CN109903105A - A kind of method and apparatus for improving end article attribute - Google Patents
A kind of method and apparatus for improving end article attribute Download PDFInfo
- Publication number
- CN109903105A CN109903105A CN201711292885.7A CN201711292885A CN109903105A CN 109903105 A CN109903105 A CN 109903105A CN 201711292885 A CN201711292885 A CN 201711292885A CN 109903105 A CN109903105 A CN 109903105A
- Authority
- CN
- China
- Prior art keywords
- attribute
- name
- value
- primary
- 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.)
- Granted
Links
Abstract
The invention discloses a kind of method and apparatus for improving end article attribute, are related to field of computer technology.One specific embodiment of this method includes: the classification according to end article, obtains the corresponding primary attribute name set of the classification and primary attribute value set；The corresponding primary attribute name of the primitive attribute name of end article is compared with each primary attribute name in primary attribute name set, with determination attribute-name to be modified；Frequency of occurrence of each primary attribute value in merchandise news in statistical basis property value set, confirm that the original property value of end article is different from the primary attribute value that corresponding frequency of occurrence is most, using the most primary attribute value of frequency of occurrence as attribute value to be modified；According to attribute-name to be modified and attribute value to be modified, the attribute of end article is modified.It is high-efficient, accuracy rate is high, the user experience is improved this embodiment avoids the artificial modification process for participating in item property.
Description
Technical field
The present invention relates to computer field more particularly to a kind of method and apparatus for improving end article attribute.
Background technique
Electric business platform in the attribute information of publishing commodity, usually by staff according to itself to the understandings of commodity with
And electric business platform recommends the attribute of commodity, improves commodity category by human-edited's modification in the background system of electric business platform
Property.
In realizing process of the present invention, at least there are the following problems in the prior art: the quotient of electric business platform for inventor's discovery
Product quantity is all several hundred million grades, due to the uncertainty of goods themselves attribute and the mode of human-edited's modification, so that publication
Attribute information subjectivity it is strong, there are wrong community or omit attribute, low efficiency, poor user experience.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of method and apparatus for improving end article attribute, it is based on target quotient
The primary attribute name set and base that primitive attribute name, original property value and the item property data according to each classification of product are established
Plinth property value set, determine end article attribute-name to be modified and attribute value to be modified, and then modify item property.By upper
Mode is stated, avoids manually participating in, it is high-efficient, accuracy rate is high, the user experience is improved.
To achieve the above object, according to an aspect of an embodiment of the present invention, it provides and a kind of improves end article attribute
Method.
A kind of method for improving end article attribute of the embodiment of the present invention, comprising: according to the classification of end article, obtain
Corresponding primary attribute name set and the primary attribute value set of classifying；The primitive attribute name of the end article is corresponding
Primary attribute name is compared with each primary attribute name in the primary attribute name set, with determination attribute-name to be modified；System
Frequency of occurrence of each primary attribute value in merchandise news in the primary attribute value set is counted, confirms the end article
Original property value is different from the primary attribute value that corresponding frequency of occurrence is most, by the most primary attribute value of the frequency of occurrence
As attribute value to be modified；According to the attribute-name to be modified and the attribute value to be modified, the category of the end article is modified
Property.
Optionally, before the step of classification according to end article, further includes: according to the item property of each classification
Data establish the primary attribute name set and a primary attribute value set for each classification respectively；Wherein, institute
Stating item property data includes the primitive attribute name and corresponding original property value.
Optionally, the item property data according to each classification establish the basis for each classification respectively
Attribute-name set and a primary attribute value set, comprising: by the identical primitive attribute name of meaning in each classification and contain
The identical original property value of justice merges respectively；Frequency of occurrence in the primitive attribute name being merged in each classification is most
Primary attribute name of the primitive attribute name as the classification, frequency of occurrence in the original property value being merged in each classification is most
Primary attribute value of the original property value as the classification；All primary attribute names of each classification constitute the base of the classification
Plinth attribute-name set, all primary attribute values constitute the primary attribute value set of the classification.
Optionally, the most primitive attribute masterpiece of frequency of occurrence in the primitive attribute name that will be merged in each classification
For the primary attribute name of the classification, by the most original property value of frequency of occurrence in the original property value being merged in each classification
Before after the step of primary attribute value as the classification and the step of the classification according to end article, further includes:
Construct the bigraph (bipartite graph) of each classification.
Optionally, after the step of bigraph (bipartite graph) of each classification of building and described by the original of the end article
The corresponding primary attribute name of attribute-name is compared with each primary attribute name in the primary attribute name set, to be repaired with determination
Before the step of changing attribute-name, further includes: according to the bigraph (bipartite graph), establish mapping relations by inverted index mode；Wherein, institute
Stating mapping relations includes the mapping relations established with the entitled key of the primitive attribute being merged, the entitled value of the primary attribute,
It is the mapping relations of value foundation using the original property value being merged as key, the primary attribute value, with the primary attribute
The mapping relations that value is key, the original property value being merged is value foundation, with the entitled key of the primary attribute, the basis
Attribute value is the mapping relations that value is established.
Optionally, the corresponding primary attribute name of the primitive attribute name by the end article and the primary attribute name
Each primary attribute name in set is compared, with determination attribute-name to be modified, comprising: according to the original category of the end article
The mapping relations of property name and the primitive attribute name being merged and primary attribute name, obtain the original category of the end article
The property corresponding primary attribute name of name；By the corresponding primary attribute name of the primitive attribute name of the end article and the primary attribute
Primary attribute name in name set is compared one by one, and the primary attribute name conduct in different primary attribute name set will be present
Attribute-name to be modified.
Optionally, each primary attribute value in the statistics primary attribute value set goes out occurrence in merchandise news
Number, confirms that the original property value of the end article is different from the primary attribute value that corresponding frequency of occurrence is most, goes out by described in
The most primary attribute value of occurrence number is as attribute value to be modified, comprising: according to the attribute-name to be modified and the basis
The mapping relations of attribute-name and the original property value being merged obtain the corresponding original category being merged of the attribute-name to be modified
Property value；Confirm that there are the corresponding original property values being merged of the attribute-name to be modified in the merchandise news, by the quilt
Combined original property value is mapped as the primary attribute value；The primary attribute value that statistics mapping obtains is believed in the commodity
Frequency of occurrence in breath confirms the original property value of the end article and the most primary attribute value of corresponding frequency of occurrence not
Together, using the most primary attribute value of the frequency of occurrence as attribute value to be modified.
To achieve the above object, according to an aspect of an embodiment of the present invention, it provides and a kind of improves end article attribute
Device.
A kind of device for improving end article attribute of the embodiment of the present invention, comprising: module is obtained, for according to target quotient
The classification of product obtains the corresponding primary attribute name set of the classification and primary attribute value set；Attribute-name to be modified determines mould
Block, for by each base in the corresponding primary attribute name of the primitive attribute name of the end article and the primary attribute name set
Plinth attribute-name is compared, with determination attribute-name to be modified；Attribute value determining module to be modified, for counting the primary attribute
Frequency of occurrence of each primary attribute value in merchandise news in value set, confirm the original property value of the end article with it is right
The most primary attribute value of the frequency of occurrence answered is different, using the most primary attribute value of the frequency of occurrence as attribute to be modified
Value；Modified module, for modifying the category of the end article according to the attribute-name to be modified and the attribute value to be modified
Property.
Optionally, described device further include: establish module, be each for the item property data according to each classification
The primary attribute name set and a primary attribute value set are established in classification respectively；Wherein, the item property
Data include the primitive attribute name and corresponding original property value.
Optionally, described to establish module, it is also used to: the identical primitive attribute name of meaning in each classification is identical with meaning
Original property value merge respectively；By the most original category of frequency of occurrence in the primitive attribute name being merged in each classification
Property primary attribute name of the name as the classification, by most original of frequency of occurrence in the original property value being merged in each classification
Primary attribute value of the attribute value as the classification；And all primary attribute names of each classification constitute the basis of the classification
Attribute-name set, all primary attribute values constitute the primary attribute value set of the classification.
Optionally, described device further include: bigraph (bipartite graph) constructs module, for constructing the bigraph (bipartite graph) of each classification.
Optionally, described device further include: mapping relations establish module, for passing through the row's of falling rope according to the bigraph (bipartite graph)
The mode of drawing establishes mapping relations；Wherein, the mapping relations include with the entitled key of the primitive attribute being merged, the basis
The mapping relations that the entitled value of attribute is established are that value is established using the original property value being merged as key, the primary attribute value
Mapping relations, using the primary attribute value as key, the original property value being merged be value establish mapping relations, with institute
State the entitled key of primary attribute, the mapping relations that the primary attribute value is value foundation.
Optionally, the attribute-name determining module to be modified, is also used to: according to the primitive attribute name of the end article with
And the mapping relations of the primitive attribute name being merged and primary attribute name, the primitive attribute name for obtaining the end article are right
The primary attribute name answered；And by the corresponding primary attribute name of the primitive attribute name of the end article and the primary attribute name
Primary attribute name in set is compared one by one, will be present primary attribute name in different primary attribute name set be used as to
Modify attribute-name.
Optionally, the attribute value determining module to be modified, is also used to: according to the attribute-name to be modified and the base
The mapping relations of plinth attribute-name and the original property value being merged, obtain the attribute-name to be modified it is corresponding be merged it is original
Attribute value；Confirm that there are the corresponding original property values being merged of the attribute-name to be modified in the merchandise news, it will be described
The original property value being merged is mapped as the primary attribute value；And the primary attribute value that statistics mapping obtains is described
Frequency of occurrence in merchandise news confirms that the original property value of the end article basis most with corresponding frequency of occurrence belongs to
Property value it is different, using the most primary attribute value of the frequency of occurrence as attribute value to be modified.
To achieve the above object, according to an embodiment of the present invention in another aspect, providing a kind of electronic equipment.
The a kind of electronic equipment of the embodiment of the present invention, comprising: one or more processors；Storage device, for storing one
A or multiple programs, when one or more of programs are executed by one or more of processors, so that one or more
A processor realizes a kind of method for improving end article attribute of the embodiment of the present invention.
To achieve the above object, according to an embodiment of the present invention in another aspect, providing a kind of computer-readable medium.
A kind of computer-readable medium of the embodiment of the present invention, is stored thereon with computer program, and described program is processed
A kind of method for improving end article attribute of the embodiment of the present invention is realized when device executes.
One embodiment in foregoing invention has the following advantages that or the utility model has the advantages that the primitive attribute for passing through end article
The primary attribute name set and primary attribute value collection that name, original property value and the item property data according to each classification are established
Close, determine end article attribute-name to be modified and attribute value to be modified, and then modify item property, avoid manually participating in, imitate
Rate is high, accuracy rate is high；It is promoted based on the attribute of bigraph (bipartite graph) modification end article so that item property data are more accurate complete
User experience.
Further effect possessed by above-mentioned non-usual optional way adds hereinafter in conjunction with specific embodiment
With explanation.
Detailed description of the invention
Attached drawing for a better understanding of the present invention, does not constitute an undue limitation on the present invention.Wherein:
Fig. 1 is the schematic diagram of the key step of the method according to an embodiment of the present invention for improving end article attribute；
Fig. 2 is the main flow schematic diagram of the method according to an embodiment of the present invention for improving end article attribute；
Fig. 3 is the schematic diagram of the main modular of the device according to an embodiment of the present invention for improving end article attribute；
Fig. 4 is that the embodiment of the present invention can be applied to exemplary system architecture figure therein；
Fig. 5 is the structural schematic diagram for being suitable for the computer installation of the electronic equipment to realize the embodiment of the present invention.
