CN109597991A - Vehicle remote detection method - Google Patents
Vehicle remote detection method Download PDFInfo
- Publication number
- CN109597991A CN109597991A CN201811425532.4A CN201811425532A CN109597991A CN 109597991 A CN109597991 A CN 109597991A CN 201811425532 A CN201811425532 A CN 201811425532A CN 109597991 A CN109597991 A CN 109597991A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- detection
- defect
- report
- column
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 205
- 230000007547 defect Effects 0.000 claims abstract description 91
- 238000012360 testing method Methods 0.000 claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000007789 sealing Methods 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 17
- 239000000284 extract Substances 0.000 claims description 15
- 239000006096 absorbing agent Substances 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 238000005215 recombination Methods 0.000 claims description 9
- 230000006798 recombination Effects 0.000 claims description 9
- 230000035939 shock Effects 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000012550 audit Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 claims description 6
- 210000004709 eyebrow Anatomy 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 241001269238 Data Species 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000005034 decoration Methods 0.000 claims description 3
- 239000002828 fuel tank Substances 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000001755 vocal effect Effects 0.000 claims description 2
- 239000003595 mist Substances 0.000 claims 2
- FFBHFFJDDLITSX-UHFFFAOYSA-N benzyl N-[2-hydroxy-4-(3-oxomorpholin-4-yl)phenyl]carbamate Chemical compound OC1=C(NC(=O)OCC2=CC=CC=C2)C=CC(=C1)N1CCOCC1=O FFBHFFJDDLITSX-UHFFFAOYSA-N 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 239000003973 paint Substances 0.000 description 4
- 206010020675 Hypermetropia Diseases 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of vehicle remote detection methods.This method comprises: the detection target for storing vehicle in vehicle defect semantics recognition rule base semantic matches rule corresponding with detection target: according to detection it needs to be determined that detection project, obtain the corresponding detection target of detection project, it is detected by detection target of the detection instrument to vehicle, the defect Preliminary detection report for the vehicle that will test is submitted on background server;Background server obtains vehicle defect to the content of text progress semantic analysis in the report of defect Preliminary detection using semantic matches rule and describes key message, describes key message based on vehicle defect and obtains vehicle assessment report.The present invention is by presetting vehicle defect semantics recognition rule base, it designs and utilizes the corresponding semantic matches rule of detection target, inspector nonstandardized technique voice, words input are realized, is converted to standard situation of remote automatically, has high flexibility and convenience.
Description
Technical field
The present invention relates to technical field of automobile detection more particularly to a kind of vehicle remote detection methods.
Background technique
Used car detects currently on the market, thousand people, thousand face, lacks a generally acknowledged examination criteria.Traditional used car detects work
The professional ability requirement having to inspector is very high, needs to carry out the detection training of profession, just can be carried out actual vehicle detection, right
What is answered is the increase of the cost and promoting service difficulty of enterprise.The disposition assistant director of many shop 4S/mechanisms does not have the second-hand of profession
Vehicle detectability needs third party testing agency to support.
Traditional used car detection instrument, which does not have, is adjusted flexibly ability to Added Business, cites a plain example,
Financial valuation business only needs to shoot the basic photo of vehicle, has the demand of a quick check and evaluation to vehicle condition, no
For trading, pursuit is detection efficiency, and Second-hand Vehicle Transaction business is just very comprehensive to the detection of vehicle, for the base of vehicle
This photo and formality information, situation of remote requires completely to record, if sharing traditional detection instrument, needs to shoot a large amount of
Photo is just able to satisfy transaction business, but does not meet the timeliness demand of financial valuation business.
NLP (Natural Language Processing, natural semantics recognition) is a son neck of artificial intelligence (AI)
Domain.Semantics recognition technology is equivalent to the brain of people, is responsible for thinking and information processing.Modern NLP algorithm is based on machine learning, spy
It is not statistical machine learning.Machine learning normal form is the trial Language Processing before being different from generally.The reality of language processing tasks
It is existing, it is usually directed to the big set rule encoding for directly using hand.
Currently, used car detection industry there is no the actual application scheme based on natural semantics recognition.
Summary of the invention
The embodiment provides a kind of vehicle remote detection methods, to overcome problem of the prior art.
To achieve the goals above, this invention takes following technical solutions.
A kind of vehicle remote detection method stores the detection target and inspection of vehicle in vehicle defect semantics recognition rule base
Survey the corresponding semantic matches rule of target, which comprises
According to detection it needs to be determined that detection project, obtains the corresponding detection target of detection project, by detection instrument to vehicle
Detection target detected, the report of the defect Preliminary detection of the vehicle that will test is submitted on background server;
The background server utilizes the corresponding language of detection target stored in the vehicle defect semantics recognition rule base
Adopted matching rule carries out semantic analysis to the content of text in defect Preliminary detection report and obtains vehicle defect description key
Information describes key message based on the vehicle defect and obtains vehicle assessment report.
Further, the method further include:
Inspector is registered in testing agency first, and the identity information of inspector, testing agency are submitted to testing agency
The identity information of the inspector received is transferred to background server, the identity information of background server audit inspector passes through
Afterwards, pass through message to the identity audit that testing agency returns to inspector, inspector succeeds in registration in testing agency, and testing agency will
The identity information of inspector carries out storage and management.
