CN109359195A - A kind of HS coding translation method - Google Patents
A kind of HS coding translation method Download PDFInfo
- Publication number
- CN109359195A CN109359195A CN201811219242.4A CN201811219242A CN109359195A CN 109359195 A CN109359195 A CN 109359195A CN 201811219242 A CN201811219242 A CN 201811219242A CN 109359195 A CN109359195 A CN 109359195A
- Authority
- CN
- China
- Prior art keywords
- coding
- commodity
- ontology
- translation method
- library
- 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
Landscapes
- Machine Translation (AREA)
Abstract
In view of the deficiencies of the prior art, the present invention provides a kind of HS coding translation method, the HS coding of importer and exporting country can be made a report on immediately, translation method is encoded to a kind of this HS of present invention, the title or attribute description of commodity are obtained first, the product ontology based on descriptive labelling is constructed by product name or attribute description, and is encoded from international trade ontology library and the HS of exported country coding catalogue according to the HS that product ontology describes to obtain the exported country for corresponding to the product ontology；It is matched the common code in catalogue is encoded with importer HS after the encoded translated description for corresponding common code of the HS of exported country again, finds the HS coding of corresponding importer.Technical solution in this way, introduce the concept of common code, the two-way HS coding of exported country and importer is realized to set up bridge, and can voluntarily learn to adjust the classification confidence level of HS coding by final result, the final two-way automatic HS coding for realizing high accuracy.
Description
Technical field
The present invention relates to product automatic classification methods, and in particular to a kind of HS coding translation method.
Background technique
HS catalogue is a kind of international import-export commodity classification system.HS catalogue passes through the classification of 5-7 level, is
The commodity in international trade are sorted out on system ground, and define digital coding (i.e. HS coding) for each stratigraphic classification for looking into
It looks for and counts.According to HS system of catalogs, all kinds of import-export commodities can be all defined in HS catalogue by its trade name and be determined uniquely
8~10 HS coding.As the basis of customs of various countries Management and statistics, HS coding has obtained wide in international trade
General application.HS encodes the foundational system for having become and executing all kinds of Regulation Policies and carrying out import and export statistics, is customs and inspection inspection
Epidemic disease department judges that commodity are applicable in the direct basis of policy, and Management takes different prisons for the different HS trade name encoded
Pipe measure.Due to its reliability, its application has also related to the industries such as auction, more extensively.
But the inquiry of HS coding and the confirmation uninteresting time-consuming of work, the professional knowledge of very big workload and profession is needed,
And it is easy error, become current an important factor for influencing cargo clearance efficiency.Due to language, the text between importer and exported country
The differences such as change, commodity classification, HS coding cannot achieve direct conversion at this stage and generate.It is convenient for although also having in the prior art
It is just devised in the product classification system of control, such as utility model TW M555499U " product classification system " a kind of unidirectional
The method that kinds of goods are classified.Although the method can classify automatically to commodity at outlet, arrive after importer still
It needs manually to be matched.
Since intelligent generation/translation of HS coding is to the automation of realization inspection and quarantine operation flow, raising customs clearance efficiency tool
It is significant.And there is no the methods for the HS coding that can unify conversion outlet state and importer in the prior art, lead to this
Conversion work still needs manually to participate in.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of HS coding translation method, can make a report on importer and defeated immediately
Go abroad HS coding, reduce fill in HS coding when deviation, reduce country variant commodity classification difference cause to encode it is wrong
May, improve the efficiency of declaration.
In order to achieve the above object, the present invention is achieved by the following technical programs:
A kind of HS coding translation method, obtains the title or attribute description of commodity first, is retouched by product name or attribute
State product ontology of the building based on descriptive labelling, and the basis from international trade ontology library and the HS of exported country coding catalogue
Product ontology description obtains the HS coding of the exported country of the corresponding product ontology；The HS of exported country is encoded translated for corresponding public affairs
It is matched again after code description with the common code in importer HS coding catalogue altogether, finds the HS coding of corresponding importer.
Preferably, applied in the conversion process to common code use based on country origins different in World Trade Organization library
On the basis of the degree of approximation between the description of commodity English language.At this stage, the commodity English language of different country origins in World Trade Organization library
Speech is the optimal selection as common code due to its official's background and by the receiving of every country.But in some special feelings
It, can also be directly using French as common code when the foreign trade carried out between condition, such as country of French Language Department.
Preferably, the specific acquisition pattern of product ontology be from the concept of commodity, be mapped to commodity field, and
A variety of relationships between commodity concept are excavated, the attribute of commodity is extracted from commodity concept, and divided classification, finds out this
Association in a little classifications.Such classification method not only nominally classifying from commodity, also not only from item property
In classify, and further pay close attention to it is interrelated between commodity actual attribute, by this be associated with embody commodity essence,
Increase the reliability of commodity classification.
Preferably, described to divide column classification method particularly includes: after obtaining item property data in commodity concept, to this
A little data are pre-processed, and aggregation process result obtains a commodity candidate attribute word finder, then dividing to this word finder
The research of category feature analysis, obtains characteristic of division collection, summarizes these test feature libraries, therefrom extract effective characteristic of division collection, structure
Corresponding characteristic of division library is made, then constructs disaggregated model according to this feature database, the classification of item property is obtained, is formed sorted
Fine granularity commodity document.Such commodity document not only can solve the coding of HS at that time, while also there are backups, are later HS
Coding work provides precedent, is convenient for systematic learning.
Further, Semantic Web combines to form international trade ontology library with knowledge mapping technology.
Preferably, when the corresponding HS coding of product ontology description is not unique, international trade ontology library combination HS encodes mesh
Record provides the possible outcome collection of multiple HS coding compositions, and each HS coding is with corresponding coding confidence level.It is some can not
The occasion that directly analysis is distinguished is associated with item property by product name, needs to be arranged coding confidence level and puts on record, pass through
The result finally declared at customs adjusts coding confidence level, provides support to declare next time.
Further, each selected HS coding of the international trade ontology library record, and compiled according to the HS of selection
Code is finally returned in HS catalogue using result and adjusts its corresponding coding confidence level.This is the specific side of adjustment coding confidence level
Method.
Preferably, item property is translated as the specific steps of common code are as follows: determines and retouches for matched country of origin's commodity
State text and target state descriptive labelling text；Keyword is screened after pre-processing to text；It is similar that text is carried out to keyword
Degree calculates；Choose HS coding of the coding of HS corresponding to the maximum text of similarity as translation；Such as there is mistake successively to choose
The similarity only corresponding HS coding of secondary text；Until successful match.
Further, final correct result is recorded as learning outcome.
Preferably, screening keyword uses TF-IDF algorithm.It is in fact many to screen the available algorithm of keyword, still
TF-IDF (term frequency-inverse document frequency) is dug as a kind of for information retrieval and data
The advantage of the common weighting technique of pick is that 1. algorithm is simple, is easily achieved, and reduces searching cost, improves retrieval rate；(2) exist
There are many successful application in terms of SEO search engine optimization, text classification, reliability has been verified；3. catering to the present invention
Using text to the scene of descriptive labelling.
The technical solution of the present invention in this way, introduces the concept of common code, so that having set up bridge realizes outlet
The two-way HS of state and importer coding, and can voluntarily learn to adjust the classification confidence level of HS coding by final result, finally
Realize the two-way automatic HS coding of high accuracy.To which by fundamentally solving, user's input information is inaccurate, information is not complete, letter
The problem of user search low efficiencys of generations such as breath is fuzzy, information ambiguity and product name be not unique.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of translation flow chart of HS coding translation method of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
HS coding is arranged based on "HS"("Harmonized Commodity Description and Coding System").Coding coordination system is managed by international customs
Thing can be formulated, and English name, which is The Harmonization System Code (HS-Code), to be gone out to various different products
The system of drawback tax rate progress quantitative management be recruited/is answered in immigration.Customs of various countries, commodity entry-exit management mechanism confirm commodity class
Not, it carries out category management, audit tariff standard, examine the fundamental of marketing quality index to be exactly that import-export commodity is general
Proof of identification --- HS coding.Due to its authority, also gradually used to fields such as auctions.
HS coding shares 22 major class, 98 chapter.2 codes, 4 codes and the 6 code HS of the current international practice are encoded by international customs director
It can formulate.More than 6 codes coding and corresponding goods are made by oneself by various countries, and there are difference for 6 or more various countries' codings.International sea simultaneously
Director Guan may require that various countries report and submit the english language version of the newest HS coding of this country every year, and advise to the English description of commodity
Model and revision.Therefore the HS coding local GEO authority of native language, the HS of English descriptive labelling encode international customs's reason
The English edition authority of thing meeting.The final HS coding schedule in China requires to be updated every year from WTO and Chinese customs.
Just because of 6 or more various countries' codings, there are difference, and HS coding and specific corresponding commodity are not an a pair
The relationship answered, therefore directly conversion is to bring biggish error, needs manual operation at this stage.But this work is to operator
The skill requirement of member is very high, does not require nothing more than the HS coding that operator is familiar with exported country, it is also necessary to which the HS for being familiar with importer is compiled
Code, it is also necessary to understand the code change of current year immediately.When occurring needing to multiple national exports, be difficult to find that substantially one it is complete
The operator in face looks for multiple operator's code levels very different, also brings along many troubles.Based on such existing
Shape, we just expect realizing automatic HS coding translation by a kind of universal method
As shown in Figure 1, a kind of HS of the present invention encodes translation method, the title or attribute description of commodity are obtained first, is passed through
Product name or attribute description construct the product ontology based on descriptive labelling, and from international trade ontology library and exported country
HS is encoded in catalogue and is encoded according to the HS that product ontology describes to obtain the exported country for corresponding to the product ontology；The HS of exported country is compiled
Code matches after being converted into the description of corresponding common code with the common code in importer HS coding catalogue again, discovery it is corresponding into
The HS coding of mouth state.Applied in the conversion process to common code use the quotient based on country origins different in World Trade Organization library
On the basis of the degree of approximation between the description of product English language.The specific acquisition pattern of product ontology is, from the concept of commodity, to reflect
It is mapped to commodity field, and excavates a variety of relationships between commodity concept, the attribute of commodity is extracted from commodity concept, and will
It divides classification, finds out the association in these classifications.
Specifically, the acquisition of relevance at this time is based on the foundation of basic data structure and data acquisition, magnanimity number of deals
According to obtain and analysis, including and be not limited to:
(1) various countries HS basis of coding data；
(2) the acquisition of transaction big data and signature analysis；
(3) various countries' trade criterion, tax rate data, Law Text are obtained and are analyzed.
Comprehensive various aspects attribute, can be with the space framework of framework commodity.
The division column classification method particularly includes: after obtaining item property data in commodity concept, to these data
It is pre-processed, aggregation process result obtains a commodity candidate attribute word finder, then the carry out characteristic of division to this word finder
The research of analysis obtains characteristic of division collection, summarizes these test feature libraries, therefrom extracts effective characteristic of division collection, and construction corresponds to
Characteristic of division library, then according to this feature database construct disaggregated model, obtain the classification of item property, form sorted fine granularity
Commodity document.
When overcoming more rules and the translation of descriptive labelling in this way not really, especially solve same commodity and be included into difference
There is one-to-many or ambiguity when translating in the problem of classification, commodity.Same processing method has been allowed also for difference
The uncurrent problem of language environment, such as the problem that language syntax rule is different or mode of thinking different band is next, consider conscientiously
The influence that the dynamic change of HS coding generates system is arrived.
Semantic Web combines to form international trade ontology library with knowledge mapping technology.This international trade sheet
Body library is constantly updated based on existing database.When the corresponding HS coding of product ontology description is not unique, international trade
Product ontology library combines HS coding catalogue to provide the possible outcome collection of multiple HS coding compositions, and each HS coding is with corresponding
Encode confidence level.The each selected HS coding of international trade ontology library record, and it is final according to the HS of selection coding
It is returned in HS catalogue using result and adjusts its corresponding coding confidence level.Item property is translated as the specific steps of common code
Are as follows: it determines and is used for matched country of origin's descriptive labelling text and target state descriptive labelling text；It is sieved after being pre-processed to text
Select keyword；Text similarity computing is carried out to keyword；It chooses the coding of HS corresponding to the maximum text of similarity and is used as and turn
The HS coding translated；Such as there is mistake and successively chooses the similarity only corresponding HS coding of secondary text；Until successful match.Record is most
Whole correct result is as learning outcome.It screens keyword and uses TF-IDF algorithm.This system application TF-IDF algorithm can have
Effect reduces development cost, improves search efficiency；TF-IDF algorithm can be made in HS in conjunction with trade big data, machine learning scheduling algorithm
Coding plays more flexible effect in can only shifting.
After the commodity HS code verification of exported country, finds out and correspond to the public of this HS coding in international trade ontology library
Then code description content removes language in the international trade ontology library of matching importer with current common code description content
The most suitable result of adopted similarity simultaneously records this correct result.Common code selects world commerce group in the present embodiment
Knit the English of official's application.But in some special popular regions, such as in the foreign trade work of Francophone, French can be selected as public
Code altogether.
We are by taking " red wine " as an example, and exported country is China, and importer is the U.S..Red wine belongs to common-use words in usually life,
And it is not then in HS coding commodity list；Data can not be directly matched to after system receives this product name information of red wine
Title in library can prompt addition additional notes at this time.Establish red wine and descriptive labelling rule base at this time: based on commodity transaction library,
HS Coding and description handles initial data, excavates the product features of red wine by association rules mining algorithm, thus raw
At retrieval red wine rule base, the inference machine reasoning to be retrieved based on red wine is prepared.Domain expert can also be with manual construction simultaneously
With maintenance regulation library.
Establish commodity red wine and HS code database descriptive labelling ontology simultaneously: with OWL ontology description language according to commodity class
Not, the product features such as title, manufacturer, date of manufacture, price establish product ontology.Simultaneously also using OWL according to item property
Such as processing method, alcoholic strength grape variety, packing specification --- the every packing list digit of unit packaging specification *, brand feature are established
Item property ontology.
According to combining product ontology library to carry out classification analysis to this noun after additional notes, it is right with red wine institute to find
The HS coding answered.If supplemental information is insufficient when leading to not be matched to direct corresponding commodity, passes through product ontology, carry out
Screening, obtains the HS code set being best suitable for when this red wine declared；Take wherein HS coding with corresponding coding confidence
Degree, selection wherein encode confidence level highest one.After finally declaring at customs, the HS in the description information is added if errorless
The confidence level of coding；The corresponding confidence level for turning down HS coding if going wrong after declaration.
Confidence level can be applied in inference machine simultaneously, be recommended using inference machine to user: inference machine according to
User preference, historical query information and term are made inferences using rule base and ontology, and the result of reasoning is utilized quotient
Product ontology and item property describe ontology and carry out confidence level measurement, and the corresponding HS coding of the high description of confidence level is pushed away
It recommends to user.
It red wine is such as inputted, can find 2204210000,7013370000,7103280000 etc., and 2204210000 set
Certainty highest.Then recommend 2204210000 first during the later period, similar red wine was declared.Exported country HS is compiled at this time
Code determines.
HS coding translation: China 2204210000 coding can using World Customs Organization description as common code into
Row description: Other wine of fresh grapes, in containers holding 2L or less.
The public generation in catalogue is encoded after the encoded translated description for corresponding common code of the HS of exported country with importer HS
Code matches again, and the HS code database that common code has corresponded to the U.S. in the present embodiment describes Effervescent wine
The corresponding coding of Other:Of an alcoholic strength by volume not over 14percent vol. description
2204.21.20.00
Obtain final translation result exported country HS coding 2204210000--- importer HS coding:
2204.21.20.00。
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of HS encodes translation method, the title or attribute description of commodity are obtained first, it is characterised in that: pass through product name
Or attribute description constructs the product ontology based on descriptive labelling, and encodes mesh from international trade ontology library and the HS of exported country
The HS for describing to obtain the exported country of the corresponding product ontology in record according to product ontology is encoded；It is by the HS of exported country is encoded translated
It is matched again after corresponding common code description with the common code in importer HS coding catalogue, finds the HS of corresponding importer
Coding.
2. a kind of HS as described in claim 1 encodes translation method, it is characterised in that: arrived applied in the conversion process
Common code uses on the basis of the degree of approximation between the commodity English language description based on country origins different in World Trade Organization library.
3. a kind of HS as described in claim 1 encodes translation method, it is characterised in that: the specific acquisition pattern of product ontology
From the concept of commodity, commodity field to be mapped to, and excavate a variety of relationships between commodity concept, from commodity concept
In extract the attribute of commodity, and divided classification, find out the association in these classifications.
4. a kind of HS as claimed in claim 3 encodes translation method, it is characterised in that: the specific method for dividing column classification
Are as follows: after obtaining item property data in commodity concept, these data are pre-processed, aggregation process result obtains a quotient
Product candidate attribute word finder, then the research of the progress characteristic of division analysis to this word finder, obtain characteristic of division collection, summarize these
Effective characteristic of division collection is therefrom extracted in test feature library, constructs corresponding characteristic of division library, then construct and classify according to this feature database
Model obtains the classification of item property, forms sorted fine granularity commodity document.
5. a kind of HS as described in claim 1 encodes translation method, it is characterised in that: Semantic Web and knowledge mapping technology phase
In conjunction with formation international trade ontology library.
6. a kind of application method of HS coding translation method as claimed in claim 5, it is characterised in that: product ontology description pair
When answering HS coding not unique, international trade ontology library combination HS coding catalogue provides the possible outcome of multiple HS coding compositions
Collection, each HS coding is with corresponding coding confidence level.
7. a kind of application method of HS coding translation method as claimed in claim 6, it is characterised in that: the international trade quotient
The each selected HS coding of product ontology library record, and finally use result to return in HS catalogue according to the HS of selection coding and adjust it
Corresponding coding confidence level.
8. a kind of application method of HS coding translation method as described in claim 1, it is characterised in that: item property is translated as
The specific steps of common code are as follows: determine and be used for matched country of origin's descriptive labelling text and target state descriptive labelling text；It is right
Text screens keyword after being pre-processed；Text similarity computing is carried out to keyword；Choose the maximum text institute of similarity
HS coding of the corresponding HS coding as translation；Such as there is mistake and successively chooses the similarity only corresponding HS coding of secondary text；
Until successful match.
9. a kind of application method of HS coding translation method as claimed in claim 8, it is characterised in that: record final correct
As a result it is used as learning outcome.
10. a kind of application method of HS coding translation method as claimed in claim 8, it is characterised in that: screening keyword is adopted
With TF-IDF algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811219242.4A CN109359195A (en) | 2018-10-19 | 2018-10-19 | A kind of HS coding translation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811219242.4A CN109359195A (en) | 2018-10-19 | 2018-10-19 | A kind of HS coding translation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109359195A true CN109359195A (en) | 2019-02-19 |
Family
ID=65345866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811219242.4A Pending CN109359195A (en) | 2018-10-19 | 2018-10-19 | A kind of HS coding translation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109359195A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488458A (en) * | 2020-04-13 | 2020-08-04 | 上海朗曦信息技术有限公司 | Automatic recognition processing method and system for international trade commodity codes |
| CN111563168A (en) * | 2020-03-03 | 2020-08-21 | 天津蒙比利埃创新网络科技有限公司 | Method for intelligently classifying customs commodities based on AI knowledge graph algorithm |
| CN112052910A (en) * | 2020-09-21 | 2020-12-08 | 深圳海关动植物检验检疫技术中心 | Food safety classification method and device, computer equipment and storage medium |
| CN112529676A (en) * | 2020-12-22 | 2021-03-19 | 畅捷通信息技术股份有限公司 | Method for carrying out tax code final-stage classification based on social-level word vectors |
-
2018
- 2018-10-19 CN CN201811219242.4A patent/CN109359195A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563168A (en) * | 2020-03-03 | 2020-08-21 | 天津蒙比利埃创新网络科技有限公司 | Method for intelligently classifying customs commodities based on AI knowledge graph algorithm |
| CN111563168B (en) * | 2020-03-03 | 2022-12-13 | 天津蒙比利埃创新网络科技有限公司 | Method for intelligently classifying customs commodities based on AI knowledge graph algorithm |
| CN111488458A (en) * | 2020-04-13 | 2020-08-04 | 上海朗曦信息技术有限公司 | Automatic recognition processing method and system for international trade commodity codes |
| CN111488458B (en) * | 2020-04-13 | 2023-04-11 | 上海朗曦信息技术有限公司 | Automatic recognition processing method and system for international trade commodity codes |
| CN112052910A (en) * | 2020-09-21 | 2020-12-08 | 深圳海关动植物检验检疫技术中心 | Food safety classification method and device, computer equipment and storage medium |
| CN112052910B (en) * | 2020-09-21 | 2024-05-10 | 深圳海关动植物检验检疫技术中心 | Food safety classification method, device, computer equipment and storage medium |
| CN112529676A (en) * | 2020-12-22 | 2021-03-19 | 畅捷通信息技术股份有限公司 | Method for carrying out tax code final-stage classification based on social-level word vectors |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11500818B2 (en) | Method and system for large scale data curation | |
| CN111428053B (en) | Construction method of tax field-oriented knowledge graph | |
| CN109359195A (en) | A kind of HS coding translation method | |
| US11222052B2 (en) | Machine learning-based relationship association and related discovery and | |
| US11386096B2 (en) | Entity fingerprints | |
| CN103810527B (en) | Data manipulation execution, data quality metric and data element coupling method and system | |
| US10642869B2 (en) | Centralized data reconciliation using artificial intelligence mechanisms | |
| CN109446221B (en) | Interactive data exploration method based on semantic analysis | |
| CN108710663A (en) | A kind of data matching method and system based on ontology model | |
| AU2020380139B2 (en) | Data preparation using semantic roles | |
| CN110659357B (en) | Geographic knowledge question-answering system based on ontology semantic similarity | |
| CN117312989A (en) | Context-aware column semantic recognition method and system based on GCN and RoBERTa | |
| CN113850570A (en) | AI-based professional scheme aided decision-making expert system construction method | |
| Zhang et al. | Research on knowledge discovery and stock forecasting of financial news based on domain ontology | |
| CN112784049B (en) | Text data-oriented online social platform multi-element knowledge acquisition method | |
| Shankar et al. | Analyzing attrition and performance of an employee using machine learning techniques | |
| Xu et al. | Application of improved decision tree method based on rough set in building smart medical analysis CRM system | |
| CN113408964A (en) | Method for assisting government carbon management based on comprehensive evaluation system | |
| Buyuklieva et al. | Estimating bibliometric links using Google Scholar: A semi-systematic literature mapping of migration and housing | |
| Al Sarkhi | Building a data washing machine for unsupervised entity resolution of unstandardized references sources | |
| Chang | [Retracted] Evaluation Model of Enterprise Lean Management Effect Based on Data Mining | |
| Ma et al. | Regional forestry economic evaluation based on neural network and fuzzy model | |
| Duan et al. | LwF4IEE: An Incremental Learning Method for Interactive Event Extraction | |
| Ahmed Mohammed Zubair | Single-valued neutrosophic uncertain linguistic set based on multi-input relationship and semantic transformation | |
| Ye | Supplier Master Data Integration in Philips |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 810, 8th floor, no.6, Nanjia sanzong Road, Wanqingsha Town, Nansha District, Guangzhou, Guangdong 511458 Applicant after: Guangzhou push point technology development Co., Ltd Address before: 310018 Unit 07-09, Building No. 2, Science Park Road, Baiyang Street, Hangzhou Economic and Technological Development Zone, Zhejiang Province Applicant before: Hangzhou Pudian Technology Development Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190219 |