CN107133358A - A kind of keyword classification method and device - Google Patents
A kind of keyword classification method and device Download PDFInfo
- Publication number
- CN107133358A CN107133358A CN201710392019.9A CN201710392019A CN107133358A CN 107133358 A CN107133358 A CN 107133358A CN 201710392019 A CN201710392019 A CN 201710392019A CN 107133358 A CN107133358 A CN 107133358A
- Authority
- CN
- China
- Prior art keywords
- grades
- classification
- product
- score
- keyword
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of keyword classification method, for any one keyword, M grades of classification of N belonging to product quantity under can classifying from each N grades belonging to keyword, the summary info of the product under N grades of classification and each N grades of classification, determine the default categories of keyword, each product under default categories can be directly obtained so when being scanned for based on keyword, search efficiency is improved.And determine that the mode of the default categories of keyword can improve classification accuracy for single angle from above-mentioned multiple angles, and without certain data accumulation for existing correction mode, so when data accumulation is not up to correction and required, the default categories that can be still improved by accuracy rate are scanned for, and improve search accuracy rate.
Description
Technical field
The invention belongs to key word processing technology field, in particular, more particularly to a kind of keyword classification method and
Device.
Background technology
When browser gets keyword, and when detecting the function of search of browser and being triggered, background service can be triggered
Device searches for the product with Keywords matching from the product data of more than one hundred million ranks, and determines classification belonging to keyword, so preceding
In platform equipment (terminal device for such as showing browser) key can also be shown while the product of display and Keywords matching
Classify belonging to word.When the classification of any one in classifying belonging to keyword is triggered, foreground equipment only shows the classification being triggered
Under product.
Being currently based on the searching method of keyword has related search method and correction searching method, wherein related search method
It is:When being scanned for by keyword, by background server by big data analysis mode, it is determined that close to search scene and completely
Product under all classification of sufficient search keyword demand, but this mode is needed to all product numbers in background server
According to being analyzed, so as to reduce search efficiency.
And way of search of rectifying a deviation is:Background server transfers the word of (such as the meaning of one's words is related) related to keyword from dictionary,
The keyword is corrected according to the word transferred, binary search is carried out further according to the keyword after correction, obtains in correction
The product that keyword afterwards matches, but this mode needs certain data accumulation, if the data of background server point
Analyse scarce capacity or data volume accumulation is smaller, background server can not be corrected accurately to keyword, obtain more accurate
Keyword (correct after keyword) scan for.
The content of the invention
In view of this, it is an object of the invention to provide a kind of keyword classification method, divided by changing belonging to keyword
Class, improves search efficiency and search accuracy rate.Specifically, technical scheme is as follows:
The present invention provides a kind of keyword classification method, and methods described includes:
Obtain the product quantity under each N grades of classification belonging to keyword and the production under the acquisition N grades of classification
The summary info of product, the N is natural number;
It is determined that it is each N grades classification belonging to N-M grades classification, the M be natural number, and N-M value be more than preset
Grade or equal to predetermined level;
The N-M grades of classification according to belonging to the product quantity, the summary info and the N grades of classification, calculate institute
There are the first total score of the N grades of classification and the second total score of each N grades of classification;
Choose the second total scores that the second total score is more than other N grade classification, and selected all N grades are classified
Second total score sum is more than N grades of the product of the first total score and default weight acquiescences for being categorized as the keyword
Classification.
Preferably, it is described according to the product quantity, the summary info and N grades of affiliated N-M grades of classifying
Classification, calculates the first total score of all N grades of classification and the second total score of each N grades of classification, including:
Product quantity under being classified respectively according to each N grades, obtains the product score of corresponding N grades of classification;
Calculate each summary info of the product and the matching score of the keyword and each N-M fractions of calculating
The classification score of class;
According to the product score, the matching score and the classification score, the of all N grades of classification is obtained
One total score and the second total score of each N grades of classification.
Preferably, the summary info for obtaining the product under the N grades of classification, including:
According to the product score of each N grades of classification, chosen from acquired all N grades of classification described in T
N grades of classification, the T is natural number;
Obtain the summary info of the product under the T N grades of classification.
Preferably, it is described respectively according to the product quantity under each N grades classification, obtain the productions of corresponding N grades of classification
Product score, including:
It is determined that the product quantity and the product number of second level product of the first level product under each N grades of classification
Amount, first level is higher than second level;
The product quantity and the product number of second level product of first level product under being classified according to each N grades
Amount, obtains the product score of corresponding N grades of classification.
Preferably, it is described to choose the second total scores that the second total score is more than other N grade classification, and selected own
N grades of the product that N grades of the second total score sums classified are more than first total score and default weight are categorized as described
The default categories of keyword, including:
According to the second total score of each N grades of classification, all N grades of classification are ranked up, obtain every
Individual described N grades be sorted in it is all N grades classification in ranking;
According to each described N grades rankings being sorted in all N grades of classification, ranking is chosen many before default ranking
Individual N grades of classification;
Judge whether the second total score sum of selected multiple N grades of classification is more than first total score and default
The product of weight, if so, then selected multiple N grades, which are classified, is defined as the default categories of the keyword, if it is not, then increasing
The value of the big default ranking, returns and performs the row that each described N grades of the basis is sorted in all N grades of classification
Position, chooses multiple N grade classification of the ranking before default ranking.
The present invention also provides a kind of keyword classification device, and described device includes:
Acquiring unit, for obtaining the product quantity under each N grades of classification belonging to keyword and obtaining the N
The summary info of product under level classification, the N is natural number;
Determining unit, for determining N-M grades classification belonging to each N grades of classification, the M is natural number, and N-M
Value is more than predetermined level or equal to predetermined level;
Computing unit, for the N-M according to belonging to the product quantity, the summary info and the N grades of classification
Level classification, calculates the first total score of all N grades of classification and the second total score of each N grades of classification;
Unit is chosen, the second total score of other N grades classification, and selected institute are more than for choosing the second total score
N grades of the product that the second total score sum for having N grades of classification is more than first total score and default weight are categorized as institute
State the default categories of keyword.
Preferably, the computing unit includes:First computation subunit, under being classified respectively according to each N grades
Product quantity, obtains the product score of corresponding N grades of classification;
Second computation subunit, for calculate the summary info of each product and the matching score of the keyword with
And calculate the classification score of each N-M grades of classification;
3rd computation subunit, for according to the product score, the matching score and the classification score, obtaining institute
There are the first total score of the N grades of classification and the second total score of each N grades of classification.
Preferably, the acquiring unit obtains the summary info of the product under the N grades of classification, including:According to each
The product score of the N grades of classification, chooses the T N grades of classification, and obtain from acquired all N grades of classification
The summary info of product under the T N grades of classification, the T is natural number.
Preferably, first computation subunit, the product for determining the first level product under each N grades of classification
The product quantity of quantity and second level product, and according to the product quantity of the first level product under each N grades classification
And the product quantity of second level product, the product score of corresponding N grades of classification is obtained, first level is higher than the second level
Not.
Preferably, the selection unit includes:Sort subelement, total for second according to each N grades of classification
All N grades of classification are ranked up by score, obtain each described N grades rows being sorted in all N grades of classification
Position;
Subelement is chosen, for according to each described N grades rankings being sorted in all N grades of classification, choosing ranking
Multiple N grades of classification before default ranking;
Judgment sub-unit, for judging it is described whether the second total score sum of selected multiple N grades of classification is more than
The product of first total score and default weight, if so, it is true by selected multiple N grades of classification then to trigger the selection subelement
It is set to the default categories of the keyword, if it is not, then triggering the selection subelement increases the value of the default ranking, and touches
Send out described and choose described in subelement according to each described N grades rankings being sorted in all N grades of classification, choose ranking and increasing
Multiple N grades of classification before default ranking after big.
Compared with prior art, the above-mentioned technical proposal that the present invention is provided has the following advantages that:
, can be from each N fractions belonging to keyword for any one keyword by above-mentioned technical proposal
N-M grades belonging to product quantity under class, the summary info of the product under N grades of classification and each N grades of classification sort out
Hair, is determined the default categories of keyword, can directly be obtained under default categories so when being scanned for based on keyword
Each product, improves search efficiency.And determined from above-mentioned multiple angles keywords default categories mode relative to
It can improve classification accuracy for single angle, and without certain data accumulation for existing correction mode, so
When data accumulation is not up to correction and required, the default categories that can be still improved by accuracy rate are scanned for, and improve search accurate
True rate.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
These accompanying drawings obtain other accompanying drawings.
Fig. 1 is the flow chart of keyword classification method provided in an embodiment of the present invention;
Fig. 2 is the flow charts that N grades of classification are chosen in keyword classification method provided in an embodiment of the present invention;
Fig. 3 is the flow chart that the second total score is calculated in keyword classification method provided in an embodiment of the present invention;
Fig. 4 is the structural representation of keyword classification device provided in an embodiment of the present invention;
Fig. 5 is the structural representation of computing unit in keyword classification device provided in an embodiment of the present invention;
Fig. 6 is the structural representation of selection unit in keyword classification device provided in an embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Referring to Fig. 1, it illustrates the flow chart of keyword classification method provided in an embodiment of the present invention, being searched for improving
Rope efficiency and search accuracy rate, the specific keyword classification method may comprise steps of:
101:Obtain the production under N grades of classification of product quantity and acquisition under each N grades of classification belonging to keyword
The summary info of product, wherein N are natural number.It is appreciated that:The embodiment of the present invention is with each N fractions belonging to keyword
Class is individual, obtains the summary of the product quantity under each N grades of classification and each product under each N grades of classification
Information.
The product of different stage may be generated in actual production process, such as franchise product and mill run, therefore this
Inventive embodiments can be obtained under the product quantity and each N grades of classification of the franchise product under each N grades of classification respectively
The product quantity of mill run, wherein franchise product is at least to show the product produced with more advanced technology with more Advanced Mode,
Mill run is then the product produced with general technology, therefore the rank for being superior to mill run of franchise product.
For each product, need to set corresponding summary info for each product when product is externally announced,
Can be matched by this summary info with corresponding keyword, wherein summary info is the brief description to product,
At least it is used to indicate type, function and material of product etc., which content embodiment of the present invention summary info specifically includes not
Enumerate again.
102:It is determined that N-M grades classification belonging to each N grades of classification, M is natural number, and N-M value is more than and preset
Grade or equal to predetermined level.Wherein predetermined level is the default categories set in advance for keyword according to practical application
Greatest level, it is not fully identical with the greatest level configured in existing each database, such as in embodiments of the present invention,
The value of greatest level can be the greatest level configured in existing each browser, and the value of certain greatest level can also be small
The greatest level configured in existing each browser.The greatest level for example in existing each database configured is the first order
When, then predetermined level can be the first order or less than the first order, if the greatest level that is configured in existing each browser and waiting
The classification situation of level is when changing, and the predetermined level in the embodiment of the present invention according to the greatest level after change and can also be waited
Level classification situation and change.
Herein it should be noted is that:In embodiments of the present invention, N grades of classification can be third level classification, the
N-M grades classification can be the first order classification, why from the two grades be because current browser show product when most
It is be shown to third level classification more, and by determining that the first order classification that each third level is classified affiliated is because under first order classification
The otherness of each classification is larger, by the first order classification difference supplement accuracy rate that the third level is classified can be caused to improve.When
So in the case where accuracy rate allows, N-M grades of classification can be from second level classification.
103:The N-M grades of classification according to belonging to product quantity, summary info and N grades of classification, calculate all N fractions
First total score of class and the second total score of each N grades of classification.That is (can simultaneously it be examined from product quantity
Consider the product quantity of different stage product), summary info and N-M grades of classification belonging to N grade classification set out, calculating all the
The first total score and the second total score of each N grades of classification that N grades are classified.
Wherein, the first total score of all N grades of classification is the second total score sum of all N grades of classification, is being calculated
Can be with the N-M fractions belonging to product quantity, summary info and N grades of classification during the second total score of each N grades of classification
Class is three independent computing units, is obtained belonging to the corresponding score of product quantity, the corresponding score of summary info and N grades of classification
N-M grades classification score, then by these three scores be added obtain the second total score or the weight according to these three scores
Want degree (can such as configure weight) to obtain the second total score, the second total score acquisition process will subsequently be carried out with reference to flow chart
Explanation.
104:Choose the second total score that the second total score is more than other N grades classification, and selected all N fractions
The N grades of acquiescences for being categorized as keyword that second total score sum of class is more than the first total score and the product of default weight are divided
Class.In embodiments of the present invention, a kind of feasible pattern of N grades of classification is chosen as shown in Fig. 2 may comprise steps of:
201:According to the second total score of each N grades classification, all N grades of classification are ranked up, each N is obtained
Level is sorted in the ranking in all N grades of classification.
202:According to each N grades rankings being sorted in all N grades of classification, ranking is chosen many before default ranking
Individual N grades of classification.It is for choosing the several N grades default categories for being categorized as keyword, in practical application wherein to preset ranking
In can according to actual needs, the product quantity that is searched after such as follow-up input keyword set default ranking, specific to its
The value embodiment of the present invention is not limited.
When the N grades of rankings being sorted in all N grades of classification are obtained by the second total score, then it can obtain pre-
If the second total scores of the corresponding N grade classification of ranking, multiple N grades before default ranking of corresponding ranking, which are classified, refers to the
Two total scores are more than the second total scores of the corresponding N grade classification of default ranking, such as default ranking it is corresponding N grades classify the
Two must be divided into 50 (only illustrate as an example, however it is not limited to this), then rank multiple N grades of classification before default ranking and refer to
Second total score is more than 50.
203:Judge whether the second total score sum of selected multiple N grades of classification is more than the first total score and default
The product of weight, if so, performing step 204;If it is not, performing step 205.
Identical with above-mentioned default ranking, it is also to be used to determine to choose several N grades that weight is preset in embodiments of the present invention
The default categories of keyword are categorized as, can be searched according to actual needs after such as follow-up input keyword in actual applications
Product quantity default weight is set, the value of for example presetting weight can 20% (be experimentally confirmed, 20% can put down
The subsequent searches efficiency that weighs and accuracy rate), its specific value embodiment of the present invention is not limited.
When the second total score sum of selected multiple N grades of classification is more than the product of the first total score and default weight
When, illustrate that selected multiple N grades of classification meet subsequent searches demand, be that this can directly perform step 204, will be selected
Multiple N grades taken, which are classified, is defined as the default categories of keyword, and if selected multiple N grades the second total scores classified
Sum is less than or equal to the product of the first total score and default weight, then after illustrating that selected multiple N grades of classification are unsatisfactory for
Continuous search need, now then performs step 205, is chosen again with increasing default ranking.
204:Selected multiple N grades are classified and is defined as the default categories of keyword.
205:The value of the default ranking of increase, and execution step 202 is returned, when return performs step 202 according to each
The N grades of rankings that are sorted in all N grades of classification, choose multiple N grades before default ranking of the ranking after increase and classify.
Herein it should be noted is that:In the embodiment of the present invention, one preset difference value, the default difference can also be set
It is worth the default categories for determining keyword, it is using process:Second when selected multiple N grades of classification must divide it
During with product more than the first total score and default weight, the second total score sum that selected multiple N grades are classified is judged
Whether it is more than preset difference value with the difference of the first total score and the product of default weight, if so, then reduce the value of default ranking, and
Return and perform step 202, to choose multiple N grade classification of the ranking before default ranking is reduced, can so reduce keyword
Default categories quantity, to improve subsequent searches efficiency.And in the value of the default ranking of increase and taking for the default ranking of reduction
, can be with certain difference during value, such as increase 1 is performed with reducing 1 every time, naturally it is also possible to according to selected multiple N grades
Second total score sum of classification is set with the difference of the first total score and the product of default weight, if the value of both differences
It is larger, then the difference preset twice between ranking can be increased, if the value of both differences is smaller, can reduce and preset twice
Difference between ranking.
, can be from each N fractions belonging to keyword for any one keyword by above-mentioned technical proposal
N-M grades belonging to product quantity under class, the summary info of the product under N grades of classification and each N grades of classification sort out
Hair, is determined the default categories of keyword, can directly be obtained under default categories so when being scanned for based on keyword
Each product, improves search efficiency.And determined from above-mentioned multiple angles keywords default categories mode relative to
It can improve classification accuracy for single angle, and without certain data accumulation for existing correction mode, so
When data accumulation is not up to correction and required, the default categories that can be still improved by accuracy rate are scanned for, and improve search accurate
True rate.
In embodiments of the present invention, the process of the second total score of above-mentioned N grades of classification of calculating is as shown in figure 3, with product
N-M grades belonging to quantity, summary info and N grades of classification are categorized as three independent computing units and are calculated, specifically can be with
Comprise the following steps:
301:Product quantity under being classified respectively according to each N grades, obtains the product score of corresponding N grades of classification.
By preceding described, for each N grades are classified, there may be the product of different stage under it, therefore obtaining product score
When can contemplate product level, then obtaining the process of product score is:It is determined that the first level product under each N grades of classification
The product quantity of product quantity and second level product, the product number of the first level product under being classified according to each N grades
The product quantity of amount and second level product, obtains the product scores of corresponding N grade classification, and wherein first level is higher than the
Two ranks, as it was previously stated, the product of both ranks of each lower privileged trading product and mill run of N grades of classification, then privilege production
Product are first level products, and mill run is second level product.
The first level product under classifying according to each N grades is illustrated how by taking franchise product and mill run as an example below
Product quantity and second level product product quantity, obtain it is corresponding N grades classification product scores:
According to the calculating weight of franchise product and the calculating weight of mill run, (the calculating weight of franchise product is higher than common
The calculating weight of product), the corresponding relation between the franchise product quantity of product and the product quantity of mill run is set, then
Set the score of mill run to can be obtained by the product score of N grades of classification again, be such as equal to 50 commonly with 1 franchise product
Product, 1 mill run is 1 point of computation rule, calculates the product score of each N grades of classification.
302:Calculate the summary info of each product and the matching score of keyword.In embodiments of the present invention, calculating
A kind of feasible pattern with score is:Calculated according to the matching degree of the summary info of each product and keyword, such as setting
Corresponding relation with degree and matching score, is calculating the matching degree of summary info and keyword, is being looked into from corresponding relation
Corresponding matching score is looked for, and the calculation for matching degree can refer to prior art, and this present invention is implemented
Example is no longer illustrated.
In embodiments of the present invention, another feasible pattern of calculating matching score is:Each product is obtained in all productions
Sequence in product, matching score is calculated according to sequence of each product in all products.As can be according to each product
Sales situation or click situation obtain sequence of each product in all products, and are sequentially reduced phase according to mode from front to back
The matching score of product in correspondence sequence, such as:
It is ranked first:Matching score is 100 points;
Ranking 2~5:Matching score is 90 points/;
Ranking 6~10:Matching score is 80 points/;
Ranking 11~20:Matching score is 70 points/;
Ranking 21~50:Matching score is 60 points/;
Ranking 51~100:Matching score is 50 points/;
Ranking 101~200:Matching score is 40 points/;
……
Ranking E (last):Matching score is 0 point/.
Noted herein is a bit:Treatment effeciency can be reduced by calculating the matching score of each product, be that this present invention is real
Apply in example can selected part product calculate matching score, that is to say, that can selected part product summary info, such as according to every
The product score of individual N grades of classification, chooses T N grade classification from acquired all N grades classification, and then acquisition T individual the
The summary info of product under N grades of classification, T is natural number.In the product scores according to each N grades classification, from acquired
When choosing T N grades of classification in all N grades of classification, the product score of T selected N grades of classification is more than the T not chosen
The product score of individual N grades of classification, to obtain the N grade classification higher with keyword degree of correlation.
303:Calculate the classification score of each N-M grades of classification.In embodiments of the present invention, one kind of classification score is calculated
Feasible pattern is:Each lower product quantity with the product of Keywords matching of N-M grades of classification is obtained, is obtained according to product quantity
The corresponding relation for the score, such as setting product quantity and score of classifying of classifying, in the case where getting N-M grades of classification with Keywords matching
Product product quantity, searched from corresponding relation it is corresponding classification score.
In embodiments of the present invention, calculating another feasible pattern of classification score is:Each N-M grades are obtained to be sorted in
Sequence in all N-M grades of classification, according to each N-M grade be sorted in all N-M grades classify in sequence calculate point
Class score.Such as each N-M grades of classification can be obtained according to the sales situation or click situation of the lower product of each N-M grades classification
In the sequence of all N-M grades classification, and N-M grades be sequentially reduced according to mode from front to back in corresponding sequence are classified
Classification score, can such as use following citings, but be not limited to following citings:
When the classification quantity≤5 of N-M grades of classification;
The N-M grades of classification ranked the first:Classification is scored at 1000 points;
N-M grades of classification being number two:Classification is scored at 500 points;
N-M grades of classification being number three:Classification is scored at 300 points;
N-M grades of classification being number four:Classification is scored at 200 points;
N-M grades of classification being number five:Classification is scored at 100 points.
As the N-M grades of classification quantity > 5 classified;
The N-M grades of classification ranked the first:Classification is scored at 1000 points;
N-M grades of classification being number two:Classification is scored at 500 points;
N-M grades of classification being number three:Classification is scored at 300 points;
N-M grades of classification being number four:Classification is scored at 200 points;
N-M grades of classification being number five:Classification is scored at 100 points;
N-M grades of classification of ranking the 6th:Classification is scored at 100 points;
……
Ranking F (last position) N-M grades of classification:Classification is scored at 100 points.
304:According to product score, matching score and classification score, obtain it is all N grades classify the first total scores and
Second total score of each N grades of classification.Directly by the product score of some N grades classification, matching score and it can for example divide
The addition of class score obtains this N grades the second total scores classified or different weights, such as product is configured for these three scores
The weight of score is that the weight of 20%, matching score is that the 40%, weight for score of classifying is 40%, then according to formula A*20%
+ B*40%+C*40% obtains the second total score, and wherein A is product score, and B is matching score, and C is classification score.Obtaining every
After second total score of individual N grades of classification, these second total scores are summed up into calculating, all N grades of classification are obtained
First total score.
For foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as to a series of combination of actions, but
It is that those skilled in the art should know, the present invention is not limited by described sequence of movement, because according to the present invention, certain
A little steps can be carried out sequentially or simultaneously using other.Secondly, those skilled in the art should also know, be retouched in specification
The embodiment stated belongs to preferred embodiment, and involved action and the module not necessarily present invention are necessary.
Corresponding with above method embodiment, the embodiment of the present invention also provides a kind of keyword classification device, for improving
Search efficiency and search accuracy rate, its structural representation are as shown in figure 4, can include:Acquiring unit 11, determining unit 12, meter
Calculate unit 13 and choose unit 14.
Acquiring unit 11, for obtaining N grades of product quantity and acquisition under each N grades of classification belonging to keyword
The summary info of product under classification, N is natural number.It is appreciated that:The embodiment of the present invention is with each belonging to keyword
N grades are categorized as individual, obtain the product quantity under each N grades of classification and each production under each N grades of classification
The summary info of product.
The product of different stage may be generated in actual production process, such as franchise product and mill run, therefore this
Inventive embodiments can be obtained under the product quantity and each N grades of classification of the franchise product under each N grades of classification respectively
The product quantity of mill run, wherein franchise product is at least to show the product produced with more advanced technology with more Advanced Mode,
Mill run is then the product produced with general technology, therefore the rank for being superior to mill run of franchise product.
For each product, need to set corresponding summary info for each product when product is externally announced,
Can be matched by this summary info with corresponding keyword, wherein summary info is the brief description to product,
At least it is used to indicate type, function and material of product etc., which content embodiment of the present invention summary info specifically includes not
Enumerate again.
Determining unit 12, for determining that N-M grades belonging to each N grades of classification are classified, M is natural number, and N-M takes
Value is more than predetermined level or equal to predetermined level.
Wherein predetermined level is the greatest level of the default categories set in advance for keyword according to practical application,
It is not fully identical with the greatest level configured in existing each database, such as in embodiments of the present invention, greatest level
Value can be the greatest level configured in existing each browser, and the value of certain greatest level might be less that existing each clear
The greatest level configured look in device.When the greatest level for example in existing each database configured is the first order, then preset etc.
Level can be for the first order or less than the first order, if the greatest level and the classification situation of grade that are configured in existing each browser
When changing, the predetermined level in the embodiment of the present invention can also be according to the greatest level after change and the classification situation of grade
And change.
Herein it should be noted is that:In embodiments of the present invention, N grades of classification can be third level classification, the
N-M grades classification can be the first order classification, why from the two grades be because current browser show product when most
It is be shown to third level classification more, and by determining that the first order classification that each third level is classified affiliated is because under first order classification
The otherness of each classification is larger, by the first order classification difference supplement accuracy rate that the third level is classified can be caused to improve.When
So in the case where accuracy rate allows, N-M grades of classification can be from second level classification.
Computing unit 13, for the N-M grades of classification according to belonging to product quantity, summary info and N grades of classification, is calculated
First total score of all N grades of classification and the second total score of each N grades of classification.That is can be from product quantity
N-M grades belonging to (product quantity that can consider different stage product simultaneously), summary info and N grades of classification sort out
Hair, calculates the first total score of all N grades of classification and the second total score of each N grades of classification.
Wherein, the first total score of all N grades of classification is the second total score sum of all N grades of classification, is being calculated
Can be with the N-M fractions belonging to product quantity, summary info and N grades of classification during the second total score of each N grades of classification
Class is three independent computing units, is obtained belonging to the corresponding score of product quantity, the corresponding score of summary info and N grades of classification
N-M grades of classification score, then obtain the second total score according to these three scores, the structure of corresponding computing unit 13
Schematic diagram is as shown in figure 5, can include:First computation subunit 131, the second computation subunit 132 and the 3rd computation subunit
133。
First computation subunit 131, for according to the product quantity under each N grades classification, obtaining corresponding N respectively
The product score of level classification.By preceding described, for each N grades are classified, there may be the product of different stage under it, because
This is when obtaining product score it is contemplated that product level, then obtaining the process of product score is:It is determined that under each N grades of classification
First level product product quantity and the product quantity of second level product, according to each N grades classify under first
The product quantity of grade product and the product quantity of second level product, obtain the product score of corresponding N grades of classification, its
Middle first level is higher than second level, as it was previously stated, each N grade classification time privileged trading products and mill run both ranks
Product, then franchise product is first level product, and mill run is second level product.
Second computation subunit 132, by calculate the summary info of each product and the matching score of keyword and based on
Calculate the classification score of each N-M grades of classification.
3rd computation subunit 133, for according to product score, matching score and classification score, obtaining all N fractions
First total score of class and the second total score of each N grades of classification.
For the second computation subunit 132 and the 3rd computation subunit 133, its process for calculating each score please join
The related description in embodiment of the method is read, this embodiment of the present invention is no longer illustrated.
Noted herein is a bit:Treatment effeciency can be reduced by calculating the matching score of each product, be that this present invention is real
Apply and understand selected part product in example to calculate matching score, that is to say, that the summary letter of the meeting selected part product of acquiring unit 11
Breath, such as according to the product score of each N grades classification, chooses T N grades of classification from acquired all N grades of classification, enters
And the summary info of the product under T N grades of classification is obtained, T is natural number.In the product score according to each N grades classification,
When choosing T N grades of classification from acquired all N grades of classification, the product score of T selected N grades of classification is big
In the product score of the T not chosen N grades of classification, to obtain the N grade classification higher with keyword degree of correlation.
Unit 14 is chosen, the second total score of other N grades classification is more than for choosing the second total score, and it is selected
N grades of the product that second total score sum of all N grades of classification is more than the first total score and default weight are categorized as key
The default categories of word.In embodiments of the present invention, the structural representation of unit 14 is chosen as shown in fig. 6, can include:Sequence
Unit 141, selection subelement 142 and judgment sub-unit 143.
Sorted subelement 141, and for the second total score according to each N grades classification, all N grades of classification are arranged
Sequence, obtains each N grades rankings being sorted in all N grades of classification.It is to be used to choose several N fractions wherein to preset ranking
Class is the default categories of keyword, in actual applications can according to actual needs, as searched after follow-up input keyword
Product quantity sets default ranking, and its specific value embodiment of the present invention is not limited.
When the N grades of rankings being sorted in all N grades of classification are obtained by the second total score, then it can obtain pre-
If the second total scores of the corresponding N grade classification of ranking, multiple N grades before default ranking of corresponding ranking, which are classified, refers to the
Two total scores are more than the second total scores of the corresponding N grade classification of default ranking, such as default ranking it is corresponding N grades classify the
Two must be divided into 50 (only illustrate as an example, however it is not limited to this), then rank multiple N grades of classification before default ranking and refer to
Second total score is more than 50.
Subelement 142 is chosen, for according to each N grades rankings being sorted in all N grades of classification, choosing ranking and existing
Multiple N grades of classification before default ranking.
Judgment sub-unit 143, for judging the second total score sums of selected multiple N grades classification whether more than the
The product of one total score and default weight, if so, then triggering chooses subelement 142 by selected multiple N grades of classification determinations
For the default categories of keyword, if it is not, then the value of the default ranking of the increase of subelement 142 is chosen in triggering, and it is single to trigger selection
Member 142 is chosen before default ranking of the ranking after increase according to each N grades rankings being sorted in all N grades of classification
Multiple N grades of classification.
Identical with above-mentioned default ranking, it is also to be used to determine to choose several N grades that weight is preset in embodiments of the present invention
The default categories of keyword are categorized as, can be searched according to actual needs after such as follow-up input keyword in actual applications
Product quantity default weight is set, the value of for example presetting weight can 20% (be experimentally confirmed, 20% can put down
The subsequent searches efficiency that weighs and accuracy rate), its specific value embodiment of the present invention is not limited.
When the second total score sum of selected multiple N grades of classification is more than the product of the first total score and default weight
When, illustrate that selected multiple N grades of classification meet subsequent searches demand, be that this can directly trigger the selection general of subelement 142
Selected multiple N grades, which are classified, is defined as the default categories of keyword, and if selected multiple N grades second classified are total
Score sum is less than or equal to the product of the first total score and default weight, then illustrates that selected multiple N grades of classification are discontented
Sufficient subsequent searches demand, now then the default ranking of the increase of subelement 142 is chosen in triggering, and is chosen again.
, can be from each N fractions belonging to keyword for any one keyword by above-mentioned technical proposal
N-M grades belonging to product quantity under class, the summary info of the product under N grades of classification and each N grades of classification sort out
Hair, is determined the default categories of keyword, can directly be obtained under default categories so when being scanned for based on keyword
Each product, improves search efficiency.And determined from above-mentioned multiple angles keywords default categories mode relative to
It can improve classification accuracy for single angle, and without certain data accumulation for existing correction mode, so
When data accumulation is not up to correction and required, the default categories that can be still improved by accuracy rate are scanned for, and improve search accurate
True rate.
The embodiment of the present invention provides a kind of equipment, and the equipment can be server, PC, PAD, mobile phone etc., wherein equipment
Including processor, memory and storage on a memory and the program that can run on a processor, reality during computing device program
Existing following steps:Obtain the product quantity under each N grades of classification belonging to keyword and obtain under the N grades of classification
The summary info of product, the N is natural number;
It is determined that it is each N grades classification belonging to N-M grades classification, the M be natural number, and N-M value be more than preset
Grade or equal to predetermined level;
The N-M grades of classification according to belonging to the product quantity, the summary info and the N grades of classification, calculate institute
There are the first total score of the N grades of classification and the second total score of each N grades of classification;
Choose the second total scores that the second total score is more than other N grade classification, and selected all N grades are classified
Second total score sum is more than N grades of the product of the first total score and default weight acquiescences for being categorized as the keyword
Classification.
Preferably, it is described according to the product quantity, the summary info and N grades of affiliated N-M grades of classifying
Classification, calculates the first total score of all N grades of classification and the second total score of each N grades of classification, including:
Product quantity under being classified respectively according to each N grades, obtains the product score of corresponding N grades of classification;
Calculate each summary info of the product and the matching score of the keyword and each N-M fractions of calculating
The classification score of class;
According to the product score, the matching score and the classification score, the of all N grades of classification is obtained
One total score and the second total score of each N grades of classification.
Preferably, the summary info for obtaining the product under the N grades of classification, including:
According to the product score of each N grades of classification, chosen from acquired all N grades of classification described in T
N grades of classification, the T is natural number;
Obtain the summary info of the product under the T N grades of classification.
Preferably, it is described respectively according to the product quantity under each N grades classification, obtain the productions of corresponding N grades of classification
Product score, including:
It is determined that the product quantity and the product number of second level product of the first level product under each N grades of classification
Amount, first level is higher than second level;
The product quantity and the product number of second level product of first level product under being classified according to each N grades
Amount, obtains the product score of corresponding N grades of classification.
Preferably, it is described to choose the second total scores that the second total score is more than other N grade classification, and selected own
N grades of the product that N grades of the second total score sums classified are more than first total score and default weight are categorized as described
The default categories of keyword, including:
According to the second total score of each N grades of classification, all N grades of classification are ranked up, obtain every
Individual described N grades be sorted in it is all N grades classification in ranking;
According to each described N grades rankings being sorted in all N grades of classification, ranking is chosen many before default ranking
Individual N grades of classification;
Judge whether the second total score sum of selected multiple N grades of classification is more than first total score and default
The product of weight, if so, then selected multiple N grades, which are classified, is defined as the default categories of the keyword, if it is not, then increasing
The value of the big default ranking, returns and performs the row that each described N grades of the basis is sorted in all N grades of classification
Position, chooses multiple N grade classification of the ranking before default ranking.
The embodiment of the present invention additionally provides a kind of computer program product, when being performed on data processing equipment, is suitable to
Perform the program of initialization there are as below methods step:Obtain keyword belonging to it is each N grade classify under product quantity and
The summary info of the product under the N grades of classification is obtained, the N is natural number;
It is determined that it is each N grades classification belonging to N-M grades classification, the M be natural number, and N-M value be more than preset
Grade or equal to predetermined level;
The N-M grades of classification according to belonging to the product quantity, the summary info and the N grades of classification, calculate institute
There are the first total score of the N grades of classification and the second total score of each N grades of classification;
Choose the second total scores that the second total score is more than other N grade classification, and selected all N grades are classified
Second total score sum is more than N grades of the product of the first total score and default weight acquiescences for being categorized as the keyword
Classification.
Preferably, it is described according to the product quantity, the summary info and N grades of affiliated N-M grades of classifying
Classification, calculates the first total score of all N grades of classification and the second total score of each N grades of classification, including:
Product quantity under being classified respectively according to each N grades, obtains the product score of corresponding N grades of classification;
Calculate each summary info of the product and the matching score of the keyword and each N-M fractions of calculating
The classification score of class;
According to the product score, the matching score and the classification score, the of all N grades of classification is obtained
One total score and the second total score of each N grades of classification.
Preferably, the summary info for obtaining the product under the N grades of classification, including:
According to the product score of each N grades of classification, chosen from acquired all N grades of classification described in T
N grades of classification, the T is natural number;
Obtain the summary info of the product under the T N grades of classification.
Preferably, it is described respectively according to the product quantity under each N grades classification, obtain the productions of corresponding N grades of classification
Product score, including:
It is determined that the product quantity and the product number of second level product of the first level product under each N grades of classification
Amount, first level is higher than second level;
The product quantity and the product number of second level product of first level product under being classified according to each N grades
Amount, obtains the product score of corresponding N grades of classification.
Preferably, it is described to choose the second total scores that the second total score is more than other N grade classification, and selected own
N grades of the product that N grades of the second total score sums classified are more than first total score and default weight are categorized as described
The default categories of keyword, including:
According to the second total score of each N grades of classification, all N grades of classification are ranked up, obtain every
Individual described N grades be sorted in it is all N grades classification in ranking;
According to each described N grades rankings being sorted in all N grades of classification, ranking is chosen many before default ranking
Individual N grades of classification;
Judge whether the second total score sum of selected multiple N grades of classification is more than first total score and default
The product of weight, if so, then selected multiple N grades, which are classified, is defined as the default categories of the keyword, if it is not, then increasing
The value of the big default ranking, returns and performs the row that each described N grades of the basis is sorted in all N grades of classification
Position, chooses multiple N grade classification of the ranking before default ranking.
For equipment provided in an embodiment of the present invention and computer program product, the explanation of each of which step and feasible
Mode refers to the related description in embodiment of the method, and this embodiment of the present invention is no longer illustrated.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation be all between difference with other embodiment, each embodiment identical similar part mutually referring to.
For device class embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is joined
See the part explanation of embodiment of the method.
Finally, in addition it is also necessary to explanation, herein, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between there is any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or equipment including a series of key elements not only include that
A little key elements, but also other key elements including being not expressly set out, or also include be this process, method, article or
The intrinsic key element of equipment.In the absence of more restrictions, the key element limited by sentence "including a ...", is not arranged
Except also there is other identical element in the process including the key element, method, article or equipment.
The foregoing description of the disclosed embodiments, enables those skilled in the art to realize or using the present invention.To this
A variety of modifications of a little embodiments will be apparent for a person skilled in the art, and generic principles defined herein can
Without departing from the spirit or scope of the present invention, to realize in other embodiments.Therefore, the present invention will not be limited
It is formed on the embodiments shown herein, and is to fit to consistent with features of novelty with principles disclosed herein most wide
Scope.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of keyword classification method, it is characterised in that methods described includes:
Obtain the lower product quantity of each N grade classification belonging to keyword and described N grades of acquisition classify under product
Summary info, the N is natural number;
It is determined that N-M grades of classification belonging to each N grades of classification, the M is natural number, and N-M value is more than predetermined level
Or equal to predetermined level;
The N-M grades of classification according to belonging to the product quantity, the summary info and the N grades of classification, calculate all institutes
State the second total score of N grades of the first total scores classified and each N grades of classification;
Choose the second total scores that the second total score is more than other N grade classification, and selected all N grades second classified
The N grades of acquiescences for being categorized as the keyword that total score sum is more than first total score and the product of default weight are divided
Class.
2. according to the method described in claim 1, it is characterised in that it is described according to the product quantity, the summary info and
N-M grades of classification belonging to the N grades of classification, calculate all described N grades the first total scores classified and each described
Second total score of N grades of classification, including:
Product quantity under being classified respectively according to each N grades, obtains the product score of corresponding N grades of classification;
Calculate each summary info of the product and each N-M grades of classification of the matching score of the keyword and calculating
Classification score;
According to the product score, the matching score and the classification score, obtain all N grades of classification first is total
Score and the second total score of each N grades of classification.
3. method according to claim 2, it is characterised in that the summary of the product under the acquisition N grades of classification
Information, including:
According to the product score of each N grades of classification, T described N grades are chosen from acquired all N grades of classification
Classification, the T is natural number;
Obtain the summary info of the product under the T N grades of classification.
4. method according to claim 2, it is characterised in that described respectively according to the product number under each N grades classification
Amount, obtains the product score of corresponding N grades of classification, including:
It is determined that the product quantity and the product quantity of second level product of the first level product under each N grades of classification, the
One is superior to second level;
The product quantity and the product quantity of second level product of first level product under being classified according to each N grades, are obtained
To the product score of corresponding N grades classification.
5. according to the method described in claim 1, it is characterised in that the second total score of the selection is more than other N grades classification
The second total score, and selected all N grades of classification the second total score sums be more than first total score with it is default
N grades of the product of weight are categorized as the default categories of the keyword, including:
According to the second total score of each N grades of classification, all N grades of classification are ranked up, each institute is obtained
State the N grades of rankings being sorted in all N grades of classification;
According to each described N grades rankings being sorted in all N grades of classification, multiple the of ranking before default ranking are chosen
N grades of classification;
Judge whether the second total score sum of selected multiple N grades of classification is more than first total score and default weight
Product, if so, then selected multiple N grades, which are classified, is defined as the default categories of the keyword, if it is not, then increasing institute
The value of default ranking is stated, returns and performs the ranking that each described N grades of the basis is sorted in all N grades of classification, choosing
Take multiple N grade classification of the ranking before default ranking.
6. a kind of keyword classification device, it is characterised in that described device includes:
Acquiring unit, for obtaining the product quantity under each N grades of classification belonging to keyword and obtaining the N fractions
The summary info of product under class, the N is natural number;
Determining unit, for determining N-M grades classification belonging to each N grades of classification, the M is natural number, and N-M value
More than predetermined level or equal to predetermined level;
Computing unit, for the N-M fractions according to belonging to the product quantity, the summary info and the N grades of classification
Class, calculates the first total score of all N grades of classification and the second total score of each N grades of classification;
Unit is chosen, is more than other N grade the second total scores classified for choosing the second total score, and selected all the
N grades of the product that N grades of the second total score sums classified are more than first total score and default weight are categorized as the pass
The default categories of keyword.
7. device according to claim 6, it is characterised in that the computing unit includes:First computation subunit, is used for
Product quantity under being classified respectively according to each N grades, obtains the product score of corresponding N grades of classification;
Second computation subunit, by calculate the summary info of each product and the matching score of the keyword and based on
Calculate the classification score of each N-M grades of classification;
3rd computation subunit, for according to the product score, the matching score and the classification score, obtaining all institutes
State the second total score of N grades of the first total scores classified and each N grades of classification.
8. device according to claim 7, it is characterised in that the acquiring unit obtains the production under the N grades of classification
The summary info of product, including:According to the product score of each N grades of classification, selected from acquired all N grades of classification
The T N grades of classification are taken, and obtain the summary info of the product under the T N grades of classification, the T is nature
Number.
9. device according to claim 7, it is characterised in that first computation subunit, for determining each N grades
The product quantity and the product quantity of second level product of first level product under classification, and according to each N grades classification
Under first level product product quantity and the product quantity of second level product, obtain it is corresponding N grades classification productions
Product score, first level is higher than second level.
10. device according to claim 6, it is characterised in that the selection unit includes:Sort subelement, for root
According to the second total score of each N grades of classification, all N grades of classification are ranked up, each described N grades are obtained
It is sorted in the ranking in all N grades of classification;
Subelement is chosen, for according to each described N grades rankings being sorted in all N grades of classification, choosing ranking pre-
If multiple N grades of classification before ranking;
Judgment sub-unit, for judging whether the second total score sum of selected multiple N grades of classification is more than described first
Selected multiple N grades of classification, are defined as by the product of total score and default weight if so, then triggering the selection subelement
The default categories of the keyword, if it is not, then triggering the selection subelement increases the value of the default ranking, and trigger institute
State and choose described in subelement according to each described N grades rankings being sorted in all N grades of classification, choose ranking after increase
Default ranking before it is multiple N grades classification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710392019.9A CN107133358A (en) | 2017-05-27 | 2017-05-27 | A kind of keyword classification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710392019.9A CN107133358A (en) | 2017-05-27 | 2017-05-27 | A kind of keyword classification method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107133358A true CN107133358A (en) | 2017-09-05 |
Family
ID=59734208
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710392019.9A Pending CN107133358A (en) | 2017-05-27 | 2017-05-27 | A kind of keyword classification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107133358A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103377436A (en) * | 2012-04-27 | 2013-10-30 | 纽海信息技术(上海)有限公司 | System and method for recommending sales promotions |
CN103577423A (en) * | 2012-07-23 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Keyword classification method and system |
CN105138680A (en) * | 2015-09-14 | 2015-12-09 | 郑州悉知信息科技股份有限公司 | Keyword classification method and device and product search method and device |
-
2017
- 2017-05-27 CN CN201710392019.9A patent/CN107133358A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103377436A (en) * | 2012-04-27 | 2013-10-30 | 纽海信息技术(上海)有限公司 | System and method for recommending sales promotions |
CN103577423A (en) * | 2012-07-23 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Keyword classification method and system |
CN105138680A (en) * | 2015-09-14 | 2015-12-09 | 郑州悉知信息科技股份有限公司 | Keyword classification method and device and product search method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9117006B2 (en) | Recommending keywords | |
US8275773B2 (en) | Method of searching text to find relevant content | |
US9436707B2 (en) | Content-based image ranking | |
US10354308B2 (en) | Distinguishing accessories from products for ranking search results | |
US8271476B2 (en) | Method of searching text to find user community changes of interest and drug side effect upsurges, and presenting advertisements to users | |
WO2019223552A1 (en) | Article recommendation method and apparatus, and computer device and storage medium | |
US9311650B2 (en) | Determining search result rankings based on trust level values associated with sellers | |
CN105653562B (en) | The calculation method and device of correlation between a kind of content of text and inquiry request | |
US20090259646A1 (en) | Method for Calculating Score for Search Query | |
TWI615723B (en) | Network search method and device | |
WO2014093433A1 (en) | Analyzing commodity evaluations | |
CN109064293B (en) | Commodity recommendation method and device, computer equipment and storage medium | |
JP2001117946A (en) | Associated text search and retrieval system | |
CN107247743A (en) | A kind of judicial class case search method and system | |
US9977816B1 (en) | Link-based ranking of objects that do not include explicitly defined links | |
CN112487283A (en) | Method and device for training model, electronic equipment and readable storage medium | |
CN109344232A (en) | A kind of public feelings information search method and terminal device | |
CN104933149A (en) | Information searching method and information searching device | |
JP6433270B2 (en) | Content search result providing system and content search result providing method | |
CN112667571A (en) | Biomedical literature search and sorting method and device | |
CN107133358A (en) | A kind of keyword classification method and device | |
CN110633418A (en) | Commodity recommendation method and device | |
KR102670060B1 (en) | Customized recommendation method and system for selecting customer reviews | |
CN115129990A (en) | Human resource online matching system based on user demands | |
CN110825967A (en) | Recommendation list re-ranking method for improving diversity of recommendation system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170905 |