CN107545460A - One kind digitlization color page promotion management and analysis method, storage device and mobile terminal - Google Patents
One kind digitlization color page promotion management and analysis method, storage device and mobile terminal Download PDFInfo
- Publication number
- CN107545460A CN107545460A CN201710613295.3A CN201710613295A CN107545460A CN 107545460 A CN107545460 A CN 107545460A CN 201710613295 A CN201710613295 A CN 201710613295A CN 107545460 A CN107545460 A CN 107545460A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- commercial goods
- color page
- goods labelses
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 100
- 238000007726 management method Methods 0.000 title claims abstract description 12
- 238000003860 storage Methods 0.000 title claims description 15
- 238000012545 processing Methods 0.000 claims abstract description 46
- 238000000556 factor analysis Methods 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000000694 effects Effects 0.000 claims abstract description 20
- 238000013500 data storage Methods 0.000 claims abstract description 19
- 238000012937 correction Methods 0.000 claims abstract description 11
- 239000013589 supplement Substances 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000003542 behavioural effect Effects 0.000 claims description 12
- 241001269238 Data Species 0.000 claims description 9
- 238000005520 cutting process Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 9
- 239000000047 product Substances 0.000 claims description 9
- 230000001902 propagating effect Effects 0.000 abstract description 11
- 238000010186 staining Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
Abstract
The invention discloses one kind digitlization color page promotion management and analysis method, suitable for being performed computer equipment, including for storing the database of commodity data, this method comprises the following steps：S1. commodity color page gathers；S2. digitized processing：Image is split；Content recognition；Factor analysis；Supplement check and correction；Data storage；S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding commodity basic information.The present invention realizes the procedure of propagating poster, automatic business processing, realizes the electronization of color page rapidly, issue shows and launched the effect of staining effect promptly and accurately by all kinds of means.
Description
Technical field
The present invention relates to electronic poster technical field, and in particular to one kind digitlization color page promotion management and analysis method.
Background technology
Color page is that propagating poster is a kind of the most frequently used advertising of retailer and sales promotion information published method, in tradition side
Under the pattern of formula, color page needs a series of links such as typesetting, check and correction, printing, dispatching, delivery, it is necessary to be related to Planning Department, buying
Multiple departments such as portion, sales department, information portion, operation portion and shops coordinate.This traditional color page is by paper printing, under line
The pattern of channel granting, it has the following disadvantages：
Participating department is more, and cost of manufacture is high；The content production cycle is long, later stage change is difficult；It is small that scope is launched under line, cost
Height, the final effect of publicity are difficult to define.
To solve the above problems, it is by the way of at present：Enterprise is converted to papery color page by Edition Contains mode
Electronics webpage, the mode being illustrated in its portal website.But this mode similarly Shortcomings：
Electronics webpage needs special messenger (webpage designer) to carry out, including the follow-up of whole website aspect safeguards that operation cost is high；
Mode of operation does not form system, bottleneck in conversion efficiency be present, often because matter of time, and reduces coverage；Launch
Scope still is limited to own channel, and exposure rate is low；Effect analysis is realized if desired, also needs substantial amounts of development, cost
It is high.
Therefore, there are a kind of procedure to be developed, automatic business processing, realize the electronization of color page rapidly, issue exhibition by all kinds of means
Show, launch the generation method of the electronics propagating poster of staining effect promptly and accurately.
The content of the invention
It is an object of the invention to overcome above-mentioned the deficiencies in the prior art, there is provided a kind of procedure, automatic business processing, rapidly
The electronization of color page is realized, displaying is issued by all kinds of means, launches the generation method of the electronics propagating poster of staining effect promptly and accurately.
To reach above-mentioned purpose, what the present invention was realized in：
One kind digitlization color page promotion management and analysis method, suitable for being performed computer equipment, including for storing up
There is the database of commodity data, this method comprises the following steps：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single business by the color page cutting by way of Boundary Recognition and human assistance
Product picture；
S3-2. content recognition：By carrying out OCR identifications to the word on particular commodity picture, commodity text corresponding to acquisition
Word description information；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, institute
The Back ground Information for stating commodity comprises at least Brand, category, specification, price and promotion method；
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission is supplemented, it is right
The information of mistake is corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and make
Structural data storage is carried out with MySQL, document datastore is carried out using ElasticSearch；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding
Commodity basic information.
