CN115809926A - Innovative alliance distribution cooperation transaction platform for converging alliance resources of multiple distribution channels - Google Patents
Innovative alliance distribution cooperation transaction platform for converging alliance resources of multiple distribution channels Download PDFInfo
- Publication number
- CN115809926A CN115809926A CN202310017909.7A CN202310017909A CN115809926A CN 115809926 A CN115809926 A CN 115809926A CN 202310017909 A CN202310017909 A CN 202310017909A CN 115809926 A CN115809926 A CN 115809926A
- Authority
- CN
- China
- Prior art keywords
- alliance
- distribution
- data
- platform
- brand
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an innovative alliance distribution cooperation transaction platform for gathering various distribution channel alliance resources, which takes the distribution resources of dozens of channels such as an offline station, various large-social media platforms, a Deals station and the like as basic data, and sorts out each distribution resource and a corresponding data index thereof through data cleaning processing and intelligent identification technology, so that a user can search corresponding data of distribution alliances according to own industry and brand, inquire out the most matched alliance guest and a corresponding detailed data index thereof according to intelligent recommending and screening functions provided by the platform, quickly find out the needed alliance resources, check and manage data of a plurality of distribution alliance platforms in a one-stop mode, and promote merchants to efficiently complete cooperation with distribution channels through a transaction system module.
Description
Technical Field
The invention relates to the technical field of e-commerce platforms, in particular to an innovative alliance distribution cooperation transaction platform for gathering alliance resources of various distribution channels.
Background
At present, brand merchants mainly rely on bringing goods by using online red resources, and can only evaluate the goods carrying capacity of online red through data indexes of media channels, such as: the number of vermicelli, the total video frequency, the average playing amount, the interaction rate and the like are limited, and a delivery channel suitable for brand promotion cannot be quickly found.
Therefore, whether an innovative alliance distribution cooperation transaction platform for gathering various distribution channel alliance resources can be built or not is convenient for brand merchants to find a distribution channel suitable for the brand merchants, and the problem that people need to solve urgently is formed.
Disclosure of Invention
In view of this, the invention provides an innovative alliance distribution cooperation transaction platform for converging various distribution channel alliance resources, so that brand merchants can find a distribution channel suitable for the brand merchants conveniently.
The technical scheme provided by the invention is specifically an innovative alliance distribution cooperation transaction platform for converging alliance resources of various distribution channels, and the platform comprises: the system comprises a database, an information insights module, a building module, a multi-platform management module and a transaction system module;
the database is accessed to distribution data resources of a plurality of channels as basic data, and the basic data is cleaned, intelligently identified and stored;
the intelligence insights module searches in data stored in the database according to the industry and brand lists, displays distribution data indexes of specified industries and brands, collects information of each alliance guest in the database, finds similarity among users according to user clicking, checking and preference information of cooperation alliance guests by using a recommendation algorithm, and recommends similar alliance guests to the users according to historical preference information of the users;
the building module is associated with the information insights module and is used for the receiving and sending operation of information such as mails and station letters of a user and the management of communication records;
after the multi-platform management module is authorized, importing a plurality of alliance platform data of a user, and after data processing, displaying distribution data in the plurality of alliance platforms of the user through one-stop management of the multi-platform management module;
the transaction system module is used for attracting brand merchants and distribution channel to stay in, bidirectional invitation management, cooperation management, order management and commission settlement.
Preferably, the database is used for cleaning the basic data, intelligently identifying and storing the basic data, and specifically comprises the following steps:
inputting a brand name to search in the basic data to obtain a return link;
performing keyword matching on all returned links, judging that the links belong to the alliance resources after successful matching, and otherwise, judging that the links do not belong to the alliance resources;
if the matching is successful, the successfully matched link is continued to analyze the corresponding data index;
meanwhile, the input links are trained by using algorithm models such as a back propagation neural network, the dependent variables related to the brands are predicted according to the input independent variables, simulation training is carried out on the links by combining a brand knowledge graph, and finally, brand names are output from massive links to provide keywords for next data retrieval.
Further preferably, the step of continuously analyzing the successfully matched link to the corresponding data index specifically includes:
cleaning and identifying the data in the link through an intelligent algorithm to form a subdivision database base; (e.g., brand data, business data, product data, market data, channel data, user data, etc.)
Extracting features of data in a fine database base from four dimensions of basic features, statistical features, complex features and natural features, wherein the basic features comprise industries, categories and the like, the statistical features comprise SKU number, average unit price, price floating rate and the like, the complex features comprise distributed product structures, user images and the like, and the natural features comprise policies, economy and the like;
and retrieving and matching the data in the subdivision database base based on the knowledge graph, checking the accuracy of the data and outputting an optimal result.
Further preferably, the information of each alliance guest in the database is collected, the similarity among the users is found by using a recommendation algorithm according to the clicking, checking and preference information of the cooperation alliance guests of the users, and the similar alliance guests are recommended to the users according to the historical preference information of the users, wherein the recommendation algorithm specifically comprises the following steps:
acquiring interactive data of the user by collecting historical behaviors of the user, learning and calculating preference interest of the user according to the extracted features, calculating similarity between the user and the content to be recommended on the basis, and finally sequencing and sorting the similarity so as to recommend the alliance distribution resources which are most matched with the user;
setting a scoring rule aiming at the sequencing of the distributed resources of different types, scoring according to indexes of different dimensions of the distributed resources, and calculating an average score standard deviation to optimize the accuracy of the scoring rule so as to sequence the distributed resources according to a final score;
the method comprises the steps of processing and extracting characteristics of mass data by using a multilayer perceptron, a convolutional neural network, a cyclic neural network, a recursion neural network and the like, and forming denser high-level semantic abstraction by combining low-level characteristics, so that multi-dimensional characteristic representation of the data is automatically found, and the recommendation effect is continuously enhanced.
Further preferably, the data index includes: industry, brand, commission ratio, EPC, cookies, league guest detail information;
the alliance guest detail information comprises: name, country/region, avatar, category, league guest type, co-operating brand, league platform, freighter, and personal home page information.
Further preferably, the information insights module includes: name, country/region, avatar, category, league guest type, co-branding, league platform, pickup commodity, and personal home page information.
Further preferably, after the multi-platform management module is authorized, the multi-platform management module imports data of a plurality of alliance platforms of the user, and after the data processing, displays the distribution data of the plurality of alliance platforms of the user through one-stop management of the multi-platform management module, specifically:
a user inputs 'merchant member ID' and 'API key' into an authorization center of a multi-platform management module to obtain authorization, data of a alliance platform is led into a background database through an API interface, the data are processed according to a comprehensive billboard, an alliance guest detail page, an order detail page and a repeated order detail page, and distribution data are checked through one-stop management.
Further preferably, the multi-platform management module further has a function of identifying cheating orders, and specifically comprises:
unifying time zones and data dimensions of the alliance platforms needing to be compared;
downloading data tables in a plurality of alliance platforms, wherein the data tables at least cover the following indexes: order number, date, alliance guest ID, promotion website, alliance name and distribution amount, wherein the order number, the date, the alliance guest ID, the promotion website, the alliance name and the distribution amount are judged to be cheating orders when the order number, the date, the alliance guest ID, the promotion website, the alliance name and the distribution amount include but are not limited to the following conditions;
1) If different alliance platforms have the same order number on the same day and the distribution amount is the same, determining that the order is a cheating order;
2) Code is covertly planted into a computer by unintentionally clicking a popup window, an advertisement program or downloaded virus/spyware, thereby cheating commission settlement;
3) Order tracking of alliance marketing is achieved through Cookie local to a user computer, and abnormal tracking and settlement can be caused due to illegal Cookie implantation;
4) By setting a domain name very similar to a brand website, after clicking is cheated, the domain name is automatically redirected to jump to a real brand website, and the cheated clicking can be tracked by Cookie and verified to be a conversion point.
Further preferably, the transaction system module comprises a brand end and a channel end, and is used for attracting the participation of brand merchants and distribution channels, inviting, cooperative management and commission settlement of both parties, and specifically comprises:
the brand merchant registration login platform is used for achieving distribution cooperation with a channel by going to a Marketplace to search for the channel or applying for an approval channel in an approval center after merchant information, project information and payment information are set;
the distribution channel registers and logs on the platform, after setting personal information and payment information, go to markplace to find brand merchants to reach cooperation, and obtain popularization resources to carry out distribution after approval is passed;
the transaction system module verifies the application qualification of the brand merchant and the distribution channel, and can successfully reside if the application qualification meets the standard so as to ensure the quality of the resident brand merchant and the distribution channel;
the brand merchant and the distribution channel issue an invitation task in the trading system module, provide indexes such as product information and corresponding commission, the distribution channel can also issue the brand invitation task, provide requirements for popularizing products and information such as intention cooperation industry and brands, both parties can select a proper invitation task to cooperate, and meanwhile, the trading system recommends a task with high matching degree aiming at both parties according to data such as historical preference use habits and historical cooperation records of both parties based on a recommendation algorithm, so as to promote efficient cooperation of both parties;
the trading system module analyzes the goods carrying effect of the distribution channel and feeds back the goods carrying effect to the brand merchant and the distribution channel, and the two parties carry out commission settlement according to the promotion effect and the rule of task release.
Further preferably, the trading system provides a unique tracking code after the brand merchant and the distribution channel are determined to cooperate, the tracking code is added to the information of the promoted product in the distribution channel, a consumer clicks or purchases a product promoted in a certain distribution channel, the platform performs tracking analysis on the effect of the promoted product and the distribution channel, after an order is completed, the trading system automatically calculates the commission amount, and after the settlement validity period expires, the regular settlement commission is given to the distribution channel.
The invention discloses an innovative alliance distribution cooperation transaction platform for gathering various distribution channel alliance resources, which takes the distribution resources of dozens of channels such as an offline station, various large-social media platforms, a Deals station and the like as basic data, and sorts out each distribution resource and a corresponding data index thereof through data cleaning processing and intelligent identification technology, so that a user can search corresponding data of distribution alliances according to own industry and brand, inquire out the most matched alliance guest and a corresponding detailed data index thereof according to intelligent recommending and screening functions provided by the platform, quickly find out the needed alliance resources, check and manage data of a plurality of distribution alliance platforms in a one-stop mode, and promote merchants to efficiently complete cooperation with distribution channels through a transaction system module.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of component modules of an innovative federation distribution cooperation transaction platform for aggregating federation resources in multiple distribution channels according to an embodiment of the present disclosure.
Fig. 2 is a flowchart of an innovative federation distribution cooperative trading platform for aggregating federation resources in multiple distribution channels according to an embodiment of the disclosure.
Fig. 3 is a flow chart of a brand-side data dashboard of a new alliance distribution cooperation trading platform for aggregating alliance resources in various distribution channels according to an embodiment of the present disclosure.
Fig. 4 is a distribution management flow diagram of brand-side of a trading system module of an innovative alliance distribution cooperative trading platform for aggregating alliance resources of various distribution channels according to an embodiment of the disclosure.
Fig. 5 is a flow chart of a markedplace end transaction system module brand end transaction platform of an innovative alliance distribution cooperation transaction platform for aggregating alliance resources in various distribution channels according to an embodiment of the disclosure.
Fig. 6 is a flow chart of a transaction system module channel-side personal dashboard of the innovative federation distribution cooperation transaction platform for aggregating various distribution channel federation resources according to an embodiment of the present disclosure.
Fig. 7 is a flowchart of the transaction system module channel commission details of the innovative federation distribution cooperation transaction platform aggregating various distribution channel federation resources according to an embodiment of the present disclosure.
Fig. 8 is a transaction system module channel end cooperation management flow diagram of an innovative alliance distribution cooperation transaction platform for aggregating various distribution channel alliance resources according to an embodiment of the disclosure of the present invention.
Fig. 9 is a flowchart of a transaction system module channel-side promotional resource of an innovative alliance distribution cooperation transaction platform for aggregating various distribution channel alliance resources according to an embodiment of the disclosure of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of methods consistent with certain aspects of the invention, as detailed in the appended claims.
Referring to fig. 1, the present embodiment provides an innovative federation distribution cooperation trading platform for aggregating federation resources in multiple distribution channels, the platform comprising: the system comprises a database 1, an information insight module 2, a connection building module 3, a multi-platform management module 4 and a transaction system module 5 which are five modules in total.
Referring to fig. 1, a database 1 accesses dozens of channel distribution data resources such as offline stations, large social media platforms, deals stations and the like as basic data, and stores the basic data after cleaning and intelligent identification; through the data cleaning processing back, the alliance platform can classify and gather the distribution resource of all alliances according to trade & brand's classification, can demonstrate a plurality of different alliance distribution resources with same dimension, conveniently seeks.
Referring to fig. 1 and 2, the intelligence insight module 2 searches data stored in the database 1 according to industry and brand lists, displays distribution data indexes of specified industry and brands, collects information of each alliance guest in the database 1, finds similarity among users by using a recommendation algorithm according to user clicking, checking and preference information of the alliance guests, and recommends the similar alliance guests to the users according to historical preference information of the users;
the intelligence insight module 2 comprises two major parts: one is industry insights and the other is brand information. The industry insights show the alliance customer indexes according to the industry (the benchmarking brand is in the industry insights part and shows the first 6 brand data of the industry), and the brand information shows the alliance customer indexes according to the specified brand. By checking the benchmark brand corresponding to each industry displayed in the intelligence report insights module, the popularization strategy and direction of the industry benchmark brand are known and used as a reference standard for users to select alliance resources for cooperation.
The information of the federation client includes: name, country/region, avatar, category (industry of the league guest), league guest type, co-operative brand, league platform, freighter, and personal home page information.
Clicking the alliance customer portrait, and entering a personal homepage, wherein the specific indexes are as follows:
basic data indexes are as follows: name, avatar, category, league guest type, co-operative brand, league platform, commodity in stock.
Other data indexes are as follows:
for example, the alliance guest belongs to the YouTube/Deals/Pinterest type,
the YouTube column of the personal homepage displays: account name, registration time, introduction, subscription number, total watching number, total video frequency, video frequency of taking goods in the last 1 year, average watching frequency of the video with goods and average comment number of the video with goods (all are YouTube platform data);
the personal home page Deals column will show: account name, brief introduction, monthly visit amount, jump rate, average number of visited pages;
the personal home page Pinterest column displays: account name, number of fans, introduction, monthly visit amount, number of loaded contents in last 1 year, average viewing times of the loaded contents, and average number of comments on the loaded contents.
Referring to fig. 1 and fig. 2, the connection establishing module 3 is associated with the intelligence insight module 2, and the connection establishing module 3 is used for managing the receiving and sending operations of the information of the user, such as mails and letters in the station, and the communication records; specifically, the information insights module collects mailbox information of the alliance guests, the user clicks a mail sending button through the information insights module, the user jumps to the connection establishing module after clicking, and all the mails are managed through the connection establishing module.
Referring to fig. 1 and 2, after the multi-platform management module 4 is authorized, importing data of a plurality of alliance platforms of a user, performing data processing, and displaying distribution data in the plurality of alliance platforms of the user through one-stop management of the multi-platform management module;
referring to fig. 1 and 2, the transaction system module 5 is composed of a brand end and a channel end and is used for attracting brand merchants and distribution channel residency, invitation of both parties, cooperative management and commission settlement.
The database 1 is used for cleaning basic data, intelligently identifying the basic data and then storing the basic data, and specifically comprises the following steps:
inputting a brand name to search in the database 1 to obtain a return link, wherein basic data is FOSHO ecological data;
performing keyword matching on all returned links, judging that the link belongs to the alliance resource after successful matching, and otherwise judging that the link does not belong to the alliance resource;
if the matching is successful, the successfully matched link is continued to analyze the corresponding data index;
meanwhile, the input links are trained by using algorithm models such as a back propagation neural network and the like, the dependent variables related to the brands are predicted according to the input independent variables, the links are simulated and trained by combining a brand knowledge graph, and finally, brand names are output from massive links to provide keywords for next data retrieval.
Continuously analyzing the successfully matched link to obtain corresponding data index
Cleaning and identifying the data through an intelligent algorithm to form a detailed database base (such as brand data, business data, product data, market data, channel data, user data and the like);
extracting features of data from four dimensions of basic features, statistical features, complex features and natural features, wherein the basic features comprise industries, categories and the like, the statistical features comprise SKU quantity, average unit price, price floating rate and the like, the complex features comprise a distributed product structure, a user image and the like, and the natural features comprise policies, economy and the like;
and retrieving and matching the data based on the knowledge graph, checking the accuracy of the data and outputting an optimal result.
Collecting information of each alliance guest in the database, finding out similarity among users by using a recommendation algorithm according to user clicking, checking and preference information of cooperative alliance guests, recommending the similar alliance guests to the users according to historical preference information of the users, and specifically comprising the following steps:
acquiring interactive data of the user by collecting historical behaviors of the user, learning and calculating preference interest of the user according to the extracted features, calculating similarity between the user and the content to be recommended on the basis, and finally sequencing and sorting the similarity so as to recommend the alliance distribution resources which are most matched with the user;
processing and extracting characteristics of mass data by using a multilayer perceptron, a convolutional neural network, a cyclic neural network, a recurrent neural network and the like, and forming denser high-level semantic abstraction by combining low-level characteristics, so that multi-dimensional characteristic representation of the data is automatically found, and the recommendation effect is continuously enhanced;
meanwhile, the received data link is trained by using algorithm models such as a back propagation neural network and the like, the dependent variable related to the brand is predicted according to the input independent variable, the link is simulated and trained by combining a brand knowledge graph, and finally, the brand name is output from the mass data link to provide keywords for next data retrieval.
Referring to fig. 2, after the multi-platform management module 4 is authorized, the data of a plurality of alliance platforms of the user is imported, and after the data is processed, the distribution data in the plurality of alliance platforms of the user is managed and displayed in one-stop mode through the multi-platform management module, specifically:
a user inputs 'merchant member ID' and 'API key' to obtain authorization in an authorization center of the multi-platform management module 4, data of a alliance platform are led into a background database through an API interface, the data are processed according to a comprehensive billboard, an alliance guest detail page, an order detail page and a repeated order detail page, distribution data can be checked through one-stop management, data in any cooperation distribution platform can be checked on the platform, and the problem that the multi-platform of the user is switched back and forth is solved.
The multi-platform management module 4 further has a function of identifying cheating orders, and specifically comprises the following steps:
unifying time zones and date dimensions of the alliance platforms needing to be compared;
downloading data tables in a plurality of alliance platforms, wherein the data tables at least cover the following indexes: order number, date, alliance guest ID, promotion website, alliance name and distribution amount, wherein the order number, date, alliance guest ID, promotion website, alliance name and distribution amount are judged to be a cheating order when the conditions include but are not limited to the following conditions;
1) If different alliance platforms have the same order number on the same day and the distribution amount is the same, determining that the order is a cheating order;
2) Code can be embedded into a computer in a concealed way when a pop-up window, an advertisement program or downloaded virus/spyware is clicked accidentally, so that commission settlement is cheated;
3) Order tracking of alliance marketing is achieved through Cookie local to a user computer, and abnormal tracking and settlement can be caused due to illegal Cookie implantation;
4) By setting a domain name very similar to a brand website, after clicking cheating, the domain name is automatically redirected to jump to a real brand website, and the clicking cheated by the domain name can be tracked by Cookie and counted to be a conversion click.
The platform cheating order recognition function can help a user to better operate the alliance project, avoid abnormal commission loss, guarantee the benefits of high-quality alliance partners and construct a healthy alliance cooperation ecology.
Referring to fig. 2, the transaction system module 5 is used for attracting the brand merchants and distribution channel to stay, inviting both parties, managing cooperation and settling commission, and specifically comprises:
the transaction system module 5 examines the application qualification of the brand merchants and the distribution channels, and can successfully reside when meeting the standard so as to ensure the quality of the brands and the distribution channels;
the brand merchant and the distribution channel publish distribution channel invitation tasks in the trading system module 5, indexes such as product information and corresponding commission are provided, the distribution channel can also publish brand invitation tasks, requirements for promoting products and information such as intention cooperation industry and brands are provided, both parties can select proper invitation tasks to cooperate, meanwhile, the trading system recommends tasks with high matching degree aiming at both parties according to data such as historical preference use habits and historical cooperation records of both parties based on a recommendation algorithm, and efficient cooperation of both parties is facilitated;
the trading system module 5 analyzes the goods carrying effect of the distribution channel and feeds back the goods carrying effect to the brand merchant and the distribution channel, and the two parties carry out commission settlement according to the goods receiving effect and the rule of task issuing.
In addition, the brand merchants can find a distribution channel for carrying goods for their products (or find the brand merchants in the distribution channel) through the transaction system, and a specific proportion or a commission with a fixed amount is issued to the distribution channel according to the goods carrying performance. The flexible commission payment settlement platform replaces a platform merchant to finish commission sending work, so that the labor cost required by commission returning and issuing is saved, the financial loss caused by errors such as missed commission, mistaken commission and the like can be avoided, and the comprehensive operation cost is saved.
The trading system provides a unique tracking code after the cooperation of a brand merchant and a distribution channel is determined, the tracking code is added to the information of the promoted product in the distribution channel, a consumer clicks or purchases a product promoted in a certain distribution channel, the platform tracks and analyzes the effect of the promoted product and the distribution channel, after an order is completed, the trading system automatically calculates the commission amount, and after the expiration of the settlement validity period, the regular settlement commission is given to the distribution channel.
The use or management process of each end in the trading platform can be seen in fig. 3-9.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It is to be understood that the present invention is not limited to what has been described above, and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. An innovative federation distribution cooperative trading platform that aggregates federation resources across multiple distribution channels, the platform comprising: the system comprises a database (1), an information insights module (2), a building module (3), a multi-platform management module (4) and a transaction system module (5);
the database (1) is accessed to distribution data resources of a plurality of channels as basic data, and the basic data is cleaned, intelligently identified and stored;
the intelligence insights module (2) searches in data stored in the database (1) according to an industry and brand list, displays distribution data indexes of specified industries and brands, collects alliance guest information of each alliance guest in the database, finds similarity among the users according to user clicking, checking and preference information of the cooperation alliance guests by using a recommendation algorithm, and recommends the similar alliance guests to the users according to historical preference information of the users;
the building module (3) is associated with the information insights module (2), and the building module (3) is used for the management of the receiving and sending operation and the communication record of the information of the user such as mails, station internal letters and the like;
after the multi-platform management module (4) is authorized, importing a plurality of alliance platform data of a user, and after data processing, displaying distribution data in the plurality of alliance platforms of the user through one-stop management of the multi-platform management module (4);
the transaction system module (5) is used for attracting brand merchants and distribution channel occupancy, bidirectional invitation management, cooperation management, order management and commission settlement.
2. The innovative alliance distribution cooperation transaction platform for converging various distribution channel alliance resources as claimed in claim 1, wherein the database (1) is used for cleaning, intelligently identifying and storing the basic data, and specifically comprises:
inputting a brand name to search in the database (1) to obtain a return link;
performing keyword matching on all returned links, judging that the link belongs to the alliance resource after successful matching, and otherwise judging that the link does not belong to the alliance resource;
if the matching is successful, continuously analyzing the corresponding data indexes of the successfully matched links;
meanwhile, the input links are trained by using algorithm models such as a back propagation neural network, the dependent variables related to the brands are predicted according to the input independent variables, simulation training is carried out on the links by combining a brand knowledge graph, and finally, brand names are output from massive links to provide keywords for next data retrieval.
3. The innovative alliance distribution cooperation transaction platform for converging various distribution channel alliance resources as claimed in claim 2, wherein the link successfully matched is continuously analyzed for corresponding data indexes, specifically:
cleaning and identifying the data in the link through an intelligent algorithm to form a subdivision database base;
performing feature extraction on data in the subdivision database base from four dimensions of basic features, statistical features, complex features and natural features;
and retrieving and matching the data in the subdivision database base based on the knowledge graph, checking the accuracy of the data, and outputting an optimal result.
4. The innovative alliance distribution cooperation transaction platform for converging various distribution channel alliance resources as claimed in claim 1, wherein the information of each alliance guest in the database is collected, according to user clicking, checking and preference information of the alliance guests, similarity among the users is found through a recommendation algorithm, and according to historical preference information of the users, the similar alliance guests are recommended to the users, and the specific scheme is as follows:
acquiring interactive data of the user by collecting historical behaviors of the user, learning and calculating preference interest of the user according to the extracted features, calculating similarity between the user and the content to be recommended on the basis, and finally sequencing and sorting the similarity so as to recommend the alliance distribution resources which are most matched with the user;
setting a scoring rule aiming at the ordering of the different types of the distribution resources, scoring according to indexes of the distribution resources with different dimensions, and calculating an average score standard deviation to optimize the accuracy of the scoring rule, so that the distribution resources are ordered according to the final score;
the method comprises the steps of processing and extracting characteristics of mass data by using a multilayer perceptron, a convolutional neural network, a cyclic neural network, a recursion neural network and the like, and forming denser high-level semantic abstraction by combining low-level characteristics, so that multi-dimensional characteristic representation of the data is automatically found, and the recommendation effect is continuously enhanced.
5. The innovative federation distribution collaboration transaction platform for aggregating multiple distribution channel federation resources of claim 2, wherein the data indicators comprise: industry, brand, commission ratio, EPC, cookies, league guest detail information;
the detail information of the alliance clients comprises the following information: name, country/region, avatar, category, league guest type, co-branding, league platform, pickup commodity, and personal home page information.
6. The innovative federation distribution collaboration transaction platform for aggregating multiple distribution channel federation resources of claim 1, wherein the intelligence insights module (2) wherein the federation guest information comprises: name, country/region, avatar, category, league guest type, co-branding, league platform, pickup commodity, and personal home page information.
7. The innovative alliance distribution cooperation transaction platform for converging various distribution channel alliance resources as claimed in claim 1, wherein the multi-platform management module (4) is authorized to import a plurality of alliance platform data of a user, and after data processing, displays the distribution data in the plurality of alliance platforms of the user through one-stop management of the multi-platform management module (4), and specifically comprises:
a user inputs 'merchant member ID' and 'API key' to obtain authorization in an authorization center of a multi-platform management module (4), data of a alliance platform are imported into a background database through an API interface, the data are processed according to a comprehensive billboard, an alliance guest detail page, an order detail page and a repeated order detail page, and distribution data are checked through one-stop management.
8. The innovative alliance distribution cooperative trading platform for converging various distribution channel alliance resources as claimed in claim 1 wherein the multi-platform management module (4) further has a cheating order discrimination function, specifically:
unifying time zones and date dimensions of the alliance platforms needing to be compared;
downloading data tables in a plurality of alliance platforms, wherein the data tables at least cover the following indexes: order number, date, alliance guest ID, promotion website, alliance name and distribution amount, wherein the order number, date, alliance guest ID, promotion website, alliance name and distribution amount are judged to be a cheating order when the conditions include but are not limited to the following conditions;
1) If different alliance platforms have the same order number and the same distribution amount on the same day, the different alliance platforms judge that the order is a cheating order;
2) Code is covertly planted into a computer by unintentionally clicking a popup window, an advertisement program or downloaded virus/spyware, thereby cheating commission settlement;
3) Order tracking of alliance marketing is realized through Cookie local to a user computer, and abnormal tracking and settlement can be caused by illegal Cookie implantation;
4) By setting a domain name very similar to a brand website, after clicking cheating, the domain name is automatically redirected to jump to a real brand website, and the clicking cheated by the domain name can be tracked by Cookie and counted to be a conversion click.
9. The innovative alliance distribution cooperative transaction platform for converging various distribution channel alliance resources according to claim 1, wherein the transaction system module (5) is composed of a brand end and a channel end, and is used for attracting brand merchants and distribution channel residency, invitation of both parties, cooperative management and commission settlement, and specifically comprises:
the brand merchant registration login platform is used for achieving distribution cooperation with a channel by going to a Marketplace to search for the channel or applying for an approval channel in an approval center after merchant information, project information and payment information are set;
the distribution channel registers a login platform, after personal information and payment information are set, the platform goes to markplace to find brand merchants to achieve cooperation, and after approval is passed, popularization resources are obtained to carry out distribution;
the transaction system module (5) checks the application qualification of the brand merchants and the distribution channels, and the brand merchants and the distribution channels can successfully reside according with the standard so as to ensure the quality of the resident brand merchants and the distribution channels;
the brand merchant and the distribution channel issue invitation tasks in the trading system module (5), indexes such as product information and corresponding commission are provided, the distribution channel can also issue the brand invitation tasks, requirements for promoting products and information such as intention cooperation industry and brands are provided, both parties can select proper invitation tasks to cooperate, meanwhile, the trading system recommends tasks with high matching degree aiming at both parties according to data such as historical preference use habits and historical cooperation records of both parties based on a recommendation algorithm, and efficient cooperation of both parties is facilitated;
the trading system module (5) can analyze the delivery effect of the distribution channel and feed back the delivery effect to the brand merchants and the distribution channel, and the two parties can settle commissions according to the promotion effect and the rules of task release.
10. The innovative alliance distribution cooperation transaction platform for converging various distribution channel alliance resources, as claimed in claim 1, wherein the transaction system provides a unique tracking code after the brand merchants and the distribution channels are confirmed to cooperate, the distribution channels add the tracking code on the information of the promoted products, consumers click or purchase the products promoted in a certain distribution channel, the platform performs tracking analysis on the effects of the promoted products and the distribution channels, after the orders are completed, the transaction system automatically calculates commission amount, and after the expiration of the settlement validity period, commissions are regularly settled to the distribution channels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310017909.7A CN115809926A (en) | 2023-01-06 | 2023-01-06 | Innovative alliance distribution cooperation transaction platform for converging alliance resources of multiple distribution channels |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310017909.7A CN115809926A (en) | 2023-01-06 | 2023-01-06 | Innovative alliance distribution cooperation transaction platform for converging alliance resources of multiple distribution channels |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115809926A true CN115809926A (en) | 2023-03-17 |
Family
ID=85487248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310017909.7A Pending CN115809926A (en) | 2023-01-06 | 2023-01-06 | Innovative alliance distribution cooperation transaction platform for converging alliance resources of multiple distribution channels |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115809926A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116028720A (en) * | 2023-03-30 | 2023-04-28 | 无锡五车人工智能科技有限公司 | Target resource processing method, system and storage medium based on artificial intelligence |
| CN116308683A (en) * | 2023-05-17 | 2023-06-23 | 武汉纺织大学 | Knowledge-graph-based clothing brand positioning recommendation method, equipment and storage medium |
| CN116911505A (en) * | 2023-07-24 | 2023-10-20 | 深圳千亚国际供应链科技有限公司 | Product distribution management method and system based on cross-border e-commerce platform |
| CN117236992A (en) * | 2023-11-15 | 2023-12-15 | 北京头条易科技有限公司 | Cross-platform general E-commerce conversion monitoring system and method |
-
2023
- 2023-01-06 CN CN202310017909.7A patent/CN115809926A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116028720A (en) * | 2023-03-30 | 2023-04-28 | 无锡五车人工智能科技有限公司 | Target resource processing method, system and storage medium based on artificial intelligence |
| CN116308683A (en) * | 2023-05-17 | 2023-06-23 | 武汉纺织大学 | Knowledge-graph-based clothing brand positioning recommendation method, equipment and storage medium |
| CN116911505A (en) * | 2023-07-24 | 2023-10-20 | 深圳千亚国际供应链科技有限公司 | Product distribution management method and system based on cross-border e-commerce platform |
| CN117236992A (en) * | 2023-11-15 | 2023-12-15 | 北京头条易科技有限公司 | Cross-platform general E-commerce conversion monitoring system and method |
| CN117236992B (en) * | 2023-11-15 | 2024-02-06 | 北京头条易科技有限公司 | Cross-platform general E-commerce conversion monitoring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10885561B2 (en) | Transaction facilitating marketplace platform | |
| US20230214941A1 (en) | Social Match Platform Apparatuses, Methods and Systems | |
| Linoff et al. | Data mining techniques: for marketing, sales, and customer relationship management | |
| Schaer et al. | Demand forecasting with user-generated online information | |
| Kudyba et al. | Data mining and business intelligence: A guide to productivity | |
| Bari et al. | Predictive analytics for dummies | |
| Kotler et al. | Marketing moves: a new approach to profits, growth, and renewal | |
| CN115809926A (en) | Innovative alliance distribution cooperation transaction platform for converging alliance resources of multiple distribution channels | |
| Mahajan et al. | New product diffusion models in marketing: A review and directions for research | |
| Magnini et al. | Data mining for hotel firms: Use and limitations | |
| Bose et al. | Quantitative models for direct marketing: A review from systems perspective | |
| US20140258032A1 (en) | Transaction facilitating marketplace platform | |
| CN106062743A (en) | Systems and methods for keyword suggestion | |
| CN106469392A (en) | Select and recommend to show the method and device of object | |
| CN113516496A (en) | Advertisement conversion rate pre-estimation model construction method, device, equipment and medium thereof | |
| CN115860870A (en) | Commodity recommendation method, system and device and readable medium | |
| CN115760202A (en) | Product operation management system and method based on artificial intelligence | |
| Anusha et al. | Segmentation of retail mobile market using HMS algorithm | |
| Aldana | Data mining industry: emerging trends and new opportunities | |
| CN110020917A (en) | A kind of on line financing Products Show method based on collaborative filtering | |
| Titiyal et al. | E-fulfillment across product type: a review of literature (2000–2020) | |
| Jarrah et al. | Building a conceptual model for E-CRM implementation strategy | |
| Iqbal | Machine learning applications in e-commerce | |
| Yang et al. | Marketing Strategy on Social Commerce Based upon Marketing Mix | |
| Moorthi et al. | Improving business process by predicting customer needs based on seasonal analysis: the role of big data in e-commerce |
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 |