CN109492795A - Airport boarding service processing method, device, equipment and medium based on AI - Google Patents
Airport boarding service processing method, device, equipment and medium based on AI Download PDFInfo
- Publication number
- CN109492795A CN109492795A CN201811182179.1A CN201811182179A CN109492795A CN 109492795 A CN109492795 A CN 109492795A CN 201811182179 A CN201811182179 A CN 201811182179A CN 109492795 A CN109492795 A CN 109492795A
- Authority
- CN
- China
- Prior art keywords
- boarding
- identified
- obtains
- identification
- gate position
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 230000004044 response Effects 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000011946 reduction process Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 38
- 238000000034 method Methods 0.000 abstract description 27
- 230000008569 process Effects 0.000 description 14
- 230000006870 function Effects 0.000 description 12
- 239000011159 matrix material Substances 0.000 description 6
- 238000009432 framing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 206010052428 Wound Diseases 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
Abstract
The present invention discloses a kind of airport boarding service processing method, device, equipment and medium based on AI, the airport boarding service processing method based on AI includes: to obtain boarding service request, processing and gray processing processing are sharpened to the original boarding card image in boarding service request, obtain boarding card image to be identified；It is positioned, is obtained N number of text filed using text detection network handles identification boarding card image；Based on each text filed position in boarding card to be identified, each text filed be input in corresponding dedicated identification model is identified according to the scene template marked in advance, obtains boarding attribute information；To automatically obtain user to boarding gate position target optimal route.This method uses the corresponding boarding attribute information in artificial intelligence (AI) means intelligent recognition this article one's respective area, to obtain boarding gate position, Automatic-searching user current location is saved the time for finding boarding gate position, is improved efficiency to the optimal route of boarding gate position.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of airport boarding service processing methods based on AI, dress
It sets, equipment and medium.
Background technique
With the rapid development of Civil Aviation Industry, the passenger demand of rapid growth and gradually complicated aeronautical environment, to airport and
Airline brings new challenge.Currently, in the self-help service method of airport, the flight number being only capable of in identification boarding card, if thinking
Obtain the corresponding boarding gate position of flight number, it is also necessary to third party airport platform be searched according to flight number, to obtain boarding gate position
It sets, is unable to boarding gate position of the Direct Recognition into boarding card.It and automatically cannot be passenger's planning in conjunction with the technology of indoor navigation
To the optimal route of boarding gate position, passenger is caused to take a significant amount of time on finding boarding gate, expends the time.
Summary of the invention
The embodiment of the present invention provides a kind of airport boarding service processing method, device, equipment and medium based on AI, with solution
Certainly current airport Self-Service is unable to boarding gate position of the Direct Recognition into boarding card and cannot be in conjunction with the technology of indoor navigation
Automatically the problem of wasting time caused by the optimal route to boarding gate position is planned for passenger.
A kind of airport boarding service processing method based on AI, comprising:
Boarding service request is obtained, the boarding service request includes original boarding card image；
Processing and gray processing processing are sharpened to the original boarding card image, obtain boarding card image to be identified；
The boarding card image to be identified is positioned using text detection network, is obtained N number of text filed；
Based on each text filed position in the boarding card image to be identified, according to the field marked in advance
Scape template identifies each text filed be input in corresponding dedicated identification model, obtains boarding attribute information,
The boarding attribute information includes identification boarding gate position；
Based on the identification boarding gate position and user current location, the indoor navigation interface being pre-created is called, is obtained
Take family to boarding gate position target optimal route.
A kind of airport boarding service processing device based on AI, comprising:
Boarding service request obtains module, and for obtaining boarding service request, the boarding service request includes original steps on
Machine board image；
Boarding card image collection module to be identified, for being sharpened processing and gray processing to the original boarding card image
Processing, obtains boarding card image to be identified；
Text filed acquisition module, for being positioned using text detection network to the boarding card image to be identified,
It obtains N number of text filed；
Boarding gate position acquisition module is identified, for based on each described text filed in the boarding card image to be identified
In position, described text filed be input in corresponding dedicated identification model according to the scene template that has marked in advance by each
It is identified, obtain boarding attribute information, the boarding attribute information includes identification boarding gate position；
Target optimal route obtains module, for being based on the identification boarding gate position and user current location, calls pre-
First indoor navigation interface created, the target optimal route of acquisition user to boarding gate position.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize the above-mentioned airport boarding clothes based on AI when executing the computer program
The step of processing method of being engaged in.
A kind of non-volatile memory medium, the non-volatile memory medium are stored with computer program, the computer
The step of above-mentioned airport boarding service processing method based on AI is realized when program is executed by processor.
In above-mentioned airport boarding service processing method, device, equipment and medium based on AI, server is stepped on by first obtaining
Machine service request obtains to be sharpened processing and gray processing processing to the original boarding card image in boarding service request
Boarding card image to be identified reduces image complexity and information processing capacity with exclusive PCR.Then, using text detection network
Boarding card image to be identified is positioned, acquisition is N number of text filed, each text filed in boarding card to be identified to be based on
In position, each text filed be input in corresponding dedicated identification model is carried out according to the scene template that has marked in advance
Identification, obtain boarding attribute information, by using dedicated identification model to it is each it is text filed identify, greatly improve and step on
The accuracy rate of machine board image recognition.Finally, based in boarding attribute information identification boarding gate position and user current location, adjust
With the indoor navigation interface being pre-created, the target optimal route of acquisition user to boarding gate position, so that user is according to mesh
Mark optimal route searches out boarding gate position.This method, which passes through, obtains each text filed position in boarding card to be identified,
To use the corresponding boarding attribute information in artificial intelligence (AI) means intelligent recognition this article one's respective area, to obtain boarding attribute
Boarding gate position in information, and combine indoor navigation interface Automatic-searching to the optimal route of boarding gate position, effectively save
It the time for finding boarding gate position, improves efficiency.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is an application environment schematic diagram of the airport boarding service processing method in one embodiment of the invention based on AI；
Fig. 2 is a flow chart of the airport boarding service processing method in one embodiment of the invention based on AI；
Fig. 3 is a specific flow chart of step S30 in Fig. 2；
Fig. 4 is another flow chart of the airport boarding service processing method in one embodiment of the invention based on AI；
Fig. 5 is the another flow chart of the airport boarding service processing method in one embodiment of the invention based on AI；
Fig. 6 is a specific flow chart of step S63 in Fig. 5；
Fig. 7 is a specific flow chart of step S50 in Fig. 2；
Fig. 8 is a schematic diagram of the airport boarding service processing device in one embodiment of the invention based on AI；
Fig. 9 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Airport boarding service processing method provided by the present application based on AI, can be applicable in the application environment such as Fig. 1, should
Airport boarding service processing method based on AI can be applicable in airport Self-Service APP, for filling up the self-service clothes in current airport
The blank of business, auxiliary user are independently checked in, are improved efficiency.Wherein, computer equipment passes through network and service
Device is communicated.Computer equipment can be, but not limited to various personal computers, laptop, smart phone, tablet computer
With portable wearable device.Server can be realized with independent server.
In one embodiment, as shown in Fig. 2, providing a kind of airport boarding service processing method based on AI, in this way
It applies and is illustrated for the server in Fig. 1, include the following steps:
S10: boarding service request is obtained, boarding service request includes original boarding card image.
Wherein, original boarding card image be by the information acquisition module in airport Self-Service APP it is collected without
The image comprising boarding card of reason.Boarding service request is that the request of Self-Service is carried out for departure airport Self-Service APP.
Specifically, user uploads original boarding card image by the information acquisition module in APP, so that server obtains original boarding card
Image.The acquisition mode of the information acquisition module includes but is not limited to camera shooting and local upload.
S20: processing is sharpened to original boarding card image and gray processing is handled, obtains boarding card image to be identified.
Wherein, boarding card image to be identified, which refers to, is sharpened processing and gray processing to original boarding card image treated
Image.Specifically, it in order to be apparent from the details of the edge of image, contour line and image, needs first to original boarding card figure
As being sharpened processing, sharpening image is obtained.After obtaining sharpening image, due to that may include multiple color in sharpening image,
And color itself is highly susceptible to the influence of the factors such as illumination, similar object color has many variations, so color itself is difficult
To provide key message, it is therefore desirable to gray processing processing is carried out to sharpening image, obtains boarding card image to be identified, it is dry to exclude
It disturbs, reduces image complexity and information processing capacity.
In the present embodiment, the method for Edge contrast includes but is not limited to Laplace operator, sobel (weighted average difference)
Operator and Prewitt (average difference) operator.By taking sobel Operator Method as an example, following formula can be used to original boarding card figure
As corresponding picture element matrix M (i, j) is converted:
A=| (M (i-1, j-1)+2M (i-1, j)+M (i-1, j+1))-(M (i+1, j-1)+2M (i+1, j)+M (i+1, j+
1))|
B=| (M (i-1, j-1)+2M (i, j-1)+M (i+1, j-1))-(M (i-1, j+1)+2M (i, j+1)+M (i+1, j+
1)) S (i, j)=A+B
Wherein, M (i, j) indicates the corresponding picture element matrix of original boarding card image.I and j represents the row and column of matrix.S (i,
J) indicate that the corresponding picture element matrix of sharpening image, A indicate that the picture element matrix after the convolution of horizontal direction, B indicate vertical direction
Picture element matrix after convolution.
S30: it is positioned, is obtained N number of text filed using text detection network handles identification boarding card image.
Wherein, text detection network includes but is not limited to ctpn network (Connectionist Text Proposal
Network, text detection network).Ctpn network is the common network for carrying out pictograph positioning, and text can be accurately positioned
Originally the accuracy rate of following model identification is improved in position in the picture.
Due to needing to identify the region in image containing text when following model identification, to exclude non-textual region
Interference, it is therefore desirable to first determine text filed.It is text filed to refer in boarding card image to be identified only comprising the region of text.Tool
Body, server are positioned using text detection network handles identification boarding card image, to obtain N number of rectangle frame and each
Each vertex position coordinate of rectangle frame；The position coordinates in the upper left corner based on rectangle frame and the lower right corner again determine the length of rectangle frame
And width；And the position coordinates in the upper left corner, the lower right corner based on rectangle frame and the length and width of rectangle frame, obtain N number of text
One's respective area.
S40: based on each text filed position in boarding card image to be identified, according to the scene mould marked in advance
Plate identifies each text filed be input in corresponding dedicated identification model, obtains boarding attribute information, boarding attribute
Information includes identification boarding gate position.
Wherein, boarding attribute information is the attribute information that can be learnt from boarding card, which includes trip
Different surname name, flight, date, destination, boarding gate position and boarding time etc..Scene template refers to developer previously according to city
The template that various boarding card images are established on face sets the corresponding scene word of every a line in boarding card image in the scene template
Section, the first behavior name, the second behavior flight, the third line are destination in boarding card as and boarding gate, fourth line are day
Phase and boarding time.Dedicated identification model is used exclusively for identifying the model of certain specific image.
In the present embodiment, dedicated identification model includes letter and digital identification model and Chinese Character Recognition model.Letter and number
Word identification model is for identification comprising number and alphabetical model.Chinese Character Recognition model is the model of Chinese character for identification.Tool
Body, server is based on the text filed position coordinates in boarding card to be identified, in a manner of reduced coordinates, determines each text
Which rectangle frame corresponding one's respective area is.For example, two rectangles got, it is assumed that with the upper left corner of one of rectangle frame
For origin, then the coordinate in the lower left corner of the rectangle frame is (0, -3), then the top left co-ordinate of another rectangle frame is that (0, -4) then may be used
Assert that (0, -4) corresponding rectangle frame is the second row, and (0, -3) corresponding rectangle frame is the first row.Then, according to preparatory mark
Good scene template identifies each text filed be input in corresponding dedicated identification model, to obtain boarding attribute letter
Breath.For example, being defaulted as surname according to the corresponding text filed content of scene template the first row rectangle frame marked in advance
Name, and name is Chinese character composition, therefore can be input to this article one's respective area in Chinese Character Recognition model and identify, to obtain boarding
Attribute information.In the present embodiment, by by different content it is corresponding it is text filed be input in corresponding dedicated identification model into
Row identification avoids the problem not high using recognition accuracy caused by extensive identification model, greatlys improve boarding card image
The accuracy rate of identification.
Further, airport Self-Service APP can provide registering flow path guide also for user, when user's success Register
When the Self-Service APP of field, server will give user to push boarding process guide, so that passenger for the first time by air being capable of basis
Registering flow path guide is checked in, and without inquiring airport employe, facilitates the trip of passenger, while reducing airport work
The workload of personnel.
S50: based on identification boarding gate position and user current location, the indoor navigation interface being pre-created is called, is obtained
Take family to boarding gate position target optimal route.
Wherein, obtained by identification boarding gate position is referred to and identified using dedicated identification model to boarding card image to be identified
To boarding card image to be identified in boarding gate position.User current location refers to that user is locating in airport at current time
Position.Specifically, server is based on identification boarding gate position, calls the indoor navigation interface being pre-created, and obtains user
It is avoided to the target optimal route of boarding gate position so that user searches out boarding gate position according to target optimal route because not
It is familiar with airport environment and leads to the problem of wasting plenty of time searching boarding gate position appearance.
In the present embodiment, server is by first obtaining boarding service request, to step on to original in boarding service request
Machine board image is sharpened processing and gray processing processing, obtains boarding card image to be identified, and with exclusive PCR, it is complicated to reduce image
Degree and information processing capacity.Then, it is positioned using text detection network handles identification boarding card image, obtains N number of text area
Domain will be each according to the scene template marked in advance so as to based on each text filed position in boarding card to be identified
Text filed be input in corresponding dedicated identification model is identified, boarding attribute information is obtained, by using dedicated identification
Model to it is each it is text filed identify, can effectively avoid not high using recognition accuracy caused by extensive identification model
Problem greatlys improve the accuracy rate of boarding card image recognition.Finally, based on identification boarding gate position and user current location,
Call the indoor navigation interface that has been pre-created, the target optimal route of acquisition user to boarding gate position, so as to user according to
Target optimal route searches out boarding gate position.This, which passes through, obtains each text filed position in boarding card to be identified, with
Just the corresponding boarding attribute information in artificial intelligence (AI) means intelligent recognition this article one's respective area is used, to obtain boarding attribute letter
Boarding gate position in breath, and combine indoor navigation interface Automatic-searching to the optimal route of boarding gate position, it avoids because not yet done
Knowing airport environment causes to waste plenty of time searching boarding gate position, saves the time for finding boarding gate position.
In one embodiment, as shown in figure 3, in step S30, i.e., boarding card image is identified using text detection network handles
It is positioned, acquisition is N number of text filed, specifically comprises the following steps:
S31: it is positioned using text detection network handles identification boarding card image, obtains positioning coordinate.
Specifically, server is positioned using text detection network handles identification boarding card image, to obtain N number of rectangle
Frame and the position coordinates on each vertex of each rectangle frame, then from the position coordinates on each vertex choose the upper left corner position coordinates and
The position coordinates in the lower right corner are cut so as to subsequent based on positioning coordinate pair boarding card image to be identified as positioning coordinate.
S32: it is cut, is obtained N number of text filed based on positioning coordinate pair boarding card image to be identified.
Specifically, server determines the length and width of rectangle frame based on positioning coordinate, further according to positioning coordinate, rectangle frame
Length and width cut, obtain that N number of rectangle frame is corresponding text filed, so as to the subsequent text area by after each cutting
Domain is input in dedicated identification model and is identified.
In the present embodiment, is first positioned using text detection network handles identification boarding card image, obtains positioning coordinate,
To determine the length and width of rectangle frame based on positioning coordinate, carried out further according to the length and width of positioning coordinate, rectangle frame
It cuts, obtains that N number of rectangle frame is corresponding text filed, the text filed method of the acquisition is realized simple, and can effectively obtain institute
Need to be text filed, so that subsequent text filed be input in dedicated identification model by after each cutting identifies.
In one embodiment, boarding service request further includes user information.As shown in figure 4, AI should be based on after step 40
Airport boarding service processing method further include following steps:
S411: third party airport platform is searched based on user information, acquisition is corresponding with the user information currently to step on
Machine mouth position and current check-in state.
Wherein, current boarding gate position refers to corresponding with user information in the platform of current time third party airport step on
Machine mouth position.Current check-in state be confirmation user current time whether the state of boarding.It is understood that current check-in state packet
Include boarding state and non-boarding state.Specifically, user can be when registering airport Self-Service APP, by user identity card number
It is bound with airport Self-Service APP, so that server when obtaining boarding service request, is directly read and APP binding
User information (i.e. user identity card number), to search third party airport platform based on the user information, obtains and the user
The corresponding current boarding gate position of information and current check-in state.Understandably, third party airport platform and the self-service clothes in airport
APP be engaged in by network interface connection, to obtain current boarding gate position in real time.
S412: when current check-in state is in non-boarding state, by current boarding gate position and identification boarding gate position
It is matched, if it fails to match, generates prompting message.
Specifically, server by current boarding gate position and is known when confirming that current check-in state is in non-boarding state
Other boarding gate position is matched, if successful match, proves that boarding gate corresponding with user information position does not change
Become.If it fails to match, prove that change occurred for boarding gate corresponding with user information position, generates prompting message and remind
User boarding gate shift in position, avoids the problem that missing flight, causes economic loss.
Further, in this embodiment present system time is also judged whether within the scope of the variable of boarding time, if
Present system time then generates boarding prompting information within the scope of the variable of boarding time, to prompt user's boarding as early as possible, keeps away
Exempting from user leads to the problem of missing flight because not having the attention time.Wherein, the variable range of boarding time is to guarantee that user can
The mobility scale of timely boarding, in the present embodiment, the variable range of boarding time is 30 minutes.If such as user's boarding time
It is whole for 2 pm, then the variable range that be the boarding time is assigned to afternoon 1: 30 at 2 points, when the current time in system is in the boarding time
Variable within the scope of, then prompt the timely boarding of user in the way of the user's boarding of prompt in every 10 minutes.Understandably,
If the current check-in state of user is boarding state, prompt information will not be generated, it is practical, when can effectively avoid because not having
Pay attention to the time and leads to the problem of missing flight.
In the present embodiment, when server APP registered in advance based on user, bound identification card number (user information) was looked into
Third party airport platform is looked for, current boarding gate position corresponding with user information and current check-in state are obtained, so as to real-time
Analyze whether current boarding gate position changes.If when current check-in state is in non-boarding state, by current boarding gate
Position is matched with identification boarding gate position, if it fails to match, is generated prompting message and is reminded user boarding gate shift in position,
It avoids the problem that missing flight, causes economic loss.
Further, while generating prompting message, it also will pop up and prompt the user whether to need the optimal road of more fresh target
The information of line generates update route request if user selects "Yes", server can based on receive this more variation route is asked
It asks, will identify boarding gate location updating, i.e., using current boarding gate position as identifying boarding gate position, and by updated identification
Boarding gate position and user current location are input in the indoor navigation interface being pre-created, with more fresh target optimal route,
It, can be as early as possible according to update when encountering boarding gate position and changing to achieve the purpose that real-time update target optimal route
The pathfinding of target optimal route saves the time to the boarding gate position updated.
In one embodiment, as shown in figure 5, being somebody's turn to do the airport boarding service processing method based on AI further includes following steps:
S61: obtaining voice assisted request, and voice assisted request includes original speech information.
Wherein, voice assisted request is the request for voice assistant function in departure airport Self-Service APP.Specifically
Ground, user can be by recording module (such as microphone) typing original speech informations in APP, so that server obtains voice assisted
Request.Original speech information refers to recording module collected untreated voice messaging in real time, and such as " I buys one before thinking boarding
A little specialties " and " my certificate is lost, and where can provide help to me " etc..
S62: noise reduction process is carried out to original speech information, obtains target voice information.
Due to collecting original speech information generally all in noise, including background environment (airport) by computer equipment
Noise and computer equipment Recording Process in the noise that generates.These original speech informations for carrying noise are carrying out voice
When identification, the accuracy of speech recognition will affect, therefore, it is necessary to carry out noise reduction process to original speech information, to mention as far as possible
Purer target voice information is got, keeps speech recognition more accurate.Wherein, the method for noise reduction being carried out to original speech information
Including but not limited to using spectrum-subtraction, EEMD decomposition algorithm and the unusual value-based algorithm of SVD etc..
S63: target voice information input is identified into preparatory trained speech recognition modeling, obtains identification text
This.
Wherein, speech recognition modeling is trained in advance for target voice information to be identified as to the model of text.It should
The training data of speech recognition modeling is acquisition existing Chinese dialogue library, address keyword library, Chinese and English common words at present
The voice messaging in library and directive statement library composition, while the application scenarios of base in this present embodiment are mixed with machine in voice messaging
Field noise is trained as training data, to enhance the accuracy rate of speech recognition.
S64: it will identify that text carries out speech analysis according to the semantic analysis rule built in advance, obtain keyword.
Specifically, before it will identify that text carries out speech analysis according to the semantic analysis rule built in advance, elder generation is needed
Identification text information is segmented using stammerer participle tool, obtains word, and word is input to the language built in advance
Semantic analysis is carried out in adopted analysis rule, obtains corresponding keyword.Semantic analysis rule is that developer builds in advance
For obtaining the semantic rules of keyword.Such as the identification text currently recognized is " I wants to buy some specialties ", then should
Section identification text segmented to obtain " I buys/some/specialty at/thinking/", then to participle obtain " I buys/mono- at/thinking/
A bit/specialty " carries out semantic analysis according to the semantic analysis rule built in advance, obtains keyword " purchase " and " specialty ".
S65: keyword being input in preparatory trained intelligent response model and is identified, obtains voice assisted letter
Breath.
Wherein, intelligent response model is preparatory trained answer model, and training data is pre-set problem
Keyword and corresponding answer.Voice assisted information is that server puts question to the information for obtaining corresponding answer based on user.Specifically
Ground, the keyword that will acquire are input in preparatory trained intelligent response model and are identified, to obtain voice assisted letter
Breath.
For example, corresponding intelligent response model is trained using the relevant information on local airport in advance, if above-mentioned steps
Obtained in keyword be " purchase " and " specialty ", then intelligent response model can pass through the keyword " purchase " that recognizes and " spy
Produce ", direct response goes out the position that and retail shop local products have, and forms response and recommends point.If user wants to open navigation,
" navigation " button can be then clicked, with input position navigation requests, which carries the position letter that point is recommended in response
Breath.By the position, navigation requests are sent to server, so that point is recommended in the response that server is selected based on user, open wound in advance
The indoor navigation system built up obtains and navigates to the navigation routine (navigation routine of i.e. a certain target retail shop) that point is recommended in response,
And show the navigation routine on interactive interface, so that user quickly reaches target retail shop position, the pathfinding time is saved, is improved
Efficiency.
In the present embodiment, server first obtains voice assisted request, so that the raw tone in requesting voice assisted is believed
Breath carries out noise reduction process, and obtaining target voice information to extract purer target voice information as far as possible makes subsequent voice
It is more accurate to identify.Then, target voice information input is identified into preparatory trained speech recognition modeling, is obtained
It identifies text, to identify that text carries out speech analysis according to the semantic analysis rule built in advance, obtains keyword, nothing
Manual intervention is needed, acquisition keyword can be automatically analyzed, and keyword is input in preparatory trained intelligent response model
It is identified, obtains voice assisted information, realize the function of voice assistant, to realize Self-Service, and effectively reduce airport
The workload of staff.
In one embodiment, as shown in fig. 6, in step S63, i.e., by target voice information input to preparatory trained language
It is identified in sound identification model, obtains identification text, specifically comprise the following steps:
S631: pre-processing target voice information, obtains voice messaging to be identified.
Wherein, carrying out pretreatment to target voice includes: framing, adding window and preemphasis.Framing is by N number of sampled point set
At an observation unit, referred to as frame.The value of N is 256 or 512 under normal conditions, and the time covered is about 20-30ms or so.For
Avoid the variation of adjacent two frame excessive, by making have one section of overlapping region between adjacent two frame, this overlapping region contains M and adopts
Sampling point, the value of usual M are about the 1/2 or 1/3 of N, this process is known as framing.
Adding window is each frame multiplied by Hamming window (i.e. Hamming Window), since the amplitude-frequency characteristic of Hamming window is that secondary lobe declines
Subtract it is larger, server by single frames voice data carry out windowing process, the continuity of frame left end and frame right end can be increased.It is i.e. logical
It crosses and windowing process is carried out to the single frames voice data after framing, non stationary speech signal can be changed into short-term stationarity signal.If
Signal after framing is S (n), n=0,1 ..., and N-1, N are the size of frame, and the signal of Hamming window is W (n), then after windowing process
Signal is S'(n)=S (n) × W (n, whereinN is the size of frame,
Different a values can generate different Hamming windows, and a takes 0.46 under normal circumstances.
Preemphasis is that the single frames voice data after adding window is passed through a high-pass filter H (Z)=1- μ z-1, wherein μ value
Between 0.9-1.0, Z indicates single frames voice data, and the target of preemphasis is to promote high frequency section, keeps the frequency spectrum of signal more flat
It is sliding, low frequency is maintained at into the entire frequency band of high frequency, and frequency spectrum, the formant of prominent high frequency can be asked with same signal-to-noise ratio.
S632: speech feature extraction is carried out to voice messaging to be identified, obtains target voice feature.
Wherein, target voice feature includes but is not limited to use filter (Filter-Bank, abbreviation Fbank) feature.Filter
Wave device is characterized in common phonetic feature in speech recognition process.Due to the meeting pair in model identification process of common Meier feature
Information carries out dimension-reduction treatment, leads to the loss of partial information, in order to avoid the above problems, special using filter in the present embodiment
Sign replaces common Meier feature, can help to the accuracy rate for improving following model identification.Correspondingly, target voice is characterized in adopting
Filter characteristic acquired in feature extraction is carried out to voice messaging to be identified with ASR speech feature extraction algorithm.ASR
(Automatic Speech Recognition, automatic speech recognition) is a kind of technology that the voice of people is converted to text.
ASR speech feature extraction algorithm is the algorithm in ASR technology for realizing speech feature extraction.Filter (Filter-Bank,
Abbreviation Fbank) it is characterized in common phonetic feature in speech recognition process.
S633: target voice feature is input in preparatory trained speech recognition modeling and is identified, identification is obtained
Text.
It is understood that speech recognition modeling includes preparatory trained acoustic model and language model.Wherein, acoustic model is
For obtaining the corresponding aligned phoneme sequence of target voice feature.Phoneme is by unit the smallest in voice, it will be appreciated that for inside Chinese character
Phonetic.Such as: Chinese syllable ā () only one phoneme, à i (love) is there are two phoneme, and there are three phonemes etc. by d ā i (slow-witted).Sound
The training method for learning model includes but is not limited to that GMM-HMM (mixed Gauss model) is used to be trained.Language model is to be used for
Aligned phoneme sequence is converted to the model of natural language text.In the present embodiment, N-Gram language model is can be used in language model.N-
Gram is common a kind of language model in large vocabulary continuous speech recognition, using the collocation information between word adjacent in context,
When needing the phonetic continuously without space to be converted into Chinese character string (i.e. sentence), the sentence with maximum probability can be calculated,
To realize the automatic conversion for arriving sentence.
Specifically, target voice feature is input in preparatory trained acoustic model and identifies by server, obtains
The corresponding aligned phoneme sequence of target voice feature, the aligned phoneme sequence that then will acquire be input in preparatory trained language model into
Row conversion will identify that text carries out voice according to the semantic analysis rule built in advance to obtain identification text so as to subsequent
Analysis, realizes the function of voice assistant.
In one embodiment, as shown in fig. 7, in step S50, i.e., based on identification boarding gate position, calling is pre-created
Indoor navigation interface, obtain target optimal route, specifically comprise the following steps:
S51: obtaining indoor navigation instruction, obtains the collected current demand signal of signal receiver based on indoor navigation instruction
Distance.
Wherein, indoor navigation instruction is the instruction for triggering indoor navigation acquisition user current location.Specifically, it is obtaining
After getting identification boarding gate position, " navigation " button can be shown on interactive interface, user can click " navigation " as needed and press
Button calls preparatory mounted signal receiver reception user in airport to be taken so that server obtains indoor navigation instruction
The current position signal and current demand signal distance that the computer equipment of band is issued.Current position signal refers to user in current institute
When locating position, entrained by the signal that is issued of computer equipment.The current position signal includes but is not limited to Bluetooth signal
Or network signal (including but not limited to wifi, 2G, 3G and 4G).Current demand signal distance refers to each current position signal to signal
The distance of receiving device.It needs to illustrate, the signal receiver installed in airport may be configured as N number of, it is preferable that in the present embodiment
It is 3, can voluntarily adjusts according to demand.
S52: being handled current demand signal distance using Pythagorean theorem, obtains user current location.
Wherein, Pythagorean theorem refers generally to Pythagorean theorem, is a basic geological theorems.Specifically, pass through letter
Number receiving device receives current position signal, to obtain distance i.e. d1, d2 that current demand signal distance arrives each signal receiver
And d3 makees three circles by radius of d1, d2 and d3 then using the location of each signal receiver coordinate as the center of circle.Root
Current demand signal distance is handled according to Pythagoras calculation formula, obtains three round intersection points i.e. user current location, with
Just the indoor navigation interface that subsequent calls have been pre-created realizes navigation feature.Wherein, the calculation formula of Pythagorean theorem
For Wherein, (x1,y1), (x2,y2),(x3,y3) 3 points be respectively in advance in airport
The position coordinates point of the signal receiver of setting.(x0,y0) it is user current location.
S53: based on user current location and identification boarding gate position, the interior for calling optimal path acquisition algorithm to provide is led
Boat interface handles user current location and identification boarding gate position, obtains target optimal route.
Specifically, by user current location and identification boarding gate position, the interior provided by optimal path acquisition algorithm
Navigation interface is input in optimal path acquisition algorithm and is calculated, to obtain target optimal route, so that user is according to target
It goes optimal route pathfinding to boarding gate position, reduces the risk missed flight.In the present embodiment, optimal path acquisition algorithm includes but not
It is limited to realize using A* algorithm.Wherein, A* (A-Star) algorithm is that solve shortest path in a kind of static road network figure most effective
Direct search method, and solve the problems, such as the efficient algorithm of many search.
In the present embodiment, server is connect by obtaining indoor navigation instruction to obtain signal based on indoor navigation instruction
The collected current demand signal distance of receiving unit, and according to current demand signal distance, it obtains current demand signal distance and is received to each signal
Distance, that is, d1, d2 and d3 of equipment, then current demand signal distance is handled using Pythagorean theorem, it is current to obtain user
Position obtains mesh to call the indoor navigation interface being pre-created based on user current location and identification boarding gate position
Optimal route is marked, the pathfinding of target optimal route is based on to boarding gate convenient for user, saves the pathfinding time, improve efficiency.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of airport boarding service processing device based on AI is provided, it should the airport boarding based on AI
Airport boarding service processing method in service processing device and above-described embodiment based on AI corresponds.As shown in figure 8, the base
It include that boarding service request obtains module 10, boarding card image collection module to be identified in the airport boarding service processing device of AI
20, text filed acquisition module 30, identification boarding gate position acquisition module 40 and target optimal route obtain module 50.Each function
Detailed description are as follows for module:
Boarding service request obtains module 10, and for obtaining boarding service request, boarding service request includes original boarding
Board image.
Boarding card image collection module 20 to be identified, for being sharpened at processing and gray processing to original boarding card image
Reason, obtains boarding card image to be identified.
Text filed acquisition module 30 is obtained for being positioned using text detection network handles identification boarding card image
It takes N number of text filed.
Boarding gate position acquisition module 40 is identified, for based on each text filed position in boarding card image to be identified
It sets, identifies each text filed be input in corresponding dedicated identification model according to the scene template marked in advance,
Boarding attribute information is obtained, boarding attribute information includes identification boarding gate position.
Target optimal route obtains module 50, for calling preparatory based on identification boarding gate position and user current location
Indoor navigation interface created, the target optimal route of acquisition user to boarding gate position.
Specifically, text filed acquisition module includes positioning coordinate acquiring unit and text filed acquiring unit.
Coordinate acquiring unit is positioned, for being positioned using text detection network handles identification boarding card image, is obtained
Position coordinate.
Text filed acquiring unit obtains N number of text for being cut based on positioning coordinate pair boarding card image to be identified
One's respective area.
Specifically, boarding service request further includes user information.The airport boarding service processing device based on AI also wraps
Include platform information feedback unit and prompting message generation unit.
Platform information feedback unit obtains and user information phase for searching third party airport platform based on user information
Corresponding current boarding gate position and current check-in state.
Prompting message generation unit is used for when current check-in state is in non-boarding state, by current boarding gate position
It is matched with identification boarding gate position, if it fails to match, generates prompting message.
Specifically, being somebody's turn to do the airport boarding service processing device based on AI further includes voice assisted request unit, target
Voice messaging acquiring unit, identification text acquiring unit, keyword acquiring unit and voice assisted information acquisition unit.
Voice assisted request unit, for obtaining voice assisted request, voice assisted request includes that raw tone is believed
Breath.
Target voice information acquisition unit obtains target voice information for carrying out noise reduction process to original speech information.
Identify text acquiring unit, for by target voice information input into preparatory trained speech recognition modeling into
Row identification obtains identification text.
Keyword acquiring unit, for that will identify that text carries out voice point according to the semantic analysis rule built in advance
Analysis obtains keyword.
Voice assisted information acquisition unit is carried out for keyword to be input in preparatory trained intelligent response model
Identification obtains voice assisted information.
Specifically, identification text acquiring unit includes that voice messaging to be identified obtains subelement, target voice feature obtains
Subelement and identification text obtain subelement.
Voice messaging to be identified obtains son list, subelement is obtained for voice messaging to be identified, for target language message
Breath is pre-processed, and voice messaging to be identified is obtained.
Target voice feature obtains subelement, for carrying out speech feature extraction to voice messaging to be identified, obtains target
Phonetic feature.
Identify that text obtains subelement, for target voice feature to be input in preparatory trained speech recognition modeling
It is identified, obtains identification text.
Specifically, it includes indoor navigation instruction acquisition unit, user current location acquisition that target optimal route, which obtains module,
Unit and target optimal route acquiring unit.
Indoor navigation instruction acquisition unit instructs acquisition signal to connect for obtaining indoor navigation instruction based on indoor navigation
The collected current demand signal distance of receiving unit.
User current location acquiring unit is obtained for being handled using Pythagorean theorem current demand signal distance
Take user current location.
Target optimal route acquiring unit, for calling optimal road based on user current location and identification boarding gate position
The indoor navigation interface that diameter acquisition algorithm provides handles user current location and identification boarding gate position, obtains target most
Major path.
Specific restriction about the airport boarding service processing device based on AI may refer to above for based on AI's
The restriction of airport boarding service processing method, details are not described herein.In the above-mentioned airport boarding service processing device based on AI
Modules can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware
Or independently of in the processor in computer equipment, can also be stored in a software form in the memory in computer equipment,
The corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 9.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to execute what the airport boarding service processing method based on AI was generated or obtained in the process for storing
Data, such as boarding attribute information.The network interface of the computer equipment is used to communicate with external terminal by network connection.It should
To realize a kind of airport boarding service processing method based on AI when computer program is executed by processor.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor execute computer program when realize in above-described embodiment based on AI
Airport boarding service processing method the step of, such as step S10-S50 or Fig. 3 shown in Fig. 2 is to step shown in fig. 7
Suddenly.Alternatively, processor is realized in airport boarding service processing device this embodiment based on AI when executing computer program
The function of each module/unit, such as the function of each module/unit shown in Fig. 8, to avoid repeating, which is not described herein again.
In one embodiment, a computer readable storage medium is provided, meter is stored on the computer readable storage medium
Calculation machine program, the computer program realize the airport boarding service processing side in above-described embodiment based on AI when being executed by processor
The step of method, such as step S10-S50 or Fig. 3 shown in Fig. 2 is to step shown in fig. 7, to avoid repeating, here not
It repeats again.Alternatively, the computer program realized when being executed by processor the above-mentioned airport boarding service processing device based on AI this
The function of each module/unit in one embodiment, such as the function of each module/unit shown in Fig. 8, to avoid repeating, here
It repeats no more.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of airport boarding service processing method based on AI characterized by comprising
Boarding service request is obtained, the boarding service request includes original boarding card image；
Processing and gray processing processing are sharpened to the original boarding card image, obtain boarding card image to be identified；
The boarding card image to be identified is positioned using text detection network, is obtained N number of text filed；
Based on each text filed position in the boarding card image to be identified, according to the scene mould marked in advance
Plate identifies each text filed be input in corresponding dedicated identification model, obtains boarding attribute information, described
Boarding attribute information includes identification boarding gate position；
Based on the identification boarding gate position and user current location, the indoor navigation interface being pre-created is called, obtains and uses
Target optimal route of the family to boarding gate position.
2. the airport boarding service processing method based on AI as described in claim 1, which is characterized in that described to be examined using text
Survey grid network positions the boarding card image to be identified, obtains N number of text filed, comprising:
The boarding card image to be identified is positioned using text detection network, obtains positioning coordinate；
It is cut, is obtained N number of text filed based on boarding card image to be identified described in the positioning coordinate pair.
3. the airport boarding service processing method based on AI as claimed in claim 2, which is characterized in that the boarding service is asked
Asking further includes user information；
In the text filed position in the boarding card to be identified, according to the scene template marked in advance by each institute
It is described after the step of stating text filed be input in corresponding dedicated identification model to be identified, obtaining boarding attribute information
Airport boarding service processing method based on AI further include:
Third party airport platform is searched based on the user information, obtains current boarding gate position corresponding with the user information
It sets and current check-in state；
When the current check-in state is in non-boarding state, by the current boarding gate position and the identification boarding gate position
It sets and is matched, if it fails to match, generate prompting message.
4. the airport boarding service processing method based on AI as described in claim 1, which is characterized in that the machine based on AI
Field boarding service processing method further include:
Voice assisted request is obtained, the voice assisted request includes original speech information；
Noise reduction process is carried out to the original speech information, obtains target voice information；
The target voice information input is identified into preparatory trained speech recognition modeling, obtains identification text；
The identification text is subjected to speech analysis according to the semantic analysis rule built in advance, obtains keyword；
The keyword is input in preparatory trained intelligent response model and is identified, voice assisted information is obtained.
5. the airport boarding service processing method based on AI as claimed in claim 4, which is characterized in that described by the target
Voice messaging is input in preparatory trained speech recognition modeling and is identified, obtains identification text, comprising:
The target voice information is pre-processed, voice messaging to be identified is obtained；
Speech feature extraction is carried out to the voice messaging to be identified, obtains target voice feature；
The target voice feature is input in preparatory trained speech recognition modeling and is identified, identification text is obtained.
6. the airport boarding service processing method based on AI as described in claim 1, which is characterized in that described to be based on the knowledge
The indoor navigation interface being pre-created is called in other boarding gate position, obtains target optimal route, comprising:
Obtain indoor navigation instruction, based on the indoor navigation instruction obtain the collected current demand signal of signal receiver away from
From；
The current demand signal distance is handled using Pythagorean theorem, obtains user current location；
Based on the user current location and the identification boarding gate position, the room for calling optimal path acquisition algorithm to provide
Interior navigation interface handles the user current location and the identification boarding gate position, obtains target optimal route.
7. a kind of airport boarding service processing device based on AI characterized by comprising
Boarding service request obtains module, and for obtaining boarding service request, the boarding service request includes original boarding card
Image；
Boarding card image collection module to be identified, for being sharpened at processing and gray processing to the original boarding card image
Reason, obtains boarding card image to be identified；
Text filed acquisition module obtains N for positioning using text detection network to the boarding card image to be identified
It is a text filed；
Boarding gate position acquisition module is identified, for based on each described text filed in the boarding card image to be identified
Position carries out each text filed be input in corresponding dedicated identification model according to the scene template marked in advance
Identification, obtains boarding attribute information, and the boarding attribute information includes identification boarding gate position；
Target optimal route obtains module, for being based on the identification boarding gate position and user current location, calls wound in advance
The indoor navigation interface built up, the target optimal route of acquisition user to boarding gate position.
8. the airport boarding service processing device based on AI as claimed in claim 7, which is characterized in that the optimal road of target
Line obtains module
Indoor navigation instruction acquisition unit instructs acquisition signal to connect for obtaining indoor navigation instruction based on the indoor navigation
The collected current demand signal distance of receiving unit；
User current location acquiring unit is obtained for being handled using Pythagorean theorem the current demand signal distance
Take user current location；
Target optimal route acquiring unit is called most for being based on the user current location and the identification boarding gate position
The indoor navigation interface that shortest path acquisition algorithm provides to the user current location and the identification boarding gate position into
Row processing, obtains target optimal route.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of airport boarding service processing method described in 6 any one based on AI.
10. a kind of non-volatile memory medium, the non-volatile memory medium is stored with computer program, which is characterized in that
The airport boarding service as described in any one of claim 1 to 6 based on AI is realized when the computer program is executed by processor
The step of processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811182179.1A CN109492795A (en) | 2018-10-11 | 2018-10-11 | Airport boarding service processing method, device, equipment and medium based on AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811182179.1A CN109492795A (en) | 2018-10-11 | 2018-10-11 | Airport boarding service processing method, device, equipment and medium based on AI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109492795A true CN109492795A (en) | 2019-03-19 |
Family
ID=65690216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811182179.1A Pending CN109492795A (en) | 2018-10-11 | 2018-10-11 | Airport boarding service processing method, device, equipment and medium based on AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109492795A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070270A (en) * | 2019-03-29 | 2019-07-30 | 广东民航机场建设有限公司 | Transmission equipment control method and device for connecting bridge fixing end |
| CN110077617A (en) * | 2019-03-29 | 2019-08-02 | 广东民航机场建设有限公司 | Control method, device, computer equipment and the storage medium of connecting bridge fixing end |
| CN110077618A (en) * | 2019-03-29 | 2019-08-02 | 广东民航机场建设有限公司 | Control method, device, computer equipment and the storage medium of connecting bridge fixing end |
| CN111582085A (en) * | 2020-04-26 | 2020-08-25 | 中国工商银行股份有限公司 | Document shooting image identification method and device |
| CN112381298A (en) * | 2020-11-16 | 2021-02-19 | 北京交通大学 | Intelligent navigation and passenger-taking guiding self-service system for airport passengers |
| CN113657856A (en) * | 2021-08-10 | 2021-11-16 | 广州民航信息技术有限公司 | Boarding information confirmation method and device |
| CN113657410A (en) * | 2021-08-18 | 2021-11-16 | 深圳壹账通智能科技有限公司 | Image contour extraction method based on artificial intelligence and related equipment |
| WO2023040109A1 (en) * | 2021-09-15 | 2023-03-23 | 深圳创维－Rgb电子有限公司 | Intelligent speech prompt method and device, and storage medium |
| CN117421444A (en) * | 2023-12-18 | 2024-01-19 | 民航成都电子技术有限责任公司 | Airport boarding gate electronic screen information pushing method, device, medium and equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005173710A (en) * | 2003-12-08 | 2005-06-30 | Nec Corp | Passenger boarding guide system and passenger boarding guide method |
| CN102081814A (en) * | 2010-12-15 | 2011-06-01 | 中国南方航空股份有限公司 | Service method for checking in by utilizing electronic boarding passes |
| CN105444757A (en) * | 2015-11-17 | 2016-03-30 | 广东欧珀移动通信有限公司 | Navigation path generation method based on airport indoor environment and user terminal |
| CN107329996A (en) * | 2017-06-08 | 2017-11-07 | 三峡大学 | A kind of chat robots system and chat method based on fuzzy neural network |
| CN107862303A (en) * | 2017-11-30 | 2018-03-30 | 平安科技（深圳）有限公司 | Information identifying method, electronic installation and the readable storage medium storing program for executing of form class diagram picture |
| CN108229463A (en) * | 2018-02-07 | 2018-06-29 | 众安信息技术服务有限公司 | Character recognition method based on image |
-
2018
- 2018-10-11 CN CN201811182179.1A patent/CN109492795A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005173710A (en) * | 2003-12-08 | 2005-06-30 | Nec Corp | Passenger boarding guide system and passenger boarding guide method |
| CN102081814A (en) * | 2010-12-15 | 2011-06-01 | 中国南方航空股份有限公司 | Service method for checking in by utilizing electronic boarding passes |
| CN105444757A (en) * | 2015-11-17 | 2016-03-30 | 广东欧珀移动通信有限公司 | Navigation path generation method based on airport indoor environment and user terminal |
| CN107329996A (en) * | 2017-06-08 | 2017-11-07 | 三峡大学 | A kind of chat robots system and chat method based on fuzzy neural network |
| CN107862303A (en) * | 2017-11-30 | 2018-03-30 | 平安科技（深圳）有限公司 | Information identifying method, electronic installation and the readable storage medium storing program for executing of form class diagram picture |
| CN108229463A (en) * | 2018-02-07 | 2018-06-29 | 众安信息技术服务有限公司 | Character recognition method based on image |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070270A (en) * | 2019-03-29 | 2019-07-30 | 广东民航机场建设有限公司 | Transmission equipment control method and device for connecting bridge fixing end |
| CN110077617A (en) * | 2019-03-29 | 2019-08-02 | 广东民航机场建设有限公司 | Control method, device, computer equipment and the storage medium of connecting bridge fixing end |
| CN110077618A (en) * | 2019-03-29 | 2019-08-02 | 广东民航机场建设有限公司 | Control method, device, computer equipment and the storage medium of connecting bridge fixing end |
| CN111582085A (en) * | 2020-04-26 | 2020-08-25 | 中国工商银行股份有限公司 | Document shooting image identification method and device |
| CN111582085B (en) * | 2020-04-26 | 2023-10-10 | 中国工商银行股份有限公司 | Document shooting image recognition method and device |
| CN112381298A (en) * | 2020-11-16 | 2021-02-19 | 北京交通大学 | Intelligent navigation and passenger-taking guiding self-service system for airport passengers |
| CN112381298B (en) * | 2020-11-16 | 2024-04-12 | 北京交通大学 | Intelligent navigation guide self-service system for airport passengers |
| CN113657856A (en) * | 2021-08-10 | 2021-11-16 | 广州民航信息技术有限公司 | Boarding information confirmation method and device |
| CN113657410A (en) * | 2021-08-18 | 2021-11-16 | 深圳壹账通智能科技有限公司 | Image contour extraction method based on artificial intelligence and related equipment |
| WO2023040109A1 (en) * | 2021-09-15 | 2023-03-23 | 深圳创维－Rgb电子有限公司 | Intelligent speech prompt method and device, and storage medium |
| CN117421444A (en) * | 2023-12-18 | 2024-01-19 | 民航成都电子技术有限责任公司 | Airport boarding gate electronic screen information pushing method, device, medium and equipment |
| CN117421444B (en) * | 2023-12-18 | 2024-03-15 | 民航成都电子技术有限责任公司 | Airport boarding gate electronic screen information pushing method, device, medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492795A (en) | Airport boarding service processing method, device, equipment and medium based on AI | |
| US10176811B2 (en) | Neural network-based voiceprint information extraction method and apparatus | |
| US20190065143A1 (en) | Voice recognition keyword user interface | |
| CN109523989B (en) | Speech synthesis method, speech synthesis device, storage medium, and electronic apparatus | |
| US9223776B2 (en) | Multimodal natural language query system for processing and analyzing voice and proximity-based queries | |
| CN106227721B (en) | Chinese Prosodic Hierarchy forecasting system | |
| WO2021000497A1 (en) | Retrieval method and apparatus, and computer device and storage medium | |
| CN110364171A (en) | A kind of audio recognition method, speech recognition system and storage medium | |
| CN108491421B (en) | Method, device and equipment for generating question and answer and computing storage medium | |
| CN110797016A (en) | Voice recognition method and device, electronic equipment and storage medium | |
| CN110415701A (en) | The recognition methods of lip reading and its device | |
| CN110147216A (en) | Page switching method, device, computer equipment and the storage medium of application program | |
| EP3519983A1 (en) | Customized and contextual translated content for travelers | |
| CN110010136A (en) | The training and text analyzing method, apparatus, medium and equipment of prosody prediction model | |
| CN110060674A (en) | Form management method, apparatus, terminal and storage medium | |
| CN110019741A (en) | Request-answer system answer matching process, device, equipment and readable storage medium storing program for executing | |
| WO2020233381A1 (en) | Speech recognition-based service request method and apparatus, and computer device | |
| CN109410935A (en) | A kind of destination searching method and device based on speech recognition | |
| CN114882862A (en) | Voice processing method and related equipment | |
| CN114220461A (en) | Customer service call guiding method, device, equipment and storage medium | |
| CN113254613A (en) | Dialogue question-answering method, device, equipment and storage medium | |
| CN108364655A (en) | Method of speech processing, medium, device and computing device | |
| CN116844529A (en) | Speech recognition method, device and computer storage medium | |
| CN110084187A (en) | Location recognition method, device, equipment and storage medium based on computer vision | |
| CN114898734A (en) | Pre-training method and device based on speech synthesis model and electronic equipment |
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: 20190319 |
|
| RJ01 | Rejection of invention patent application after publication |