CN109598238A - Information processing method and device, storage medium and electronic equipment - Google Patents
Information processing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN109598238A CN109598238A CN201811475919.0A CN201811475919A CN109598238A CN 109598238 A CN109598238 A CN 109598238A CN 201811475919 A CN201811475919 A CN 201811475919A CN 109598238 A CN109598238 A CN 109598238A
- Authority
- CN
- China
- Prior art keywords
- recipient
- information
- address
- location
- recipient address
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
- G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Character Discrimination (AREA)
Abstract
The invention discloses a kind of information processing method and devices, storage medium and electronic equipment, wherein information processing method includes: to obtain recipient's image information from sender, which is picture format；Text region is carried out to recipient's image information, to obtain recipient's text information, recipient's text information includes: recipient's personal information and recipient address；Location matches are carried out to recipient address according to the location information of sender, to obtain the location information of recipient address；Distribution information is generated according to the location information of recipient's personal information and recipient address, in order to be dispensed.By the invention it is possible to accurately obtain the location information of recipient address, the higher distribution information of accuracy rate is generated, so as to promote the experience sense of trade company.
Description
Technical field
The present invention, which discloses, is related to field of image processing, and in particular to a kind of information processing method and device, storage medium and
Electronic equipment.
Background technique
Currently, immediate distribution service can be provided for trade company using (app) by third-part delivery service.Trade company one day
Delivery service amount is about up to ten thousand, wherein trade company is manually entered about 2 one-tenth of order information accounting, and the quantity by client
In sustainable growth.
Trade company by being manually entered, be subject to map recommend, the mode of guidance, complete addressee information typing, with this come to
Third-part delivery service application provides distribution information.Specifically, trade company is manually filling sender information, addressee information, connection
It is mode and POI (Point of Interest, point of interest) information (that is, effectively dispensing address), confirms corresponding carrying ore structure
The information being manually entered is sent to downstream waybill system after mode.
It is manually entered distribution information and occupies trade company's plenty of time, efficiency is lower；Also, it is manually entered in trade company non-standard
When address information, easily occur that POI information (including position location longitude and latitude and POI title) can not be matched, so that trade company can be caused
Maloperation, reduce dispatching efficiency.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of information processing method and device, storage medium and electronic equipment, with
Solve it is in the prior art be manually entered low efficiency existing for distribution information and sometimes due to POI information can not be matched caused by
The problem of mistake distribution information.
According to a first aspect of the embodiments of the present invention, a kind of information processing method is provided, this method comprises: obtaining next spontaneous
The recipient's image information for the side of sending, recipient's image information are picture format；Text region is carried out to recipient's image information,
To obtain recipient's text information, recipient's text information includes: recipient's personal information and recipient address；According to sender
Location information to recipient address carry out location matches, to obtain the location information of recipient address；According to recipient individual
The location information of information and recipient address generates distribution information.
According to a second aspect of the embodiments of the present invention, a kind of information processing unit is provided, which includes: that image obtains list
Member, for obtaining recipient's image information from sender, which is picture format；Text region list
Member, for carrying out Text region to recipient's image information, to obtain recipient's text information, recipient's text information includes:
Recipient's personal information and recipient address；Location matches unit, for the location information according to sender to recipient address
Location matches are carried out, to obtain the location information of recipient address；Distribution information generation unit, for being believed according to recipient individual
Breath and the location information of recipient address generate distribution information.
According to a third aspect of the embodiments of the present invention, a kind of computer readable storage medium is provided, stores computer thereon
Program instruction, wherein computer program instructions realize method as described in relation to the first aspect when being executed by processor.
According to a fourth aspect of the embodiments of the present invention, a kind of electronic equipment, including memory and processor are provided, wherein
Memory is for storing one or more computer program instructions, wherein one or more computer program instructions are by processor
It executes to realize method as described in relation to the first aspect.
The embodiment of the present invention is believed further according to the position of sender later by carrying out Text region to recipient's image information
Breath carry out location matches obtain the location information of recipient address, accordingly generate distribution information, compared with the existing technology in hand
Dynamic input distribution information, since the embodiment of the present invention is manually operated without trade company (that is, sender), thus can be improved generation and matches
It delivers letters the efficiency of breath, and location matches is carried out by the location information thus according to sender, so as to accurately obtain
The location information of recipient address generates the higher distribution information of accuracy rate, so as to promote the experience sense of trade company.
Detailed description of the invention
By referring to the drawings to the description of the embodiment of the present invention, the above and other purposes of the present invention, feature and
Advantage will be apparent from, in the accompanying drawings:
Fig. 1 is the flow chart of information processing method according to an embodiment of the present invention；
Fig. 2 is the flow chart according to an embodiment of the present invention based on OCR Text region；
Fig. 3 is the flow chart of location matches according to an embodiment of the present invention；
Fig. 4 is delivery service flow diagram according to an embodiment of the present invention；
Fig. 5 is the structural block diagram of information processing unit according to an embodiment of the present invention；
Fig. 6 is the structural block diagram of word recognition unit 502 according to an embodiment of the present invention；
Fig. 7 is the detailed block diagram of information processing unit according to an embodiment of the present invention；
Fig. 8 is the structural block diagram of location matches unit 503 according to an embodiment of the present invention；
Fig. 9 (a) (b) is the application scenario diagram of information processing unit according to an embodiment of the present invention；
Figure 10 is the schematic diagram of electronic equipment according to an embodiment of the present invention.
Specific embodiment
Below based on embodiment, present invention is described, but the present invention is not restricted to these embodiments.Under
Text is detailed to describe some specific detail sections in datail description of the invention.Do not have for a person skilled in the art
The present invention can also be understood completely in the description of these detail sections.In order to avoid obscuring essence of the invention, well known method, mistake
There is no narrations in detail for journey, process, element and circuit.
In addition, it should be understood by one skilled in the art that provided herein attached drawing be provided to explanation purpose, and
What attached drawing was not necessarily drawn to scale.
Unless the context clearly requires otherwise, "include", "comprise" otherwise throughout the specification and claims etc. are similar
Word should be construed as the meaning for including rather than exclusive or exhaustive meaning；That is, be " including but not limited to " contains
Justice.
In the description of the present invention, it is to be understood that, term " first ", " second " etc. are used for description purposes only, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present invention, unless otherwise indicated, the meaning of " multiple "
It is two or more.
The distribution information in the prior art that is manually entered is primarily present two class problems: being on the one hand to influence merchant effect
On the other hand rate is the POI information input based on artificial judgment, can not incorporation range circle, address longitude and latitude judge, cause
Cost, and interference information accuracy are attempted in the presence of multiple, to affect downstream consumption and situation of actually honouring an agreement.Based on this, originally
Inventive embodiments provide a kind of information processing scheme, to solve the efficiency of service being related in the prior art and POI information matching
Problem.
The embodiment of the present invention provides a kind of information processing method, and Fig. 1 is the flow chart of information processing method, as shown in Figure 1,
This method comprises:
Step 101, recipient's image information of the picture format from sender is obtained；
Step 102, Text region is carried out to recipient's image information, to obtain recipient's text information of text formatting,
Recipient's text information includes: recipient's personal information and recipient address；
Step 103, location matches are carried out to recipient address according to the location information of sender, to obtain recipient address
Location information；
Step 104, according to the location information of recipient's personal information and recipient address generate distribution information, in order into
Row dispatching.
In embodiments of the present invention, sender can be trade company, and recipient can be user, and trade company is dispensed by third party
It is served by and provides commodity delivery service for user, asked in the dispatching that sender (that is, trade company) gets recipient (that is, user)
After asking (that is, above-mentioned recipient's image information), sender carries out Text region to recipient's image information, obtains of recipient
People's information and address carry out location matches later using the location information of sender as center position in a manner of spreading to surrounding
Obtain the location information of recipient address, accordingly generate distribution information, compared with the existing technology in be manually entered distribution information,
Since the embodiment of the present invention is manually operated without trade company, thus the efficiency for generating distribution information can be improved, and due to being root
Location matches are carried out according to the location information of sender, so as to accurately obtain the location information of recipient address, are generated
The higher distribution information of accuracy rate, so as to promote the experience sense of trade company.
In actual practice it is preferred to which ground, can pass through optical character identification (Optical Character
Recognition, OCR) interface differential technique debit's image information progress Text region.
Specifically, can first scheme to recipient when carrying out Text region to recipient's image information by OCR technique
As information is pre-processed, which includes at least one of: binary conversion treatment, denoising, correction inclination processing.Its
In, binary conversion treatment is that the pixel gray value on image is set to 0 or 255, and image is made to be rendered as obvious black and white effect；Removal
Noise can be using the grain noise of mean filter removal image (for example, scanned picture) of the field method of average, correction inclination
It can be eastern (radon) correction process of drawing.By pretreatment, Text region can be made more acurrate.
Later, character area cutting process can be carried out to pretreated image.Specifically, first to pretreated figure
As carrying out word area detection, then, character area cutting process is carried out to image according to testing result.
Preferably, above-mentioned detection can be by including scene text (Efficient and Accuracy Scene
Text, EAST) and the detection model of example segmentation (PIXELLINK) algorithm realize.
EAST algorithm is based on Method for text detection end to end, and having eliminated unnecessary intermediate steps, (candidate region is poly-
Close the segmentation with word), reduce detection time, detection accuracy is higher.
PIXELLINK algorithm is the novel scene text detection algorithm of Case-based Reasoning segmentation, can be directly from segmentation
Line of text region obtains the frame (bounding box, bbox) of line of text, which abandons frame recurrence, so that training
More easily learn, detection effect and result are all preferable.
After character area cutting process is completed, multiple cutting regions are input to identification model and carry out Text region.This
In identification model can be the connection timing based on convolutional neural networks classification (Convolutional Neural
Networks+Connectionist Temporal Classification, CNN+CTC) model.
Fig. 2 is the flow chart according to an embodiment of the present invention based on OCR Text region, as shown in Fig. 2, the process includes:
Step 201, the acquisition based on identification scene and sample, input picture (or picture), the picture format can be
280mm*210mm, it is long to be greater than width；
Step 202, the image of input is pre-processed by binaryzation, noise remove, radon Slant Rectify etc.；
Step 203, by the judgement of text layout density and keyword (for example, " cell-phone number ", " contact method ", "
Location ", " contact address ", " name ", " Customer Name " etc.) positioning etc. image layout is analyzed, select Slicing Model for Foreign, here
Cutting can be realized using model E AST and PIXELLINK；
Step 204, carry out Primary Location identification sample according to cell-phone number digital information, restriction line number, special title etc. (to order
Single receipt image or order image screenshot) effective information region, exclude the interference region of non-addressee information, carry out space of a whole page word
Symbol cutting；
Step 205, identification model will be inputted after the frame interception after cutting, is lacked by additional character, line feed displacement and character
The processing such as lose and carry out character recognition, identify the text in each frame, removal title (i.e. keyword), " turning ", separator ", ",
The interference of the invalid informations such as "-", " * ", identification model here can use CNN+CTC；
Step 206, page format, position are restored by format match and interference removal etc.；
Step 207, last to require to do post-processing and text check and correction according to context and field format, tuning rule retains
Address, name, phone information etc.；
Step 208, result parameter is exported.
The result parameter can be recorded by third party's distribution side's server, the OCR Text region in the embodiment of the present invention
Accuracy rate can be more than 95%.
Recipient's personal information and the recipient of text formatting are obtained carrying out OCR Text region to recipient's image information
After address, recipient address can be parsed according to pre-defined rule, to obtain the location name of recipient address；Specifically
For, after parsing to recipient address, at least one keyword is successively extracted according to parsing result；By what is extracted
First keyword is determined as the location name of recipient address.
In actual operation, mode is filled in due to current Order Address and substantially first fills in building name, then again
In addition the detailed address specific to room number, thus, in embodiments of the present invention, the address recognized is successively extracted
First keyword is substantially building name, therefore, it is possible to which the building name to be determined as to the position of recipient address
Title.
Then, position is carried out to the location name of the recipient address in the preset range of sender's location information
Match；And the location information of recipient address is determined according to matching result.In embodiments of the present invention, location information can be longitude and latitude
Information is spent, location name (being referred to as POI name) and its longitude and latitude are specifically included.
In the specific implementation process, the address comprising other keywords other than first keyword can be determined as connecing
The better address of debit, that is, can be true by remaining recipient address after to first keyword of recipient's address extraction
It is set to the better address of recipient.In this way, the distribution information in step 104 can include recipient's personal information, recipient
The location information of address and the better address of recipient, detailed accurate distribution information are conducive to third-party dispatching.
For example, trade company receives the order of user A, trade company carries out OCR Text region to order image information, available
The address of the user A of text formatting: international young city (Tianyuan Road) (7 1 rooms unit * * * *) of taking a sea-voyage eastward can be with by parsing
Extract keyword: (1) take a sea-voyage eastward international young city and (2) Tianyuan Road.In embodiments of the present invention, will take a sea-voyage eastward international young city
It is determined as the location name of recipient address, later, centered on the location information of trade company, within the scope of trade company longitude and latitude 3km
The corresponding longitude and latitude in international young city of taking a sea-voyage eastward is inquired respectively, and 5km range, the available world of taking a sea-voyage eastward are extended to if it can not find out
The longitude and latitude in young city are as follows: 118.838987,31.931969.Furthermore it is possible to by the address except international young city of taking a sea-voyage eastward, i.e.,
(Tianyuan Road) (7 1 rooms unit * * * *) is determined as better address.
Fig. 3 is the flow chart of location matches according to an embodiment of the present invention, as shown in figure 3, the process includes:
Step 301, OCR identification parameter and the information words such as sender's location name and its longitude and latitude, city ID are inputted
Section；
Step 302, address of the addressee ingredient is parsed；
Step 303, keyword is extracted according to strategy from front to back, is analyzed, can be determined near preceding based on actual sample
(that is, first extracted) keyword is location name, i.e. POI title (POI name)；Based on interception keyword strategy, removal
Province, city and region's information, POI name are then directly removed in beginning of the sentence, otherwise retain the field, using the remaining part of raw address as in detail
Address (Detail Address)；
Step 304, based on sender city ID (City ID, urban sign code) address turn longitude and latitude service (for example,
High moral service), step 303 extract keyword and POI name carry out location finding in a certain range of sender position periphery
Strategy；
Step 305, longitude and latitude matching is carried out based on above-mentioned search strategy, text similarity height is corresponded to according to longitude and latitude,
Determine that text similarity is up to unique latitude and longitude value.
Step 306, it is exported determining longitude and latitude as the longitude and latitude of recipient address.
In actual operation, the location matches accuracy rate of the embodiment of the present invention can be more than 95%.
In the specific implementation process, the arbitrary steps in above-mentioned steps 102,103 and 104 can also be monitored, that is,
Text region operation to recipient's image information, the location matches operation to recipient address, and/or generation distribution information behaviour
It is monitored, it is higher so as to generate accuracy rate in order to understand the accuracy of Text region and location matches in time
Distribution information facilitates subsequent delivery service.
In actual operation, the arbitrary steps in the information processing method can also be monitored.
Fig. 4 is delivery service flow diagram according to an embodiment of the present invention, as shown in figure 4, the delivery service process packet
It includes:
Step 401, distribution information original page (that is, bill page) is obtained, carries out step 402-403 or step 404- later
405；
Step 402, typing of taking pictures is carried out to distribution information original page；
Step 403, judge whether the distribution information original page is typing for the first time, if it is, step 406 is carried out, if
It is not typing for the first time, then enters step 407；
Step 404, function introduction is carried out；
Step 405, regular page of taking pictures is entered, rules guide is carried out into typing of taking pictures and enters step 407 later；
Step 406, regulation guidance is carried out, enters back into step 407 after the completion；
Step 407, into camera page, 409 are entered step after carrying out shooting photo, or switching photograph album enters step 408；
Step 408, photograph is selected；
Step 409, photo is cut out and other is handled, carry out step 410 later；
Step 410, OCR Text region is carried out, output character parameter is completed in identification, carries out step 411 later；
Step 411, POI address matching is carried out to the text parameter of output and carries out step 412 if successful match, it is no
Then return to step 409；
Step 412, to the data input of successful match, such as progress step 414 without exception, step 413 is otherwise carried out；
Step 413, it after abnormal prompt, is re-typed and returns to step 409, or be manually entered after information
Carry out step 414；
Step 414, information calibration is carried out, confirmation places an order and carries out step 415 later；
Step 415, it obtains distribution information and generates page (that is, bill of lading page), be sent to third party in order to dispense.
In the specific implementation process, it is whole quasi- for can also defining the similarity of system identification information and practical distribution information
True rate, the whole accuracy rate of online guarantee is more than 95%, and city where Covering samples, by monitoring OCR utilization rate, (OCR business is covered
Lid rate；The conversion funnel that the click of OCR entrance, photo upload, confirmation place an order) and identification accuracy (OCR identification and POI matching),
Consider recognition success rate, recognition speed, interface optimization degree simultaneously, is periodically solved based on badcase (bad order) check, iteration
Rule, Continuous optimization iterative technique model and strategy, expand service coverage.
The embodiment of the present invention can overcome the prior art by OCR Text region and the address POI intelligent Matching core means
In delivery service scene under addressee information be manually entered and bring low efficiency and POI information match unsuccessful problem.
In actual operation, the result of OCR Text region and the address POI intelligent Matching can be called separately, and result
Can be directly used for Apollo (Apollo) waybill center, shunt scheduling, T duration calculation, jockey honour an agreement the downstream process such as link.
The embodiment of the present invention also provides a kind of information processing unit, and Fig. 5 is the structural block diagram of the information processing unit, such as schemes
Shown in 5, which includes: that image acquisition unit 501, word recognition unit 502, location matches unit 503 and distribution information are raw
At unit 504, in which:
Image acquisition unit 501, for obtaining recipient's image information of the picture format from sender；
Word recognition unit 502, for carrying out Text region to recipient's image information, to obtain the reception of text formatting
Square text information, recipient's text information include: recipient's personal information and recipient address；
Location matches unit 503, for carrying out location matches to recipient address according to the location information of sender, with
To the location information of recipient address；
Distribution information generation unit 504, for being generated according to the location information of recipient's personal information and recipient address
Distribution information, in order to be dispensed.
The embodiment of the present invention passes through recipient's image information that word recognition unit 502 obtains image acquisition unit 501
Text region is carried out, location matches unit 503 carries out location matches further according to the location information of sender and obtains recipient later
The location information of address, accordingly distribution information generation unit 504 generate distribution information, compared with the existing technology in be manually entered
Since the embodiment of the present invention is manually operated without trade company (that is, sender), thus generation distribution information can be improved in distribution information
Efficiency, and by thus according to sender location information carry out location matches, so as to accurately obtain recipient
The location information of address generates the higher distribution information of accuracy rate, so as to promote the experience sense of trade company.
Preferably, word recognition unit 502 can by optical character identification (OCR) interface differential technique debit image information into
Row Text region.
Specifically, as shown in fig. 6, word recognition unit 502 includes: cutting process module 5021 and Text region module
5022, in which:
Cutting process module 5021, for carrying out character area cutting process to recipient's image information；
Text region module 5022, for multiple cutting regions after character area cutting process to be input to identification model
Carry out Text region.Preferably, which can be classification (CNN+CTC) mould of the connection timing based on convolutional neural networks
Type.
Above-mentioned cutting process module 5021 specifically includes: detection sub-module 50211 and cutting process submodule 50212,
In: detection sub-module 50211 specifically can be by including scene for carrying out word area detection to recipient's image information
The detection model of text (EAST) and example segmentation (PIXELLINK) algorithm carries out character area inspection to recipient's image information
It surveys；Cutting process submodule 50212, for carrying out character area cutting process to recipient's image information according to testing result.
Preferably, above-mentioned apparatus may include pretreatment unit 505 as shown in Figure 7, which is used for
Before cutting process module 5021 executes cutting process to recipient's image information, which is located in advance
Reason, pretreatment include at least one of: binary conversion treatment, denoising, correction inclination processing.Pass through the pretreatment unit
505, Text region can be made more acurrate.
Fig. 8 is the specific block diagram of location matches unit 503, as shown in figure 8, the location matches unit 503 includes: solution
Analyse module 5031, location matches module 5032 and location information determining module 5033, in which:
Parsing module 5031, for being parsed according to pre-defined rule to recipient address, to obtain recipient address
Location name；
Location matches module 5032, in the preset range of sender's location information to the location name of recipient address
Claim to carry out location matches；
Location information determining module 5033, for determining the location information of recipient address according to matching result.In this hair
In bright embodiment, location information can be latitude and longitude information, specifically include location name (being referred to as POI name) and its
Longitude and latitude.
Above-mentioned parsing module 5031 specifically includes: analyzing sub-module 50311, keyword extraction submodule 50312 and position
Title determines submodule 50313, in which: analyzing sub-module 50311, for being solved according to pre-defined rule to recipient address
Analysis；Keyword extraction submodule 50312, for successively extracting at least one keyword according to parsing result；Location name determines
Submodule 50313, first keyword for that will extract are determined as the location name of recipient address.
In actual operation, above-mentioned apparatus can also include better address determination unit 506 shown in Fig. 7, this is in detail
Location determination unit 506 is used to the address comprising other keywords other than first keyword being determined as recipient in detail
Location, that is, the better address recipient address after first keyword will be extracted be determined as recipient.
In this way, distribution information generation unit 504 can be specifically used for: according to the position of recipient's personal information, recipient address
The better address of confidence breath and recipient generate distribution information.In this way, detailed accurate distribution information can be conducive to third
The dispatching of side.
In the specific implementation process, referring to Fig. 7, above-mentioned apparatus can also include: monitoring unit 507, for down toward
A few operation is monitored: being operated to the Text region of recipient's image information；Location matches operation to recipient address；
Generate the operation of distribution information.That is, monitoring unit 507 can monitor each unit in above-mentioned apparatus, so as to understand in time
The accuracy of Text region and location matches generates the higher distribution information of accuracy rate, facilitates subsequent delivery service.
In actual operation, monitoring unit 507 can be to any unit, module, the submodule in the information processing unit
It is monitored.
Fig. 9 (a) (b) is the application scenario diagram of information processing unit according to an embodiment of the present invention, as shown in Fig. 9 (a), quotient
Family receives multiple orders, order 1, order 2 ... ..., order N, information processing unit respectively to each order got into
Row processing, image acquisition unit 501 obtain the order information (for example, order 1) for the picture format that trade company sends, Text region list
502 pairs of order informations of member carry out Text region, and specifically, cutting process module 5021 carries out character area to order information and cuts
Cut processing, the order information after obtaining the cutting process as shown in Fig. 9 (b), Text region module 5022 is by cutting process later
Multiple cutting regions afterwards are input to CNN+CTC model and carry out Text region, the text information of 1 client of order are obtained, for example, such as
Shown in lower:
OCR recognition result parameter:
Name: Yang Nvshi
Cell-phone number: 130*****42,
Extension number: 3105,
Better address: international young city (Tianyuan Road) (7 1 rooms unit * * * *) of taking a sea-voyage eastward.
Later, location matches unit 503 carries out location matches to 1 customer address of order according to the location information of trade company, obtains
It, specifically, can be according to trade company's longitude, trade company's dimension, trade company city ID and knowledge to the latitude and longitude information of 1 customer address of order
Not Chu 1 client's better address of order (take a sea-voyage eastward international young city (Tianyuan Road) (7 1 rooms unit * * * *)) carry out position
Match, specific matching process is as follows:
Analyzing sub-module 50311 parses better address；Keyword extraction submodule 50312 extracts keyword:
(1) it takes a sea-voyage eastward international young city and (2) Tianyuan Road；Location name determines that submodule 50313 determines that POI name is the world of taking a sea-voyage eastward
Young city；Location matches module 5032 inquires POI name (i.e. within the scope of trade company longitude and latitude 3km according to trade company city ID respectively
Take a sea-voyage eastward international young city) corresponding longitude and latitude, 5km range is extended to if it can not find out, available 1 customer address of order
POI name (international young city of taking a sea-voyage eastward) longitude and latitude: 118.838987,31.931969.
Then, better address determination unit 506 determines that better address is (Tianyuan Road) (7 1 rooms unit * * * *), dispatching
Information generating unit 504 is generated according to 1 client personal information of order, its address POI name and its longitude and latitude and better address
Distribution information is sent to third party by distribution information, is dispensed convenient for subsequent for 1 client of order.
Figure 10 is the schematic diagram of the electronic equipment of the embodiment of the present invention.Electronic equipment shown in Fig. 10 is general data processing
Device comprising general computer hardware structure includes at least processor 1001 and memory 1002.1001 He of processor
Memory 1002 is connected by bus 1003.Memory 1002 is suitable for one or more instruction that storage processor 1001 can be performed
Or program.One or more instruction or program are executed by processor 1001 to realize following steps:
Obtain recipient's image information of the picture format from sender；
Text region is carried out to recipient's image information, to obtain recipient's text information of text formatting, recipient's text
This information includes: recipient's personal information and recipient address；
Location matches are carried out to recipient address according to the location information of sender, to obtain the position letter of recipient address
Breath；
Distribution information is generated according to the location information of recipient's personal information and recipient address, in order to be dispensed.
The location information of above-mentioned sender carries out location matches to recipient address to obtain the position of recipient address and believe
Breath includes: to be parsed according to pre-defined rule to recipient address, to obtain the location name of recipient address；Sending orientation
Location matches are carried out to the location name of recipient address in the preset range of confidence breath；With determining recipient according to matching result
The location information of location.
Above-mentioned parsed to recipient address according to pre-defined rule to obtain the location name of recipient address includes: root
Recipient address is parsed according to pre-defined rule；At least one keyword is successively extracted according to parsing result；By what is extracted
First keyword is determined as the location name of recipient address.
After first keyword that will be extracted is determined as the location name of recipient address, above-mentioned steps are also wrapped
It includes: the better address recipient address after first keyword will be extracted be determined as recipient.
Generating distribution information according to the location information of recipient's personal information and recipient address includes: according to recipient
The better address of people's information, the location information of recipient address and recipient generates distribution information.
Preferably, Text region can be carried out by optical character identification (OCR) interface differential technique debit's image information.
Carrying out Text region to recipient's image information includes: to carry out character area cut place to recipient's image information
Reason；Multiple cutting regions after character area cutting process are input to identification model and carry out Text region.
Preferably, identification model can be the connection timing disaggregated model based on convolutional neural networks.
Carrying out character area cutting process to recipient's image information includes: to carry out character area to recipient's image information
Detection；Character area cutting process is carried out to recipient's image information according to testing result.
Carrying out word area detection to recipient's image information includes: by including scene text and example partitioning algorithm
Detection model carries out word area detection to recipient's image information.
Before carrying out character area cutting process to recipient's image information, above-mentioned steps further include: recipient is schemed
As information is pre-processed, pretreatment includes at least one of: binary conversion treatment, denoising, correction inclination processing.
Above-mentioned steps can also include being monitored at least one following operation: know to the text of recipient's image information
It does not operate；Location matches operation to recipient address；Generate the operation of distribution information.
Above-mentioned processor 1001 can be independent microprocessor, be also possible to one or more microprocessor set.
The order that processor 1001 is stored by executing memory 1002 as a result, thereby executing embodiment present invention as described above
Information processing method process realize the processing for data and the control for other devices.Bus 1003 is by above-mentioned multiple groups
Part links together, while said modules are connected to display controller 1004 and display device and input/output (I/O) dress
Set 1005.Input/output (I/O) device 1005 can be mouse, keyboard, modem, network interface, touch-control input dress
It sets, body-sensing input unit, printer and other devices well known in the art.Typically, input/output (I/O) device 1005
It is connected by input/output (I/O) controller 1006 with system.
Wherein, memory 1002 can store component software, such as operating system, communication module, interactive module and answer
Use program.Above-described each module and application program both correspond to complete one or more functions and in inventive embodiments
One group of executable program instructions of the information processing method of description.
In conclusion the embodiment of the present invention mainly solves under the scene that trade company is manually entered distribution information, efficiency of service
And two problems of accuracy of information, it introduces OCR and constructs delivery service scene Recognition model, by trade company's order channel source
(papery receipt & order screenshot) Context resolution obtains the dispatching such as address, contact person's mode core information, removal in trade company's order
Irrelevant information；Simultaneously disassemble and solves according to address information, in Amap system-based, according to it is scheduled extract, match,
Search strategy, it is automatic obtain addressee POI title and its longitude and latitude and better address and, so that it is converted into dispatching waybill,
It is provided to downstream consumption, and for side verification of honouring an agreement.Relative to the distribution information that is manually entered of existing scheme, the embodiment of the present invention is mentioned
The scheme of confession gets rid of the dependence to result is manually entered, and has liberated manpower, while introducing trade company geographical location, dispatching range
The dimensions intelligent Matching latitude and longitude informations such as circle, crucial Word similarity, significantly improve accuracy rate, reduce misclassification rate, and
Two-part independent iteration ability is remained, it is easily scalable.
It is above-mentioned according to the method for the embodiment of the present invention, the flow chart and/or frame of equipment (system) and computer program product
Figure describes various aspects of the invention.It should be understood that each of flowchart and or block diagram piece and flow chart legend and/or frame
The combination of block in figure can be realized by computer program instructions.These computer program instructions can be provided to general meter
The processor of calculation machine, special purpose computer or other programmable data processing devices, to generate machine so that (via computer or
What the processors of other programmable data processing devices executed) instruction creates for realizing in flowchart and or block diagram block or block
The device of specified function action.
Meanwhile as skilled in the art will be aware of, the various aspects of the embodiment of the present invention may be implemented as be
System, method or computer program product.Therefore, the various aspects of the embodiment of the present invention can take following form: complete hardware
Implementation, complete software implementation (including firmware, resident software, microcode etc.) usually can all claim herein
For the implementation for combining software aspects with hardware aspect of circuit, " module " or " system ".In addition, side of the invention
Face can take following form: the computer program product realized in one or more computer-readable medium, computer can
Reading medium has the computer readable program code realized on it.
It can use any combination of one or more computer-readable mediums.Computer-readable medium can be computer
Readable signal medium or computer readable storage medium.Computer readable storage medium can be such as (but not limited to) electronics,
Magnetic, optical, electromagnetism, infrared or semiconductor system, device or any suitable combination above-mentioned.Meter
The more specific example (exhaustive to enumerate) of calculation machine readable storage medium storing program for executing will include the following terms: with one or more electric wire
Electrical connection, hard disk, random access memory (RAM), read-only memory (ROM), erasable is compiled portable computer diskette
Journey read-only memory (EPROM or flash memory), optical fiber, portable optic disk read-only storage (CD-ROM), light storage device,
Magnetic memory apparatus or any suitable combination above-mentioned.In the context of the embodiment of the present invention, computer readable storage medium
It can be that can include or store the program used by instruction execution system, device or combine instruction execution system, set
Any tangible medium for the program that standby or device uses.
Computer-readable signal media may include the data-signal propagated, and the data-signal of the propagation has wherein
The computer readable program code realized such as a part in a base band or as carrier wave.The signal of such propagation can use
Any form in diversified forms, including but not limited to: electromagnetism, optical or its any combination appropriate.It is computer-readable
Signal media can be following any computer-readable medium: not be computer readable storage medium, and can be to by instructing
Program that is that execution system, device use or combining instruction execution system, device to use is communicated, is propagated
Or transmission.
Computer program code for executing the operation for being directed to various aspects of the present invention can be with one or more programming languages
Any combination of speech is write, the programming language include: programming language such as Java, Smalltalk of object-oriented, C++,
PHP, Python etc.；And conventional process programming language such as " C " programming language or similar programming language.Program code can be made
It fully on the user computer, is partly executed on the user computer for independent software package；Partly in subscriber computer
Above and partly execute on the remote computer；Or it fully executes on a remote computer or server.In latter feelings
It, can be by remote computer by including that any type of network connection of local area network (LAN) or wide area network (WAN) are extremely used under condition
Family computer, or (such as internet by using ISP) can be attached with outer computer.
The above description is only a preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For, the invention can have various changes and changes.All any modifications made within the spirit and principles of the present invention are equal
Replacement, improvement etc., should all be included in the protection scope of the present invention.
The embodiment of the invention discloses A1, a kind of information processing method, wherein the described method includes:
Recipient's image information from sender is obtained, recipient's image information is picture format；
Text region is carried out to recipient's image information, to obtain recipient's text information, recipient's text
Information includes: recipient's personal information and recipient address；
Location matches are carried out to the recipient address according to the location information of described sender, to obtain the recipient
The location information of address；
Distribution information is generated according to the location information of recipient's personal information and the recipient address.
A2, the information processing method according to claim A1, wherein according to the location information of described sender to institute
Recipient address progress location matches, which are stated, with the location information for obtaining the recipient address includes:
The recipient address is parsed according to pre-defined rule, to obtain the location name of the recipient address；
Position is carried out to the location name of the recipient address in the preset range of described sender location information
Match；
The location information of the recipient address is determined according to matching result.
A3, the information processing method according to claim A2, wherein according to pre-defined rule to the recipient address
It is parsed to obtain the location name of the recipient address and include:
The recipient address is parsed according to the pre-defined rule；
At least one keyword is successively extracted according to parsing result；
Extract first keyword is determined as to the location name of the recipient address.
A4, the information processing method according to claim A3, wherein be determined as extract first keyword
After the location name of the recipient address, the method also includes:
The address comprising other keywords other than first keyword is determined as the recipient in detail
Location.
A5, the information processing method according to claim A4, wherein according to recipient's personal information and described
The location information of recipient address generates distribution information
In detail according to recipient's personal information, the location information of the recipient address and the recipient
Location generates distribution information.
A6, the information processing method according to claim A1, wherein connect by optical character recognition technology to described
Debit's image information carries out Text region.
A7, the information processing method according to claim A6, wherein text is carried out to recipient's image information
Identification includes:
Character area cutting process is carried out to recipient's image information；
Multiple cutting regions after character area cutting process are input to identification model and carry out Text region.
A8, the information processing method according to claim A7, wherein the identification model is based on convolutional Neural net
The connection timing disaggregated model of network.
A9, the information processing method according to claim A7, wherein text is carried out to recipient's image information
Region cutting process includes:
Word area detection is carried out to recipient's image information；
Character area cutting process is carried out to recipient's image information according to testing result.
A10, the information processing method according to claim A9, wherein text is carried out to recipient's image information
Word region detection includes:
Text is carried out to recipient's image information by the detection model for including scene text and example partitioning algorithm
Region detection.
A11, the information processing method according to claim A7, wherein carried out to recipient's image information
Before character area cutting process, the method also includes:
Recipient's image information is pre-processed, the pretreatment includes at least one of: binary conversion treatment,
Denoising, correction inclination processing.
A12, the information processing method according to claim A1, wherein the method also includes: to following at least one
A operation is monitored:
Text region operation to recipient's image information；
Location matches operation to the recipient address；
Generate the operation of distribution information.
The embodiment of the invention discloses B1, a kind of information processing unit, wherein described device includes:
Image acquisition unit, for obtaining recipient's image information from sender, recipient's image information is
Picture format；
Word recognition unit, for carrying out Text region to recipient's image information, to obtain recipient's text envelope
Breath, recipient's text information includes: recipient's personal information and recipient address；
Location matches unit, for carrying out position to the recipient address according to the location information of described sender
Match, to obtain the location information of the recipient address；
Distribution information generation unit, for the location information according to recipient's personal information and the recipient address
Generate distribution information.
The embodiment of the invention discloses C1, a kind of computer readable storage medium, store computer program instructions thereon,
In, the computer program instructions realize the method as described in any one of claim A1-A12 when being executed by processor.
The embodiment of the invention discloses D1, a kind of electronic equipment, including memory and processor, wherein the memory
For storing one or more computer program instructions, wherein one or more computer program instructions are by the processing
Device is executed to realize following steps:
Recipient's image information from sender is obtained, recipient's image information is picture format；
Text region is carried out to recipient's image information, to obtain recipient's text information, recipient's text
Information includes: recipient's personal information and recipient address；
Location matches are carried out to the recipient address according to the location information of described sender, to obtain the recipient
The location information of address；
Distribution information is generated according to the location information of recipient's personal information and the recipient address.
D2, the electronic equipment according to claim D1, wherein connect according to the location information of described sender to described
Debit address carries out location matches with the location information for obtaining the recipient address
The recipient address is parsed according to pre-defined rule, to obtain the location name of the recipient address；
Position is carried out to the location name of the recipient address in the preset range of described sender location information
Match；
The location information of the recipient address is determined according to matching result.
D3, the electronic equipment according to claim D2, wherein the recipient address is carried out according to pre-defined rule
It parses with the location name for obtaining the recipient address and includes:
The recipient address is parsed according to the pre-defined rule；
At least one keyword is successively extracted according to parsing result；
Extract first keyword is determined as to the location name of the recipient address.
D4, the electronic equipment according to claim D3, wherein be determined as extract first keyword described
After the location name of recipient address, the step further include:
The address comprising other keywords other than first keyword is determined as the recipient in detail
Location.
D5, the electronic equipment according to claim D4, wherein according to recipient's personal information and the reception
The location information of square address generates distribution information
In detail according to recipient's personal information, the location information of the recipient address and the recipient
Location generates distribution information.
D6, the electronic equipment according to claim D1, wherein by optical character recognition technology to the recipient
Image information carries out Text region.
D7, the electronic equipment according to claim D6, wherein Text region is carried out to recipient's image information
Include:
Character area cutting process is carried out to recipient's image information；
Multiple cutting regions after character area cutting process are input to identification model and carry out Text region.
D8, the electronic equipment according to claim D7, wherein the identification model is based on convolutional neural networks
Connect timing disaggregated model.
D9, the electronic equipment according to claim D7, wherein character area is carried out to recipient's image information
Cutting process includes:
Word area detection is carried out to recipient's image information；
Character area cutting process is carried out to recipient's image information according to testing result.
D10, the electronic equipment according to claim D9, wherein literal field is carried out to recipient's image information
It detects in domain
Text is carried out to recipient's image information by the detection model for including scene text and example partitioning algorithm
Region detection.
D11, the electronic equipment according to claim D7, wherein text is being carried out to recipient's image information
Before the cutting process of region, the step further include:
Recipient's image information is pre-processed, the pretreatment includes at least one of: binary conversion treatment,
Denoising, correction inclination processing.
D12, the electronic equipment according to claim D1, wherein the step further include: at least one following behaviour
It is monitored:
Text region operation to recipient's image information；
Location matches operation to the recipient address；
Generate the operation of distribution information.
Claims (10)
1. a kind of information processing method, which is characterized in that the described method includes:
Recipient's image information from sender is obtained, recipient's image information is picture format；
Text region is carried out to recipient's image information, to obtain recipient's text information, recipient's text information
It include: recipient's personal information and recipient address；
Location matches are carried out to the recipient address according to the location information of described sender, to obtain the recipient address
Location information；
Distribution information is generated according to the location information of recipient's personal information and the recipient address.
2. information processing method according to claim 1, which is characterized in that according to the location information of described sender to institute
Recipient address progress location matches, which are stated, with the location information for obtaining the recipient address includes:
The recipient address is parsed according to pre-defined rule, to obtain the location name of the recipient address；
Location matches are carried out to the location name of the recipient address in the preset range of described sender location information；
The location information of the recipient address is determined according to matching result.
3. information processing method according to claim 2, which is characterized in that according to pre-defined rule to the recipient address
It is parsed to obtain the location name of the recipient address and include:
The recipient address is parsed according to the pre-defined rule；
At least one keyword is successively extracted according to parsing result；
Extract first keyword is determined as to the location name of the recipient address.
4. information processing method according to claim 3, which is characterized in that extract first keyword to be determined as
After the location name of the recipient address, the method also includes:
The address comprising other keywords other than first keyword is determined as to the better address of the recipient.
5. information processing method according to claim 4, which is characterized in that according to recipient's personal information and described
The location information of recipient address generates distribution information
It is raw according to the better address of recipient's personal information, the location information of the recipient address and the recipient
At distribution information.
6. information processing method according to claim 1, which is characterized in that connect by optical character recognition technology to described
Debit's image information carries out Text region.
7. information processing method according to claim 6, which is characterized in that carry out text to recipient's image information
Identification includes:
Character area cutting process is carried out to recipient's image information；
Multiple cutting regions after character area cutting process are input to identification model and carry out Text region.
8. a kind of information processing unit, which is characterized in that described device includes:
Image acquisition unit, for obtaining recipient's image information from sender, recipient's image information is image
Format；
Word recognition unit, for carrying out Text region to recipient's image information, to obtain recipient's text information, institute
Stating recipient's text information includes: recipient's personal information and recipient address；
Location matches unit, for carrying out location matches to the recipient address according to the location information of described sender, with
Obtain the location information of the recipient address；
Distribution information generation unit, for being generated according to the location information of recipient's personal information and the recipient address
Distribution information.
9. a kind of computer readable storage medium, stores computer program instructions thereon, which is characterized in that the computer program
Such as method of any of claims 1-7 is realized in instruction when being executed by processor.
10. a kind of electronic equipment, including memory and processor, which is characterized in that the memory is for storing one or more
Computer program instructions, wherein one or more computer program instructions are executed by the processor to realize such as power
Benefit requires method described in any one of 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811475919.0A CN109598238A (en) | 2018-12-04 | 2018-12-04 | Information processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811475919.0A CN109598238A (en) | 2018-12-04 | 2018-12-04 | Information processing method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598238A true CN109598238A (en) | 2019-04-09 |
Family
ID=65962091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811475919.0A Pending CN109598238A (en) | 2018-12-04 | 2018-12-04 | Information processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598238A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458499A (en) * | 2019-08-14 | 2019-11-15 | 北京顺丰同城科技有限公司 | A kind of express delivery order generation method, device, electronic equipment and storage medium |
| CN110490232A (en) * | 2019-07-18 | 2019-11-22 | 北京捷通华声科技股份有限公司 | Method, apparatus, the equipment, medium of training literal line direction prediction model |
| CN110543812A (en) * | 2019-07-19 | 2019-12-06 | 拉扎斯网络科技（上海）有限公司 | information extraction method and device, electronic equipment and storage medium |
| CN110991446A (en) * | 2019-11-22 | 2020-04-10 | 上海欧冶物流股份有限公司 | Label identification method, device, equipment and computer readable storage medium |
| CN111899855A (en) * | 2020-07-16 | 2020-11-06 | 武汉大学 | Individual health and public health data space-time aggregation visualization construction method and platform |
| CN112633283A (en) * | 2021-03-08 | 2021-04-09 | 广州市玄武无线科技股份有限公司 | Method and system for identifying and translating English mail address |
| CN112862387A (en) * | 2020-11-12 | 2021-05-28 | 北京京东乾石科技有限公司 | Logistics distribution vehicle stop point setting method, device, system, equipment and medium |
| CN113537418A (en) * | 2020-04-14 | 2021-10-22 | 天津科技大学 | Identification system for handwritten Chinese characters |
| US11379441B1 (en) * | 2021-12-17 | 2022-07-05 | Capped Out Media | System and methods for self-input information validation and correction |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484790A (en) * | 2014-12-26 | 2015-04-01 | 清华大学深圳研究生院 | Address match method and device of logistics business |
| CN108204816A (en) * | 2016-12-20 | 2018-06-26 | 北京四维图新科技股份有限公司 | Address process of refinement method and device, logistics navigation system and the terminal of location navigation |
-
2018
- 2018-12-04 CN CN201811475919.0A patent/CN109598238A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484790A (en) * | 2014-12-26 | 2015-04-01 | 清华大学深圳研究生院 | Address match method and device of logistics business |
| CN108204816A (en) * | 2016-12-20 | 2018-06-26 | 北京四维图新科技股份有限公司 | Address process of refinement method and device, logistics navigation system and the terminal of location navigation |
Non-Patent Citations (4)
| Title |
|---|
| ABDUL KALEEM等: "Address Standardization Using Supervised Machine Learning", 《INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND MANAGEMENT》 * |
| 方清: "基于深度学习的自然场景文本检测与识别", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 王勇等: "顾及位置关系的网络POI地址信息标准化处理方法", 《测绘学报》 * |
| 胡提坤: "基于OCR快递单据识别的研究与实现", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490232A (en) * | 2019-07-18 | 2019-11-22 | 北京捷通华声科技股份有限公司 | Method, apparatus, the equipment, medium of training literal line direction prediction model |
| CN110543812A (en) * | 2019-07-19 | 2019-12-06 | 拉扎斯网络科技（上海）有限公司 | information extraction method and device, electronic equipment and storage medium |
| CN110458499A (en) * | 2019-08-14 | 2019-11-15 | 北京顺丰同城科技有限公司 | A kind of express delivery order generation method, device, electronic equipment and storage medium |
| CN110991446A (en) * | 2019-11-22 | 2020-04-10 | 上海欧冶物流股份有限公司 | Label identification method, device, equipment and computer readable storage medium |
| CN113537418A (en) * | 2020-04-14 | 2021-10-22 | 天津科技大学 | Identification system for handwritten Chinese characters |
| CN111899855A (en) * | 2020-07-16 | 2020-11-06 | 武汉大学 | Individual health and public health data space-time aggregation visualization construction method and platform |
| CN111899855B (en) * | 2020-07-16 | 2024-04-26 | 武汉大学 | Method and platform for constructing individual health and public health data space-time aggregation visualization |
| CN112862387A (en) * | 2020-11-12 | 2021-05-28 | 北京京东乾石科技有限公司 | Logistics distribution vehicle stop point setting method, device, system, equipment and medium |
| CN112633283A (en) * | 2021-03-08 | 2021-04-09 | 广州市玄武无线科技股份有限公司 | Method and system for identifying and translating English mail address |
| US11379441B1 (en) * | 2021-12-17 | 2022-07-05 | Capped Out Media | System and methods for self-input information validation and correction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598238A (en) | Information processing method and device, storage medium and electronic equipment | |
| US11238310B2 (en) | Training data acquisition method and device, server and storage medium | |
| KR101462289B1 (en) | Digital image archiving and retrieval using a mobile device system | |
| CN110674255B (en) | Text content auditing method and device | |
| US20210286835A1 (en) | Method and device for matching semantic text data with a tag, and computer-readable storage medium having stored instructions | |
| CN107657056A (en) | Method and apparatus based on artificial intelligence displaying comment information | |
| CN110334640A (en) | A kind of ticket processing method and system | |
| CN109697291A (en) | The semantic paragraph recognition methods of text and device | |
| CN106296195A (en) | A kind of Risk Identification Method and device | |
| CN109598517B (en) | Commodity clearance processing, object processing and category prediction method and device thereof | |
| CN111126514A (en) | Image multi-label classification method, device, equipment and medium | |
| CN109299399B (en) | Learning content recommendation method and terminal equipment | |
| CN107967250B (en) | Information processing method and device | |
| CN109582788A (en) | Comment spam training, recognition methods, device, equipment and readable storage medium storing program for executing | |
| CN110390110B (en) | Method and apparatus for pre-training generation of sentence vectors for semantic matching | |
| CN110348346A (en) | A kind of bill classification recognition methods and system | |
| Maiti et al. | Capturing, eliciting, and prioritizing (CEP) NFRs in agile software engineering | |
| CN112364216A (en) | Edge node content auditing and filtering system and method | |
| CN107766498A (en) | Method and apparatus for generating information | |
| CN114240796A (en) | Remote sensing image cloud and fog removing method and device based on GAN and storage medium | |
| CN104077288B (en) | Web page contents recommend method and web page contents recommendation apparatus | |
| CN114338586A (en) | Message pushing method and device, electronic equipment and storage medium | |
| KR101169444B1 (en) | 2 dimension code searching and storing device | |
| CN111597805B (en) | Method and device for auditing short message text links based on deep learning | |
| CN112905787B (en) | Text information processing method, short message processing method, electronic device and readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |
|
| RJ01 | Rejection of invention patent application after publication |