CN115983950A - Commodity information recommendation method, device and medium for electronic mall - Google Patents
Commodity information recommendation method, device and medium for electronic mall Download PDFInfo
- Publication number
- CN115983950A CN115983950A CN202310262071.8A CN202310262071A CN115983950A CN 115983950 A CN115983950 A CN 115983950A CN 202310262071 A CN202310262071 A CN 202310262071A CN 115983950 A CN115983950 A CN 115983950A
- Authority
- CN
- China
- Prior art keywords
- user
- commodities
- commodity
- node
- crawler
- 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
- 238000000034 method Methods 0.000 title claims abstract description 136
- 238000001914 filtration Methods 0.000 claims description 22
- 230000009193 crawling Effects 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000004220 aggregation Methods 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002688 persistence Effects 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a commodity information recommendation method, a device and a medium for an electronic mall, which are characterized in that a crawler system is utilized to collect commodity information of various large e-commerce websites, and the commodity information of the electronic mall is combined to form a set of commodity data system in a regular manner; and then recommending commodity information based on the commodity data system. The data adopted in the commodity recommendation process comprises the commodity information of the electronic shopping mall where the user logs in and also comprises the commodity information of other electronic shopping malls, so that the commodity recommendation method can meet the requirements of the user and accurately recommend suitable commodities to the user; the electronic shopping mall visited by the user is called as the home electronic mall, and in the process of recommending commodities to the user based on the commodity data system, the defects of commodities in the home electronic mall can be conveniently known, and meanwhile, the user requirements can be accurately known, so that the parameters of the commodities can be upgraded according to the requirements of the user, the superiority and universality of the commodities in the home electronic mall are ensured, and the economic loss caused by the upgrading direction of the commodities is reduced.
Description
Technical Field
The invention relates to the field of data mining recommendation, in particular to a method and a device for recommending commodity information of an electronic mall and a computer-readable storage medium.
Background
With the development of science and the advancement of society, information technology becomes an indispensable part of modern production and life. Online shopping is becoming the mainstream shopping method for users to shop. Meanwhile, the e-commerce system also faces many challenges, so how to design an e-commerce website with complete functions, easy maintenance and strong expandability is an important research hotspot, and the e-commerce system has the following pain points:
(1) The information is various and disordered, and the commodities which are matched with the information are difficult to screen. With the development of electronic commerce, the variety and quantity of commodities are more and more abundant, consumers need to spend a great deal of time and energy to find interesting commodities in a great quantity of commodities; and like products are full of the Lin Lang, various parameters need to be consulted and compared by a user, and the user can not select commodities suitable for the user from the like products.
(2) The disadvantage of large price fluctuation exists in online shopping, and the phenomenon of expensive shopping is often caused by less price solved by a plurality of people, so that the online shopping is not favorable for quick and effective online shopping.
(3) The online shopping has the defect that the same articles of different sellers frequently appear, the aim of efficiently screening the heart instrument products cannot be achieved, and the time and the labor are wasted.
Therefore, a mall product information comparison system capable of solving the problems of information overload and information loss is also an indispensable part of electronic commerce.
Most of the current commodity recommendation methods only recommend commodity information of an electronic shopping mall visited by a user, and commodity information recommendation of the whole network cannot be realized. Moreover, the recommendation method cannot perform comparative analysis from multiple dimensions of the commodity, and cannot accurately recommend the commodity meeting the requirements for the user.
Disclosure of Invention
In view of the problems in the prior art, an object of the present invention is to provide a method and an apparatus for recommending commodity information in an electronic mall, and a computer-readable storage medium, wherein a crawler system collects commodity information of each large electronic mall in the whole network to form a commodity data system, and accurately recommends commodities meeting requirements for a user based on the commodity data system.
In order to realize the purpose, the invention adopts the technical scheme that:
a goods information recommending method of an electronic mall comprises the steps of firstly, utilizing a crawler system to collect goods information of each large electronic mall in a whole network, and combining the goods information with the goods information of the electronic mall visited by a user to form a goods data system; then recommending commodity information based on the commodity data system;
the crawler system defines a crawler process and process scheduling in an imaging mode; the commodity information recommendation generates user preferences through the collection of user behaviors, so that recommendation based on user and article collaborative filtering is performed in different scenes, and a recommendation result is displayed.
The crawler system comprises a crawler scheduler, a flow engine, a downloader, a page resolver and an output pipeline; the crawler scheduler is used for managing the crawler flow to be executed and uniformly scheduling and executing; the process engine is used for providing a graphic self-defined crawler process configuration function and executing the graphic self-defined crawler process according to a preset crawler process under the triggering of the crawler scheduler; the downloader is responsible for downloading pages from all large electronic mall websites in the whole network; the page analyzer is used for analyzing pages, extracting commodity information and finding new links; the output pipeline is used for outputting the analyzed content to a file or a database;
the crawler process comprises configuration nodes, a crawler process node and a crawler process node, wherein the configuration nodes comprise a starting node, a crawling node, a definition variable node, an output node, a circulation node and a waiting ending node; when a crawler process is configured by using a process engine, the crawler process at least comprises a starting node, a definition variable node, a crawling node and an output node;
when a crawler scheduler triggers a start node of a configured crawler process, a variable node, a loop node and a waiting end node are defined to be executed in a process engine, a crawling node triggers an execution of a downloader, an output node triggers an execution of a page parser and an output pipeline, and the downloader, the page parser and the output pipeline are limited by the variable node, the loop node and the waiting end node during the execution.
The commodity information recommendation specifically comprises the following steps: acquiring user information, judging the user information, and adopting a recommendation process in a tourist scene for unregistered or registered but unregistered users, namely a recommendation process based on commodity information recommendation ranking;
for users with login times less than a set value, adopting a recommendation process under a new user scene, namely a recommendation process based on personal information of the users;
for users with the login times reaching a set value or more, adopting a recommendation process under an old user scene, namely user-based collaborative filtering recommendation;
after a user adds commodities into a shopping cart, adopting a collaborative filtering recommendation process based on the commodities of the shopping cart;
and after the user places an order for the commodity, recommending the flow based on the commodity collected by the user.
In a tourist scene, recommending commodities for a user based on a recommendation flow of commodity information recommendation ranking, and presenting the recommended commodities to the user on a shopping cart page;
specifically, recommending by taking commodity sales as a standard, and sorting the commodity table according to sales descending to obtain the top M recommendations to the user; or recommending by taking the good evaluation number as a standard, and sorting the commodity table in a descending manner according to the good evaluation number to obtain the top M recommendations to the user; or, with the collection number as a standard, the commodity table is sorted in a descending manner according to the collection number, and the top M recommendations are obtained and are sent to the user; or, with the search quantity as a standard, the commodity table is sorted in a descending manner according to the collection number, and the top M recommendations are obtained and are provided for the user.
Under a new user scene, recommending commodities for a user according to personal information of the user, and presenting the recommended commodities to the user on a shopping cart page; the method comprises the following specific steps:
acquiring the age, gender, city and occupation of a recommended user, inquiring favorite commodities of a user group with the same age as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group with the same gender as the recommended user and recording the number of people each commodity likes;
inquiring favorite commodities of a user group in the same city as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group with the same occupation as the recommended user and recording the number of people each commodity is liked;
summarizing hot commodities with four dimensions, sorting the hot commodities in a descending manner according to the number of people liked, and taking out the top M commodities to recommend to a user.
Under the old user scene, recommending commodities for the user according to the collaborative filtering of the user, and presenting the recommended commodities to the user on the shopping cart page; the method comprises the following specific steps:
after the user successfully logs in, acquiring a favorite commodity collection K1 of the user, and when the favorite number of the user is not 0, grouping the users according to the age, the gender and the user grade of the user;
acquiring a user favorite commodity collection { K2, K3 … Kn } in a family of a user group;
calculating the similarity between the collection K1 and the collection { K2, K3 … Kn }, acquiring commodities with the similarity not being 0, and directly recommending the commodities to a user when the quantity of the commodities with the similarity not being 0 is not more than M; when the number of the commodities with the similarity not being 0 is larger than M, obtaining M commodities with the maximum similarity;
and deleting the commodities which are not in the love of the user from the M commodities, and recommending the commodities to the user.
After the user adds the commodities into the shopping cart, recommending the commodities for the user based on the collaborative filtering of the commodities in the shopping cart of the user, and presenting the recommended commodities to the user on the page of the shopping cart. The method comprises the following specific steps:
entering a user shopping cart, finding out favorite users of each commodity of the shopping cart and counting the number of people;
finding out favorite users of the commodities except the shopping cart commodities, counting the number of people, and calculating the number of people favorite of each shopping cart commodity and other commodities together;
sorting according to the number of people sharing the favorite people;
when the quantity of the commodities which are commonly loved is not more than M, directly recommending the commodities to the user; and when the quantity of the commodities loved together is more than M, acquiring the commodities with M ranks before and recommending the commodities to the user.
After the user places an order, recommending the user according to the commodities collected by the user, and presenting the recommended commodities to the user on an order generation page; the method comprises the following specific steps:
after the user places an order, order information is generated;
acquiring commodity information collected by a user;
finding out a commodity set of the same type as the collected commodities;
sorting each set in a descending manner according to the number of good scores;
and recommending the top M commodities of each set to the user.
A commodity information recommending device of an electronic mall is used for realizing the commodity information recommending method, and comprises a crawler system, a commodity data system and a commodity information recommending system, wherein the crawler system is used for collecting commodity information of all large and electronic mall websites in the whole network; the commodity data system is used for storing commodity information collected by the crawler system and commodity information of an electronic mall visited by a user; and the commodity information recommendation system carries out commodity information recommendation to the user according to the commodity information in the commodity data system.