Specific embodiment
Below in conjunction with attached drawing, an exemplary embodiment of the present invention will be described, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
Fig. 1 is the schematic diagram of the key step of the method according to an embodiment of the present invention for improving end article attribute.Such as Fig. 1
Shown, the method for improving end article attribute of the embodiment of the present invention mainly includes the following steps:
Step S101: it according to the classification of end article, obtains the corresponding primary attribute name set of the classification and basis belongs to
Property value set.Wherein, the end article is to need to carry out the perfect any commodity of attribute, and attribute, which improves, for example can be completion
(amendment is for the incorrect feelings of item property data for (completion is for the incomplete situation of item property data) or amendment
Condition), the item property data include primitive attribute name and corresponding raw value.In addition, it is necessary to obtain in advance more as far as possible
The item property data of type, and according to the item property data establish each classification primary attribute name set and corresponding basis
Attribute value, when needing to improve end article attribute, the primary attribute name set and corresponding basis for directly acquiring the classification belong to
Property value.
Step S102: by the corresponding primary attribute name of the primitive attribute name of the end article and the primary attribute name collection
Each primary attribute name in conjunction is compared, with determination attribute-name to be modified.The step is needed first according to the end article
The mapping relations of primitive attribute name and the primitive attribute name being merged and primary attribute name, obtain the original of the end article
The corresponding primary attribute name of attribute-name；Then by the corresponding primary attribute name of the primitive attribute name of the end article and the base
Primary attribute name in plinth attribute-name set is compared one by one, and the primary attribute in different primary attribute name set will be present
Name is used as attribute-name to be modified.Wherein, the primitive attribute being merged is entitled in advance by the identical original of meaning in each classification
What beginning attribute-name obtained after merging respectively.
Step S103: it counts each primary attribute value in the primary attribute value set and goes out occurrence in merchandise news
Number, confirms that the original property value of the end article is different from the primary attribute value that corresponding frequency of occurrence is most, goes out by described in
The most primary attribute value of occurrence number is as attribute value to be modified.The step is needed first according to the attribute-name to be modified and institute
The mapping relations of original property value stating primary attribute name and being merged, obtain that the attribute-name to be modified is corresponding to be merged
Original property value；Confirm that there are the corresponding primitive attributes being merged of the attribute-name to be modified in the merchandise news later
Value, is mapped as the primary attribute value for the original property value being merged；The basis that finally statistics mapping obtains belongs to
Frequency of occurrence of the property value in the merchandise news confirms the original property value of the end article and corresponding frequency of occurrence most
More primary attribute values is different, using the most primary attribute value of the frequency of occurrence as attribute value to be modified.Wherein, the quilt
Combined original property value obtains after in advance merging the identical original property value of meaning in each classification respectively.
Step S104: according to the attribute-name to be modified and the attribute value to be modified, the category of the end article is modified
Property.Item property data according to the attribute-name to be modified and the attribute value modification end article to be modified.
In the preferred embodiment of the present invention, item property data are obtained first from Data Mart, due to commodity category
There are specification attribute and non-specification attributes in property, it is therefore desirable to which both types are separated processing.Wherein, the specification attribute and
The judgement of non-specification attribute needs to preset judgment criteria, for example can set digital and English shared in original property value
Ratio is more than 80%, then is determined as specification attribute, if being determined as non-specification attribute less than 80%.For example, primitive attribute is entitled
The accounting of weight, original property value 10g, number and English is 100%, then the attribute is specification attribute；Primitive attribute name
For color, original property value is green, and number and English accounting are 0%, then the attribute is non-specification attribute.The present invention is real
The item property that example is applied suitable for non-specification attribute is perfect.
Fig. 2 is the main flow schematic diagram of the method according to an embodiment of the present invention for improving end article attribute.Such as Fig. 2 institute
Show, the method for improving end article attribute of the embodiment of the present invention mainly comprises the steps that
Step S201: the item property data of each classification are obtained from Data Mart.Data Mart is one from operation
Data and it is other be some special professional's community services data sources in collect the warehouses of data.The classification of commodity
Refer to the process of that commodity are divided into several classifications by attribute and feature according to commodity.Item property data include primitive attribute
Name and corresponding original property value, primitive attribute name such as color, material, original property value such as green, linen-cotton.In embodiment
By Spark from the item property data for obtaining each classification in itself transaction platform and competitor's transaction platform in Data Mart,
Such as the item property data of the classification such as men's clothing, women's dress, electric appliance.Wherein, Spark aims at large-scale data processing and designs
The computing engines of Universal-purpose quick need the MapReduce's (mapping is concluded) of iteration suitable for data mining and machine learning etc.
Algorithm.The item property data of acquisition are more, subsequent more rationally, therefore to remove in embodiment when improving end article attribute
The item property data for obtaining itself transaction platform, also obtain the item property data of competitor's transaction platform.
Step S202: by the identical primitive attribute name of meaning in each classification and the identical original property value of meaning respectively into
Row merges.Meaning is identical in the primitive attribute name that will acquire by way of manually marking in embodiment merges, such as
In this classification of women's dress, color, commodity color in primitive attribute name are merged into color, by material, fabric, commodity fabric,
Commodity material merges into material；Meaning is identical in the original property value that will acquire by way of manually marking merges,
Still by taking this classification of women's dress as an example, original property value Green, green system, Green (green) are merged into green, by cotton
Fiber crops, linen-cotton fabric merge into linen-cotton.
Step S203: according to the amalgamation result of classification each in step S202, the original category that will be merged in each classification
Primary attribute name of the most primitive attribute name of frequency of occurrence as the classification, original by what is be merged in each classification in property name
Primary attribute value of the most original property value of frequency of occurrence as the classification in attribute value.Such as in this classification of women's dress,
Color occurs 16 times in the primitive attribute name being merged, and commodity color occurs 4 times, then using color as a primary attribute name；
In the primitive attribute name being merged material occur 12 times, fabric occur 10 times, commodity fabric occur 6 times, commodity material occur 8
It is secondary, then using material as another primary attribute name.The acquisition modes of primary attribute value are identical as primary attribute name.
Step S204: all primary attribute names of each classification constitute the primary attribute name set of the classification, own
Primary attribute value constitutes the primary attribute value set of the classification.Such as in this classification of women's dress, primary attribute name may include
Color, material etc., the corresponding primary attribute value of color may include green, red, yellow etc., the corresponding primary attribute name of material
It may include linen-cotton, fiber, silk etc., all primary attribute names of the classification constitute the primary attribute name set of the classification,
All primary attribute values constitute the primary attribute value set of the classification, and primary attribute name set and primary attribute value set are constituted
Primary attribute set.
Step S205: according to the corresponding relationship of primary attribute name in each classification and the primitive attribute name being merged, basis
The corresponding relationship and primary attribute name of attribute value and combined original property value and the corresponding relationship of the primary attribute value, structure
Build the bigraph (bipartite graph) of each classification.Wherein, bigraph (bipartite graph) is one of graph theory particular module, if G=(V, E) is a non-directed graph,
If vertex V may be partitioned into two mutually disjoint subsets (A, B), and two tops associated by each edge (i, j) in figure
Point i and j is belonging respectively to the two different vertex sets (i in A, j in B), then figure G is referred to as a bigraph (bipartite graph).
Step S206: four mapping relations are established according to the bigraph (bipartite graph)；Wherein, the mapping relations include to be merged
The entitled key of primitive attribute (Key), primary attribute it is entitled value (Value) establish mapping relations, with the primitive attribute being merged
Value is Key, primary attribute value is mapping relations that Value is established, with primary attribute value is Key, the original property value that is merged
It is the mapping relations that Value is established with the entitled Key of primary attribute, primary attribute value for the mapping relations that Value is established.Implement
It can be established by inverted index mode in example, above-mentioned mapping relations can also be established by the associated mode of multilist.
Step S207: according to the classification of end article, the corresponding primary attribute set of the classification is obtained.Wherein, described
End article is any commodity obtained from database, and attribute, which improves, for example can be completion (completion is for item property number
According to incomplete situation) or amendment (amendment is for the incorrect situation of item property data).For example end article is female
Dress then obtains the corresponding primary attribute set of women's dress this classification.Assuming that the entitled color of primary attribute in primary attribute set,
Material, style and style, corresponding primary attribute value are green, red, yellow, linen-cotton, fiber, silk, surplus, middle surplus,
Shortage of money, academic attitude, street corner wind, commuting wind.
Step S208: obtaining the commodity data of end article, loops through the primitive attribute name in item property data, root
According to the mapping relations of the primitive attribute name and primary attribute name that are merged, each primitive attribute name for obtaining end article is corresponding
Primary attribute name.It include SKU (product Unified number, every kind of product are corresponding with unique SKU), item property number in commodity data
According to and merchandise news, merchandise news include commodity title, specifications parameter and descriptive labelling.Such as the primitive attribute name of end article
For commodity material, style and style, then the entitled material of corresponding primary attribute, style and style.
Step S209: by corresponding with the end article point of the corresponding primary attribute name of each primitive attribute name of end article
The primary attribute name set of class is compared one by one, if the two is not exactly the same, thens follow the steps S210；If the two is complete
It is identical, then follow the steps S211.The not exactly the same situation of the two is illustrated below:
Embodiment one: if the entitled material of the corresponding all primary attributes of each primitive attribute name of end article, style,
Style, quantity are 3；And the entitled face of all primary attributes in the primary attribute name set of the corresponding classification of the end article
Color, material, style, style, quantity are 4, then illustrate that the item property data of the end article are imperfect, will be above two
Primary attribute name is compared one by one, finds out the primary attribute name " color " lacked.
Embodiment two: if the entitled weight of the corresponding all primary attributes of each primitive attribute name of end article, material,
Style, style, and the entitled color of all primary attributes, material in the representative name attribute set of the corresponding classification of the end article,
Style, style, then it can be concluded that " color " in primary attribute name set is corresponding with the primitive attribute name of end article " heavy
Amount " is not identical.
Step S210: the primary attribute name in different primary attribute name set will be present as attribute-name to be modified, root
According to the attribute-name to be modified and the mapping relations of the primary attribute name and the original property value being merged, obtain it is described to
Modify the corresponding original property value being merged of attribute-name.The attribute-name to be modified is that the commodity need perfect attribute-name.
It will need to improve below to be divided into needing to fill (corresponding embodiment one) and needing to correct (corresponding embodiment two) two kinds of situations and distinguish
It is illustrated: in embodiment one, attribute-name to be modified that the primary attribute name " color " lacked as needs to fill.Embodiment two
In, " weight " this primary attribute is entitled to need modified attribute-name to be modified.
In embodiment in the corresponding original property value being merged of the acquisition attribute-name to be modified, first according to be modified
The mapping relations of attribute-name and primary attribute name and primary attribute value are closed with the entitled Key of attribute to be modified by above-mentioned mapping
System obtains the corresponding primary attribute value of attribute-name to be modified；Then reflecting according to primary attribute value and the original property value that is merged
Relationship is penetrated, is that Key obtains the corresponding original category being merged of attribute-name to be modified by above-mentioned mapping relations with primary attribute value
Property value.For example, the entitled color of attribute to be modified of end article, then the corresponding original property value being merged is green, green
System, Green, red, red colour system, Red, yellow, yellow class, Yellow.
Step S211: it according to the corresponding primary attribute name of each primitive attribute name and the primary attribute name and is merged
Original property value mapping relations, obtain the corresponding original property value being merged of each primitive attribute name.It is preferred one
In embodiment, which only obtains in primitive attribute name removal and needs corresponding after modified primitive attribute name be merged
Original property value.
Step S212: the original property value being merged obtained according to step S210 and step S211, in merchandise news ratio
If in commodity title, descriptive labelling and specifications parameter search to find out the original property value being merged, be recorded in commodity title,
The corresponding number occurred in descriptive labelling and specifications parameter, and be that Key foundation is merged with the original property value being merged
The mapping relations of original property value and primary attribute value obtain corresponding primary attribute value.For example occur in commodity title Green
1 time, there are 5 times, red appearance 2 times in specifications parameter Green system, Green occurs 1 time in descriptive labelling, then passes through mapping
Relationship finds out green, green system, red primary attribute value corresponding with Green, i.e., green and red.
Step S213: the obtained primary attribute value going out in the merchandise news is mapped in statistic procedure S212
Occurrence number confirms that the original property value of the end article is different from the primary attribute value that corresponding frequency of occurrence is most, will go out
The most primary attribute value of occurrence number is as attribute value to be modified.Such as the entitled color of primitive attribute of end article, original category
Property value be red, mapped the obtained corresponding primary attribute value of the primitive attribute name for green and red, as fruit green this
Frequency of occurrence of the primary attribute value in merchandise news then needs for original property value to be revised as green more than red frequency of occurrence
Color, therefore it regard green as attribute value to be modified；If fruit green is identical with red frequency of occurrence, then according to parameter of regularity > quotient
Product title > descriptive labelling (this is sequentially obtained by artificial experience) sequence, takes the primary attribute value more than frequency of occurrence as to be repaired
Change attribute value；If red frequency of occurrence is not required to modify more than the frequency of occurrence of green, original property value.
Step S214: according to the attribute-name to be modified and the attribute value to be modified determined, end article is modified
Item property.The step is the item property data according to the attribute-name to be modified and attribute value to be modified to end article
It is filled or corrects.
Step S215: according to the mapping relations, based on all item property data unification of the end article
Attribute-name and primary attribute value.Wherein the item property data in the step include primitive attribute name, it is original property value, to be modified
Attribute-name and attribute value to be modified.
The method for improving end article attribute through the embodiment of the present invention can be seen that the original category by end article
Property name, original property value and according to each classification item property data establish primary attribute name set and primary attribute value collection
Close, determine end article attribute-name to be modified and attribute value to be modified, and then modify item property, avoid manually participating in, imitate
Rate is high, accuracy rate is high；It is promoted based on the attribute of bigraph (bipartite graph) modification end article so that item property data are more accurate complete
User experience.
Fig. 3 is the schematic diagram of the main modular of the device according to an embodiment of the present invention for improving end article attribute.Such as Fig. 3
Shown, the device 300 for improving end article attribute of the embodiment of the present invention specifically includes that
Obtain module 301, for the classification according to end article, obtain the corresponding primary attribute name set of the classification and
Primary attribute value set.Wherein, the end article is to need to carry out the perfect any commodity of attribute, and attribute improves for example can be with
Be completion (completion be for the incomplete situation of item property data) or amendment (amendment be for item property data not just
True situation), the item property data include primitive attribute name and corresponding raw value.In addition, the basis respectively classified
Attribute-name set and primary attribute value set are that the item property data for the multiple types as far as possible that foundation obtains in advance generate.
Attribute-name determining module 302 to be modified, for by the corresponding primary attribute of primitive attribute name of the end article
Name is compared with each primary attribute name in the primary attribute name set, with determination attribute-name to be modified.The module needs root
According to the primitive attribute name of the end article and the mapping relations of the primitive attribute name and primary attribute name that are merged, institute is obtained
State the corresponding primary attribute name of primitive attribute name of end article；And by the corresponding base of primitive attribute name of the end article
Plinth attribute-name is compared one by one with the primary attribute name in the primary attribute name set, and different primary attribute names will be present
Primary attribute name in set is as attribute-name to be modified.Wherein, the primitive attribute that is merged is entitled preparatory will each divide
The identical primitive attribute name of meaning obtains after merging respectively in class.
Attribute value determining module 303 to be modified, each primary attribute value for counting in the primary attribute value set exist
Frequency of occurrence in merchandise news confirms that the original property value of the end article basis most with corresponding frequency of occurrence belongs to
Property value it is different, using the most primary attribute value of the frequency of occurrence as attribute value to be modified.The module need to be according to described to be repaired
Change the mapping relations of attribute-name and the primary attribute name and the original property value being merged, obtains the attribute-name to be modified
The corresponding original property value being merged；Confirm in the merchandise news and is merged there are the attribute-name to be modified is corresponding
The original property value being merged is mapped as the primary attribute value by original property value；And the institute that statistics mapping obtains
State frequency of occurrence of the primary attribute value in the merchandise news, confirm the original property value of the end article with it is corresponding go out
The most primary attribute value of occurrence number is different, using the most primary attribute value of the frequency of occurrence as attribute value to be modified.Its
In, the original property value being merged is in advance will be after the identical original property value of meaning merges respectively in each classification
It obtains.
Modified module 304, for modifying the target quotient according to the attribute-name to be modified and the attribute value to be modified
The attribute of product.Item property data according to the attribute-name to be modified and the attribute value modification end article to be modified.
In addition, the device 300 for improving end article attribute of the embodiment of the present invention can also include: to establish module, two
Figure building module, mapping relations establish module (not shown).It is described to establish module, for the commodity category according to each classification
Property data, for it is each classification establish the primary attribute name set and a primary attribute value set respectively；It is described
Bigraph (bipartite graph) constructs module, for constructing the bigraph (bipartite graph) of each classification；The mapping relations establish module, for according to described two
Figure, establishes the mapping relations by inverted index mode.
From the above, it can be seen that by the primitive attribute name of end article, original property value and according to each classification
Item property data establish primary attribute name set and primary attribute value set, determine the attribute-name to be modified of end article
With attribute value to be modified, and then item property is modified, avoids manually participating in, it is high-efficient, accuracy rate is high；Mesh is modified based on bigraph (bipartite graph)
The attribute of commodity is marked, so that item property data are more accurate complete, the user experience is improved.
Fig. 4 is shown can be using the method for the processing real-time messages of the embodiment of the present invention or the system of processing real-time messages
Exemplary system architecture 400.
As shown in figure 4, system architecture 400 may include terminal device 401,402,403, network 404 and server 405.
Network 404 between terminal device 401,402,403 and server 405 to provide the medium of communication link.Network 404 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 401,402,403 and be interacted by network 404 with server 405, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 401,402,403
(merely illustrative) such as the application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform softwares.
Terminal device 401,402,403 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 405 can be to provide the server of various services, such as utilize terminal device 401,402,403 to user
Generated click event provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to receiving
The data such as click data, content of text analyze etc. processing, and (such as target push information, product are believed by processing result
Breath -- merely illustrative) feed back to terminal device.
It should be noted that improving the method for end article attribute provided by the embodiment of the present application generally by server
405 execute, and correspondingly, the device for improving end article attribute is generally positioned in server 405.
It should be understood that the number of terminal device, network and server in Fig. 4 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
According to an embodiment of the invention, the present invention also provides a kind of electronic equipment and a kind of computer-readable medium.
Electronic equipment of the invention includes: one or more processors；Storage device, for storing one or more journeys
Sequence, when one or more of programs are executed by one or more of processors, so that one or more of processors are real
A kind of method for improving end article attribute of the existing embodiment of the present invention.
Computer-readable medium of the invention is stored thereon with computer program, real when described program is executed by processor
A kind of method for improving end article attribute of the existing embodiment of the present invention.
Below with reference to Fig. 5, it illustrates the computer systems 500 being suitable for realize the electronic equipment of the embodiment of the present invention
Structural schematic diagram.Electronic equipment shown in Fig. 5 is only an example, function to the embodiment of the present invention and should not use model
Shroud carrys out any restrictions.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into the program in random access storage device (RAM) 503 from storage section 508 and
Execute various movements appropriate and processing.In RAM 503, also it is stored with computer system 500 and operates required various programs
And data.CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input/output (I/O) interface 505
It is connected to bus 504.
I/O interface 505 is connected to lower component: the importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 508 including hard disk etc.；
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net executes communication process.Driver 510 is also connected to I/O interface 505 as needed.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 510, in order to read from thereon
Computer program be mounted into storage section 508 as needed.
Particularly, disclosed embodiment, the process of key step figure description above may be implemented as counting according to the present invention
Calculation machine software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable
Computer program on medium, the computer program include the program code for executing method shown in key step figure.?
In such embodiment, which can be downloaded and installed from network by communications portion 509, and/or from can
Medium 511 is dismantled to be mounted.When the computer program is executed by central processing unit (CPU) 501, system of the invention is executed
The above-mentioned function of middle restriction.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in module involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described module also can be set in the processor, for example, can be described as: a kind of processor packet
It includes and obtains module, attribute-name determining module to be modified, attribute value determining module to be modified and modified module.Wherein, these modules
Title do not constitute the restriction to the module itself under certain conditions, for example, obtain module be also described as " according to
The classification of end article obtains the module of the classification corresponding primary attribute name set and primary attribute value set ".
As on the other hand, the present invention also provides a kind of computer-readable medium, which be can be
Included in equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying equipment.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the equipment, makes
Obtaining the equipment includes: the classification according to end article, obtains the corresponding primary attribute name set of the classification and primary attribute value
Set；By each basis in the corresponding primary attribute name of the primitive attribute name of the end article and the primary attribute name set
Attribute-name is compared, with determination attribute-name to be modified；Each primary attribute value in the primary attribute value set is counted in quotient
Frequency of occurrence in product information confirms the original property value of the end article primary attribute most with corresponding frequency of occurrence
Value is different, using the most primary attribute value of the frequency of occurrence as attribute value to be modified；According to the attribute-name to be modified and
The attribute value to be modified, modifies the attribute of the end article.
From the above, it can be seen that by the primitive attribute name of end article, original property value and according to each classification
Item property data establish primary attribute name set and primary attribute value set, determine the attribute-name to be modified of end article
With attribute value to be modified, and then item property is modified, avoids manually participating in, it is high-efficient, accuracy rate is high；Mesh is modified based on bigraph (bipartite graph)
The attribute of commodity is marked, so that item property data are more accurate complete, the user experience is improved.
Method provided by the embodiment of the present invention can be performed in the said goods, has the corresponding functional module of execution method and has
Beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to method provided by the embodiment of the present invention.
Above-mentioned specific embodiment, does not constitute a limitation on the scope of protection of the present invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and substitution can occur.It is any
Made modifications, equivalent substitutions and improvements etc. within the spirit and principles in the present invention, should be included in the scope of the present invention
Within.
Claims (16)
1. a kind of method for improving end article attribute characterized by comprising
According to the classification of end article, the corresponding primary attribute name set of the classification and primary attribute value set are obtained；
By each basis in the corresponding primary attribute name of the primitive attribute name of the end article and the primary attribute name set
Attribute-name is compared, with determination attribute-name to be modified；
Frequency of occurrence of each primary attribute value in merchandise news in the primary attribute value set is counted, confirms the target
The original property value of commodity is different from the primary attribute value that corresponding frequency of occurrence is most, by the most basis of the frequency of occurrence
Attribute value is as attribute value to be modified；
According to the attribute-name to be modified and the attribute value to be modified, the attribute of the end article is modified.
2. the method according to claim 1, wherein before the step of classification according to end article, also
Include: the item property data according to each classification, establishes the primary attribute name set and one respectively for each classification
A primary attribute value set；Wherein, the item property data include the primitive attribute name and corresponding primitive attribute
Value.
3. according to the method described in claim 2, it is characterized in that, the item property data according to each classification, are every
The primary attribute name set and a primary attribute value set are established in a classification respectively, comprising:
The identical primitive attribute name of meaning in each classification and the identical original property value of meaning are merged respectively；
Using the most primitive attribute name of frequency of occurrence in the primitive attribute name being merged in each classification as the basis of the classification
Attribute-name, using the most original property value of frequency of occurrence in the original property value being merged in each classification as the base of the classification
Plinth attribute value；
All primary attribute names of each classification constitute the primary attribute name set of the classification, and all primary attribute values are constituted
The primary attribute value set of the classification.
4. according to the method described in claim 3, it is characterized in that, in the primitive attribute name that will be merged in each classification
Primary attribute name of the most primitive attribute name of frequency of occurrence as the classification, the original property value that will be merged in each classification
It is after the step of primary attribute value of the most original property value of middle frequency of occurrence as the classification and described according to target quotient
Before the step of classification of product, further includes: construct the bigraph (bipartite graph) of each classification.
5. according to the method described in claim 4, it is characterized in that, after the step of the bigraph (bipartite graph) of each classification of the building with
And each base in the corresponding primary attribute name of the primitive attribute name by the end article and the primary attribute name set
Before the step of plinth attribute-name is compared, attribute-name to be modified with determination, further includes: according to the bigraph (bipartite graph), pass through the row of falling
Indexed mode establishes mapping relations；Wherein, the mapping relations include with the entitled key of the primitive attribute being merged, the base
The mapping relations that the entitled value of plinth attribute is established, are that value is built by key, the primary attribute value of the original property value being merged
Vertical mapping relations are the mapping relations of value foundation using the primary attribute value as key, the original property value being merged, with
The entitled key of the primary attribute, the primary attribute value are the mapping relations that value is established.
6. the method according to claim 3 or 5, which is characterized in that the primitive attribute name by the end article is right
The primary attribute name answered is compared with each primary attribute name in the primary attribute name set, with determination attribute to be modified
Name, comprising:
According to the mapping of the primitive attribute name of the end article and the primitive attribute name and primary attribute name being merged
Relationship obtains the corresponding primary attribute name of primitive attribute name of the end article；
Basis in the corresponding primary attribute name of the primitive attribute name of the end article and the primary attribute name set is belonged to
Property name is compared one by one, and the primary attribute name in different primary attribute name set will be present as attribute-name to be modified.
7. the method according to claim 3 or 5, which is characterized in that each in the statistics primary attribute value set
Frequency of occurrence of the primary attribute value in merchandise news confirms the original property value of the end article and corresponding frequency of occurrence
Most primary attribute values is different, using the most primary attribute value of the frequency of occurrence as attribute value to be modified, comprising:
According to the attribute-name to be modified and the mapping relations of the primary attribute name and the original property value being merged, obtain
The corresponding original property value being merged of the attribute-name to be modified；
Confirm in the merchandise news there are the corresponding original property value being merged of the attribute-name to be modified, is closed described
And original property value be mapped as the primary attribute value；
Frequency of occurrence of the primary attribute value that statistics mapping obtains in the merchandise news, confirms the end article
Original property value is different from the primary attribute value that corresponding frequency of occurrence is most, by the most primary attribute value of the frequency of occurrence
As attribute value to be modified.
8. a kind of device for improving end article attribute characterized by comprising
Module is obtained, for the classification according to end article, the corresponding primary attribute name set of the classification is obtained and basis belongs to
Property value set；
Attribute-name determining module to be modified, for by the corresponding primary attribute name of the primitive attribute name of the end article with it is described
Each primary attribute name in primary attribute name set is compared, with determination attribute-name to be modified；
Attribute value determining module to be modified, for counting each primary attribute value in the primary attribute value set in merchandise news
In frequency of occurrence, confirm the original property value of the end article and the most primary attribute value of corresponding frequency of occurrence not
Together, using the most primary attribute value of the frequency of occurrence as attribute value to be modified；
Modified module, for modifying the category of the end article according to the attribute-name to be modified and the attribute value to be modified
Property.
9. device according to claim 8, which is characterized in that described device further include: module is established, for according to each
The item property data of classification establish the primary attribute name set and a primary attribute for each classification respectively
Value set；Wherein, the item property data include the primitive attribute name and corresponding original property value.
10. device according to claim 9, which is characterized in that it is described to establish module, it is also used to:
The identical primitive attribute name of meaning in each classification and the identical original property value of meaning are merged respectively；
Using the most primitive attribute name of frequency of occurrence in the primitive attribute name being merged in each classification as the basis of the classification
Attribute-name, using the most original property value of frequency of occurrence in the original property value being merged in each classification as the base of the classification
Plinth attribute value；And
All primary attribute names of each classification constitute the primary attribute name set of the classification, and all primary attribute values are constituted
The primary attribute value set of the classification.
11. device according to claim 10, which is characterized in that described device further include: bigraph (bipartite graph) constructs module, is used for
Construct the bigraph (bipartite graph) of each classification.
12. device according to claim 11, which is characterized in that described device further include: mapping relations establish module, use
According to the bigraph (bipartite graph), mapping relations are established by inverted index mode；Wherein, the mapping relations include being closed with described
And the entitled key of primitive attribute, the primary attribute it is entitled value establish mapping relations, with the original property value being merged
It is the mapping relations that value is established for key, the primary attribute value, using the primary attribute value as key, the original category being merged
Property value be value establish mapping relations, with the entitled key of the primary attribute, the primary attribute value be value foundation mapping relations.
13. device described in 0 or 12 according to claim 1, which is characterized in that the attribute-name determining module to be modified is also used
In:
According to the mapping of the primitive attribute name of the end article and the primitive attribute name and primary attribute name being merged
Relationship obtains the corresponding primary attribute name of primitive attribute name of the end article；And
Basis in the corresponding primary attribute name of the primitive attribute name of the end article and the primary attribute name set is belonged to
Property name is compared one by one, and the primary attribute name in different primary attribute name set will be present as attribute-name to be modified.
14. device described in 0 or 12 according to claim 1, which is characterized in that the attribute value determining module to be modified is also used
In:
According to the attribute-name to be modified and the mapping relations of the primary attribute name and the original property value being merged, obtain
The corresponding original property value being merged of the attribute-name to be modified；
Confirm in the merchandise news there are the corresponding original property value being merged of the attribute-name to be modified, is closed described
And original property value be mapped as the primary attribute value；And
Frequency of occurrence of the primary attribute value that statistics mapping obtains in the merchandise news, confirms the end article
Original property value is different from the primary attribute value that corresponding frequency of occurrence is most, by the most primary attribute value of the frequency of occurrence
As attribute value to be modified.
15. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-7.
16. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1-7 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711292885.7A CN109903105B (en) | 2017-12-08 | 2017-12-08 | Method and device for perfecting target commodity attributes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711292885.7A CN109903105B (en) | 2017-12-08 | 2017-12-08 | Method and device for perfecting target commodity attributes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109903105A true CN109903105A (en) | 2019-06-18 |
| CN109903105B CN109903105B (en) | 2021-11-30 |
Family
ID=66940243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711292885.7A Active CN109903105B (en) | 2017-12-08 | 2017-12-08 | Method and device for perfecting target commodity attributes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109903105B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110971974A (en) * | 2019-12-06 | 2020-04-07 | 北京小米移动软件有限公司 | Configuration parameter creating method, device, terminal and storage medium |
| CN112699672A (en) * | 2019-10-23 | 2021-04-23 | 北京沃东天骏信息技术有限公司 | Method and device for selecting articles |
| CN113362093A (en) * | 2020-03-05 | 2021-09-07 | 北京沃东天骏信息技术有限公司 | Method, device and equipment for determining product target attribute and readable storage medium |
| CN113609112A (en) * | 2021-08-02 | 2021-11-05 | 北京值得买科技股份有限公司 | E-commerce commodity attribute data standardization processing method and system |
| CN115063211A (en) * | 2022-08-16 | 2022-09-16 | 华能能源交通产业控股有限公司 | Method and device for acquiring commodity attribute data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332009A (en) * | 2011-09-02 | 2012-01-25 | 北京大学 | Relational query method implemented on large-scale data set |
| CN103116639A (en) * | 2013-02-20 | 2013-05-22 | 新浪网技术(中国)有限公司 | Item recommendation method and system based on user-item bipartite model |
| CN103578015A (en) * | 2012-08-07 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and device for achieving commodity attribute navigation |
| CN106033456A (en) * | 2015-03-18 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Method and device for correcting attribute values of background attributes of goods |
| CN106776834A (en) * | 2016-11-28 | 2017-05-31 | 中通服公众信息产业股份有限公司 | A kind of data analysis based on index is from access method and system |
-
2017
- 2017-12-08 CN CN201711292885.7A patent/CN109903105B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102332009A (en) * | 2011-09-02 | 2012-01-25 | 北京大学 | Relational query method implemented on large-scale data set |
| CN103578015A (en) * | 2012-08-07 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and device for achieving commodity attribute navigation |
| CN103116639A (en) * | 2013-02-20 | 2013-05-22 | 新浪网技术(中国)有限公司 | Item recommendation method and system based on user-item bipartite model |
| CN106033456A (en) * | 2015-03-18 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Method and device for correcting attribute values of background attributes of goods |
| CN106776834A (en) * | 2016-11-28 | 2017-05-31 | 中通服公众信息产业股份有限公司 | A kind of data analysis based on index is from access method and system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699672A (en) * | 2019-10-23 | 2021-04-23 | 北京沃东天骏信息技术有限公司 | Method and device for selecting articles |
| CN112699672B (en) * | 2019-10-23 | 2024-04-05 | 北京沃东天骏信息技术有限公司 | Method and device for selecting articles |
| CN110971974A (en) * | 2019-12-06 | 2020-04-07 | 北京小米移动软件有限公司 | Configuration parameter creating method, device, terminal and storage medium |
| CN110971974B (en) * | 2019-12-06 | 2022-02-15 | 北京小米移动软件有限公司 | Configuration parameter creating method, device, terminal and storage medium |
| CN113362093A (en) * | 2020-03-05 | 2021-09-07 | 北京沃东天骏信息技术有限公司 | Method, device and equipment for determining product target attribute and readable storage medium |
| CN113609112A (en) * | 2021-08-02 | 2021-11-05 | 北京值得买科技股份有限公司 | E-commerce commodity attribute data standardization processing method and system |
| CN115063211A (en) * | 2022-08-16 | 2022-09-16 | 华能能源交通产业控股有限公司 | Method and device for acquiring commodity attribute data |
| CN115063211B (en) * | 2022-08-16 | 2022-11-11 | 华能能源交通产业控股有限公司 | Method and device for acquiring commodity attribute data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109903105B (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109903105A (en) | A kind of method and apparatus for improving end article attribute | |
| CN109697641A (en) | The method and apparatus for calculating commodity similarity | |
| CN108959633A (en) | It is a kind of that the method and apparatus of customer service are provided | |
| CN104346698B (en) | Based on the analysis of the food and drink member big data of cloud computing and data mining and checking system | |
| CN110232487A (en) | A kind of task allocating method and device | |
| CN110019258A (en) | The method and apparatus for handling order data | |
| CN109614402A (en) | Multidimensional data query method and device | |
| CN110245140A (en) | Data branch mailbox processing method and processing device, electronic equipment and computer-readable medium | |
| CN109002440A (en) | Method, apparatus and system for big data multidimensional analysis | |
| CN109634833A (en) | A kind of Software Defects Predict Methods and device | |
| CN110348771A (en) | The method and apparatus that a kind of pair of order carries out group list | |
| CN111489201A (en) | Method, device and storage medium for analyzing customer value | |
| CN108776692A (en) | Method and apparatus for handling information | |
| CN109214730A (en) | Information-pushing method and device | |
| CN109993179A (en) | The method and apparatus that a kind of pair of data are clustered | |
| Liao et al. | Extension innovation design of product family based on Kano requirement model | |
| CN110020376A (en) | Data linkage method and system | |
| CN109961199A (en) | A kind of method and apparatus for analyzing data fluctuations | |
| CN110309142A (en) | The method and apparatus of regulation management | |
| CN109978213A (en) | A kind of task path planning method and device | |
| CN110263791A (en) | A kind of method and apparatus in identification function area | |
| CN110335165A (en) | A kind of link prediction method and apparatus | |
| CN109977139A (en) | Data processing method and device based on type of structured query statement | |
| CN110362583A (en) | A kind of data processing method and device for multi-data source | |
| CN110309244A (en) | A kind of method and apparatus of object location |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |