CN110738553A - method and system for mapping commodity links of different shopping malls to each other - Google Patents
method and system for mapping commodity links of different shopping malls to each other Download PDFInfo
- Publication number
- CN110738553A CN110738553A CN201910992565.5A CN201910992565A CN110738553A CN 110738553 A CN110738553 A CN 110738553A CN 201910992565 A CN201910992565 A CN 201910992565A CN 110738553 A CN110738553 A CN 110738553A
- Authority
- CN
- China
- Prior art keywords
- commodity
- similarity
- pushed
- candidate
- information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides methods and systems for mutually mapping commodity links of different shopping malls, which comprise the steps of obtaining commodity information of related commodities to be pushed from a media article, intelligently searching the same type of commodities in a target shopping mall for each pushed commodity to obtain a corresponding candidate commodity list, respectively calculating the similarity between a pushed commodity and a candidate commodity for each pushed commodity, and replacing the commodity information of the pushed commodity in the media article with the commodity information of the candidate commodity with the largest similarity for each pushed commodity.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the field of electronic commerce, in particular to methods and systems for mutually mapping commodity links of different malls.
[ background of the invention ]
In the modern age covered by information networks, electronic commerce based on information networks is rapidly developed, wherein the electronic commerce refers to novel business operation modes that buyers and sellers conduct various business activities without conspiracy in the open network environment of the internet, and the electronic commerce realizes the online shopping of consumers, online transaction and online electronic payment among merchants, various business activities, transaction activities, financial activities and related comprehensive service activities.
With the rapid development of electronic commerce, more and more people choose to purchase the required goods on the internet. The number of commodities on the network is more and more huge, and the number of e-commerce platforms is more and more. Different e-commerce platforms are used for striving for customer resources and expanding influence, platforms such as Arifather and Beijing alliance are constructed, and third-party websites are encouraged to import buyer traffic for the e-commerce platforms.
Meanwhile, the development of the mobile internet prompts a self-media e-commerce mode. From the media worker, the content is output on the Internet platform to attract readers to read. Meanwhile, the self-media worker inserts the E-commerce commodity link into the self-media article issued by the self-media worker, and the reader clicks the commodity to purchase and then obtains the commission return of the E-commerce platform so as to realize the flow cash change. The "from media + e-commerce" model helps to export more valuable content from the media.
When a media worker sends own articles to various large Internet platforms (such as WeChat public numbers, headings of today and the like), part of the platforms forbid commodity links of certain shopping malls, and users of the part of the platforms prefer to enable the commodity links of specific shopping malls to have higher click rate and conversion rate.
[ summary of the invention ]
In order to solve the defects of the prior art, the invention aims to provide methods and systems for mapping commodity links of different shopping malls with each other, which can solve the problem of low efficiency of the operation of mapping the commodity links of different shopping malls in a media e-commerce.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
th object of the present invention, methods for mapping merchandise links of different shopping malls to each other, comprising the steps of:
101. acquiring commodity information of related commodities to be pushed from the media article;
102. for each pushed commodity, intelligently searching the same-style commodity in a target mall respectively to obtain a corresponding candidate commodity list;
103. for each pushed commodity, calculating a similarity between the pushed commodity and the candidate commodity;
104. for each push item, the item information from the push item in the media article is replaced with the item information of the most similar candidate item.
, in the step 101, the commodity information includes at least two kinds of information of a commodity title, a commodity link, a price, a brand name and a picture link, wherein the commodity information must include the commodity title and the commodity link information.
, in the step 101, the commodity information acquiring method of the related commodity adopts a user input or program automatic identification mode.
, in the step 102, the candidate commodity list is a commodity information list of similar commodities returned by the target e-commerce platform according to rules through a network interface thereof, each candidate commodity information includes at least four kinds of information of a commodity title, a commodity, a picture link, a commodity brand name and a store name, wherein each candidate commodity information must include the commodity title, the commodity, the picture link and the commodity link information.
, in the step 102, the method further includes that for the commodity title to be pushed, the number of words is marked as N, N words are extracted, N is less than N, new character strings are spliced again according to the original sequence as query texts, and the query texts are used as keywords to obtain a candidate commodity list from the target store.
, the method for obtaining the corresponding candidate commodity list in step 102 includes:
a. using a natural language tool to perform word segmentation and part-of-speech tagging on the title of the pushed commodity;
b. intelligently identifying and pushing brand names of commodities and extracting brand words in the appointed text;
d. extracting texts from the titles of the pushed commodities according to rules to construct a priority query text list;
d. and calling a service interface in the target mall by using the query text to obtain a candidate commodity list.
, the step a of the step 102 includes performing word segmentation and part-of-speech tagging, where the word segmentation and part-of-speech tagging are proprietary words in the natural language processing field, the word segmentation is a process of recombining continuous word sequences of the commodity title into word sequences according to a specification set by , and the part-of-speech tagging is used for tagging kinds of parts of each word belonging to common nouns, names of people, orientation nouns, quantitative words, place names, organization names, or punctuation marks.
, in the step a of the step 102, the natural language tool includes an offline tool or a third party remote service, the offline tool is, for example, jieba, etc., and the third party remote service is, for example, a Baidu natural language cloud service, etc.
, in the step b of the step 102, the intelligent recognition push brand name of the commodity refers to that for commodity without brand name to be pushed, the brand name of the commodity to be pushed is intelligently obtained by using the title, brand name and store name information of the commodity in the candidate commodity list returned by the title, brand name and store name information of the commodity to be pushed .
, in step b of the step 102, the designated text includes the title of the item to be pushed or the candidate item, the shop name text.
, in the step d of the step 102, the query text is used as a keyword to assist other information, a service interface of the target mall is called, and a related commodity list is searched as a candidate commodity list of the query text.
, the method for calculating the similarity between the pushed commodity and the candidate commodity in the step 103 comprises:
a. calculating the title similarity between the pushed commodity and the candidate commodity;
b. calculating the similarity of the shop names of the pushed commodities and the candidate commodities;
c. calculating the brand name similarity of the pushed commodity and the candidate commodity;
d. calculating price similarity between the pushed commodity and the candidate commodity;
e. the similarity between the pushed commodity and the candidate commodity is comprehensively determined by the title similarity, the shop name similarity, the brand name similarity and the price similarity;
and calculating the similarity between the pushed commodity and the candidate commodity by using the title similarity, the shop name similarity, the brand name similarity and the price similarity in the four similarities, wherein the title similarity is definitely existed, and the similarity between the pushed commodity and the candidate commodity does not exist as long as the attributes of the three similarities do not exist in the three similarities of the shop name similarity, the brand name similarity and the price similarity in the pushed commodity or the candidate commodity .
, in the step 103, the similarity between the item of the pushout and the candidate item is calculated by weighted sum of the title similarity, the shop name similarity, the brand name similarity and the price similarity.
, in step a of step 103, similarity between two titles is calculated using edit distance, Jacard coefficient, TF-IDF or word vector method, considering characteristics that the E-commerce title is optimized by store owners artificially, and based on the consideration of saving calculation resources and improving efficiency, title similarity is preferably calculated using Jacard (Jaccard) coefficient method.
Further , in step b of step 103, the brand word in the shop name needs to be extracted, and similarity calculation is performed.
In step , in step c of step 103, in consideration of the fact that the brand name is mixed with both chinese and english, it is necessary to extract a plurality of aliases of the brand name and then perform similarity calculation.
, in the step d of step 103, the price similarity is calculated by converting the prices of the two commodities into similarity using a formula to achieve the goal of the similarity being the largest when the prices are the same and the similarity being smaller when the price difference is larger.
, the method for replacing the commodity information of the pushed commodity from the media article with the commodity information of the candidate commodity with the largest similarity in the step 104 comprises:
acquiring a push link from a target mall as a commodity link of the commodity by utilizing commodity information of the candidate commodity with the maximum similarity and push account information;
and replacing corresponding pushed merchandise information in the self-media article with the updated candidate merchandise information from step .
A second object of the present invention, a system for mapping commodity links of different shopping malls with each other, comprising:
the self-media article commodity information acquisition module is used for acquiring commodity information of related commodities to be pushed from the media article;
the intelligent search module is used for intelligently searching the same-style commodities in the target mall and acquiring a corresponding candidate commodity list;
a similarity calculation module for calculating a similarity between the pushed commodity and the candidate commodity;
and the self-media article commodity information replacing module is used for replacing the commodity information of the pushed commodities in the self-media article with the commodity information of the candidate commodity with the largest similarity.
And , the commodity information includes at least two kinds of information of a commodity title, a commodity link, a price, a brand name and a picture link, wherein the commodity information must include the commodity title and the commodity link information.
Further , the intelligent search module includes:
the word segmentation and part of speech tagging submodule is used for carrying out word segmentation and part of speech tagging on the commodity title by utilizing a natural language tool;
the brand word recognition submodule is used for intelligently recognizing the brand name of the product and extracting the brand words in the product title and the shop name text;
the search text construction sub-module is used for extracting texts from the titles of the pushed commodities according to rules to construct a priority query text list;
and the mall searching submodule is used for calling the service interface in the target mall by using the query text and other necessary information to acquire the candidate commodity list.
, the intelligent search module further comprises a candidate commodity list merging submodule for merging and deduplicating the candidate commodity list obtained from the multiple search texts of the pushed commodities.
, in the intelligent search module, a brand word recognition sub-module, a search text construction sub-module and a mall search sub-module form loop structures in an execution flow;
the brand word identification submodule is used for acquiring a search result of the mall search submodule and identifying the brand words, and the identification result and the search result of the mall search submodule are output to the search text construction submodule;
the search text construction sub-module is used for reconstructing a search text list with priority by utilizing the input brand word recognition result, the mall search text and the obtained candidate commodity list;
if the search text list is empty, the cycle is ended; otherwise, outputting the search text with the highest priority to the mall search submodule;
and the mall searching submodule searches the target mall for the commodities by using the new search text and inputs the search result into the brand word recognition submodule.
The search text construction sub-module operates according to the principle of 1), the search texts output to the mall search sub-module cannot be repeated so as to reduce the total query times to the target mall, 2), the total number of the search texts output to the mall search sub-module cannot exceed threshold values so as to control the upper limit of the total query number to the target mall, and 3), the search sub-text sequencing is adjusted according to the search results of the mall search sub-module so as to improve the search quality within the limited query times.
Further , the similarity calculation module includes:
the commodity title similarity calculation operator module is used for calculating the similarity between the pushed commodity and the candidate commodity title;
the shop name similarity operator module is used for calculating the similarity between the shop name of the pushed commodity and the shop name of the candidate commodity;
the brand name similarity operator module is used for calculating the similarity between the brand to which the pushed commodity belongs and the brand to which the candidate commodity belongs;
the price similarity operator module is used for calculating the similarity between the pushed commodity price and the candidate commodity price;
and the similarity comprehensive calculation submodule is used for synthesizing the title similarity, the shop name similarity, the brand name similarity and the price similarity and determining the similarity between the pushed commodity and the candidate commodity.
Further , the self-media article merchandise information replacement module includes:
a push link acquisition submodule for acquiring a push link of the final replacement commodity and setting the push link as a commodity link of the final replacement commodity;
and the commodity information replacement submodule is used for performing information replacement on the corresponding pushed commodity by using the final replacement commodity in the self-media article.
The invention has the beneficial effects that:
(1) the automatic operation is adopted, so that the labor is saved;
(2) when the commodity link is replaced, only the information such as the title, the shop name, the brand name and the like of the E-commerce commodity is needed, a large E-commerce commodity data set does not need to be prepared, and a model does not need to be trained;
(3) the calculation speed is high, the consumed resources are few, the total number of times of searching the target e-commerce is less than 10, and the commodity mapping effect is ideal;
(4) the universal access method has strong universality and low requirement on the mall interface, and can be conveniently accessed into different malls.
[ description of the drawings ]
FIG. 1 is a diagram of the system application architecture of the present invention;
FIG. 2 is a diagram of the method steps for merchandise link mapping in accordance with the present invention;
FIG. 3 is a diagram illustrating steps of a method for obtaining candidate goods according to the present invention;
FIG. 4 is a diagram of candidate products returned from high to low in accordance with the degree of correlation in the search of the present invention;
FIG. 5 is a diagram illustrating the effectiveness of a candidate item in the present invention after calculating the similarity between a pushed item and the candidate item;
fig. 6 is a schematic diagram of the system architecture of the present invention.
[ detailed description ] embodiments
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Referring to fig. 1, in order to implement the system application architecture diagram of the present invention, the system application architecture diagram includes a commodity link mapping system (server), a client and a shopping mall (server) interfaced with the mapping system.
methods for mapping merchandise links of different shopping malls to each other, as shown in figure 2,
the method comprises the following steps:
step 101, commodity information of a related commodity to be pushed from a media article is obtained.
For the self-media e-commerce, the author inserts commodity to be pushed into the self-media article, the position of the commodity to be pushed in the article can be collectively called notice position, when a reader clicks on the push commodity on the notice position , a page automatically jumps to a specified commodity page of a specified mall, when the reader purchases the commodity to become a buyer, the mall can obtain the identity of the push by utilizing the commodity link clicked by the buyer, and thus commissions are given to the user.
The commodity information of the commodity to be pushed includes the commodity title, commodity link, price, brand name, picture link and other information.
It is noted that more than push commodities may appear in the self-media article, and furthermore, the same push commodities may appear at different notice positions.
102, aiming at each pushed commodity, intelligently searching the same-style commodity in the target shopping mall respectively to obtain a corresponding candidate commodity list, and referring to fig. 3, the method comprises the following steps:
step 301, using a natural language tool to perform word segmentation and part-of-speech tagging on the title of the pushed commodity;
step 302, intelligently identifying the brand name of the pushed commodity and extracting brand words in the appointed text;
step 303, extracting texts from titles of pushed commodities according to rules to construct a priority query text list;
and step 304, calling a service interface in the target mall by using the query text to obtain a candidate commodity list.
Optionally, step 102 may further include: and step 305, merging and removing the duplicate of the candidate commodity list.
Step 301, using a natural language tool to perform word segmentation and part-of-speech tagging on the title of the pushed commodity, wherein the natural language tool including an offline tool (e.g., jieba, etc.) and a third-party remote service (e.g., Baidu natural language cloud service, etc.) may be used to perform word segmentation and part-of-speech tagging on the title of the pushed commodity.
The substeps 302, 303 and 304 in the step 102 form loop structures, specifically 1), step 302, according to the search result of the step 304, the steps are used for identifying brand words, and the identification result and the mall search result are output to the step 303, 2), in the step 303, the input brand word identification result, the mall search text and the obtained candidate commodity list are used for reconstructing search text lists with priorities, if the search text lists are empty, the loop is ended, otherwise, the query text with the highest priority is output to the step 304, 3), in the step 304, the new search text is used for searching commodities in the target mall, and the search result is output to the step 302.
Step 302, intelligently identifying the brand name of the commodity to be pushed and extracting the brand words in the appointed text, searching the shop name and the brand name of the obtained candidate commodity by mainly utilizing the commodity to be pushed and the mall, presuming the brand name of the commodity to be pushed , and identifying the brand words in the titles and the shop names of the commodity to be pushed and the candidate commodity, wherein it is pointed out that the commodity to be pushed or the candidate commodity may not have the shop name or the brand name.
Step 302 is to intelligently identify the brand name of the commodity to be pushed mainly by using the information of the candidate commodity in combination with the information of the commodity to be pushed . for example, for the commodity to be pushed , the title is "love lipstick, matte, lasting moisture retention, no discoloration, student money, loved star air pregnant woman, waterproof lip gloss, no store name and no brand name exist. in the candidate commodity list obtained by the first search in the target mall a, the brand names of some commodities are called" Love (LIANYI) ", the method of step 302 can intelligently identify the brand name of the commodity to be pushed as" Love (LIANYI) ", the store name has the alias" love "," LIANYI ". step 302 is to extract the brand word in the designated text on the basis of identifying the brand name.A step 302 includes the title in the commodity to be pushed and the brand name in the candidate commodity, and the brand name in the brand name of the brand name, and the step 302 also identifies all the brand names in the candidate commodity to be pushed .
Step 303, extracting texts from titles of pushed commodities according to rules to construct a priority query text list, wherein the principle of the step 303 is that a plurality of characters can be extracted from the character sequence of the title and spliced into a new character string according to the original sequence to form a query text as a keyword by utilizing the characteristics of artificial optimization and rich information of the titles of the commodities of the commercial, the query text is used for searching the shopping mall, the structural quality of the query text needs to be improved for controlling the total searching times of the shopping mall, and brand words, quantifier words, nouns and the like are considered to have obvious effects on the commodity searching quality.
Step 303, constructing a priority query text list according to rules by using the segmentation and part-of-speech tagging results of step 301, the brand word recognition results provided by step 302 and the search results provided by step 304, preferably, in the th query text list, the query text with the highest priority is the title of the commodity to be pushed , the query text list is updated times every time step 303 is performed, the query text list cannot appear in the query text list again in the updating process, when the number of times step 305 is performed reaches a predetermined threshold or the query results reach the target, the query text list needs to be set to be empty to actively terminate the intelligent search, when the query text list is a pure product, the intelligent search is finished, otherwise, the query text with the highest priority in the current query text list is output to step 304 and is performed to step 304, the actions of step 303 are exemplified, for example, the decoloration and decoloration of the special dry and moist pigskin snack foods manufactured by year soreens with the title of "[ 12 g-refined pigskin beauty warns", the special products of yearly production, koff, the MAC lip charm and koff, the steps of pushing, such as step 304, the steps of "365, the procedure of pushing naught, the special pigskin and the magic pigskin care food, the magic and the magic pigskin care food of the magic pigskin care food, the magic and the magic pigskin care food, the magic food of the magic food, the magic food of pigskin care, the magic food of the magic food, the.
Step 304, using the query text to call a service interface in a target mall to obtain a candidate commodity list, wherein the mall provides a search interface special for to provide keyword search service for people, in the service, part of the mall may also allow parameters such as commodity category and price range to be added to narrow the search range, furthermore, of the candidate commodities returned by the mall has attributes such as commodity title, price, commodity link and commodity picture, and possibly attributes such as shop name and brand name, the search service provided by the mall requires time for each search time, meanwhile, the number of calls or frequency of the search service allowed by the mall is limited, so that the total number of queries needs to be controlled, step 304 mainly uses the query text as a keyword to assist other information (such as price range, returned commodity number and the like), calls the service interface of the target mall, searches for a related commodity list as the candidate commodity list of the query text, step 303 provides the query text, and the query result is output to step 302.
Optionally, in step 305, the candidate merchandise lists are merged and deduplicated as can be seen from the previous steps 302, 303 and 304, for pushup merchandise, the number of queries in the target mall using the search text is not less than 1, corresponding candidate merchandise lists are obtained for each query, all the candidate merchandise lists of the same pushup merchandise need to be merged into , and in the final candidate merchandise list, only repeated candidate merchandise items are reserved.
Step 103, for each pushed item, separately calculate the similarity between the pushed item and the candidate item.
The similarity between the item of the push and the candidate item is obtained by comprehensively calculating four of the item title similarity, the store name similarity, the brand name similarity, and the price similarity, since it is essential in the information of the push item that the item title and the item link exist, only the item title similarity among the four similarities inevitably exists.
The similarity of the product titles can be obtained by calculation through methods such as an edit distance, a Jaccard coefficient (Jaccard similarity), TF-IDF, word vectors and the like, and considering that the E-commerce commodity titles are artificially optimized by merchants according to the characteristic, the similarity of the titles is preferably calculated by using the Jaccard coefficient method on the basis of the consideration of saving calculation resources and improving efficiency.
And (3) the similarity of the brand names, namely, considering the situation that the brand names are mixed in Chinese and English, a plurality of aliases of the brands need to be extracted, and then the similarity is calculated. For example, for the brand name "Coco Cola" and the brand name "coca Cola", the former may extract the brand names "Coco Cola" and "coca Cola", and the latter may extract the brand name "coca Cola", so the former and latter brand names should be considered to be the same.
The simplest method for calculating the similarity of store names is to calculate the similarity by using the edit distance. In addition, considering that some brands of goods tend to be sold in brand authorization online stores, the similarity of the same brand authorization stores should be higher; for example, the similarity between the store names, "Hua Qin warship shop" and "Hua Xun monopoly shop" should be higher than the similarity between "Hua Qin warship shop" and "Hua Shuo Qin warship shop".
For example, the price of the commodity to be pushed is x, the price of the candidate commodity is y, and the similarity between the two prices is 2-2/(1+ exp (| x-y |/(x +0.0001)) can be calculated by using a formula.
In order to better describe the functions of the two parts, cases are explained in detail, fig. 4 is a comparison graph of the embodiment, fig. 5 is an effect graph after the steps 102 and 103 are executed in the embodiment, for a product with the title of ' baicao flavor-refined dried pork slice 200g ' which is a special local product of snack jingjiang dried meat cubes ', and the price is 19.9 yuan of push product, the same type of product is searched in a target mall a.
Step 104, for each pushed item, replace the item information from the pushed item in the media article with the item information of the candidate item with the greatest similarity.
It is worth pointing out that in order to realize the commodity push , the information of push (such as from a media author) needs to be carried so that after a purchaser purchases the commodity through the link, the mall can recognize the identity of the push , and further provides the branch commission for the push person, a part of the mall returns the commodity link in the candidate commodity through the search interface, and the information of the push is not carried, so that the commodity information of the final replacement commodity and the push account information need to be requested to the target mall, and the push link is obtained from the target mall as the commodity link of the final replacement commodity.
Note that like push commodities, more than times may appear in the self-media article page, which requires that we implement a full replacement.
The system for mapping the commodity links of different shopping malls with each other, referring to fig. 6, includes a self-media article commodity information acquisition module 10, an intelligent search module 20, a similarity calculation module 30, and a self-media article commodity information replacement module 40.
The self-media article commodity information acquisition module 10 is used for acquiring commodity information of related commodities to be pushed from the media article.
And the intelligent searching module 20 is configured to intelligently search the same-style commodity in the target mall and obtain a corresponding candidate commodity list.
And the similarity calculation module 30 is used for calculating the similarity between the pushed commodity and the candidate commodity.
And the self-media article commodity information replacing module 40 is used for replacing the commodity information of the pushed commodity in the self-media article with the commodity information of the candidate commodity with the largest similarity.
The intelligent search module 20 comprises a word segmentation and part-of-speech tagging submodule for performing word segmentation and part-of-speech tagging on a commodity title by using a natural language tool, a brand word identification submodule for intelligently identifying the brand name of a pushed commodity and extracting the brand words in texts such as the commodity title and a shop name, a search text construction submodule for extracting texts from the title of the pushed commodity according to rules to construct a query text list with priorities, and a mall search submodule for calling a service interface in a target mall by using the query text and other necessary information to obtain a candidate commodity list.
In the intelligent search module 20, a brand word recognition submodule, a search text construction submodule and a mall search submodule form circular structures in an execution flow, specifically, 1) the brand word recognition submodule acquires a search result of the mall search submodule and is used for recognizing a brand word, and the recognition result and the search result of the mall search submodule are output to the search text construction submodule, 2) the search text construction submodule reconstructs a search text list with priority by using the input brand word recognition result, the mall search text and an acquired candidate commodity list, if the search text list is empty, the circular is ended, otherwise, the search text with the highest priority is output to the mall search submodule, and 3) the mall search submodule searches commodities in a target mall by using a new search text and inputs the search result to the brand word recognition submodule.
The search text construction sub-module in the intelligent search module 20 meets the principle during operation, 1) search texts output to the mall search sub-module cannot be repeated to reduce the total query times to a target mall, 2) the total number of the search texts output to the mall search sub-module cannot exceed threshold values to control the upper limit of the total query number to the target mall, and 3) the search sub-text sequencing is adjusted according to the search results of the mall search sub-module to improve the search quality within the limited query times.
The intelligent search module 20 may further include a candidate commodity list merging sub-module, configured to merge and deduplicate candidate commodity lists obtained from multiple search texts of pushed commodities.
The similarity calculation module 30 comprises a commodity title similarity calculation operator module, a shop name similarity calculation operator module, a brand name similarity calculation operator module, a price similarity calculation operator module and a similarity comprehensive calculation sub-module, wherein the commodity title similarity calculation operator module is used for calculating the similarity between a pushed commodity and a candidate commodity title, the shop name similarity calculation operator module is used for calculating the similarity between a pushed commodity belonging shop name and a candidate commodity belonging shop name, the brand name similarity calculation operator module is used for calculating the similarity between a pushed commodity belonging brand and a candidate commodity belonging brand, the price similarity calculation operator module is used for calculating the similarity between a pushed commodity price and a candidate commodity price, and the similarity comprehensive calculation sub-module is used for integrating the title similarity, the shop name similarity, the brand name similarity and the price similarity to determine the similarity between the pushed commodity and the candidate commodity.
The commodity information replacing module 40 of the self-media article comprises a commodity push link obtaining submodule and a commodity information replacing submodule, wherein the push link obtaining submodule is used for obtaining a push link of a final replaced commodity and setting the push link as a commodity link of the final replaced commodity, and the commodity information replacing submodule is used for performing information replacement on the corresponding push commodity by using the final replaced commodity in the self-media article.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
It is to be understood that each flow and/or block in the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions which can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagram flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above detailed description is provided for the merchandise recommendation method and system provided by the present invention, and the principle and the embodiment of the present invention are explained by applying specific examples herein, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention, meanwhile, for those skilled in the art , there are changes in the specific embodiment and the application scope according to the idea of the present invention, and in conclusion, the present description should not be construed as limiting the present invention.
Claims (25)
1, A method for mapping commodity links of different shopping malls with each other, comprising the steps of:
101. acquiring commodity information of related commodities to be pushed from the media article;
102. for each pushed commodity, intelligently searching the same-style commodity in a target mall respectively to obtain a corresponding candidate commodity list;
103. for each pushed commodity, calculating a similarity between the pushed commodity and the candidate commodity;
104. for each push item, the item information from the push item in the media article is replaced with the item information of the most similar candidate item.
2. The method of kinds of mutual mapping for commodity links of different shopping malls according to claim 1, wherein in step 101, said commodity information includes at least two kinds of information selected from a commodity title, a commodity link, a price, a brand name and a picture link, wherein said commodity information must include a commodity title and commodity link information.
3. The method of kinds of mutual mapping between commodity links of different shopping malls according to claim 1, wherein in step 101, the commodity information acquisition method of the related commodities adopts a user input or program automatic identification mode.
4. The method of different shopping mall commodity links mapping with each other as claimed in claim 1, wherein the candidate commodity list in step 102 is a commodity information list of similar commodities returned by the target e-commerce platform according to rules through a network interface thereof, each candidate commodity information includes at least four kinds of information of a commodity title, a commodity, a picture link, a commodity brand name and a shop name, and each candidate commodity information must include a commodity title, a commodity, a picture link and commodity link information.
5. The method for mapping the merchandise links of different shopping malls with each other, according to claim 4, wherein the step 102 further comprises the steps of marking the number of words of the title of merchandise to be pushed as N, extracting N words, N < ═ N, re-splicing the words into new character strings in the sequence of the original arrangement as query texts, and using the query texts as keywords to obtain the candidate merchandise list from the target shopping malls.
6. The method of for mapping merchandise links of different shopping malls with each other, according to claim 1, wherein the step 102 of obtaining a corresponding candidate merchandise list comprises:
a. using a natural language tool to perform word segmentation and part-of-speech tagging on the title of the pushed commodity;
b. intelligently identifying and pushing brand names of commodities and extracting brand words in the appointed text;
c. extracting texts from the titles of the pushed commodities according to rules to construct a priority query text list;
d. and calling a service interface in the target mall by using the query text to obtain a candidate commodity list.
7. The method of kinds of commodity links of different shopping malls being mapped onto each other, wherein step a of step 102 is performed with word segmentation and part-of-speech tagging, said word segmentation and part-of-speech tagging are all proprietary words in the natural language processing field, said word segmentation is a process of recombining continuous word sequences of commodity titles into word sequences according to the specification of , and said part-of-speech tagging is a process of tagging which kinds of common nouns, names of people, orientation nouns, number words, place names, organization names or punctuation part-of-speech each word belongs to.
8. The method of , wherein in step 102, the natural language tool comprises an offline tool or a third-party remote service.
9. The method for mapping merchandise links of different shopping malls onto each other, according to the step 102, wherein in the step b, the smart identification of the brand name of the merchandise refers to the smart acquisition of the brand name of merchandise to be pushed by using the title, brand name, and store name information of the merchandise in the merchandise to be pushed, store name and return candidate merchandise list without brand name for merchandise to be pushed.
10. The method of kinds of commodity links of different shopping malls being mapped to each other according to claim 6, wherein in step b of step 102, said designated text includes the title of the commodity to be pushed or the candidate commodity, the shop name text.
11. The method as claimed in claim 6, , wherein in the step d of step 102, the query text is used as a key word to assist other information, the service interface of the target mall is called, and the related item list is searched as the candidate item list of the query text.
12. The method of for mapping merchandise links of different shopping malls onto each other, wherein in step 103, the method for calculating the similarity between the pushed merchandise and the candidate merchandise comprises:
a. calculating the title similarity between the pushed commodity and the candidate commodity;
b. calculating the similarity of the shop names of the pushed commodities and the candidate commodities;
c. calculating the brand name similarity of the pushed commodity and the candidate commodity;
d. calculating price similarity between the pushed commodity and the candidate commodity;
e. the similarity between the pushed commodity and the candidate commodity is comprehensively determined by the title similarity, the shop name similarity, the brand name similarity and the price similarity;
and calculating the similarity between the pushed commodity and the candidate commodity by using the title similarity, the shop name similarity, the brand name similarity and the price similarity in the four similarities, wherein the title similarity is definitely existed, and the similarity between the pushed commodity and the candidate commodity does not exist as long as the attributes of the three similarities do not exist in the three similarities of the shop name similarity, the brand name similarity and the price similarity in the pushed commodity or the candidate commodity .
13. The method of product links of different shopping malls being mapped onto each other, wherein in step 103, the similarity between the pushed product and the candidate product is calculated by weighted sum of title similarity, store name similarity, brand name similarity, and price similarity.
14. The method of for mapping merchandise links of different shopping malls onto each other, wherein in step 103, a, the similarity between two titles is calculated by using edit distance, Jacard coefficient, TF-IDF or word vector method.
15. The method of kinds of mutual mapping between merchandise links of different shopping malls according to claim 12, wherein in step b of step 103, it is required to extract brand words in store names and then perform similarity calculation.
16. The method of different shopping mall commodity links mapping with each other as claimed in claim 12, wherein in the step c of step 103, in consideration of the fact that the brand names are mixed in both chinese and english, a plurality of aliases of the brand need to be extracted and similarity calculation needs to be performed.
17. The method for mapping the commodity links of different malls onto each other according to claim 12, wherein in the step d of step 103, the price similarity is calculated by converting the prices of two commodities into the similarity according to a formula, so as to achieve the goal of maximum similarity between the same prices and smaller similarity when the price difference is larger.
18. The method of kinds of goods links of different shopping malls being mapped to each other, wherein in step 104, the method of replacing the goods information of the pushed goods from the media article with the goods information of the candidate goods with the largest similarity comprises:
acquiring a push link from a target mall as a commodity link of the commodity by utilizing commodity information of the candidate commodity with the maximum similarity and push account information;
and replacing corresponding pushed merchandise information in the self-media article with the updated candidate merchandise information from step .
19, A system for mapping merchandise links of different shopping malls to each other, comprising:
the self-media article commodity information acquisition module is used for acquiring commodity information of related commodities to be pushed from the media article;
the intelligent search module is used for intelligently searching the same-style commodities in the target mall and acquiring a corresponding candidate commodity list;
a similarity calculation module for calculating a similarity between the pushed commodity and the candidate commodity;
and the self-media article commodity information replacing module is used for replacing the commodity information of the pushed commodities in the self-media article with the commodity information of the candidate commodity with the largest similarity.
20. The system of kinds of mutual mapping between commodity links of different shopping malls according to claim 19, wherein said commodity information includes at least two kinds of information selected from the group consisting of commodity title, commodity link, price, brand name and picture link, wherein said commodity information must include commodity title and commodity link information.
21. The system of for mapping merchandise links of different shopping malls onto each other, wherein the intelligent search module comprises:
the word segmentation and part of speech tagging submodule is used for carrying out word segmentation and part of speech tagging on the commodity title by utilizing a natural language tool;
the brand word recognition submodule is used for intelligently recognizing the brand name of the product and extracting the brand words in the product title and the shop name text;
the search text construction sub-module is used for extracting texts from the titles of the pushed commodities according to rules to construct a priority query text list;
and the mall searching submodule is used for calling the service interface in the target mall by using the query text and other necessary information to acquire the candidate commodity list.
22. The system for mapping merchandise links of different shopping malls with each other, wherein the intelligent search module further comprises a candidate merchandise list merge sub-module for merging and de-duplicating candidate merchandise lists obtained from multiple search texts of push merchandise.
23. The system for mapping merchandise links of different malls onto each other, wherein in the intelligent search module, the brand word recognition sub-module, the search text construction sub-module, and the mall search sub-module form loop structures in the execution flow;
the brand word identification submodule is used for acquiring a search result of the mall search submodule and identifying the brand words, and the identification result and the search result of the mall search submodule are output to the search text construction submodule;
the search text construction sub-module is used for reconstructing a search text list with priority by utilizing the input brand word recognition result, the mall search text and the obtained candidate commodity list;
if the search text list is empty, the cycle is ended; otherwise, outputting the search text with the highest priority to the mall search submodule;
and the mall searching submodule searches the target mall for the commodities by using the new search text and inputs the search result into the brand word recognition submodule.
24. The system of for mapping merchandise links of different shopping malls onto each other, wherein the similarity calculation module comprises:
the commodity title similarity calculation operator module is used for calculating the similarity between the pushed commodity and the candidate commodity title;
the shop name similarity operator module is used for calculating the similarity between the shop name of the pushed commodity and the shop name of the candidate commodity;
the brand name similarity operator module is used for calculating the similarity between the brand to which the pushed commodity belongs and the brand to which the candidate commodity belongs;
the price similarity operator module is used for calculating the similarity between the pushed commodity price and the candidate commodity price;
and the similarity comprehensive calculation submodule is used for synthesizing the title similarity, the shop name similarity, the brand name similarity and the price similarity and determining the similarity between the pushed commodity and the candidate commodity.
25. The system of commodity links of different shopping malls for mapping each other according to claim 19, wherein said self-media article commodity information replacement module comprises:
a push link acquisition submodule for acquiring a push link of the final replacement commodity and setting the push link as a commodity link of the final replacement commodity;
and the commodity information replacement submodule is used for performing information replacement on the corresponding pushed commodity by using the final replacement commodity in the self-media article.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910992565.5A CN110738553A (en) | 2019-10-18 | 2019-10-18 | method and system for mapping commodity links of different shopping malls to each other |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910992565.5A CN110738553A (en) | 2019-10-18 | 2019-10-18 | method and system for mapping commodity links of different shopping malls to each other |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110738553A true CN110738553A (en) | 2020-01-31 |
Family
ID=69269220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910992565.5A Pending CN110738553A (en) | 2019-10-18 | 2019-10-18 | method and system for mapping commodity links of different shopping malls to each other |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110738553A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111400345A (en) * | 2020-02-21 | 2020-07-10 | 北京九州云动科技有限公司 | Commodity searching method and device supporting multiple platforms |
| CN112036981A (en) * | 2020-09-02 | 2020-12-04 | 珠海随变科技有限公司 | Method, device, equipment and medium for providing target comparison commodities |
| CN113722377A (en) * | 2021-08-30 | 2021-11-30 | 武汉海云健康科技股份有限公司 | Method and system for building drug standard library |
| CN113793191A (en) * | 2021-02-09 | 2021-12-14 | 京东科技控股股份有限公司 | Commodity matching method and device and electronic equipment |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1674001A (en) * | 2005-04-04 | 2005-09-28 | 栾奕 | Method for establishing key word indx advertisement for articles in internet |
| TW200821970A (en) * | 2006-11-09 | 2008-05-16 | Yan-Yau Wang | Reward feedback method and management server thereof for network publication platform |
| CN101802857A (en) * | 2007-04-19 | 2010-08-11 | 伊扎克·巴拉斯 | Self service advertising method and system |
| CN101819582A (en) * | 2009-02-27 | 2010-09-01 | 捷讯研究有限公司 | System and method for linking AD tagged words |
| CN101896928A (en) * | 2007-12-16 | 2010-11-24 | 软银公司 | Advertisement system and advertising method |
| CN102111905A (en) * | 2009-12-28 | 2011-06-29 | 上海亿动信息技术有限公司 | Method for controlling advertisement information released in editable form of mobile terminal |
| CN102737051A (en) * | 2011-04-12 | 2012-10-17 | 贾洪明 | Method for acquiring merchandize cashback information |
| CN102968729A (en) * | 2011-09-01 | 2013-03-13 | 吉菲斯股份有限公司 | User-based advertisement target location |
| CN103198118A (en) * | 2013-04-01 | 2013-07-10 | 清华大学 | Method and system for backtracking product web pages |
| CN103578012A (en) * | 2012-08-03 | 2014-02-12 | 盛乐信息技术（上海）有限公司 | Information trading method and system |
| CN103577432A (en) * | 2012-07-26 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and system for searching commodity information |
| CN104268282A (en) * | 2014-10-15 | 2015-01-07 | 李阳 | Web banner advertisement displaying method and system |
| CN104657396A (en) * | 2013-11-25 | 2015-05-27 | 腾讯科技（深圳）有限公司 | Data migration method and device |
| CN106294425A (en) * | 2015-05-26 | 2017-01-04 | 富泰华工业（深圳）有限公司 | The automatic image-text method of abstracting of commodity network of relation article and system |
| CN106600357A (en) * | 2016-10-28 | 2017-04-26 | 浙江大学 | Commodity collocation method based on electronic commerce commodity titles |
| CN106776937A (en) * | 2016-12-01 | 2017-05-31 | 腾讯科技（深圳）有限公司 | The method and apparatus of chain keyword in a kind of determination |
| CN107230123A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | commodity mapping method, device and equipment |
| CN107851261A (en) * | 2015-04-03 | 2018-03-27 | 埃克斯凯利博Ip有限责任公司 | For providing the method and system of relevant advertisements |
| CN107908607A (en) * | 2017-11-09 | 2018-04-13 | 中国平安人寿保险股份有限公司 | The product promotion method, apparatus and storage medium that soft text and product are combined |
| CN108833952A (en) * | 2018-06-20 | 2018-11-16 | 北京优酷科技有限公司 | The advertisement placement method and device of video |
| CN110020195A (en) * | 2018-08-16 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Article recommended method and device, storage medium, electronic equipment |
-
2019
- 2019-10-18 CN CN201910992565.5A patent/CN110738553A/en active Pending
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1674001A (en) * | 2005-04-04 | 2005-09-28 | 栾奕 | Method for establishing key word indx advertisement for articles in internet |
| TW200821970A (en) * | 2006-11-09 | 2008-05-16 | Yan-Yau Wang | Reward feedback method and management server thereof for network publication platform |
| CN101802857A (en) * | 2007-04-19 | 2010-08-11 | 伊扎克·巴拉斯 | Self service advertising method and system |
| CN101896928A (en) * | 2007-12-16 | 2010-11-24 | 软银公司 | Advertisement system and advertising method |
| CN101819582A (en) * | 2009-02-27 | 2010-09-01 | 捷讯研究有限公司 | System and method for linking AD tagged words |
| CN102111905A (en) * | 2009-12-28 | 2011-06-29 | 上海亿动信息技术有限公司 | Method for controlling advertisement information released in editable form of mobile terminal |
| CN102737051A (en) * | 2011-04-12 | 2012-10-17 | 贾洪明 | Method for acquiring merchandize cashback information |
| CN102968729A (en) * | 2011-09-01 | 2013-03-13 | 吉菲斯股份有限公司 | User-based advertisement target location |
| CN103577432A (en) * | 2012-07-26 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Method and system for searching commodity information |
| CN103578012A (en) * | 2012-08-03 | 2014-02-12 | 盛乐信息技术（上海）有限公司 | Information trading method and system |
| CN103198118A (en) * | 2013-04-01 | 2013-07-10 | 清华大学 | Method and system for backtracking product web pages |
| CN104657396A (en) * | 2013-11-25 | 2015-05-27 | 腾讯科技（深圳）有限公司 | Data migration method and device |
| CN104268282A (en) * | 2014-10-15 | 2015-01-07 | 李阳 | Web banner advertisement displaying method and system |
| CN107851261A (en) * | 2015-04-03 | 2018-03-27 | 埃克斯凯利博Ip有限责任公司 | For providing the method and system of relevant advertisements |
| CN106294425A (en) * | 2015-05-26 | 2017-01-04 | 富泰华工业（深圳）有限公司 | The automatic image-text method of abstracting of commodity network of relation article and system |
| CN107230123A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | commodity mapping method, device and equipment |
| CN106600357A (en) * | 2016-10-28 | 2017-04-26 | 浙江大学 | Commodity collocation method based on electronic commerce commodity titles |
| CN106776937A (en) * | 2016-12-01 | 2017-05-31 | 腾讯科技（深圳）有限公司 | The method and apparatus of chain keyword in a kind of determination |
| CN107908607A (en) * | 2017-11-09 | 2018-04-13 | 中国平安人寿保险股份有限公司 | The product promotion method, apparatus and storage medium that soft text and product are combined |
| CN108833952A (en) * | 2018-06-20 | 2018-11-16 | 北京优酷科技有限公司 | The advertisement placement method and device of video |
| CN110020195A (en) * | 2018-08-16 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Article recommended method and device, storage medium, electronic equipment |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111400345A (en) * | 2020-02-21 | 2020-07-10 | 北京九州云动科技有限公司 | Commodity searching method and device supporting multiple platforms |
| CN112036981A (en) * | 2020-09-02 | 2020-12-04 | 珠海随变科技有限公司 | Method, device, equipment and medium for providing target comparison commodities |
| CN113793191A (en) * | 2021-02-09 | 2021-12-14 | 京东科技控股股份有限公司 | Commodity matching method and device and electronic equipment |
| CN113793191B (en) * | 2021-02-09 | 2024-05-24 | 京东科技控股股份有限公司 | Commodity matching method and device and electronic equipment |
| CN113722377A (en) * | 2021-08-30 | 2021-11-30 | 武汉海云健康科技股份有限公司 | Method and system for building drug standard library |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230192947A1 (en) | System and method allowing social fashion selection in an electronic marketplace | |
| CN110738553A (en) | method and system for mapping commodity links of different shopping malls to each other | |
| CN107861972B (en) | Method and equipment for displaying full commodity result after user inputs commodity information | |
| CN107748754B (en) | Knowledge graph perfecting method and device | |
| US10360623B2 (en) | Visually generated consumer product presentation | |
| CN107833082B (en) | Commodity picture recommendation method and device | |
| CN105550369B (en) | A kind of method and device for searching for end article collection | |
| CN107332910B (en) | Information pushing method and device | |
| CN105740268B (en) | A kind of information-pushing method and device | |
| CN109635198B (en) | Method, device, medium and electronic equipment for presenting user search results on commodity display platform | |
| CN105868219B (en) | A kind of information issuing method and device | |
| CN102567543A (en) | Clothing picture search method and clothing picture search device | |
| CN108763223A (en) | Method for constructing Chinese-English Mongolian Tibetan language multilingual parallel corpus | |
| US11682060B2 (en) | Methods and apparatuses for providing search results using embedding-based retrieval | |
| CN107169002A (en) | A kind of personalized interface method for pushing and device recognized based on face | |
| JP2019133620A (en) | Coordination retrieval method, computer device and computer program that are based on coordination of multiple objects in image | |
| CN112488781A (en) | Search recommendation method and device, electronic equipment and readable storage medium | |
| CN116739626A (en) | Commodity data mining processing method and device, electronic equipment and readable medium | |
| CN112084307A (en) | Data processing method and device, server and computer readable storage medium | |
| KR20210032691A (en) | Method and apparatus of recommending goods based on network | |
| CN109325529A (en) | Sketch identification method and application of sketch identification method in commodity retrieval | |
| CN117788109A (en) | Method for generating commodity label based on large language model and electronic equipment | |
| CN114756570A (en) | Vertical search method, device and system for purchase scene | |
| CN115641179A (en) | Information pushing method and device and electronic equipment | |
| KR101764361B1 (en) | Method of providing shopping mall service based sns and apparatus for the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200131 |
|
| RJ01 | Rejection of invention patent application after publication |