Further, the detection target that vehicle is stored in vehicle defect semantics recognition rule base and detection target
Corresponding semantic matches rule, comprising:
Vehicle defect semantics recognition rule base is managed in background server, is deposited in vehicle defect semantics recognition rule base
All detection targets and the corresponding all possible testing results of each detection target of storage vehicle and each detection target are corresponding
Semantic matches rule, which includes the vehicle condition language of voice, picture, mathematic sign, label and/or text representation
Justice coding.
Further, all detection targets include: left front tire, left front wheel hub, left front fender, outside left A column
Side, left front car door, left exterior mirror, left front car door edge sealing, the left big side in bottom, left front threshold, left B column outside, left C column outside,
Left back car door, left back car door edge sealing, left back threshold, left rear tire, left back wheel hub, fuel tank cap, left back fender, front bumper,
Air-inlet grille has right headlamp assembly, left headlamp assembly, left front fog lamp, right front fog lamp, front windshield, front windshield rain brush
Device, roof, rear seat windscreen, luggage-boot lid, luggage-boot lid edge, rear windshield rain brush, off-front wheel hub, right front fire, before right
Fender, on the outside of right A column, right exterior mirror, right front door, right front door edge sealing, the right big side in bottom, right front door sill, outside right B column
Side, right rear door, right C column outside, right rear door edge sealing, right-rear-door sill, right rear fender, off hind wheel hub, right rear fire, vehicle
Top, boot, left front vehicle door interior trim panel, left A column trim panel, left back vehicle door interior trim panel, left B column trim panel, left C column trim panel,
Steering wheel, workbench, front-seat air-conditioner air outlet, glove box, instrument, centralized control, handle of gear handle, handle of gear dirt-proof boot, armrest box,
Master drives seat, the passenger side seat, left back seat, right back seat, left front vehicle door interior trim panel, right A column trim panel, right rear door interior trim
Plate, right B column trim panel, right C column trim panel, front anti-collision beam, left front shock absorber bearing, removable water tank frame, left headlamp frame, water
Case upper bracket, water tank lower bracket, left front fender liner, left front girder, left front A column inside and edge sealing, left B column inside and envelope
Side, left C column inside and edge sealing, preceding surrounding baffle, back buffer beam, squab panel, left back shock absorber bearing, left tail lamp frame, underbody,
Luggage case edge sealing, baggage-compartment partition, left rear longitudinal beam, right front damper seat, right headlamp frame, right front fender liner, before right
Stringer, right B column inside and edge sealing, right C column inside and edge sealing, right A column inside and edge sealing, right rear shock absorber seat, right tail lamp frame,
Right floor side member, left front catch, left back catch, right front door knob, right-rear-door knob, front fog lamp, Rear Fog Lamp, left front wheel arch,
Left back wheel arch, off-front wheel eyebrow, off hind wheel eyebrow, plaque under front bumper, plaque, front fog lamp grid and Rear Fog Lamp lattice under rear bumper
Grid.
Further, it is described according to detection it needs to be determined that detection project, obtain the corresponding detection target of detection project, lead to
It crosses detection instrument to detect the detection target of vehicle, after the defect Preliminary detection report for the vehicle that will test is submitted to
On platform server, comprising:
Management detection configuration database, matches in the detection configuration database according to the requirement of business in background server
Each detection project on computer applied algorithm APP is set, includes multiple detection targets in each detection project;
Inspector is first according to actually detected it needs to be determined that detection project, inquires detection configuration database according to detection project
The corresponding detection target of detection project is obtained, inspector is carried out using APP by detection target of the various detection instruments to vehicle
Detection, and the defect problem that detected by voice, picture and/or verbal description, obtain the defect Preliminary detection report of vehicle
It accuses, defect Preliminary detection report is submitted on background server.
Further, the background server utilizes the detection mesh stored in the vehicle defect semantics recognition rule base
Corresponding semantic matches rule is marked, vehicle is obtained to the content of text progress semantic analysis in defect Preliminary detection report and is lacked
Description key message is fallen into, key message is described based on the vehicle defect and obtains vehicle assessment report, comprising:
After background server receives the defect Preliminary detection report of the vehicle, extract in the report of defect Preliminary detection
Content of text carries out semantic analysis to content of text using semantic matches rule, obtains vehicle defect and describe key message;
Background server extracts the image content in the report of defect Preliminary detection, orients in image content where license plate
Image-region blurs the image-region where license plate;
Background server describes the style that key message identifies using model data library vehicle according to the vehicle defect
Information confirms vehicle configuration information, inquires vehicle history maintenance record by the maintenance query interface on backstage and insurance records,
The comprehensive all kinds of detection datas of background server describe key message and license plate virtualization as a result, obtaining vehicle in conjunction with the vehicle defect
Assessment report;
Described includes following processing step to content of text progress semantic analysis using semantic matches rule:
Step_1: Chinese spcial character processing is carried out to content of text, the double byte character in content of text is converted to half
Angle character;
Step_2: with English branch (;) sentence division is carried out to content of text, obtain sentence set to be processed;
Step_3: word segmentation processing is carried out to each sentence, obtains the sequence of words of each sentence;
Step_4: traversing the sequence of words of sentence, mapping word is substituted for corresponding mapping content set, after being mapped
The set of sequence of words;
Step_5: the sequence of words after recombination mapping obtains recombination sentence set, and divides the sentence after recombination
Word obtains new sequence of words set;
Step_6: each vocabulary in sequence of words is mapped as to the correspondence stored in vehicle defect semantics recognition rule base
Detection target, it is right further according to the corresponding semantic matches rule of the detection target that is stored in vehicle defect semantics recognition rule base
Each sequence of words carries out rule match, obtains candidate vehicle defect detection information;
Step_7: process is extracted using key message and extracts vehicle defect from candidate vehicle defect detection information set
Key message is described;
The key message extracts process
1. traversing the sequence of words in candidate vehicle defect detection information set;
2. finding the vocabulary C for being marked as component;
3. respectively forwardly and backward being traversed online cliction based on vocabulary C and being converged, the window size for traversing context is 5,
The vocabulary for being marked as position and described is found, to constitute key message combination;
4. traverse context, position the and described vocabulary quantity forwardly and rearwardly found is up to 2;
5. obtaining vehicle defect describes key message.
Further, the background server extracts the image content in the report of defect Preliminary detection, orients picture
Image-region in content where license plate blurs the image-region where license plate, comprising:
Background server extracts the image content in the report of defect Preliminary detection, is extracted using depth convolutional neural networks
The high-level feature of license plate in image obtains license plate institute by forward calculation using the mode that shallow-layer feature and further feature merge
In the coordinate points and rotation angle of the rectangle of position, the figure where license plate is outlined according to the coordinate points of the rectangle and rotation angle
As region, license plate virtualization processing is carried out to the image-region where the license plate using mean filter process.
As can be seen from the technical scheme provided by the above-mentioned embodiment of the present invention, the embodiment of the present invention by customizing language in advance
Adopted recognition rule library, and have data learning functionality, inspector is more, and data are more quasi-, has significantly simplified existing used car
The threshold of industry detection, improves the detectability of inspector.By the design of vehicle condition method for recognizing semantics, inspector is realized
Nonstandardized technique voice, words input, method are converted to standard situation of remote automatically, have high flexibility and convenience, nothing
It needs to ask testing staff according to testing requirements, shoots whole vehicle condition photos, it is only necessary to take pictures to the vehicle condition found the problem standby
Note.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill of field, without creative efforts, it can also be obtained according to these attached drawings others
Attached drawing.
Fig. 1 is a kind of realization principle schematic diagram of vehicle remote detection method provided in an embodiment of the present invention;
Fig. 2 is a kind of process flow diagram of vehicle remote detection method provided in an embodiment of the present invention;
Fig. 3 is a kind of process flow diagram of semantic analysis provided in an embodiment of the present invention.
Specific embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the accompanying drawings, wherein from beginning
Same or similar element or element with the same or similar functions are indicated to same or similar label eventually.Below by ginseng
The embodiment for examining attached drawing description is exemplary, and for explaining only the invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or coupling.Wording used herein
"and/or" includes one or more associated any cells for listing item and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term) there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, which should be understood that, to be had and the meaning in the context of the prior art
The consistent meaning of justice, and unless defined as here, it will not be explained in an idealized or overly formal meaning.
In order to facilitate understanding of embodiments of the present invention, it is done by taking several specific embodiments as an example below in conjunction with attached drawing further
Explanation, and each embodiment does not constitute the restriction to the embodiment of the present invention.
The embodiment of the invention provides a kind of vehicle remote detection method, this method detection Shi Jing senior according to industry
Test, design detected rule and process and detection function easy to use, make to have the inspector of basic vehicle common sense according to
It is required that shooting specified photo, paint film instrument data are imported, the dual mode for identifying by cloud and manually identifying assists inspector
Generate believable used car examining report.This method energizes the detectability of automobile in a manner of cloud to different detectabilities
User, find vehicle problem in time.
Vehicle remote detection method provided in an embodiment of the present invention and APP (Application, computer applied algorithm) are matched
It closes and uses.
User role in vehicle remote detection method provided in an embodiment of the present invention is defined as follows:
Inspector: all front-end detection personnel using vehicle remote detection method;
Cloud: the background server of vehicle remote detection method, the user of the background server include professional assessment division
Team;
Testing agency: all to detect demand client using the third party for putting management backstage outside;
Buyer: the auction buyer of platform registration is associated in farsighted person, it may be possible to car trader, the shop 4S group etc.;
Seller: the used car seller of platform registration is associated in farsighted person, it may be possible to car trader, the shop 4S group, market;
Authentication process:
Inspector needs to submit inspector identity information real-name authentication, and the background audit by vehicle remote detection method is logical
Later vehicle real name is detected;
Testing agency needs to sign a contract with vehicle remote detection method platform, can just be managed to inspector, and
It trades;
Buyer is with seller: need the auction platform that is associated in vehicle remote detection method to pay guarantee fund, it just can be right
Vehicle is traded
Detect operation flow:
The seller and testing agency initiate detection demand, and by regular under worksheet processing system and line, arrangement inspector sends out vehicle
Detection is played, vehicle remote detection method can obtain different detection configurations, then improve detection information submission according to business need
To farsighted person backstage.
Appraiser can generate professional examining report point in conjunction with system miscellaneous function processing detection data according to system worksheet processing
Issue inspector and testing agency;If detection data is problematic, it can reject and require to detect again to inspector;If testing number
According to there is no problem, testing staff or testing agency can be traded with the direct restocking commodity of examining report.
The realization principle schematic diagram of vehicle remote detection method provided in an embodiment of the present invention is as described in Figure 1, specific to handle
Process is as shown in Fig. 2, include following processing step:
Step 21, inspector are registered firstly the need of in testing agency, and the identity letter of inspector is submitted to testing agency
Breath.The identity information of the inspector received is transferred to cloud (the i.e. background service of vehicle remote detection method by testing agency
Device).After the identity information of cloud audit inspector passes through, the identity audit for returning to inspector to testing agency passes through message.In
It is that inspector succeeds in registration in testing agency, the identity information of the testing agency person of will test is stored, and carries out pipe to inspector
Reason, inspector can be carried out vehicle transaction.
Step 22, all detection targets and each detection target that vehicle is stored in vehicle defect semantics recognition rule base
Corresponding all possible testing results and the corresponding semantic matches rule of each detection target.
Pre-defined vehicle defect semantics recognition rule base, stores the institute of vehicle in vehicle defect semantics recognition rule base
There are detection target and the corresponding all possible testing results of each detection target and the corresponding semantic matches of each detection target
Rule, the semantic matches rule may include that the vehicle condition semanteme of voice, picture, mathematic sign, label and/or text representation is compiled
Code.
All detection targets may include: left front tire, left front wheel hub, left front fender, on the outside of left A column, left front car door,
Left exterior mirror, left front car door edge sealing, the left big side in bottom, left front threshold, left B column outside, left C column outside, left back car door are left back
Car door edge sealing, left back threshold, left rear tire, left back wheel hub, fuel tank cap, left back fender, front bumper, air-inlet grille have the right side
Headlamp assembly, left headlamp assembly, left front fog lamp, right front fog lamp, front windshield, front windshield rain brush, roof, after keep out the wind
Glass, luggage-boot lid, luggage-boot lid edge, rear windshield rain brush, off-front wheel hub, right front fire, right front fender, outside right A column
Side, right exterior mirror, right front door, right front door edge sealing, the right big side in bottom, right front door sill, right B column outside, right rear door are right
On the outside of C column, right rear door edge sealing, right-rear-door sill, right rear fender, off hind wheel hub, right rear fire, roof, boot, left front vehicle
Door internal decoration plate, left A column trim panel, left back vehicle door interior trim panel, left B column trim panel, left C column trim panel, steering wheel, workbench are preceding
Row's air-conditioner air outlet, glove box, instrument, centralized control, handle of gear handle, handle of gear dirt-proof boot, armrest box, master drive seat, vice operator's seat
Chair, left back seat, right back seat, left front vehicle door interior trim panel, right A column trim panel, right rear door inner decoration board, right B column trim panel are right
C column trim panel, front anti-collision beam, left front shock absorber bearing, removable water tank frame, left headlamp frame, water tank upper bracket prop up under water tank
Frame, left front fender liner, left front girder, left front A column inside and edge sealing, left B column inside and edge sealing, left C column inside and edge sealing,
Preceding surrounding baffle (firewall), back buffer beam, squab panel, left back shock absorber bearing, left tail lamp frame, underbody, luggage case edge sealing,
Baggage-compartment partition, left rear longitudinal beam, right front damper seat, right headlamp frame, right front fender liner, front right longitudinal beam, in right B column
Side and edge sealing, right C column inside and edge sealing, right A column inside and edge sealing, right rear shock absorber seat, right tail lamp frame, right floor side member are left
Front door handle, left back catch, right front door knob, right-rear-door knob, front fog lamp, Rear Fog Lamp, left front wheel arch, left back wheel arch are right
Preceding wheel arch, off hind wheel eyebrow, plaque under front bumper, plaque, front fog lamp grid and Rear Fog Lamp grid under rear bumper.
For example, being directed to the detection target of vehicle paint film, testing result has included: whether touch-up paint, putty reparation.
Each detection project on APP is configured in step 23, detection configuration database beyond the clouds, in each detection project
Including multiple above-mentioned detection targets.
Also need to establish a set of detection configuration database beyond the clouds, according to the requirement of business in the detection configuration database
Each detection project on APP (Application, computer applied algorithm) is configured, includes on multiple in each detection project
State detection target.The detection target for including in each detection project can carry out flexible configuration according to actual needs, appropriate to increase
Or it reduces.
Step 24, inspector are detected using APP by detection target of the various detection instruments to vehicle, by vehicle
The report of defect Preliminary detection is submitted on cloud.
Inspector is first according to actually detected it needs to be determined that detection project, inquires detection configuration database according to detection project
Obtain the corresponding detection target of detection project.It is then detected that member utilizes APP by various detection instruments to the detection target of vehicle
The defect problem for being detected, and being detected by descriptions such as voice, picture and/or texts, the defect for obtaining vehicle are preliminary
Examining report after detection, the defect Preliminary detection report of vehicle is submitted on cloud, the automobile for waiting cloud to return is commented
Estimate result.
Step 25 carries out semantic analysis to the content of text in the report of defect Preliminary detection using semantic matches rule, obtains
Key message is described to vehicle defect, and license plate virtualization process is combined to obtain vehicle assessment report.
After cloud receives the defect Preliminary detection report of above-mentioned vehicle, extract in the text in the report of defect Preliminary detection
Hold, semantic analysis is carried out to content of text, semantic analysis is carried out to content of text using semantic matches rule, obtains vehicle defect
Key message is described.The process flow of the semantic analysis is as shown in figure 3, include following processing step:
Step_1: Chinese spcial character processing is carried out to content of text, the double byte character in content of text is converted to half
Angle character;
Step_2: with English branch (;) sentence division is carried out to content of text, obtain sentence set to be processed;
Step_3: word segmentation processing is carried out to each sentence, obtains the sequence of words of each sentence;
Step_4: traversing the sequence of words of sentence, mapping word is substituted for corresponding mapping content set, after being mapped
The set of sequence of words;
Step_5: the sequence of words after recombination mapping obtains recombination sentence set, and divides the sentence after recombination
Word obtains new sequence of words set;
Step_6: each vocabulary in sequence of words is mapped as to the correspondence stored in vehicle defect semantics recognition rule base
Detection target, it is right further according to the corresponding semantic matches rule of the detection target that is stored in vehicle defect semantics recognition rule base
Each sequence of words carries out rule match, obtains candidate vehicle defect detection information;
Step_7: process is extracted using key message and extracts vehicle defect from candidate vehicle defect detection information set
Key message is described.
Above-mentioned key message extracts process
1. traversing the sequence of words in candidate vehicle defect detection information set;
2. finding the vocabulary C for being marked as component;
3. respectively forwardly and backward being traversed online cliction based on vocabulary C and being converged, the window size for traversing context is 5,
The vocabulary for being marked as position and described is found, to constitute key message combination;
4. traverse context, position the and described vocabulary quantity forwardly and rearwardly found is up to 2;
5. obtaining vehicle defect describes key message.
Since different classes of license plate purposes is different, format may also be different, and licence plate classification is by licence plate face
Color determines, therefore color identification is important step of Car license recognition, and determines whether Car license recognition is correctly crucial,
One of factor, the raising of recognition correct rate facilitate the raising of final Recognition Algorithm of License Plate performance.To the vehicle of specified angle
License plate identified, and the license plate identified is blurred automatically, and then protect privacy of user.
Picture recognition refers to be handled image, analyzed and is understood using computer, to identify various different modes
Target and technology to picture.At present industry for the scheme of image recognition be mainly license plate number identification smear, or to license plate into
Pedestrian's work is blocked, and privacy of user is protected.
A kind of license plate virtualization process provided in an embodiment of the present invention includes: in the picture extracted in the report of defect Preliminary detection
Hold, orients the image-region in image content where license plate, the image-region where license plate is blurred.Where license plate
The high-level feature of license plate in image is mainly extracted in image-region positioning using the depth convolutional neural networks of lightweight, is passed through
Forward calculation obtains the coordinate points and rotation angle of the rectangle of license plate position, accurately outlines the image district where license plate
Domain, the mode merged in model using shallow-layer feature and further feature, increases the precision of model orientation license plate.Obtaining license plate institute
Image-region after, realized using a mean filter license plate blur.
Cloud, which describes key message according to above-mentioned vehicle defect, can quickly recognize using model data library the money of vehicle
Then type information confirms vehicle configuration information, can also inquire vehicle history maintenance note by the maintenance query interface on backstage
Record and insurance record, avoid the occurrence of mileometer adjustment vehicle, accident vehicle.Appraiser identifies vehicle basic photo and formality photo, such as
Fruit shooting photo is unintelligible, can reject to inspector, it is desirable that detect again, it is ensured that authenticity, the validity of vehicle detection data.
Cloud comprehensive review vehicle condition, comprehensive all kinds of detection datas give one comprehensive land gradation of vehicle and marking, and license plate are combined to blur process
A vehicle assessment report is provided.It is subsequent, online transaction can be carried out to vehicle according to vehicle assessment report.
It has done a large amount of used car vehicle condition semantic rules coding from the background beyond the clouds, has made in vehicle condition detection process, for detection
The accuracy rate of picture indicia test problems is up to 95% or more
In conclusion the embodiment of the present invention is by presetting vehicle defect semantics recognition rule base, and have data
Function is practised, inspector is more, and data are more quasi-, has significantly simplified the threshold of existing used car industry detection, has improved detection
The detectability of member.By designing and using the corresponding semantic matches rule of detection target, inspector nonstandardized technique language is realized
Sound, words input are converted to standard situation of remote automatically, have high flexibility and convenience, without requiring testing staff
According to testing requirements, whole vehicle condition photos are shot, it is only necessary to which remarks of taking pictures are carried out to the vehicle condition found the problem.
The present invention has higher identification energy by blurring color, angle, the scene that technology is directed to license plate using license plate
Power, and support it is automatic smear, reduce the testing cost of testing staff, improve detection efficiency, this is our originals to be protected
Cause.
The remote automobile detection method of the embodiment of the present invention supports different testing staff, under different regions, scene
Detection used car simultaneously generates unified examining report, greatly reduces testing staff's training cost of enterprise, has expanded detection originally
The scope of business of body, improves detection efficiency and quality.It can be customized according to customer demand, business demand, in kit
Detection content generates a general examining report.
The remote automobile detection method of the embodiment of the present invention can easily clap 40,000 a plurality of vehicle libraries data, paint film number based on vehicle
According to history valuation data, provide detection Valuation Modelling for vehicle detection, fast and accurately generate examining report.
Those of ordinary skill in the art will appreciate that: attached drawing is the schematic diagram of one embodiment, module in attached drawing or
Process is not necessarily implemented necessary to the present invention.
As seen through the above description of the embodiments, those skilled in the art can be understood that the present invention can
It realizes by means of software and necessary general hardware platform.Based on this understanding, technical solution of the present invention essence
On in other words the part that contributes to existing technology can be embodied in the form of software products, the computer software product
It can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes the certain of each embodiment or embodiment of the invention
Method described in part.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device or
For system embodiment, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to method
The part of embodiment illustrates.Apparatus and system embodiment described above is only schematical, wherein the conduct
The unit of separate part description may or may not be physically separated, component shown as a unit can be or
Person may not be physical unit, it can and it is in one place, or may be distributed over multiple network units.It can root
According to actual need that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.Ordinary skill
Personnel can understand and implement without creative efforts.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims
Subject to.
Claims (7)
1. a kind of vehicle remote detection method, which is characterized in that store the inspection of vehicle in vehicle defect semantics recognition rule base
Survey target semantic matches rule corresponding with detection target, which comprises
According to detection it needs to be determined that detection project, obtains the corresponding detection target of detection project, by detection instrument to vehicle
Detection target is detected, and the defect Preliminary detection report for the vehicle that will test is submitted on background server;
The background server corresponding semantic using the detection target stored in the vehicle defect semantics recognition rule base
With rule, semantic analysis is carried out to the content of text in defect Preliminary detection report and obtains the crucial letter of vehicle defect description
Breath, describes key message based on the vehicle defect and obtains vehicle assessment report.
2. the method according to claim 1, wherein the method further include:
Inspector is registered in testing agency first, and the identity information of inspector is submitted to testing agency, and testing agency will connect
The identity information of the inspector received is transferred to background server, after the identity information of background server audit inspector passes through,
The identity audit for returning to inspector to testing agency passes through message, and inspector succeeds in registration in testing agency, and testing agency will examine
The identity information of survey person carries out storage and management.
3. the method according to claim 1, wherein described store in vehicle defect semantics recognition rule base
The detection target of vehicle semantic matches rule corresponding with detection target, comprising:
Vehicle defect semantics recognition rule base is managed in background server, stores vehicle in vehicle defect semantics recognition rule base
The corresponding all possible testing results of all detection targets and each detection target and the corresponding language of each detection target
Adopted matching rule, the semantic matches rule include that the vehicle condition semanteme of voice, picture, mathematic sign, label and/or text representation is compiled
Code.
4. left front according to the method described in claim 3, it is characterized in that, all detection targets include: left front tire
Wheel hub, left front fender, left A column outside, left front car door, left exterior mirror, left front car door edge sealing, the left big side in bottom, left front door
Sill, left B column outside, left C column outside, left back car door, left back car door edge sealing, left back threshold, left rear tire, left back wheel hub, fuel tank
Lid, left back fender, front bumper, air-inlet grille have a right headlamp assembly, left headlamp assembly, left front fog lamp, it is right before mist
Lamp, front windshield, front windshield rain brush, roof, rear seat windscreen, luggage-boot lid, luggage-boot lid edge, rear windshield rain brush
Device, off-front wheel hub, right front fire, right front fender, right A column outside, right exterior mirror, right front door, right front door edge sealing,
The right big side in bottom, right front door sill, right B column outside, right rear door, right C column outside, right rear door edge sealing, right-rear-door sill, right rear wing
Plate, off hind wheel hub, right rear fire, roof, boot, left front vehicle door interior trim panel, left A column trim panel, left back vehicle door interior trim panel are left
B column trim panel, left C column trim panel, steering wheel, workbench, front-seat air-conditioner air outlet, glove box, instrument, centralized control, handle of gear
Handle, handle of gear dirt-proof boot, armrest box, master drive seat, the passenger side seat, left back seat, right back seat, left front vehicle door interior trim panel, right A
Column trim panel, right rear door inner decoration board, right B column trim panel, right C column trim panel, front anti-collision beam, left front shock absorber bearing, removable water
Cabinet frame, left headlamp frame, water tank upper bracket, water tank lower bracket, left front fender liner, left front girder, left front A column inside
And edge sealing, on the inside of left B column and edge sealing, on the inside of left C column and edge sealing, preceding surrounding baffle, back buffer beam, squab panel, left back shock absorber bearing,
Left tail lamp frame, underbody, luggage case edge sealing, baggage-compartment partition, left rear longitudinal beam, right front damper seat, right headlamp frame,
Right front fender liner, front right longitudinal beam, right B column inside and edge sealing, right C column inside and edge sealing, right A column inside and edge sealing, after right
Shock absorber bearing, right tail lamp frame, right floor side member, left front catch, left back catch, right front door knob, right-rear-door knob, preceding mist
Lamp, Rear Fog Lamp, left front wheel arch, left back wheel arch, off-front wheel eyebrow, off hind wheel eyebrow, plaque under front bumper, plaque under rear bumper,
Front fog lamp grid and Rear Fog Lamp grid.
5. the method according to claim 3 or 4, which is characterized in that it is described according to detection it needs to be determined that detection project, is obtained
The corresponding detection target of detection project is taken, is detected by detection target of the detection instrument to vehicle, the vehicle that will test
Defect Preliminary detection report be submitted on background server, comprising:
Management detection configuration database, configures according to the requirement of business in the detection configuration database and counts in background server
Each detection project in calculation machine application APP includes multiple detection targets in each detection project;
Inspector is first according to actually detected it needs to be determined that detection project, inquires detection configuration database according to detection project and obtain
The corresponding detection target of detection project, inspector are detected using APP by detection target of the various detection instruments to vehicle,
And the defect problem that detected by voice, picture and/or verbal description, the defect Preliminary detection report of vehicle is obtained, it will
The defect Preliminary detection report is submitted on background server.
6. according to the method described in claim 5, it is characterized in that, the background server is semantic using the vehicle defect
The corresponding semantic matches rule of the detection target stored in recognition rule library, in the text in defect Preliminary detection report
Hold and carry out semantic analysis and obtain vehicle defect and describe key message, describes key message based on the vehicle defect and obtain vehicle to comment
Estimate report, comprising:
After background server receives the defect Preliminary detection report of the vehicle, the text in the report of defect Preliminary detection is extracted
Content carries out semantic analysis to content of text using semantic matches rule, obtains vehicle defect and describe key message;
Background server extracts the image content in the report of defect Preliminary detection, orients the image in image content where license plate
Region blurs the image-region where license plate;
Background server describes the style information that key message identifies using model data library vehicle according to the vehicle defect,
Confirm vehicle configuration information, vehicle history maintenance record is inquired by the maintenance query interface on backstage and insurance records, backstage
The comprehensive all kinds of detection datas of server describe key message and license plate virtualization in conjunction with the vehicle defect and comment as a result, obtaining vehicle
Estimate report;
Described includes following processing step to content of text progress semantic analysis using semantic matches rule:
Step_1: Chinese spcial character processing is carried out to content of text, the double byte character in content of text is converted into half widths
Symbol;
Step_2: with English branch (;) sentence division is carried out to content of text, obtain sentence set to be processed;
Step_3: word segmentation processing is carried out to each sentence, obtains the sequence of words of each sentence;
Step_4: traversing the sequence of words of sentence, and mapping word is substituted for corresponding mapping content set, vocabulary after being mapped
The set of sequence;
Step_5: the sequence of words after recombination mapping obtains recombination sentence set, and segments to the sentence after recombination, obtains
Obtain sequence of words set newly;
Step_6: each vocabulary in sequence of words is mapped as to the corresponding inspection stored in vehicle defect semantics recognition rule base
Target is surveyed, further according to the corresponding semantic matches rule of detection target stored in vehicle defect semantics recognition rule base, to each
Sequence of words carries out rule match, obtains candidate vehicle defect detection information;
Step_7: process is extracted using key message and extracts vehicle defect description from candidate vehicle defect detection information set
Key message;
The key message extracts process
1. traversing the sequence of words in candidate vehicle defect detection information set;
2. finding the vocabulary C for being marked as component;
3. respectively forwardly and backward being traversed online cliction based on vocabulary C and being converged, the window size for traversing context is 5, is found
It is marked as the vocabulary of position and described, to constitute key message combination;
4. traverse context, position the and described vocabulary quantity forwardly and rearwardly found is up to 2;
5. obtaining vehicle defect describes key message.
7. according to the method described in claim 6, it is characterized in that, the background server extracts the report of defect Preliminary detection
In image content, orient the image-region in image content where license plate, the image-region where license plate blurred,
Include:
Background server extracts the image content in the report of defect Preliminary detection, extracts image using depth convolutional neural networks
The high-level feature of middle license plate obtains license plate institute in place by forward calculation using the mode that shallow-layer feature and further feature merge
The coordinate points and rotation angle for the rectangle set outline the image district where license plate according to the coordinate points of the rectangle and rotation angle
Domain carries out license plate virtualization processing to the image-region where the license plate using mean filter process.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811425532.4A CN109597991B (en) | 2018-11-27 | 2018-11-27 | Automobile remote detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811425532.4A CN109597991B (en) | 2018-11-27 | 2018-11-27 | Automobile remote detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109597991A true CN109597991A (en) | 2019-04-09 |
CN109597991B CN109597991B (en) | 2023-04-28 |
Family
ID=65960473
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811425532.4A Active CN109597991B (en) | 2018-11-27 | 2018-11-27 | Automobile remote detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109597991B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110610007A (en) * | 2019-09-20 | 2019-12-24 | 广州穗圣信息科技有限公司 | Maintenance vehicle condition intelligent identification method and device based on NLP |
CN110889593A (en) * | 2019-11-01 | 2020-03-17 | 浙江大搜车软件技术有限公司 | Vehicle evaluation method, device, computer-readable storage medium and computer equipment |
CN111553285A (en) * | 2020-04-29 | 2020-08-18 | 上海智勘科技有限公司 | Method and system for protecting user privacy information in vehicle remote damage assessment process |
CN111626815A (en) * | 2020-05-07 | 2020-09-04 | 成都检车家汽车服务有限公司 | Vehicle detection order processing system and method |
CN111626690A (en) * | 2020-04-23 | 2020-09-04 | 成都检车家汽车服务有限公司 | Vehicle detection system and method |
CN112102838A (en) * | 2020-03-04 | 2020-12-18 | 浙江大搜车软件技术有限公司 | Vehicle detection report generation method and system and electronic equipment |
CN112785561A (en) * | 2021-01-07 | 2021-05-11 | 天津狮拓信息技术有限公司 | Second-hand commercial vehicle condition detection method based on improved Faster RCNN prediction model |
CN113254113A (en) * | 2021-05-24 | 2021-08-13 | 国家计算机网络与信息安全管理中心 | Vehicle safety defect verification method and system |
CN113487047A (en) * | 2021-07-01 | 2021-10-08 | 石家庄华燕交通科技有限公司 | Intelligent guide system for motor vehicle inspection business |
CN114279718A (en) * | 2021-11-30 | 2022-04-05 | 重庆长安汽车股份有限公司 | Configurable fault diagnosis method and system based on real-time vehicle condition |
CN114584584A (en) * | 2022-02-28 | 2022-06-03 | 福思(杭州)智能科技有限公司 | System and method for processing vehicle driving data and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101853478A (en) * | 2009-04-01 | 2010-10-06 | 杭州信雅达科技有限公司 | Automobile fault diagnosis system based on ontology and mobile network |
CN105610850A (en) * | 2016-01-13 | 2016-05-25 | 天津大学 | Vehicle service and management system based on internet of vehicles |
CN106169098A (en) * | 2016-06-28 | 2016-11-30 | 江苏车置宝信息科技股份有限公司 | Used car vehicle condition intelligent checking system and method |
CN106708017A (en) * | 2016-12-26 | 2017-05-24 | 华东理工大学 | Vehicle fault real-time monitoring and service system and application thereof |
CN106971322A (en) * | 2017-05-17 | 2017-07-21 | 因车(上海)企业管理有限公司 | A kind of mirror valency system and its mirror valency method for used car remote evaluation |
JP2018097540A (en) * | 2016-12-12 | 2018-06-21 | 三菱自動車工業株式会社 | Positional information reporting device for defective vehicle |
CN108364653A (en) * | 2018-02-12 | 2018-08-03 | 王磊 | Voice data processing method and processing unit |
-
2018
- 2018-11-27 CN CN201811425532.4A patent/CN109597991B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101853478A (en) * | 2009-04-01 | 2010-10-06 | 杭州信雅达科技有限公司 | Automobile fault diagnosis system based on ontology and mobile network |
CN105610850A (en) * | 2016-01-13 | 2016-05-25 | 天津大学 | Vehicle service and management system based on internet of vehicles |
CN106169098A (en) * | 2016-06-28 | 2016-11-30 | 江苏车置宝信息科技股份有限公司 | Used car vehicle condition intelligent checking system and method |
JP2018097540A (en) * | 2016-12-12 | 2018-06-21 | 三菱自動車工業株式会社 | Positional information reporting device for defective vehicle |
CN106708017A (en) * | 2016-12-26 | 2017-05-24 | 华东理工大学 | Vehicle fault real-time monitoring and service system and application thereof |
CN106971322A (en) * | 2017-05-17 | 2017-07-21 | 因车(上海)企业管理有限公司 | A kind of mirror valency system and its mirror valency method for used car remote evaluation |
CN108364653A (en) * | 2018-02-12 | 2018-08-03 | 王磊 | Voice data processing method and processing unit |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110610007A (en) * | 2019-09-20 | 2019-12-24 | 广州穗圣信息科技有限公司 | Maintenance vehicle condition intelligent identification method and device based on NLP |
CN110889593A (en) * | 2019-11-01 | 2020-03-17 | 浙江大搜车软件技术有限公司 | Vehicle evaluation method, device, computer-readable storage medium and computer equipment |
CN112102838A (en) * | 2020-03-04 | 2020-12-18 | 浙江大搜车软件技术有限公司 | Vehicle detection report generation method and system and electronic equipment |
CN111626690A (en) * | 2020-04-23 | 2020-09-04 | 成都检车家汽车服务有限公司 | Vehicle detection system and method |
CN111553285A (en) * | 2020-04-29 | 2020-08-18 | 上海智勘科技有限公司 | Method and system for protecting user privacy information in vehicle remote damage assessment process |
CN111626815B (en) * | 2020-05-07 | 2023-09-12 | 成都检车家汽车服务有限公司 | Processing system and method for vehicle detection order |
CN111626815A (en) * | 2020-05-07 | 2020-09-04 | 成都检车家汽车服务有限公司 | Vehicle detection order processing system and method |
CN112785561A (en) * | 2021-01-07 | 2021-05-11 | 天津狮拓信息技术有限公司 | Second-hand commercial vehicle condition detection method based on improved Faster RCNN prediction model |
CN113254113A (en) * | 2021-05-24 | 2021-08-13 | 国家计算机网络与信息安全管理中心 | Vehicle safety defect verification method and system |
CN113487047A (en) * | 2021-07-01 | 2021-10-08 | 石家庄华燕交通科技有限公司 | Intelligent guide system for motor vehicle inspection business |
CN113487047B (en) * | 2021-07-01 | 2022-11-08 | 石家庄华燕交通科技有限公司 | Intelligent guiding system for motor vehicle inspection business |
CN114279718A (en) * | 2021-11-30 | 2022-04-05 | 重庆长安汽车股份有限公司 | Configurable fault diagnosis method and system based on real-time vehicle condition |
CN114279718B (en) * | 2021-11-30 | 2023-02-28 | 重庆长安汽车股份有限公司 | Configurable fault diagnosis method and system based on real-time vehicle condition |
CN114584584A (en) * | 2022-02-28 | 2022-06-03 | 福思(杭州)智能科技有限公司 | System and method for processing vehicle driving data and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109597991B (en) | 2023-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109597991A (en) | Vehicle remote detection method | |
US11244438B2 (en) | Auxiliary parts damage determination | |
CN110378236B (en) | Vehicle identity recognition model construction and recognition method and system based on deep learning | |
CN110569701B (en) | Computer-implemented vehicle damage assessment method and device | |
Hassan et al. | Real-time uav detection based on deep learning network | |
CN106845412B (en) | Obstacle identification method and device, computer equipment and readable medium | |
CN110532855B (en) | Natural scene certificate image character recognition method based on deep learning | |
CN115810134A (en) | Image acquisition quality inspection method, system and device for preventing car insurance from cheating | |
CN116452802A (en) | Vehicle loss detection method, device, equipment and storage medium | |
CN110929502B (en) | Text error detection method and device | |
Dvorak et al. | Automated Train Operations (ATO) Sensor Platform Data Analysis Rapid Prototype | |
KR20240010927A (en) | Apparatus and method for determining dangerous road section based on natural language processing | |
Heitzinger | High accuracy image segmentation for motor vehicles | |
CN117196799A (en) | Self-adaptive processing method and device for due diligence based on big data analysis |
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 |