CN115938347A - Flight student communication normative scoring method and system based on voice recognition - Google Patents
Flight student communication normative scoring method and system based on voice recognition Download PDFInfo
- Publication number
- CN115938347A CN115938347A CN202310236989.5A CN202310236989A CN115938347A CN 115938347 A CN115938347 A CN 115938347A CN 202310236989 A CN202310236989 A CN 202310236989A CN 115938347 A CN115938347 A CN 115938347A
- Authority
- CN
- China
- Prior art keywords
- flight
- call
- trainee
- text
- deviation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a flight student communication normative scoring method and system based on voice recognition. According to the method and the system, the voice call content is obtained in real time and is converted into the text, the calculation of the deviation of the call content is completed based on the semantic matching and comparison verification model, and finally the nonstandard marking and scoring of the call of the flight trainee during the flight training are given, so that the flight trainee is helped to recognize and correct the call problem, the culture degree of the flight trainee is improved, and the aviation safety problem caused by the land-air call quality can be reduced.
Description
Technical Field
The invention relates to the field of land-air communication normative scoring, in particular to a flight trainee communication normative scoring method and system based on voice recognition.
Background
The training of the standard expression of the air traffic control instruction is very important and indispensable content in the air traffic management, and the training of the standard expression of the air-ground communication has been the key point in the cultivation of air controllers. The aircraft operates safely and efficiently, and the air traffic controller and the pilot can accurately communicate and understand each other without leaving. Therefore, whether the airphibious language of the pilot is standard and standard or not is also very important to the influence of the airphibious language on the flight safety.
With the rapid development of civil aviation technology, the faults of communication equipment are gradually reduced, but unsafe aviation events such as inaccurate repeated reading, misunderstanding, irregular wording, incomplete contents and the like related to wireless telephone communication errors still occur sometimes. According to NASA reports, over 50% of aviation accidents are associated with radiotelephone communication errors. With the continuous development of civil aviation transportation industry in China, the air traffic flow is rapidly increased, the working pressure of pilots is higher and higher, the demand on high-quality pilots is higher and higher, and higher requirements are also put forward for the cultivation of flight trainees. During the flight learning period, especially the flight learning period, the flight trainees are nervous, unskilled, under great stress and the like, so that the flight trainees are mainly concentrated on the operation, the flight trainees are difficult to comprehensively deal with the rapid land-air communication instructions of the controllers, and the phenomena of misreading, irregular wording and the like are inevitable.
Therefore, a set of specific problems capable of feeding back the communication phrases during the flight learning of flight trainees needs to be designed, help the trainees to establish the normative concept of the land-air communication phrases and standardize the land-air communication of the trainees, and guarantee flight safety of the trainees in the flight learning and flight and future actual work.
Disclosure of Invention
The invention aims to provide a flight student communication normative scoring method and system based on voice recognition, which are used for standardizing the contents of land-air communication in the process of flight learning of flight trainees and reducing the problem of unsafe aviation caused by wrong related expressions.
In order to achieve the above purpose, the invention provides the following technical scheme:
a flight student call normative scoring method based on voice recognition comprises the following steps:
s1: acquiring voice uploaded by a land-air call terminal in real time;
s2: converting the speech into text;
s3: analyzing and classifying the text, and marking and positioning a flight trainee call text;
s4: calculating the irregular deviation of the communication text of the flight trainees based on a semantic matching and comparison verification model, assigning a heat value vector hvv, and giving a total value hvvM of the heat value vector on each flight finishing flight training;
s5: and calculating and evaluating the flight trainee call text according to the grading main points and the total heat value vector value hvvM.
Preferably, S3 specifically includes:
s31: identifying the flight corresponding to the instruction from the call sign in the conversation text;
s32: arranging the instructions of the same call sign according to the time sequence;
s33: identifying the role of the land-air call through part-of-speech and semantic analysis;
s34: and marking and positioning flight trainee call texts.
Preferably, S4 specifically includes:
s41: after the communication text of the flight trainees is obtained, marking whether the communication text of each section of the flight trainees has deviation or not in a manual marking mode by taking the content of the communication text as a training set, and assigning a heat value vector hvv according to a deviation result;
s42: putting the marked sample into training of a semantic matching and comparison verification model;
s43: putting the trained semantic matching and comparison verification model into use, and directly outputting a deviation result and a heat value vector hvv of the communication text of the flight trainee by an algorithm;
s44: for each flight finishing flight training, obtaining the total dimensionality of the hvvM matrix as n x, wherein n is the number of rows, namely the total number of the flight trainees talking after the flight is finished, and x is the number of the nonstandard classifications including the deviation scoring item.
Preferably, the bias in S4 includes a misreading inaccuracy bias, a wording irregular bias, a content incomplete bias, and a misinterpretation bias.
Preferably, S5 is calculated and evaluated according to the following formula:
e=a*Sum[hvvM[[:,x]]]/n*100%
s=100%-e
wherein e is a percentage of deduction, a is a deviation definition weighting coefficient ranging from 0 to 2, s is a total score, x is the number of the non-standard classifications including the deviation score item, and n is the number of the rows.
In order to achieve the above purpose, the invention provides the following technical scheme:
a flight student conversation normative scoring system based on voice recognition is characterized by comprising:
a voice unit: the system is used for acquiring the voice uploaded by the air-ground communication terminal in real time;
a transformation unit: for converting the speech into text;
an analysis unit: the system is used for analyzing and classifying the texts, and marking and positioning flight trainee call texts;
a comparison unit: the system is used for calculating the nonstandard deviation of the communication text of the flight trainees based on a semantic matching and comparison verification model, assigning a heat value vector hvv, and giving a total value hvvM of the heat value vector on each flight finishing flight training;
an evaluation unit: and the method is used for calculating and evaluating the flight trainee call text according to the grading main points and the total heat value vector value hvvM.
Preferably, the analysis unit specifically includes:
an identification module: the system is used for identifying the flight corresponding to the instruction from the call sign in the dialog text;
a sorting module: instructions for arranging the same call sign in chronological order;
an analysis module: the system is used for identifying the land-air conversation role through part of speech and semantic analysis;
a marking module: the device is used for marking and positioning flight trainee call texts;
preferably, the comparison unit specifically includes:
a labeling module: the method comprises the steps of acquiring a flight trainee call text, marking whether each section of flight trainee call text has deviation or not by using the content of the flight trainee call text as a training set in a manual marking mode, and assigning a heat value vector hvv according to a deviation result;
a training module: the system is used for putting the marked samples into the training of a semantic matching and comparison verification model;
an output module: the method is used for putting the trained semantic matching and comparison verification model into use, and the deviation result and the heat value vector hvv of the flight trainee calling text are directly output by an algorithm;
a summary module: for each flight that finishes flight training, the total dimension of the hvvM matrix is obtained as n x, n is the number of rows, i.e. the total number of student calls after flight finishes, and x is the number of non-standard classifications that incorporate the deviation score.
Preferably, the evaluation unit is adapted to calculate and evaluate according to the following formula:
e=a*Sum[hvvM[[:,x]]]/n*100%
s=100%-e
wherein e is a percentage of deduction, a is a deviation definition weighting coefficient ranging from 0 to 2, s is a total score, x is the number of the non-standard classifications including the deviation score item, and n is the number of the rows.
Preferably, the scoring system can recover the call content in the scoring report, mark out-of-specification and correct wording content, and print the scoring report.
Compared with the prior art, the invention has the beneficial effects that:
the flight trainee call normative scoring system based on voice recognition can enable the flight trainee to realize the problem and correct related irregular contents by the scoring report and the call contents restored therein after finishing the flight training task of the same day, thereby improving the culture degree of the flight trainee and reducing the aviation safety problem caused by the land-air call quality; the scoring system starts when the flight trainee performs single training flight, and obtains an evaluation result after the flight trainee finishes the single training flight, and the whole call quality evaluation process does not need manual intervention.
Drawings
FIG. 1 is a schematic diagram of the system operating environment of the present invention;
FIG. 2 is a flow chart of the scoring system of the present invention;
FIG. 3 illustrates a method for call normative bias identification and classification in accordance with the present invention;
fig. 4 is a call normative scoring point of the present invention.
Detailed Description
The present invention will be described in further detail with reference to test examples and specific embodiments. It should be understood that the scope of the above-described subject matter is not limited to the following examples, and any techniques implemented based on the disclosure of the present invention are within the scope of the present invention.
Example 1
According to the method, through real-time voice recognition, semantic matching comparison verification is carried out on the communication of the flight trainees according to the voice text, and the communication is compared with standard air-ground communication, so that a deviation value between each comparison factor of real-time voice and a comparison factor of a voice sample is obtained; and finally, performing integral evaluation on the real-time voice of the flight trainee according to the deviation value to obtain an evaluation total score, restoring all land-air calls of the training flights corresponding to the same call sign in a report form after the flight is finished, and performing deviation type marking on the deviated part in the call of the flight trainee and remarking the call content with correct standard. Therefore, the communication content of the flight trainees can be comprehensively monitored, reminded and corrected, and the purpose of improving the land-air communication standardization of the flight trainees is achieved.
Referring to fig. 1, the operating environment of the flight trainee communication normative scoring system based on voice recognition is shown schematically, the voice recognition and flight trainee communication normative scoring system receives the land-air communication voice uploaded in real time from the flight trainee 1 and the flight commander 2 and from the flight trainee 1 and the controller 3, wherein the voice flows from the flight trainee 1 and the flight commander 2 or from the flight trainee 1 and the controller 3 to the scoring result report print 5 through the voice recognition and flight trainee communication normative scoring system 4. The speech recognition and flight trainee communication normative scoring system 4 is a system core, performs real-time text conversion on speech in a communication process, performs series semantic matching comparison and verification, and prints an analysis result to the terminal 5, so that a pilot can complete timely standard self land-air communication after training and flying on duty.
Referring to fig. 2, a working flow chart of each unit of the flight trainee call normative scoring system based on voice recognition in the present invention includes:
s1: and acquiring the voice uploaded by the land-air terminals 2 and 3 based on the voice unit. The terminals 2 and 3 are communicated with the system in real time, and the conversation voice can be automatically uploaded to the system as long as the land-air conversation is carried out.
S2: based on the recognition unit, the speech is converted into text. The system converts speech to text in real time based on streaming speech recognition.
S3: and based on the part-of-speech analysis of the control text of the analysis unit, clustering the instructions corresponding to different call signs and identifying the instruction roles. According to the text content, performing part-of-speech analysis, firstly, identifying flights corresponding to instructions according to call signs in the conversation text, and arranging and aggregating the instructions of the same call sign into a class according to the time sequence; secondly, through the analysis of the part of speech and the semantic meaning, the role of the sender of the voice call is identified, which type of flight trainee, flight commander or controller is determined, and the marking is carried out, so that the land-air call content of the flight trainee is conveniently positioned.
S4: training the semantic matching and comparison verification model based on the semantic matching and comparison verification model of the comparison unit, and importing and calculating the call deviation of each flight student. And (4) positioning the communication content of each flight trainee according to the instruction clustering and instruction role identification marking results corresponding to different call signs in the S3, and identifying and classifying the communication deviation of the flight trainees by combining the instruction contents of flight trainees and controllers in the adjacent time.
In one aspect of this embodiment, referring to fig. 3, a method for calculating a semantic matching and comparison verification model according to the present invention includes:
and for the land-air call clustering result corresponding to each call sign, taking the communication text of the ith flight trainee of each identified role and all communication texts of corresponding flights before the text as input, importing a semantic matching and comparison verification model, initializing a heat value vector (hvv), wherein the length of the heat value vector is 4 (the heat value vector is divided into 4 classes of non-specifications and can be expanded according to actual conditions), and the initial value is 0, namely hvv = {0, 0}. The specific method for identifying various deviations comprises the following steps:
s41: the repeated reads are not accurate. Based on a semantic matching and comparison verification model, if the recognition result is a repeated reading, judging whether the repeated reading is accurate, if not, marking out a word with a repeated reading error, assigning 1 to the first element of hvv, namely hvv = {1, 0}, ending the recognition of the ith flight trainee call text, and integrating the hvv = {1, 0} as the recognition result into a total pilot call normative heat value vector Matrix (hvm), namely hvm [ i ] = hvv.
S42: the wording does not specify a deviation. Based on semantic matching and comparison verification models, if the recognition result is that the used word is not standard, a word which is not standard is marked, the second element of hvv is assigned to be 1, namely hvv = {0,1, 0}, the recognition of the ith flight trainee call text is ended, and the hvv = {0,1, 0} is used as the recognition result and is integrated into a pilot call normative heat value vector Matrix (hot value vector Matrix: hvvM), namely hvvM [ i ] = hvv.
S43: incomplete content bias. Based on semantic matching and comparison verification models, if the recognition result is incomplete, words with incomplete contents are marked, the third element of hvv is assigned to be 1, namely hvv = {0,1, 0}, the recognition of the ith flight trainee call text is ended, and the hvv = {0,1, 0} is used as the recognition result and is integrated into a total pilot call normative heat value vector Matrix (hvvM), namely hvvM [ i ] = hvv.
S44: the deviation is misunderstood. Based on semantic matching and comparison verification models, if the recognition result is misleading, marking out misleading words, assigning the fourth element of hvv as 1, namely hvv = {0, 1}, ending the recognition of the ith flight trainee conversation text, and integrating the hvv = {0, 1} as the recognition result into a total pilot conversation normative heat value vector Matrix (hvvM), namely hvvM [ i ] = hvv.
If the identification result does not belong to the four types of deviation, the land-air conversation is standard, and the initial value is kept, namely hvv = {0, 0}.
For each flight that finishes the flight training, we get the total dimension of the hvvM matrix to be n x 4, n is the number of rows, i.e. the total number of student calls after the flight finishes, and 4 is 4 irregular classifications in this example.
S5: real-time speech is evaluated. Defining a weight coefficient for each deviation, calculating the mark deduction percentage of each deviation according to the total deviation vector obtained in S4, and obtaining a total mark through summation to further obtain a total score, wherein the specific method comprises the following steps:
referring to fig. 4, a flight trainee conversation normative scoring point according to the embodiment of the present invention is shown, where the scoring point includes:
s51: the rereading is inaccurate, the percentage e1 is deducted, and the formula is as follows:
e1=a1*Sum[hvvM[[:,1]]]/n*100%
s52: the words are not standardized, the percentage e2 is deducted, and the formula is as follows:
e2=a2*Sum[hvvM[[:,2]]]/n*100%
s53: incomplete content, percentage of deduction e3, formula:
e3=a3*Sum[hvvM[[:,3]]]/n*100%
s54: misinterpretation, the percentage e4 is deducted, and the formula is:
e4=a4*Sum[hvvM[[:,4]]]/n*100%
s55: the formula is as follows:
s=100- e1- e2- e3- e4
wherein s is the total score, a 1-a 4 are each deviation in the range of 0-2 to define a weighting coefficient,
s6: and printing a report with a total score and each deviation deduction, wherein the report contains the original call content, and notes the places with irregular calls, deviation types and correct phrase contents of flight trainees.
The above description is intended to be illustrative of the preferred embodiment of the present invention and should not be taken as limiting the invention, but rather, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (10)
1. A flight student conversation normative scoring method based on voice recognition is characterized by comprising the following steps:
s1: acquiring voice of a service call;
s2: converting the speech into text;
s3: analyzing and classifying the text, and marking and positioning the flight trainee call text in the text;
s4: calculating the irregular deviation of the communication text of the flight trainees based on a semantic matching and comparison verification model, assigning a heat value vector hvv, and giving a total value hvvM of the heat value vector on each flight finishing flight training;
s5: and calculating and evaluating the flight trainee call text according to the grading main points and the total heat value vector value hvvM.
2. The flight trainee call normative scoring method based on voice recognition as claimed in claim 1, wherein the S3 specifically includes:
s31: identifying the flight corresponding to the instruction from the call sign in the conversation text;
s32: arranging the instructions of the same call sign according to the time sequence;
s33: identifying the role of the land-air conversation through part of speech and semantic analysis;
s34: and marking and positioning flight trainee call texts.
3. The flight trainee conversation normative scoring method based on the voice recognition as claimed in claim 1, wherein the S4 specifically includes:
s41: after the flight trainee call text is obtained, marking whether each section of the flight trainee call text has an irregular deviation or not in a manual marking mode by taking the content of the flight trainee call text as a training set, and assigning a heat value vector hvv according to a deviation result;
s42: putting the marked samples into training of a semantic matching and comparison verification model;
s43: putting the trained semantic matching and comparison verification model into use, and directly outputting the deviation result and the heat value vector hvv of the flight trainee call text by an algorithm;
s44: for each flight finishing flight training, obtaining the total dimensionality of the hvvM matrix as n x, wherein n is the number of rows, namely the total number of the flight trainees talking after the flight is finished, and x is the number of the nonstandard classifications including the deviation scoring item.
4. The flight trainee call normative scoring method based on the voice recognition as claimed in claim 3, wherein the irregular deviation comprises a repeated reading inaccurate deviation, a wording irregular deviation, a content incomplete deviation and a misinterpretation deviation.
5. The flight trainee call normative scoring method based on the voice recognition according to the claim 1, wherein the S5 is calculated and evaluated according to the following formula:
e=a*Sum[hvvM[[:,x]]]/n*100%
s=100%-e
wherein e is a percentage of deduction, a is a deviation definition weighting coefficient ranging from 0 to 2, s is a total score, x is the number of the non-standard classifications including the deviation score item, and n is the number of the rows.
6. A flight student conversation normative scoring system based on voice recognition is characterized by comprising:
a voice unit: the voice uploading device is used for acquiring voice uploaded by a service call end in real time;
a conversion unit: for converting the speech into text;
an analysis unit: the system is used for analyzing and classifying the texts, and marking and positioning flight trainee call texts in the texts;
a comparison unit: the system is used for calculating the nonstandard deviation of the communication text of the flight trainees based on a semantic matching and comparison verification model, assigning a heat value vector hvv, and giving a total value hvvM of the heat value vector on each flight finishing flight training;
an evaluation unit: and the method is used for calculating and evaluating the flight trainee call text according to the grading main points and the total heat value vector value hvvM.
7. The flight student call normative scoring system based on voice recognition as claimed in claim 5, wherein the analysis unit specifically comprises:
an identification module: the system is used for identifying the flight corresponding to the instruction from the call sign in the dialog text;
a sorting module: instructions for arranging the same call sign in chronological order;
an analysis module: the system is used for identifying the land-air conversation role through part of speech and semantic analysis;
a marking module: for marking and locating flight trainee call text therein.
8. The flight student communication normative scoring system based on voice recognition as claimed in claim 5, wherein the comparing unit specifically comprises:
a labeling module: after the flight trainee call text is obtained, a manual marking mode is acquired by taking the content of the flight trainee call text as a training set, whether each section of flight trainee call text has an irregular deviation or not is marked, and a heat value vector hvv is assigned according to a deviation result;
a training module: the system is used for putting the marked samples into the training of a semantic matching and comparison verification model;
an output module: the method is used for putting the trained semantic matching and comparison verification model into use, and the deviation result and the heat value vector hvv of the communication text of the flight trainee are directly output by an algorithm;
a summary module: for each flight that finishes flight training, the total dimension of the hvvM matrix is obtained as n x, n is the number of rows, i.e. the total number of student calls after flight finishes, and x is the number of non-standard classifications that incorporate the deviation score.
9. The flight trainee call normative scoring system based on voice recognition as claimed in claim 5, wherein the evaluation unit is used for calculating and evaluating according to the following formula:
e=a*Sum[hvvM[[:,x]]]/n*100%
s=100%-e
wherein e is a deduction percentage, a is a deviation definition weighting coefficient ranging from 0 to 2, s is a total score, x is the number of the nonstandard classifications of the deviation inclusion scoring item, and n is the number of the lines.
10. The flight trainee call normative scoring system based on the voice recognition as claimed in claim 5, wherein the scoring system generates a scoring report after the evaluation is completed, restores call contents, marks out-of-specification places and correct phrase contents, and prints the scoring report.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310236989.5A CN115938347B (en) | 2023-03-13 | 2023-03-13 | Flight student conversation normalization scoring method and system based on voice recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310236989.5A CN115938347B (en) | 2023-03-13 | 2023-03-13 | Flight student conversation normalization scoring method and system based on voice recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115938347A true CN115938347A (en) | 2023-04-07 |
CN115938347B CN115938347B (en) | 2023-05-23 |
Family
ID=85818616
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310236989.5A Active CN115938347B (en) | 2023-03-13 | 2023-03-13 | Flight student conversation normalization scoring method and system based on voice recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115938347B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117593924A (en) * | 2024-01-19 | 2024-02-23 | 中国民用航空飞行学院 | Scene reproduction-based air traffic controller training method and system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130158982A1 (en) * | 2011-11-29 | 2013-06-20 | Educational Testing Service | Computer-Implemented Systems and Methods for Content Scoring of Spoken Responses |
US20130185314A1 (en) * | 2012-01-16 | 2013-07-18 | Microsoft Corporation | Generating scoring functions using transfer learning |
CN109101518A (en) * | 2018-05-21 | 2018-12-28 | 全球能源互联网研究院有限公司 | Phonetic transcription text quality appraisal procedure, device, terminal and readable storage medium storing program for executing |
CN110335609A (en) * | 2019-06-26 | 2019-10-15 | 四川大学 | A kind of air-ground communicating data analysis method and system based on speech recognition |
CN110490428A (en) * | 2019-07-26 | 2019-11-22 | 合肥讯飞数码科技有限公司 | Job of air traffic control method for evaluating quality and relevant apparatus |
CN113066499A (en) * | 2021-03-12 | 2021-07-02 | 四川大学 | Method and device for identifying identity of land-air conversation speaker |
CN114049893A (en) * | 2022-01-11 | 2022-02-15 | 四川大学 | Method for monitoring and analyzing illegal operation of controller based on air traffic control voice recognition |
CN114187893A (en) * | 2021-12-15 | 2022-03-15 | 首都机场集团有限公司 | Intelligent voice monitoring method and system for air traffic control |
CN115223558A (en) * | 2022-06-24 | 2022-10-21 | 重庆中科云从科技有限公司 | Method, system and computer storage medium for managing air traffic control voice |
-
2023
- 2023-03-13 CN CN202310236989.5A patent/CN115938347B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130158982A1 (en) * | 2011-11-29 | 2013-06-20 | Educational Testing Service | Computer-Implemented Systems and Methods for Content Scoring of Spoken Responses |
US20130185314A1 (en) * | 2012-01-16 | 2013-07-18 | Microsoft Corporation | Generating scoring functions using transfer learning |
CN109101518A (en) * | 2018-05-21 | 2018-12-28 | 全球能源互联网研究院有限公司 | Phonetic transcription text quality appraisal procedure, device, terminal and readable storage medium storing program for executing |
CN110335609A (en) * | 2019-06-26 | 2019-10-15 | 四川大学 | A kind of air-ground communicating data analysis method and system based on speech recognition |
CN110490428A (en) * | 2019-07-26 | 2019-11-22 | 合肥讯飞数码科技有限公司 | Job of air traffic control method for evaluating quality and relevant apparatus |
CN113066499A (en) * | 2021-03-12 | 2021-07-02 | 四川大学 | Method and device for identifying identity of land-air conversation speaker |
CN114187893A (en) * | 2021-12-15 | 2022-03-15 | 首都机场集团有限公司 | Intelligent voice monitoring method and system for air traffic control |
CN114049893A (en) * | 2022-01-11 | 2022-02-15 | 四川大学 | Method for monitoring and analyzing illegal operation of controller based on air traffic control voice recognition |
CN115223558A (en) * | 2022-06-24 | 2022-10-21 | 重庆中科云从科技有限公司 | Method, system and computer storage medium for managing air traffic control voice |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117593924A (en) * | 2024-01-19 | 2024-02-23 | 中国民用航空飞行学院 | Scene reproduction-based air traffic controller training method and system |
CN117593924B (en) * | 2024-01-19 | 2024-03-26 | 中国民用航空飞行学院 | Scene reproduction-based air traffic controller training method and system |
Also Published As
Publication number | Publication date |
---|---|
CN115938347B (en) | 2023-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109359293B (en) | Mongolian name entity recognition method neural network based and its identifying system | |
US10650231B2 (en) | Method, device and server for recognizing characters of claim document, and storage medium | |
CN111198948B (en) | Text classification correction method, apparatus, device and computer readable storage medium | |
CN108734379B (en) | Online training method for realizing differentiation of customer service personnel | |
CN111428467B (en) | Method, device, equipment and storage medium for generating problem questions for reading and understanding | |
CN109947836A (en) | English paper structural method and device | |
CN115938347A (en) | Flight student communication normative scoring method and system based on voice recognition | |
CN111145724B (en) | Polyphone marking method and device and computer readable storage medium | |
CN114913729A (en) | Question selection method and device, computer equipment and storage medium | |
CN104142912A (en) | Accurate corpus category marking method and device | |
CN115063119A (en) | Recruitment decision system and method based on adaptivity of recruitment behavior data | |
CN116451646A (en) | Standard draft detection method, system, electronic equipment and storage medium | |
CN115470796A (en) | Text instruction generation method and equipment for air traffic control simulation training | |
CN110909162A (en) | Text quality inspection method, storage medium and electronic equipment | |
CN107516284A (en) | Operation and test and appraisal solution based on mobile intelligent terminal | |
CN116805208B (en) | Engineering project data analysis system and method based on artificial intelligence | |
CN113408253A (en) | Job review system and method | |
CN112035668A (en) | Event subject recognition model optimization method, device and equipment and readable storage medium | |
CN116992142A (en) | Intelligent course recommendation system and method based on user big data | |
CN114219302B (en) | Method for portraying wind competence of pilot facing to flight skill full life cycle | |
CN115601778A (en) | Job correction method, device and equipment based on image recognition and storage medium | |
Rüdian et al. | Automatic Feedback for Open Writing Tasks: Is this text appropriate for this lecture? | |
CN114818929B (en) | Self-learning annotation-based annotation model training method and annotation method | |
Perez et al. | Implementation of a test constructor utilizing a calibrated item bank using 3PL-IRT model | |
CN110096257B (en) | Design graph automatic evaluation system and method based on intelligent recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |