CN108509441A - Training of address validity classifier, verification method thereof and related device - Google Patents
Training of address validity classifier, verification method thereof and related device Download PDFInfo
- Publication number
- CN108509441A CN108509441A CN201710103991.XA CN201710103991A CN108509441A CN 108509441 A CN108509441 A CN 108509441A CN 201710103991 A CN201710103991 A CN 201710103991A CN 108509441 A CN108509441 A CN 108509441A
- Authority
- CN
- China
- Prior art keywords
- address
- information
- address information
- validity
- characteristic information
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a training method and a verification method of an address validity classifier and a related device thereof, wherein the training method of the address validity classifier comprises the following steps: acquiring address information; generating address characteristic information according to the address information; labeling a validity label on the address information; and taking the address characteristic information and the validity label as a training sample and a training address validity classifier. The embodiment of the application is based on the classification idea, the address information is classified by the address valid classifier, the validity of the address information is recognized, the valid address information and the invalid address information are distinguished, the automatic verification of the validity of the address information is realized, the manual intervention operation is greatly reduced, the verification efficiency and accuracy are improved, the cost is reduced, and the implementation in the environments such as a mass transaction platform is ensured.
Description
Technical field
This application involves the technical fields of computer disposal, more particularly to a kind of training side of address validity grader
Method, a kind of training device of address validity grader, a kind of verification method of address validity, a kind of address validity are tested
Card device, a kind of device and one or more computer-readable mediums.
Background technology
With the rapid development of Internet, more and more consumers are traded in the network platform, for example, being purchased in network
Object platform is done shopping.
Some malice buyer fills in abnormal address information and phone when lower single, and seller can not normally deliver, alternatively,
Since address information or phone lead to not send with charge free extremely, signs for after delivery, the regular loophole of the network platform is then utilized
It is complained and is extorted, cause to sell family property loss, not just postage, the inventory of cargo may also can be reduced for this loss.
Certainly, there are also normal buyers to lack the accurate understanding to address, fills in the address information of mistake, this
Loss can be brought to seller.
Currently, for exception, the address information of mistake, seller is substantially leaned on to find, logistics company is fed back and operation
Personnel's screening etc., the method for this manual intervention verify, not only verification efficiency is low, but also is easy error, in magnanimity
The cost implemented in the environment such as the platform of transaction is very big, leads to not bear.
Invention content
In view of the above problems, it is proposed that the embodiment of the present application overcoming the above problem or at least partly in order to provide one kind
A kind of training method of the address validity grader to solve the above problems, a kind of training device of address validity grader,
A kind of verification method of address validity, a kind of verification device of address validity, a kind of device and one or more computers
Readable medium.
The embodiment of the present application provides a kind of training method of address validity grader, including：
Obtain address information；
Address characteristic information is generated according to described address information；
To described address information labeling validity label；
Using described address characteristic information and the validity label as training sample, train address validity grader.
The embodiment of the present application provides a kind of verification method of address validity, including：
Order data is received, there is address information in the order data；
Address characteristic information is generated according to described address information；
Described address characteristic information is inputted to preset address validity grader, to identify the effective of described address information
Property.
The embodiment of the present application provides a kind of training device of address validity grader, including：
Address information acquisition module, for obtaining address information；
Address characteristic information generation module, for generating address characteristic information according to described address information；
Validity label for labelling module, for described address information labeling validity label；
Classifier training module is used for using described address characteristic information and the validity label as training sample, instructs
Practice address validity grader.
The embodiment of the present application provides a kind of verification device of address validity, including：
Order data receiving module has address information for receiving order data in the order data；
Address characteristic information generation module, for generating address characteristic information according to described address information；
Validity identification module, for described address characteristic information to be inputted to preset address validity grader, to know
The validity of other described address information.
The embodiment of the present application provides a kind of device, including：
One or more processors；With
Instruction in the one or more computer-readable mediums stored thereon, is executed by one or more of processors
When, cause described device to execute such as above-mentioned method.
The embodiment of the present application provides one or more computer-readable mediums, is stored thereon with instruction, when by one or
When multiple processors execute so that terminal device executes above-mentioned method.
The embodiment of the present application provides a kind of device, including：
One or more processors；With
Instruction in the one or more computer-readable mediums stored thereon, is executed by one or more of processors
When, cause described device to execute above-mentioned method.
The embodiment of the present application provides one or more computer-readable mediums, is stored thereon with instruction, when by one or
When multiple processors execute so that terminal device executes above-mentioned method.
The embodiment of the present application includes the following advantages：
The embodiment of the present application extracts address information from order data and generates address characteristic information with this, in addition, over the ground
Location information labeling validity label is divided using address characteristic information and validity label as training sample, training address validity
Class device, the thought based on classification classify to address information by the effective grader in the address, identify its validity, distinguish
Effective address information, invalid address information, realize the automatic verification of address information validity, greatly reduce artificial dry
Pre- operation reduces cost, ensure that the environment such as the platform merchandised in magnanimity to improve efficiency, the accuracy rate of verification
Middle execution.
The embodiment of the present application generates address characteristic information to the address information in order data, and inputs preset address and have
Effect property grader, to identify the validity of address information, the thought based on classification believes address by the effective grader in the address
Breath is classified, and is identified its validity, is distinguished effective address information, invalid address information, it is effective to realize address information
The automatic verification of property, greatly reduces the operation of manual intervention, to improve efficiency, the accuracy rate of verification, reduces cost,
It ensure that and implemented in the environment such as the platform that magnanimity is merchandised.
Description of the drawings
Fig. 1 is a kind of step flow chart of the training method of address validity grader of the application one embodiment；
Fig. 2 is a kind of step flow chart of the verification method of address validity of the application one embodiment；
Fig. 3 is a kind of training of address validity grader of the application one embodiment and its exemplary flow of verification method
Cheng Tu；
Fig. 4 is a kind of structure diagram of the training device of address validity grader of the application one embodiment；
Fig. 5 is a kind of structure diagram of the verification device of address validity of the application one embodiment；
Fig. 6 schematically shows the exemplary system that can be used for realizing each embodiment described in the disclosure.
Specific implementation mode
In order to make the above objects, features, and advantages of the present application more apparent, below in conjunction with the accompanying drawings and it is specific real
Applying mode, the present application will be further described in detail.
Referring to Fig.1, the step of showing a kind of training method of address validity grader of the application one embodiment
Flow chart can specifically include following steps：
Step 101, address information is obtained.
In the concrete realization, the embodiment of the present application can be applied in address server, which can store
There is address information.
It is independent server or server cluster using transaction platform as address server example, essence,
For example, distributed system.
It should be noted that the transaction platform, can be third-party platform, i.e. the transaction independently of buyer, seller is flat
Platform, or directly-managed platform, i.e. platform side are used as seller, can also introduce independent seller in directly-managed platform, alternatively,
As seller, etc. in third-party platform, the embodiment of the present application does not limit this.
In transaction platform, one or more sellers can provide cargo data in the transaction platform, for example, clothes,
Furniture and other items, raw and fresh foods such as fruit, crab, etc., buyer can browse cargo data in the transaction platform, in cash, purchase
The actual cargo of the forms such as object certificate, Gift Card transaction.
The behavior of this transaction cargo can be referred to as order, and the relevant data of this order can be referred to as order data,
For example, buyer ID, seller ID, cargo ID, cargo parameter (such as quantity, price), address information, exchange hour, transaction amount,
Buyer's message, etc..
In order data, buyer can be with fill address information (also known as dispensing address, ship-to), i.e., actual cargo
Transport destination, seller can by actual cargo by the logistics modes such as express delivery, ordinary mail, shipping be sent to the address letter
Breath, buyer sign for actual cargo in the address information, and this time transaction is completed.
In the embodiment of the present application, transaction platform has carried out a large amount of transaction, produces a large amount of order data, wherein wrapping
Include numerous address informations.
These address informations may be normal, such as：
Hangzhou, Zhejiang province city Yuhang District text one West Road 969 Arriba Brazil small stream garden
But these address informations may have following one or more exceptions：
1, imperfect, such as：
City of Taizhou Linhai City ocean street
Taizhou of Zhejiang borders on the sea ocean street
Zhongshan City, Guangdong Province 4453
Hainan Province Sanya Dongdaemun 29
2, it is not present or not unique, such as：
20,4th areas Hangzhou, Zhejiang province city Yuhang District Cui Yuan, 3 units 401
Xihu District China Mobile of Hangzhou, Zhejiang province city business hall
3, there is junk information, such as：
(wherein, * * * are hiding number to the Changsha, Hunan Furong District literature and art road street palaces Nan Yuan lane button button 2941346***
Word)
Shanghai Minhang District, Shanghai Sapporo town Poly building phone contact
Dead No. 38 of Beijing Dongcheng District, Beijing during March Jingshan mountain street streets grass storekeeper Ni Ma
If address information is normal, actual cargo can normally send the address of address information characterization, the i.e. ground with charge free
Location information is effective address information.
If address information is abnormal, actual cargo possibly can not send the address of address information breath characterization with charge free, i.e., should
Address information is invalid address information.
Step 102, address characteristic information is generated according to described address information.
In the embodiment of the present application, the information that the address information feature of withdrawing deposit can be generated, as address characteristic information.
In one embodiment of the application, step 102 may include following sub-step：
Described address information MAP is address elements at different levels by sub-step S1021.
Described address element is converted to address characteristic information by sub-step S1022.
In the embodiment of the present application, word segmentation processing can be carried out to address information, obtains address participle, address participle is reflected
It is mapped to province, city, area/county, street (small towns), community (villagers' committee), road, number, Zi Lu, sub- road number, POI (Point of
Interest, information point) etc. address elements.
If address information has the address element of some rank, first identifier can be converted to, for example, 1.
If address information does not have the address element of some rank, second identifier can be converted to, for example, 0.
In another embodiment of the application, address information includes the address information in order data, then implements herein
In example, step 102 may include following sub-step：
Sub-step S1023 counts the corresponding trading activity data of described address information from the order data.
Sub-step S1024 sets the trading activity data to address characteristic information.
In the embodiment of the present application, it can be directed in one or more order datas with the same address information, system
The trading activity data in a period of time are counted, and are set as address characteristic information.
In the concrete realization, trading activity data may include following one or more：
The successful number of order number, order transaction, order transaction failure number, address information sign for successfully time
The number for signing for failure of number, address information.
It should be noted that because certain orders do not reach specified state also in the period of statistics, order number is not
Certain the sum of number equal to the successful number of order transaction and order transaction failure；Because logistics platform flows back, data are imperfect
Or having delay, the successful number of signing for of address information also needs not be equal to the successful number of order transaction；Because order is handed over
Easily unsuccessfully have a many factors, such as user cancels an order etc., the number for signing for failure of address information also needs not be equal to
The number of order transaction failure.
Certainly, above-mentioned trading activity data are intended only as example, can be according to practical feelings when implementing the embodiment of the present application
Other trading activity data are arranged in condition, and the embodiment of the present application does not limit this.In addition, in addition to above-mentioned trading activity data
Outside, those skilled in the art can also use other trading activity data according to actual needs, the embodiment of the present application to this not yet
It limits.
In another embodiment of the application, step 102 may include following sub-step：
Sub-step S1025 extracts extended address information from described address information.
Sub-step S1026 sets the extended address information to address characteristic information.
In the embodiment of the present application, the other information of address information can be excavated from the dimension in addition to administrative region, made
For extended address information, and it is set as address characteristic information.
In the concrete realization, extended address information may include following one or more：
1, the richness of address information
In this extended address information, weight can be configured to administrative regions at different levels, calculating has in address information
The sum of the weight of administrative region, obtain the richness of address information.
2, the text size of the address element of specified level
In this extended address information, street (small towns), community (villagers' committee), road, number, Zi Lu, son can be counted
The text size of the address elements such as Lu Hao, POI administrative region, as address characteristic information.
3, town and country information
In area/county, the other address element of street (small towns) grade, the town and country information of the address information can be identified (i.e.
City or rural area).
If the address information belongs to city, town and country information can be set to third mark, for example, 1.
If the address information belongs to rural area, town and country information can be set to the 4th mark, for example, 0.
Certainly, above-mentioned extended address information is intended only as example, can be according to practical feelings when implementing the embodiment of the present application
Other extended address information are arranged in condition, and the embodiment of the present application does not limit this.In addition, in addition to above-mentioned extended address information
Outside, those skilled in the art can also use other extended address information according to actual needs, the embodiment of the present application to this not yet
It limits.
Step 103, to described address information labeling validity label.
In the embodiment of the present application, can to address information standard validity label, that is, indicate effective label (for example,
1) invalid label (for example, 0), is indicated.
In one embodiment of the application, step 103 may include following sub-step：
Sub-step S1031, inquiry mark rule.
Sub-step S1032, when the address element of described address information and administrative address template matches success, to institute
It states address information and marks the corresponding validity label of the administrative address template.
In the embodiment of the present application, mark rule can be pre-set, which has comprising one or more
The administrative address template and validity label of address element, i.e. the administrative address template may be effective administrative address template,
It is also likely to be invalid administrative address template.
The address element of address information is matched with the administrative address template, it, can be to this if the two matches
Address information marks the corresponding validity label of the administrative address template.
In order to improve the accuracy of validity label for labelling, the address information of validity label can be marked with extraction section,
Carry out desk checking.
Certainly, the notation methods of above-mentioned validity label are intended only as example, when implementing the embodiment of the present application, Ke Yigen
The notation methods of other validity labels are set according to actual conditions, for example, being marked to address information feedack according to seller
Validity label marks validity label, etc., the embodiment of the present application pair according to logistics platform to address information feedack
This is not limited.In addition, other than the notation methods of above-mentioned validity label, those skilled in the art can also be according to reality
It needs also not limit this using the notation methods of other validity labels, the embodiment of the present application.
Step 104, using described address characteristic information and the validity label as training sample, training address validity
Grader.
In the concrete realization, if generating address characteristic information based on address information, and to address information labeling validity
Label, then can using address characteristic information and validity label as training sample, by the way of machine learning, for example, LR
(Logistic Regression, Logic Regression Models), random forest etc. train optimal address to have by parameter adjustment
Effect property grader verifies its validity (i.e. effectively, invalid) for classifying to address information.
The embodiment of the present application extracts address information from order data and generates address characteristic information with this, in addition, over the ground
Location information labeling validity label is divided using address characteristic information and validity label as training sample, training address validity
Class device, the thought based on classification classify to address information by the effective grader in the address, identify its validity, distinguish
Effective address information, invalid address information, realize the automatic verification of address information validity, greatly reduce artificial dry
Pre- operation reduces cost, ensure that the environment such as the platform merchandised in magnanimity to improve efficiency, the accuracy rate of verification
Middle execution.
With reference to Fig. 2, a kind of step flow chart of the verification method of address validity of the application one embodiment is shown,
It can specifically include following steps：
Step 201, order data is received.
In the concrete realization, the embodiment of the present application can be applied to transaction platform, and essence is independent server or clothes
Business device cluster, for example, distributed system.
In transaction platform, if buyer and seller's transaction cargo, can generate order, and configure order data.
In the embodiment of the present application, there is address information in order data.
Step 202, address characteristic information is generated according to described address information.
In one embodiment of the application, step 202 may include following sub-step：
Described address information MAP is address elements at different levels by sub-step S2021.
Described address element is converted to address characteristic information by sub-step S2022.
In another embodiment of the application, step 202 may include following sub-step：
Sub-step S2023 counts the corresponding trading activity data of described address information from order data.
Sub-step S2024 sets the trading activity data to address characteristic information.
In another embodiment of the application, step 202 may include following sub-step：
Sub-step S2025 extracts extended address information from described address information.
Sub-step S2026 sets the extended address information to address characteristic information.
In the embodiment of the present application, due to step 202 (including sub-step S2021- sub-step S2026) and step 102 (packet
Enclosed tool step S1021- sub-step S1026) application it is substantially similar, so description is fairly simple, related place is referring to step
The part of 102 (including sub-step S1021- sub-step S1026) illustrates that the embodiment of the present application is not described in detail herein.
Step 203, described address characteristic information is inputted to preset address validity grader, to identify that described address is believed
The validity of breath.
It in the concrete realization, can be by the address characteristic information if generating address characteristic information based on address information
Input address validity grader, classifies to the address information, verifies its validity (i.e. effectively, invalid).
If it is effective to verify the address information, order can be continued with.
If it is invalid to verify the address information, alert process can be carried out, for example, the technology people of prompt transaction platform
Member, prompt seller, prompt buyer, etc..
In one embodiment of the application, address validity grader can generate in the following way：
Sub-step S2031 obtains address information；
Sub-step S2032 generates address characteristic information according to described address information；
Sub-step S2033, to described address information labeling validity label；
Sub-step S2034 has using described address characteristic information and the validity label as training sample, training address
Effect property grader.
In the embodiment of the present application, due to the application base of sub-step S2031- sub-steps S2034 and step 101- steps 104
This is similar, so description is fairly simple, related place illustrates that the application is real referring to the part of step 101- steps 104
Example is applied not to be described in detail herein.
The embodiment of the present application generates address characteristic information to the address information in order data, and inputs preset address and have
Effect property grader, to identify the validity of address information, the thought based on classification believes address by the effective grader in the address
Breath is classified, and is identified its validity, is distinguished effective address information, invalid address information, it is effective to realize address information
The automatic verification of property, greatly reduces the operation of manual intervention, to improve efficiency, the accuracy rate of verification, reduces cost,
It ensure that and implemented in the environment such as the platform that magnanimity is merchandised.
To make those skilled in the art more fully understand the embodiment of the present application, referring to Fig. 3, come below by way of specific example
Illustrate the training of address validity grader and its verification method in the embodiment of the present application.
Step 301, address information is extracted in the order data of transaction platform history, and it is corresponding to count the address information
Trading activity data.
In this example, the address information of extraction is as shown in table 1：
Table 1
| Serial number | Address information |
| 1 | Hangzhou, Zhejiang province city Yuhang District text one West Road 969 Arriba Brazil small stream garden |
| 2 | Hangzhou, Zhejiang province city Yuhang District |
For the address information of table 1, the trading activity data of statistics are as shown in table 2：
Table 2
| Serial number | 1 | 2 |
| Order number | 100234 | 109 |
| The successful number of order transaction | 90854 | 1 |
| The number of order transaction failure | 2859 | 98 |
| Address information signs for successful number | 78439 | 0 |
| The number for signing for failure of address information | 2 | 86 |
Step 302, extended address information is extracted from address information.
For the address information of table 1, the address element being mapped to is as shown in table 3
Table 3
| Serial number | 1 | 2 |
| It saves | Zhejiang Province | Zhejiang Province |
| City | Hangzhou | Hangzhou |
| Area/county | Yuhang District | Yuhang District |
| Street (small towns) | / | / |
| Community (villagers' committee) | / | / |
| Road | A literary West Road | / |
| Number | No. 969 | / |
| Sub- road | / | / |
| Sub- road number | / | / |
| POI | Arriba Brazil small stream garden | / |
For the address information of table 1, the extended address information of extraction is as shown in table 4：
Table 4
| Serial number | 1 | 2 |
| The richness of address information | 921 | 896 |
| The text size of the address element of specified level | 16 | 0 |
| Town and country information | 1 | 1 |
Wherein, to province, city, area/county, street (small towns), community (villagers' committee), road, number, Zi Lu, sub- road number, POI
Configure corresponding weight.
The address element of specified level be street (small towns), community (villagers' committee), road, number, Zi Lu, sub- road number,
POI。
In the information of town and country, 1 indicates city, and 0 indicates rural area.
Step 303, address information, trading activity data and extended address information are subjected to discretization, obtain address feature
Information.
Wherein, if address information has province, city, area/county, street (small towns), community (villagers' committee), road, number, son
Road, sub- road number, the other address element of POI grades, then be set as 1, otherwise, be set as 0.
The address characteristic information of discretization be province, city, area/county, street (small towns), community (villagers' committee), road, number,
Zi Lu, sub- road number, POI, the richness of address information, the text size of the address element of specified level, town and country information, order
Number, the number of the successful number of order transaction, order transaction failure, address information sign for successful number, address information
Sign for the number of failure.
For the address information of table 1, the address characteristic information of discretization is as shown in table 5：
Table 5
| Serial number | Address information |
| 1 | 1 1 1 0 0 1 1 0 0 1 921 16 1 100234 90854 2859 78439 2 |
| 2 | 1 1 1 0 0 0 0 0 0 0 896 0 1 109 1 98 0 86 |
Step 304, by marking rule to address information labeling validity label.
Mark rule is as follows：
city,roadNo 0
city,devZone,roadNo 0
city,roadNo,poi 0
city,devZone,roadNo,poi 1
city,roadNo,subRoadNo 0
city,devZone,roadNo,subRoadNo 1
city,roadNo,subRoadNo,poi 0
city,devZone,roadNo,subRoadNo,poi 1
city,roadNo,subRoad 0
city,devZone,roadNo,subRoad 1
city,roadNo,subRoad,poi 0
city,devZone,roadNo,subRoad,poi 1
city,roadNo,subRoad,subRoadNo 0
city,devZone,roadNo,subRoad,subRoadNo 1
city,roadNo,subRoad,subRoadNo,poi 1
city,devZone,roadNo,subRoad,subRoadNo,poi 1
city,road 0
city,devZone,road 1
city,road,poi 0
city,devZone,road,poi 1
city,road,subRoadNo 0
city,devZone,road,subRoadNo 1
city,road,subRoadNo,poi 0
city,devZone,road,subRoadNo,poi 1
city,road,subRoad 1
city,devZone,road,subRoad 1
city,road,subRoad,poi 0
city,devZone,road,subRoad,poi 1
city,road,subRoad,subRoadNo 1
city,devZone,road,subRoad,subRoadNo 1
city,road,subRoad,subRoadNo,poi 1
city,devZone,road,subRoad,subRoadNo,poi 1
Wherein, 0 expression validity label is invalid, and 1 expression validity label is effective, and the Chinese and English of each label is right
According to：Save (province), city (city), area/county (district), street/small towns (town), community/villagers' committee
(community), road (road), number (roadNo), sub- road (subRoad), sub- road number (subRoadNo), POI (poi).
For the address information of table 1, " Hangzhou, Zhejiang province city Yuhang District text one West Road 969 Arriba Brazil small stream garden " symbol
Normally " province, city and region/county road number poi " therefore can mark validity label " 1 ", and " Hangzhou, Zhejiang province city Yuhang
Area ", which meets regular " province, city and region/county ", therefore can mark validity label " 0 "
Using address characteristic information, validity label as training sample, have by the model trainings such as LR, random forest address
Effect property grader 305.
Step 306, if transaction platform receives new order data, address information can be extracted, and counts the address
The corresponding trading activity data of information.
Step 307, extended address information is extracted from address information
Step 308, address information, trading activity data and extended address information are subjected to discretization, obtain address feature
Information.
By in address characteristic information input validity grader 305, validity grader 305 carries out operation, exports the ground
The validity 309 of location information.
It should be noted that for embodiment of the method, for simple description, therefore it is all expressed as a series of action group
It closes, but those skilled in the art should understand that, the embodiment of the present application is not limited by the described action sequence, because according to
According to the embodiment of the present application, certain steps can be performed in other orders or simultaneously.Secondly, those skilled in the art also should
Know, embodiment described in this description belongs to preferred embodiment, and involved action not necessarily the application is implemented
Necessary to example.
With reference to Fig. 4, a kind of structure of the training device of address validity grader of the application one embodiment is shown
Block diagram can specifically include following module：
Address information acquisition module 401, for obtaining address information；
Address characteristic information generation module 402, for generating address characteristic information according to described address information；
Validity label for labelling module 403, for described address information labeling validity label；
Classifier training module 404, for using described address characteristic information and the validity label as training sample,
Training address validity grader.
In one embodiment of the application, described address characteristic information generation module 402 includes：
Address element mapping submodule, for being address elements at different levels by described address information MAP；
Address characteristic information transform subblock, for described address element to be converted to address characteristic information.
In another embodiment of the application, described address information includes the address information in order data；Describedly
Location characteristic information generation module 402 further includes：
Trading activity data statistics submodule, for counting the corresponding transaction of described address information from the order data
Behavioral data；
Submodule is arranged in trading activity data, for setting the trading activity data to address characteristic information；
Wherein, the trading activity data include following one or more：
Order number, order transaction successful number, the number of order transaction failure, described address information sign for success
Number, described address information the number for signing for failure.
In another embodiment of the application, described address characteristic information generation module 402 further includes：
Extended address information extraction submodule, for extracting extended address information from described address information；
Submodule is arranged in extended address information, for setting the extended address information to address characteristic information；
Wherein, the extended address information includes following one or more：
The richness of described address information, the text size of the address element of specified level, town and country information.
In one embodiment of the application, the validity label for labelling module 403 includes：
Rule query submodule is marked, for inquiring mark rule, the mark regular record has comprising one or more
The administrative address template and validity label of address element；
Administrative address template matches module is used for the address element in described address information and the administrative address template
When with success, validity label corresponding to administrative address template described in described address information labeling.
With reference to Fig. 5, a kind of structure diagram of the verification device of address validity of the application one embodiment, tool are shown
Body may include following module：
Order data receiving module 501 has address information for receiving order data in the order data；
Address characteristic information generation module 502, for generating address characteristic information according to described address information；
Validity identification module 503, for described address characteristic information to be inputted to preset address validity grader, with
Identify the validity of described address information.
In one embodiment of the application, described address characteristic information generation module 502 includes：
Address element mapping submodule, for being address elements at different levels by described address information MAP；
Address characteristic information transform subblock, for described address element to be converted to address characteristic information.
In another embodiment of the application, described address characteristic information generation module 502 further includes：
Trading activity data statistics submodule, for counting the corresponding transaction of described address information from the order data
Behavioral data；
Submodule is arranged in trading activity data, for setting the trading activity data to address characteristic information；
Wherein, the trading activity data include following one or more：
Order number, order transaction successful number, the number of order transaction failure, described address information sign for success
Number, described address information the number for signing for failure.
In another embodiment of the application, described address characteristic information generation module 502 further includes：
Extended address information extraction submodule, for extracting extended address information from described address information；
Submodule is arranged in extended address information, for setting the extended address information to address characteristic information；
Wherein, the extended address information includes following one or more：
The richness of described address information, the text size of the address element of specified level, town and country information.
For device embodiments, since it is basically similar to the method embodiment, so fairly simple, the correlation of description
Place illustrates referring to the part of embodiment of the method.
Embodiment of the disclosure can be implemented as
System.Fig. 6 schematically shows the exemplary system 600 that can be used for realizing each embodiment described in the disclosure.
For one embodiment, Fig. 6 shows exemplary system 600, the system have one or more processors 602,
It is coupled to the system control module (chipset) 604 of at least one of (one or more) processor 602, is coupled to and be
The system storage 606 for control module 604 of uniting is coupled to the nonvolatile memory (NVM) of system control module 604/deposit
Storage equipment 608 is coupled to one or more input-output apparatus 610 of system control module 604, and is coupled to and is
The network interface 612 for control module 606 of uniting.
Processor 602 may include one or more single or multiple core processors, processor 602 may include general processor or
The arbitrary combination of application specific processor (such as graphics processor, application processor, Baseband processor etc.).In some embodiments,
System 600 can be as the transaction platform described in the embodiment of the present application.
In some embodiments, system 600 may include with instruction one or more computer-readable mediums (for example,
System storage 606 or NVM/ storage devices 608) and mutually merge with the one or more computer-readable medium and be configured as
It executes instruction and executes the one or more processors 602 of the action described in the disclosure to realize module.
For one embodiment, system control module 604 may include any suitable interface controller, with to (one or
It is multiple) at least one of processor 602 and/or any suitable equipment or component that are communicated with system control module 604 carries
For any suitable interface.
System control module 604 may include Memory Controller module, to provide interface to system storage 606.Storage
Device controller module can be hardware module, software module and/or firmware module.
System storage 606 can be used for for example, load of system 600 and storage data and/or instruction.For a reality
Example is applied, system storage 606 may include any suitable volatile memory, for example, DRAM appropriate.In some embodiments
In, system storage 606 may include four Synchronous Dynamic Random Access Memory of Double Data Rate type (DDR4SDRAM).
For one embodiment, system control module 604 may include one or more i/o controllers, with to
NVM/ storage devices 608 and (one or more) input-output apparatus 610 provide interface.
For example, NVM/ storage devices 608 can be used for storing data and/or instruction.NVM/ storage devices 608 may include appointing
It anticipates and nonvolatile memory appropriate (for example, flash memory) and/or may include that any suitable (one or more) is non-volatile and deposit
Equipment is stored up (for example, one or more hard disk drives (HDD), one or more CD (CD) drivers and/or one or more
Digital versatile disc (DVD) driver).
NVM/ storage devices 608 may include a part for the equipment being physically mounted on as system 600
Storage resource or its beautiful part for being not necessarily as the equipment can be accessed by the equipment.For example, NVM/ storage devices 608 can
It is accessed via (one or more) input-output apparatus 610 by network.
(one or more) input-output apparatus 610 can be system 600 provide interface with other arbitrary equipment appropriate
Communication, input-output apparatus 610 may include communication component, audio component, sensor module etc..Network interface 612 can be
System 600 provides interfaces with by one or more network communications, system 600 can according to one or more wireless network standards and/
Or arbitrary standards in agreement and/or agreement are carried out wireless communication with the one or more components of wireless network, such as access
Wireless network based on communication standard, such as WiFi, 2G or 3G or combination thereof carry out wireless communication.
For one embodiment, at least one of (one or more) processor 602 can be with system control module 604
The logic of one or more controllers (for example, Memory Controller module) is packaged together.For one embodiment, (one
Or multiple) at least one of processor 602 can be encapsulated in the logic of one or more controllers of system control module 604
Together to form system in package (SiP).For one embodiment, at least one of (one or more) processor 602 can
It is integrated on same mold with the logic of one or more controllers of system control module 604.For one embodiment, (one
It is a or multiple) at least one of processor 602 can be integrated with the logic of one or more controllers of system control module 604
To form system on chip (SoC) on same mold.
In various embodiments, system 600 can be, but not limited to be：Server, work station, desk-top computing device or movement
Computing device (for example, lap-top computing devices, handheld computing device, tablet computer, net book etc.).In various embodiments,
System 600 can have more or fewer components and/or different frameworks.For example, in some embodiments, system 600 includes
One or more video cameras, keyboard, liquid crystal display (LCD) screen (including touch screen displays), nonvolatile memory port,
Mutiple antennas, graphic chips, application-specific integrated circuit (ASIC) and loud speaker.
Wherein, if display includes touch panel, display screen may be implemented as touch screen displays, be used by oneself with receiving
The input signal at family.Touch panel includes one or more touch sensors to sense the hand on touch, slide, and touch panel
Gesture.The touch sensor can not only sense the boundary of a touch or slide action, but also detect and the touch or sliding
Operate relevant duration and pressure.
The embodiment of the present application discloses method and apparatus, and example 1 includes a kind of training method of address validity grader,
This method includes：Obtain address information；Address characteristic information is generated according to described address information；Have to described address information labeling
Effect property label；Using described address characteristic information and the validity label as training sample, train address validity grader.
Example 2 includes the method described in example 1, wherein described to generate address characteristic information according to described address information
Step includes：It is address elements at different levels by described address information MAP；Described address element is converted into address feature letter
Breath.
Example 3 includes the method described in example 2, wherein described address information includes the address information in order data；Institute
Stating the step of generating address characteristic information according to described address information further includes：Described address information pair is counted from order data
The trading activity data answered；Set the trading activity data to address characteristic information；Wherein, the trading activity data packet
It includes following one or more：The successful number of order number, order transaction, the number of order transaction failure, described address letter
Breath sign for successful number, described address information the number for signing for failure.
Example 4 includes the method described in example 2, wherein described to generate address characteristic information according to described address information
Step further includes：Extended address information is extracted from described address information；Set the extended address information to address feature
Information；Wherein, the extended address information includes following one or more：The richness of described address information, specified level
The text size of address element, town and country information.
Example 5 includes the method described in example 2 or example 3 or example 4, wherein described to have to described address information labeling
Effect property label the step of include：Inquiry mark rule, the mark regular record have the row for including one or more address elements
Political affairs address template and validity label；When the address element of described address information and administrative address template matches success,
Validity label corresponding to administrative address template described in described address information labeling.
Example 6 includes a kind of verification method of address validity, and this method includes：Receive order data, the order numbers
There is address information in；Address characteristic information is generated according to described address information；Described address characteristic information is inputted preset
Address validity grader, to identify the validity of described address information.
Example 7 includes a kind of training device of address validity grader, which includes：Address information acquisition module,
For obtaining address information；Address characteristic information generation module, for generating address characteristic information according to described address information；Have
Effect property label for labelling module, for described address information labeling validity label；Classifier training module, for described
Location characteristic information and the validity label are as training sample, training address validity grader.
Example 8 includes the device described in example 7, wherein described address characteristic information generation module includes：Address element is reflected
Submodule is penetrated, for being address elements at different levels by described address information MAP；Address characteristic information transform subblock, is used for
Described address element is converted into address characteristic information.
Example 9 includes the device described in example 8, wherein described address information includes the address information in order data；Institute
Stating address characteristic information generation module further includes：Trading activity data statistics submodule, described in the statistics from order data
The corresponding trading activity data of address information；Submodule is arranged in trading activity data, for the trading activity data to be arranged
For address characteristic information；Wherein, the trading activity data include following one or more：Order number, order transaction at
The number of work(, the number of order transaction failure, described address information sign for successful number, described address information is signed for losing
The number lost.
Example 10 includes the device described in example 8, wherein described address characteristic information generation module further includes：Extension ground
Location information extraction submodule, for extracting extended address information from described address information；Submodule is arranged in extended address information,
For setting the extended address information to address characteristic information；Wherein, the extended address information includes following one kind
Or it is a variety of：The richness of described address information, the text size of the address element of specified level, town and country information.
Example 11 includes the device described in example 8 or example 9 or example 10, wherein the validity label for labelling module
Including：Rule query submodule is marked, for inquiring mark rule, the mark regular record has comprising one or more addresses
The administrative address template and validity label of element；Administrative address template matches module, in the address of described address information
It is corresponding to administrative address template described in described address information labeling effective when element is with administrative address template matches success
Property label.
Example 12 includes a kind of verification device of address validity, which includes：Order data receiving module, for connecing
Forms data is received and processed subscriptions, there is address information in the order data；Address characteristic information generation module, for being believed according to described address
Breath generates address characteristic information；Validity identification module, for described address characteristic information to be inputted to preset address validity
Grader, to identify the validity of described address information.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiment, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiments of the present application may be provided as method, apparatus or calculating
Machine program product.Therefore, the embodiment of the present application can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present application can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
In a typical configuration, the computer equipment includes one or more processors (CPU), input/output
Interface, network interface and memory.Memory may include the volatile memory in computer-readable medium, random access memory
The forms such as device (RAM) and/or Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is to calculate
The example of machine readable medium.Computer-readable medium includes that permanent and non-permanent, removable and non-removable media can be with
Information storage is realized by any method or technique.Information can be computer-readable instruction, data structure, the module of program or
Other data.The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM
(SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), fast flash memory bank or other memory techniques, CD-ROM are read-only
Memory (CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic disk storage or
Other magnetic storage apparatus or any other non-transmission medium can be used for storage and can be accessed by a computing device information.According to
Herein defines, and computer-readable medium does not include non-persistent computer readable media (transitory media), such as
The data-signal and carrier wave of modulation.
The embodiment of the present application is with reference to according to the method for the embodiment of the present application, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in flow and/or box combination.These can be provided
Computer program instructions are set to all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine so that is held by the processor of computer or other programmable data processing terminal equipments
Capable instruction generates for realizing in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes
The device of specified function.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing terminal equipments
In computer-readable memory operate in a specific manner so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one flow of flow chart or multiple flows and/or one side of block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing terminal equipments so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one flow of flow chart or multiple flows
And/or in one box of block diagram or multiple boxes specify function the step of.
Although preferred embodiments of the embodiments of the present application have been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and all change and modification within the scope of the embodiments of the present application.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also include other elements that are not explicitly listed, or further include for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device including the element.
Classify above to a kind of training method of address validity grader provided herein, a kind of address validity
The training device of device, a kind of verification method of address validity, a kind of verification device of address validity, a kind of device and one
Or multiple computer-readable mediums, it is described in detail, used herein principle and implementation of the specific case to the application
Mode is expounded, the description of the example is only used to help understand the method for the present application and its core ideas；Meanwhile
For those of ordinary skill in the art, according to the thought of the application, has change in specific embodiments and applications
Become place, in conclusion the contents of this specification should not be construed as limiting the present application.
Claims (16)
1. a kind of training method of address validity grader, which is characterized in that including：
Obtain address information；
Address characteristic information is generated according to described address information；
To described address information labeling validity label；
Using described address characteristic information and the validity label as training sample, train address validity grader.
2. according to the method described in claim 1, it is characterized in that, described generate address characteristic information according to described address information
The step of include：
It is address elements at different levels by the dispatching address of cache；
Described address element is converted into address characteristic information.
3. according to the method described in claim 2, it is characterized in that, described address information includes the address letter in order data
Breath；
It is described according to described address information generate address characteristic information the step of further include：
The corresponding trading activity data of described address information are counted from the order data；
Set the trading activity data to address characteristic information；
Wherein, the trading activity data include following one or more：
The successful number of order number, order transaction, order transaction failure number, described address information sign for successfully time
The number for signing for failure of number, described address information.
4. according to the method described in claim 2, it is characterized in that, described generate address characteristic information according to described address information
The step of further include：
Extended address information is extracted from described address information；
Set the extended address information to address characteristic information；
Wherein, the extended address information includes following one or more：
The richness of described address information, the text size of the address element of specified level, town and country information.
5. according to the method described in Claims 2 or 3 or 4, which is characterized in that described to described address information labeling validity mark
The step of label includes：
Inquiry mark rule, the mark regular record have the administrative address template comprising one or more address elements and effectively
Property label；
When the address element of described address information and administrative address template matches success, institute is marked to the dispatching address
State the corresponding validity label of administrative address template.
6. a kind of verification method of address validity, which is characterized in that including：
Order data is received, there is address information in the order data；
Address characteristic information is generated according to described address information；
Described address characteristic information is inputted to preset address validity grader, to identify the validity of described address information.
7. a kind of training device of address validity grader, which is characterized in that including：
Address information acquisition module, for obtaining address information；
Address characteristic information generation module, for generating address characteristic information according to described address information；
Validity label for labelling module, for described address information labeling validity label；
Classifier training module is used for using described address characteristic information and the validity label as training sample, trains ground
Location validity grader.
8. device according to claim 7, which is characterized in that described address characteristic information generation module includes：
Address element mapping submodule, for being address elements at different levels by described address information MAP；
Address characteristic information transform subblock, for described address element to be converted to address characteristic information.
9. device according to claim 8, which is characterized in that described address information includes the address letter in order data
Breath；Described address characteristic information generation module further includes：
Trading activity data statistics submodule, for counting the corresponding trading activity of described address information from the order data
Data；
Submodule is arranged in trading activity data, for setting the trading activity data to address characteristic information；
Wherein, the trading activity data include following one or more：
The successful number of order number, order transaction, order transaction failure number, described address information sign for successfully time
The number for signing for failure of number, described address information.
10. device according to claim 8, which is characterized in that described address characteristic information generation module further includes：
Extended address information extraction submodule, for extracting extended address information from described address information；
Submodule is arranged in extended address information, for setting the extended address information to address characteristic information；
Wherein, the extended address information includes following one or more：
The richness of described address information, the text size of the address element of specified level, town and country information.
11. according to the device described in claim 8 or 9 or 10, which is characterized in that the validity label for labelling module includes：
Rule query submodule is marked, for inquiring mark rule, the mark regular record has comprising one or more addresses
The administrative address template and validity label of element；
Administrative address template matches module, for address element and the administrative address template matches in described address information at
When work(, validity label corresponding to administrative address template described in described address information labeling.
12. a kind of verification device of address validity, which is characterized in that including：
Order data receiving module has address information for receiving order data in the order data；
Address characteristic information generation module, for generating address characteristic information according to described address information；
Validity identification module, for described address characteristic information to be inputted to preset address validity grader, to identify
State the validity of address information.
13. a kind of device, which is characterized in that including：
One or more processors；With
Instruction in the one or more computer-readable mediums stored thereon, when being executed by one or more of processors,
Described device is caused to execute the method such as claim 1-5.
14. one or more computer-readable mediums, are stored thereon with instruction, when executed by one or more processors, make
The method for obtaining the claim 1-5 that terminal device executes.
15. a kind of device, which is characterized in that including：
One or more processors；With
Instruction in the one or more computer-readable mediums stored thereon, when being executed by one or more of processors,
Described device is caused to execute method as claimed in claim 6.
16. one or more computer-readable mediums, are stored thereon with instruction, when executed by one or more processors, make
The method for obtaining the claim 6 that terminal device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710103991.XA CN108509441A (en) | 2017-02-24 | 2017-02-24 | Training of address validity classifier, verification method thereof and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710103991.XA CN108509441A (en) | 2017-02-24 | 2017-02-24 | Training of address validity classifier, verification method thereof and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108509441A true CN108509441A (en) | 2018-09-07 |
Family
ID=63372916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710103991.XA Pending CN108509441A (en) | 2017-02-24 | 2017-02-24 | Training of address validity classifier, verification method thereof and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108509441A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109344254A (en) * | 2018-09-20 | 2019-02-15 | 北京神州泰岳软件股份有限公司 | A kind of address information classification method and device |
| CN109359186A (en) * | 2018-10-25 | 2019-02-19 | 杭州时趣信息技术有限公司 | A kind of method, apparatus and computer readable storage medium of determining address information |
| CN109583933A (en) * | 2018-10-09 | 2019-04-05 | 顺丰科技有限公司 | Address information judgment method, device, equipment and its storage medium |
| CN111274802A (en) * | 2018-11-19 | 2020-06-12 | 阿里巴巴集团控股有限公司 | Validity judgment method and device for address data |
| CN111966768A (en) * | 2020-06-29 | 2020-11-20 | 北京百度网讯科技有限公司 | Address description method and device, electronic equipment and storage medium |
| CN113344592A (en) * | 2021-05-31 | 2021-09-03 | 中检集团溯源技术服务有限公司 | Tracing label validity management system and method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140172774A1 (en) * | 2011-12-13 | 2014-06-19 | Peking University Founder Group Co., Ltd | Method and device for named-entity recognition |
| CN104217160A (en) * | 2014-09-19 | 2014-12-17 | 中国科学院深圳先进技术研究院 | Method and system for detecting Chinese phishing website |
| CN105389722A (en) * | 2015-11-20 | 2016-03-09 | 小米科技有限责任公司 | Malicious order identification method and device |
| CN105447204A (en) * | 2016-01-04 | 2016-03-30 | 北京百度网讯科技有限公司 | Website recognition method and apparatus |
| CN105512145A (en) * | 2014-09-26 | 2016-04-20 | 阿里巴巴集团控股有限公司 | Method and device for information classification |
| CN105528383A (en) * | 2014-10-27 | 2016-04-27 | 阿里巴巴集团控股有限公司 | Method and device for indentifying risks of accounts |
| US20160147943A1 (en) * | 2014-11-21 | 2016-05-26 | Argo Data Resource Corporation | Semantic Address Parsing Using a Graphical Discriminative Probabilistic Model |
| CN106202028A (en) * | 2015-04-30 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of address information recognition methods and device |
-
2017
- 2017-02-24 CN CN201710103991.XA patent/CN108509441A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140172774A1 (en) * | 2011-12-13 | 2014-06-19 | Peking University Founder Group Co., Ltd | Method and device for named-entity recognition |
| CN104217160A (en) * | 2014-09-19 | 2014-12-17 | 中国科学院深圳先进技术研究院 | Method and system for detecting Chinese phishing website |
| CN105512145A (en) * | 2014-09-26 | 2016-04-20 | 阿里巴巴集团控股有限公司 | Method and device for information classification |
| CN105528383A (en) * | 2014-10-27 | 2016-04-27 | 阿里巴巴集团控股有限公司 | Method and device for indentifying risks of accounts |
| US20160147943A1 (en) * | 2014-11-21 | 2016-05-26 | Argo Data Resource Corporation | Semantic Address Parsing Using a Graphical Discriminative Probabilistic Model |
| CN106202028A (en) * | 2015-04-30 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of address information recognition methods and device |
| CN105389722A (en) * | 2015-11-20 | 2016-03-09 | 小米科技有限责任公司 | Malicious order identification method and device |
| CN105447204A (en) * | 2016-01-04 | 2016-03-30 | 北京百度网讯科技有限公司 | Website recognition method and apparatus |
Non-Patent Citations (5)
| Title |
|---|
| 汪立东: "《网络流量分类方法与实践》", 31 October 2013, 人民邮电出版社, pages: 51 - 52 * |
| 王勇: "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》 * |
| 王勇: "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》, 31 May 2016 (2016-05-31), pages 624 * |
| 邵妍等: "基于概率统计模型的快递地址自动分类方法", 《计算机工程》 * |
| 邵妍等: "基于概率统计模型的快递地址自动分类方法", 《计算机工程》, no. 23, 5 December 2012 (2012-12-05) * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109344254A (en) * | 2018-09-20 | 2019-02-15 | 北京神州泰岳软件股份有限公司 | A kind of address information classification method and device |
| CN109583933A (en) * | 2018-10-09 | 2019-04-05 | 顺丰科技有限公司 | Address information judgment method, device, equipment and its storage medium |
| CN109359186A (en) * | 2018-10-25 | 2019-02-19 | 杭州时趣信息技术有限公司 | A kind of method, apparatus and computer readable storage medium of determining address information |
| CN109359186B (en) * | 2018-10-25 | 2020-12-08 | 杭州时趣信息技术有限公司 | Method and device for determining address information and computer readable storage medium |
| CN111274802A (en) * | 2018-11-19 | 2020-06-12 | 阿里巴巴集团控股有限公司 | Validity judgment method and device for address data |
| CN111274802B (en) * | 2018-11-19 | 2023-04-18 | 阿里巴巴集团控股有限公司 | Validity judgment method and device for address data |
| CN111966768A (en) * | 2020-06-29 | 2020-11-20 | 北京百度网讯科技有限公司 | Address description method and device, electronic equipment and storage medium |
| CN111966768B (en) * | 2020-06-29 | 2023-11-17 | 北京百度网讯科技有限公司 | Address description method, address description device, electronic equipment and storage medium |
| CN113344592A (en) * | 2021-05-31 | 2021-09-03 | 中检集团溯源技术服务有限公司 | Tracing label validity management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509441A (en) | Training of address validity classifier, verification method thereof and related device | |
| WO2020077877A1 (en) | Platform commodity stationing method and apparatus, and computer device and storage medium | |
| US12086702B2 (en) | Neural network for processing graph data | |
| US11652628B2 (en) | Deterministic verification of digital identity documents | |
| CN109190044A (en) | Personalized recommendation method, device, server and medium | |
| WO2021063045A1 (en) | Blockchain-based transaction query method, apparatus and device, and blockchain-based transaction data processing method, apparatus and device | |
| CN103678335B (en) | The method of method, apparatus and the commodity navigation of commodity sign label | |
| CN109816134B (en) | Method and device for predicting delivery address and storage medium | |
| CN110110244B (en) | Interest point recommendation method integrating multi-source information | |
| CN109255565A (en) | Address attribution identification and logistics task distribution method and device | |
| CN110874534B (en) | Data processing method and data processing device | |
| CN109255564A (en) | Pick-up point address recommendation method and device | |
| WO2018035164A1 (en) | Description information generation and presentation systems, methods, and devices | |
| CN111522838B (en) | Address similarity calculation method and device | |
| CN107423278A (en) | The recognition methods of essential elements of evaluation, apparatus and system | |
| CN108734469A (en) | The method and apparatus for determining consumer's risk label undetermined | |
| CN116308684B (en) | Online shopping platform store information pushing method and system | |
| CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
| US20130304539A1 (en) | User recommendation method and device | |
| CN110503453A (en) | Customer-action analysis method, apparatus, computer equipment and storage medium | |
| CN105589911A (en) | Customer value assessment method and system | |
| CN110362825A (en) | A kind of text based finance data abstracting method, device and electronic equipment | |
| CN112860905A (en) | Text information extraction method, device and equipment and readable storage medium | |
| CN104778538A (en) | Agricultural product cellphone tracing method based on NFC | |
| CN105574480B (en) | A kind of information processing method, device and terminal |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180907 |