CN108241677A - A kind of method and system for the tax revenue sorting code number for obtaining commodity - Google Patents
A kind of method and system for the tax revenue sorting code number for obtaining commodity Download PDFInfo
- Publication number
- CN108241677A CN108241677A CN201611219407.9A CN201611219407A CN108241677A CN 108241677 A CN108241677 A CN 108241677A CN 201611219407 A CN201611219407 A CN 201611219407A CN 108241677 A CN108241677 A CN 108241677A
- Authority
- CN
- China
- Prior art keywords
- tax revenue
- code number
- commodity
- sorting code
- tax
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/10—Tax strategies
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Cash Registers Or Receiving Machines (AREA)
Abstract
The present invention provides a kind of method and system for the tax revenue sorting code number for obtaining commodity, obtain the merchandise news of the commodity in merchandising database;Obtain the corresponding lemma combination of the merchandise news;It is combined based on the lemma, is matched automatically in tax revenue taxonomy database, obtain the tax revenue sorting code number of the commodity.By being matched automatically in tax revenue taxonomy database, so as to solve in the prior art using acquisition commodity tax revenue sorting code number by the way of, matching accuracy is low, in match selection, error-prone and inconvenient, the technical issues of user's alternative duty contracture class difficulty is larger is manually participated in, has reached the matching accuracy for the tax revenue sorting code number for improving commodity, the difficulty that user obtains the tax revenue sorting code number of commodity is reduced, so as to which user be facilitated to obtain the technique effect of tax revenue sorting code number.
Description
Technical field
The present invention relates to classification field more particularly to a kind of method and system for the tax revenue sorting code number for obtaining commodity.
Background technology
To accelerate tax revenue modernization construction, facilitate that taxpayer is convenient, specification issues VAT invoice, be conducive to the tax authority
Strengthen the value-added tax administration of collection, State Administration of Taxation writes《Commodity and the classification of service tax revenue and coding》, hereinafter referred to as tax revenue classification
Coding, and increase coding correlation function in VAT invoice system upgrade version.
Tax revenue sorting code number includes commodity and two component parts of tax revenue classification and coding of service.Commodity and service tax revenue
Classification, including four major class such as cargo, labor service, service, intangible asset, 4021 class commodity and service name;Coding is added using 19
Custom coding 19+2*n.The commodity major class of tax revenue sorting code number is safeguarded that enterprise, individual cannot be from edlins by State Administration of Taxation
Modification, commodity group can voluntarily be safeguarded under the bottom commodity of tax revenue sorting code number commodity by taxpayer.Tax revenue sorting code number
VAT invoice, value-added tax common invoice, the goods issued suitable for the taxpayer using VAT invoice system upgrade version
Object transport service VAT invoice and motor vehicle sale uniform invoice.
From part of in August, 2016, the VAT invoice that enterprise issues, when selecting merchandise news, it is necessary to safeguard that tax revenue is classified
Coding.At present by the way of:
Manual entry:During typing commodity, safeguard that attribute tax revenue is classified, fuzzy query selects by hand, but enterprise customer is to tax
Contracture class is unfamiliar with, and many matchings do not know how to select less than situation.
File imports:The more user of merchandise news by export, safeguards tax revenue classification information, again by hand
It imports in VAT invoice system.This mode needs to know each commodity and services corresponding tax revenue sorting code number, and input is
Problem is susceptible to mistake and does not know what the problem of inputted.
Tool matching:File imports or interface mode, imports commodity and tax revenue classification, carries out database fuzzy matching, but
Matching accuracy is relatively low, needs manual intervention.
The present inventor has found that following technical problem or defect exists in the prior art in the practice of the invention:
Using acquisition commodity tax revenue sorting code number by the way of, matching accuracy is low, artificial to participate in match selection
Error-prone and inconvenient, user's alternative duty contracture class difficulty is larger.
Invention content
The present invention provides a kind of method and system for the tax revenue sorting code number for obtaining commodity, to solve in the prior art
Using acquisition commodity tax revenue sorting code number by the way of, matching accuracy, which must not obtain, to be ensured, artificial to participate in match selection
It is error-prone and inconvenient, the technical issues of user's alternative duty contracture class difficulty is larger.
One aspect of the present invention provides a kind of method for the tax revenue sorting code number for obtaining commodity, including:
Obtain the merchandise news of the commodity in merchandising database;
Obtain the corresponding lemma combination of the merchandise news;
It is combined based on the lemma, is matched automatically in tax revenue taxonomy database, obtain the tax revenue point of the commodity
Class encodes.
Preferably, it is described to be combined based on the lemma, it is matched automatically in tax revenue taxonomy database, obtains the quotient
The tax revenue sorting code number of product, specially:
It is combined based on the lemma, is matched automatically in tax revenue taxonomy database, obtain pair of the lemma combination
The N number of tax revenue sorting code number answered;Wherein N is integer, and N >=1;
The tax revenue sorting code number of the commodity is obtained from N number of tax revenue sorting code number based on preset rules.
Preferably, it is described to obtain the commodity from N number of tax revenue sorting code number based on preset rules in N=1
Tax revenue sorting code number, specially:
1 Individual Income Tax is directly received into tax revenue sorting code number of the sorting code number as the commodity.
Preferably, it is described to obtain the quotient from N number of tax revenue sorting code number based on preset rules as the N > 1
The tax revenue sorting code number of product, specially:
The history selection percentage for characterizing each tax revenue sorting code number in N number of tax revenue sorting code number is obtained, it is N number of altogether
History selection percentage;
Based on the comparison of maximum history selection percentage and first threshold in N number of history selection percentage, determine described
The tax revenue sorting code number of commodity.
Preferably, the ratio of the maximum history selection percentage and first threshold based in N number of history selection percentage
Compared with determining the tax revenue sorting code number of the commodity, specially:
When the maximum history selection percentage in N number of history selection percentage is more than first threshold, directly by described in most
Tax revenue sorting code number of the corresponding tax revenue sorting code number of history selection percentage as the commodity greatly.
Preferably, the ratio of the maximum history selection percentage and first threshold based in N number of history selection percentage
Compared with determining the tax revenue sorting code number of the commodity, specially:
When the maximum history selection percentage in N number of history selection percentage is less than first threshold, generates and export one
For the prompt message of tax revenue sorting code number that user is prompted to select the commodity from N number of tax revenue sorting code number;
Obtain selection operation of the user based on the prompt message;
The selection operation is responded, the corresponding tax revenue point of the selection operation is determined from N number of tax revenue sorting code number
Class encodes the tax revenue sorting code number as the commodity.
