CN110807095A - Article matching method and device - Google Patents
Article matching method and device Download PDFInfo
- Publication number
- CN110807095A CN110807095A CN201810863709.2A CN201810863709A CN110807095A CN 110807095 A CN110807095 A CN 110807095A CN 201810863709 A CN201810863709 A CN 201810863709A CN 110807095 A CN110807095 A CN 110807095A
- Authority
- CN
- China
- Prior art keywords
- article
- current
- target
- similarity
- attribute
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 239000003086 colorant Substances 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 20
- 238000010586 diagram Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000000835 fiber Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an article matching method and device, and relates to the technical field of computers. One embodiment of the method comprises: extracting the common attribute and the individual attribute of the current article from the article information of the current article, and extracting the common attribute and the individual attribute of the target article from the article information of the target article; determining similarity between the common attributes of the current item and the target item and similarity between the individual attributes of the current item and the target item; and determining the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determining the target article matched with the current article according to the matching degree. According to the embodiment, the individual attributes with the category characteristics and the common attributes of all articles are created according to different categories, full-quantity matching is not needed in the article matching process, the calculated quantity is small, and the efficiency is high; the article matching process can be automatically realized, the manual matching and checking process is omitted, and time and labor are saved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an article matching method and device.
Background
The virtual commodity is sold on the network, and the problems that different commodity descriptions are substantially the same when the virtual commodity is sold on the network, repeated purchase and difficult commodity selection occur when a user purchases the commodity, and the like, because the commodity descriptions with the same physical address and the same attribute are defined differently by each merchant. To merge duplicates first needs to find a homogenous good.
In the prior art, in order to find homogeneous commodities, a method of matching specified fields in commodity information in a full quantity manner is adopted for commodity matching.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
the full-quantity matching method has large calculation amount and low efficiency;
the information which cannot be matched in the fields in the full amount needs a large amount of manpower for verification, and time and labor are wasted.
Disclosure of Invention
In view of this, embodiments of the present invention provide an article matching method and apparatus, which create individual attribute fields with article characteristics and common attribute fields of all articles according to different article types, and do not require full matching in the article matching process, so that the calculation amount is small and the efficiency is high; the article matching process can be automatically realized, the manual matching and checking process is omitted, and time and labor are saved.
According to an aspect of an embodiment of the present invention, there is provided an article matching method.
An article matching method according to an embodiment of the present invention includes:
extracting the common attribute and the individual attribute of the current article from the article information of the current article, and extracting the common attribute and the individual attribute of the target article from the article information of the target article; the individual attribute is determined according to the category to which the current article belongs;
determining the similarity between the common attributes of the current article and the target article and the similarity between the individual attributes of the current article and the target article;
and determining the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determining the target article matched with the current article according to the matching degree.
Optionally, determining the matching degree between the current item and the target item according to the similarity between the common attributes and the similarity between the individual attributes includes:
extracting candidate target articles from the target articles, wherein the target articles with the similarity between the target articles and the individual attribute of the current article being greater than or equal to a preset individual threshold are extracted firstly, and then the template articles with the similarity between the target articles and the common attribute of the current article being greater than or equal to a preset similarity threshold are extracted according to the sequence of the priority of each common attribute from high to low until the number of the candidate target articles is greater than a preset number threshold;
and for each candidate target object, summing the similarity between the common attributes and the similarity between the individual attributes of the current object and the candidate target object to obtain the matching degree of the current object and the candidate target object.
Optionally, the similarity between the personality attributes of the current item and the target item is determined according to the following steps:
extracting attribute values of individual attributes of the current article from the article information of the current article;
judging whether the attribute values of the individual attributes of the current article exist in the article information of the target article; if all the objects exist, the similarity between the individual attributes of the current object and the target object is a first threshold value; if the current object and the target object do not exist, the similarity between the individual attributes of the current object and the target object is a second threshold value; and if the part exists, the similarity between the individual attributes of the current article and the target article is a third threshold value.
Optionally, the commonality attribute or the personality attribute comprises: a title; determining the similarity between the titles of the current item and the target item according to the following steps:
removing invalid characters and repeated characters in the titles of the current article and the target article to obtain an effective title of the current article and an effective title of the target article;
merging the effective titles of the current article and the effective titles of the target article, and then removing repeated characters in the effective titles to obtain merged titles;
determining the similarity between the titles of the current item and the target item according to the following formula:
simScore＝(L1+L2-T)/T
in the formula, simscope represents the similarity between the titles of the current item and the target item, L represents the character length of the valid title of the current item, L2 represents the character length of the valid title of the target item, and T represents the character length of the merged title.
Optionally, the commonality attribute or the personality attribute comprises: the model number; determining the similarity between the models of the current article and the target article according to the following steps:
if the attribute value of the model attribute of the current article or the target article is null, the similarity between the models of the current article and the target article is a fifth threshold value;
if the attribute values of the model attributes of the current article or the target article are the same, the similarity between the models of the current article and the target article is a fourth threshold value;
and if the attribute values of the model attributes of the current article or the target article are different, judging whether one of the attribute values is a subset of the other one, if so, determining that the similarity between the models of the current article and the target article is a seventh threshold, otherwise, determining that the similarity between the models of the current article and the target article is a sixth threshold.
Optionally, the commonality attribute or the personality attribute comprises: color; determining the similarity between the colors of the current article and the target article according to the following steps:
if the attribute value of the color attribute of the current article or the target article is null, the similarity between the colors of the current article and the target article is a ninth threshold value;
if the attribute values of the color attributes of the current article or the target article are the same, the similarity between the colors of the current article and the target article is an eighth threshold value;
if the attribute values of the color attributes of the current article or the target article are different, the similarity between the models of the current article and the target article is a tenth threshold.
Optionally, the commonality attribute or the personality attribute comprises: title word intersection; determining the similarity between the intersection of the title words of the current item and the target item according to the following steps:
performing word segmentation processing on the titles of the current article and the target article to obtain each word;
determining the number of intersections between each word corresponding to the title of the current article and each word corresponding to the title of the target article;
determining the similarity between the intersection of the title words of the current item and the target item according to the following formula:
Intersect Score＝O/A
in the formula, Intersect Score represents the similarity between the intersections of the titles and words of the current item and the target item, O represents the number of intersections, and a represents the number of words corresponding to the title of the current item and the title of the target item with longer character length.
According to an aspect of an embodiment of the present invention, there is provided an article matching method.
An article matching device according to an embodiment of the present invention includes:
the extraction module is used for extracting the common attribute and the individual attribute of the current article from the article information of the current article and extracting the common attribute and the individual attribute of the target article from the article information of the target article; the individual attribute is determined according to the category to which the current article belongs;
the determining module is used for determining the similarity between the common attributes of the current article and the target article and the similarity between the individual attributes of the current article and the target article;
and the matching module is used for determining the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determining the target article matched with the current article according to the matching degree.
Optionally, the determining, by the matching module, the matching degree between the current item and the target item according to the similarity between the common attributes and the similarity between the individual attributes includes:
extracting candidate target articles from the target articles, wherein the target articles with the similarity between the target articles and the individual attribute of the current article being greater than or equal to a preset individual threshold are extracted firstly, and then the template articles with the similarity between the target articles and the common attribute of the current article being greater than or equal to a preset similarity threshold are extracted according to the sequence of the priority of each common attribute from high to low until the number of the candidate target articles is greater than a preset number threshold;
and for each candidate target object, summing the similarity between the common attributes and the similarity between the individual attributes of the current object and the candidate target object to obtain the matching degree of the current object and the candidate target object.
Optionally, the determining module determines the similarity between the personality attributes of the current item and the target item according to the following steps:
extracting attribute values of individual attributes of the current article from the article information of the current article;
judging whether the attribute values of the individual attributes of the current article exist in the article information of the target article; if all the objects exist, the similarity between the individual attributes of the current object and the target object is a first threshold value; if the current object and the target object do not exist, the similarity between the individual attributes of the current object and the target object is a second threshold value; and if the part exists, the similarity between the individual attributes of the current article and the target article is a third threshold value.
Optionally, the commonality attribute or the personality attribute comprises: a title; the determining module determines similarity between the titles of the current item and the target item according to the following steps:
removing invalid characters and repeated characters in the titles of the current article and the target article to obtain an effective title of the current article and an effective title of the target article;
merging the effective titles of the current article and the effective titles of the target article, and then removing repeated characters in the effective titles to obtain merged titles;
determining the similarity between the titles of the current item and the target item according to the following formula:
simScore＝(L1+L2-T)/T
in the formula, simscope represents the similarity between the titles of the current item and the target item, L represents the character length of the valid title of the current item, L2 represents the character length of the valid title of the target item, and T represents the character length of the merged title.
Optionally, the commonality attribute or the personality attribute comprises: the model number; the determining module determines the similarity between the models of the current article and the target article according to the following steps:
if the attribute value of the model attribute of the current article or the target article is null, the similarity between the models of the current article and the target article is a fifth threshold value;
if the attribute values of the model attributes of the current article or the target article are the same, the similarity between the models of the current article and the target article is a fourth threshold value;
and if the attribute values of the model attributes of the current article or the target article are different, judging whether one of the attribute values is a subset of the other one, if so, determining that the similarity between the models of the current article and the target article is a seventh threshold, otherwise, determining that the similarity between the models of the current article and the target article is a sixth threshold.
Optionally, the commonality attribute or the personality attribute comprises: color; the determining module determines the similarity between the colors of the current article and the target article according to the following steps:
if the attribute value of the color attribute of the current article or the target article is null, the similarity between the colors of the current article and the target article is a ninth threshold value;
if the attribute values of the color attributes of the current article or the target article are the same, the similarity between the colors of the current article and the target article is an eighth threshold value;
if the attribute values of the color attributes of the current article or the target article are different, the similarity between the models of the current article and the target article is a tenth threshold.
Optionally, the commonality attribute or the personality attribute comprises: title word intersection; the determining module determines the similarity between the title word intersections of the current item and the target item according to the following steps:
performing word segmentation processing on the titles of the current article and the target article to obtain each word;
determining the number of intersections between each word corresponding to the title of the current article and each word corresponding to the title of the target article;
determining the similarity between the intersection of the title words of the current item and the target item according to the following formula:
Intersect Score＝O/A
in the formula, Intersect Score represents the similarity between the intersections of the titles and words of the current item and the target item, O represents the number of intersections, and a represents the number of words corresponding to the title of the current item and the title of the target item with longer character length.
According to another aspect of an embodiment of the present invention, an article matching electronic device is provided.
An item matching electronic device according to an embodiment of the present invention includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the item matching method provided by the first aspect of the embodiment of the present invention.
According to yet another aspect of an embodiment of the present invention, a computer-readable medium is provided.
According to the computer readable medium of the embodiment of the present invention, a computer program is stored thereon, and when the program is executed by a processor, the method for matching items provided by the first aspect of the embodiment of the present invention is implemented.
One embodiment of the above invention has the following advantages or benefits: individual attribute fields with category characteristics and common attribute fields of all articles are created according to different categories, full-quantity matching is not needed in the article matching process, the calculated quantity is small, and the efficiency is high; the article matching process can be automatically realized, the manual matching and checking process is omitted, and time and labor are saved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a schematic diagram of a main flow of an item matching method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the main modules of an article matching apparatus according to an embodiment of the present invention;
FIG. 3 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 4 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
According to an aspect of an embodiment of the present invention, there is provided an article matching method.
Fig. 1 is a schematic diagram of a main flow of an item matching method according to an embodiment of the present invention. As shown in fig. 1, the item matching method includes: step S101, step S102, and step S103.
Step S101, extracting the common attribute and the individual attribute of the current article from the article information of the current article, and extracting the common attribute and the individual attribute of the target article from the article information of the target article.
The article in the embodiment of the present invention refers to a commodity, and specifically, the commodity may be a tangible commodity, such as a mobile phone, a food, a garment, and the like, or an intangible commodity, such as a life service, a travel service, and the like. The article information refers to information describing article-related content, such as text and picture introduction on article promotion posters, and further such as detail information of articles in e-commerce platforms.
The common attribute refers to an attribute common to each article, and the common attribute may be an attribute common to all articles. It should be noted that, in the actual application process, common attributes of each category of articles may be set for some categories in the full categories according to different application scenarios, for example, in order to recommend an article that may be interested in another category for the user according to the current article, common attributes may be set for articles of each category that may be involved in the article matching process, and then, the individual attributes of the current article may be set according to the category to which the current article belongs. The commonality attributes may include: item name, manufacturer, place of manufacture, color, model, date of manufacture, etc. Taking the e-commerce field as an example, the common attribute can be a title, a detailed description and the like. The individual attribute is determined according to the class to which the current article belongs, and can be understood as the most key attribute in the commodity description. In the practical application process, individual attributes with category characteristics can be created according to different categories to serve as item matching check fields, such as hotel room types, bed sizes, geographic positions, inventory and the like. . The number of the common attributes and the individual attributes and the specific attribute content may be selectively set according to an actual application scenario, which is not specifically limited in the embodiment of the present invention.
Step S102, determining the similarity between the common attributes of the current article and the target article and the similarity between the individual attributes of the current article and the target article.
Regardless of the common attribute or the individual attribute, when determining the similarity between the attributes, the similarity between the individual attributes of the current item and the target item can be determined by using algorithms such as euclidean distance, manhattan distance, cosine similarity, Jaccard coefficient, pearson correlation coefficient and the like according to the attribute value of the attribute of the current item and the attribute value of the attribute of the target item. Of course, the following method may be adopted to determine the similarity between the attributes:
(1) determining the similarity between the individual attributes of the current item and the target item according to the following steps:
extracting attribute values of individual attributes of the current article from the article information of the current article;
judging whether the attribute values of the individual attributes of the current article exist in the article information of the target article; if all the objects exist, the similarity between the individual attributes of the current object and the target object is a first threshold value; if the current object and the target object do not exist, the similarity between the individual attributes of the current object and the target object is a second threshold value; and if the part exists, the similarity between the individual attributes of the current article and the target article is a third threshold value.
For example, assuming that the personality attributes include three attributes of X1, X2 and X3, if three attributes of X1, X2 and X3 are not maintained in the target item, the similarity between the personality attributes of the current item and the target item is 0; if all the three attributes of X1, X2 and X3 are hit, namely the three attributes of X1, X2 and X3 exist in the target object and the attribute value part is null, the similarity between the individual attributes of the current object and the target object is 1; if the three attributes of X1, X2 and X3 are only partially hit, i.e. the target item is only hit on one or two of the three attributes of X1, X2 and X3, the similarity between the individual attributes of the current item and the target item is-1.
(2) The common attribute or the individual attribute includes: a title; determining the similarity between the titles of the current item and the target item according to the following steps:
removing invalid characters and repeated characters in the titles of the current article and the target article to obtain an effective title of the current article and an effective title of the target article;
merging the effective titles of the current article and the effective titles of the target article, and then removing repeated characters in the effective titles to obtain merged titles;
determining the similarity between the titles of the current item and the target item according to the following formula:
simScore＝(L1+L2-T)/T
in the formula, simscope represents the similarity between the titles of the current item and the target item, L represents the character length of the valid title of the current item, L2 represents the character length of the valid title of the target item, and T represents the character length of the merged title.
The invalid characters can be set according to actual conditions, such as spaces, connectors, punctuation marks, prepositions and the like. In the actual application process, an invalid character set can be preset, and when the title contains characters in the invalid character set, the characters are removed from the title.
The repeated character refers to a character that appears repeatedly in the title, for example, if the character "XX is the same" appears twice in the title of the current article, the repeated character "XX is the same" is removed from the title, and only one character "XX is the same" is reserved.
(3) The common attribute or the individual attribute includes: the model number; determining the similarity between the models of the current article and the target article according to the following steps:
if the attribute value of the model attribute of the current article or the target article is null, the similarity between the models of the current article and the target article is a fifth threshold value;
if the attribute values of the model attributes of the current article or the target article are the same, the similarity between the models of the current article and the target article is a fourth threshold value;
and if the attribute values of the model attributes of the current article or the target article are different, judging whether one of the attribute values is a subset of the other one, if so, determining that the similarity between the models of the current article and the target article is a seventh threshold, otherwise, determining that the similarity between the models of the current article and the target article is a sixth threshold.
For example, if a certain party lacks a model, that is, if the attribute value of the model attribute of the current article or the target article is null, the similarity between the models of the current article and the target article is 0;
if the model of the current article or the target article is completely consistent after the unit of the model (such as cm \ l \ pcs) is removed, the similarity between the models of the current article and the target article is 1;
if the models are inconsistent after the unit is removed, and the models on both sides contain a "-" or a space (such as px-320 or px-17-320), and after the "-" or the space is subjected to word segmentation, one side is of the other side subset (such as px-320 is cut into [ px, 320], px-17-320 is cut into [ px, 17, 320], and the former is the latter subset), the similarity between the models of the current article and the target article is 0.9999.
If the model is inconsistent after the unit is removed and less than one is the other subset, the model character similarity score is calculated, but since there is already a 0-score and 1-score logic in the foregoing, the calculated model character similarity score of 1 can be converted to 0.8888 and the model character similarity score of 0 to-1. Through conversion, the value ranges of the similarity obtained by different methods are the same, and comparison is facilitated.
(4) The common attribute or the individual attribute includes: color; determining the similarity between the colors of the current article and the target article according to the following steps:
if the attribute value of the color attribute of the current article or the target article is null, the similarity between the colors of the current article and the target article is a ninth threshold value;
if the attribute values of the color attributes of the current article or the target article are the same, the similarity between the colors of the current article and the target article is an eighth threshold value;
if the attribute values of the color attributes of the current article or the target article are different, the similarity between the models of the current article and the target article is a tenth threshold.
For example, for a title with one party with no color, the similarity is 0; for the same color, the similarity is 1; for colors that are not the same, the similarity is-1.
(5) The common attribute or the individual attribute includes: title word intersection; determining the similarity between the intersection of the title words of the current item and the target item according to the following steps:
performing word segmentation processing on the titles of the current article and the target article to obtain each word;
determining the number of intersections between each word corresponding to the title of the current article and each word corresponding to the title of the target article;
determining the similarity between the intersection of the title words of the current item and the target item according to the following formula:
Intersect Score＝O/A
in the formula, Intersect Score represents the similarity between the intersections of the titles and words of the current item and the target item, O represents the number of intersections, and a represents the number of words corresponding to the title of the current item and the title of the target item with longer character length.
For example, the title of the current item is participled to obtain words Q1, Q2, Q3, Q4 and Q5; performing word segmentation on the title of the target object to obtain words Q1, Q1 and Q8; the intersection between the two words is a word Q1, and the number of the words is 1; the longer character length of the two characters is the title of the current article, and the number of corresponding words is 5; the similarity between the intersection of the title words of the current item and the target item is: the Intersect Score is 0.2 as O/a 1/5.
It should be noted that the values of the first to tenth thresholds mentioned in the embodiments of the present invention may be selectively set according to actual situations. Further, for convenience of subsequent calculation processing and comparison, the similarity values of the attributes may be normalized, so that the value ranges of the similarity values of the attributes are the same.
Step S103, determining the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determining the target article matched with the current article according to the matching degree.
In some embodiments, the similarity between the common attributes and the similarity between the individual attributes may be directly summed or the result of weighted summation may be used as the matching degree between the current item and the target item, and the calculation method is simple.
In other embodiments, determining the matching degree between the current item and the target item according to the similarity between the common attributes and the similarity between the individual attributes may include:
extracting candidate target articles from the target articles, wherein the target articles with the similarity between the target articles and the personality attribute of the current article being greater than or equal to a preset personality threshold are extracted firstly, and then the template articles with the similarity between the target articles and the commonality attribute of the current article being greater than or equal to a preset similarity threshold are extracted according to the sequence of the priority of the commonalities attributes from high to low until the number of the candidate target articles is greater than a preset number threshold (for example, 5 or 10);
and for each candidate target object, summing the similarity between the common attributes and the similarity between the individual attributes of the current object and the candidate target object to obtain the matching degree of the current object and the candidate target object.
The common attribute is an important description of the item information, so the priority of the part of fields is very high, and the priority of the common attribute can be: the priority of the model score > the priority of the intersection score. Candidate target articles are extracted according to the priority sequence, so that the calculated amount can be greatly reduced while the target article which is most matched with the current article is accurately screened out.
Optionally, before extracting the candidate target item, the method may further include: and confirming that each similarity meets a preset condition. For example: the number of the title intersection is larger than a preset number threshold, or the title character similarity score is larger than or equal to 0.7, or the keyword score is equal to 1, or the color score is equal to 1, or the model score is equal to 0.9999. Therefore, the matching degree of the determined target object matched with the current object and the current object is prevented from being too low, and the practicability of the object matching method is improved.
And summing the similarity between the common attributes and the similarity between the individual attributes of the current object and the candidate object to obtain the matching degree of the current object and the candidate object, wherein the obtained candidate object may be one or more. In the practical application process, each candidate target object and the corresponding matching degree thereof can also be displayed, and the matching data is confirmed through a manual operation auditing link, for example, the previous candidate target objects with higher matching degrees are manually screened. When a plurality of candidate target objects are screened manually, further screening can be performed according to other attributes of the target objects, for example, a unique piece of matching data is calculated according to weighting such as the shop score of the target object, whether the shop of the target object is self-supporting, and the like, so that a unique target object matched with the current object can be obtained.
The invention adopts the cosine similarity idea to digitize each attribute field, and determines the matching degree of the current article and the target article after calculating the different similarity of each field. The calculation amount is small, the automatic realization can be realized, the flow of manual matching and checking is saved, and the time and the labor are saved.
According to an aspect of an embodiment of the present invention, there is provided an article matching apparatus for implementing the above article matching method.
Fig. 2 is a schematic diagram of main modules of an article matching apparatus according to an embodiment of the present invention. As shown in fig. 2, an article matching apparatus 200 according to an embodiment of the present invention includes:
the extraction module 201 is used for extracting the commonality attribute and the individual attribute of the current article from the article information of the current article, and extracting the commonality attribute and the individual attribute of the target article from the article information of the target article; the individual attribute is determined according to the category to which the current article belongs;
the determining module 202 is used for determining the similarity between the common attributes of the current item and the target item and the similarity between the individual attributes of the current item and the target item;
the matching module 203 determines the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determines the target article matched with the current article according to the matching degree.
Optionally, the determining, by the matching module, the matching degree between the current item and the target item according to the similarity between the common attributes and the similarity between the individual attributes includes:
extracting candidate target articles from the target articles, wherein the target articles with the similarity between the target articles and the individual attribute of the current article being greater than or equal to a preset individual threshold are extracted firstly, and then the template articles with the similarity between the target articles and the common attribute of the current article being greater than or equal to a preset similarity threshold are extracted according to the sequence of the priority of each common attribute from high to low until the number of the candidate target articles is greater than a preset number threshold;
and for each candidate target object, summing the similarity between the common attributes and the similarity between the individual attributes of the current object and the candidate target object to obtain the matching degree of the current object and the candidate target object.
Optionally, the determining module determines the similarity between the personality attributes of the current item and the target item according to the following steps:
extracting attribute values of individual attributes of the current article from the article information of the current article;
judging whether the attribute values of the individual attributes of the current article exist in the article information of the target article; if all the objects exist, the similarity between the individual attributes of the current object and the target object is a first threshold value; if the current object and the target object do not exist, the similarity between the individual attributes of the current object and the target object is a second threshold value; and if the part exists, the similarity between the individual attributes of the current article and the target article is a third threshold value.
Optionally, the commonality attribute or the personality attribute comprises: a title; the determining module determines similarity between the titles of the current item and the target item according to the following steps:
removing invalid characters and repeated characters in the titles of the current article and the target article to obtain an effective title of the current article and an effective title of the target article;
merging the effective titles of the current article and the effective titles of the target article, and then removing repeated characters in the effective titles to obtain merged titles;
determining the similarity between the titles of the current item and the target item according to the following formula:
simScore＝(L1+L2-T)/T
in the formula, simscope represents the similarity between the titles of the current item and the target item, L represents the character length of the valid title of the current item, L2 represents the character length of the valid title of the target item, and T represents the character length of the merged title.
Optionally, the commonality attribute or the personality attribute comprises: the model number; the determining module determines the similarity between the models of the current article and the target article according to the following steps:
if the attribute value of the model attribute of the current article or the target article is null, the similarity between the models of the current article and the target article is a fifth threshold value;
if the attribute values of the model attributes of the current article or the target article are the same, the similarity between the models of the current article and the target article is a fourth threshold value;
and if the attribute values of the model attributes of the current article or the target article are different, judging whether one of the attribute values is a subset of the other one, if so, determining that the similarity between the models of the current article and the target article is a seventh threshold, otherwise, determining that the similarity between the models of the current article and the target article is a sixth threshold.
Optionally, the commonality attribute or the personality attribute comprises: color; the determining module determines the similarity between the colors of the current article and the target article according to the following steps:
if the attribute value of the color attribute of the current article or the target article is null, the similarity between the colors of the current article and the target article is a ninth threshold value;
if the attribute values of the color attributes of the current article or the target article are the same, the similarity between the colors of the current article and the target article is an eighth threshold value;
if the attribute values of the color attributes of the current article or the target article are different, the similarity between the models of the current article and the target article is a tenth threshold.
Optionally, the commonality attribute or the personality attribute comprises: title word intersection; the determining module determines the similarity between the title word intersections of the current item and the target item according to the following steps:
performing word segmentation processing on the titles of the current article and the target article to obtain each word;
determining the number of intersections between each word corresponding to the title of the current article and each word corresponding to the title of the target article;
determining the similarity between the intersection of the title words of the current item and the target item according to the following formula:
Intersect Score＝O/A
in the formula, Intersect Score represents the similarity between the intersections of the titles and words of the current item and the target item, O represents the number of intersections, and a represents the number of words corresponding to the title of the current item and the title of the target item with longer character length.
According to another aspect of an embodiment of the present invention, an article matching electronic device is provided.
An item matching electronic device according to an embodiment of the present invention includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the item matching method provided by the first aspect of the embodiment of the present invention.
Fig. 3 illustrates an exemplary system architecture 300 to which the item matching method or the item matching apparatus of the present invention may be applied.
As shown in fig. 3, the system architecture 300 may include terminal devices 301, 302, 303, a network 304, and a server 305. The network 304 serves as a medium for providing communication links between the terminal devices 301, 302, 303 and the server 305. Network 304 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal device 301, 302, 303 to interact with the server 305 via the network 304 to receive or send messages or the like. The terminal devices 301, 302, 303 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 301, 302, 303 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 305 may be a server providing various services, such as a background management server (for example only) providing support for shopping-like websites browsed by users using the terminal devices 301, 302, 303. The backend management server may analyze and perform other processing on the received data such as the product information query request, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.
It should be noted that the item matching method provided by the embodiment of the present invention is generally executed by the server 305, and accordingly, the item matching apparatus is generally disposed in the server 305.
It should be understood that the number of terminal devices, networks, and servers in fig. 3 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 4, a block diagram of a computer system 400 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU)401 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the system 400 are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as necessary, so that a computer program read out therefrom is mounted into the storage section 408 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program performs the above-described functions defined in the system of the present invention when executed by a Central Processing Unit (CPU) 401.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprising: the extraction module is used for extracting the common attribute and the individual attribute of the current article from the article information of the current article and extracting the common attribute and the individual attribute of the target article from the article information of the target article; the individual attribute is determined according to the category to which the current article belongs; the determining module is used for determining the similarity between the common attributes of the current article and the target article and the similarity between the individual attributes of the current article and the target article; and the matching module is used for determining the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determining the target article matched with the current article according to the matching degree. The names of the modules do not form a limitation on the modules themselves in some cases, for example, the determination module may also be described as a module for determining the matching degree of the current item and the target item according to the similarity between the common attributes and the similarity between the individual attributes.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: extracting the common attribute and the individual attribute of the current article from the article information of the current article, and extracting the common attribute and the individual attribute of the target article from the article information of the target article; the individual attribute is determined according to the category to which the current article belongs; determining the similarity between the common attributes of the current article and the target article and the similarity between the individual attributes of the current article and the target article; and determining the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determining the target article matched with the current article according to the matching degree.
According to the technical scheme of the embodiment of the invention, the method has the following advantages or beneficial effects: individual attribute fields with category characteristics and common attribute fields of all articles are created according to different categories, full-quantity matching is not needed in the article matching process, the calculated quantity is small, and the efficiency is high; the article matching process can be automatically realized, the manual matching and checking process is omitted, and time and labor are saved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (16)
1. An item matching method, comprising:
extracting the common attribute and the individual attribute of the current article from the article information of the current article, and extracting the common attribute and the individual attribute of the target article from the article information of the target article; the personality attribute is determined according to the category to which the current article belongs;
determining the similarity between the common attributes of the current article and the target article and the similarity between the individual attributes of the current article and the target article;
and determining the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determining the target article matched with the current article according to the matching degree.
2. The method of claim 1, wherein determining the matching degree of the current item and the target item according to the similarity between the commonality attributes and the similarity between the personality attributes comprises:
extracting candidate target articles from the target articles, wherein the target articles with the similarity between the target articles and the individual attribute of the current article being greater than or equal to a preset individual threshold are extracted firstly, and then the template articles with the similarity between the target articles and the common attribute of the current article being greater than or equal to a preset similarity threshold are extracted according to the sequence of the priority of each common attribute from high to low until the number of the candidate target articles is greater than a preset number threshold;
and for each candidate target object, summing the similarity between the common attributes and the similarity between the individual attributes of the current object and the candidate target object to obtain the matching degree of the current object and the candidate target object.
3. The method of claim 1, wherein the similarity between the personality attributes of the current item and the target item is determined according to the following steps:
extracting attribute values of individual attributes of the current article from the article information of the current article;
judging whether the attribute values of the individual attributes of the current article exist in the article information of the target article; if all the objects exist, the similarity between the individual attributes of the current object and the target object is a first threshold value; if the current object and the target object do not exist, the similarity between the individual attributes of the current object and the target object is a second threshold value; and if the part exists, the similarity between the individual attributes of the current article and the target article is a third threshold value.
4. The method of claim 2, wherein the commonality attribute or the personality attribute comprises: a title; determining the similarity between the titles of the current item and the target item according to the following steps:
removing invalid characters and repeated characters in the titles of the current article and the target article to obtain an effective title of the current article and an effective title of the target article;
merging the effective titles of the current article and the effective titles of the target article, and then removing repeated characters in the effective titles to obtain merged titles;
determining the similarity between the titles of the current item and the target item according to the following formula:
simScore＝(L1+L2-T)/T
in the formula, simscope represents the similarity between the titles of the current item and the target item, L1 represents the character length of the valid title of the current item, L2 represents the character length of the valid title of the target item, and T represents the character length of the merged title.
5. The method of claim 2, wherein the commonality attribute or the personality attribute comprises: the model number; determining the similarity between the models of the current article and the target article according to the following steps:
if the attribute value of the model attribute of the current article or the target article is null, the similarity between the models of the current article and the target article is a fifth threshold value;
if the attribute values of the model attributes of the current article or the target article are the same, the similarity between the models of the current article and the target article is a fourth threshold value;
and if the attribute values of the model attributes of the current article or the target article are different, judging whether one of the attribute values is a subset of the other one, if so, determining that the similarity between the models of the current article and the target article is a seventh threshold, otherwise, determining that the similarity between the models of the current article and the target article is a sixth threshold.
6. The method of claim 2, wherein the commonality attribute or the personality attribute comprises: color; determining the similarity between the colors of the current article and the target article according to the following steps:
if the attribute value of the color attribute of the current article or the target article is null, the similarity between the colors of the current article and the target article is a ninth threshold value;
if the attribute values of the color attributes of the current article or the target article are the same, the similarity between the colors of the current article and the target article is an eighth threshold value;
if the attribute values of the color attributes of the current article or the target article are different, the similarity between the models of the current article and the target article is a tenth threshold.
7. The method of claim 2, wherein the commonality attribute or the personality attribute comprises: title word intersection; determining the similarity between the intersection of the title words of the current item and the target item according to the following steps:
performing word segmentation processing on the titles of the current article and the target article to obtain each word;
determining the number of intersections between each word corresponding to the title of the current article and each word corresponding to the title of the target article;
determining the similarity between the intersection of the title words of the current item and the target item according to the following formula:
IntersectScore＝O/A
in the formula, IntersectScore represents the similarity between the intersection of the title words of the current item and the target item, O represents the number of intersections, and a represents the number of words corresponding to the title of the current item and the title of the target item with longer character length.
8. An article matching apparatus, comprising:
the extraction module is used for extracting the common attribute and the individual attribute of the current article from the article information of the current article and extracting the common attribute and the individual attribute of the target article from the article information of the target article; the personality attribute is determined according to the category to which the current article belongs;
the determining module is used for determining the similarity between the common attributes of the current article and the target article and the similarity between the individual attributes of the current article and the target article;
and the matching module is used for determining the matching degree of the current article and the target article according to the similarity between the common attributes and the similarity between the individual attributes, and determining the target article matched with the current article according to the matching degree.
9. The apparatus of claim 8, wherein the matching module determines the matching degree of the current item and the target item according to the similarity between the common attributes and the similarity between the individual attributes, comprising:
extracting candidate target articles from the target articles, wherein the target articles with the similarity between the target articles and the individual attribute of the current article being greater than or equal to a preset individual threshold are extracted firstly, and then the template articles with the similarity between the target articles and the common attribute of the current article being greater than or equal to a preset similarity threshold are extracted according to the sequence of the priority of each common attribute from high to low until the number of the candidate target articles is greater than a preset number threshold;
and for each candidate target object, summing the similarity between the common attributes and the similarity between the individual attributes of the current object and the candidate target object to obtain the matching degree of the current object and the candidate target object.
10. The apparatus of claim 8, wherein the determination module determines the similarity between the personality attributes of the current item and the target item according to the following steps:
extracting attribute values of individual attributes of the current article from the article information of the current article;
judging whether the attribute values of the individual attributes of the current article exist in the article information of the target article; if all the objects exist, the similarity between the individual attributes of the current object and the target object is a first threshold value; if the current object and the target object do not exist, the similarity between the individual attributes of the current object and the target object is a second threshold value; and if the part exists, the similarity between the individual attributes of the current article and the target article is a third threshold value.
11. The apparatus of claim 9, wherein the commonality attribute or the personality attribute comprises: a title; the determining module determines similarity between the titles of the current item and the target item according to the following steps:
removing invalid characters and repeated characters in the titles of the current article and the target article to obtain an effective title of the current article and an effective title of the target article;
merging the effective titles of the current article and the effective titles of the target article, and then removing repeated characters in the effective titles to obtain merged titles;
determining the similarity between the titles of the current item and the target item according to the following formula:
simScore＝(L1+L2-T)/T
in the formula, simscope represents the similarity between the titles of the current item and the target item, L1 represents the character length of the valid title of the current item, L2 represents the character length of the valid title of the target item, and T represents the character length of the merged title.
12. The apparatus of claim 9, wherein the commonality attribute or the personality attribute comprises: the model number; the determining module determines the similarity between the models of the current article and the target article according to the following steps:
if the attribute value of the model attribute of the current article or the target article is null, the similarity between the models of the current article and the target article is a fifth threshold value;
if the attribute values of the model attributes of the current article or the target article are the same, the similarity between the models of the current article and the target article is a fourth threshold value;
and if the attribute values of the model attributes of the current article or the target article are different, judging whether one of the attribute values is a subset of the other one, if so, determining that the similarity between the models of the current article and the target article is a seventh threshold, otherwise, determining that the similarity between the models of the current article and the target article is a sixth threshold.
13. The apparatus of claim 9, wherein the commonality attribute or the personality attribute comprises: color; the determining module determines the similarity between the colors of the current article and the target article according to the following steps:
if the attribute value of the color attribute of the current article or the target article is null, the similarity between the colors of the current article and the target article is a ninth threshold value;
if the attribute values of the color attributes of the current article or the target article are the same, the similarity between the colors of the current article and the target article is an eighth threshold value;
if the attribute values of the color attributes of the current article or the target article are different, the similarity between the models of the current article and the target article is a tenth threshold.
14. The apparatus of claim 9, wherein the commonality attribute or the personality attribute comprises: title word intersection; the determining module determines the similarity between the title word intersections of the current item and the target item according to the following steps:
performing word segmentation processing on the titles of the current article and the target article to obtain each word;
determining the number of intersections between each word corresponding to the title of the current article and each word corresponding to the title of the target article;
determining the similarity between the intersection of the title words of the current item and the target item according to the following formula:
IntersectScore＝O/A
in the formula, IntersectScore represents the similarity between the intersection of the title words of the current item and the target item, O represents the number of intersections, and a represents the number of words corresponding to the title of the current item and the title of the target item with longer character length.
15. An item matching electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
16. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810863709.2A CN110807095A (en) | 2018-08-01 | 2018-08-01 | Article matching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810863709.2A CN110807095A (en) | 2018-08-01 | 2018-08-01 | Article matching method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110807095A true CN110807095A (en) | 2020-02-18 |
Family
ID=69486743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810863709.2A Pending CN110807095A (en) | 2018-08-01 | 2018-08-01 | Article matching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110807095A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861684A (en) * | 2021-01-29 | 2021-05-28 | 北京电解智科技有限公司 | Article display method and device |
| CN113743856A (en) * | 2021-01-05 | 2021-12-03 | 北京京东乾石科技有限公司 | Article sorting method and device, and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662949A (en) * | 2012-02-27 | 2012-09-12 | 安科智慧城市技术（中国）有限公司 | Method and system for retrieving specified object based on multi-feature fusion |
| CN104424230A (en) * | 2013-08-26 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Network commodity recommendation method and device |
| CN105426528A (en) * | 2015-12-15 | 2016-03-23 | 中南大学 | Retrieving and ordering method and system for commodity data |
| CN106228179A (en) * | 2016-07-13 | 2016-12-14 | 乐视控股（北京）有限公司 | The method and system of vehicle comparison |
| CN107203548A (en) * | 2016-03-17 | 2017-09-26 | 阿里巴巴集团控股有限公司 | Attribute acquisition methods and device |
| CN107291825A (en) * | 2017-05-26 | 2017-10-24 | 北京奇艺世纪科技有限公司 | With the search method and system of money commodity in a kind of video |
| CN107341204A (en) * | 2017-06-22 | 2017-11-10 | 电子科技大学 | A kind of collaborative filtering recommending method and system for merging article label information |
-
2018
- 2018-08-01 CN CN201810863709.2A patent/CN110807095A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662949A (en) * | 2012-02-27 | 2012-09-12 | 安科智慧城市技术（中国）有限公司 | Method and system for retrieving specified object based on multi-feature fusion |
| CN104424230A (en) * | 2013-08-26 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Network commodity recommendation method and device |
| CN105426528A (en) * | 2015-12-15 | 2016-03-23 | 中南大学 | Retrieving and ordering method and system for commodity data |
| CN107203548A (en) * | 2016-03-17 | 2017-09-26 | 阿里巴巴集团控股有限公司 | Attribute acquisition methods and device |
| CN106228179A (en) * | 2016-07-13 | 2016-12-14 | 乐视控股（北京）有限公司 | The method and system of vehicle comparison |
| CN107291825A (en) * | 2017-05-26 | 2017-10-24 | 北京奇艺世纪科技有限公司 | With the search method and system of money commodity in a kind of video |
| CN107341204A (en) * | 2017-06-22 | 2017-11-10 | 电子科技大学 | A kind of collaborative filtering recommending method and system for merging article label information |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743856A (en) * | 2021-01-05 | 2021-12-03 | 北京京东乾石科技有限公司 | Article sorting method and device, and storage medium |
| CN112861684A (en) * | 2021-01-29 | 2021-05-28 | 北京电解智科技有限公司 | Article display method and device |
| WO2022161116A1 (en) * | 2021-01-29 | 2022-08-04 | 北京电解智科技有限公司 | Article display method and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11038975B2 (en) | Information pushing method and device | |
| CN110020162B (en) | User identification method and device | |
| CN109711917B (en) | Information pushing method and device | |
| CN112884405A (en) | Inquiry system and scheduling method thereof | |
| CN112835904A (en) | Data processing method and data processing device | |
| WO2014110950A1 (en) | Method and device for pushing information | |
| CN112347147A (en) | Information pushing method and device based on user association relationship and electronic equipment | |
| CN110910178A (en) | Method and device for generating advertisement | |
| CN110807095A (en) | Article matching method and device | |
| CN107291923B (en) | Information processing method and device | |
| CN110633405A (en) | Method and device for pushing information | |
| CN113744002A (en) | Method, device, equipment and computer readable medium for pushing information | |
| CN111782850A (en) | Object searching method and device based on hand drawing | |
| CN107330126B (en) | Method and apparatus for outputting information | |
| CN114817297A (en) | Method and device for processing data | |
| CN113139113A (en) | Search request processing method and device | |
| CN113191840A (en) | Article information display method and device, electronic equipment and computer readable medium | |
| CN113742564A (en) | Target resource pushing method and device | |
| CN112860858A (en) | Method and device for answering questions | |
| CN107368597B (en) | Information output method and device | |
| CN113379433A (en) | Advertisement putting method and device | |
| CN112256566A (en) | Test case preservation method and device | |
| CN112184370A (en) | Method and device for pushing product | |
| CN111339124A (en) | Data display method and device, electronic equipment and computer readable medium | |
| CN113434754A (en) | Method and device for determining recommended API (application program interface) service, electronic equipment and storage medium |
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 |