CN109685618A - Electric business platform activity dissemination method based on big data - Google Patents
Electric business platform activity dissemination method based on big data Download PDFInfo
- Publication number
- CN109685618A CN109685618A CN201811584426.0A CN201811584426A CN109685618A CN 109685618 A CN109685618 A CN 109685618A CN 201811584426 A CN201811584426 A CN 201811584426A CN 109685618 A CN109685618 A CN 109685618A
- Authority
- CN
- China
- Prior art keywords
- trade company
- preferential
- information
- activity
- business
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0222—During e-commerce, i.e. online transactions
-
- 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]
- G06Q30/0621—Item configuration or customization
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of electric business platform activity dissemination method based on big data is generated for showing preferential movable preferential active script to trade company the following steps are included: configure preferential active rule and commodity;Trade company receives preferential active script, it is determined whether participates in preferential activity, submits participation activity request if participating in;The present invention reduces traditional data publications to inquire bring workload, substantially reduce the response time of system, improve activity efficiency for issuing, shorten preferential movable time, so that the portability of system further increases, merchant information is switched to the hash binary coding of low-dimensional using learning network, not only it had maintained characteristics of image of the trade company on platform but also had reduced the resource consumption of the storage and inquiry of high-volume characteristics of image, when can do preferential activity with effective solution electric business platform the problem of high-volume match query, it is particularly suitable for using during double 11 activities.
Description
Technical field
The present invention relates to electric business platform technology field, specially a kind of electric business platform activity publisher based on big data
Method.
Background technique
In the prior art, electric business platform is needed in manual examination and verification link after issuing preferential action message to participation
Preferential movable commodity are controlled and are inquired, if data change when inquiring and count trade company, need to open again
Code is sent out, workload is considerably increased, causes development efficiency lower,
And the storage of high-volume characteristics of image of the trade company on platform and inquiry consume vast resources, do preferential activity
When high-volume match query it is less suitable.
Summary of the invention
The purpose of the invention is to overcome above-mentioned deficiency to provide a kind of electric business platform activity publisher based on big data
Method.
A kind of electric business platform activity dissemination method based on big data the following steps are included:
Preferential active rule and commodity are configured, are generated for showing preferential movable preferential active script to trade company;
Trade company receives preferential active script, it is determined whether participates in preferential activity, submits participation activity request if participating in;
After the activity request for receiving trade company's submission, trade company is audited, judges whether it meets auditing rule, such as
Fruit meets auditing rule, then sends verification file to the trade company, if not meeting auditing rule, sends not to the trade company
Meet item prompt.
The trade company is verified after receiving verification file, and platform obtains trade company's preferential activity data of participation and handled.
The platform obtains the preferential activity data progress processing method of trade company's participation
Preferential activity data is participated in the trade company of acquisition and carries out filtering sensitive words and duplicate removal processing, according to meeting auditing rule
The data information of trade company and trade company's business classification, the trade company for establishing commerce system operation participate in preferential inquiry library and trade company's business class
Other library;
The head portrait and business license figure information for obtaining trade company, if there is new trade company's participation is preferential, with figure letter
Breath is base map, is then superimposed new trade company and participates in preferential inquiry data, imports data synchronization updating with online mode and realizes figure
Real-time update show.
The preferential newest preferential activity policy of inquiry library typing is participated in trade company in real time, in real time to trade company's business classification typing
Trade company's range of business bulletin, association trade company participate in preferential inquiry library and trade company's business class library, and real-time query trade company participates in preferential
The situation of activity.
The real-time query trade company participates in the situation of preferential activity specifically: set trade company participate in preferential inquiry library asWherein V indicates to participate in preferential trade company's number, and i indicates to participate in preferential trade company's serial number, often
A preferential trade company of participation includes trade company's head portrait figure information Pi∈R128x128With trade company business license figure information Mi∈R32x32x4, Li
For the class label for participating in preferential trade company i;It participates in sampling trade company's head portrait figure information in preferential inquiry library from trade company, will each match
The depth hash convolutional network of figure information input trade company head portrait figure information extracts the feature of imageΨ(Pi,
ΛP)∈RlIndicate depth hash convolutional network obtained spy of trade company's head portrait figure information Jing Guo trade company's head portrait figure information
Sign, l are the length of final output hash coding, ΛPFor the depth hash convolutional network parameter of trade company's head portrait figure information, lead to
Cross the eigenmatrix F that iteration updates entire trade company's head portrait figure informationP∈Rl×V;It participates in sampling quotient in preferential inquiry library from trade company
Family business license figure information mentions the depth hash convolutional network of each figure information input trade company business license figure information
Take the feature of imageΥ(Mi,ΛM)∈RlIndicate that trade company's business license figure information passes through trade company's head portrait
The obtained feature of depth hash convolutional network of figure information, l are the length of final output hash coding, ΛMFor battalion, trade company
The depth hash convolutional network parameter of industry license figure information, the spy of entire trade company's business license figure information is updated by iteration
Levy matrix FM∈Rl×V;Update network parameter ΛPWith ΛMAnd corresponding hash code B=sign (C)=sign (β (FP+FM)),
Middle sign () sign function, otherwise it is -1 that output positive number, which is+1,;If inquiring trade company by trade company's head portrait figure information to participate in
The situation of preferential activity goes out entire trade company's business license figure by trade company's business license figure information depth hash network query function
The hash code B of information database*,i=sign (Υ (Mi,ΛM)), the trade company head portrait figure information new for one calculates hash
CodingHash code in the database is inquired;If passing through trade company's business license figure information
Inquiry trade company participates in the situation of preferential activity, goes out entire trade company's head portrait by trade company's head portrait figure information depth hash network query function
The hash code B of figure information database*,i=sign (Ψ (Pi,ΛP)), the trade company business license figure information new for one,
Calculate hash codingHash code in the database is inquired.
Construction trade company in preferential inquiry library, which is participated in, in the trade company participates in preferential activity attributes table;In trade company business class
Trade company's business class library Merchant Category dictionary table, trade company's Multimedia Metadata table and trade company's three-dimensional data metadata are constructed in other library
Table.
The present invention reduces traditional data publications to inquire bring workload, substantially reduces the response time of system,
Activity efficiency for issuing is improved, preferential movable time is shortened, so that the portability of system further increases, is utilized
Merchant information is switched to the hash binary coding of low-dimensional by learning network, has not only maintained characteristics of image but also drop of the trade company on platform
The resource consumption of the storage and inquiry of low high-volume characteristics of image can be done big when preferential activity with effective solution electric business platform
The problem of batch query matches is particularly suitable for using during double 11 activities.
Specific embodiment
Below with reference to a specific embodiment of the invention to the present invention is based on the electric business platform activity dissemination methods of big data
It makes the following instructions.
Embodiment: a kind of electric business platform activity dissemination method based on big data the following steps are included:
Preferential active rule and commodity are configured, are generated for showing preferential movable preferential active script to trade company;
Trade company receives preferential active script, it is determined whether participates in preferential activity, submits participation activity request if participating in;
After the activity request for receiving trade company's submission, trade company is audited, judges whether it meets auditing rule, such as
Fruit meets auditing rule, then sends verification file to the trade company, if not meeting auditing rule, sends not to the trade company
Meet item prompt.
The trade company is verified after receiving verification file, and platform obtains trade company's preferential activity data of participation and handled.
The platform obtains the preferential activity data progress processing method of trade company's participation
Preferential activity data is participated in the trade company of acquisition and carries out filtering sensitive words and duplicate removal processing, according to meeting auditing rule
The data information of trade company and trade company's business classification, the trade company for establishing commerce system operation participate in preferential inquiry library and trade company's business class
Other library;
The head portrait and business license figure information for obtaining trade company, if there is new trade company's participation is preferential, with figure letter
Breath is base map, is then superimposed new trade company and participates in preferential inquiry data, imports data synchronization updating with online mode and realizes figure
Real-time update show.
The preferential newest preferential activity policy of inquiry library typing is participated in trade company in real time, in real time to trade company's business classification typing
Trade company's range of business bulletin, association trade company participate in preferential inquiry library and trade company's business class library, and real-time query trade company participates in preferential
The situation of activity.
The real-time query trade company participates in the situation of preferential activity specifically: set trade company participate in preferential inquiry library asWherein V indicates to participate in preferential trade company's number, and i indicates to participate in preferential trade company's serial number, often
A preferential trade company of participation includes trade company's head portrait figure information Pi∈R128x128With trade company business license figure information Mi∈R32x32x4, Li
For the class label for participating in preferential trade company i;Wherein it is possible to construct similarity matrix SPM∈RV×V×2If PiWith MjBelong to same
Trade company, thenIf PiWith MjIt is not belonging to same trade company, thenConstruct trade company's head portrait figure information similarity matrix SP∈RV×V×2If PiWith PjBelong to same trade company, thenIf PiWith PjIt is not belonging to same trade company, thenConstruct trade company's business license figure information
Similarity matrix SM∈RV×V×2If MiWith MjBelong to same trade company, thenIf MiWith MjIt is not belonging to same
One trade company, thenIt participates in sampling trade company's head portrait figure information in preferential inquiry library from trade company, each figure is believed
The depth hash convolutional network of breath input trade company's head portrait figure information extracts the feature of imageΨ(Pi,ΛP)
∈RlIndicate depth hash convolutional network obtained feature of trade company's head portrait figure information Jing Guo trade company's head portrait figure information, l
For the length of final output hash coding, ΛPFor the depth hash convolutional network parameter of trade company's head portrait figure information, pass through iteration
Update the eigenmatrix F of entire trade company's head portrait figure informationP∈Rl×V;Sampling trade company business in preferential inquiry library is participated in from trade company
The depth hash convolutional network of each figure information input trade company business license figure information is extracted image by license figure information
FeatureΥ(Mi,ΛM)∈RlIndicate that trade company's business license figure information is believed by trade company's head portrait figure
The obtained feature of depth hash convolutional network of breath, l are the length of final output hash coding, ΛMFor trade company's business license
The depth hash convolutional network parameter of figure information, the eigenmatrix of entire trade company's business license figure information is updated by iteration
FM∈Rl×V;Update network parameter ΛPWith ΛMAnd corresponding hash code B=sign (C)=sign (β (FP+FM)), wherein sign
() sign function, otherwise it is -1 that output positive number, which is+1,;If inquiring trade company by trade company's head portrait figure information participates in preferential work
Dynamic situation goes out entire trade company's business license figure Information Number by trade company's business license figure information depth hash network query function
According to the hash code B in library*,i=sign (Υ (Mi,ΛM)), the trade company head portrait figure information new for one calculates hash codingHash code in the database is inquired;If inquired by trade company's business license figure information
Trade company participates in the situation of preferential activity, goes out entire trade company's head portrait figure by trade company's head portrait figure information depth hash network query function
The hash code B of information database*,i=sign (Ψ (Pi,ΛP)), the trade company business license figure information new for one calculates
Hash codingHash code in the database is inquired.
Construction trade company in preferential inquiry library, which is participated in, in the trade company participates in preferential activity attributes table;In trade company business class
Trade company's business class library Merchant Category dictionary table, trade company's Multimedia Metadata table and trade company's three-dimensional data metadata are constructed in other library
Table.
Claims (5)
1. a kind of electric business platform activity dissemination method based on big data, it is characterised in that: method includes the following steps:
Preferential active rule and commodity are configured, are generated for showing preferential movable preferential active script to trade company;
Trade company receives preferential active script, it is determined whether participates in preferential activity, submits participation activity request if participating in;
After the activity request for receiving trade company's submission, trade company is audited, judges whether it meets auditing rule, if symbol
Auditing rule is closed, then sends verification file to the trade company, if not meeting auditing rule, sends and does not meet to the trade company
Item prompt.
2. the electric business platform activity dissemination method according to claim 1 based on big data, which is characterized in that the trade company
It is verified after receiving verification file, platform obtains trade company's preferential activity data of participation and handled.
3. the electric business platform activity dissemination method according to claim 2 based on big data, which is characterized in that the platform
Obtaining the preferential activity data progress processing method of trade company's participation includes:
Preferential activity data is participated in the trade company of acquisition and carries out filtering sensitive words and duplicate removal processing, according to meeting auditing rule trade company
The data information for classification of doing business with trade company, the trade company for establishing commerce system operation participate in preferential inquiry library and trade company's business classification
Library;
The head portrait and business license figure information for obtaining trade company be with the figure information if there is new trade company participates in preferential
Base map, is then superimposed new trade company and participates in preferential inquiry data, imports the reality that data synchronization updating realizes figure with online mode
Shi Gengxin is shown.
The preferential newest preferential activity policy of inquiry library typing is participated in trade company in real time, in real time to business classification typing trade company, trade company
Range of business bulletin, association trade company participate in preferential inquiry library and trade company's business class library, and real-time query trade company participates in preferential activity
The case where.
4. the electric business platform activity dissemination method according to claim 3 based on big data, which is characterized in that the real-time query
Trade company participates in the situation of preferential activity specifically: set trade company participate in preferential inquiry library as
Wherein V indicates to participate in preferential trade company's number, and i indicates to participate in preferential trade company's serial number, and each preferential trade company of participation includes trade company's head portrait
Figure information Pi∈R128x128With trade company business license figure information Mi∈R32x32x4, LiFor the class label for participating in preferential trade company i;
It participates in sampling trade company's head portrait figure information in preferential inquiry library from trade company, by each figure information input trade company head portrait figure information
Depth hash convolutional network extract image featureΨ(Pi,ΛP)∈RlIndicate trade company's head portrait figure letter
The obtained feature of depth hash convolutional network Jing Guo trade company's head portrait figure information is ceased, l is the length of final output hash coding
Degree, ΛPFor the depth hash convolutional network parameter of trade company's head portrait figure information, entire trade company's head portrait figure is updated by iteration and is believed
The eigenmatrix F of breathP∈Rl×V;It participates in sampling trade company's business license figure information in preferential inquiry library from trade company, by each figure
The depth hash convolutional network of information input trade company business license figure information extracts the feature of imageΥ
(Mi,ΛM)∈RlIt indicates obtained by depth hash convolutional network of trade company's business license figure information Jing Guo trade company's head portrait figure information
The feature arrived, l are the length of final output hash coding, ΛMFor the depth hash convolution net of trade company's business license figure information
Network parameter updates the eigenmatrix F of entire trade company's business license figure information by iterationM∈Rl×V;Update network parameter ΛP
With ΛMAnd corresponding hash code B=sign (C)=sign (β (FP+FM)), wherein sign () sign function, output positive number is+
1, it is otherwise -1;If inquiring the situation that trade company participates in preferential activity by trade company's head portrait figure information, held by trade company's business
Go out the hash code B of entire trade company's business license figure information database according to figure information depth hash network query function*,i=sign
(Υ(Mi,ΛM)), the trade company head portrait figure information new for one calculates hash codingIn data
Hash code in library is inquired;If inquiring the situation that trade company participates in preferential activity by trade company's business license figure information,
Go out the hash code B of entire trade company's head portrait figure information database by trade company's head portrait figure information depth hash network query function*,i=sign
(Ψ(Pi,ΛP)), the trade company business license figure information new for one calculates hash coding?
Hash code in database is inquired.
5. the electric business platform activity dissemination method according to claim 4 based on big data, which is characterized in that in the quotient
Family participates in construction trade company in preferential inquiry library and participates in preferential activity attributes table;The battalion, construction trade company in trade company business class library
Industry class library Merchant Category dictionary table, trade company's Multimedia Metadata table and trade company's three-dimensional data metadata table.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811584426.0A CN109685618A (en) | 2018-12-24 | 2018-12-24 | Electric business platform activity dissemination method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811584426.0A CN109685618A (en) | 2018-12-24 | 2018-12-24 | Electric business platform activity dissemination method based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109685618A true CN109685618A (en) | 2019-04-26 |
Family
ID=66188164
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811584426.0A Pending CN109685618A (en) | 2018-12-24 | 2018-12-24 | Electric business platform activity dissemination method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109685618A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111091439A (en) * | 2019-11-08 | 2020-05-01 | 泰康保险集团股份有限公司 | Order association marketing campaign implementation method, system, equipment and storage medium |
-
2018
- 2018-12-24 CN CN201811584426.0A patent/CN109685618A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111091439A (en) * | 2019-11-08 | 2020-05-01 | 泰康保险集团股份有限公司 | Order association marketing campaign implementation method, system, equipment and storage medium |
CN111091439B (en) * | 2019-11-08 | 2023-08-08 | 泰康保险集团股份有限公司 | Order-related marketing campaign realization method, system, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020140386A1 (en) | Textcnn-based knowledge extraction method and apparatus, and computer device and storage medium | |
CN106959965B (en) | Information processing method and server | |
CN106528693B (en) | Educational resource recommended method and system towards individualized learning | |
JP2019504428A (en) | Web interface generation and test system based on machine learning | |
CN107123047B (en) | Data acquisition system based on bond transaction and data acquisition method thereof | |
WO2022048363A1 (en) | Website classification method and apparatus, computer device, and storage medium | |
CN110196848B (en) | Cleaning and duplicate removal method and system for public resource transaction data | |
CN112529429B (en) | Client information verification method, device, computer equipment and storage medium | |
CN103279515A (en) | Recommendation method based on microblog groups and microblog group recommendation device | |
CN111639253A (en) | Data duplication judging method, device, equipment and storage medium | |
CN114491047A (en) | Multi-label text classification method and device, electronic equipment and storage medium | |
CN113282623A (en) | Data processing method and device | |
CN113268665A (en) | Information recommendation method, device and equipment based on random forest and storage medium | |
CN106874368B (en) | RTB bidding advertisement position value analysis method and system | |
CN107908735A (en) | Information displaying method and device and computing device | |
CN109685618A (en) | Electric business platform activity dissemination method based on big data | |
CN111737315B (en) | Address fuzzy matching method and device | |
CN109711878A (en) | Electric business platform activity delivery system based on big data | |
CN112214602A (en) | Text classification method and device based on humor, electronic equipment and storage medium | |
CN107291808A (en) | It is a kind of that big data sorting technique is manufactured based on semantic cloud | |
CN106780199A (en) | A kind of intellectual property evaluation system | |
CN116340516A (en) | Entity relation cluster extraction method, device, equipment and storage medium | |
CN110472056A (en) | A kind of comment data classification method and system | |
Umamaheshwari et al. | Customer Relationship Management using Sentimental Analysis | |
CN115545976A (en) | Cross-border trademark registration method, system, device and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190426 |