Preferably, the collection of the commodity color page includes collection manually or directly grabbed automatically from network by network
Take；
Participle analyzing and processing is carried out by Lucence or Lingpipe in the S3-3. factor analysis step.
Preferably, in addition to step：
S5 user behavior datas gather：Carry out data in App and H5 to bury a little, by burying a collection consumer consumption behavior number
According to and by streaming computing combined data；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation, which touches to reach, to divide
Analysis, content analysis and customer analysis report.
Preferably, the streaming computing combined data includes：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, Commercial goods labelses and user
Behavior attention rate functional relation on some Commercial goods labels, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior concern of Commercial goods labelses and user on some Commercial goods labels
Functional relation is spent, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
Described touch includes up to analysis, content analysis and customer analysis report：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content
Analysis report；Customer analysis report is formed by being summarized by user.
A kind of storage device, wherein storing a plurality of instruction, the instruction loads suitable for processor and performs following behaviour
Make：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single business by the color page cutting by way of Boundary Recognition and human assistance
Product picture；
S3-2. content recognition：By carrying out OCR identifications to the word on particular commodity picture, commodity text corresponding to acquisition
Word description information；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, institute
The Back ground Information for stating commodity comprises at least Brand, category, specification, price and promotion method；
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission is supplemented, it is right
The information of mistake is corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and make
Structural data storage is carried out with MySQL, document datastore is carried out using ElasticSearch；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding
Commodity basic information.
Preferably, the collection of the commodity color page includes collection manually or directly grabbed automatically from network by network
Take；
Participle analyzing and processing is carried out by Lucence or Lingpipe in the S3-3. factor analysis step.
Preferably, in addition to step：
S5 user behavior datas gather：Carry out data in App and H5 to bury a little, by burying a collection consumer consumption behavior number
Include according to and by streaming computing combined data, the streaming computing combined data：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, Commercial goods labelses and user
Behavior attention rate functional relation on some Commercial goods labels, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior concern of Commercial goods labelses and user on some Commercial goods labels
Functional relation is spent, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation, which touches to reach, to divide
Analysis, content analysis and customer analysis report, described touch include up to analysis, content analysis and customer analysis report：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content
Analysis report；Customer analysis report is formed by being summarized by user.
A kind of mobile terminal, including processor, it is adapted to carry out each instruction；Including holder, suitable for storing a plurality of instruction,
The instruction is suitable to be loaded by the processor and perform following operation：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single business by the color page cutting by way of Boundary Recognition and human assistance
Product picture；
S3-2. content recognition：By carrying out OCR identifications to the word on particular commodity picture, commodity text corresponding to acquisition
Word description information；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, institute
The Back ground Information for stating commodity comprises at least Brand, category, specification, price and promotion method；
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission is supplemented, it is right
The information of mistake is corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and make
Structural data storage is carried out with MySQL, document datastore is carried out using ElasticSearch；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding
Commodity basic information.
Preferably, the collection of the commodity color page includes collection manually or directly grabbed automatically from network by network
Take；
Participle analyzing and processing is carried out by Lucence or Lingpipe in the S3-3. factor analysis step.
Preferably, in addition to step：
S5 user behavior datas gather：Carry out data in App and H5 to bury a little, by burying a collection consumer consumption behavior number
Include according to and by streaming computing combined data, the streaming computing combined data：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, Commercial goods labelses and user
Behavior attention rate functional relation on some Commercial goods labels, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior concern of Commercial goods labelses and user on some Commercial goods labels
Functional relation is spent, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation, which touches to reach, to divide
Analysis, content analysis and customer analysis report, described touch include up to analysis, content analysis and customer analysis report：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content
Analysis report；Customer analysis report is formed by being summarized by user.
The beneficial effects of the invention are as follows：The present invention to traditional color page by being acquired and digitized processing is saved in data
In simultaneously by being issued to channel, quantitative analysis then is acquired to the buying behavior data of consumer after issue, obtained
To touching up to analysis, content analysis and customer analysis report, procedure, the automatic business processing of propagating poster are realized, it is rapid to realize
The electronization of color page, the by all kinds of means effect of issue displaying and dispensing staining effect promptly and accurately.
Brief description of the drawings
Fig. 1, which is that the present invention is a kind of, digitizes color page promotion management and the operating process block diagram of analysis method；
Fig. 2 is the operating process block diagram of digital processing step of the present invention.
Embodiment
The embodiment of the present invention is described further below in conjunction with the accompanying drawings.
As illustrated in fig. 1 and 2, a kind of digitlization color page promotion management and analysis method, including for storing commodity data
Database, this method comprises the following steps：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database, color page here
Refer to the propagating poster that retailer advertises with sales promotion information, justifying, there is papery, also there is the electronic edition on webpage
, the collection of the commodity color page includes collection manually or directly captured automatically from network by network；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single business by the color page cutting by way of Boundary Recognition and human assistance
Product picture；
S3-2. content recognition：By carrying out OCR identifications (Optical Character to the word on particular commodity picture
Recognition, OCR, it is by the word content on picture, photo, is converted directly into editable text
Technology), commodity character description information corresponding to acquisition；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, institute
The Back ground Information for stating commodity comprises at least Brand, category, specification, price and promotion method；
By Lucence, (Lucene is the one of apache software foundation 4jakarta project team in factor analysis step
Sub-project, be the full-text search engine kit of an open source code) or Lingpipe (Lingpipe is alias companies
A natural language processing software kit of exploitation) carry out participle analyzing and processing.
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission is supplemented, it is right
The information of mistake is corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and make
Structural data storage is carried out with MySQL (MySQL is a Relational DBMS) (structural data, simply to come
Say to be exactly database, structural data is also referred to as row data, be by bivariate table structure come logical expression and realize data, strictly
Ground follows data format and length specification, is mainly stored and is managed by relevant database), use
ElasticSearch (ElasticSearch is a search server based on Lucene) carries out document datastore；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding
Commodity basic information, the channel of issue have own channel, a third party's channel, pushing-type (third-party platform) and it is pull-type (SDK,
Software Development Kit SDKs) etc..
S5 user behavior datas gather：(Html5 abbreviation, it is kernel language, the standard universal of WWW in App and H5
The 5th time of one under markup language application HTML (HTML) great to repair) in carry out data and bury point (burying a little, be
A kind of conventional collecting method of web analytics), by burying a collection consumer consumption behavior data and passing through streaming computing
Combined data；
Wherein, the streaming computing combined data includes：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, Commercial goods labelses and user
Behavior attention rate functional relation on some Commercial goods labels, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior concern of Commercial goods labelses and user on some Commercial goods labels
Functional relation is spent, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation, which touches to reach, to divide
Analysis, content analysis and customer analysis report.
Contain the volume of data such as user, commodity, shop, time in behavioral data, can be by different during concrete analysis
Dimension, successively collected, ultimately form 3 major class analysis reports：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content
Analysis report；Customer analysis report is formed by being summarized by user.
After the issue of electronics propagating poster, user obtains sales promotion information and carries out purchase consumption, by entering to user's buying behavior
Row processing can obtain accurately the effect of publicity feedback.
A kind of storage device, wherein storing a plurality of instruction, the instruction loads suitable for processor and performs following behaviour
Make：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database, color page here
Refer to the propagating poster that retailer advertises with sales promotion information, justifying, there is papery, also there is the electronic edition on webpage
, the collection of the commodity color page includes collection manually or directly captured automatically from network by network；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single business by the color page cutting by way of Boundary Recognition and human assistance
Product picture；
S3-2. content recognition：By carrying out OCR identifications to the word on particular commodity picture, commodity text corresponding to acquisition
Word description information；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, institute
The Back ground Information for stating commodity comprises at least Brand, category, specification, price and promotion method；
Participle analyzing and processing is carried out by Lucence or Lingpipe in factor analysis step.
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission is supplemented, it is right
The information of mistake is corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and make
Structural data storage is carried out with MySQL, document datastore is carried out using ElasticSearch；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding
Commodity basic information, the channel of issue have own channel, third party's channel, pushing-type (third-party platform) and pull-type (SDK) etc..
S5 user behavior datas gather：Carry out data in App and H5 to bury a little, by burying a collection consumer consumption behavior number
According to and by streaming computing combined data；
Wherein, the streaming computing combined data includes：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, Commercial goods labelses and user
Behavior attention rate functional relation on some Commercial goods labels, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior concern of Commercial goods labelses and user on some Commercial goods labels
Functional relation is spent, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation, which touches to reach, to divide
Analysis, content analysis and customer analysis report.
Contain the volume of data such as user, commodity, shop, time in behavioral data, can be by different during concrete analysis
Dimension, successively collected, ultimately form 3 major class analysis reports：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content
Analysis report；Customer analysis report is formed by being summarized by user.
After the issue of electronics propagating poster, user obtains sales promotion information and carries out purchase consumption, by entering to user's buying behavior
Row processing can obtain accurately the effect of publicity feedback.
A kind of mobile terminal, including processor, it is adapted to carry out each instruction；Including holder, suitable for storing a plurality of instruction,
The instruction is suitable to be loaded by the processor and perform following operation：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database, color page here
Refer to the propagating poster that retailer advertises with sales promotion information, justifying, there is papery, also there is the electronic edition on webpage
, the collection of the commodity color page includes collection manually or directly captured automatically from network by network；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single business by the color page cutting by way of Boundary Recognition and human assistance
Product picture；
S3-2. content recognition：By carrying out OCR identifications to the word on particular commodity picture, commodity text corresponding to acquisition
Word description information；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, institute
The Back ground Information for stating commodity comprises at least Brand, category, specification, price and promotion method；
Participle analyzing and processing is carried out by Lucence or Lingpipe in factor analysis step.
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission is supplemented, it is right
The information of mistake is corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and make
Structural data storage is carried out with MySQL, document datastore is carried out using ElasticSearch；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding
Commodity basic information, the channel of issue have own channel, third party's channel, pushing-type (third-party platform) and pull-type (SDK) etc..
S5 user behavior datas gather：Carry out data in App and H5 to bury a little, by burying a collection consumer consumption behavior number
According to and by streaming computing combined data；
Wherein, the streaming computing combined data includes：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, Commercial goods labelses and user
Behavior attention rate functional relation on some Commercial goods labels, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior concern of Commercial goods labelses and user on some Commercial goods labels
Functional relation is spent, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation, which touches to reach, to divide
Analysis, content analysis and customer analysis report.
Contain the volume of data such as user, commodity, shop, time in behavioral data, can be by different during concrete analysis
Dimension, successively collected, ultimately form 3 major class analysis reports：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content
Analysis report；Customer analysis report is formed by being summarized by user.
After the issue of electronics propagating poster, user obtains sales promotion information and carries out purchase consumption, by entering to user's buying behavior
Row processing can obtain accurately the effect of publicity feedback.
The announcement and teaching of book according to the above description, those skilled in the art in the invention can also be to above-mentioned embodiment party
Formula is changed and changed.Therefore, the invention is not limited in embodiment disclosed and described above, to the one of invention
A little modifications and changes should also be as falling into the scope of the claims of the present invention.In addition, although used in this specification
Some specific terms, but these terms are merely for convenience of description, do not form any restrictions to the present invention.
Claims (10)
1. one kind digitlization color page promotion management and analysis method, suitable for being performed computer equipment, including for storing
There is the database of commodity data, it is characterised in that this method comprises the following steps：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single commodity figure by the color page cutting by way of Boundary Recognition and human assistance
Piece；
S3-2. content recognition：By carrying out OCR identifications to the word on particular commodity picture, commodity word is retouched corresponding to acquisition
State information；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, the business
The Back ground Information of product comprises at least Brand, category, specification, price and promotion method；
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission supplemented, to mistake
Information corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and use
MySQL carries out structural data storage, and document datastore is carried out using ElasticSearch；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding commodity
Back ground Information.
2. a kind of digitlization color page promotion management as claimed in claim 1 and analysis method, it is characterised in that the commodity are color
The collection of page includes collection manually or directly captured automatically from network by network；
Participle analyzing and processing is carried out by Lucence or Lingpipe in the S3-3. factor analysis step.
3. a kind of digitlization color page promotion management as claimed in claim 1 and analysis method, it is characterised in that also include step
Suddenly：
S5 user behavior datas gather：Carry out data in App and H5 to bury a little, by burying a collection consumer consumption behavior data simultaneously
Pass through streaming computing combined data；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation is touched to reach and analyzes, be interior
Hold analysis and customer analysis report.
4. a kind of digitlization color page promotion management as claimed in claim 3 and analysis method, it is characterised in that the streaming meter
Calculating combined data includes：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, and Commercial goods labelses and user are at certain
Behavior attention rate functional relation on individual Commercial goods labelses, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior attention rate letter of Commercial goods labelses and user on some Commercial goods labels
Number relation, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
Described touch includes up to analysis, content analysis and customer analysis report：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content analysis
Report；Customer analysis report is formed by being summarized by user.
5. a kind of storage device, wherein storing a plurality of instruction, it is characterised in that the instruction is loaded and held suitable for processor
Row is following to be operated：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single commodity figure by the color page cutting by way of Boundary Recognition and human assistance
Piece；
S3-2. content recognition：By carrying out OCR identifications to the word on particular commodity picture, commodity word is retouched corresponding to acquisition
State information；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, the business
The Back ground Information of product comprises at least Brand, category, specification, price and promotion method；
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission supplemented, to mistake
Information corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and use
MySQL carries out structural data storage, and document datastore is carried out using ElasticSearch；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding commodity
Back ground Information.
6. a kind of storage device as claimed in claim 5, it is characterised in that the collection of the commodity color page includes collection manually
Or directly captured automatically from network by network；
Participle analyzing and processing is carried out by Lucence or Lingpipe in the S3-3. factor analysis step.
7. a kind of digitlization color page promotion management as claimed in claim 5 and analysis method, it is characterised in that also include step
Suddenly：
S5 user behavior datas gather：Carry out data in App and H5 to bury a little, by burying a collection consumer consumption behavior data simultaneously
By streaming computing combined data, the streaming computing combined data includes：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, and Commercial goods labelses and user are at certain
Behavior attention rate functional relation on individual Commercial goods labelses, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior attention rate letter of Commercial goods labelses and user on some Commercial goods labels
Number relation, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation is touched to reach and analyzes, be interior
Hold analysis and customer analysis report, described touch includes up to analysis, content analysis and customer analysis report：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content analysis
Report；Customer analysis report is formed by being summarized by user.
8. a kind of mobile terminal, including processor, it is adapted to carry out each instruction；Including holder, suitable for storing a plurality of instruction, its
It is characterised by, the instruction is suitable to be loaded by the processor and perform following operation：
S1. commodity color page gathers：Commodity color page is gathered, and is imported into by FPDP in database；
S2. digitized processing：Processing is digitized to collecting the color page, digitized processing specifically includes：
S3-1. image is split:It is single commodity figure by the color page cutting by way of Boundary Recognition and human assistance
Piece；
S3-2. content recognition：By carrying out OCR identifications to the word on particular commodity picture, commodity word is retouched corresponding to acquisition
State information；
S3-3. factor analysis:The commodity character description information is analyzed, extracts the Back ground Information of commodity, the business
The Back ground Information of product comprises at least Brand, category, specification, price and promotion method；
S3-4. supplement check and correction：Artificial nucleus couple are carried out to the factor analysis result, the information of omission supplemented, to mistake
Information corrected；
S3-5. data storage:By particular commodity picture and the storage of corresponding Back ground Information into the database, and use
MySQL carries out structural data storage, and document datastore is carried out using ElasticSearch；
S4. color page is issued：The commodity data stored is issued, issue content includes commodity picture and corresponding commodity
Back ground Information.
9. a kind of mobile terminal as claimed in claim 8, it is characterised in that the collection of the commodity color page includes collection manually
Or directly captured automatically from network by network；
Participle analyzing and processing is carried out by Lucence or Lingpipe in the S3-3. factor analysis step.
10. a kind of mobile terminal as claimed in claim 1, it is characterised in that also including step：
S5 user behavior datas gather：Carry out data in App and H5 to bury a little, by burying a collection consumer consumption behavior data simultaneously
By streaming computing combined data, the streaming computing combined data includes：
User behavior quantifies：Classification is carried out to the behavioral data of collection to collect, and establishes user, and Commercial goods labelses and user are at certain
Behavior attention rate functional relation on individual Commercial goods labelses, its formula are：
Wherein：
i：Represent user；
j：Represent Commercial goods labelses；
p：Represent the type of operation, common n kinds operation；
T(i,j)：Represent the number of operations that user i occurs on Commercial goods labelses j；
T(i,j)p：Represent that the number of p operations occurs on Commercial goods labelses j for user i；
Wp：The weight of p operations is represented, the participation of user is bigger, and weight is bigger；
Sp：Scene indices when representing that p operations occur, the coefficient is bigger, represents that interference of the scene to user behavior is lower；
V(i,j)：The behavior attention rate quantized value for being user i on Commercial goods labelses j；
Establish user preferences matrix：According to user, the behavior attention rate letter of Commercial goods labelses and user on some Commercial goods labels
Number relation, establishes user preferences function：
Wherein：
K(i,j)old：Represent preference degrees of the user i to Commercial goods labelses j history；
V(i,j)：For behavior attention rate quantized values of this operation user i on Commercial goods labelses j；
Rj：It is relevant with the consumption frequency of commodity for the superposition coefficient of Commercial goods labelses；
K(i,j)new：Represent after this operation occurs, preference degrees of the user i to Commercial goods labelses j；
Multiple user preferences degree form user and like matrix；
S6 effect analyses：For the user behavior data collected, successively collected by different dimensions, generation is touched to reach and analyzes, be interior
Hold analysis and customer analysis report, described touch includes up to analysis, content analysis and customer analysis report：
Summarize to be formed to touch by by date+shop and reach analysis report；Summarize by by date+brand+category and to form content analysis
Report；Customer analysis report is formed by being summarized by user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710613295.3A CN107545460B (en) | 2017-07-25 | 2017-07-25 | Digital color page promotion management and analysis method, storage device and mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710613295.3A CN107545460B (en) | 2017-07-25 | 2017-07-25 | Digital color page promotion management and analysis method, storage device and mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107545460A true CN107545460A (en) | 2018-01-05 |
| CN107545460B CN107545460B (en) | 2020-12-18 |
Family
ID=60970747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710613295.3A Active CN107545460B (en) | 2017-07-25 | 2017-07-25 | Digital color page promotion management and analysis method, storage device and mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107545460B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921185A (en) * | 2018-05-04 | 2018-11-30 | 广州图匠数据科技有限公司 | A kind of shelf sales promotion information recognition methods based on image recognition, device and system |
| CN109146096A (en) * | 2018-09-07 | 2019-01-04 | 上海携程商务有限公司 | Report processing method, device, storage medium and the electronic equipment of event for repairment |
| CN109325163A (en) * | 2018-07-09 | 2019-02-12 | 深圳市吧圃创新科技有限公司 | It is a kind of from be designed into product issue high efficiency method |
| CN109360063A (en) * | 2018-10-17 | 2019-02-19 | 浙江忧点网络科技有限公司 | A kind of intelligence generates the prepackaged food recommender system of label |
| CN109492864A (en) * | 2018-09-29 | 2019-03-19 | 广东智合创享营销策划有限公司 | A kind of campaign management system and its management analysis method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103458300A (en) * | 2013-08-28 | 2013-12-18 | 天津三星电子有限公司 | Television false advertisement prompting method and system |
| CN104346609A (en) * | 2013-08-01 | 2015-02-11 | 阿里巴巴集团控股有限公司 | Method and device for recognizing characters on printed products |
| CN105373938A (en) * | 2014-08-27 | 2016-03-02 | 阿里巴巴集团控股有限公司 | Method for identifying commodity in video image and displaying information, device and system |
| CN106708821A (en) * | 2015-07-21 | 2017-05-24 | 广州市本真网络科技有限公司 | User personalized shopping behavior-based commodity recommendation method |
-
2017
- 2017-07-25 CN CN201710613295.3A patent/CN107545460B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346609A (en) * | 2013-08-01 | 2015-02-11 | 阿里巴巴集团控股有限公司 | Method and device for recognizing characters on printed products |
| CN103458300A (en) * | 2013-08-28 | 2013-12-18 | 天津三星电子有限公司 | Television false advertisement prompting method and system |
| CN105373938A (en) * | 2014-08-27 | 2016-03-02 | 阿里巴巴集团控股有限公司 | Method for identifying commodity in video image and displaying information, device and system |
| CN106708821A (en) * | 2015-07-21 | 2017-05-24 | 广州市本真网络科技有限公司 | User personalized shopping behavior-based commodity recommendation method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921185A (en) * | 2018-05-04 | 2018-11-30 | 广州图匠数据科技有限公司 | A kind of shelf sales promotion information recognition methods based on image recognition, device and system |
| CN109325163A (en) * | 2018-07-09 | 2019-02-12 | 深圳市吧圃创新科技有限公司 | It is a kind of from be designed into product issue high efficiency method |
| CN109146096A (en) * | 2018-09-07 | 2019-01-04 | 上海携程商务有限公司 | Report processing method, device, storage medium and the electronic equipment of event for repairment |
| CN109146096B (en) * | 2018-09-07 | 2020-11-17 | 上海携程商务有限公司 | Processing method and device for repair event, storage medium and electronic equipment |
| CN109492864A (en) * | 2018-09-29 | 2019-03-19 | 广东智合创享营销策划有限公司 | A kind of campaign management system and its management analysis method |
| CN109360063A (en) * | 2018-10-17 | 2019-02-19 | 浙江忧点网络科技有限公司 | A kind of intelligence generates the prepackaged food recommender system of label |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107545460B (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pournarakis et al. | A computational model for mining consumer perceptions in social media | |
| CN107545460A (en) | One kind digitlization color page promotion management and analysis method, storage device and mobile terminal | |
| CN112035653B (en) | Policy key information extraction method and device, storage medium and electronic equipment | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| Holt et al. | Extracting structured data from invoices | |
| CN106688215A (en) | Automated click type selection for content performance optimization | |
| CN111143505B (en) | Document processing method, device, medium and electronic equipment | |
| Tanudjaja et al. | Exploring bibliometric mapping in NUS using BibExcel and VOSviewer | |
| CN107992500A (en) | A kind of information processing method and server | |
| US8504425B2 (en) | Process of advertisements | |
| CN114372731B (en) | Post target making method, device, equipment and storage medium based on big data | |
| US10282467B2 (en) | Mining product aspects from opinion text | |
| JP6289989B2 (en) | User emotion analysis apparatus and program for product | |
| JP2020524833A (en) | Method and apparatus for displaying textual information | |
| Poonnawat et al. | Jobs analysis for business intelligence skills requirements in the ASEAN region: A text mining study | |
| CN110503306A (en) | A kind of Satisfaction index visible processing method and device | |
| CN107093103B (en) | Brand value evaluation method and system based on big data statistical analysis | |
| Pustulka et al. | Text mining innovation for business | |
| Markić et al. | Sentiment analysis of social networks as a challenge to the digital marketing | |
| KR102238438B1 (en) | System for providing commercial product transaction service using price standardization | |
| Huang et al. | Smartphone market analysis with respect to brand performance using hybrid multicriteria decision making methods | |
| CN106716403A (en) | Automated generation of web site entry pages | |
| Diaz et al. | Strategy mining for inferring business information system user intentions | |
| Jiang et al. | Promoting institutional repositories via visualizations: A change-point study | |
| CN111061960A (en) | Method for generating user image based on social big data |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Digital color page promotion management and analysis method, storage device and mobile terminal Effective date of registration: 20210708 Granted publication date: 20201218 Pledgee: Bank of China Limited by Share Ltd. Guangzhou Panyu branch Pledgor: GUANGZHOU SMARTGO TECHNOLOGY Co.,Ltd. Registration number: Y2021980005943 |
|
| CP03 | Change of name, title or address |
Address after: 510630 rooms 801, 802, 803, 804 and 805, No. 221, Gaotang Road, Tianhe District, Guangzhou City, Guangdong Province (office only) Patentee after: Zhixuan digital technology (Guangzhou) Co.,Ltd. Address before: Room 8009, building 22-24, 251 Kehua street, Wushan Road, Guangzhou, Guangdong 510000 Patentee before: GUANGZHOU SMARTGO TECHNOLOGY CO.,LTD. |
|
| CP03 | Change of name, title or address | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20220913 Granted publication date: 20201218 Pledgee: Bank of China Limited by Share Ltd. Guangzhou Panyu branch Pledgor: GUANGZHOU SMARTGO TECHNOLOGY CO.,LTD. Registration number: Y2021980005943 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method of digital color page promotion management and analysis, storage device and mobile terminal Effective date of registration: 20221020 Granted publication date: 20201218 Pledgee: Bank of China Limited by Share Ltd. Guangzhou Panyu branch Pledgor: Zhixuan digital technology (Guangzhou) Co.,Ltd. Registration number: Y2022980018944 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |