CN108804541A - Electric business title optimization system and optimization method - Google Patents
Electric business title optimization system and optimization method Download PDFInfo
- Publication number
- CN108804541A CN108804541A CN201810431891.4A CN201810431891A CN108804541A CN 108804541 A CN108804541 A CN 108804541A CN 201810431891 A CN201810431891 A CN 201810431891A CN 108804541 A CN108804541 A CN 108804541A
- Authority
- CN
- China
- Prior art keywords
- commodity
- ranking
- title
- under
- class
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Present invention is disclosed a kind of electric business title optimization system and optimization method, system includes list product ID input units, single product information scratching unit, class term acquiring unit, search result placement unit, the short word acquiring unit of high frequency, ranking predicting unit, removes homogeneous unit, new title input unit and result display unit.Method includes list product ID input steps, single product information scratching step, class term obtaining step, search result crawl step, the short word obtaining step of high frequency, ranking prediction steps, homogeneous step, new title input step and result is gone to show step.The present invention carries out mining analysis for each class each keyword now and its search result, and bigger income is obtained by reasonable combination keyword, brings more flows for commodity and makes flow more accurate.
Description
Technical field
The present invention relates to a kind of optimization system and optimization methods, and in particular to a kind of electricity applied to internet shopping platform
Trade mark inscribes optimization system and optimization method, belongs to e-commerce field.
Background technology
With the universal of internet, the continuous development of shopping online platform, shopping online has been increasingly becoming the shopping of mainstream
One of mode, popularity rate, the utilization rate of shopping online platform are also all rising year by year.
Common net purchase platform is substantially all with function of search at present, and buyer can be searched out by search key
Oneself is to the commodity needed, exactly because also such search mechanisms, the search rank given tacit consent on net purchase platform will directly affect
The sales volume of commodity.For current this kind of search mechanisms, the default search ranking system of the titles of commodity in net purchase platform
Occupy sizable weight in system, how to allow the title of commodity not only to meet the feature of commodity, but also searched for conducive to buyer, just become
Cope with a key problem of net purchase platform search system.
But for actual conditions, the self-ordained title of seller is compared in no database, and is provided to title name
In the case of unfamiliar, the title name formulated generally is difficult the search rank obtained.And seller is if it is desired to pass through oneself
Study to title name rule and optimal commodity title is found by each large database concept, workload is excessively heavy multiple
It is miscellaneous, do not have the possibility of realization.
Thus, the tool that seller optimizes commodity title can be helped to come into being.Such as Chinese patent
CN103544264A discloses a kind of commodity title optimization tool, is related to software technology field, including search term recommendation unit, on
Undercarriage suggests unit, Format adjusting unit, score statistic unit.Although the commodity title optimization tool can provide commodity title
Amending advice, but complete title optimal solution can not be provided, some key search words can only be recommended to allow operation people
Member's self assemble still needs to judge by the experience of operation personnel.In addition, different businessmans, different sales volumes it is same
Commodity, the system also can not be distinguished effectively, can not accomplish precisely to analyze.
In conclusion how to provide a kind of one-stop, the title optimization system that can precisely analyze and optimization method, just at
For those skilled in that art institute urgent problem to be solved.
Invention content
In view of the prior art there are drawbacks described above, the purpose of the present invention is to propose to a kind of applied to internet shopping platform
Electric business title optimization system and optimization method.
The purpose of the present invention will be achieved by the following technical programs:
A kind of electric business title optimization system, including:
Single product ID input units, single product id information for inputting commodity into system;
Single product information scratching unit, for according to the single product id information inputted, capturing classification ID and quotient in electric business platform
The details of product;
Class term acquiring unit for obtaining corresponding class term according to the classification ID of crawl, and determines classification core word;
Search result placement unit, for according to the class term obtained, capturing the search result under each class term;
The short word acquiring unit of high frequency, the title for the search result to crawl are segmented two-by-two, obtain the short word of high frequency;
Ranking predicting unit, for commodity to be made with the ranking prediction based on sales volume;
Homogeneous unit is removed, for analyzing, comparing other titles in shop, avoids title homogeneous;
New title input unit, the title for inputting new commodity into system;
As a result display unit is reported for providing commodity new title with former headed comparison modification.
Preferably, the details of the commodity include the sales volume of commodity and the title of commodity.
Preferably, the ranking predicting unit includes:
Whether ranking judging treatmenting module has ranking, when commodity have under keyword for judging commodity under keyword
When ranking, the difference between the search rank of commodity and sales volume ranking is calculated, when commodity do not have ranking under keyword, does not do and locates
Reason;
First ranking difference judging treatmenting module, ranking difference of the commodity under all class terms has been calculated for judging whether,
When ranking mathematic interpolation of the commodity under all class terms is completed, it is poor to calculate average ranking of the commodity under all keywords
Value, when not completing ranking mathematic interpolation of the commodity under all class terms, the ranking that reruns judging treatmenting module;
Secondary ranking difference judging treatmenting module has calculated ranking difference of the shop under all class terms for judging whether,
When ranking mathematic interpolation of the shop under all class terms is completed, all commodity are under single keyword in calculating shop
Average ranking difference, when not completing ranking mathematic interpolation of the shop under all class terms, the ranking that reruns judgement processing
Module;
Prediction result display module, for according to result of calculation, predicting ranking of the commodity under single keyword, and export ranking
Prediction result.
Preferably, described to go the homogeneous unit to include:
Word segmentation processing module, for all commodity titles in shop to be carried out word segmentation processing by class term;
Repetitive rate computing module, the repetitive rate for calculating commodity title under class term;
Repetitive rate judging treatmenting module, for judging whether the repetitive rate of commodity title is more than system thresholds, when commodity title
When repetitive rate is more than system thresholds, calculate under class term that commodity title is to the coverage rate of classification core word, when the weight of commodity title
When multiple rate is less than system thresholds, it is not processed;
Coverage rate judging treatmenting module, for judging whether coverage rate is less than system thresholds, when coverage rate is less than system thresholds,
Weight of the high-repetition-rate keyword in title score is reduced, when coverage rate is more than system thresholds, is not processed.
A kind of electric business title optimization method, includes the following steps:
S1, single product ID input steps, single product id information of commodity is inputted into method;
S2, single product information scratching step capture classification ID and commodity in electric business platform according to the single product id information inputted
Details;
S3, class term obtaining step obtain corresponding class term according to the classification ID of crawl, and determine classification core word;
S4, search result crawl step capture the search result under each class term according to the class term obtained;
The short word obtaining step of S5, high frequency, segments the title of the search result of crawl two-by-two, obtains the short word of high frequency;
S6, ranking prediction steps make the prediction of the ranking based on sales volume to commodity;
S7, homogeneous step, other titles in analysis, comparison shop is gone to avoid title homogeneous;
S8, new title input step, the title of new commodity is inputted into method;
S9, result show step, provide commodity new title and are reported with former headed comparison modification.
Preferably, the details of the commodity include the sales volume of commodity and the title of commodity.
Preferably, the ranking prediction steps include:
S61, ranking judge processing sub-step, judge commodity under keyword whether have ranking, when commodity under keyword
When having ranking, the difference between the search rank of commodity and sales volume ranking is calculated, when commodity do not have ranking under keyword, is not done
Processing;
S62, first ranking difference judge processing sub-step, and it is poor to judge whether to have calculated ranking of the commodity under all class terms
Value calculates average row of the commodity under all keywords when ranking mathematic interpolation of the commodity under all class terms is completed
Name difference, when not completing ranking mathematic interpolation of the commodity under all class terms, the ranking that reruns judges processing sub-step;
S63, secondary ranking difference judge processing sub-step, and it is poor to judge whether to have calculated ranking of the shop under all class terms
Value, when ranking mathematic interpolation of the shop under all class terms is completed, all commodity are in single keyword in calculating shop
Under average ranking difference, when not completing ranking mathematic interpolation of the shop under all class terms, the ranking that reruns judges
Handle sub-step;
S64, prediction result show sub-step, according to result of calculation, ranking of the prediction commodity under single keyword, and the row of output
Name prediction result.
Preferably, described to go the homogeneous step to include:
All commodity titles in shop are carried out word segmentation processing by S71, word segmentation processing sub-step by class term;
S72, repetitive rate calculate sub-step, calculate the repetitive rate of commodity title under class term;
S73, repetitive rate judge processing sub-step, judge whether the repetitive rate of commodity title is more than method threshold value, when commodity title
Repetitive rate when being more than method threshold value, calculate under class term that commodity title is to the coverage rate of classification core word, when commodity title
When repetitive rate is less than method threshold value, it is not processed;
S74, coverage rate judge processing sub-step, judge whether coverage rate is less than method threshold value, when coverage rate is less than method threshold value
When, weight of the high-repetition-rate keyword in title score is reduced, when coverage rate is more than method threshold value, is not processed.
Compared in the prior art, protrusion effect of the invention is as follows:
The present invention carries out mining analysis for each class each keyword now and its search result, passes through reasonable combination
Keyword obtains bigger income, brings more flows for commodity and makes flow more accurate.
Meanwhile the present invention provides most suitable current quotient by analyzing the keyword drainage of dotey and fetched data
The title of product, even if with a commodity, the scheme of different times, title optimization will not be identical.
In addition, the present invention provides whole title optimal solution for client, and it is more than and recommends some keywords
Client oneself is allowed to remove combination title.Even for the operation personnel that experience is slightly short of, by the present invention, can also exempt from platform
One seat is obtained in expense search flow.And for veteran personnel, it can also obtain preferably search flow and sales volume
It is promoted.
In conclusion the present invention provides one-stop whole title optimization service, using effect is good and precise degrees are high,
With very high use and promotional value.
Just attached drawing in conjunction with the embodiments below, the embodiment of the present invention is described in further detail, so that of the invention
Technical solution is more readily understood, grasps.
Description of the drawings
Fig. 1 is the system structure diagram of the present invention;
Fig. 2 is the operational flow diagram of ranking predicting unit in the present invention;
Fig. 3 is the operational flow diagram that homogeneous unit is removed in the present invention.
Specific implementation mode
As shown, present invention is disclosed a kind of electric business title optimization system applied to internet shopping platform and optimizations
Method.
A kind of electric business title optimization system, including:
Single product ID input units, single product id information for inputting commodity into system;
Single product information scratching unit, for according to the single product id information inputted, capturing classification ID and quotient in electric business platform
The details of product;
Class term acquiring unit for obtaining corresponding class term according to the classification ID of crawl, and determines classification core word;
Search result placement unit, for according to the class term obtained, capturing the search result under each class term;
The short word acquiring unit of high frequency, the title for the search result to crawl are segmented two-by-two, obtain the short word of high frequency;
Ranking predicting unit, for commodity to be made with the ranking prediction based on sales volume;
Homogeneous unit is removed, for analyzing, comparing other titles in shop, avoids title homogeneous;
New title input unit, the title for inputting new commodity into system;
As a result display unit is reported for providing commodity new title with former headed comparison modification.
The details of the commodity include the sales volume of commodity and the title of commodity.
The ranking predicting unit includes:
Whether ranking judging treatmenting module has ranking, when commodity have under keyword for judging commodity under keyword
When ranking, the difference between the search rank of commodity and sales volume ranking is calculated, when commodity do not have ranking under keyword, does not do and locates
Reason;
First ranking difference judging treatmenting module, ranking difference of the commodity under all class terms has been calculated for judging whether,
When ranking mathematic interpolation of the commodity under all class terms is completed, it is poor to calculate average ranking of the commodity under all keywords
Value, when not completing ranking mathematic interpolation of the commodity under all class terms, the ranking that reruns judging treatmenting module;
Secondary ranking difference judging treatmenting module has calculated ranking difference of the shop under all class terms for judging whether,
When ranking mathematic interpolation of the shop under all class terms is completed, all commodity are under single keyword in calculating shop
Average ranking difference, when not completing ranking mathematic interpolation of the shop under all class terms, the ranking that reruns judgement processing
Module;
Prediction result display module, for according to result of calculation, predicting ranking of the commodity under single keyword, and export ranking
Prediction result.
It is described to go the homogeneous unit to include:
Word segmentation processing module, for all commodity titles in shop to be carried out word segmentation processing by class term;
Repetitive rate computing module, the repetitive rate for calculating commodity title under class term;
Repetitive rate judging treatmenting module, for judging whether the repetitive rate of commodity title is more than system thresholds, when commodity title
When repetitive rate is more than system thresholds, calculate under class term that commodity title is to the coverage rate of classification core word, when the weight of commodity title
When multiple rate is less than system thresholds, it is not processed;
Coverage rate judging treatmenting module, for judging whether coverage rate is less than system thresholds, when coverage rate is less than system thresholds,
Weight of the high-repetition-rate keyword in title score is reduced, when coverage rate is more than system thresholds, is not processed.
Present invention further teaches a kind of electric business title optimization methods, include the following steps:
S1, single product ID input steps, single product id information of commodity is inputted into method;
S2, single product information scratching step capture classification ID and commodity in electric business platform according to the single product id information inputted
Details;
S3, class term obtaining step obtain corresponding class term according to the classification ID of crawl, and determine classification core word;
S4, search result crawl step capture the search result under each class term according to the class term obtained;
The short word obtaining step of S5, high frequency, segments the title of the search result of crawl two-by-two, obtains the short word of high frequency;
S6, ranking prediction steps make the prediction of the ranking based on sales volume to commodity;
S7, homogeneous step, other titles in analysis, comparison shop is gone to avoid title homogeneous;
S8, new title input step, the title of new commodity is inputted into method;
S9, result show step, provide commodity new title and are reported with former headed comparison modification.
The details of the commodity include the sales volume of commodity and the title of commodity.
The ranking prediction steps include:
S61, ranking judge processing sub-step, judge commodity under keyword whether have ranking, when commodity under keyword
When having ranking, the difference between the search rank of commodity and sales volume ranking is calculated, when commodity do not have ranking under keyword, is not done
Processing;
S62, first ranking difference judge processing sub-step, and it is poor to judge whether to have calculated ranking of the commodity under all class terms
Value calculates average row of the commodity under all keywords when ranking mathematic interpolation of the commodity under all class terms is completed
Name difference, when not completing ranking mathematic interpolation of the commodity under all class terms, the ranking that reruns judges processing sub-step;
S63, secondary ranking difference judge processing sub-step, and it is poor to judge whether to have calculated ranking of the shop under all class terms
Value, when ranking mathematic interpolation of the shop under all class terms is completed, all commodity are in single keyword in calculating shop
Under average ranking difference, when not completing ranking mathematic interpolation of the shop under all class terms, the ranking that reruns judges
Handle sub-step;
S64, prediction result show sub-step, according to result of calculation, ranking of the prediction commodity under single keyword, and the row of output
Name prediction result.
It is described to go the homogeneous step to include:
All commodity titles in shop are carried out word segmentation processing by S71, word segmentation processing sub-step by class term;
S72, repetitive rate calculate sub-step, calculate the repetitive rate of commodity title under class term;
S73, repetitive rate judge processing sub-step, judge whether the repetitive rate of commodity title is more than method threshold value, when commodity title
Repetitive rate when being more than method threshold value, calculate under class term that commodity title is to the coverage rate of classification core word, when commodity title
When repetitive rate is less than method threshold value, it is not processed;
S74, coverage rate judge processing sub-step, judge whether coverage rate is less than method threshold value, when coverage rate is less than method threshold value
When, weight of the high-repetition-rate keyword in title score is reduced, when coverage rate is more than method threshold value, is not processed.
The present invention carries out mining analysis for each class each keyword now and its search result, by reasonable
Keyword is combined to obtain bigger income, more flows is brought for commodity and makes flow more accurate.
Meanwhile the present invention provides most suitable current quotient by analyzing the keyword drainage of dotey and fetched data
The title of product, even if with a commodity, the scheme of different times, title optimization will not be identical.
In addition, the present invention provides whole title optimal solution for client, and it is more than and recommends some keywords
Client oneself is allowed to remove combination title.Even for the operation personnel that experience is slightly short of, by the present invention, can also exempt from platform
One seat is obtained in expense search flow.And for veteran personnel, it can also obtain preferably search flow and sales volume
It is promoted.
In conclusion the present invention provides one-stop whole title optimization service, using effect is good and precise degrees are high,
With very high use and promotional value.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case of without departing substantially from spirit and essential characteristics of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Profit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent requirements of the claims
Variation is included within the present invention, and should not be considered as the note of any attached drawing table in claim and be limited the claims involved.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiment being appreciated that.
Claims (8)
1. a kind of electric business title optimization system, which is characterized in that including:
Single product ID input units, single product id information for inputting commodity into system;
Single product information scratching unit, for according to the single product id information inputted, capturing classification ID and quotient in electric business platform
The details of product;
Class term acquiring unit for obtaining corresponding class term according to the classification ID of crawl, and determines classification core word;
Search result placement unit, for according to the class term obtained, capturing the search result under each class term;
The short word acquiring unit of high frequency, the title for the search result to crawl are segmented two-by-two, obtain the short word of high frequency;
Ranking predicting unit, for commodity to be made with the ranking prediction based on sales volume;
Homogeneous unit is removed, for analyzing, comparing other titles in shop, avoids title homogeneous;
New title input unit, the title for inputting new commodity into system;
As a result display unit is reported for providing commodity new title with former headed comparison modification.
2. electric business title optimization system according to claim 1, it is characterised in that:The details of the commodity include quotient
The sales volume of product and the title of commodity.
3. electric business title optimization system according to claim 1, which is characterized in that the ranking predicting unit includes:
Whether ranking judging treatmenting module has ranking, when commodity have under keyword for judging commodity under keyword
When ranking, the difference between the search rank of commodity and sales volume ranking is calculated, when commodity do not have ranking under keyword, does not do and locates
Reason;
First ranking difference judging treatmenting module, ranking difference of the commodity under all class terms has been calculated for judging whether,
When ranking mathematic interpolation of the commodity under all class terms is completed, it is poor to calculate average ranking of the commodity under all keywords
Value, when not completing ranking mathematic interpolation of the commodity under all class terms, the ranking that reruns judging treatmenting module;
Secondary ranking difference judging treatmenting module has calculated ranking difference of the shop under all class terms for judging whether,
When ranking mathematic interpolation of the shop under all class terms is completed, all commodity are under single keyword in calculating shop
Average ranking difference, when not completing ranking mathematic interpolation of the shop under all class terms, the ranking that reruns judgement processing
Module;
Prediction result display module, for according to result of calculation, predicting ranking of the commodity under single keyword, and export ranking
Prediction result.
4. electric business title optimization system according to claim 1, which is characterized in that described to go the homogeneous unit to include:
Word segmentation processing module, for all commodity titles in shop to be carried out word segmentation processing by class term;
Repetitive rate computing module, the repetitive rate for calculating commodity title under class term;
Repetitive rate judging treatmenting module, for judging whether the repetitive rate of commodity title is more than system thresholds, when commodity title
When repetitive rate is more than system thresholds, calculate under class term that commodity title is to the coverage rate of classification core word, when the weight of commodity title
When multiple rate is less than system thresholds, it is not processed;
Coverage rate judging treatmenting module, for judging whether coverage rate is less than system thresholds, when coverage rate is less than system thresholds,
Weight of the high-repetition-rate keyword in title score is reduced, when coverage rate is more than system thresholds, is not processed.
5. a kind of electric business title optimization method, which is characterized in that include the following steps:
S1, single product ID input steps, single product id information of commodity is inputted into method;
S2, single product information scratching step capture classification ID and commodity in electric business platform according to the single product id information inputted
Details;
S3, class term obtaining step obtain corresponding class term according to the classification ID of crawl, and determine classification core word;
S4, search result crawl step capture the search result under each class term according to the class term obtained;
The short word obtaining step of S5, high frequency, segments the title of the search result of crawl two-by-two, obtains the short word of high frequency;
S6, ranking prediction steps make the prediction of the ranking based on sales volume to commodity;
S7, homogeneous step, other titles in analysis, comparison shop is gone to avoid title homogeneous;
S8, new title input step, the title of new commodity is inputted into method;
S9, result show step, provide commodity new title and are reported with former headed comparison modification.
6. electric business title optimization method according to claim 5, it is characterised in that:The details of the commodity include quotient
The sales volume of product and the title of commodity.
7. electric business title optimization method according to claim 5, which is characterized in that the ranking prediction steps include:
S61, ranking judge processing sub-step, judge commodity under keyword whether have ranking, when commodity under keyword
When having ranking, the difference between the search rank of commodity and sales volume ranking is calculated, when commodity do not have ranking under keyword, is not done
Processing;
S62, first ranking difference judge processing sub-step, and it is poor to judge whether to have calculated ranking of the commodity under all class terms
Value calculates average row of the commodity under all keywords when ranking mathematic interpolation of the commodity under all class terms is completed
Name difference, when not completing ranking mathematic interpolation of the commodity under all class terms, the ranking that reruns judges processing sub-step;
S63, secondary ranking difference judge processing sub-step, and it is poor to judge whether to have calculated ranking of the shop under all class terms
Value, when ranking mathematic interpolation of the shop under all class terms is completed, all commodity are in single keyword in calculating shop
Under average ranking difference, when not completing ranking mathematic interpolation of the shop under all class terms, the ranking that reruns judges
Handle sub-step;
S64, prediction result show sub-step, according to result of calculation, ranking of the prediction commodity under single keyword, and the row of output
Name prediction result.
8. electric business title optimization method according to claim 5, which is characterized in that described to go the homogeneous step to include:
All commodity titles in shop are carried out word segmentation processing by S71, word segmentation processing sub-step by class term;
S72, repetitive rate calculate sub-step, calculate the repetitive rate of commodity title under class term;
S73, repetitive rate judge processing sub-step, judge whether the repetitive rate of commodity title is more than method threshold value, when commodity title
Repetitive rate when being more than method threshold value, calculate under class term that commodity title is to the coverage rate of classification core word, when commodity title
When repetitive rate is less than method threshold value, it is not processed;
S74, coverage rate judge processing sub-step, judge whether coverage rate is less than method threshold value, when coverage rate is less than method threshold value
When, weight of the high-repetition-rate keyword in title score is reduced, when coverage rate is more than method threshold value, is not processed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810431891.4A CN108804541B (en) | 2018-05-08 | 2018-05-08 | Electric trademark optimization system and optimization method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810431891.4A CN108804541B (en) | 2018-05-08 | 2018-05-08 | Electric trademark optimization system and optimization method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108804541A true CN108804541A (en) | 2018-11-13 |
CN108804541B CN108804541B (en) | 2020-09-18 |
Family
ID=64091983
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810431891.4A Active CN108804541B (en) | 2018-05-08 | 2018-05-08 | Electric trademark optimization system and optimization method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108804541B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111047412A (en) * | 2019-12-16 | 2020-04-21 | 武汉智领云科技有限公司 | Big data electricity merchant operation platform |
CN111191022A (en) * | 2019-12-27 | 2020-05-22 | 苏宁云计算有限公司 | Method and device for generating short titles of commodities |
CN113393289A (en) * | 2021-05-27 | 2021-09-14 | 阿里巴巴新加坡控股有限公司 | Method and device for processing commodity object information and modifying title |
CN115169337A (en) * | 2022-08-24 | 2022-10-11 | 中教畅享(北京)科技有限公司 | Method for calculating keyword score in commodity title optimization |
CN117151083A (en) * | 2023-10-30 | 2023-12-01 | 中教畅享(北京)科技有限公司 | Calculation method for repetition rate in commodity title optimization |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010049664A1 (en) * | 2000-05-19 | 2001-12-06 | Kunio Kashino | Information search method and apparatus, information search server utilizing this apparatus, relevant program, and storage medium storing the program |
US20120016804A1 (en) * | 2010-07-16 | 2012-01-19 | National Taiwan University Of Science And Technology | Carrier selection method for logistics network |
CN103544264A (en) * | 2013-10-17 | 2014-01-29 | 常熟市华安电子工程有限公司 | Commodity title optimizing tool |
CN203778548U (en) * | 2014-03-29 | 2014-08-20 | 南昌辉门密封件系统有限公司 | Corrugated plate forming equipment |
CN105760446A (en) * | 2016-02-03 | 2016-07-13 | 杭州驭猫科技有限公司 | Big data analysis method for shopping website |
CN106682012A (en) * | 2015-11-06 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Commodity object information searching method and device |
CN106919543A (en) * | 2015-12-24 | 2017-07-04 | 阿里巴巴集团控股有限公司 | Determine the method and device of merchandise items title text |
CN106934699A (en) * | 2017-04-28 | 2017-07-07 | 苏州亮磊知识产权运营有限公司 | A kind of large supermarket's intelligent shopping guide system based on Internet of Things |
CN107330752A (en) * | 2017-05-31 | 2017-11-07 | 北京京东尚科信息技术有限公司 | The method and apparatus for recognizing brand word |
-
2018
- 2018-05-08 CN CN201810431891.4A patent/CN108804541B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010049664A1 (en) * | 2000-05-19 | 2001-12-06 | Kunio Kashino | Information search method and apparatus, information search server utilizing this apparatus, relevant program, and storage medium storing the program |
US20120016804A1 (en) * | 2010-07-16 | 2012-01-19 | National Taiwan University Of Science And Technology | Carrier selection method for logistics network |
CN103544264A (en) * | 2013-10-17 | 2014-01-29 | 常熟市华安电子工程有限公司 | Commodity title optimizing tool |
CN203778548U (en) * | 2014-03-29 | 2014-08-20 | 南昌辉门密封件系统有限公司 | Corrugated plate forming equipment |
CN106682012A (en) * | 2015-11-06 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Commodity object information searching method and device |
CN106919543A (en) * | 2015-12-24 | 2017-07-04 | 阿里巴巴集团控股有限公司 | Determine the method and device of merchandise items title text |
CN105760446A (en) * | 2016-02-03 | 2016-07-13 | 杭州驭猫科技有限公司 | Big data analysis method for shopping website |
CN106934699A (en) * | 2017-04-28 | 2017-07-07 | 苏州亮磊知识产权运营有限公司 | A kind of large supermarket's intelligent shopping guide system based on Internet of Things |
CN107330752A (en) * | 2017-05-31 | 2017-11-07 | 北京京东尚科信息技术有限公司 | The method and apparatus for recognizing brand word |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111047412A (en) * | 2019-12-16 | 2020-04-21 | 武汉智领云科技有限公司 | Big data electricity merchant operation platform |
CN111191022A (en) * | 2019-12-27 | 2020-05-22 | 苏宁云计算有限公司 | Method and device for generating short titles of commodities |
CN111191022B (en) * | 2019-12-27 | 2023-07-25 | 苏宁云计算有限公司 | Commodity short header generation method and device |
CN113393289A (en) * | 2021-05-27 | 2021-09-14 | 阿里巴巴新加坡控股有限公司 | Method and device for processing commodity object information and modifying title |
CN115169337A (en) * | 2022-08-24 | 2022-10-11 | 中教畅享(北京)科技有限公司 | Method for calculating keyword score in commodity title optimization |
CN115169337B (en) * | 2022-08-24 | 2023-02-14 | 中教畅享(北京)科技有限公司 | Method for calculating keyword score in commodity title optimization |
CN117151083A (en) * | 2023-10-30 | 2023-12-01 | 中教畅享(北京)科技有限公司 | Calculation method for repetition rate in commodity title optimization |
CN117151083B (en) * | 2023-10-30 | 2024-04-19 | 中教畅享(北京)科技有限公司 | Calculation method for repetition rate in commodity title optimization |
Also Published As
Publication number | Publication date |
---|---|
CN108804541B (en) | 2020-09-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gao et al. | Identifying competitors through comparative relation mining of online reviews in the restaurant industry | |
CN108804541A (en) | Electric business title optimization system and optimization method | |
Sohail et al. | Feature extraction and analysis of online reviews for the recommendation of books using opinion mining technique | |
CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
Chen et al. | The determinants of online customer ratings: a combined domain ontology and topic text analytics approach | |
KR102252188B1 (en) | Product recommendation system and method reflecting user purchasing criterion | |
KR20200048004A (en) | Product recommendation system and method based on user purchase criterion and product review | |
KR101566616B1 (en) | Advertisement decision supporting system using big data-processing and method thereof | |
CN105677767A (en) | Equipment configuration recommending method and device | |
KR102142126B1 (en) | Hierarchical Category Cluster Based Shopping Basket Associated Recommendation Method | |
US20220253874A1 (en) | Product evaluation system and method of use | |
CN112528153B (en) | Content recommendation method, device, apparatus, storage medium, and program product | |
CN105468649B (en) | Method and device for judging matching of objects to be displayed | |
KR20220086932A (en) | Method and apparatus for analyzing customer's needs | |
KR101707660B1 (en) | An e-commerce system based on interest category using related keywords | |
KR20220117425A (en) | Marketability analysis and commercialization methodology analysis system using big data | |
CN105808641A (en) | Mining method and device of off-line resources | |
CN110489531B (en) | Method and device for determining high-frequency problem | |
Jha et al. | Sentiment analysis for E-commerce products using natural language processing | |
Ren et al. | Online choice decision support for consumers: Data-driven analytic hierarchy process based on reviews and feedback | |
Guo et al. | An opinion feature extraction approach based on a multidimensional sentence analysis model | |
Soliman et al. | Utilizing support vector machines in mining online customer reviews | |
Lim et al. | Rule-based personalized comparison shopping including delivery cost | |
JP6509590B2 (en) | User's emotion analysis device and program for goods | |
Kamaruddin | Comparative Study on Sentiment Analysis Approach for Online Shopping Review |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP02 | Change in the address of a patent holder |
Address after: Room 1101, building 1, Rongsheng business center, 135 wangdun Road, Suzhou Industrial Park, Jiangsu Province Patentee after: SUZHOU WENDAO NETWORK TECHNOLOGY Co.,Ltd. Address before: 215123 E-1804 388, Shui Shui Road, Suzhou Industrial Park, Jiangsu. Patentee before: SUZHOU WENDAO NETWORK TECHNOLOGY Co.,Ltd. |
|
CP02 | Change in the address of a patent holder |