Preferably, it is combined based on the lemma, is matched automatically in merchandising database, obtained identical with the commodity
The merchandise news of another commodity of classification or close classification;
It is combined described based on the lemma, is matched automatically in tax revenue taxonomy database, obtain the commodity
After tax revenue sorting code number, the method further includes:
When another commodity do not have tax revenue sorting code number, using the tax revenue sorting code number of the commodity as described another
The tax revenue sorting code number of one commodity.
Another aspect provides it is a kind of obtain commodity tax revenue sorting code number system, including:
First obtains unit, for obtaining the merchandise news of the commodity in merchandising database;
Second obtaining unit, for obtaining the corresponding lemma combination of the merchandise news;
Third obtaining unit for being based on the lemma combination, in tax revenue taxonomy database is matched, is obtained automatically
The tax revenue sorting code number of the commodity.
Preferably, the third obtaining unit includes:
First obtains subelement, for being based on the lemma combination, is matched, obtained automatically in tax revenue taxonomy database
Obtain corresponding N number of tax revenue sorting code number of the lemma combination;Wherein N is integer, and N >=1;
Second obtains subelement, for obtaining the commodity from N number of tax revenue sorting code number based on preset rules
Tax revenue sorting code number.
Preferably, in N=1, the second acquisition subelement includes:
First determining module, for 1 Individual Income Tax directly to be received tax revenue sorting code number of the sorting code number as the commodity.
Preferably, as the N > 1, the second acquisition subelement includes:
First obtains module, for obtaining to characterize each tax revenue sorting code number in N number of tax revenue sorting code number
History selection percentage, common N number of history selection percentage;
Second determining module, for based on the maximum history selection percentage and the first threshold in N number of history selection percentage
The comparison of value determines the tax revenue sorting code number of the commodity.
Preferably, second determining module includes:
First determination sub-module, for working as the maximum history selection percentage in N number of history selection percentage more than first
During threshold value, directly the corresponding tax revenue sorting code number of the maximum history selection percentage as the tax revenue of the commodity is classified and is compiled
Code.
Preferably, second determining module includes:
Prompt message generates submodule, is less than for working as the maximum history selection percentage in N number of history selection percentage
During first threshold, generate and export one for prompting user's tax revenue that the commodity are selected from N number of tax revenue sorting code number
The prompt message of sorting code number;
First obtains submodule, for obtaining selection operation of the user based on the prompt message;
Second determination sub-module for responding the selection operation, determines the choosing from N number of tax revenue sorting code number
Select the tax revenue sorting code number for operating corresponding tax revenue sorting code number as the commodity.
Preferably, the system also includes::
4th obtaining unit for being based on the lemma combination, is matched, acquisition and institute automatically in merchandising database
State the merchandise news of another commodity of commodity the same category or close classification;
First determination unit, for when another commodity do not have tax revenue sorting code number when, by the tax revenue of the commodity
Tax revenue sorting code number of the sorting code number as another commodity.
One or more embodiment provided by the invention includes at least following technique effect or advantage:The embodiment of the present invention
In by obtaining the merchandise news of the commodity in merchandising database;Obtain the corresponding lemma combination of the merchandise news;It is based on
The lemma combination, in tax revenue taxonomy database is matched, obtains the tax revenue sorting code number of the commodity automatically.Due to right
The merchandise news is segmented, and the corresponding lemma combination of the commodity is obtained, according to commodity word segmentation result i.e. word
Member combination matches commodity data;Based on matching result, sorted out according to display rule displaying commodity and suggest data.The present invention
The method and system of the tax revenue sorting code number of commodity is obtained, engine is segmented by using, high in the clouds, to commodity and information on services, tax
Contracture class keywords and illustrate etc. to be segmented, establish merchandising database and tax revenue taxonomy database;Pass through fuzzy query, craft
The methods of selection, user preference cloud computing intelligent Matching, be user's Recommendations and service corresponding tax revenue sorting code number, so as to
Solve in the prior art using acquisition commodity tax revenue sorting code number by the way of, matching accuracy is low, in match selection,
Error-prone and inconvenient, the technical issues of user's alternative duty contracture class difficulty is larger is manually participated in, has reached the tax for improving commodity
The matching accuracy of sorting code number is received, the difficulty that user obtains the tax revenue sorting code number of commodity is reduced, so as to which user be facilitated to obtain
The technique effect of tax revenue sorting code number.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments, for those of ordinary skill in the art, without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 show a kind of flow chart of the method for the tax revenue sorting code number for obtaining commodity in the embodiment of the present invention one;
Fig. 2 show a kind of schematic diagram of the system for the tax revenue sorting code number for obtaining commodity in the embodiment of the present invention two;
Fig. 3 show a kind of schematic diagram of the method for the tax revenue sorting code number for obtaining commodity in the embodiment of the present invention three.
Specific embodiment
The present invention provides a kind of method and systems for the tax revenue sorting code number for obtaining commodity, obtain in merchandising database
The merchandise news of one commodity;Obtain the corresponding lemma combination of the merchandise news;It is combined based on the lemma, in tax revenue classification number
It is matched automatically according in library, obtains the tax revenue sorting code number of the commodity.By being carried out automatically in tax revenue taxonomy database
Matching, so as to solve in the prior art using acquisition commodity tax revenue sorting code number by the way of, matching accuracy is low,
It is error-prone and inconvenient in selection, manually participating in, the technical issues of user's alternative duty contracture class difficulty is larger, reach raising
The matching accuracy of the tax revenue sorting code number of commodity reduces the difficulty that user obtains the tax revenue sorting code number of commodity, so as to convenient
User obtains the technique effect of tax revenue sorting code number.
Technical solution of the present invention is described in detail below by attached drawing and specific embodiment, it should be understood that the present invention
Embodiment is the detailed description to technical solution of the present invention, and is not limited to the technical solution, and is not being conflicted
In the case of, the technical characteristic in the embodiment of the present invention and embodiment can be combined with each other.
As shown in Figure 1, a kind of stream of the method for the tax revenue sorting code number for obtaining commodity is provided in the embodiment of the present invention one
Cheng Tu, this method include:
S101 obtains the merchandise news of the commodity in merchandising database;
S102 obtains the corresponding lemma combination of the merchandise news;
S103 is combined based on the lemma, is matched automatically in tax revenue taxonomy database, obtain the tax of the commodity
Receive sorting code number.
Specifically, for example, in step S101, the merchandise news that a commodity are obtained from merchandising database is convenient for Chef Kang
Face.Such as structure tax revenue classification intelligent Matching system, mainly including merchandise control, tax revenue Classification Management function.Wherein commercial pipes
Reason provides the functions such as merchandise news importing or access, commodity detection, intelligent Matching, preservation, recovery;Tax revenue Classification Management provides pre-
The newest tax revenue classification information issued of State General Taxation Administration is put, update, participle function are provided.To preset during environmental preparation early period
Tax revenue sorting code number, by segmenting title, keyword that engine IKAnalyzer classifies to tax revenue, illustrating etc. to have carried out point
Word.
Such as merchandise news is imported or accessed in merchandising database, merchandise control function provides merchandise news and imports work(
Can, support txt, excel file lead-in mode, importing content includes:The information such as coding, title, brevity code, commodity tax items, the tax rate.
Third-party application merchandise news interface access way is also supported in merchandise control, directly extracts merchandise news and passback tax revenue classification phase
Close field.Merchandise control is also supported to have matched the merchandise news access of tax revenue sorting code number and is imported, in txt, excel or interface
Whether the sorting code number of supplement tax revenue enjoys preferential policies, tax revenue sorting code number title, preferential policy type, zero tax rate mark, compiles
Code version number row.It is verified and is corrected by commodity detection after importing or accessing.
Specifically, S102 is, for example, to obtain " Chef Kang's instant noodles " corresponding lemma combination " Chef Kang, instant noodles ".Example
Such as, engine is segmented by high in the clouds IKAnalyzer, each merchandise news is segmented, parses all possible lemma;
Ambiguity elimination, disambiguation logic are carried out to lemma:Compare effective text size;Lack lemma more as possible;Compared with large span path;Inversely
Cutting probability is higher than positive cutting, position rearward preferential;Word length is average as possible.Choose optimal (or close) non-intersect lemma
Combination is stored in cloud database, and expand IKAnalyzer dictionaries as last solution.With the increase of user volume, by industry
It safeguards commodity library or uses more professional participle engine.
Specifically, S103 is, for example, the lemma combination " Chef Kang, instant noodles " based on acquisition, in tax revenue taxonomy database
Automatically it is matched, obtains the tax revenue sorting code number of commodity Chef Kang instant noodles.For example, intelligent that passes through tax revenue matching system
With function, a key matches the tax revenue sorting code number of commodity.Backstage is respectively to the participle of trade name, commodity, matching tax revenue classification
Title, keyword, explanation and related participle.
Above step can also obtain a plurality of merchandise news in batches, based on a plurality of merchandise news, carry out tax revenue classification respectively
The matching of coding, and the corresponding tax revenue sorting code number of a plurality of merchandise news of batch signatures.
The step S103 is preferably:
It is combined based on the lemma, is matched automatically in tax revenue taxonomy database, obtain pair of the lemma combination
The N number of tax revenue sorting code number answered;Wherein N is integer, and N >=1;
The tax revenue sorting code number of the commodity is obtained from N number of tax revenue sorting code number based on preset rules.
Specifically, previous example is continued to use, such as the combination of the lemma based on acquisition " Chef Kang, instant noodles " is in tax revenue classification number
It is matched automatically according in library, obtains lemma combination " Chef Kang, instant noodles " tax revenue sorting code number 3 corresponding
【103020303】、【106010503】、【109021403】, based on preset rules, receive in sorting code number and select from above-mentioned 3 Individual Income Tax
One tax revenue sorting code number as commodity " Chef Kang's instant noodles ".
In N=1, the tax revenue for obtaining the commodity from N number of tax revenue sorting code number based on preset rules point
Class encodes, specially:
1 Individual Income Tax is directly received into tax revenue sorting code number of the sorting code number as the commodity.
Specifically, previous example is continued to use, such as the lemma that commodity " watermelon " obtain is combined as " watermelon ", the lemma combination
It is matched automatically in tax revenue taxonomy database for " watermelon ", obtains lemma combination " watermelon " tax revenue classification 1 corresponding and compile
Code【10101150120】, then directly by the tax revenue sorting code number of 1【10101150120】Tax as the commodity " watermelon "
Receive sorting code number.
As the N > 1, the tax for obtaining the commodity from N number of tax revenue sorting code number based on preset rules
Sorting code number is received, specially:
The history selection percentage for characterizing each tax revenue sorting code number in N number of tax revenue sorting code number is obtained, it is N number of altogether
History selection percentage;
Based on the comparison of maximum history selection percentage and first threshold in N number of history selection percentage, determine described
The tax revenue sorting code number of commodity.
Specifically, previous example is continued to use, such as first threshold is 0.8, that is to say, that more than 80% user selects N number of tax
When receiving tax revenue sorting code number of some in sorting code number as this commodity, tax revenue of the coding as this commodity is selected
Sorting code number, corresponding 3 Individual Income Taxes of lemma combination of commodity " Chef Kang's instant noodles " receive sorting code number【103020303】、
【106010503】、【109021403】, it obtains to characterize the history selection percentage that this 3 Individual Income Tax receives sorting code number user, such as
【103020303】History selection percentage be 90%, that is to say, that 90% user selects【103020303】This coding is made
For the tax revenue sorting code number of commodity " Chef Kang's instant noodles ",【106010503】History selection percentage be 5%,【109021403】
5%, then maximum history selection percentage【103020303】History selection percentage be 90% with first threshold be 0.8 comparison,
Obtain the tax revenue sorting code number of commodity " Chef Kang's instant noodles ".
The comparison of the maximum history selection percentage and first threshold based in N number of history selection percentage determines
The tax revenue sorting code number of the commodity, specially:
When the maximum history selection percentage in N number of history selection percentage is more than first threshold, directly by described in most
Tax revenue sorting code number of the corresponding tax revenue sorting code number of history selection percentage as the commodity greatly.
Specifically, previous example is continued to use, for example, maximum history selection percentage【103020303】History selection percentage be
90%% is more than 0.8, then all selects 90% user【103020303】Tax revenue point as commodity " Chef Kang's instant noodles "
Class encodes, that is to say, that method of the invention has carried out machine learning.
The comparison of the maximum history selection percentage and first threshold based in N number of history selection percentage determines
The tax revenue sorting code number of the commodity, specially:
When the maximum history selection percentage in N number of history selection percentage is less than first threshold, generates and export one
For the prompt message of tax revenue sorting code number that user is prompted to select the commodity from N number of tax revenue sorting code number;
Obtain selection operation of the user based on the prompt message;
The selection operation is responded, the corresponding tax revenue point of the selection operation is determined from N number of tax revenue sorting code number
Class encodes the tax revenue sorting code number as the commodity.
Specifically, previous example is continued to use, such as first threshold is 0.8, that is to say, that more than 80% user selects N number of tax
When receiving tax revenue sorting code number of some in sorting code number as this commodity, tax revenue of the coding as this commodity is selected
Sorting code number, corresponding 3 Individual Income Taxes of lemma combination of commodity " Chef Kang's instant noodles " receive sorting code number【103020303】、
【106010503】、【109021403】, it obtains to characterize the history selection percentage that this 3 Individual Income Tax receives sorting code number user, such as
【103020303】History selection percentage be 70%, that is to say, that 70% user selects【103020303】This coding is made
For the tax revenue sorting code number of commodity " Chef Kang's instant noodles ",【106010503】History selection percentage be 25%,
【109021403】5%, then maximum history selection percentage【103020303】History selection percentage be 70% be less than the first threshold
It is 0.8 to be worth, then generates and export one for user to be prompted to select the tax revenue point of the commodity from 3 Individual Income Tax receipts sorting code number
The prompt message of class coding;Such as the receipts sorting code number of 3 Individual Income Taxes is supplied to user in the form of drop-down menu, so that user carries out
Selection;When user has selected one of tax revenue sorting code number for example to select【103020303】When, it obtains the user and is based on
The selection operation of the prompt message;The selection operation is responded, the selection behaviour is determined from N number of tax revenue sorting code number
Make corresponding tax revenue sorting code number【103020303】Tax revenue sorting code number as the commodity.Meanwhile to the selection of user into
It has gone and has remembered and learn, as the part in the history selection percentage of commodity " Chef Kang's instant noodles " this commodity.
Based on the lemma combine, matched automatically in merchandising database, obtain with the commodity the same category or
The merchandise news of another commodity of close classification;
It is combined described based on the lemma, is matched automatically in tax revenue taxonomy database, obtain the commodity
After tax revenue sorting code number, the method further includes:
When another commodity do not have tax revenue sorting code number, using the tax revenue sorting code number of the commodity as described another
The tax revenue sorting code number of one commodity.
Specifically, previous example is continued to use, such as commodity " BT910 roll toilet papers of having mutual affinity " are by aforementioned match party
Method matches tax revenue sorting code number【106010504】And it is updated in the merchandising database, and commodity " are had mutual affinity
It BT910 roll toilet papers " while is also matched in merchandising database, matches the another of the same category or close classification
Commodity such as " the special soft 3 layers of roll toilet paper of the tea family of languages of having mutual affinity row ", as user, to commodity, " the tea family of languages of having mutual affinity does not arrange
During special soft 3 layers of roll toilet paper " alternative duty contracture class coding specification, then by commodity " BT910 roll toilet papers of having mutual affinity "
Tax revenue sorting code number【106010504】As another commodity of the same category or close classification, for example " the tea family of languages of having mutual affinity arranges
The tax revenue sorting code number of special soft 3 layers of roll toilet paper ".
In addition, it is compiled when a certain commodity are not all automatically matched to tax revenue classification in tax revenue taxonomy database and merchandising database
When code does not recommend tax revenue sorting code number yet, when user has been by hand the commodity selection or has been added to tax revenue sorting code number,
Match system automatically learns the selection of user or addition, and the next tax revenue sorting code number matching for the commodity is prepared.And
The present invention carries commodity tax receipts sorting code number after supporting the matching and matching of the tax revenue sorting code number of the merchandise news of batch
The batch signatures of merchandise news.
As shown in Fig. 2, the embodiment of the present invention two provides a kind of system for the tax revenue sorting code number for obtaining commodity, packet
It includes:
First obtains unit 101, for obtaining the merchandise news of the commodity in merchandising database;
Second obtaining unit 102, for obtaining the corresponding lemma combination of the merchandise news;
Third obtaining unit 103 for being based on the lemma combination, is matched automatically in tax revenue taxonomy database,
Obtain the tax revenue sorting code number of the commodity.
Specifically, for example, first obtains unit 101, is health for obtaining the merchandise news of a commodity from merchandising database
Master worker's instant noodles.Such as the tax revenue classification intelligent Matching system that the system of the tax revenue sorting code number for obtaining commodity is structure,
Mainly include merchandise control, tax revenue Classification Management function.Wherein merchandise control provides merchandise news importing or access, commodity inspection
The functions such as survey, intelligent Matching, preservation, recovery;Tax revenue Classification Management provides preset State General Taxation Administration the newest tax revenue classification letter issued
Breath, provides update, participle function.To preset tax revenue sorting code number during environmental preparation early period, by segmenting engine
Title that IKAnalyzer classifies to tax revenue, keyword illustrate etc. to be segmented.
Such as merchandise news is imported or accessed in merchandising database, merchandise control function provides merchandise news and imports work(
Can, support txt, excel file lead-in mode, importing content includes:The information such as coding, title, brevity code, commodity tax items, the tax rate.
Third-party application merchandise news interface access way is also supported in merchandise control, directly extracts merchandise news and passback tax revenue classification phase
Close field.Merchandise control is also supported to have matched the merchandise news access of tax revenue sorting code number and is imported, in txt, excel or interface
Whether the sorting code number of supplement tax revenue enjoys preferential policies, tax revenue sorting code number title, preferential policy type, zero tax rate mark, compiles
Code version number row.It is verified and is corrected by commodity detection after importing or accessing.
Specifically, the second obtaining unit 102, for obtaining the corresponding lemma combination of the merchandise news, for example, obtains
" Chef Kang's instant noodles " corresponding lemma combination " Chef Kang, instant noodles ".For example, the second obtaining unit 102 is high in the clouds
IKAnalyzer segments engine, segments engine by high in the clouds IKAnalyzer, each merchandise news is segmented, is parsed
All possible lemma;Ambiguity elimination, disambiguation logic are carried out to lemma:Compare effective text size;Lack lemma more as possible;Compared with
Large span path;Reverse cutting probability is higher than positive cutting, position rearward preferential;Word length is average as possible.Choose optimal (or connect
The combination of closely) non-intersect lemma is stored in cloud database, and expand IKAnalyzer dictionaries as last solution.With user
The increase of amount safeguards commodity library by industry or uses more professional participle engine.
Specifically, third obtaining unit 103, for being based on the lemma combination, in tax revenue taxonomy database automatically into
Row matching obtains the tax revenue sorting code number of the commodity, such as lemma combination " Kang Shi of the third obtaining unit 103 based on acquisition
Fu, instant noodles " are matched automatically in tax revenue taxonomy database, obtain the tax revenue sorting code number of commodity Chef Kang instant noodles.
For example, by the intelligent Matching function of tax revenue matching system, a key matches the tax revenue sorting code number of commodity.Backstage is respectively to commodity
The participle of title, commodity, matching tax revenue specific name, keyword, explanation and related participle.
Above step can also obtain a plurality of merchandise news in batches, based on a plurality of merchandise news, carry out tax revenue classification respectively
The matching of coding, and the corresponding tax revenue sorting code number of a plurality of merchandise news of batch signatures.
The third obtaining unit includes:
First obtains subelement, for being based on the lemma combination, is matched, obtained automatically in tax revenue taxonomy database
Obtain corresponding N number of tax revenue sorting code number of the lemma combination;Wherein N is integer, and N >=1;
Second obtains subelement, for obtaining the commodity from N number of tax revenue sorting code number based on preset rules
Tax revenue sorting code number.
Specifically, continue to use previous example, such as first obtains lemma combination " Chef Kang, conveniently of the subelement based on acquisition
Face " is matched automatically in tax revenue taxonomy database, obtains lemma combination " Chef Kang, instant noodles " tax revenue 3 corresponding point
Class encodes【103020303】、【106010503】、【109021403】, second obtains subelement, for being based on preset rules, from
Above-mentioned 3 Individual Income Tax is received in sorting code number and selects a tax revenue sorting code number as commodity " Chef Kang's instant noodles ".
In N=1, the second acquisition subelement includes:
First determining module, for 1 Individual Income Tax directly to be received tax revenue sorting code number of the sorting code number as the commodity.
Specifically, previous example is continued to use, such as the lemma that commodity " watermelon " obtain is combined as " watermelon ", the lemma combination
It is matched automatically in tax revenue taxonomy database for " watermelon ", obtains lemma combination " watermelon " tax revenue classification 1 corresponding and compile
Code【10101150120】, then the first determining module is directly by the tax revenue sorting code number of 1【10101150120】As the quotient
The tax revenue sorting code number of product " watermelon ".
As the N > 1, the second acquisition subelement includes:
First obtains module, for obtaining to characterize each tax revenue sorting code number in N number of tax revenue sorting code number
History selection percentage, common N number of history selection percentage;
Second determining module, for based on the maximum history selection percentage and the first threshold in N number of history selection percentage
The comparison of value determines the tax revenue sorting code number of the commodity.
Specifically, previous example is continued to use, such as first threshold is 0.8, that is to say, that more than 80% user selects N number of tax
When receiving tax revenue sorting code number of some in sorting code number as this commodity, tax revenue of the coding as this commodity is selected
Sorting code number, corresponding 3 Individual Income Taxes of lemma combination of commodity " Chef Kang's instant noodles " receive sorting code number【103020303】、
【106010503】、【109021403】, first obtains module, obtains to characterize the history that this 3 Individual Income Tax receives sorting code number user
Selection percentage, such as【103020303】History selection percentage be 90%, that is to say, that 90% user selects
【103020303】Tax revenue sorting code number of this coding as commodity " Chef Kang's instant noodles ",【106010503】History selection
Ratio is 5%,【109021403】It is 5%;Then the second determining module, based on maximum history selection percentage【103020303】Go through
History selection percentage is 90% and the comparison that first threshold is 0.8, obtains the tax revenue sorting code number of commodity " Chef Kang's instant noodles ".
Second determining module includes:
First determination sub-module, for working as the maximum history selection percentage in N number of history selection percentage more than first
During threshold value, directly the corresponding tax revenue sorting code number of the maximum history selection percentage as the tax revenue of the commodity is classified and is compiled
Code.
Specifically, previous example is continued to use, for example, maximum history selection percentage【103020303】History selection percentage be
90% is more than 0.8, then the first determination sub-module all selects 90% user【103020303】As commodity " Chef Kang side
The tax revenue sorting code number in just face ", that is to say, that method of the invention has carried out machine learning.
Second determining module includes:
Prompt message generates submodule, is less than for working as the maximum history selection percentage in N number of history selection percentage
During first threshold, generate and export one for prompting user's tax revenue that the commodity are selected from N number of tax revenue sorting code number
The prompt message of sorting code number;
First obtains submodule, for obtaining selection operation of the user based on the prompt message;
Second determination sub-module for responding the selection operation, determines the choosing from N number of tax revenue sorting code number
Select the tax revenue sorting code number for operating corresponding tax revenue sorting code number as the commodity.
Specifically, previous example is continued to use, such as first threshold is 0.8, that is to say, that more than 80% user selects N number of tax
When receiving tax revenue sorting code number of some in sorting code number as this commodity, tax revenue of the coding as this commodity is selected
Sorting code number, corresponding 3 Individual Income Taxes of lemma combination of commodity " Chef Kang's instant noodles " receive sorting code number【103020303】、
【106010503】、【109021403】, it obtains to characterize the history selection percentage that this 3 Individual Income Tax receives sorting code number user, such as
【103020303】History selection percentage be 70%, that is to say, that 70% user selects【103020303】This coding is made
For the tax revenue sorting code number of commodity " Chef Kang's instant noodles ",【106010503】History selection percentage be 25%,
【109021403】5%, then maximum history selection percentage【103020303】History selection percentage be 70% be less than the first threshold
It is 0.8 to be worth, then prompt message generation submodule generates and exports one and selected for user to be prompted to be received in sorting code number from 3 Individual Income Tax
Select the prompt message of the tax revenue sorting code number of the commodity;Such as the receipts sorting code number of 3 Individual Income Taxes is provided in the form of drop-down menu
To user, so that user is selected;When user has selected one of tax revenue sorting code number for example to select【103020303】
When, first, which obtains submodule, obtains the selection operation of the user based on the prompt message;Second determination sub-module responds institute
Selection operation is stated, the corresponding tax revenue sorting code number of the selection operation is determined from N number of tax revenue sorting code number
【103020303】Tax revenue sorting code number as the commodity.Meanwhile the selection of user is remembered and learnt, as
A part in the history selection percentage of commodity " Chef Kang's instant noodles " this commodity.
4th obtaining unit for being based on the lemma combination, is matched, acquisition and institute automatically in merchandising database
State the merchandise news of another commodity of commodity the same category or close classification;
First determination unit, for when another commodity do not have tax revenue sorting code number when, by the tax revenue of the commodity
Tax revenue sorting code number of the sorting code number as another commodity.
Specifically, previous example is continued to use, such as commodity " BT910 roll toilet papers of having mutual affinity " are by aforementioned match party
Method matches tax revenue sorting code number【106010504】And it is updated in the merchandising database, and the 4th obtaining unit
The lemma of commodity " BT910 roll toilet papers of having mutual affinity " is combined and is matched in merchandising database, is matched identical
Another commodity of classification or close classification such as " the tea family of languages of having mutual affinity row special soft 3 layers of roll toilet paper ", when user without pair
During commodity " the tea family of languages of having mutual affinity row special soft 3 layers of roll toilet paper " alternative duty contracture class coding specification, then the first determination unit
By the tax revenue sorting code number of commodity " BT910 roll toilet papers of having mutual affinity "【106010504】As the same category or close class
The tax revenue sorting code number of other another commodity such as " the special soft 3 layers of roll toilet paper of the tea family of languages of having mutual affinity row ".
In addition, it is compiled when a certain commodity are not all automatically matched to tax revenue classification in tax revenue taxonomy database and merchandising database
When code does not recommend tax revenue sorting code number yet, when user has been by hand the commodity selection or has been added to tax revenue sorting code number,
Match system carries out cloud computing to the selection of user or addition (user preference) automatically, the preference including storing all users, by row
Industry, a variety of dimensions such as by type calculate analysis preference temperatures, and same or similar commodity, intelligent recommendation matching are used for subsequent user
Tax revenue classification.And carry commodity tax after the matching and matching of the tax revenue sorting code number of the merchandise news of present invention support batch
Receive the batch signatures of the merchandise news of sorting code number.
The third embodiment of the present invention provides a kind of method and system for the tax revenue sorting code number for obtaining commodity, method stream
Journey figure can be found in Fig. 3, including:
Build tax revenue classification intelligent Matching system;
S201 imports or accesses merchandise news;Merchandise news import feature is provided, supports txt, excel file importing side
Formula, importing content include:The information such as coding, title, brevity code, commodity tax items, the tax rate.
Third-party application merchandise news interface access way is also supported in merchandise control, directly extracts merchandise news and passback tax
Contracture class relevant field.
Merchandise control is also supported to have matched the merchandise news access of tax revenue sorting code number and be imported, txt, excel or interface
Middle supplement tax revenue sorting code number, whether enjoy preferential policies, tax revenue sorting code number title, preferential policy type, zero tax rate mark,
Version of code number arranges.It is verified and is corrected by commodity detection after importing or accessing.
S202, merchandise news detection obtain lemma combination;Engine is segmented by high in the clouds IKAnalyzer, to each quotient
Product information is segmented, and parses all possible lemma, is obtained lemma combination or is used more professional participle engine.Pass through
High in the clouds IKAnalyzer segments engine, and each merchandise news is segmented.
Ambiguity elimination, disambiguation logic are carried out to lemma:Compare effective text size;Lack lemma more as possible;Compared with large span
Path;Reverse cutting probability is higher than positive cutting, position rearward preferential;Word length is average as possible.
The combination of optimal (or close) non-intersect lemma is chosen as last solution, is stored in cloud database, and expand
IKAnalyzer dictionaries.With the increase of user volume, safeguard commodity library by industry or use more professional participle engine.
S203, key matching, passes through【Intelligent Matching】Function, a key match the tax revenue sorting code number of commodity.Backstage is respectively
To the participle of trade name, commodity, matching tax revenue specific name, keyword, explanation and related participle.
Matching logic:By the maximum matching-Keywords matching-synonym matching of complete match-Forward Maximum Method-reversely-
The matched sequence of near synonym one by one batch.
Matching result:
It directly displays:One-to-one match condition directly recommends display;
Intelligent recommendation:One-to-many matching situation, cloud service are intelligently pushed away according to the preference of all user's alternative duty contracture classes
It recommends;
Temperature highest:More than 80% user's selection, then directly recommend, directly display.
Temperature is general:User's selection less than 80%, then multi-option recommendation, enumerates display.
Temperature is relatively low:User's selection less than 10%, then prompt user to select by hand.
Result above supports manual error correction.
Selection by hand:Without matching result situation, the suitable tax revenue sorting code number of commodity is selected by hand.
Cloud computing is carried out to user preference (result selected by hand), includes the preference of all users of storage, by industry,
A variety of dimensions calculate analysis preference temperatures by type etc., are subsequent user using same or similar commodity, and intelligent recommendation is matched
Tax revenue is classified.
S204, as a result export or third party's passback
Matching result call file export or third party software interface pass back to user and make out an invoice in basis of software data, in case
It makes out an invoice use.
Export or passback content:Whether commodity code trade name, tax revenue sorting code number, enjoys preferential policies, tax revenue point
Class encoding name, preferential policy type, zero tax rate mark, version of code number etc..
For example, providing a kind of commodity based on cloud computing and tax revenue classification intelligent Matching method, one is illustrated completely
Recommendation process is matched, is specifically included:
Quotient surpasses enterprise customer and gives goods matching tax revenue sorting code number, in case use of making out an invoice.Such as watermelon, Chef Kang are conveniently
Face, Sprite 600ml, BT910 roll toilet papers of having mutual affinity.
User imports merchandise news in intelligent Matching system, clicks key matching button, and matching process is as shown in table 1:
Table 1
It after whole successful match, can export, interface write-back third party software can be passed through.
The present invention provides a kind of method and systems for the tax revenue sorting code number for obtaining commodity, obtain in merchandising database
The merchandise news of one commodity;Obtain the corresponding lemma combination of the merchandise news;It is combined based on the lemma, in tax revenue classification number
It is matched automatically according in library, obtains the tax revenue sorting code number of the commodity.By being carried out automatically in tax revenue taxonomy database
Matching, so as to solve in the prior art using acquisition commodity tax revenue sorting code number by the way of, matching accuracy is low,
It is error-prone and inconvenient in selection, manually participating in, the technical issues of user's alternative duty contracture class difficulty is larger, reach raising
The matching accuracy of the tax revenue sorting code number of commodity reduces the difficulty that user obtains the tax revenue sorting code number of commodity, so as to convenient
User obtains the technique effect of tax revenue sorting code number.And a kind of method of tax revenue sorting code number for obtaining commodity provided by the invention
With system by adopting the above-described technical solution, also having reached the increase with user volume, the probability selected by hand is less and less,
Accuracy also higher and higher technique effect.
Finally it should be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that:It still may be used
To modify to the technical solution recorded in foregoing embodiments or carry out equivalent replacement to which part technical characteristic;
And these modification or replace, various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (14)
- A kind of 1. method for the tax revenue sorting code number for obtaining commodity, which is characterized in that including:Obtain the merchandise news of the commodity in merchandising database;Obtain the corresponding lemma combination of the merchandise news;It is combined based on the lemma, is matched automatically in tax revenue taxonomy database, the tax revenue classification for obtaining the commodity is compiled Code.
- 2. according to the method described in claim 1, it is characterized in that, described combined based on the lemma, in tax revenue grouped data It is matched automatically in library, obtains the tax revenue sorting code number of the commodity, specially:It is combined based on the lemma, is matched automatically in tax revenue taxonomy database, obtain the corresponding N of the lemma combination Individual Income Tax receives sorting code number;Wherein N is integer, and N >=1;The tax revenue sorting code number of the commodity is obtained from N number of tax revenue sorting code number based on preset rules.
- 3. according to the method described in claim 2, it is characterized in that, in N=1, the preset rules that are based on are from N number of tax The tax revenue sorting code number that the commodity are obtained in sorting code number is received, specially:1 Individual Income Tax is directly received into tax revenue sorting code number of the sorting code number as the commodity.
- 4. according to the method described in claim 2, it is characterized in that, as the N > 1, the preset rules that are based on are from the N Individual Income Tax receives the tax revenue sorting code number that the commodity are obtained in sorting code number, specially:The history selection percentage for characterizing each tax revenue sorting code number in N number of tax revenue sorting code number is obtained, altogether N number of history Selection percentage;Based on the comparison of maximum history selection percentage and first threshold in N number of history selection percentage, the commodity are determined Tax revenue sorting code number.
- 5. the according to the method described in claim 4, it is characterized in that, maximum based in N number of history selection percentage The comparison of history selection percentage and first threshold determines the tax revenue sorting code number of the commodity, specially:When the maximum history selection percentage in N number of history selection percentage is more than first threshold, the most great calendar directly by described in Tax revenue sorting code number of the corresponding tax revenue sorting code number of history selection percentage as the commodity.
- 6. the according to the method described in claim 4, it is characterized in that, maximum based in N number of history selection percentage The comparison of history selection percentage and first threshold determines the tax revenue sorting code number of the commodity, specially:When the maximum history selection percentage in N number of history selection percentage is less than first threshold, generates and export one and be used for Prompting user selects the prompt message of the tax revenue sorting code number of the commodity from N number of tax revenue sorting code number;Obtain selection operation of the user based on the prompt message;The selection operation is responded, determines that the corresponding tax revenue classification of the selection operation is compiled from N number of tax revenue sorting code number Tax revenue sorting code number of the code as the commodity.
- 7. according to the method described in claim 1, it is characterized in that:It is combined based on the lemma, it is automatic in merchandising database It is matched, obtains the merchandise news of another commodity with the commodity the same category or close classification;It is combined described based on the lemma, is matched automatically in tax revenue taxonomy database, obtain the tax revenue of the commodity After sorting code number, the method further includes:When another commodity do not have tax revenue sorting code number, using the tax revenue sorting code number of the commodity as another quotient The tax revenue sorting code number of product.
- 8. a kind of system for the tax revenue sorting code number for obtaining commodity, which is characterized in that including:First obtains unit, for obtaining the merchandise news of the commodity in merchandising database;Second obtaining unit, for obtaining the corresponding lemma combination of the merchandise news;Third obtaining unit for being based on the lemma combination, is matched, described in acquisition automatically in tax revenue taxonomy database The tax revenue sorting code number of commodity.
- 9. system according to claim 8, which is characterized in that the third obtaining unit includes:First obtains subelement, for being based on the lemma combination, is matched automatically in tax revenue taxonomy database, obtains institute Corresponding N number of tax revenue sorting code number of predicate member combination;Wherein N is integer, and N >=1;Second obtains subelement, for obtaining the tax revenue of the commodity from N number of tax revenue sorting code number based on preset rules Sorting code number.
- 10. system according to claim 9, which is characterized in that in N=1, the second acquisition subelement includes:First determining module, for 1 Individual Income Tax directly to be received tax revenue sorting code number of the sorting code number as the commodity.
- 11. system according to claim 9, which is characterized in that as the N > 1, described second obtains subelement packet It includes:First obtains module, for obtaining the history for characterizing each tax revenue sorting code number in N number of tax revenue sorting code number Selection percentage, common N number of history selection percentage;Second determining module, for based on the maximum history selection percentage in N number of history selection percentage and first threshold Compare, determine the tax revenue sorting code number of the commodity.
- 12. system according to claim 10, which is characterized in that second determining module includes:First determination sub-module, for working as the maximum history selection percentage in N number of history selection percentage more than first threshold When, directly using the corresponding tax revenue sorting code number of the maximum history selection percentage as the tax revenue sorting code number of the commodity.
- 13. system according to claim 10, which is characterized in that second determining module includes:Prompt message generates submodule, for working as the maximum history selection percentage in N number of history selection percentage less than first During threshold value, generate and export one for user to be prompted the tax revenue of the commodity to be selected to classify from N number of tax revenue sorting code number The prompt message of coding;First obtains submodule, for obtaining selection operation of the user based on the prompt message;Second determination sub-module for responding the selection operation, determines the selection behaviour from N number of tax revenue sorting code number Make tax revenue sorting code number of the corresponding tax revenue sorting code number as the commodity.
- 14. system according to claim 8, which is characterized in that the system also includes::4th obtaining unit for being based on the lemma combination, in merchandising database is matched, is obtained and the quotient automatically Condition is generic or the merchandise news of another commodity of close classification;First determination unit, for when another commodity do not have tax revenue sorting code number, the tax revenue of the commodity to be classified Encode the tax revenue sorting code number as another commodity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611219407.9A CN108241677A (en) | 2016-12-26 | 2016-12-26 | A kind of method and system for the tax revenue sorting code number for obtaining commodity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611219407.9A CN108241677A (en) | 2016-12-26 | 2016-12-26 | A kind of method and system for the tax revenue sorting code number for obtaining commodity |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108241677A true CN108241677A (en) | 2018-07-03 |
Family
ID=62701788
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611219407.9A Pending CN108241677A (en) | 2016-12-26 | 2016-12-26 | A kind of method and system for the tax revenue sorting code number for obtaining commodity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108241677A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109766440A (en) * | 2018-12-17 | 2019-05-17 | 航天信息股份有限公司 | A kind of method and system for for the determining default categories information of object text description |
CN109785099A (en) * | 2018-12-27 | 2019-05-21 | 大象慧云信息技术有限公司 | A kind of method and system that service data information is handled automatically |
CN109801149A (en) * | 2018-12-20 | 2019-05-24 | 航天信息股份有限公司 | The method for creating tax return, device, storage medium and electronic equipment |
CN109949113A (en) * | 2019-03-21 | 2019-06-28 | 南京金信通信息服务有限公司 | A kind of VAT invoice online management system |
CN110287218A (en) * | 2019-06-26 | 2019-09-27 | 浙江诺诺网络科技有限公司 | A kind of matched method of tax revenue sorting code number, system and equipment |
CN110377801A (en) * | 2019-07-24 | 2019-10-25 | 浙江诺诺网络科技有限公司 | A kind of product name bearing calibration, device and computer readable storage medium |
CN110457291A (en) * | 2019-07-18 | 2019-11-15 | 重庆智荟数创科技有限公司 | A kind of enterprise practical operation and the associated algorithm of trademark class and device |
CN110851587A (en) * | 2018-07-25 | 2020-02-28 | 阿里巴巴集团控股有限公司 | Commodity code prediction model generation and commodity code determining method, device and equipment |
CN111401977A (en) * | 2018-12-28 | 2020-07-10 | 航天信息股份有限公司 | Tax classification code determining method and device |
CN112348604A (en) * | 2020-11-26 | 2021-02-09 | 税友软件集团股份有限公司 | Invoice commodity code assignment method, system and device and readable 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 |
CN113065935A (en) * | 2019-12-27 | 2021-07-02 | 航天信息股份有限公司 | Data processing method, device, equipment and storage medium |
CN113157918A (en) * | 2021-03-23 | 2021-07-23 | 浙江工业大学 | Commodity name short text classification method and system based on attention mechanism |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101118465A (en) * | 2007-09-03 | 2008-02-06 | 陆庆方 | Digitization inputting and words information using novel scheme |
CN103605815A (en) * | 2013-12-11 | 2014-02-26 | 焦点科技股份有限公司 | Automatic commodity information classifying and recommending method applicable to B2B (Business to Business) e-commerce platform |
CN105117426A (en) * | 2015-07-31 | 2015-12-02 | 重庆龙工场跨境电子商务投资有限公司 | Intelligent search system for HSCODE |
CN105354194A (en) * | 2014-08-19 | 2016-02-24 | 上海中怡通信息科技有限公司 | Intelligent commodity classifying method and system |
CN106095759A (en) * | 2016-06-20 | 2016-11-09 | 西安交通大学 | A kind of invoice goods classifying method based on heuristic rule |
-
2016
- 2016-12-26 CN CN201611219407.9A patent/CN108241677A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101118465A (en) * | 2007-09-03 | 2008-02-06 | 陆庆方 | Digitization inputting and words information using novel scheme |
CN103605815A (en) * | 2013-12-11 | 2014-02-26 | 焦点科技股份有限公司 | Automatic commodity information classifying and recommending method applicable to B2B (Business to Business) e-commerce platform |
CN105354194A (en) * | 2014-08-19 | 2016-02-24 | 上海中怡通信息科技有限公司 | Intelligent commodity classifying method and system |
CN105117426A (en) * | 2015-07-31 | 2015-12-02 | 重庆龙工场跨境电子商务投资有限公司 | Intelligent search system for HSCODE |
CN106095759A (en) * | 2016-06-20 | 2016-11-09 | 西安交通大学 | A kind of invoice goods classifying method based on heuristic rule |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110851587A (en) * | 2018-07-25 | 2020-02-28 | 阿里巴巴集团控股有限公司 | Commodity code prediction model generation and commodity code determining method, device and equipment |
CN110851587B (en) * | 2018-07-25 | 2024-04-05 | 阿里巴巴集团控股有限公司 | Commodity coding prediction model generation and commodity coding determination method, device and equipment |
CN109766440B (en) * | 2018-12-17 | 2023-09-01 | 航天信息股份有限公司 | Method and system for determining default classification information for object text description |
CN109766440A (en) * | 2018-12-17 | 2019-05-17 | 航天信息股份有限公司 | A kind of method and system for for the determining default categories information of object text description |
CN109801149A (en) * | 2018-12-20 | 2019-05-24 | 航天信息股份有限公司 | The method for creating tax return, device, storage medium and electronic equipment |
CN109785099A (en) * | 2018-12-27 | 2019-05-21 | 大象慧云信息技术有限公司 | A kind of method and system that service data information is handled automatically |
CN109785099B (en) * | 2018-12-27 | 2021-07-06 | 大象慧云信息技术有限公司 | Method and system for automatically processing service data information |
CN111401977A (en) * | 2018-12-28 | 2020-07-10 | 航天信息股份有限公司 | Tax classification code determining method and device |
CN109949113A (en) * | 2019-03-21 | 2019-06-28 | 南京金信通信息服务有限公司 | A kind of VAT invoice online management system |
CN110287218A (en) * | 2019-06-26 | 2019-09-27 | 浙江诺诺网络科技有限公司 | A kind of matched method of tax revenue sorting code number, system and equipment |
CN110457291A (en) * | 2019-07-18 | 2019-11-15 | 重庆智荟数创科技有限公司 | A kind of enterprise practical operation and the associated algorithm of trademark class and device |
CN110457291B (en) * | 2019-07-18 | 2022-05-10 | 重庆智荟数创科技有限公司 | Algorithm and device for associating actual business of enterprise with trademark category |
CN110377801A (en) * | 2019-07-24 | 2019-10-25 | 浙江诺诺网络科技有限公司 | A kind of product name bearing calibration, device and computer readable storage medium |
CN113065935A (en) * | 2019-12-27 | 2021-07-02 | 航天信息股份有限公司 | Data processing method, device, equipment and storage medium |
CN112348604A (en) * | 2020-11-26 | 2021-02-09 | 税友软件集团股份有限公司 | Invoice commodity code assignment method, system and device and readable storage medium |
CN112348604B (en) * | 2020-11-26 | 2023-11-17 | 税友软件集团股份有限公司 | Invoice commodity code assignment method, system, device and readable 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 |
CN113157918A (en) * | 2021-03-23 | 2021-07-23 | 浙江工业大学 | Commodity name short text classification method and system based on attention mechanism |
CN113157918B (en) * | 2021-03-23 | 2022-07-22 | 浙江工业大学 | Commodity name short text classification method and system based on attention mechanism |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108241677A (en) | A kind of method and system for the tax revenue sorting code number for obtaining commodity | |
US11704325B2 (en) | Systems and methods for automatic clustering and canonical designation of related data in various data structures | |
US11562129B2 (en) | Adding machine understanding on spreadsheets data | |
CN110609902B (en) | Text processing method and device based on fusion knowledge graph | |
US20190057421A1 (en) | Visualization of Reputation Ratings | |
CN103748579B (en) | Data are handled in MapReduce frame | |
WO2017079224A1 (en) | Rich data types | |
US20240126815A1 (en) | Data Preparation Using Semantic Roles | |
CN114817553A (en) | Knowledge graph construction method, knowledge graph construction system and computing equipment | |
US12008047B2 (en) | Providing an object-based response to a natural language query | |
CN114860916A (en) | Knowledge retrieval method and device | |
CN106469182A (en) | A kind of information recommendation method based on mapping relations and device | |
CN111160699A (en) | Expert recommendation method and system | |
US20210216708A1 (en) | System and method for identifying sentiment in text strings | |
CN106844365A (en) | The application message method for pushing and device of a kind of application distribution platform | |
US9619458B2 (en) | System and method for phrase matching with arbitrary text | |
US20180246901A1 (en) | Suggesting query items based on database fields | |
CN106294875A (en) | A kind of name entity fuzzy retrieval method and system | |
Han et al. | Developing smart service concepts: morphological analysis using a Novelty-Quality map | |
WO2023159766A1 (en) | Catering data analysis method and apparatus, and electronic device and storage medium | |
CN112052656A (en) | Recommending topic patterns for documents | |
CN110287218A (en) | A kind of matched method of tax revenue sorting code number, system and equipment | |
CN114564914A (en) | Table data display method and device, electronic equipment and medium | |
US20160019204A1 (en) | Matching large sets of words | |
Daniel et al. | Developing a new multidimensional model for selecting strategic plans in balanced scorecard |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180703 |
|
RJ01 | Rejection of invention patent application after publication |