CN110083678A - A kind of electric business platform goods matching method, device and readable storage medium storing program for executing - Google Patents
A kind of electric business platform goods matching method, device and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN110083678A CN110083678A CN201910191090.XA CN201910191090A CN110083678A CN 110083678 A CN110083678 A CN 110083678A CN 201910191090 A CN201910191090 A CN 201910191090A CN 110083678 A CN110083678 A CN 110083678A
- Authority
- CN
- China
- Prior art keywords
- commodity
- label
- word
- combination
- classification
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- 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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0629—Directed, with specific intent or strategy for generating comparisons
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a kind of electric business platform goods matching method, device and readable storage medium storing program for executing, this method comprises: the corresponding label word corpus of each commodity classification on electric business platform is obtained respectively, wherein the label word corpus includes at least one label word corresponding with the commodity classification;According to the label word corpus corresponding with the commodity classification belonging to commodity on the electric business platform, the corresponding commodity key message combination of the commodity is obtained from the title of the commodity;The commodity key message corresponding with the commodity is combined and carries out screening and standardization, obtains the corresponding standard label combination of the commodity;The matching probability between combining with corresponding two standard label of commodity described in any two in the same commodity classification is calculated, when the matching probability is greater than preset matching probability threshold value, determines that two commodity are identical commodity.This programme can be improved the efficiency of electric business platform goods matching.
Description
Technical field
The present invention relates to technical field of electronic commerce more particularly to a kind of electric business platform goods matching methods, device and can
Read storage medium.
Background technique
B2B be between the abbreviation, in particular to enterprise and enterprise of Business-to-Business by dedicated network or
Internet carries out the exchange of data information, transmitting, to carry out the business model of transaction.Some conglomerates for the ease of
The procurement of commodities process of each subsidiary/member companies is managed collectively, conglomerate constructs personal B2B platform, and supplier is in B2B
Publishing commodity on platform, each subsidiary/member companies buys commodity from B2B platform in conglomerate.
Supplier can be with customized commodity title in publishing commodity on B2B platform, this will lead to different suppliers to same
One commodity define the appearance of the case where different commodity titles.At the same time, in order to reduce the buying of each subsidiary/member companies, conglomerate
Cost, platform operation personnel need to filter out the lower supplier of price for identical commodity.Since different suppliers are to same
One commodity define different commodity titles, and platform operation personnel can not determine whether two commodity are identical by commodity title
Commodity, platform operation personnel need to determine whether two commodity are identical by way of manually checking commodity detail thus
Commodity.
For the method that current B2B platform matches identical commodity, since platform operation personnel need to check each respectively
For the detail of commodity to match identical commodity, this will expend the platform operation personnel more time, lead to the efficiency of goods matching
It is lower.
Summary of the invention
The present invention provides a kind of electric business platform goods matching method, device and readable storage medium storing program for executing, main purpose and is
Acquisition includes the label word corpus of multiple label words, and then is segmented according to label word corpus to commodity title, is led to
Cross the keyword that participle obtains is matched, screen and standardization after obtain standard label word, and then corresponded to
Each commodity include multiple standard label words standard label combination, by comparing the corresponding standard label of two commodity
Combination is to determine whether two commodity are identical commodity, the detail without each commodity of platform operation personnel's artificial enquiry
To determine whether two commodity are identical commodity, the efficiency of electric business platform goods matching is improved.
In a first aspect, the embodiment of the invention provides a kind of electric business platform goods matching methods, comprising:
The corresponding label word corpus of each commodity classification on electric business platform is obtained respectively, wherein the label word material
Library includes at least one label word corresponding with the commodity classification;
According to the label word corpus corresponding with the commodity classification belonging to commodity on the electric business platform, from
The corresponding commodity key message combination of the commodity is obtained in the title of the commodity;
The commodity key message corresponding with the commodity is combined and carries out screening and standardization, described in acquisition
The corresponding standard label combination of commodity;
It calculates and combines it with corresponding two standard label of commodity described in any two in the same commodity classification
Between matching probability, the matching probability be greater than preset matching probability threshold value when, determine two commodity be it is identical
Commodity.
It is optionally, described to obtain the corresponding label word corpus of each commodity classification on electric business platform respectively, comprising:
For each commodity classification on the electric business platform, the electric business for having constructed Commercial goods labels word from least one is flat
The corresponding label word of the commodity classification is acquired on platform, using at least one collected described label contamination as with the commodity
The corresponding label word corpus of classification, wherein the label word includes the brand of commodity, the place of production, packaging, specification, grade, adds
At least one of work technique and qualification certification.
Optionally, described according to the label corresponding with the commodity classification belonging to commodity on the electric business platform
Word corpus obtains the corresponding commodity key message combination of the commodity from the title of the commodity, comprising:
S1: end article classification belonging to commodity on the electric business level is determined;
S2: the title of the commodity is determined as corpus to be slit;
S3: it is long that setting cutting length is equal to preset most major term;
S4: target segmenting word of the length equal to the cutting length is taken by forward direction from the corpus to be slit;
S5: by the label word in target segmenting word target labels word corpus corresponding with the end article classification
It is matched, if successful match executes S6, otherwise executes S8;
S6: the target segmenting word is determined as a keyword;
S7: it is determined as the corpus to be slit for the remainder after the keyword is removed in the title of the commodity
After execute S4;
S8: it if the cutting length is greater than two characters, is held after the cutting length is reduced by least two bytes
Row S4 is executed after removing two characters on the head of the corpus to be slit if the cutting length is equal to two characters
S3;
S9: it is combined using each crucial contamination as the corresponding commodity key message of the commodity.
Optionally, described combine to the commodity key message corresponding with the commodity carries out at screening and standardization
Reason obtains the corresponding standard label combination of the commodity, comprising:
According to preset concern message catalog, the commodity key message combination corresponding to the commodity includes
Each keyword is screened, and will meet the crucial contamination of the concern message catalog as the commodity pair
The Commercial goods labels combination answered;
It is each in the Commercial goods labels combination corresponding to the commodity according to preset label word transformation rule
A keyword formats respectively, obtains corresponding standard label word;
Using each standard label contamination as the corresponding standard label combination of the commodity.
Optionally, after the corresponding standard label combination of the acquisition commodity, further comprise:
For each described commodity classification on the electric business platform, the commodity class will be belonged on the electric business platform
The corresponding standard label combination of each commodity of purpose is stored by column, wherein first row stores the commodity
Coding, secondary series store the corresponding standard label of the commodity and combine the standard label word for including.
Optionally, described to calculate two standards corresponding with commodity described in any two in the same commodity classification
Matching probability between tag combination, comprising:
By the mark in the corresponding standard label combination of commodity described in any two in the same commodity classification
Fiducial mark label word is compared, and determines the standard label word shared in the corresponding standard label combination of two commodity
Number, and calculate by following formula the matching probability of the corresponding standard label combination of two commodity;
Wherein, the P characterizes the matching probability of the corresponding standard label combination of two commodity, the M characterization
The number of the standard label word shared in the corresponding standard label combination of two commodity, the M1With the M2
The number of standard label word described in the corresponding standard label combination of the commodity of characterization two respectively.
Optionally, after the determination two commodity are identical commodity, further comprise:
Judge whether two commodity are issued by same supplier;
After determining that two commodity are same supplier publication, the platform operation personnel of Xiang Suoshu electric business platform are sent out
Send warning message.
Second aspect, the embodiment of the invention also provides a kind of electric business platform goods matching devices, comprising: corpus obtains
Module, word segmentation module, standardized module and goods matching module;
The corpus obtains module, for obtaining the corresponding label word of each commodity classification on electric business platform respectively
Library is expected, wherein the label word corpus includes at least one label word corresponding with the commodity classification;
The word segmentation module, for according to it is corresponding with the commodity classification belonging to commodity on the electric business platform and by
The corpus obtains the label word corpus that module is got, and it is corresponding that the commodity are obtained from the title of the commodity
Commodity key message combination;
The standardized module, for being got to the word segmentation module and the commodity corresponding with the commodity close
Key information combination carries out screening and standardization, obtains the corresponding standard label combination of the commodity;
The goods matching module, for calculate it is corresponding with commodity described in any two in the same commodity classification and by
The matching probability between two standard label combinations that the standardized module is got, is greater than pre- in the matching probability
If matching probability threshold value when, determine two commodity be identical commodity.
The third aspect, it is described to deposit the embodiment of the invention also provides a kind of computer equipment, including memory and processor
Reservoir is stored with computer program, and the processor is realized any described in above-mentioned first aspect when executing the computer program
Electric business platform goods matching method.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program, the computer program realize any electric business platform goods matching in above-mentioned first aspect when being executed by processor
Method.
Electric business platform goods matching method, device and computer equipment provided in an embodiment of the present invention and computer-readable
Storage medium, for each commodity classification on electric business platform, acquisition includes corresponding with the commodity classification at least one
The label word corpus of a label word, later for each commodity on electric business platform, according to the affiliated commodity classification of the commodity
Corresponding label word corpus obtains the corresponding commodity key message combination of the commodity from the title of the commodity, and then to commodity
Key message combination obtains corresponding standard label combination after carrying out screening and standardization, later on electric business platform
Any two commodity for belonging to same commodity classification determine that the matching between the corresponding two Commercial goods labels combination of two commodity is general
Rate, if it is determined that the matching probability gone out is greater than preset matching probability threshold value, it is determined that the two commodity are identical quotient
Product.It can be seen that the combination of commodity key message is obtained from the title of commodity according to constructed label word corpus, by pass
Key information combination carries out screening and standardization obtains standard label combination, and then can be according to respective standard tag combination
Matching relationship determines whether two commodity are identical commodity, without platform operation personnel manually checks that commodity detail can be true
Whether fixed two commodity are identical commodity, so as to improve the efficiency of electric business platform goods matching.
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 the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of flow chart of electric business platform goods matching method provided by one embodiment of the present invention;
Fig. 2 is a kind of flow chart of commodity key message combination acquisition methods provided by one embodiment of the present invention;
Fig. 3 is a kind of flow chart of standard label combination acquisition methods provided by one embodiment of the present invention;
Fig. 4 is the flow chart of method whether a kind of two commodity of judgement provided by one embodiment of the present invention are identical;
Fig. 5 is the flow chart of another electric business platform goods matching method provided by one embodiment of the present invention;
Fig. 6 is a kind of schematic diagram of electric business platform goods matching device provided by one embodiment 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.It answers
Work as understanding, the specific embodiments described herein are merely illustrative of the present invention, is not intended to limit the present invention.
As shown in Figure 1, one embodiment of the invention provides a kind of electric business platform goods matching method, this method be can wrap
Include following steps:
Step 101: obtaining the corresponding label word corpus of each commodity classification on electric business platform respectively, wherein label word
Corpus includes at least one label word corresponding with commodity classification;
Step 102: according to label word corpus corresponding with commodity classification belonging to commodity on electric business platform, from commodity
Title in obtain commodity corresponding commodity key message combination;
Step 103: commodity key message corresponding with commodity being combined and carries out screening and standardization, obtains commodity
Corresponding standard label combination;
Step 104: between calculating two standard label corresponding with any two commodity in same commodity classification combines
Matching probability determines that two commodity are identical commodity when matching probability is greater than preset matching probability threshold value.
Electric business platform goods matching method provided in an embodiment of the present invention, for each commodity class on electric business platform
Mesh, acquisition include the label word corpus of at least one label word corresponding with the commodity classification, flat for electric business later
Each commodity on platform obtain from the title of the commodity according to the corresponding label word corpus of the affiliated commodity classification of the commodity
The corresponding commodity key message combination of the commodity, and then obtained after carrying out screening and standardization to the combination of commodity key message
Corresponding standard label combination calculates two later for any two commodity for belonging to same commodity classification on electric business platform
Matching probability between the corresponding two Commercial goods labels combination of a commodity, if calculated matching probability be greater than it is preset
Matching probability threshold value, it is determined that the two commodity are identical commodity.It can be seen that according to constructed label word corpus from quotient
The combination of commodity key message is obtained in the title of product, by carrying out screening and standardization acquisition standard to key message combination
Tag combination, and then can determine whether two commodity are identical quotient according to the matching relationship of respective standard tag combination
Product, manually checking commodity detail i.e. without platform operation personnel can determine whether two commodity are identical commodity, so as to mention
The efficiency of high electric business platform goods matching.
Optionally, it on the basis of electric business platform goods matching method shown in Fig. 1, is obtained and commodity classification in step 101
When corresponding label word corpus, label word can be acquired from the electric business platform of mainstream, and then by collected label word
Label word corpus is used as after combination, specific implementation process can be carried out as follows:
For each commodity classification on electric business platform, on the electric business platform for having constructed Commercial goods labels word from least one
The corresponding label word of the commodity classification is acquired, and then the commodity classification will be used as corresponding after collected all label word combinations
Label word corpus.Wherein, label word collected may include brand, the place of production, packaging, specification, grade, the processing work of commodity
It is any one or more in skill and qualification certification.
For example, constructing corresponding label since the mainstreams electric business platform such as Taobao, Jingdone district has been directed to different commodity classifications
Word, therefore the commodity classification being related to according to the affiliated electric business platform of commodity to be matched, can construct commodity mark with Taobao, Jingdone district etc.
Sign the label word that corresponding commodity classification is acquired on the electric business platform of word.For example, being directed to " edible oil " this commodity classification, Ke Yicong
It is acquired under the projects such as brand, classification, the place of production, capacity, grade, packaging, qualification certification and processing technology on the electric business platform of Jingdone district
Label word, and then by collected left and right label word combination to together as the corresponding label word of " edible oil " this commodity classification
Corpus.
For each commodity classification on electric business platform, the commodity class is acquired from one or more mainstream electric business platforms
The corresponding label word of mesh, and then collected label word combination is obtained into label word material corresponding with the commodity classification
Library voluntarily works out label word for commodity classification without platform operation personnel in this way, on the one hand can reduce platform operation personnel
On the other hand the cost paid during goods matching can make the label word obtained more accurate and specification.
Optionally, on the basis of electric business platform goods matching method shown in Fig. 1, step 102 is according to label word corpus
The combination of commodity key message is obtained from the title of commodity, as shown in Fig. 2, specifically may be used for each commodity on electric business platform
To obtain the combination of its key message by following sub-step:
Step 201: determining end article classification belonging to commodity;
Step 202: the title of commodity is determined as corpus to be slit;
Step 203: it is long that setting cutting length is equal to preset most major term;
Step 204: taking target segmenting word of the length equal to cutting length by forward direction from corpus to be slit;
Step 205: judging to whether there is and target segmenting word in the corresponding target labels word corpus of end article classification
The label word to match, if so, step 206 is executed, it is no to then follow the steps 208;
Step 206: target segmenting word is determined as a keyword;
Step 207: removing target segmenting word from corpus to be slit and execute step 203;
Step 208: judge whether cutting length is greater than two bytes, if so, step 209 is executed, it is no to then follow the steps
210;
Step 209: executing step 204 after cutting length is reduced by least two bytes;
Step 210: step 203 is executed after two characters for removing corpus head to be slit.
After the title cutting to commodity is completed, using each crucial contamination as the corresponding commodity keyword of commodity
Information combination.
The title of commodity is determined as to initial corpus to be slit, and long to be determined as cutting long by most major term predetermined
Degree, later from corpus to be slit by forward direction take length be equal to cutting length target segmenting word, later by target segmenting word with
The corresponding label word corpus of the affiliated commodity classification of the commodity is matched.If the corresponding label of the affiliated commodity classification of the commodity
There is the label word to match with target segmenting word in word corpus, then the target segmenting word being syncopated as is determined as a key
Word, and the commodity title after the target segmenting word will be removed as new corpus to be slit and continue cutting keyword.If should
There is no the label words to match with target segmenting word in the corresponding label word corpus of the affiliated commodity classification of commodity, then by cutting
Length reduces the cutting target segmenting word from corpus to be slit again after two bytes.It, can be with by the way that above-mentioned steps are performed a plurality of times
The keyword that multiple label word corpus corresponding with the affiliated commodity classification of commodity match is syncopated as from commodity title, in turn
Each crucial contamination is determined as the corresponding key message combination of commodity.
For example, entitled " the non-transgenic squeezing level-one 5L of edible oil " of commodity A, the affiliated commodity classification of commodity A is corresponding
Label word corpus A in include labels words such as " edible oil, non-transgenic, squeezing, level-one, 5L ".Preset maximum
Word a length of 4.Initially will " edible oil is non-" cutting be target segmenting word, due in label word corpus A not with " edible oil is non-"
The label word to match is syncopated as target segmenting word " edible oil ", due to label word again after cutting length is then reduced to 3
There is the label word to match with " edible oil " in material library A, then target segmenting word " edible oil " is determined as a keyword, it
It is afterwards that new target cutting time matches by " non-transgenic " cutting, it is final to obtain " edible oil ", " non-transgenic ", " pressure
Squeezing ", " level-one ", " 5L " amount to 5 keywords, combine using then 5 crucial contaminations as the commodity key message of commodity A.
After being syncopated as target segmenting word in commodity title, by target segmenting word and the progress of corresponding label word corpus
Match, if it is possible to successful match is then used as a keyword, if failing successful match by increasing or decreasing single word after
Continue to compare, there remains an individual character always and then terminate.By the way that from left to right, matched to short sequence from long, guarantee can
Easily and accurately to determine the corresponding commodity key message combination of commodity.
Optionally, on the basis of commodity key message combination acquisition methods shown in Fig. 2, step 103 can be closed commodity
The keyword that key information combination includes carries out screening and standardization, and then obtains standard label combination, as shown in figure 3, needle
Each commodity on electric business platform can specifically be obtained with the combination of its standard label as follows:
Step 301: according to preset concern message catalog, including to the combination of the commodity corresponding commodity key message
Each keyword screened, will meet concern message catalog crucial contamination as the corresponding Commercial goods labels of the commodity
Combination;
Step 302: according to preset label word transformation rule, respectively in the combination of the commodity corresponding Commercial goods labels
Each keyword format, obtain corresponding standard label word;
Step 303: being combined each standard label contamination as the corresponding standard label of the commodity.
Firstly, since generally included a fairly large number of label word in label word corpus, thus by with label word
The commodity key message combination that label word in material library is matched and obtained also includes multiple keywords, but these keywords
It is not entirely that platform operation personnel are of interest.For this purpose, platform operation personnel can pre-define concern information according to demand
Catalogue, after getting commodity key message, whether each keyword that successively determining commodity key message combination includes
Defined in the concern message catalog in range of information, so that it is determined that go out each keyword for meeting concern message catalog, into
And it combines each crucial contamination for meeting concern message catalog determined as the Commercial goods labels of corresponding commodity.
Key message combination is screened by preset concern message catalog, is determined in key message combination
After the keyword of non-user concern, using key message combine in user's concern each crucial contamination as Commercial goods labels group
It closes, so as to match identical commodity from electric business platform according to user's information of interest, meets the individual character of different user
Change demand promotes the usage experience of user.
Secondly as the mark of commodity may be defined when different supplier's publishing commodities using different describing modes
Topic, such as the Chinese and English annotation formatting (connection of the front-rear position relationship, Chinese and English of English capital and small letter, Chinese and English
Symbol etc.), the use of abbreviation or full name, or even be also possible that wrong word.By presetting label word transformation rule, Ke Yigen
Each of Commercial goods labels combination keyword is formatted according to label word transformation rule, in being combined to Commercial goods labels
Chinese and English annotation formatting, the use of abbreviation/full name and the wrong word of keyword are converted, and the mark with unified format is obtained
Fiducial mark label word matches convenient for the subsequent standard label word to different commodity.
Optionally, on the basis of electric business platform goods matching method shown in Fig. 1, it is corresponding that step 103 obtains each commodity
Standard label combination after, can by column to each commodity corresponding standard label combination store.Specifically, for electricity
Each commodity classification on quotient's platform belongs to the corresponding standard of all commodity of the commodity classification on getting electric business platform
It include being stored to each standard label combination got in the table of two column at one, wherein first row after tag combination
The coding of commodity is stored, the corresponding standard label of secondary series storage corresponding commodity combines the standard label word for including.
For example, commodity A and commodity B belong to same commodity classification X.Commodity A's is encoded to SKU1, the corresponding standard of commodity A
It include 4 standard label words, respectively standard label word 1 to 4 in tag combination.Commodity B's is encoded to SKU2, and B pairs of commodity
It include 3 standard label words, respectively standard label word 5 to 7 in the standard label combination answered.Then by commodity A and B couples of commodity
After the standard label combination storage answered is in corresponding to the double entry table of commodity classification X, the double entry table corresponding to commodity classification X is such as
Shown in the following table 1.
Table 1
…… | …… |
SKU1 | Standard label word 1 |
SKU1 | Standard label word 2 |
SKU1 | Standard label word 3 |
SKU1 | Standard label word 4 |
SKU2 | Standard label word 5 |
SKU2 | Standard label word 6 |
SKU2 | Standard label word 7 |
…… | …… |
The standard label word for including to the combination of each commodity corresponding standard label in column form stores, Ke Yifang
Just standard label word is extended, and guaranteeing can not with sequence of the standard label word in standard label combines.In addition,
It is stored by the standard label word for including to standard label combination in column form, it can be more easily to two commodity
Corresponding standard label word is matched.
Optionally, on the basis of electric business platform goods matching method shown in Fig. 1, step 104 is by calculating same commodity
Matching probability in classification between the combination of standard label corresponding to two commodity determines whether the two commodity are identical quotient
Product, as shown in figure 4, the step can specifically be realized by following sub-step:
Step 401: the included standard label word of the corresponding standard label combination of two commodity being compared, determines two
The number of standard label word is shared in the corresponding standard label combination of a commodity;
Step 402: the number of included standard label word being combined according to the corresponding standard label of two commodity and shares mark
The number of fiducial mark label word calculates the matching probability of the corresponding standard label combination of two commodity by following formula;
Wherein, P characterizes the matching probability of the corresponding standard label combination of two commodity, and M characterizes the corresponding mark of two commodity
The number of standard label word, M are shared in quasi- tag combination1And M2The corresponding standard label combination acceptance of the bid of two commodity is characterized respectively
The number of fiducial mark label word;
Step 403: judging whether matching probability is greater than preset matching probability threshold value, if so, executing step
404, it is no to then follow the steps 405;
Step 404: determining that two commodity are identical commodity, and terminate current process;
Step 405: determining that two commodity are different commodity.
For two commodity belonged to through commodity classification, will be wrapped in the corresponding two standard label combination of the two commodity
The standard label word included is compared, and determines to share standard label word in the corresponding two standard label combination of two commodity
Number, and then the number of Plays label word and the number calculating of shared standard label word can be combined according to two standard labels
Matching probability between two standard label combinations out, matching probability is higher to be illustrated to share standard mark in two standard labels combinations
Sign word number it is more, thus two standard labels combine corresponding two commodity be identical commodity probability it is also bigger, when
After being greater than preset matching probability threshold value with probability, it can determine that two commodity are identical commodity.
It, specifically can be with it should be noted that matching probability threshold value can be obtained and the test analysis to mass data
Any value matching probability threshold value set between 80%-95%.
By comparing the corresponding standard label combination of two commodity, and then two are calculated corresponding to two commodity
Matching probability between standard label combination, determines whether two commodity are identical commodity according to calculated matching probability,
It thereby may be ensured that the accuracy of matching result.
Optionally, on the basis of electric business platform goods matching method shown in Fig. 1, step 104 determines that two commodity are phase
After commodity, it may further determine that whether the two commodity are issued by same supplier, if the two commodity are identical
Commodity and issued by the same supplier, then to the platform operation personnel of electric business platform send warning message.
If the same supplier is repeatedly issued on electric business platform for the same commodity, which exists
The unlawful practice that different commodity titles and price are defined for identical commodity is determining two commodity for identical commodity and by same
Warning message is sent to the platform operation personnel of electric business platform after one supplier's publication, so that platform operation personnel can be timely
It was found that the misconduct of supplier, guarantees the interests of purchaser.
For below using self-built B2B platform as electric business platform, to electric business platform commodity provided in an embodiment of the present invention
Method of completing the square is described in further detail, as shown in figure 5, this method may comprise steps of:
Step 501: obtaining the corresponding label word corpus of each commodity classification on self-built B2B platform respectively.
In embodiments of the present invention, it according to the type of institute's tradable commodity on self-built B2B platform, determines on self-built B2B platform
At least one corresponding commodity classification of commodity.For each commodity classification on self-built B2B platform, from one or more of mainstream
Acquire the corresponding label word of the commodity classification on a B2B platform, so by collected all label words carry out it is centrally stored after
As the corresponding label word corpus of the commodity classification.
For example, the corresponding commodity classification of commodity on self-built B2B platform includes " grain and oil seasoning " and " mobile phone digital ", difference
Corresponding label word is acquired from the B2B platform of mainstream for " grain and oil seasoning " and " mobile phone digital " the two commodity classifications, into
And it generates and is directed to the label word corpus 1 of " grain and oil seasoning " and is directed to the label word corpus 2 of " mobile phone digital ".
Step 502: being combined according to the commodity key message that label word corpus obtains commodity on self-built B2B platform.
In embodiments of the present invention, for each commodity on self-built B2B platform, commodity class belonging to the commodity is determined
Mesh, and then the title of the commodity is segmented according to determined commodity classification corresponding label word corpus, obtain multiple passes
Keyword.Finally combined using each crucial contamination as the corresponding commodity key message of the commodity.
Step 503: the combination of commodity key message being screened according to preset concern message catalog, obtains commodity
Tag combination.
In embodiments of the present invention, for each commodity on self-built B2B platform, the corresponding quotient of the commodity is being got
After the combination of product key message, according to preset concern message catalog to each pass for including in the combination of commodity key message
Keyword is screened, and is filtered out and is belonged to the keyword that user pays close attention to the information content, and then by the group of each keyword filtered out
Cooperation is the corresponding Commercial goods labels combination of the commodity.
For example, preset concern message catalog includes Brand, commodity packaging, commercial specification and the commodity place of production,
Having a keyword in 6 included keywords of the corresponding commodity key message of commodity 1 combination is the processing technology of commodity 1,
As the keyword be not belonging to concern message catalog included by content, to the key message be screened out, by remaining 5
Crucial contamination is combined as the Commercial goods labels of commodity 1.
Step 504: format is carried out to the keyword in Commercial goods labels combination according to preset label word transformation rule
Conversion obtains standard label combination.
In embodiments of the present invention, for each commodity on self-built B2B platform, the corresponding quotient of the commodity is being got
After product tag combination, according to preset label word transformation rule to each in the combination of the commodity corresponding Commercial goods labels
Keyword formats, and keyword is converted to the standard label word with unified format, and then by each standard label
Contamination is as the corresponding standard label combination of the commodity.Wherein, format is carried out to keyword according to label word transformation rule
Conversion, mainly include to the Chinese and English annotation formatting of keyword (the front-rear position relationship of English capital and small letter, Chinese and English,
Connector etc. of Chinese and English) and the use of abbreviation or full name converted and the amendment of wrong word etc..
For example, 5 keywords included by the combination of the corresponding Commercial goods labels of commodity 1 are respectively keyword 1 to 5, keyword 1
Chinese and English brand name is located at before Chinese brand name, and the commodity place of production has used referred to as in keyword 2, occurs in keyword 3
Wrong word.According to preset label word transformation rule, the Chinese and English brand name of keyword 1 is placed in Chinese brand name
Standard label word 1 is obtained later, and the abbreviation in the commodity place of production in keyword 2 is converted into the full name in the commodity place of production and obtains standard
Label word 2 will obtain standard label word 3 after the wrong word amendment in keyword 3, directly by keyword 4 and keyword 5 as mark
Fiducial mark label word 4 and standard label word 5.And then it is combined the combination of standard label word 1 to 5 as the corresponding standard label of commodity 1
1。
Step 505: the combination of each commodity corresponding standard label being stored by column.
In embodiments of the present invention, for each commodity classification on self-built B2B platform, the commodity classification is being got
Under after the corresponding standard label combination of all commodity, accessed each standard label combination is deposited in column form
Storage.Wherein, the table for storing standard label combination includes two column, and first row is used to store the coding of commodity, and secondary series is used
The standard label word for including is combined in the standard label of storage corresponding commodity.
For example, including 30 commodity under commodity classification " grain and oil seasoning ", this corresponding standard of 30 commodity is being got
After tag combination, the standard mark for including is combined to the coding of 30 commodity and 30 standard labels according to the form of above-mentioned table 1
Label word is stored.
Step 506: determining whether two commodity are identical commodity according to stored standard label word.
In embodiments of the present invention, according to the demand of platform operation personnel, when platform operation personnel input needs to match phase
It is for each commodity that the affiliated commodity classification of end article includes, end article is corresponding after the end article of commodity
Each standard label word standard label corresponding with the commodity that standard label combination includes combines each standard label for including
Word is compared, and determines to share the number of standard label word in two standard label combinations, and then calculate by following formula
The corresponding standard label of end article combine standard label corresponding with the commodity combine between matching probability;
Wherein, P characterizes the matching probability of the corresponding standard label combination of two commodity, and M characterizes the corresponding mark of two commodity
The number of standard label word, M are shared in quasi- tag combination1And M2Characterization end article standard label corresponding with the commodity respectively
Combine the number of Plays label word.
It is combined between standard label corresponding with end article combines calculating the corresponding standard label of each commodity
After matching probability, determine that Corresponding matching probability is greater than the commodity of preset matching probability threshold value and end article is identical commodity.
For example, platform operation personnel it needs to be determined that on self-built B2B platform with 1 identical commodity of commodity when, it is true by calculating
Determine to only have commodity 3 in remaining 29 commodity included by commodity classification " grain and oil seasoning " and the corresponding matching probability of commodity 6 is greater than
Preset matching probability threshold value, it is determined that commodity 1, commodity 3 and commodity 6 are identical commodity.
As shown in fig. 6, one embodiment of the invention provides a kind of electric business platform goods matching device, comprising: corpus
Obtain module 601, word segmentation module 602, standardized module 603 and goods matching module 604;
The corpus obtains module 601, for obtaining each corresponding label of commodity classification on electric business platform respectively
Word corpus, wherein the label word corpus includes at least one label word corresponding with the commodity classification;
The word segmentation module 602, for according to corresponding with the commodity classification belonging to commodity on the electric business platform
And the label word corpus that module 601 is got is obtained by the corpus, from the title of the commodity described in acquisition
The corresponding commodity key message combination of commodity;
The standardized module 603, for being got to the word segmentation module 602 and corresponding with the commodity described
The combination of commodity key message carries out screening and standardization, obtains the corresponding standard label combination of the commodity;
The goods matching module 604, it is corresponding with commodity described in any two in the same commodity classification for calculating
And by two standard labels that the standardized module 603 is got combine between matching probability, it is general in the matching
When rate is greater than preset matching probability threshold value, determine that two commodity are identical commodity.
In embodiments of the present invention, corpus obtains module 601 and can be used for executing the step 101 in above method embodiment
With step 501, word segmentation module 602 can be used for executing step 102, step 201 to 211 and step in above method embodiment
502, standardized module 603 can be used for executing step 103, step 301 to 303 and step 503 in above method embodiment
With step 504, goods matching module 604 can be used for executing step 104 in above method embodiment, step 401 to 405 and
Step 506.
It should be noted that in information exchange, implementation procedure between modules included by present apparatus embodiment etc.
Hold, since based on the same inventive concept, particular content may refer to chatting in above method embodiment with above method embodiment
It states, details are not described herein again.In addition, present apparatus embodiment can also include other modules, for executing above method embodiment
In each step.
The embodiment of the invention also provides a kind of computer equipments, include memory and processor, store on memory
There is computer program, can be achieved on above-mentioned each embodiment institute when processor executes the computer program stored on memory
The electric business platform goods matching method of offer.
The embodiment of the invention also provides a kind of computer readable storage medium, stored on the computer readable storage medium
There is computer program, is performed that the electric business that above-mentioned each embodiment provides may be implemented is flat in the computer storage that it is stored
Platform goods matching method.
In conclusion electric business platform goods matching method, device and computer that each embodiment of the present invention provides are set
Standby and computer readable storage medium, at least has the following beneficial effects:
1, in embodiments of the present invention, for each commodity classification on electric business platform, acquisition includes and the commodity
The label word corpus of at least one corresponding label word of classification, each commodity being directed on electric business platform later, according to
It is crucial to obtain the corresponding commodity of the commodity from the title of the commodity for the corresponding label word corpus of the affiliated commodity classification of the commodity
Information combination, and then corresponding standard label group is obtained after carrying out screening and standardization to the combination of commodity key message
It closes, later for any two commodity for belonging to same commodity classification on electric business platform, determines corresponding two quotient of two commodity
Matching probability between product tag combination, if it is determined that the matching probability gone out is greater than preset matching probability threshold value, then really
The two fixed commodity are identical commodity.It can be seen that obtaining quotient from the title of commodity according to constructed label word corpus
Product key message combination, by carrying out screening and standardization acquisition standard label combination, Jin Erke to key message combination
To determine whether two commodity are identical commodity according to the matching relationship of respective standard tag combination, it is not necessarily to platform operation people
Manually check commodity detail i.e. can determine whether two commodity are identical commodity to member, so as to improve electric business platform goods matching
Efficiency.
2, in embodiments of the present invention, for each commodity classification on electric business platform, from one or more mainstream electricity
The corresponding label word of the commodity classification is acquired on quotient's platform, and then collected label word combination is obtained and the commodity classification
Corresponding label word corpus voluntarily works out label word for commodity classification without platform operation personnel in this way, on the one hand may be used
To reduce the cost that platform operation personnel pay during goods matching, the label word obtained on the other hand can be made more
Accurate and specification.
3, in embodiments of the present invention, after being syncopated as target segmenting word in commodity title, by target segmenting word and accordingly
Label word corpus matched, if it is possible to successful match is then used as a keyword, leads to if failing successful match
It crosses after increasing or decreasing single word and continues to compare, there remains an individual character always and then terminate.By from left to right, from long to short
Sequence is matched, and guarantee can be convenient, accurately determine the corresponding commodity key message combination of commodity.
4, in embodiments of the present invention, key message combination is screened by preset concern message catalog,
Determine key message combination in non-user concern keyword after, by key message combine in user concern each keyword
Combination as Commercial goods labels combine, so as to match identical quotient from electric business platform according to user's information of interest
Product meet the individual demand of different user, promote the usage experience of user.
It 5, can be according to label word transformation rule in embodiments of the present invention, by presetting label word transformation rule
Each of Commercial goods labels combination keyword is formatted, with the Chinese and English mark of keyword in being combined to Commercial goods labels
Note format, the use of abbreviation/full name and wrong word are converted, and the standard label word with unified format are obtained, after being convenient for
It is continuous that the standard label word of different commodity is matched.
6, the standard mark for including in embodiments of the present invention, is combined to the corresponding standard label of each commodity in column form
Label word is stored, and is extended to standard label word with can be convenient, and is guaranteed with standard label word in standard label group
Sequence in conjunction can not.In addition, stored by the standard label word for including to standard label combination in column form, it can be with
More easily the corresponding standard label word of two commodity is matched.
7, it in embodiments of the present invention, by comparing the corresponding standard label combination of two commodity, and then calculates
Matching probability between two standard label combinations corresponding to two commodity out, determines two quotient according to calculated matching probability
Whether product are identical commodity, thereby may be ensured that the accuracy of matching result.
8, in embodiments of the present invention, if the same supplier carries out repeatedly on electric business platform for the same commodity
Publication, then there is the unlawful practice that different commodity titles and price are defined for identical commodity in the supplier, determine two quotient
Product send warning message to the platform operation personnel of electric business platform after issuing for identical commodity and from the same supplier, thus
Platform operation personnel can have found the misconduct of supplier in time, guarantee the interests of purchaser.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, device, article or the method that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, device, article or method institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, device of element, article or method.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.Pass through above embodiment party
The description of formula, it is required general that those skilled in the art can be understood that above-described embodiment method can add by software
The mode of hardware platform is realized, naturally it is also possible to which by hardware, but in many cases, the former is more preferably embodiment.It is based on
Such understanding, substantially the part that contributes to existing technology can be with software product in other words for technical solution of the present invention
Form embody, which is stored in a storage medium (such as ROM/RAM, magnetic disk, light as described above
Disk) in, including some instructions use is so that a terminal device (can be mobile phone, computer, server or the network equipment
Deng) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of electric business platform goods matching method characterized by comprising
The corresponding label word corpus of each commodity classification on electric business platform is obtained respectively, wherein the label word corpus packet
At least one label word corresponding with the commodity classification is included;
According to the label word corpus corresponding with the commodity classification belonging to commodity on the electric business platform, from described
The corresponding commodity key message combination of the commodity is obtained in the title of commodity;
The commodity key message corresponding with the commodity is combined and carries out screening and standardization, obtains the commodity
Corresponding standard label combination;
Calculate between corresponding two standard label of commodity combines described in any two in the same commodity classification
Matching probability determines that two commodity are identical quotient when the matching probability is greater than preset matching probability threshold value
Product.
2. the method according to claim 1, wherein described obtain each commodity classification on electric business platform respectively
Corresponding label word corpus, comprising:
For each commodity classification on the electric business platform, on the electric business platform for having constructed Commercial goods labels word from least one
Acquire the corresponding label word of the commodity classification, using at least one collected described label contamination as with the commodity classification
Corresponding label word corpus, wherein the label word includes brand, the place of production, packaging, specification, grade, the processing work of commodity
At least one of skill and qualification certification.
3. the method according to claim 1, wherein it is described according to institute belonging to commodity on the electric business platform
The corresponding label word corpus of commodity classification is stated, the corresponding commodity of the commodity are obtained from the title of the commodity and are closed
Key information combination, comprising:
S1: end article classification belonging to commodity on the electric business level is determined;
S2: the title of the commodity is determined as corpus to be slit;
S3: it is long that setting cutting length is equal to preset most major term;
S4: target segmenting word of the length equal to the cutting length is taken by forward direction from the corpus to be slit;
S5: the label word in target segmenting word target labels word corpus corresponding with the end article classification is carried out
Otherwise matching executes S8 if successful match executes S6;
S6: the target segmenting word is determined as a keyword;
S7: S3 is executed after removing the keyword in the corpus to be slit;
S8: if the cutting length is greater than two bytes, executing S4 after the cutting length is reduced by least two bytes,
If the cutting length is equal to two bytes, S3 is executed after removing two characters on the corpus head to be slit;
S9: it is combined using each crucial contamination as the corresponding commodity key message of the commodity.
4. according to the method described in claim 3, it is characterized in that, described crucial to the commodity corresponding with the commodity
Information combination carries out screening and standardization, obtains the corresponding standard label combination of the commodity, comprising:
According to preset concern message catalog, the commodity key message combination corresponding to the commodity includes each
The keyword is screened, and the crucial contamination for meeting the concern message catalog is corresponding as the commodity
Commercial goods labels combination;
According to preset label word transformation rule, each of described Commercial goods labels combination corresponding to commodity institute
It states keyword to format respectively, obtains corresponding standard label word;
Using each standard label contamination as the corresponding standard label combination of the commodity.
5. the method according to claim 1, wherein obtaining the corresponding standard label combination of the commodity described
Later, further comprise:
For each described commodity classification on the electric business platform, the commodity classification will be belonged on the electric business platform
The corresponding standard label combination of each commodity is stored by column, wherein and first row stores the coding of the commodity,
Secondary series stores the corresponding standard label of the commodity and combines the standard label word for including.
6. according to the method described in claim 4, it is characterized in that, the calculating and any two in the same commodity classification
Matching probability between the corresponding two standard label combinations of the commodity, comprising:
By the standard mark in the corresponding standard label combination of commodity described in any two in the same commodity classification
Label word is compared, and determines of the standard label word shared in the corresponding standard label combination of two commodity
Number, and pass through the matching probability of the corresponding standard label combination of the commodity of following formula calculating two;
Wherein, the P characterizes the matching probability of the corresponding standard label combination of two commodity, and the M characterizes two
The number of the standard label word shared in the corresponding standard label combination of the commodity, the M1With the M2Respectively
The number of standard label word described in the corresponding standard label combination of the commodity of characterization two.
7. according to claim 1 to any method in 6, which is characterized in that in the determination, two commodity are
After identical commodity, further comprise:
Judge whether two commodity are issued by same supplier;
After determining that two commodity are same supplier publication, the platform operation personnel of Xiang Suoshu electric business platform send report
Alert information.
8. a kind of electric business platform goods matching device characterized by comprising corpus obtains module, word segmentation module, standardization
Module and goods matching module;
The corpus obtains module, for obtaining the corresponding label word material of each commodity classification on electric business platform respectively
Library, wherein the label word corpus includes at least one label word corresponding with the commodity classification;
The word segmentation module, for according to corresponding with the commodity classification belonging to commodity on the electric business platform and by described
Corpus obtains the label word corpus that module is got, and the corresponding quotient of the commodity is obtained from the title of the commodity
The combination of product key message;
The standardized module, for being got to the word segmentation module and the commodity key corresponding with commodity letter
Breath combination carries out screening and standardization, obtains the corresponding standard label combination of the commodity;
The goods matching module, it is corresponding with commodity described in any two in the same commodity classification and by described for calculating
The matching probability between two standard label combinations that standardized module is got, is greater than preset in the matching probability
When matching probability threshold value, determine that two commodity are identical commodity.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of any one of claims 1 to 7 the method is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910191090.XA CN110083678A (en) | 2019-03-12 | 2019-03-12 | A kind of electric business platform goods matching method, device and readable storage medium storing program for executing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910191090.XA CN110083678A (en) | 2019-03-12 | 2019-03-12 | A kind of electric business platform goods matching method, device and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110083678A true CN110083678A (en) | 2019-08-02 |
Family
ID=67412504
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910191090.XA Pending CN110083678A (en) | 2019-03-12 | 2019-03-12 | A kind of electric business platform goods matching method, device and readable storage medium storing program for executing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110083678A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111461783A (en) * | 2020-03-31 | 2020-07-28 | 广东奥园奥买家电子商务有限公司 | E-commerce commodity sequencing display method, device and equipment |
CN112258244A (en) * | 2020-11-06 | 2021-01-22 | 微医云(杭州)控股有限公司 | Method, device, equipment and storage medium for determining task of target object |
CN112308674A (en) * | 2020-11-03 | 2021-02-02 | 博思数采科技发展有限公司 | Method and terminal for intelligently aggregating price comparison of commodities |
CN112380347A (en) * | 2020-11-24 | 2021-02-19 | 苏宁云计算有限公司 | Method, device and system for determining related item class words |
CN112632273A (en) * | 2020-10-23 | 2021-04-09 | 东南数字经济发展研究院 | Commodity fine-grained classification method based on social e-commerce public text information |
CN113342969A (en) * | 2020-03-03 | 2021-09-03 | 北京沃东天骏信息技术有限公司 | Data processing method and device |
CN113744014A (en) * | 2020-09-29 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Article information monitoring method, device, equipment and computer readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102332137A (en) * | 2011-09-23 | 2012-01-25 | 纽海信息技术(上海)有限公司 | Goods matching method and system |
US20120117072A1 (en) * | 2010-11-10 | 2012-05-10 | Google Inc. | Automated Product Attribute Selection |
KR20180052204A (en) * | 2016-11-10 | 2018-05-18 | (주)준소프트웨어 | Method for online monitoring to detect trademark right infringement products |
CN108228665A (en) * | 2016-12-22 | 2018-06-29 | 阿里巴巴集团控股有限公司 | Determine object tag, the method and device for establishing tab indexes, object search |
-
2019
- 2019-03-12 CN CN201910191090.XA patent/CN110083678A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120117072A1 (en) * | 2010-11-10 | 2012-05-10 | Google Inc. | Automated Product Attribute Selection |
CN102332137A (en) * | 2011-09-23 | 2012-01-25 | 纽海信息技术(上海)有限公司 | Goods matching method and system |
KR20180052204A (en) * | 2016-11-10 | 2018-05-18 | (주)준소프트웨어 | Method for online monitoring to detect trademark right infringement products |
CN108228665A (en) * | 2016-12-22 | 2018-06-29 | 阿里巴巴集团控股有限公司 | Determine object tag, the method and device for establishing tab indexes, object search |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113342969A (en) * | 2020-03-03 | 2021-09-03 | 北京沃东天骏信息技术有限公司 | Data processing method and device |
CN111461783A (en) * | 2020-03-31 | 2020-07-28 | 广东奥园奥买家电子商务有限公司 | E-commerce commodity sequencing display method, device and equipment |
CN113744014A (en) * | 2020-09-29 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Article information monitoring method, device, equipment and computer readable storage medium |
CN112632273A (en) * | 2020-10-23 | 2021-04-09 | 东南数字经济发展研究院 | Commodity fine-grained classification method based on social e-commerce public text information |
CN112308674A (en) * | 2020-11-03 | 2021-02-02 | 博思数采科技发展有限公司 | Method and terminal for intelligently aggregating price comparison of commodities |
CN112258244A (en) * | 2020-11-06 | 2021-01-22 | 微医云(杭州)控股有限公司 | Method, device, equipment and storage medium for determining task of target object |
CN112258244B (en) * | 2020-11-06 | 2024-05-03 | 微医云(杭州)控股有限公司 | Method, device, equipment and storage medium for determining task to which target object belongs |
CN112380347A (en) * | 2020-11-24 | 2021-02-19 | 苏宁云计算有限公司 | Method, device and system for determining related item class words |
CN112380347B (en) * | 2020-11-24 | 2022-11-18 | 苏宁云计算有限公司 | Method, device and system for determining related item class words |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110083678A (en) | A kind of electric business platform goods matching method, device and readable storage medium storing program for executing | |
US8005874B2 (en) | Data tag creation from a physical item data record to be attached to a physical item | |
CN109582857A (en) | Based on big data information-pushing method, device, computer equipment and storage medium | |
US20090164431A1 (en) | Analysis, Inference, and Visualization of Social Networks | |
CN109658478A (en) | It is a kind of that the method and system of enterprise's portrait are provided | |
CN109063945A (en) | A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system | |
CN104115178A (en) | Methods and systems for predicting market behavior based on news and sentiment analysis | |
Leong et al. | The determinants of customer loyalty in Malaysian mobile telecommunication services: a structural analysis | |
CN110362689A (en) | A kind of methods of risk assessment, device, storage medium and server | |
CN109492104A (en) | Training method, classification method, system, equipment and the medium of intent classifier model | |
CN106294676B (en) | A kind of data retrieval method of ecommerce government system | |
CN110134844A (en) | Subdivision field public sentiment monitoring method, device, computer equipment and storage medium | |
CN115757623A (en) | Account checking method, account checking system and electronic equipment | |
US8065385B2 (en) | Transferring information and records via a data structure for a physical item in the control of a user | |
Zhao et al. | Anatomy of a web-scale resale market: a data mining approach | |
CN108537635A (en) | A kind of recommendation method and device of product | |
CN111639700A (en) | Target similarity recognition method and device, computer equipment and readable storage medium | |
Bracci et al. | Macroscopic properties of buyer–seller networks in online marketplaces | |
Engemann et al. | Institutional quality and the duration of agri‐food trade flows | |
CN107451879B (en) | Information judgment method and device | |
CN111444368B (en) | Method and device for constructing user portrait, computer equipment and storage medium | |
CN113064936A (en) | User portrait method and system and storage medium | |
CN117611295A (en) | Multi-merchant electronic commerce recommendation system based on user requirements | |
CN108764995A (en) | A kind of data value determines system and method | |
Simons et al. | A cross-disciplinary technology transfer for search-based evolutionary computing: from engineering design to software engineering design |
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 |