen that many artificial passengers of interactive voice machine provide Flight Information consulting.In robot and user
In interactive process, the language for accurately identifying user is the prerequisite for providing help and service to the user.
Interactive voice is being carried out come when inquiring Flight Information, since China's language and culture is abundant, the big phase diameter of pronunciation of various regions
Front yard, for Chinese passengers when saying English, many pronunciations are not very standards, and current many flight number all contain English (such as
MU5367), therefore, sound interaction robot, can be very to the identification difficulty of English when carrying out interactive voice with China passenger
Greatly.
To solve the above-mentioned problems, recognition accuracy of the robot to flight number is improved, the present invention provides one kind to be based on
The interactive voice recognition methods of airport environment and interactive voice robot.
Invention content
The interactive voice recognition methods and interactive voice robot that the object of the present invention is to provide a kind of based on airport environment,
The discrimination to flight number during robot is interacted with user speech can be improved, more accurately Flight Information is provided to the user and looks into
Ask service.
Technical solution provided by the invention is as follows：
The interactive voice recognition methods based on airport environment that the present invention provides a kind of, including step：S1 in airport, if
When having detected that passenger carries out interactive voice, according to speech recognition library, the voice messaging got in interactive voice is converted to
Text message；S2 is according to the semantic understanding to the text message, in flight semantic base, finds out the text message and corresponds to
Flight phrase；S3 judges whether contain flight number in the flight phrase according to the semantic understanding to the flight phrase；If
Have, thens follow the steps S5；S5 is inquired according to Flight Information system and is shown the corresponding Flight Information of the flight number.
Preferably, step S2 specifically includes step：S21 carries out semantic understanding to the text message, judges the text
Whether the feature phrase that meets preset language assemblage characteristic is had in information, and the preset language assemblage characteristic includes Chinese character and number
The language combination feature of the language combination feature or English alphabet and number composition of composition；If satisfied, thening follow the steps S22；
S22, according to the semantic understanding to the feature phrase, finds out the corresponding boat of the feature phrase in the flight semantic base
Class's phrase.
Preferably, step is specifically included before step S5：S41 issues the user with the confirmation prompt message of the flight number；
S42 parses the operational order of user, if the operational order is when confirming instruction, to execute step S5；Otherwise, step S43 is executed；
S43 prompt users are manually entered flight number, and store flight number input by user.
Preferably, include step after step S5：What S61 counted the corresponding different characteristic phrase of each flight number goes out occurrence
Number；S62 calculates the weight of each feature phrase according to the occurrence number of the corresponding different characteristic phrase of each flight number.
Preferably, include step before step S41：S40 judges the corresponding weight of feature phrase in the text message
Whether default weight is reached, if so, thening follow the steps S5；Otherwise, step S41 is executed.
The present invention also provides a kind of interactive voice robots applied to airport, including：Text conversion module is used for
In airport, if detected that passenger carries out interactive voice, according to speech recognition library, the voice got in interactive voice is believed
Breath is converted to text message；Searching module is electrically connected with the text conversion module, for according to the language to the text message
Reason and good sense solution finds out the corresponding flight phrase of the text message in flight semantic base；Judgment module, with the lookup mould
Block is electrically connected, for according to the semantic understanding to the flight phrase, judging whether contain flight number in the flight phrase；Institute
Searching module is stated, if being additionally operable to contain flight number in the flight phrase, according to Flight Information system, inquires the flight number
Corresponding Flight Information；Display module is electrically connected with the searching module, for showing the corresponding flight letter of the flight number
Breath.
Preferably, further include：Semantic understanding module is electrically connected with the text conversion module, for the text envelope
Breath carries out semantic understanding；The judgment module is also electrically connected with the semantic understanding module, for judging in the text message
It includes Chinese character and number composition whether to have the feature phrase for meeting preset language assemblage characteristic, the preset language assemblage characteristic
The language combination feature of language combination feature or English alphabet and number composition；The searching module, if being additionally operable to the text
There is the feature phrase for meeting preset language assemblage characteristic in information, then in the flight semantic base, according to the Feature Words
The semantic understanding of group, finds out the corresponding flight phrase of the feature phrase.
Preferably, further include：Reminding module is electrically connected with the display module, is additionally operable to through display module to user
Send out the confirmation prompt message of the flight number；Parsing module, the operational order for parsing user；The reminding module, also
If not being when confirming instruction, user to be prompted to be manually entered flight number for the operational order；Storage module, for storing user
The flight number of input.
Preferably, further include：Statistical module goes out occurrence for count the corresponding different characteristic phrase of each flight number
Number；Computing module is electrically connected with the statistical module, for going out occurrence according to the corresponding different characteristic phrase of each flight number
Number, calculates the weight of each feature phrase.
Preferably, the judgment module is additionally operable to judge whether is the corresponding weight of feature phrase in the text message
Reach default weight；The reminding module is additionally operable to when the corresponding weight of feature phrase in the text message is not up to pre-
If when weight, the confirmation prompt message of the flight number is issued the user with by display module；The searching module is additionally operable to work as
When the corresponding weight of feature phrase in the text message reaches default weight, according to Flight Information system, the boat is inquired
Class's number corresponding Flight Information.
A kind of the interactive voice recognition methods and interactive voice robot based on airport environment provided through the invention, energy
Enough bring following at least one advantageous effect：
1, the present invention first passes through counting user to the corresponding text data of alphabetical difference pronunciation in advance, forms flight semantic base,
By semantic understanding, the text message obtained to interaction is modified, effectively increase robot user English equivalents not
On time, to the recognition accuracy of flight number.
2, since flight number is letter+number combinatorics on words (such as MU5367) or airline's title+number combinatorics on words
(such as East Airways 5367 or east aviation 5367), for user in speech polling Flight Information, the text message that interaction is formed is pertinent
Surely it will include one kind of above two language combination feature.Therefore, before finding out the corresponding flight phrase of the text message,
First judge whether there is the feature phrase for meeting preset language assemblage characteristic in text message, can avoid letter unrelated with aviation number
Breath is also modified, and the accuracy of flight number speech recognition is improved.
3, after the flight number that robot identifies that user to be inquired, confirmation prompt message can be issued the user with, is carried out
Secondary-confirmation ensures the accuracy of the Flight Information to be inquired of user.
4, after robot identifies flight number in text message, going out for the corresponding feature phrase of each flight number can be counted
Occurrence number calculates the weight of each feature phrase.When a certain user interacts, the corresponding weight of feature phrase in text message
Default weight is reached, has not then needed user and carry out secondary-confirmation, reduce the participation of user, improve the intelligence of robot
Degree can be changed.
Description of the drawings
Below by a manner of clearly understandable, preferred embodiment is described with reference to the drawings, to a kind of based on airport environment
Above-mentioned characteristic, technical characteristic, advantage and its realization method of interactive voice recognition methods and interactive voice robot give into one
Walk explanation.
Fig. 1 is a kind of flow chart of one embodiment of the interactive voice recognition methods based on airport environment of the present invention；
Fig. 2 is a kind of flow chart of another embodiment of the interactive voice recognition methods based on airport environment of the present invention；
Fig. 3 is a kind of flow chart of the further embodiment of the interactive voice recognition methods based on airport environment of the present invention；
Fig. 4 is a kind of structural schematic diagram of one embodiment of interactive voice robot applied to airport of the invention；
Fig. 5 is a kind of structural schematic diagram of another embodiment of interactive voice robot applied to airport of the invention.
Drawing reference numeral explanation：
1- text conversion modules, 2- searching modules, 3- judgment modules, 4- display modules, 5- semantic understandings module, 6- processing
Module, 7- reminding modules, 8- parsing modules, 9- storage modules, 10- statistical modules, 11- computing modules.
Specific implementation mode
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, control is illustrated below
The specific implementation mode of the present invention.It should be evident that drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, other are can also be obtained according to these attached drawings
Attached drawing, and obtain other embodiments.
To make simplified form, part related to the present invention is only schematically shown in each figure, they are not represented
Its practical structures as product.In addition, so that simplified form is easy to understand, there is identical structure or function in some figures
Component only symbolically depicts one of those, or has only marked one of those.Herein, "one" is not only indicated
" only this ", can also indicate the situation of " more than one ".
As shown in Figure 1, one embodiment of the present invention provides a kind of interactive voice recognition methods based on airport environment,
Including：
If S0 detected that passenger carries out interactive voice, obtains the voice messaging of user in airport；
S1 is converted to text message according to speech recognition library, by the voice messaging got in interactive voice；
S2 is according to the semantic understanding to the text message, in flight semantic base, finds out the text message and corresponds to
Flight phrase；
S3 judges whether contain flight number in the flight phrase according to the semantic understanding to the flight phrase；If so,
Then follow the steps S5；If nothing, return to step S0；
S5 is inquired according to Flight Information system and is shown the corresponding Flight Information of the flight number.
The present embodiment can be applicable in the interactive voice robot on airport, carry interactive voice robot under airport environment
Interactive voice ability.
The flight number that current each airline provides all is write a Chinese character in simplified form by the English of airline to be formed plus digital number.
Since China's language and culture is abundant, the pronunciation of various regions is far from each other, and for Chinese passengers when saying English, many pronunciations are not to mark very much
Standard, and current many flight number all contain English (such as MU5367), therefore, sound interacts robot and is carrying out language with China passenger
It, can be very big to the identification difficulty of English when sound interacts.
Specifically, the present embodiment can be previously according to a large amount of statistics, when obtaining user and saying that each airline's English is write a Chinese character in simplified form
Corresponding each text data, such as the English of east aviation are abbreviated as MU, and the corresponding homophonic text of pronunciation of " MU " has " A Mu
It is excellent ", " amen excellent ", " ebony is excellent " etc..Then corresponding each text data and associated boat are write a Chinese character in simplified form by these airlines
Empty Business Name is stored in flight semantic base.
When there is user to seek advice from this flight of MU5367 to robot, robot is according to speech recognition, by user's word
Text message is converted to, such as it is " I wants to inquire the departure time of Ah nurse excellent 5367 " to obtain the text message of user, according to right
The semantic understanding of the text message, in flight semantic base, it should be " MU " to find out " Ah nurse is excellent " corresponding airline,
The corresponding text reference information containing flight phrase of the text message is " I wants to inquire the departure time of MU5367 ".Then
Robot judges there is flight number " MU5367 " in this text reference information to the semantic understanding of the text reference information.
Then it be departure location is Pudong, Shanghai that robot can inquire " MU5367 " corresponding Flight Information in Flight Information system
T1 terminals, destination are Changsha Huanghua T2 terminals, and departure time plan is：21:30, boarding gate is the information such as 201
As can be seen that by flight semantic base, " Ah nurse is excellent " can be corrected as " MU " by robot by semantic understanding,
The accuracy for improving robot identification English, can effectively identify user to flight number.
As shown in Fig. 2, one embodiment of the present invention provides a kind of interactive voice recognition methods based on airport environment,
Including：
If S0 detected that passenger carries out interactive voice, obtains the voice messaging of user in airport；
S1 is converted to text message according to speech recognition library, by the voice messaging got in interactive voice；
Whether S21 carries out semantic understanding to the text message, judge to have in the text message and meet preset language group
The feature phrase of feature is closed, the preset language assemblage characteristic includes the language combination feature of Chinese character and number composition, or English
The language combination feature of letter and number composition；If satisfied, S22 is thened follow the steps, and otherwise, return to step S0；
S22, according to the semantic understanding to the feature phrase, finds out the feature phrase in the flight semantic base
Corresponding flight phrase；
S3 judges whether contain flight number in the flight phrase according to the semantic understanding to the flight phrase；If so,
Then follow the steps S41；If nothing, return to step S0；
S41 issues the user with the confirmation prompt message of the flight number；
S42 parses the operational order of user, if the operational order is when confirming instruction, to execute step S5；Otherwise, it executes
Step S43；
S43 prompt users are manually entered flight number, and store flight number input by user；
S5 is inquired according to Flight Information system and is shown the corresponding Flight Information of the flight number.
Specifically, in the present embodiment, since flight number is generally letter+number combinatorics on words or airline's title+number
Combination.Flight number is identified in order to be more accurate, can be carried out according to the feature of flight number " precisely identification ".When getting and use
After text message when family interacts, first determine whether there is the feature phrase for meeting preset language assemblage characteristic in text message.
Such as user say be " I want to inquire today Shanghai to Wuhan air ticket ", in this text message, do not meet preset language
The feature phrase of assemblage characteristic then will continue to detect next text message；What such as user said again is that " I wants to inquire color A3301
Flight Information ", you can judge there is the feature phrase " A3301 " for meeting preset language assemblage characteristic in text message thus.
Then robot, according to the semantic understanding to the feature phrase, can find out institute in the flight semantic base
The corresponding flight phrase of feature phrase is stated, specially：The corresponding flight phrase of the flight semanteme library lookup " A3301 ", still
It can be found that " A " is not writing a Chinese character in simplified form for airline, " A3301 " can not inquire corresponding flight number；Then robot
Feature phrase can be modified according to semantic understanding, obtains the feature phrase after " color A3301 " this amendment, then arrive boat
The corresponding flight phrase of the semantic library lookup " color A3301 " of class, you can be to find " color A3301 " corresponding flight phrase
" CA3301 " (the text correspondence of " color A3301 " and " CA3301 " need to have previously been stored in flight semantic base).Then machine
" color A3301 " in text message is replaced with " CA3301 " by device people, and obtaining the text reference information, " I wants to inquire CA3301
Flight Information ".
In the present embodiment, also add the process of passenger confirmation, when robot identify flight number that user says it
Afterwards, confirmation prompt message can be issued the user with by the display screen of robot, if user confirms, clicks corresponding confirmation and press
Button, robot can be inquired according to Flight Information system and show the corresponding Flight Information of the flight number.If user thinks
Robot identification is wrong, and input window can be also popped up on the display screen of robot, and user is prompted to be manually entered flight number.Pass through
This process can effectively ensure that passenger inquires the accuracy of flight.
As shown in figure 3, one embodiment of the present invention provides a kind of interactive voice recognition methods based on airport environment,
Including：
If S0 detected that passenger carries out interactive voice, obtains the voice messaging of user in airport；
S1 is converted to text message according to speech recognition library, by the voice messaging got in interactive voice；
Whether S21 carries out semantic understanding to the text message, judge to have in the text message and meet preset language group
The feature phrase of feature is closed, the preset language assemblage characteristic includes the language combination feature of Chinese character and number composition, or English
The language combination feature of letter and number composition；If satisfied, S22 is thened follow the steps, and otherwise, return to step S0；
S22, according to the semantic understanding to the feature phrase, finds out the feature phrase in the flight semantic base
Corresponding flight phrase；
S3 judges whether contain flight number in the flight phrase according to the semantic understanding to the flight phrase；If so,
Then follow the steps S40；Otherwise, return to step S0；
S40 judges whether the corresponding weight of feature phrase in the text message reaches default weight, if so, executing
Step S5；Otherwise, step S41 is executed；
S41 issues the user with the confirmation prompt message of the flight number；
S42 parses the operational order of user, if the operational order is when confirming instruction, to execute step S5；Otherwise, it executes
Step S43；
S43 prompt users are manually entered flight number, and store flight number input by user；
S5 is inquired according to Flight Information system and is shown the corresponding Flight Information of the flight number；
S61 counts the occurrence number of the corresponding different characteristic phrase of each flight number；
S62 calculates the weight of each feature phrase according to the occurrence number of the corresponding different characteristic phrase of each flight number.
Specifically, the occurrence number of the corresponding feature phrase of each flight number can be counted during specific use.
Such as the flight number to be inquired of user is " CA3301 ", if detecting the feature phrase in the corresponding text message of user speech
It is " color A3301 ", i.e., the number of " color A3301 " this feature phrase is added 1；If detecting the corresponding text envelope of user speech
Feature phrase in breath is " wiping 3301 ", i.e., the number of " wiping 3301 " this feature phrase is added 1；Thus it is right to obtain " CA3301 "
The occurrence number for the different characteristic phrase answered.
The occurrence number that can obtain the corresponding different characteristic phrase of each flight number later calculates each feature phrase
Weight, computational methods are corresponding all for the occurrence number of the corresponding feature phrase of a certain flight number divided by a certain flight number
The occurrence number of feature phrase.Such as the corresponding feature phrase of flight number " MU5367 " and occurrence number are respectively：" Ah nurse is excellent
5367 " 566 times, " amen excellent 5367 " 102 times, " excellent 5367 " of ebony 88 times, " mother 5367 " 779 times can calculate that " Ah nurse is excellent
5367 " respective weights are 556/ (556+102+88+779), and " amen excellent 5367 " respective weights are 102/ (556+102+88+
779), " the excellent 5367 " respective weights of ebony are 88/ (556+102+88+779), and " mother 5367 " respective weights are 779/ (556+102
+88+779)。
After robot judges to contain flight number in the text reference information, the feature in the text message can be judged
Whether the corresponding weight of phrase reaches default weight, if reaching, proves that many people can send out when saying this aviation
This corresponding voice of feature phrase, it is not necessary to send out secondary-confirmation to client again, directly be inquired simultaneously in Flight Information system
Show the corresponding Flight Information of the flight number.
As shown in figure 4, the present invention provides a kind of one embodiment of the interactive voice robot applied to airport, packet
It includes：
Text conversion module 1 is used in airport, if detected that passenger carries out interactive voice, according to speech recognition
The voice messaging got in interactive voice is converted to text message by library；
Searching module 2 is electrically connected with the text conversion module 1, is used for according to the semantic understanding to the text message,
In flight semantic base, the corresponding flight phrase of the text message is found out；
Judgment module 3 is electrically connected with the searching module 2, for according to the semantic understanding to the flight phrase, judging
Whether contain flight number in the flight phrase；
The searching module 2, according to Flight Information system, is looked into if being additionally operable to contain flight number in the flight phrase
Ask the corresponding Flight Information of the flight number；
Display module 4 is electrically connected with the searching module 2, for showing the corresponding Flight Information of the flight number.
Specifically, above-mentioned module can be integrated in robot, the work of speech recognition is completed.The work(of the display module 4
It can be realized by the display screen in robot.
Speech recognition library is stored in reservoir in robot, voice when user can speak is converted to text envelope
Breath.Flight semantic base is also stored in reservoir in robot, and each airline's letter is stored in the flight semantic base
Claim the text message of corresponding different pronunciations.Such as the English of east aviation is abbreviated as " MU ", the corresponding difference of pronunciation of " MU "
The text of pronunciation has " Ah nurse is excellent ", " amen excellent ", " ebony is excellent " etc..Specific interactive voice identification step can refer to above-mentioned one kind
The embodiment of interactive voice recognition methods based on airport environment, details are not described herein again.
As shown in figure 5, the present invention also provides a kind of another embodiment of the interactive voice robot applied to airport,
Including：
Text conversion module 1 is used in airport, if detected that passenger carries out interactive voice, according to speech recognition
The voice messaging got in interactive voice is converted to text message by library；
Semantic understanding module 5 is electrically connected with the text conversion module 1, for carrying out semantic reason to the text message
Solution；
The judgment module 3 is also electrically connected with the semantic understanding module 5, for judge in the text message whether
It includes the language of Chinese character and number composition to have the feature phrase for meeting preset language assemblage characteristic, the preset language assemblage characteristic
The language combination feature of assemblage characteristic or English alphabet and number composition；
The searching module 2, if being additionally operable to have the feature phrase for meeting preset language assemblage characteristic in the text message,
Then in the flight semantic base, according to the semantic understanding to the feature phrase, the corresponding boat of the feature phrase is found out
Class's phrase；
Processing module 6 is electrically connected with the searching module 2, for replacing the feature phrase in the text message
It is changed to the flight phrase, obtains the text reference information；
Judgment module 3 is electrically connected with the searching module 2, for according to the semantic understanding to the flight phrase, judging
Whether contain flight number in the flight phrase；
The judgment module 3, is additionally operable to judge whether the corresponding weight of feature phrase in the text message reaches pre-
If weight；
The searching module 2 is additionally operable to reach default weight when the corresponding weight of feature phrase in the text message
When, according to Flight Information system, inquire the corresponding Flight Information of the flight number；
Reminding module 7 is electrically connected with the display module 4, is additionally operable to correspond to when the feature phrase in the text message
Weight not up to default weight when, the confirmation prompt message of the flight number is issued the user with by display module 4；
Parsing module 8, the operational order for parsing user；
The reminding module 7 is electrically connected with the parsing module 8, if be additionally operable to the operational order to confirm instruction,
Prompt user is manually entered flight number；
Storage module 9, for storing flight number input by user.
The searching module 2 is also electrically connected with the storage module 9, is additionally operable to according to Flight Information system, described in inquiry
The corresponding Flight Information of flight number；
Display module 4 is electrically connected with the searching module 2, for showing the corresponding Flight Information of the flight number；
Statistical module 10 is electrically connected with the searching module 2, for counting the corresponding different characteristic phrase of each flight number
Occurrence number；
Computing module 11 is electrically connected with the statistical module 10, for according to the corresponding different characteristic word of each flight number
The occurrence number of group, calculates the weight of each feature phrase.
Specifically, in the present embodiment, since flight number is generally letter+number combinatorics on words or airline's title+number
Combination.Flight number is identified in order to be more accurate, can be carried out according to the feature of flight number " precisely identification ".Text conversion module
1 will get after voice messaging is converted to text message, can judge whether have satisfaction default in text message by judgment module 3
The feature phrase of language combination feature.If there is the feature phrase for meeting preset language assemblage characteristic in the text message, search
Module 2, according to the semantic understanding to the feature phrase, can find out the feature phrase and correspond in the flight semantic base
Flight phrase, and the feature phrase in text message is replaced with into flight phrase, obtains the text reference information.
In the present embodiment, also add the process of passenger confirmation, when robot identify flight number that user says it
Afterwards, confirmation prompt message can be issued the user with by the display screen of robot, if user confirms, clicks corresponding confirmation and press
Button, robot can be inquired according to Flight Information system and show the corresponding Flight Information of the flight number.If user thinks
Robot identification is wrong, and input window can be also popped up on the display screen of robot, and user is prompted to be manually entered flight number.Pass through
This process can effectively ensure that passenger inquires the accuracy of flight.
Specifically, the occurrence number of the corresponding feature phrase of each flight number can be counted during specific use.
The occurrence number that can obtain the corresponding different characteristic phrase of each flight number later calculates the weight of each feature phrase, goes out
The more feature phrase weight of occurrence number is bigger.After robot judges to contain flight number in the text reference information, it can sentence
Whether the corresponding weight of feature phrase in the disconnected text message reaches default weight, if reaching, proves that many people exist
This feature phrase can all be sent out by saying when this aviation, it is not necessary to secondary-confirmation be sent out to client again, directly in Flight Information
It is inquired in system and shows the corresponding Flight Information of the flight number.
It should be noted that above-described embodiment can be freely combined as needed.The above is only the preferred of the present invention
Embodiment, it is noted that for those skilled in the art, in the premise for not departing from the principle of the invention
Under, several improvements and modifications can also be made, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of interactive voice recognition methods based on airport environment, which is characterized in that including step：
If S1 detected that passenger carries out interactive voice, according to speech recognition library, will be got in airport in interactive voice
Voice messaging be converted to text message；
S2 is according to the semantic understanding to the text message, in flight semantic base, finds out the corresponding boat of the text message
Class's phrase；
S3 judges whether contain flight number in the flight phrase according to the semantic understanding to the flight phrase；If so, then holding
Row step S5；
S5 is inquired according to Flight Information system and is shown the corresponding Flight Information of the flight number.
2. a kind of interactive voice recognition methods based on airport environment according to claim 1, which is characterized in that step S2
Specifically include step：
S21 carries out semantic understanding to the text message, judges whether to have in the text message that meet preset language combination special
The feature phrase of sign, the preset language assemblage characteristic include the language combination feature or English alphabet of Chinese character and number composition
With the language combination feature of number composition；If satisfied, thening follow the steps S22；
S22, according to the semantic understanding to the feature phrase, finds out the feature phrase and corresponds in the flight semantic base
Flight phrase.
3. a kind of interactive voice recognition methods based on airport environment according to claim 1 or 2, which is characterized in that step
Step is specifically included before rapid S5：
S41 issues the user with the confirmation prompt message of the flight number；
S42 parses the operational order of user, if the operational order is when confirming instruction, to execute step S5；Otherwise, step is executed
S43；
S43 prompt users are manually entered flight number, and store flight number input by user.
4. a kind of interactive voice recognition methods based on airport environment according to claim 3, which is characterized in that step S5
Include step later：
S61 counts the occurrence number of the corresponding different characteristic phrase of each flight number；
S62 calculates the weight of each feature phrase according to the occurrence number of the corresponding different characteristic phrase of each flight number.
5. a kind of interactive voice recognition methods based on airport environment according to claim 4, which is characterized in that step
It include step before S41：
S40 judges whether the corresponding weight of feature phrase in the text message reaches default weight, if so, thening follow the steps
S5；Otherwise, step S41 is executed.
6. a kind of interactive voice robot applied to airport, which is characterized in that including：
Text conversion module is used in airport,, will according to speech recognition library if detected that passenger carries out interactive voice
The voice messaging got in interactive voice is converted to text message；
Searching module is electrically connected with the text conversion module, for basis to the semantic understanding of the text message, in flight
In semantic base, the corresponding flight phrase of the text message is found out；
Judgment module is electrically connected with the searching module, for according to the semantic understanding to the flight phrase, judging the boat
Whether contain flight number in class's phrase；
The searching module, if being additionally operable to contain flight number in the flight phrase, according to Flight Information system, described in inquiry
The corresponding Flight Information of flight number；
Display module is electrically connected with the searching module, for showing the corresponding Flight Information of the flight number.
7. a kind of interactive voice robot applied to airport according to claim 6, which is characterized in that further include：
Semantic understanding module is electrically connected with the text conversion module, for carrying out semantic understanding to the text message；
The judgment module is also electrically connected with the semantic understanding module, for judging whether there is satisfaction in the text message
The feature phrase of preset language assemblage characteristic, the preset language assemblage characteristic include the language combination spy of Chinese character and number composition
The language combination feature of sign or English alphabet and number composition；
The searching module, if being additionally operable to have the feature phrase for meeting preset language assemblage characteristic in the text message,
In the flight semantic base, according to the semantic understanding to the feature phrase, the corresponding flight word of the feature phrase is found out
Group.
8. a kind of interactive voice robot applied to airport described according to claim 6 or 7, which is characterized in that further include：
Reminding module is electrically connected with the display module, is additionally operable to issue the user with the flight number really by display module
Recognize prompt message；
Parsing module, the operational order for parsing user；
The reminding module, if it is when confirming instruction, user to be prompted to be manually entered flight number to be additionally operable to the operational order not；
Storage module, for storing flight number input by user.
9. a kind of interactive voice robot applied to airport according to claim 8, which is characterized in that further include：
Statistical module, the occurrence number for counting the corresponding different characteristic phrase of each flight number；
Computing module is electrically connected with the statistical module, for the appearance according to the corresponding different characteristic phrase of each flight number
Number calculates the weight of each feature phrase.
10. a kind of interactive voice robot applied to airport according to claim 9, it is characterised in that：
The judgment module, is additionally operable to judge whether the corresponding weight of feature phrase in the text message reaches default power
Weight；
The reminding module is additionally operable to when the not up to default weight of the corresponding weight of feature phrase in the text message,
The confirmation prompt message of the flight number is issued the user with by display module；
The searching module is additionally operable to when the corresponding weight of feature phrase in the text message reaches default weight, root
According to Flight Information system, the corresponding Flight Information of the flight number is inquired.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810581590.XA CN108777142A (en) | 2018-06-05 | 2018-06-05 | A kind of interactive voice recognition methods and interactive voice robot based on airport environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810581590.XA CN108777142A (en) | 2018-06-05 | 2018-06-05 | A kind of interactive voice recognition methods and interactive voice robot based on airport environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108777142A true CN108777142A (en) | 2018-11-09 |
Family
ID=64024710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810581590.XA Pending CN108777142A (en) | 2018-06-05 | 2018-06-05 | A kind of interactive voice recognition methods and interactive voice robot based on airport environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108777142A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110136700A (en) * | 2019-03-15 | 2019-08-16 | 湖北亿咖通科技有限公司 | A kind of voice information processing method and device |
| CN110364165A (en) * | 2019-07-18 | 2019-10-22 | 青岛民航凯亚系统集成有限公司 | Flight dynamic information voice inquiry method |
| CN110399462A (en) * | 2019-07-26 | 2019-11-01 | 沈阳民航东北凯亚有限公司 | A kind of querying method and device of information |
| CN112084272A (en) * | 2019-06-13 | 2020-12-15 | 上海擎感智能科技有限公司 | Interaction method, device, system and computer readable storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1514387A (en) * | 2002-12-31 | 2004-07-21 | 中国科学院计算技术研究所 | Sound distinguishing method in speech sound inquiry |
| CN1659624A (en) * | 2002-04-05 | 2005-08-24 | 英特尔公司 | Dynamic and adaptive selection of vocabulary and acoustic models based on a call context for speech recognition |
| CN102867511A (en) * | 2011-07-04 | 2013-01-09 | 余喆 | Method and device for recognizing natural speech |
| CN103714048A (en) * | 2012-09-29 | 2014-04-09 | 国际商业机器公司 | Method and system used for revising text |
| CN104021186A (en) * | 2014-06-13 | 2014-09-03 | 中国民航信息网络股份有限公司 | Dynamic intelligent flight information query system and method based on voice recognition |
| CN104021786A (en) * | 2014-05-15 | 2014-09-03 | 北京中科汇联信息技术有限公司 | Speech recognition method and speech recognition device |
| CN105574173A (en) * | 2015-12-18 | 2016-05-11 | 畅捷通信息技术股份有限公司 | Commodity searching method and commodity searching device based on voice recognition |
| CN105632499A (en) * | 2014-10-31 | 2016-06-01 | 株式会社东芝 | Method and device for optimizing voice recognition result |
| CN105976818A (en) * | 2016-04-26 | 2016-09-28 | Tcl集团股份有限公司 | Instruction identification processing method and apparatus thereof |
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | A kind of method and apparatus waking up voice service up |
| CN107393530A (en) * | 2017-07-18 | 2017-11-24 | 国网山东省电力公司青岛市黄岛区供电公司 | Guide service method and device |
| CN107665705A (en) * | 2017-09-20 | 2018-02-06 | 平安科技（深圳）有限公司 | Voice keyword recognition method, device, equipment and computer-readable recording medium |
| CN107704317A (en) * | 2017-08-25 | 2018-02-16 | 深圳天珑无线科技有限公司 | Smart machine and its application management method and the device with store function |
-
2018
- 2018-06-05 CN CN201810581590.XA patent/CN108777142A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1659624A (en) * | 2002-04-05 | 2005-08-24 | 英特尔公司 | Dynamic and adaptive selection of vocabulary and acoustic models based on a call context for speech recognition |
| CN1514387A (en) * | 2002-12-31 | 2004-07-21 | 中国科学院计算技术研究所 | Sound distinguishing method in speech sound inquiry |
| CN102867511A (en) * | 2011-07-04 | 2013-01-09 | 余喆 | Method and device for recognizing natural speech |
| CN103714048A (en) * | 2012-09-29 | 2014-04-09 | 国际商业机器公司 | Method and system used for revising text |
| CN104021786A (en) * | 2014-05-15 | 2014-09-03 | 北京中科汇联信息技术有限公司 | Speech recognition method and speech recognition device |
| CN104021186A (en) * | 2014-06-13 | 2014-09-03 | 中国民航信息网络股份有限公司 | Dynamic intelligent flight information query system and method based on voice recognition |
| CN105632499A (en) * | 2014-10-31 | 2016-06-01 | 株式会社东芝 | Method and device for optimizing voice recognition result |
| CN105574173A (en) * | 2015-12-18 | 2016-05-11 | 畅捷通信息技术股份有限公司 | Commodity searching method and commodity searching device based on voice recognition |
| CN105976818A (en) * | 2016-04-26 | 2016-09-28 | Tcl集团股份有限公司 | Instruction identification processing method and apparatus thereof |
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | A kind of method and apparatus waking up voice service up |
| CN107393530A (en) * | 2017-07-18 | 2017-11-24 | 国网山东省电力公司青岛市黄岛区供电公司 | Guide service method and device |
| CN107704317A (en) * | 2017-08-25 | 2018-02-16 | 深圳天珑无线科技有限公司 | Smart machine and its application management method and the device with store function |
| CN107665705A (en) * | 2017-09-20 | 2018-02-06 | 平安科技（深圳）有限公司 | Voice keyword recognition method, device, equipment and computer-readable recording medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110136700A (en) * | 2019-03-15 | 2019-08-16 | 湖北亿咖通科技有限公司 | A kind of voice information processing method and device |
| CN110136700B (en) * | 2019-03-15 | 2021-04-20 | 湖北亿咖通科技有限公司 | Voice information processing method and device |
| CN112084272A (en) * | 2019-06-13 | 2020-12-15 | 上海擎感智能科技有限公司 | Interaction method, device, system and computer readable storage medium |
| CN110364165A (en) * | 2019-07-18 | 2019-10-22 | 青岛民航凯亚系统集成有限公司 | Flight dynamic information voice inquiry method |
| CN110399462A (en) * | 2019-07-26 | 2019-11-01 | 沈阳民航东北凯亚有限公司 | A kind of querying method and device of information |
| CN110399462B (en) * | 2019-07-26 | 2022-03-04 | 沈阳民航东北凯亚有限公司 | Information query method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108777142A (en) | A kind of interactive voice recognition methods and interactive voice robot based on airport environment | |
| CN107204184B (en) | Audio recognition method and system | |
| CN109063035A (en) | A kind of man-machine more wheel dialogue methods towards trip field | |
| CN107665706B (en) | Rapid voice interaction method and system | |
| US20190251417A1 (en) | Artificial Intelligence System for Inferring Grounded Intent | |
| CN108984650B (en) | Computer-readable recording medium and computer device | |
| CN107665708A (en) | Intelligent sound exchange method and system | |
| CN106683662A (en) | Speech recognition method and device | |
| JP6637947B2 (en) | Cognitive robotics analyzer | |
| US20150302056A1 (en) | Method, system, and storage medium for information search | |
| CN102439661A (en) | Service oriented speech recognition for in-vehicle automated interaction | |
| CN105096942A (en) | Semantic analysis method and semantic analysis device | |
| US20210343287A1 (en) | Voice processing method, apparatus, device and storage medium for vehicle-mounted device | |
| US20210019370A1 (en) | Neural relation extraction within and across sentence boundaries | |
| CN106202270A (en) | Interactive method based on natural language and device | |
| Pieraccini et al. | Stochastic representation of conceptual structure in the ATIS task | |
| US20140214406A1 (en) | Method and system of adding punctuation and establishing language model | |
| CN111027309A (en) | Method for extracting entity attribute value based on bidirectional long-short term memory network | |
| WO2023108994A1 (en) | Sentence generation method, electronic device and storage medium | |
| CN115099239B (en) | Resource identification method, device, equipment and storage medium | |
| CN111309876A (en) | Service request processing method and device, electronic equipment and storage medium | |
| CN108520065B (en) | Method, system, equipment and storage medium for constructing named entity recognition corpus | |
| WO2019165732A1 (en) | Robot emotional state-based reply information generating method and apparatus | |
| CN112541095A (en) | Video title generation method and device, electronic equipment and storage medium | |
| US10319378B2 (en) | Interaction apparatus and method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181109 |
|
| RJ01 | Rejection of invention patent application after publication |