A computer-readable storage medium, characterized in that: the computer readable storage medium has stored therein instructions that, when run on a terminal device, cause the terminal device to execute the goods information recommendation method as described above.
After the scheme is adopted, the data adopted in the commodity recommendation process comprises the commodity information of the electronic shopping mall where the user logs in and also comprises the commodity information of other electronic shopping malls, so that the commodity recommendation method can meet the requirements of the user and accurately recommend suitable commodities to the user; the electronic shopping mall visited by the user is called as the home electronic mall, and in the process of recommending commodities to the user based on the commodity data system, the defects of commodities in the home electronic mall can be conveniently known, and meanwhile, the user requirements can be accurately known, so that the parameters of the commodities can be upgraded according to the requirements of the user, the superiority and universality of the commodities in the home electronic mall are ensured, and the economic loss caused by the upgrading direction of the commodities is reduced.
In addition, when the commodity information of other electronic shopping malls is obtained, the type of the crawled data can be flexibly changed according to the scene by using the self-defined crawler system, and the development and maintenance cost of the system is reduced.
Drawings
FIG. 1 is a functional block diagram of a crawler system;
FIG. 2 is a first configuration embodiment of a crawler system;
FIG. 3 is a second configuration embodiment of the crawler system;
FIG. 4 is an overall flow diagram of product recommendation;
FIG. 5 is a flowchart of a recommendation process based on a merchandise news;
FIG. 6 is a flow chart of recommendation based on user profile information;
FIG. 7 is a recommendation flow diagram for user-based collaborative filtering;
FIG. 8 is a flow diagram of a collaborative filtering recommendation based on shopping cart items;
FIG. 9 is a flow chart illustrating a recommendation based on a user's favorite merchandise.
Detailed description of the preferred embodiments
The invention discloses a commodity information recommendation method for an electronic mall, which comprises the steps of firstly, utilizing a crawler system to collect commodity information of each large electronic mall in the whole network, and storing the commodity information and the commodity information of the electronic mall visited by a user together to form a commodity data system; and then recommending commodity information based on the commodity data system, wherein the user can be a registered user of each large electronic mall of the whole network or not.
The commodity information stored in the commodity data system specifically comprises commodity specification parameters, commodity prices, commodity comments and user information, wherein the user information is basic information of commodity commentators.
As shown in fig. 1, in the embodiment, the crawler system defines a crawler flow and a flow schedule in an imaging manner, and a new crawler can be implemented without code when the crawler flow is changed. The crawler system comprises a crawler scheduler, a flow engine, a downloader, a page resolver and an output pipeline; these modules correspond to the functions of scheduling management, self-defining flow, downloading, processing, persistence and the like in the life cycle of the crawler. Specifically, the crawler scheduler is configured to manage a crawler flow to be executed, and uniformly schedule and execute the crawler flow. The process engine is used for providing a graphical user-defined crawler process configuration function and executing the crawler process according to a preset crawler process under the triggering of the crawler scheduler. The downloader is responsible for downloading pages from all large e-mall websites on the whole network. In this embodiment Jsoup is used as a download tool. The page analyzer is used for analyzing the page, extracting commodity information and finding a new link. This embodiment uses Jsoup as an HTML parsing tool and develops a tool Xsoup for parsing XPath based thereon. The output pipeline is used for outputting the analyzed content to a file or a database. In this embodiment, two result processing schemes, "save to database" and "save to file" are provided. In the invention, the crawler system supports self-defined variables, functions and plug-ins to realize customized development.
The configuration nodes of the crawler process comprise a starting node, a crawling node, a definition variable node, an output node, a circulation node and a waiting ending node. When the crawler process is configured by using the process engine, the crawler process at least comprises a starting node, a definition variable node, a crawling node and an output node. When a crawler scheduler triggers a start node of a configured crawler process, a variable node, a loop node and a waiting end node are defined to execute in a process engine, a crawling node triggers an execution of a downloader, an output node triggers an execution of a page parser and an output pipeline, and the downloader, the page parser and the output pipeline are limited by the variable node, the loop node and the waiting end node during the execution.
When a developer crawls data by using the crawler system, different nodes can be configured according to scenes, so that different types of data are crawled. Fig. 2 and 3 show two embodiments of the crawler process of the present invention.
The crawler flow execution process shown in fig. 2 is: a- > B- > C- > D, but because the A node is a loop node, if the loop number of the A node is 3, the execution process at this time becomes A, A, A- > B, B, B- > C, C, C- > D, D and D (3A are executed together, but the sequence is not fixed, and the flow is directly to the next node every time the execution is finished, but 3A are not finished). In fig. 2, a is a loop node, B is a definition variable node, C is a crawler execution node, and D is an output node.
Since the nodes B, C and D can also be provided with loops, and if the node C is also provided with loops, the number of loops is 2, then the whole flow is executed by a, a- > B, B- > C, C, C, C, C- > D, D, D, D, D, D (i.e., nested loops are formed).
The applicable scenario of fig. 2 is that crawling of the same web page information needs to be performed circularly. If a Beijing Dong webpage is crawled, the A node sets the cycle number, the B node extracts a variable and transmits the variable to the next node, the C node executes the request webpage downloading and analyzing, and the D node outputs the analyzed content.
The crawler flow execution process shown in fig. 3 is: a- > B- > (C- > F), (D- > E) - > G- > H, namely the A node is executed firstly; when the node A finishes executing, executing the node B; when the node B finishes executing, the node B simultaneously executes the C, D node; when the C node is executed, executing the F node; when the D node finishes executing, executing the E node; E. when the F nodes are all executed, executing the G nodes (the G nodes are waiting for ending nodes, so the G nodes wait for E, F to end, otherwise, the G nodes are executed no matter which node E, F is executed completely); executing the H node when the G node is executed; and when the H node finishes executing, ending the process.
Since the C node is a loop node, if the loop number of the C node is 3, the upper part becomes C, C, C- > F, F, F- > G- > H from the C node.
In fig. 3, a is a definition variable node, B, D is a crawler execution node, C is a loop node, E, F, H is an output node, and G is a wait node.
Applicable scenario of fig. 3: a plurality of page information needs to be crawled simultaneously, and the crawling of the pages is in sequence.
The B node extracts variables and transmits the variables to the next node, the C node executes the request webpage downloading and analyzing, simultaneously executes C, D nodes, the C node sets a loop, the D node continues to crawl the next webpage information, the E, F node outputs the content result crawled by C, D, the process continues to walk the next node G until E, F is executed, and finally the content is summarized and output.
As shown in fig. 4, the product information recommendation generates user preferences by collecting user behaviors, thereby performing recommendation based on collaborative filtering of a user and an article in different scenes, and also performing recommendation based on user personal information and product information to a user. And calling different parameters to recommend according to different scenes, and displaying a recommendation result in a corresponding page.
The recommended process specifically comprises the following steps: acquiring user information, judging the user information, and adopting a recommendation process in a tourist scene for unregistered or registered but unregistered users, namely a recommendation process based on commodity information recommendation ranking;
for users with login times less than a set value, adopting a recommendation process under a new user scene, namely a recommendation process based on personal information of the users;
for users with login times reaching a set value (for example, 40 times) or more, adopting a recommendation process under an old user scene, namely collaborative filtering recommendation based on the users;
after a user adds commodities into a shopping cart, adopting a collaborative filtering recommendation process based on the commodities in the shopping cart;
and after the user places an order for the commodity, recommending the flow based on the commodity collected by the user.
As shown in fig. 5, in a tourist scenario, a recommendation process based on the commodity information recommendation ranking recommends commodities for a user, and presents the recommended commodities to the user on a shopping cart page. Specifically, recommending by taking commodity sales as a standard, and sorting the commodity table according to sales descending to obtain the top M recommendations to the user; or recommending by taking the good evaluation number as a standard, and sorting the commodity table in a descending manner according to the good evaluation number to obtain the top M recommendations to the user; or, with the collection number as a standard, the commodity table is sorted in a descending manner according to the collection number, and the top M recommendations are obtained and are sent to the user; or, with the search quantity as a standard, the commodity table is sorted in a descending manner according to the collection number, and the top M recommendations are obtained and are provided for the user.
As shown in fig. 6, in a new user scenario, a commodity is recommended for a user according to user personal information, and the recommended commodity is presented to the user on a shopping cart page. The method comprises the following specific steps:
acquiring personal information of the recommended users such as age, sex, city and occupation, inquiring favorite commodities of user groups at the same age as the recommended users, and recording the number of people each commodity likes;
inquiring favorite commodities of a user group with the same gender as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group in the same city as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group with the same occupation as the recommended user and recording the number of people each commodity is liked;
summarizing hot commodities with four dimensions, sorting the hot commodities in a descending manner according to the number of people liked, and taking out the top M commodities to recommend to a user.
As shown in fig. 7, in an old user scenario, a commodity is recommended for a user according to collaborative filtering of the user, and the recommended commodity is presented to the user on a shopping cart page. The method comprises the following specific steps:
after the user successfully logs in, acquiring a favorite commodity collection K1 of the user, and when the favorite number of the user is not 0, grouping the users according to the age, the gender and the user grade of the user;
acquiring a user favorite commodity collection { K2, K3 … Kn } in a family of a user group;
calculating the similarity between the collection K1 and the collection { K2, K3 … Kn }, acquiring commodities with the similarity not being 0, and directly recommending the commodities to a user when the quantity of the commodities with the similarity not being 0 is not more than M; when the number of the commodities with the similarity not being 0 is larger than M, obtaining M commodities with the maximum similarity;
and deleting the commodities which are not in the love of the user from the M commodities, and recommending the commodities to the user.
As shown in fig. 8, after the user adds the goods to the shopping cart, the goods are recommended for the user based on the collaborative filtering of the goods in the shopping cart of the user, and the recommended goods are presented to the user on the page of the shopping cart. The method comprises the following specific steps:
entering a user shopping cart, finding out favorite users of each commodity of the shopping cart and counting the number of people;
finding out favorite users of the goods except the shopping cart goods, counting the number of people, and calculating the number of people favorite in each shopping cart goods and other goods together;
sorting according to the number of people sharing the favorite people;
when the quantity of the commodities which are commonly loved is not more than M, directly recommending the commodities to the user; and when the quantity of the commodities loved together is more than M, acquiring the commodities with M ranks before and recommending the commodities to the user.
As shown in fig. 9, after the user places an order, the user is recommended according to the commodities collected by the user, and the recommended commodities are presented to the user on the order generation page. The method comprises the following specific steps:
after the user places an order, order information is generated;
acquiring commodity information collected by a user;
finding out a commodity set of the same type as the collected commodities;
sorting each set in a descending manner according to the number of good scores;
and recommending the top M commodities of each set to the user.
Based on the same invention concept, the invention also discloses a recommendation device for the commodity information of the electronic mall, which comprises a crawler system, a commodity data system and a commodity information recommendation system, wherein the crawler system is used for acquiring the commodity information of each large electronic mall website in the whole network; the commodity data system is used for storing commodity information acquired by the crawler system and commodity information of an electronic mall visited by a user; and the commodity information recommending system recommends the commodity information to the user according to the commodity information in the commodity data system.
Specifically, the crawler system defines a crawler process and a process schedule in an imaging mode, and a new crawler can be realized without codes when the crawler process is changed. As shown in FIG. 1, the crawler system comprises a crawler scheduler, a flow engine, a downloader, a page parser and an output pipeline; these modules correspond to the functions of scheduling management, self-defining flow, downloading, processing, persistence and the like in the life cycle of the crawler. Specifically, the crawler scheduler is configured to manage a crawler flow to be executed, and uniformly schedule and execute the crawler flow. The process engine is used for providing a graphical user-defined crawler process configuration function and executing the crawler process according to a preset crawler process under the triggering of the crawler scheduler. The downloader is responsible for downloading pages from all the large electronic mall websites in the whole network. In this embodiment, jsoup is used as a download tool. The page parser is used for parsing the page, extracting the commodity information and finding a new link. This embodiment uses Jsoup as an HTML parsing tool and develops a tool Xsoup for parsing XPath based thereon. And custom variables, functions and plug-ins are supported to realize customized development. The output pipeline is used for outputting the analyzed content to a file or a database. In this embodiment, two result processing schemes, "save to database" and "save to file" are provided.
The configuration nodes of the crawler process comprise a starting node, a crawling node, a definition variable node, an output node, a circulation node and a waiting ending node. When the crawler process is configured by using the process engine, the crawler process at least comprises a starting node, a definition variable node, a crawling node and an output node. When a crawler scheduler triggers a start node of a configured crawler process, a variable node, a loop node and a waiting end node are defined to execute in a process engine, a crawling node triggers an execution of a downloader, an output node triggers an execution of a page parser and an output pipeline, and the downloader, the page parser and the output pipeline are limited by the variable node, the loop node and the waiting end node during the execution.
When a developer crawls data by using the crawler system, different nodes can be configured according to scenes, so that different types of data are crawled.
The commodity data system is a database that stores data. The commodity information recommendation system generates user preferences by collecting user behaviors, thereby performing recommendation based on collaborative filtering of the user and the article in different scenes, and also performing recommendation based on personal information and commodity information of the user. And calling different parameters for recommendation according to different scenes, and displaying a recommendation result in a corresponding page.
As shown in fig. 4, the specific recommendation process of the product information recommendation system is as follows: acquiring user information, judging the user information, and adopting a recommendation process in a tourist scene for unregistered or registered but unregistered users, namely a recommendation process based on commodity information recommendation ranking;
for users with login times less than a set value, adopting a recommendation process under a new user scene, namely a recommendation process based on personal information of the users;
for users with login times reaching a set value or more, adopting a recommendation process under an old user scene, namely collaborative filtering recommendation based on users;
after a user adds commodities into a shopping cart, adopting a collaborative filtering recommendation process based on the commodities in the shopping cart;
and after the user places an order for the commodity, recommending the flow based on the commodity collected by the user.
As shown in fig. 5, in a tourist scenario, a recommendation process based on the commodity information recommendation ranking recommends commodities for a user, and presents the recommended commodities to the user on a shopping cart page. Specifically, recommending by taking commodity sales as a standard, and sequencing a commodity table in a descending manner according to sales to obtain top M recommendations to a user; or, recommending by taking the good evaluation number as a standard, and sequencing the commodity table in a descending manner according to the good evaluation number to obtain the top M recommendations to the user; or, with the collection number as a standard, the commodity table is sorted in a descending manner according to the collection number, and the top M recommendations are obtained and are sent to the user; or, with the search quantity as a standard, the commodity table is sorted in a descending manner according to the collection number, and the top M recommendations are obtained and are provided for the user.
As shown in fig. 6, in a new user scenario, a commodity is recommended for a user according to user personal information, and the recommended commodity is presented to the user on a shopping cart page. The method comprises the following specific steps:
acquiring personal information of the recommended user such as age, gender, city and occupation, inquiring favorite commodities of a user group with the same age as the recommended user, and recording the number of people each commodity likes;
inquiring favorite commodities of a user group with the same gender as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group in the same city as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group with the same occupation as the recommended user and recording the number of people each commodity is liked;
summarizing hot commodities with four dimensions, sorting the hot commodities in a descending manner according to the number of people liked, and taking out the top M commodities to recommend to a user.
As shown in fig. 7, in an old user scenario, goods are recommended for a user according to collaborative filtering of the user, and the recommended goods are presented to the user on a shopping cart page. The method comprises the following specific steps:
after the user successfully logs in, acquiring a favorite commodity collection K1 of the user, and when the favorite number of the user is not 0, grouping the users according to the age, the gender and the user grade of the user;
acquiring a user favorite commodity collection { K2, K3 … Kn } in a family of a user group;
calculating the similarity between the aggregation K1 and the aggregation { K2, K3 … Kn }, acquiring commodities with the similarity not being 0, and directly recommending the commodities to the user when the number of the commodities with the similarity not being 0 is not more than M; when the number of the commodities with the similarity not being 0 is larger than M, obtaining M commodities with the maximum similarity;
and deleting the commodities which are not in the love of the user from the M commodities, and recommending the commodities to the user.
As shown in fig. 8, after the user adds the goods to the shopping cart, the goods are recommended for the user based on the collaborative filtering of the goods in the shopping cart of the user, and the recommended goods are presented to the user on the page of the shopping cart. The method comprises the following specific steps:
entering a user shopping cart, finding out favorite users of each commodity of the shopping cart and counting the number of people;
finding out favorite users of the goods except the shopping cart goods, counting the number of people, and calculating the number of people favorite in each shopping cart goods and other goods together;
sorting according to the number of people sharing the favorite people;
when the quantity of the commodities which are commonly loved is not more than M, directly recommending the commodities to the user; and when the quantity of the commodities loved together is more than M, acquiring the commodities with M ranks before and recommending the commodities to the user.
As shown in fig. 9, after the user places an order, the user is recommended according to the commodities collected by the user, and the recommended commodities are presented to the user in the order generation page. The method comprises the following specific steps:
after the user places an order, order information is generated;
acquiring commodity information collected by a user;
finding out a commodity set of the same type as the collected commodities;
sorting each set in a descending manner according to the good scores;
and recommending the top M commodities of each set to the user.
The data adopted in the commodity recommendation process comprises the commodity information of the electronic shopping mall where the user logs in and also comprises the commodity information of other electronic shopping malls, so that the commodity recommendation method can meet the requirements of the user and accurately recommend suitable commodities to the user; the electronic shopping mall visited by the user is called as the home electronic mall, and in the process of recommending commodities to the user based on the commodity data system, the defects of commodities in the home electronic mall can be conveniently known, and meanwhile, the user requirements can be accurately known, so that the parameters of the commodities can be upgraded according to the requirements of the user, the superiority and universality of the commodities in the home electronic mall are ensured, and the economic loss caused by the upgrading direction of the commodities is reduced.
In addition, when the commodity data of other electronic malls are obtained, the type of the crawled data can be flexibly changed according to the scene by using the customized crawler system, and the development and maintenance cost of the system is reduced.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above should not be understood to necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Claims (10)
1. A commodity information recommendation method for an electronic mall is characterized by comprising the following steps: the method comprises the steps that firstly, a crawler system is used for collecting commodity information of each large electronic mall in the whole network, and the commodity information of the electronic mall visited by a user are stored together to form a commodity data system; then recommending commodity information based on the commodity data system;
the crawler system defines a crawler process and process scheduling in an imaging mode; the commodity information recommendation generates user preferences through the collection of user behaviors, so that recommendation based on user and article collaborative filtering is performed in different scenes, and a recommendation result is displayed.
2. The electronic mall commodity information recommendation method according to claim 1, wherein: the crawler system comprises a crawler scheduler, a flow engine, a downloader, a page parser and an output pipeline; the crawler scheduler is used for managing the crawler processes to be executed and uniformly scheduling and executing; the process engine is used for providing a graphical user-defined crawler process configuration function and executing the graphical user-defined crawler process according to a preset crawler process under the triggering of the crawler scheduler; the downloader is responsible for downloading pages from all large electronic mall websites in the whole network; the page analyzer is used for analyzing pages, extracting commodity information and finding new links; the output pipeline is used for outputting the analyzed content to a file or a database;
the crawler process comprises configuration nodes, a starting node, a crawling node, a definition variable node, an output node, a circulation node and a waiting ending node; when a crawler process is configured by using a process engine, the crawler process at least comprises a starting node, a definition variable node, a crawling node and an output node;
when a crawler scheduler triggers a start node of a configured crawler process, a variable node, a loop node and a waiting end node are defined to be executed in a process engine, a crawling node triggers an execution of a downloader, an output node triggers an execution of a page parser and an output pipeline, and the downloader, the page parser and the output pipeline are limited by the variable node, the loop node and the waiting end node during the execution.
3. The commodity information recommendation method for an electronic mall according to claim 1, wherein: the commodity information recommendation specifically comprises the following steps: acquiring user information, judging the user information, and adopting a recommendation process in a tourist scene for unregistered or registered but unregistered users, namely a recommendation process based on commodity information recommendation ranking;
for users with the login times less than the set value, adopting a recommendation process under a new user scene, namely a recommendation process based on the personal information of the users;
for users with login times reaching a set value or more, adopting a recommendation process under an old user scene, namely collaborative filtering recommendation based on users;
after a user adds commodities into a shopping cart, adopting a collaborative filtering recommendation process based on the commodities in the shopping cart;
and after the user places an order for the commodity, recommending the flow based on the commodity collected by the user.
4. The commodity information recommendation method for the electronic mall according to claim 3, wherein: in a tourist scene, recommending commodities for a user based on a recommendation flow of commodity information recommendation ranking, and presenting the recommended commodities to the user on a shopping cart page;
specifically, recommending by taking commodity sales as a standard, and sorting the commodity table according to sales descending to obtain the top M recommendations to the user; or, recommending by taking the good evaluation number as a standard, and sequencing the commodity table in a descending manner according to the good evaluation number to obtain the top M recommendations to the user; or, with the collection number as a standard, the commodity table is sorted in a descending manner according to the collection number, and the top M recommendations are obtained and are sent to the user; or, with the search quantity as a standard, the commodity table is sorted in a descending manner according to the collection number, and the top M recommendations are obtained and are provided for the user.
5. The commodity information recommendation method for the electronic mall according to claim 3, wherein: under a new user scene, recommending commodities for a user according to personal information of the user, and presenting the recommended commodities to the user on a shopping cart page; the method comprises the following specific steps:
acquiring the age, gender, city and occupation of a recommended user, inquiring favorite commodities of a user group with the same age as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group with the same gender as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group in the same city as the recommended user and recording the number of people each commodity is favorite;
inquiring favorite commodities of a user group with the same occupation as the recommended user and recording the number of people each commodity is liked;
summarizing hot commodities with four dimensions, sorting the hot commodities in a descending manner according to the number of people liked, and taking out the top M commodities to recommend to a user.
6. The commodity information recommendation method for an electronic mall according to claim 3, wherein: under the old user scene, recommending commodities for the user according to the collaborative filtering of the user, and presenting the recommended commodities to the user on the shopping cart page; the method comprises the following specific steps:
after the user successfully logs in, acquiring a favorite commodity collection K1 of the user, and when the favorite number of the user is not 0, grouping the users according to the age, the gender and the user grade of the user;
acquiring a user favorite commodity collection { K2, K3 … Kn } in a family of a user group;
calculating the similarity between the aggregation K1 and the aggregation { K2, K3 … Kn }, acquiring commodities with the similarity not being 0, and directly recommending the commodities to the user when the number of the commodities with the similarity not being 0 is not more than M; when the number of the commodities with the similarity not being 0 is larger than M, obtaining M commodities with the maximum similarity;
and deleting the commodities which are not loved by the user from the M commodities, and recommending the commodities to the user.
7. The commodity information recommendation method for the electronic mall according to claim 3, wherein: after the user adds the commodities into the shopping cart, recommending the commodities for the user based on the collaborative filtering of the commodities in the shopping cart of the user, and presenting the recommended commodities to the user on the page of the shopping cart. The method comprises the following specific steps:
entering a user shopping cart, finding favorite users of each commodity of the shopping cart, and counting the number of people;
finding out favorite users of the commodities except the shopping cart commodities, counting the number of people, and calculating the number of people favorite of each shopping cart commodity and other commodities together;
sorting according to the number of people sharing the favorite people;
when the quantity of the commodities which are commonly loved is not more than M, directly recommending the commodities to the user; and when the quantity of the commodities loved together is more than M, acquiring the commodities with M ranks before and recommending the commodities to the user.
8. The commodity information recommendation method for an electronic mall according to claim 3, wherein: after the user places an order, recommending the user according to the commodities collected by the user, and presenting the recommended commodities to the user on an order generation page; the method comprises the following specific steps:
after the user places an order, order information is generated;
acquiring commodity information collected by a user;
finding out a commodity set of the same type as the collected commodities;
sorting each set in a descending manner according to the number of good scores;
and recommending the top M commodities of each set to the user.
9. The utility model provides a commodity information recommendation device in electron shopping mall which characterized in that: the device is used for realizing the commodity information recommendation method according to any one of claims 1 to 8, and comprises a crawler system, a commodity data system and a commodity information recommendation system, wherein the crawler system is used for collecting commodity information of all large e-commerce websites of the whole network; the commodity data system is used for storing commodity information acquired by the crawler system and commodity information of an electronic mall visited by a user; and the commodity information recommendation system is used for recommending commodity information to the user according to the commodity information in the commodity data system.
10. A computer-readable storage medium characterized by: the computer-readable storage medium has stored therein instructions that, when executed on a terminal device, cause the terminal device to execute the goods information recommendation method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310262071.8A CN115983950B (en) | 2023-03-17 | 2023-03-17 | Commodity information recommendation method, device and medium for electronic mall |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310262071.8A CN115983950B (en) | 2023-03-17 | 2023-03-17 | Commodity information recommendation method, device and medium for electronic mall |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115983950A true CN115983950A (en) | 2023-04-18 |
CN115983950B CN115983950B (en) | 2023-10-27 |
Family
ID=85970840
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310262071.8A Active CN115983950B (en) | 2023-03-17 | 2023-03-17 | Commodity information recommendation method, device and medium for electronic mall |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115983950B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012003677A (en) * | 2010-06-21 | 2012-01-05 | Nippon Telegr & Teleph Corp <Ntt> | Commodity recommendation device, commodity recommendation method and commodity recommendation program |
CN102609860A (en) * | 2012-01-20 | 2012-07-25 | 彭立发 | Method and system suitable for categorizing and recommending e-commerce commodities and information |
CN108596705A (en) * | 2018-03-23 | 2018-09-28 | 郑州大学西亚斯国际学院 | A kind of commodity suitable for e-commerce recommend method and system with information classification |
CN110147475A (en) * | 2019-03-29 | 2019-08-20 | 汇通达网络股份有限公司 | A kind of network data acquisition system of distributed deployment |
CN114547419A (en) * | 2022-02-28 | 2022-05-27 | 同济大学 | Agricultural product electronic commerce big data intelligent acquisition and integration system based on multi-source isomerism |
-
2023
- 2023-03-17 CN CN202310262071.8A patent/CN115983950B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012003677A (en) * | 2010-06-21 | 2012-01-05 | Nippon Telegr & Teleph Corp <Ntt> | Commodity recommendation device, commodity recommendation method and commodity recommendation program |
CN102609860A (en) * | 2012-01-20 | 2012-07-25 | 彭立发 | Method and system suitable for categorizing and recommending e-commerce commodities and information |
CN108596705A (en) * | 2018-03-23 | 2018-09-28 | 郑州大学西亚斯国际学院 | A kind of commodity suitable for e-commerce recommend method and system with information classification |
CN110147475A (en) * | 2019-03-29 | 2019-08-20 | 汇通达网络股份有限公司 | A kind of network data acquisition system of distributed deployment |
CN114547419A (en) * | 2022-02-28 | 2022-05-27 | 同济大学 | Agricultural product electronic commerce big data intelligent acquisition and integration system based on multi-source isomerism |
Non-Patent Citations (1)
Title |
---|
王彤: "《数字媒体内容管理技术与实践》", pages: 71 - 72 * |
Also Published As
Publication number | Publication date |
---|---|
CN115983950B (en) | 2023-10-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108228873B (en) | Object recommendation and release content pushing method and device, storage medium and equipment | |
CN105718184A (en) | Data processing method and apparatus | |
US20180082350A1 (en) | Generating display information using a dynamically selected strategy | |
US8626602B2 (en) | Consumer shopping and purchase support system and marketplace | |
US20230214895A1 (en) | Methods and systems for product discovery in user generated content | |
US9727906B1 (en) | Generating item clusters based on aggregated search history data | |
US20200226168A1 (en) | Methods and systems for optimizing display of user content | |
US10984460B2 (en) | Medium, method and apparatus for native page generation | |
WO2013161105A1 (en) | Tag management device, tag management method, tag management program, and computer-readable recording medium for storing said program | |
US20200265491A1 (en) | Dynamic determination of data facets | |
JP2009193098A (en) | Information processor, information processing method, and program | |
US11568011B2 (en) | System and method for improved searching across multiple databases | |
CN110990695A (en) | Recommendation system content recall method and device | |
CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
US8150878B1 (en) | Device method and computer program product for sharing web feeds | |
JP5249415B2 (en) | Method and apparatus for providing data statistics | |
KR20220001616A (en) | Method, Apparatus and System for Constructing Bigdata Based on Generating United Identifier of Customer | |
KR20160117678A (en) | Product registration and recommendation method in curation commerce | |
US11410418B2 (en) | Methods and systems for tagged image generation | |
KR20220081807A (en) | Shopping mall system and method for recommendation goods | |
KR20220001618A (en) | Method, Apparatus and System for Recommendation in Groups Using Bigdata | |
CN115983950B (en) | Commodity information recommendation method, device and medium for electronic mall | |
JP6698041B2 (en) | Information processing apparatus, method and program | |
KR101655368B1 (en) | Method and system to search and provide shopping postscript | |
JP2001229171A (en) | Article retrieval system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |